CN113487361A - Method, device, equipment and storage medium for predicting platform user value - Google Patents
Method, device, equipment and storage medium for predicting platform user value Download PDFInfo
- Publication number
- CN113487361A CN113487361A CN202110791170.6A CN202110791170A CN113487361A CN 113487361 A CN113487361 A CN 113487361A CN 202110791170 A CN202110791170 A CN 202110791170A CN 113487361 A CN113487361 A CN 113487361A
- Authority
- CN
- China
- Prior art keywords
- platform
- user
- new user
- target
- target new
- 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 54
- 238000012549 training Methods 0.000 claims description 38
- 238000012360 testing method Methods 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 238000013475 authorization Methods 0.000 description 14
- 230000006399 behavior Effects 0.000 description 11
- 238000012790 confirmation Methods 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for predicting platform user value. The method comprises the following steps: when a target new user of the platform is detected, acquiring characteristic data of the target new user; inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform; the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration. The embodiment of the invention can aim at the new user of the network service platform, namely the new user who has not generated historical behavior data when the network service platform is registered for the first time, and quickly and accurately aim at the value of the new user to the network service platform according to the characteristic data of the new user.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a method, a device, equipment and a storage medium for predicting platform user value.
Background
With the development of the internet, different kinds of network service platforms have been advanced into various aspects of daily life, such as live broadcast platforms, social contact platforms, shopping platforms, and the like. Prediction and measurement of platform user value are always important concerns of network service platforms.
In the related art, the network service platform usually bases on historical behavior data of a platform user on the network service platform, and needs to predict the value of the platform user for the network service platform after collecting the behavior data of the platform user for a long time. For a new user of the network service platform, namely a new user who has not generated historical behavior data when the network service platform is registered for the first time, the value of the new user of the network service platform for the network service platform cannot be predicted by a platform user value prediction mode in the related technology.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting the value of a platform user, which can predict the value of a new user of a network service platform for the network service platform.
In a first aspect, an embodiment of the present invention provides a method for predicting a platform user value, including:
when a target new user of a platform is detected, collecting characteristic data of the target new user;
inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform;
the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
In a second aspect, an embodiment of the present invention further provides a device for predicting a platform user value, where the device includes:
the system comprises a characteristic data acquisition module, a characteristic data acquisition module and a characteristic data acquisition module, wherein the characteristic data acquisition module is used for acquiring characteristic data of a target new user when the target new user of a platform is detected;
the user value prediction module is used for inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform;
the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for predicting a platform user value according to the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for predicting a platform user value according to the embodiment of the present invention.
According to the technical scheme, when the target new user of the platform is detected, the feature data of the target new user is collected, then the feature data of the target new user is input into the pre-trained user value prediction model, the user value of the target new user for each preset category in the platform is obtained, the value of the target new user for the network service platform can be rapidly and accurately predicted according to the feature data of the target new user after the target new user registers the network service platform, the new user for the network service platform, namely the new user which does not generate historical behavior data and is registered for the first time on the network service platform, and the value of the new user for the network service platform is rapidly and accurately obtained according to the feature data of the new user.
Drawings
Fig. 1 is a flowchart of a method for predicting a platform user value according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for predicting a platform user value according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a device for predicting a platform user value according to a third embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a method for predicting a platform user value according to an embodiment of the present invention. The embodiment of the invention can be suitable for predicting the value of the new user of the network service platform aiming at the network service platform by registering the new user of the network service platform for the first time, namely the new user which does not generate historical behavior data, and the method can be executed by the device for predicting the value of the platform user provided by the embodiment of the invention, and the device can be realized by adopting a software and/or hardware mode and can be generally integrated in computer equipment. Such as a server. As shown in fig. 1, the method of the embodiment of the present invention specifically includes:
Optionally, the target new user is one or more new users who have not generated historical behavior data by the first registration of the web service platform. The server can detect whether the user is a target new user of the platform according to the registration information and the historical behavior data of the user in the platform. The network service platform includes but is not limited to a live platform, a social platform, a shopping platform and the like. The characteristic data is data which does not relate to the historical behaviors of the user on the network service platform and is related to natural attributes carried by the user.
Optionally, the characteristic data may include: the method comprises the following steps of installing channel information of a platform application program client on a user terminal device, interest preference selected by the user when the platform application program client is in cold start, the type of the user terminal device, other application program types installed on the user terminal device, a system of the user terminal device, an Internet Protocol (IP) Address of the user, the city where the user is located, the age of the user, the sex of the user, the occupation of the user, the academic history of the user, game preference of the user and/or application program preference of the user and the like, wherein the data do not relate to historical behaviors of the user on a network service platform and are related to natural attributes carried by the user.
