CN113743968A - Information delivery method, device and equipment - Google Patents
Information delivery method, device and equipment Download PDFInfo
- Publication number
- CN113743968A CN113743968A CN202010475888.XA CN202010475888A CN113743968A CN 113743968 A CN113743968 A CN 113743968A CN 202010475888 A CN202010475888 A CN 202010475888A CN 113743968 A CN113743968 A CN 113743968A
- Authority
- CN
- China
- Prior art keywords
- candidate
- user
- target
- seed
- population
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides an information delivery method, an information delivery device and information delivery equipment, and the method can comprise the following steps: when information is released, an operation instruction which is input by a user on an operation interface and comprises configuration parameters and/or service demand parameters is received, namely different personalized crowd diffusion service requirements are considered, candidate crowds and target characteristic information are determined according to the configuration parameters and/or the service demand parameters input by the user, target candidate crowds are determined in the candidate crowds together according to the target characteristic information and the seed crowds corresponding to each candidate user in the candidate crowds, the flexibility and humanization of crowd diffusion are effectively improved, and then the information is released to the target candidate crowds. Compared with the prior art in which information is directly put into the diffusion crowd of the seed crowd, the accuracy of information putting is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to an information delivery method, device and equipment.
Background
In internet enterprises, it is usually necessary to determine the population to be spread among a large number of users, and to perform information distribution to the population to be spread by means of advertisement distribution, coupon sending, short message reaching, and the like, so as to achieve the purpose of marketing.
In the prior art, when information is put in, people are diffused to seed people to obtain diffused people, and information is put in the diffused people. Wherein, the seed population refers to the population with the same requirements and interests for products and services; people with the same characteristics as the seed population are called extended population, and the number of the extended population is usually multiple times of that of the seed population. However, when the seed population is large, it results in a large number of diffused populations; in addition, non-quality seed users with redundancy or low reliability may exist in the seed population, and the determination of the diffusion population is influenced to a certain extent, so that the accuracy of information delivery is not high.
Therefore, how to improve the accuracy of information delivery when information delivery is performed is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the application provides an information delivery method, an information delivery device and information delivery equipment, and the accuracy of information delivery is improved when information delivery is carried out.
In a first aspect, an embodiment of the present application provides an information delivery method, where the information delivery method may include:
receiving an operation instruction input on an operation interface, wherein the operation instruction comprises configuration parameters and/or service requirement parameters.
Determining candidate crowd and target characteristic information according to the configuration parameters and/or the service demand parameters; the candidate crowd comprises a plurality of candidate users.
Acquiring a seed population; the seed crowd comprises a plurality of seed users.
And determining a target candidate group in the candidate group according to the target characteristic information corresponding to each candidate user in the candidate group and the seed group.
And delivering information to the target candidate group.
Therefore, when information delivery is performed, an operation instruction which is input by a user on an operation interface and comprises configuration parameters and/or service demand parameters is received, namely different personalized crowd diffusion service appeal requirements are considered, candidate crowd and target characteristic information are determined according to the configuration parameters and/or the service demand parameters input by the user, then the target candidate crowd is determined in the candidate crowd together according to the target characteristic information and the seed crowd corresponding to each candidate user in the candidate crowd, the flexibility and humanization of crowd diffusion are effectively increased, and information is delivered to the target candidate crowd. Compared with the prior art in which information is directly put into the diffusion crowd of the seed crowd, the accuracy of information putting is improved.
In a possible implementation manner, the determining a target candidate group from the candidate group according to the target feature information corresponding to each candidate user in the candidate group and the seed group may include:
clustering the plurality of seed users according to the target characteristic information corresponding to each seed user in the seed population to obtain M clusters; wherein, the central point of each cluster is used as a cluster central user; m is an integer greater than or equal to 2.
And determining the corresponding association degree of each candidate user according to the target characteristic information corresponding to each candidate user in the candidate crowd and the target characteristic information corresponding to the M cluster center users.
According to the sequence of the relevance degrees from big to small, the candidate users corresponding to the first N relevance degrees are determined as the target candidate crowd, so that the accuracy of the obtained target candidate crowd is improved, and the relevance degrees between the target characteristic information corresponding to each candidate user in the candidate crowd and the target characteristic information corresponding to the M cluster center users are only calculated, so that the calculation resources are effectively saved, and the calculation efficiency is improved.
In a possible implementation manner, the determining, according to the target feature information corresponding to each candidate user in the candidate group and the target feature information corresponding to the M cluster center users, a degree of association corresponding to each candidate user may include:
and calculating the association degree between the target characteristic information corresponding to any one candidate user in the candidate crowd and the target characteristic information corresponding to each clustering center in the M clustering center users respectively to obtain M association degrees.
The average value of the M relevance degrees is determined as the relevance degree corresponding to the candidate user, so that the relevance degree corresponding to the candidate user is obtained through calculation, when the relevance degree is calculated, target characteristic information corresponding to the clustered M clustering center users is adopted for calculation, the problems that abnormal users possibly doped in seed crowds and the seed crowds contain a plurality of sub-crowd can be solved to a certain extent, the calculation is not affected by abnormal data, the crowd characteristics are strengthened, the finally calculated characteristic information of the target candidate crowds is more remarkable, and the problems that computing resources of a super-large matrix and the super-large matrix are consumed for a long time are solved.
In a possible implementation manner, the obtaining of the seed population may include:
an initial seed population is obtained.
And screening the initial seed population according to the target characteristic information corresponding to each seed user in the initial seed population to obtain the seed population, so that outlier outliers in the initial seed population can be eliminated, and the seed population with the characteristic information with higher similarity is obtained.
In a possible implementation manner, if the operation instruction includes the configuration parameter, the candidate group includes a user corresponding to the configuration parameter; if the operation instruction comprises the service demand parameter, the candidate crowd comprises the user corresponding to the service demand parameter; if the operation instruction comprises the configuration parameter and the service demand parameter, the candidate crowd comprises an intersection of the user corresponding to the configuration parameter and the user corresponding to the service demand parameter, and therefore the candidate crowd is determined. It can be seen that when determining the candidate group, the configuration parameters and/or the service demand parameters input by the user are taken into consideration, that is, different personalized population diffusion service requirements are taken into consideration, so that the flexibility and the personalization of population diffusion can be effectively increased.
In a possible implementation manner, the information delivery method may further include:
and inputting the business characteristics corresponding to each preset user in the preset population into a prediction model to obtain the probability that the preset user meets the business requirements.
And determining the preset users with the probability larger than a preset threshold value as the users corresponding to the service demand parameters.
In a possible implementation manner, determining the target feature information according to the configuration parameter and/or the service requirement parameter may include:
acquiring a plurality of attribute feature information;
the feature information corresponding to the configuration parameters and/or the feature information corresponding to the business demand parameters and the attribute feature information are determined as the target feature information, so that the final target candidate crowd can be determined from the candidate crowd when the relevance is calculated according to the target feature information subsequently.
In a second aspect, an embodiment of the present application further provides an information delivery apparatus, where the information delivery apparatus may include:
the receiving module is used for receiving an operation instruction input on an operation interface, wherein the operation instruction comprises configuration parameters and/or service requirement parameters.
The processing module is used for determining candidate crowd and target characteristic information according to the configuration parameters and/or the service demand parameters; the candidate crowd comprises a plurality of candidate users.
The acquisition module is used for acquiring seed crowds; the seed crowd comprises a plurality of seed users.
The processing module is further configured to determine a target candidate group from the candidate groups according to the target feature information corresponding to each candidate user in the candidate groups and the seed group;
and the sending module is used for releasing information to the target candidate group.
In a possible implementation manner, the processing module is specifically configured to perform clustering processing on the plurality of seed users according to target feature information corresponding to each seed user in the seed population to obtain M clusters; wherein, the central point of each cluster is used as a cluster central user; m is an integer greater than or equal to 2; determining the corresponding association degree of each candidate user according to the target characteristic information corresponding to each candidate user in the candidate population and the target characteristic information corresponding to the M cluster center users; and determining the target candidate group by the candidate users corresponding to the first N relevance degrees according to the sequence of the relevance degrees from large to small.
In a possible implementation manner, the processing module is specifically configured to calculate association degrees between target feature information corresponding to any one candidate user in the candidate group and target feature information corresponding to each clustering center of the M clustering center users, so as to obtain M association degrees; and determining the average value of the M association degrees as the association degree corresponding to the candidate user.
In a possible implementation manner, the obtaining module is specifically configured to obtain an initial seed population; and screening the initial seed population according to the target characteristic information corresponding to each seed user in the initial seed population to obtain the seed population.