Optionally, the installation channel information is information indicating an installation source of the platform application client. The installation channel information may include: preinstalled in the terminal device, downloaded through an application store, and downloaded through information recommendation. The interest preferences selected by the user at the cold start of the platform application client are one or more of the interest preferences selected by the user in an interest preferences settings page provided by the platform application client at the first start of the platform application client.
Optionally, the acquiring the feature data of the target new user includes: sending data permission query information to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the data permission query information to the target new user through a query information display page; the data authority inquiry information is inquiry information used for inquiring whether the target new user grants the acquisition authority of the feature data of the target new user for the platform or not; and acquiring the characteristic data of the target new user through the platform application program client when the target new user is confirmed to grant the acquisition right of the characteristic data of the target new user for the platform according to the interactive operation of the target new user and the inquiry information display page.
Optionally, the server sends data permission query information to the platform application client installed in the terminal device of the target new user. And when the platform application program client receives the data permission inquiry information, displaying an inquiry information display page containing the data permission inquiry information, and displaying the data permission inquiry information to the target new user through the inquiry information display page. The query information presentation page is a page for presenting query information to the user.
Optionally, a confirmation authorization control and a denial authorization control are set in the inquiry information display page. The target new user can confirm that the acquisition permission of the feature data of the target new user is granted to the platform by clicking the confirmation authorization control. The target new user can also confirm that the acquisition permission of the feature data of the target new user is not granted to the platform by clicking the authorization rejection control.
Optionally, the platform application client generates an authorization confirmation prompt message and sends the authorization confirmation prompt message to the server when the target new user clicks the confirmation authorization control. The authorization confirmation prompt message is used for prompting the server that the target new user confirms that the platform grants the acquisition authority of the feature data of the target new user. And when receiving the authorization confirmation prompt message, the server confirms that the target new user grants the acquisition permission of the characteristic data of the target new user for the platform, and acquires the characteristic data of the target new user through the platform application program client.
Optionally, the platform application client generates an authorization rejection prompt message and sends the authorization rejection prompt message to the server when the target new user clicks the rejection authorization control. The authorization rejection prompt message is used for prompting the server that the target new user confirms that the acquisition permission of the feature data of the target new user is not granted to the platform. And when receiving the authorization confirmation prompt message, the server confirms that the target new user does not grant the acquisition permission of the characteristic data of the target new user for the platform, and does not execute subsequent data acquisition operation.
Optionally, the acquiring feature data of the target new user includes: and acquiring the characteristic data of the target new user through a platform application program client installed on the terminal equipment of the user.
In a specific example, the collecting, by the platform application client, the feature data of the target new user includes: and the server controls a platform application program client installed on the terminal equipment of the user and provides a characteristic data acquisition page for the target new user. The feature data acquisition page is a page for acquiring feature data of the target new user, and the target new user can fill in or select own feature data on the feature data acquisition page. And the platform application program client acquires the characteristic data filled or selected by the target new user on the characteristic data acquisition page so as to obtain the characteristic data of the target new user, and sends the characteristic data of the target new user to a server.
In another specific example, the collecting, by the platform application client, the feature data of the target new user includes: the server controls a platform application program client installed on the terminal equipment of the user, collects the characteristic data of the target new user from user information and equipment information stored in the terminal equipment and configuration information of the platform application program client, and sends the characteristic data of the target new user to the server. The user information is information associated with a user of the terminal device. The device information is information associated with the terminal device. The configuration information of the platform application client itself may include installation channel information of the platform application client.
Therefore, on the premise of fully respecting and protecting the personal privacy and personal information of the platform user, the characteristic data of the target new user can be acquired through the platform application program client installed in the terminal equipment of the user.
And 102, inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform.
The input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
Optionally, the first preset duration may be set according to a service requirement. Illustratively, the first predetermined period of time is 30 days.
Optionally, each preset category in the platform is a category or a category of an object that a user can browse or view preset in the platform. For each preset category in the platform, the number of active days of the user for the preset category in the first preset time after registration may be the number of days when the time for the user to browse or watch the content in the preset category exceeds the preset time threshold in the first preset time after registration. The preset time threshold can be set according to the service requirement. Illustratively, the preset duration threshold is 1 hour.