In a possible implementation manner, if the operation instruction includes the configuration parameter, the candidate group includes a user corresponding to the configuration parameter; if the operation instruction comprises the service demand parameter, the candidate crowd comprises the user corresponding to the service demand parameter; if the operation instruction comprises the configuration parameter and the service demand parameter, the candidate crowd comprises an intersection of the user corresponding to the configuration parameter and the user corresponding to the service demand parameter.
In a possible implementation manner, the processing module is further configured to input, to the prediction model, a service feature corresponding to each preset user in a preset population, so as to obtain a probability that the preset user meets a service requirement; and determining the preset users with the probability larger than a preset threshold value as the users corresponding to the service demand parameters.
In a possible implementation manner, the processing module is specifically configured to obtain a plurality of attribute feature information; and determining the characteristic information corresponding to the configuration parameters and/or the characteristic information corresponding to the service requirement parameters and the attribute characteristic information as the target characteristic information.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, where the processor, when executing the program, implements the information delivery method as described in any one of the possible implementations of the first aspect.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed on an electronic device, the electronic device is caused to execute the information delivery method described in any one of the foregoing possible implementation manners of the first aspect.
According to the information delivery method, the information delivery device and the information delivery equipment, when information delivery is carried out, the operation instruction which is input by a user on an operation interface and comprises the configuration parameters and/or the service demand parameters is received, namely different personalized crowd diffusion service appeal requirements are considered, the candidate crowd and the target characteristic information are determined according to the configuration parameters and/or the service demand parameters input by the user, the target candidate crowd is determined in the candidate crowd together according to the target characteristic information and the seed crowd corresponding to each candidate user in the candidate crowd, the flexibility and the humanization of crowd diffusion are effectively improved, and then the information is delivered to the target candidate crowd. Compared with the prior art in which information is directly put into the diffusion crowd of the seed crowd, the accuracy of information putting is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic flowchart of an information delivery method according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating an embodiment of the present application for determining a probability of a default user achieving a high-order potential demand target;
FIG. 3 is a block diagram of a method for determining a target candidate group according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart illustrating a process for determining a target candidate group among the candidate groups according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an exemplary pattern extraction provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of an information delivery apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an embodiment of an electronic device according to an embodiment of the present disclosure.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In the embodiments of the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In the description of the text of the present application, the character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The information delivery method provided by the embodiment of the application can be applied to the scenes of information delivery or advertisement marketing, and certainly can also be applied to the scenes of e-market or other scenes. Taking an information delivery scene as an example, in a general case, when information delivery is performed by an electronic device, a diffusion crowd is obtained based on a local seed crowd, and information is delivered to the diffusion crowd. However, when the seed population is large, it results in a large number of diffused populations; in addition, non-quality seed users with redundancy or low reliability may exist in the seed population, and the determination of the diffusion population is influenced to a certain extent, so that the accuracy of information delivery is not high.
In order to improve the accuracy of information delivery, an information delivery method is provided in an embodiment of the present application, when information delivery is performed, an operation instruction including a configuration parameter and/or a service demand parameter, which is input on an operation interface by a user, is received, that is, different personalized population diffusion service appeal is considered, candidate populations and target feature information are determined according to the configuration parameter and/or the service demand parameter input by the user, and then target candidate populations are determined in the candidate populations together according to target feature information and seed populations corresponding to each candidate user in the candidate populations, so that the flexibility and humanization of population diffusion are effectively increased, and then information is delivered to the target candidate populations. Compared with the prior art in which information is directly put into the diffusion crowd of the seed crowd, the accuracy of information putting is improved.
Taking the application of the embodiment of the application to e-commerce scenes as an example, the released information can be marketing advertisements, coupons and the like. For example, the configuration parameters may include at least one of a category, a store, a value, and an intent; the business demand parameters may include at least one of high conversion potential demand, high concern potential demand, and high order potential demand. In the embodiment of the application, when population diffusion is performed, the configuration parameters and/or the service demand parameters input by a user are considered, namely different personalized population diffusion service requirements are considered, so that the flexibility and personalization of population diffusion are effectively increased when target candidate populations are determined, and the accuracy of the obtained diffused populations is improved; therefore, when information is put into the diffusion crowd, the accuracy of information putting is improved.
It can be understood that, when the embodiment of the present application is applied to other scenarios, corresponding configuration parameters and parameters that do not need to be required may also be added or replaced with other parameters, as long as the indexes that conform to business logic and have data support can all be replaced in the implementation process, but the implementation principle is similar to the implementation process in the e-commerce scenario, and here, the embodiment of the present application is not described again.
The following describes the technical solution of the present application and how to solve the above technical problem in detail by taking an e-commerce scenario as an example and a specific embodiment. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating an information delivery method according to an embodiment of the present disclosure, where the information delivery method may be executed by software and/or a hardware device, for example, the hardware device may be an information delivery device, and the information delivery device may be disposed in an electronic device. For example, referring to fig. 1, the information delivery method may include:
and S101, receiving an operation instruction input on an operation interface.
The operation instruction comprises configuration parameters and/or service requirement parameters.
For example, before receiving an operation instruction input by a user on an operation interface, a configuration parameter and a business requirement parameter list may be displayed to the user through the operation interface, where the configuration parameter list may include a plurality of configuration parameters, such as categories, stores, values, intentions, and the like, and the business requirement parameter list may include a plurality of business requirement parameters, such as high conversion potential requirements, high attention potential requirements, high order potential requirements, and the like; the user can select the configuration parameters and/or the service demand parameters to be used according to the configuration parameter list and the service demand parameter list displayed on the operation interface, and the configuration parameters and/or the service demand parameters can reflect the crowd diffusion service appeal.
It can be understood that, when the user selects the parameters to be used from the configuration parameter list and the service requirement parameter list, only one or more parameters in the configuration parameter list, such as the category, may be selected; or only one or more parameters in the service requirement parameter list can be selected, such as high-order and low-order potential requirements; of course, one or more parameters, such as categories and high-order and low-order potential requirements, may also be selected from the configuration parameter list and the service requirement parameter list at the same time, and the selection may be specifically performed according to actual needs, which is not further limited in the embodiments of the present application.
After receiving an operation instruction including a configuration parameter and/or a service requirement parameter input by a user on the operation interface, the following S102 may be executed:
and S102, determining candidate crowd and target characteristic information according to the configuration parameters and/or the business demand parameters.
The candidate crowd comprises a plurality of candidate users.
For example, when a candidate group is determined according to a configuration parameter and/or a service requirement parameter, if the operation instruction includes the configuration parameter, the candidate group includes a user corresponding to the configuration parameter; taking the configuration parameters as categories as an example, the candidate population is the user corresponding to the categories; if the operation instruction comprises the service requirement parameter, the candidate crowd comprises the user corresponding to the service requirement parameter; taking the service demand parameter as the high-order potential demand as an example, the candidate population is the user meeting the high-order potential demand; if the operation instruction comprises the configuration parameter and the service demand parameter, the candidate population comprises an intersection of the user corresponding to the configuration parameter and the user corresponding to the service demand parameter, taking the configuration parameter as the category and taking the service demand parameter as the high-low-order potential demand as an example, the candidate population is an intersection user of the user corresponding to the category and the user meeting the high-low-order potential demand, namely the intersection user is both the user corresponding to the category and the user meeting the high-low-order potential demand, so that the candidate population can be determined according to the configuration parameter and/or the service demand parameter.
In the above description, when determining the user corresponding to the service demand parameter, for example, the service characteristics corresponding to each preset user in the preset population may be input to the prediction model, so as to obtain the probability that the preset user meets the service demand; for example, the probability of each preset user reaching the service demand target in the next five days is predicted, and the preset user with the probability greater than the preset threshold is determined as the user corresponding to the service demand parameter, so that the diffused population can be depicted more accurately, the service application has directivity, the marketing cost is further saved, and the profitability is improved. Wherein, the preset crowd can be understood as the crowd consisting of the users with the business characteristic behaviors recently. It can be understood that before the prediction model is used for predicting the probability that the preset user meets the business requirement, model training needs to be performed to obtain the prediction model. By way of example, supervised classification algorithms may be utilized; for example, a logistic regression algorithm, a random forest algorithm, GBDT, XGboost, etc. are used to train a model to obtain the prediction model, or a comprehensive evaluation method may be used to combine models with artificial experience or train a deep learning algorithm to obtain the prediction model, which may be specifically set according to actual needs.