Optionally, for the live broadcast platform, each preset item in the platform may be a live broadcast category or category that a user preset in the platform can view, and may include different types of games, dances, and gourmets. In the live broadcast platform, a user can watch different types of live game, live dance and live food.
In one embodiment, the preset categories in the live platform include: a first type of game, a second type of game, a dance, a food. The number of active days of the user for the first type of game within the first preset time after registration is the number of days that the time length for watching the live game of the first type exceeds the preset time length threshold value within the first preset time after registration. The number of active days of the user for the second type of game within the first preset time after registration is the number of days that the time length for watching the live game of the second type exceeds the preset time length threshold value within the first preset time after registration. The number of active days for dancing in the first preset time length after the registration of the user is the number of days when the time length for watching the dancing live broadcast exceeds the preset time length threshold value in the first preset time length after the registration of the user. The active days of the user for the gourmet within the first preset time after registration are days when the time for watching the direct broadcast of the gourmet exceeds the preset time threshold within the first preset time after registration.
Optionally, for the live broadcast platform, each preset item in the platform may also be each anchor that a user preset in the platform can watch. In the live platform, users can watch different anchor live broadcasts.
In one embodiment, the preset categories in the live platform include: a first anchor, a second anchor, and a third anchor. The number of active days of the user for the first anchor within the first preset time after registration is the number of days when the time for watching the live broadcast of the first anchor exceeds the preset time threshold within the first preset time after registration. The number of active days of the user for the second anchor within the first preset time after registration is the number of days that the time length for watching the live broadcast of the second anchor exceeds the preset time length threshold within the first preset time after registration. The number of active days of the user for the third anchor within the first preset time after registration is the number of days that the time length for watching the live broadcast of the third anchor exceeds the preset time length threshold within the first preset time after registration.
Optionally, the method further includes: collecting feature data of all new users within a second preset time length and user values of all the new users aiming at all preset categories in the platform; and training a machine learning model by taking the feature data of each new user and the user value of each preset category in the platform as training samples to obtain a user value prediction model.
Optionally, the second preset duration may be set according to a service requirement. Illustratively, the second predetermined period of time is 6 months. Feature data of all new users within 6 months from 12 months in 2020 to 5 months in 2021 and user values of each of the new users for each preset category in the platform are collected.
Optionally, the collecting feature data of all new users within a second preset duration and the user value of each new user for each preset category in the platform includes: sending data permission query information to a platform application program client installed on the terminal equipment of each new user, so that the platform application program client displays the data permission query information to each new user through a query information display page; the data authority inquiry information is inquiry information used for inquiring whether each new user grants the characteristic data of each new user and the acquisition authority aiming at the user value of each preset type in the platform for the platform or not; and when confirming that each new user grants the collection permission for the platform for the feature data of each new user and the user value of each preset category in the platform according to the interactive operation between each new user and the inquiry information display page, collecting the feature data of each new user through the platform application program client, and collecting the user value of each new user for each preset category in the platform according to the historical operation data of each new user.
And acquiring the user value of each new user for each preset category in the platform according to the historical operation data of each new user, namely determining the number of active days of each new user for each preset category in the platform within a first preset time after registration according to the historical operation data of each new user. The historical operational data is all data related to the user's operation on the platform.
Optionally, the machine learning model includes, but is not limited to, a Multilayer Perceptron (MLP).
Optionally, the collected feature data of all new users within a second preset time period and the user value of each new user for each preset category in the platform are used as training samples, a preset machine learning model is trained, parameters of the machine learning model are determined, and a user value prediction model is obtained. And the input of the user value prediction model is the characteristic data of the new user, and the output is the user value of the new user for each preset category in the platform.
Therefore, a training sample of the user value prediction model is obtained by collecting the characteristic data of a new user in a specified time interval of the platform and the user value of each preset category in the platform, then the machine learning model is trained by using the training sample to obtain the user value prediction model, the characteristic data used for receiving the new user can be trained, the user value prediction model of the new user for the user value of each preset category in the platform is output, and therefore the value of the new user of the network service platform for the network service platform can be rapidly and accurately predicted according to the characteristic data of the new user after the new user registers the network service platform.
Optionally, the training of the machine learning model by using the feature data of each new user and the user value for each preset category in the platform as training samples to obtain a user value prediction model includes: dividing training samples formed by the feature data of each new user and the user value aiming at each preset category in the platform into a training sample set and a test sample set; training a machine learning model by using the training sample set to obtain a user value prediction model; and testing the user value prediction model by using the test sample set to obtain the accuracy of the user value prediction model.
Optionally, according to a preset division ratio, the training samples composed of the feature data of each new user and the user value for each preset category in the platform are divided into a training sample set and a test sample set.
In one embodiment, the training sample contains the feature data of 2000 new users and the user value for each preset category in the platform. And dividing 80% of sample data of the training sample, namely 1600 new users' feature data and user values aiming at each preset category in the platform into a training sample set. And dividing 20% of sample data of the training sample, namely the feature data of 400 new users and the user value aiming at each preset category in the platform into a test sample set.
Optionally, the step of testing the user value prediction model by using the test sample set to obtain the accuracy of the user value prediction model includes: inputting the characteristic data of each new user into the user value prediction model to obtain the user value of each new user, which is output by the user value prediction model, for each preset category in the platform; calculating the root mean square error between the user value of each new user for each preset category in the platform and the user value of each new user for each preset category in the platform output by the user value prediction model by using a root mean square error calculation formula; and determining the accuracy of the user value prediction model according to the root mean square error.
Optionally, determining the accuracy of the user value prediction model according to the root mean square error includes: determining the difference between 1 and the root mean square error as the accuracy of the user value prediction model. Illustratively, the root mean square error between the user value of each new user for each preset category in the platform and the user value of each new user for each preset category in the platform output by the user value prediction model is 22%. The accuracy of the user value prediction model was 78%.
Optionally, the method further includes: and verifying the sequencing result of the user value of each new user aiming at each preset category in the platform, which is output by the user value prediction model, by using Normalized broken and damaged Cumulative Gain (NDCG).
Therefore, a training sample set and a testing sample set can be determined according to the feature data of a new user of the platform in a specified time interval and the user value of each preset type in the platform, a user value prediction model is trained through the training sample set, the trained user value prediction model is tested through the testing sample set, and the accuracy of the user value prediction model is obtained.
And inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform. Therefore, after the target new user registers the network service platform, the value of the target new user for the network service platform is quickly and accurately predicted according to the characteristic data of the target new user, and the value of the new user for the network service platform is quickly and accurately predicted according to the characteristic data of the new user, namely the value of the new user for the network service platform, which is not generated by the network service platform when the target new user registers for the network service platform for the first time.
Optionally, after obtaining the user value of the target new user for each preset category in the platform, the method further includes: and recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform. The user value of the target new user for each preset category in the platform reflects the preference of the target new user for each preset category in the platform. Therefore, after the target new user registers the network service platform, the value of the target new user for the network service platform can be rapidly and accurately predicted according to the characteristic data of the target new user, so that the preference of the new user for each preset item in the platform is determined, then personalized content recommendation is provided for the new user according to the preference of the new user for each preset item in the platform, the recommendation efficiency for the new user is improved, and the cold start problem of the new user is solved.
Optionally, the recommending, according to the user value of the target new user for each preset category in the platform, each preset category in the platform to the target new user includes: calculating the target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category in the platform; determining the target content proportion of the recommended content of each preset category in the platform in the home page content of the platform application program client according to the target user value proportion of each preset category in the platform; generating home page content corresponding to the target new user according to the recommended content of each preset category in the platform and the target content ratio; and sending the home page content corresponding to the target new user to a platform application program client installed in the terminal equipment of the target new user, so that the platform application program client displays the home page content corresponding to the target new user in the home page of the platform application program client when the target new user starts the platform application program client.
Optionally, calculating a target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category in the platform, including: calculating the target user value ratio of the ith preset item in the platform by using the following user value ratio calculation formula:
wherein, PiFor the target user value ratio, V, of the ith preset item class in the platformiThe user value of the target new user for the ith preset category in the platform is obtained, that is, the number of days that the time length for the target new user to browse or watch the content under the ith preset category exceeds a preset time length threshold value within the first preset time length after registration, wherein i is 1,2, … … n, n is the total number of the preset categories in the platform, and sum (v) is the sum of the user values of the target new user for the preset categories in the platform.
In one embodiment, the web services platform is a live platform. Live platform includes 4 and predetermines the article types: a first type of game, a second type of game, a dance, a food. The user values of the target new user for the first type of game, the second type of game, the dance and the food in the platform are respectively as follows: 20, 15, 10,6. The sum of the user values of the target new user for all the preset categories in the platform is 51. And calculating the target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category by using a user value ratio calculation formula: the target user value for the first type of game is 39%. The target user value for the second type of game is 29%. The target user value of dance is 20%. The target user value of the food accounts for 12%. The higher the target user value of the preset category is, the higher the preference degree of the target new user to the preset category is.