For example, when the service demand parameter is a high-order potential demand, the prediction model may be a high-order potential model that is expected to be implemented by the user, in this case, please refer to fig. 2, where fig. 2 is a schematic diagram that is provided in the embodiment of the present application and determines a probability that the preset user achieves the high-order potential demand target, and the relevant service features corresponding to each preset user, such as a basic attribute feature, a search feature, a browsing feature, a clicking feature, an adding purchasing feature, a service feature, a category behavior feature, and the like, may be input into the pre-established high-order potential model to predict the probability that each preset user achieves the high-order potential demand target, that is, the user with a high probability that meets the high-order demand is screened out as the user corresponding to the high-order potential demand.
After the candidate population is determined according to the configuration parameters and/or the business demand parameters, the candidate users in the candidate population are further screened based on the target characteristics of each candidate user in the candidate population and the seed population to obtain the final target candidate population, so that the target characteristic information can be determined according to the configuration parameters and/or the business demand parameters. For example, when determining the target feature information according to the configuration parameters and/or the service requirement parameters, a plurality of attribute feature information may be obtained first; and then determining the characteristic information corresponding to the configuration parameters and/or the characteristic information corresponding to the service demand parameters, and determining the characteristic information corresponding to the configuration parameters and/or the characteristic information corresponding to the service demand parameters and the plurality of attribute characteristic information as target characteristic information.
For example, when acquiring a plurality of attribute feature information, a plurality of attribute feature information may be selected from basic feature information (gender, age, academic history, marital status, etc.), behavior attribute feature information (search, browse, click, purchase, order placement, etc.), value attribute feature information (life cycle, user value, user purchasing power, etc.), credit attribute (order cancelled, after sale, risk level, etc.) and a large number of attribute feature information by combining methods such as analysis of variance, correlation analysis, loss rate, manual judgment, etc., so as to extract typical attribute feature information from an unsupervised large feature information set. It is understood that, in the embodiment of the present application, through the extraction of the typical attribute feature information, the purpose is to: 1. when clustering or diffusion is carried out through mass attribute feature information at a later stage, the diffusion stability of target candidate users is poor, and the interpretability of target candidate groups is weak; 2. the attribute characteristic information with high missing rate and the columns with very small characteristic change contain less information, and can not be reserved during diffusion; 3. when the crowd diffusion is realized by the homogeneous attribute feature information, only important variables need to be reserved, the same category variables are reserved too much, on one hand, the calculation efficiency is influenced, on the other hand, the information redundancy does not have too much correction effect on the crowd diffusion result, but the information redundancy can be mutually braked, so that the subsequent result in the calculation of the correlation degree, such as the similarity or the distance, is influenced too much by the attribute feature information of a certain category, and the accuracy of the calculated correlation degree is lower.
It should be noted that the plurality of attribute feature information obtained by feature screening are only attribute feature information, and in order to make population diffusion more suitable for personalized business requirements, behavior feature information may also be obtained according to configuration parameters and/or business requirement parameters, and the behavior feature information corresponding to the configuration parameters and/or the business requirement parameters and the obtained plurality of attribute feature information are used as target feature information, so as to determine target feature information, and thus when calculating the degree of association according to the target feature information, a final target candidate population may be determined from candidate populations. For example, taking the configuration parameter as the category as an example, the feature information corresponding to the configuration parameter is the feature information corresponding to the category; and if the service demand parameter is the high-order potential demand, the characteristic information corresponding to the service demand parameter is the probability characteristic for achieving the high-order potential demand target.
Taking configuration parameters as cross-product classes as an example, when a user selects a certain product class for cross-product class, a user behavior sequence can be formed according to the recent behavior (clicking, paying attention, purchasing and purchasing) data of the user and time sequencing, a Word2Vec model is constructed to conduct embedding to calculate the similarity between the product classes, a graph relation between the product classes is constructed, a product class association suitable for cross-product class update is established, and associated product class recommendation can be conducted on the user. In this case, the features of both the candidate population and the prediction model are dynamically adjusted. Candidate population: and the candidate users who have bought the related categories of the categories in the last year or have searched, browsed, clicked, purchased and the like in the last three months, and the prediction model predicts the users with the identification of yes, so that the candidate crowd of cross categories is obtained. Wherein the characteristics of the prediction model are: the method mainly comprises user attribute characteristic information (user basic attribute characteristic information, user value characteristic information, life cycle characteristic information, consumption preference characteristic information and total station behavior characteristic information), and category behavior characteristic information, category value characteristic information, category preference characteristic information and the like of the category and the associated categories.