Optionally, determining a target content ratio of recommended content of each preset category in the platform in the home page content of the platform application client according to the target user value ratio of each preset category in the platform, including: and determining the target user value ratio of each preset category in the platform as the target content ratio of the recommended content of each preset category in the platform in the home page content of the platform application program client.
In one embodiment, the target user value ratio of each preset category in the platform includes: the target user value for the first type of game is 39%. The target user value for the second type of game is 29%. The target user value of dance is 20%. The target user value of the food accounts for 12%. And determining the target user value ratio of each preset category in the platform as the target content ratio of the recommended content of each preset category in the platform in the home page content of the platform application program client. I.e. the target content percentage of the first type of game is 39%. The target content percentage of the second type of game is 29%. The target content of dance is 20%. The target content of the food is 12 percent.
Optionally, the recommended content of the preset item may be animation, pictures, characters, and the like for recommending the preset item.
Optionally, generating the home page content corresponding to the target new user according to the recommended content of each preset category in the platform and the target content ratio, including: and acquiring the recommended content of each preset item with corresponding size according to the target content proportion of the recommended content of each preset item in the platform in the home page content of the platform application program client, and forming the home page content corresponding to the target new user.
The higher the target user value of the preset item class is, the higher the preference degree of the target new user to the preset item class is, and the higher the content proportion in the home page content is correspondingly, so that the longer-space recommendation is performed on the preset item class preferred by the target new user in the home page content.
Optionally, the server sends the home page content corresponding to the target new user to a platform application client installed in the terminal device of the target new user, so that the platform application client displays the home page content corresponding to the target new user in the home page of the platform application client when the target new user starts the platform application client.
Therefore, according to the preference of the target new user for each preset item in the platform, the home page content corresponding to the target new user can be generated, when the target new user starts the platform application program client, the home page content corresponding to the target new user is displayed, personalized content recommendation is provided for the new user through the home page content corresponding to the target new user, and long-space recommendation is carried out on the preset item preferred by the target new user in the home page content.
Optionally, the recommending, according to the user value of the target new user for each preset category in the platform, each preset category in the platform to the target new user includes: sequencing the preset categories in the platform according to the user value of the target new user for each preset category in the platform from high to low; acquiring a similar class corresponding to a preset class positioned at the first position of the sorting result; and sending the recommended content of the similar categories to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the recommended content of the similar categories to the target new user in the process that the target new user uses the platform application program client.
The higher the top preset category in the ranking result, the higher the preference degree of the target new user. The preset category at the first position of the sorting result is the preset category with the highest preference degree of the target new user. And acquiring a similar category corresponding to the preset category positioned at the first position of the sorting result in the preset categories in the platform. The similar categories corresponding to the preset categories may be other preset categories of which the similarity to the preset categories is greater than a preset similarity threshold.
Optionally, the displaying, by the platform application client, the recommended content of the similar category to the target new user in a process that the target new user uses the platform application client includes: and the platform application client displays the recommended contents of the similar categories in a popup mode in the process that the target new user uses the platform application client.
Optionally, the displaying, by the platform application client, the recommended content of the similar category to the target new user in a process that the target new user uses the platform application client includes: and the platform application program client displays the recommended contents of the similar categories in a preset recommended content display area in the current page where the target new user is located in the process that the target new user uses the platform application program client.
Therefore, other preset categories similar to the preset category with the highest preference degree of the target new user can be recommended to the target new user in the process that the target new user uses the platform application client, and therefore the duration and the number of remaining days for using the platform application client of the target new user are prolonged.
The embodiment of the invention provides a method for predicting the user value of a platform, which comprises the steps of collecting the characteristic data of a target new user when the target new user of the platform is detected, inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform, quickly and accurately predicting the value of the target new user for a network service platform according to the characteristic data of the target new user after the target new user registers the network service platform, and realizing the new user for the network service platform, namely the new user which does not generate historical behavior data when the network service platform is registered for the first time, and quickly and accurately predicting the value of the new user for the network service platform according to the characteristic data of the new user.
Example two
Fig. 2 is a flowchart of a method for predicting a platform user value according to a second embodiment of the present invention. Embodiments of the invention may be combined with various alternatives in one or more of the embodiments described above. As shown in fig. 2, the method of the embodiment of the present invention specifically includes:
And 203, recommending each preset item in the platform to the target new user according to the user value of the target new user for each preset item in the platform.
Optionally, the recommending, according to the user value of the target new user for each preset category in the platform, each preset category in the platform to the target new user includes: calculating the target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category in the platform; determining the target content proportion of the recommended content of each preset category in the platform in the home page content of the platform application program client according to the target user value proportion of each preset category in the platform; generating home page content corresponding to the target new user according to the recommended content of each preset category in the platform and the target content ratio; and sending the home page content corresponding to the target new user to a platform application program client installed in the terminal equipment of the target new user, so that the platform application program client displays the home page content corresponding to the target new user in the home page of the platform application program client when the target new user starts the platform application program client.
Therefore, according to the preference of the target new user for each preset item in the platform, the home page content corresponding to the target new user can be generated, when the target new user starts the platform application program client, the home page content corresponding to the target new user is displayed, personalized content recommendation is provided for the new user through the home page content corresponding to the target new user, and long-space recommendation is carried out on the preset item preferred by the target new user in the home page content.
Optionally, the recommending, according to the user value of the target new user for each preset category in the platform, each preset category in the platform to the target new user includes: sequencing the preset categories in the platform according to the user value of the target new user for each preset category in the platform from high to low; acquiring a similar class corresponding to a preset class positioned at the first position of the sorting result; and sending the recommended content of the similar categories to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the recommended content of the similar categories to the target new user in the process that the target new user uses the platform application program client.
Therefore, other preset categories similar to the preset category with the highest preference degree of the target new user can be recommended to the target new user in the process that the target new user uses the platform application client, and therefore the duration and the number of remaining days for using the platform application client of the target new user are prolonged.
The embodiment of the invention provides a method for predicting the user value of a platform, which comprises the steps of collecting the characteristic data of a target new user when the target new user of the platform is detected, inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform, recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform, and rapidly and accurately predicting the value of the target new user for a network service platform according to the characteristic data of the target new user after the target new user registers the network service platform, so that the new user for the network service platform, namely the new user which does not generate historical behavior data and is registered for the first time on the network service platform, and rapidly and accurately predicting the value of the target new user for the network service platform according to the characteristic data of the new user, therefore, the preference of the new user for each preset item in the platform is determined, and then personalized content recommendation is provided for the new user according to the preference of the new user for each preset item in the platform, the recommendation efficiency for the new user is improved, and the cold start problem of the new user is solved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a device for predicting a platform user value according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: a feature data acquisition module 301 and a user value prediction module 302.
The characteristic data acquisition module 301 is configured to acquire characteristic data of a target new user when the target new user of a platform is detected; the user value prediction module 302 is configured to input the feature data of the target new user into a pre-trained user value prediction model, so as to obtain a user value of the target new user for each preset category in the platform; the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
The embodiment of the invention provides a prediction device of platform user value, which is characterized in that when a target new user of a platform is detected, the characteristic data of the target new user is collected, and then the characteristic data of the target new user is input into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform.
In an optional implementation manner of the embodiment of the present invention, optionally, when the feature data acquisition module 301 performs an operation of acquiring the feature data of the target new user, specifically, the feature data acquisition module is configured to: sending data permission query information to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the data permission query information to the target new user through a query information display page; the data authority inquiry information is inquiry information used for inquiring whether the target new user grants the acquisition authority of the feature data of the target new user for the platform or not; and acquiring the characteristic data of the target new user through the platform application program client when the target new user is confirmed to grant the acquisition right of the characteristic data of the target new user for the platform according to the interactive operation of the target new user and the inquiry information display page.
In an optional implementation manner of the embodiment of the present invention, optionally, the apparatus for predicting a platform user value further includes: the sample acquisition module is used for acquiring feature data of all new users within a second preset time length and user values of all the new users aiming at all preset categories in the platform; and the model training module is used for training the machine learning model by taking the characteristic data of each new user and the user value of each preset category in the platform as training samples to obtain a user value prediction model.
In an optional implementation manner of the embodiment of the present invention, optionally, when the model training module performs an operation of training the machine learning model by using the feature data of each new user and the user value for each preset category in the platform as training samples to obtain the user value prediction model, the model training module is specifically configured to: dividing training samples formed by the feature data of each new user and the user value aiming at each preset category in the platform into a training sample set and a test sample set; training a machine learning model by using the training sample set to obtain a user value prediction model; and testing the user value prediction model by using the test sample set to obtain the accuracy of the user value prediction model.