After the candidate population and the target feature information are respectively determined according to the configuration parameters and/or the business demand parameters through the step S102, the seed population can be obtained, so as to determine the target candidate population in the candidate population according to the target feature information and the seed population corresponding to each candidate user in the candidate population, namely, the following steps S103-S104 are executed.
S103, acquiring seed population.
Wherein, the seed crowd comprises a plurality of seed users.
For example, when a seed population is obtained, an initial seed population that it maintains may be obtained locally; because many sub-populations are often mixed in the initial seed population, if the initial seed population is directly used for subsequent relevance calculation, the characteristics of the seed population are weakened, so that the characteristics of the target candidate population finally determined based on the initial seed population are not obvious; therefore, when calculating the subsequent relevance, the initial seed population can be screened according to the target characteristic information corresponding to each seed user in the initial seed population to obtain the seed population with the characteristic information with higher similarity.
For example, when the initial seed population is screened according to the target feature information corresponding to each seed user in the initial seed population, the abnormal value may be processed by using a boxplot method, where the abnormal value is defined as a value smaller than Q1(Q1 refers to a first quartile) -1.5IQR (IQR refers to a difference value between a third quartile and a first quartile), or defined as a value greater than Q3(Q3 refers to a third quartile) +1.5IQR, where the value greater than Q3+1.5IQR is replaced by Q3+1.5IQR, and the value smaller than Q1-1.5IQR is replaced by Q1-1.5 IQR.
And S104, determining a target candidate group in the candidate group according to the target characteristic information and the seed group corresponding to each candidate user in the candidate group.
Wherein, the target candidate group can be understood as the group needing to be obtained finally.
When a target candidate group is determined in a candidate group according to target feature information and a seed group corresponding to each candidate user in the candidate group, for example, please refer to fig. 3, where fig. 3 is a schematic diagram of a framework for determining the target candidate group provided in the embodiment of the present application, it can be seen that the seed group can be obtained first, and when population diffusion is performed based on the seed group, a diffusion target can be determined first, and the diffusion target can be realized through configuration parameters and/or business requirement parameters, and the diffusion group in a diffusion direction corresponding to the diffusion target is the target candidate group.
And S105, delivering information to the target candidate group.
Therefore, when information delivery is performed, an operation instruction which is input by a user on an operation interface and comprises configuration parameters and/or service demand parameters is received, namely different personalized crowd diffusion service appeal is considered, candidate crowd and target characteristic information are determined according to the configuration parameters and/or the service demand parameters input by the user, then the target candidate crowd is determined in the candidate crowd together according to the target characteristic information and the seed crowd corresponding to each candidate user in the candidate crowd, the flexibility and humanization of crowd diffusion are effectively increased, and information is delivered to the target candidate crowd. Compared with the prior art in which information is directly put into the diffusion crowd of the seed crowd, the accuracy of information putting is improved.
Based on the above-mentioned embodiment shown in fig. 1, in order to facilitate understanding how to determine the target candidate group in the candidate group according to the target feature information and the seed group corresponding to each candidate user in the candidate group in the above-mentioned S104, a detailed description will be made through the following embodiment.
Fig. 4 is a schematic flowchart of determining a target candidate group from among candidate groups according to an embodiment of the present application, for example, please refer to fig. 4, where the method may include:
s401, clustering a plurality of seed users according to target characteristic information corresponding to each seed user in the seed population to obtain M clusters.
Wherein, the central point of each cluster is used as a cluster central user; m is an integer greater than or equal to 2.
For example, when clustering is performed on a plurality of seed users, the seed population can be clustered through a K-means algorithm, and of course, the seed population can also be clustered through other algorithms, and each clustering center point is extracted as a typical pattern of the seed user and serves as a virtual clustering center user, so that not only is the computing resource saved, but also the characteristics of the seed population can be more obvious. For example, please refer to fig. 5, where fig. 5 is a schematic diagram of a typical pattern extraction provided in the embodiment of the present application, it can be seen that a plurality of attribute feature information obtained through feature screening may be added with behavior feature information corresponding to configuration parameters and/or service demand parameters as target feature information, and then, in combination with a seed population, a plurality of seed users may be clustered according to the target feature information corresponding to each seed user in the seed population to obtain M clusters, and each cluster center point may be used as a typical pattern of the seed user.
S402, determining the corresponding association degree of each candidate user according to the target characteristic information corresponding to each candidate user in the candidate crowd and the target characteristic information corresponding to the M cluster center users.