In an optional implementation manner of the embodiment of the present invention, optionally, the apparatus for predicting a platform user value further includes: and the category recommending module is used for recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform.
In an optional implementation manner of the embodiment of the present invention, optionally, when the category recommendation module executes an operation of recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform, the operation is specifically configured to: calculating the target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category in the platform; determining the target content proportion of the recommended content of each preset category in the platform in the home page content of the platform application program client according to the target user value proportion of each preset category in the platform; generating home page content corresponding to the target new user according to the recommended content of each preset category in the platform and the target content ratio; and sending the home page content corresponding to the target new user to a platform application program client installed in the terminal equipment of the target new user, so that the platform application program client displays the home page content corresponding to the target new user in the home page of the platform application program client when the target new user starts the platform application program client.
In an optional implementation manner of the embodiment of the present invention, optionally, when the category recommendation module executes an operation of recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform, the operation is specifically configured to: sequencing the preset categories in the platform according to the user value of the target new user for each preset category in the platform from high to low; acquiring a similar class corresponding to a preset class positioned at the first position of the sorting result; and sending the recommended content of the similar categories to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the recommended content of the similar categories to the target new user in the process that the target new user uses the platform application program client.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The device for predicting the platform user value can execute the method for predicting the platform user value provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method for predicting the platform user value.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 4 is only one example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors 16, a memory 28, and a bus 18 connecting the various business system components (including the memory 28 and the processors 16).
The memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processor 16 executes various functional applications and data processing by running the program stored in the memory 28, thereby implementing the method for predicting the user value of the platform according to the embodiment of the present invention: when a target new user of a platform is detected, collecting characteristic data of the target new user; inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform; the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
EXAMPLE five
Fifth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where when the computer program is executed by a processor, the method for predicting a platform user value provided in the fifth embodiment of the present invention is implemented: when a target new user of a platform is detected, collecting characteristic data of the target new user; inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform; the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. 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 (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
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, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, 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 user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or computer device. In the case of a remote computer, the remote computer may be connected to the user's 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).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for predicting a platform user value, comprising:
when a target new user of a platform is detected, collecting characteristic data of the target new user;
inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform;
the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
2. The method of claim 1, wherein the collecting the feature data of the target new user comprises:
sending data permission query information to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the data permission query information to the target new user through a query information display page;
the data authority inquiry information is inquiry information used for inquiring whether the target new user grants the acquisition authority of the feature data of the target new user for the platform or not;
and acquiring the characteristic data of the target new user through the platform application program client when the target new user is confirmed to grant the acquisition right of the characteristic data of the target new user for the platform according to the interactive operation of the target new user and the inquiry information display page.
3. The method of claim 1, further comprising:
collecting feature data of all new users within a second preset time length and user values of all the new users aiming at all preset categories in the platform;
and training a machine learning model by taking the feature data of each new user and the user value of each preset category in the platform as training samples to obtain a user value prediction model.
4. The method of claim 3, wherein training a machine learning model by using the feature data of each new user and the user value of each preset category in the platform as training samples to obtain a user value prediction model comprises:
dividing training samples formed by the feature data of each new user and the user value aiming at each preset category in the platform into a training sample set and a test sample set;
training a machine learning model by using the training sample set to obtain a user value prediction model;
and testing the user value prediction model by using the test sample set to obtain the accuracy of the user value prediction model.
5. The method of claim 1, further comprising, after obtaining the user value of the target new user for each preset category in the platform:
and recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform.
6. The method of claim 5, wherein recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform comprises:
calculating the target user value ratio of each preset category in the platform according to the user value of the target new user for each preset category in the platform;
determining the target content proportion of the recommended content of each preset category in the platform in the home page content of the platform application program client according to the target user value proportion of each preset category in the platform;
generating home page content corresponding to the target new user according to the recommended content of each preset category in the platform and the target content ratio;
and sending the home page content corresponding to the target new user to a platform application program client installed in the terminal equipment of the target new user, so that the platform application program client displays the home page content corresponding to the target new user in the home page of the platform application program client when the target new user starts the platform application program client.
7. The method of claim 5, wherein recommending each preset category in the platform to the target new user according to the user value of the target new user for each preset category in the platform comprises:
sequencing the preset categories in the platform according to the user value of the target new user for each preset category in the platform from high to low;
acquiring a similar class corresponding to a preset class positioned at the first position of the sorting result;
and sending the recommended content of the similar categories to a platform application program client installed on the terminal equipment of the target new user, so that the platform application program client displays the recommended content of the similar categories to the target new user in the process that the target new user uses the platform application program client.
8. An apparatus for predicting a user value of a platform, comprising:
the system comprises a characteristic data acquisition module, a characteristic data acquisition module and a characteristic data acquisition module, wherein the characteristic data acquisition module is used for acquiring characteristic data of a target new user when the target new user of a platform is detected;
the user value prediction module is used for inputting the characteristic data of the target new user into a pre-trained user value prediction model to obtain the user value of the target new user for each preset category in the platform;
the input of the user value prediction model is the characteristic data of a new user, the output is the user value of the new user for each preset category in the platform, and the user value for each preset category in the platform is the number of active days of the user for each preset category in the platform within a first preset time after registration.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements a method of predicting a platform user value according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for predicting a user value of a platform according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791170.6A CN113487361A (en) | 2021-07-13 | 2021-07-13 | Method, device, equipment and storage medium for predicting platform user value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791170.6A CN113487361A (en) | 2021-07-13 | 2021-07-13 | Method, device, equipment and storage medium for predicting platform user value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113487361A true CN113487361A (en) | 2021-10-08 |
Family
ID=77938443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791170.6A Pending CN113487361A (en) | 2021-07-13 | 2021-07-13 | Method, device, equipment and storage medium for predicting platform user value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487361A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108683734A (en) * | 2018-05-15 | 2018-10-19 | 广州虎牙信息科技有限公司 | Category method for pushing, device and storage device, computer equipment |
| CN108769725A (en) * | 2018-06-07 | 2018-11-06 | 广州虎牙信息科技有限公司 | Application program launching method, device, storage medium and computer equipment is broadcast live |
| CN109684546A (en) * | 2018-12-24 | 2019-04-26 | 北京城市网邻信息技术有限公司 | Recommended method, device, storage medium and terminal |
-
2021
- 2021-07-13 CN CN202110791170.6A patent/CN113487361A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108683734A (en) * | 2018-05-15 | 2018-10-19 | 广州虎牙信息科技有限公司 | Category method for pushing, device and storage device, computer equipment |
| CN108769725A (en) * | 2018-06-07 | 2018-11-06 | 广州虎牙信息科技有限公司 | Application program launching method, device, storage medium and computer equipment is broadcast live |
| CN109684546A (en) * | 2018-12-24 | 2019-04-26 | 北京城市网邻信息技术有限公司 | Recommended method, device, storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9606712B1 (en) | Placement of user interface elements in a browser based on navigation input | |
| CN109348237B (en) | Live broadcast room management method and device, server and storage medium | |
| CN110633381B (en) | Method and device for identifying false house source, storage medium and electronic equipment | |
| CN109976997B (en) | Test method and device | |
| US8798521B2 (en) | Content creation in an online learning environment | |
| US20150106723A1 (en) | Tools for locating, curating, editing, and using content of an online library | |
| US8612478B1 (en) | Location based query-response management system | |
| CN105493057A (en) | Content selection with precision controls | |
| CN108694324B (en) | Information leakage monitoring method and device | |
| CN111046292B (en) | Live broadcast recommendation method and device, computer readable storage medium and electronic equipment | |
| US20150199774A1 (en) | One click on-boarding crowdsourcing information incentivized by a leaderboard | |
| CN104580348A (en) | Accessing location-based content | |
| US9626647B2 (en) | Providing a contact service | |
| CN109561212B (en) | Merging method, device, equipment and storage medium for published information | |
| CN110110236B (en) | Information pushing method, device, equipment and storage medium | |
| CN111949859B (en) | User portrait updating method, device, computer equipment and storage medium | |
| CN114036381A (en) | Course recommendation method and device, storage medium and electronic equipment | |
| CN112163879B (en) | User rights pushing method, device, server and storage medium | |
| JP2008072205A (en) | Server, terminal, and action recording system and method | |
| CN110969479B (en) | Method, equipment and computer storage medium for displaying popularization resources | |
| CN110276183B (en) | Reverse Turing verification method and device, storage medium and electronic equipment | |
| US20090197232A1 (en) | Matching learning objects with a user profile using top-level concept complexity | |
| US20150288627A1 (en) | Correlating electronic mail with media monitoring | |
| CN112749327A (en) | Content pushing method and device | |
| CN113487361A (en) | Method, device, equipment and storage medium for predicting platform user value |
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 |