For example, when determining the association degree corresponding to each candidate user according to the target feature information corresponding to each candidate user in the candidate population and the target feature information corresponding to the M cluster center users, since the calculation methods of the association degrees corresponding to each candidate user are similar, for avoiding redundancy, any candidate user in the candidate population may be taken as an example, and when calculating the association degree corresponding to the candidate user, the association degrees between the target feature information corresponding to the candidate user and the target feature information corresponding to each cluster center in the M cluster center users may be obtained by first calculating the association degrees corresponding to the candidate user; calculating the mean value of the M association degrees, and determining the mean value of the M association degrees as the association degree corresponding to the candidate user; according to the method, the corresponding relevance of each candidate user in the candidate crowd can be obtained.
For example, the association may be a similarity and/or a distance. When calculating the similarity between the target feature information corresponding to the candidate user and the target feature information corresponding to each cluster center of the M cluster center users, different algorithms are usually selected according to different data. Currently, the most used similarity algorithms are: pearson correlation coefficient algorithm, cosine similarity algorithm, and corrected cosine similarity algorithm, etc. When the distance between the target characteristic information corresponding to the candidate user and the target characteristic information corresponding to each cluster center of the M cluster center users is calculated, different algorithms can be selected according to different data. Currently, the most used distance algorithms are: euclidean distance, minkowski distance, manhattan distance, chebyshev distance, mahalanobis distance, and the like.
It should be noted that, when calculating the association degree, the target feature information corresponding to the M clustered users at the clustering centers is used for calculation, so that the problems that abnormal users possibly doped in the seed population and the seed population itself contain a plurality of sub-population groups can be solved to a certain extent, the influence of abnormal data is avoided during calculation, the population features are enhanced, the finally calculated feature information of the target candidate population is more significant, and the problem of large resource consumption and long time consumption in calculating the super-large matrix and the super-large matrix is solved.
Thus, after the association degree corresponding to each candidate user is calculated according to the target feature information corresponding to each candidate user in the candidate population and the target feature information corresponding to the M cluster center users, the following S403 may be performed:
and S403, determining target candidate groups of the candidate users corresponding to the first N relevance degrees according to the sequence of the relevance degrees from large to small.
After the association degree corresponding to each candidate user is obtained through calculation, the association degrees can be ranked in a descending order, and the candidate users corresponding to the top N larger association degrees in the candidate crowd are determined as the target candidate crowd; of course, the association degrees may not be performed in the descending order, but the candidate users corresponding to the association degrees greater than the preset threshold may be directly determined as the target candidate group, which may be specifically set according to actual needs. The preset threshold value can be set according to actual needs.
Therefore, when the target candidate group is determined in the candidate group according to the target characteristic information and the seed group corresponding to each candidate user in the candidate group, firstly, clustering a plurality of seed users in the seed group to obtain M clusters, wherein each cluster corresponds to one cluster center user; and determining the relevance degree corresponding to each candidate user according to the target characteristic information corresponding to each candidate user in the candidate population and the target characteristic information corresponding to M cluster center users, and determining the target candidate population from the candidate users corresponding to the first N relevance degrees according to the sequence of the relevance degrees from large to small, so that the accuracy of the obtained target candidate population is improved, and only the relevance degrees between the target characteristic information corresponding to each candidate user in the candidate population and the target characteristic information corresponding to M cluster center users are calculated, so that the calculation resources are effectively saved, and the calculation efficiency is improved.
Fig. 6 is a schematic structural diagram of an information delivery apparatus 60 according to an embodiment of the present application, and for example, referring to fig. 6, the information delivery apparatus 60 may include:
the receiving module 601 is configured to receive an operation instruction input on an operation interface, where the operation instruction includes a configuration parameter and/or a service requirement parameter.
The processing module 602 is configured to determine candidate population and target feature information according to the configuration parameters and/or the service requirement parameters; the candidate population includes a plurality of candidate users.
An obtaining module 603, configured to obtain a seed population; the seed crowd comprises a plurality of seed users.
The processing module 602 is further configured to determine a target candidate group from the candidate groups according to the target feature information and the seed group corresponding to each candidate user in the candidate groups.
A sending module 604, configured to deliver information to the target candidate group.
Optionally, the processing module 602 is specifically configured to perform clustering processing on multiple seed users according to target feature information corresponding to each seed user in a seed population to obtain M clusters; wherein, the central point of each cluster is used as a cluster central user; m is an integer greater than or equal to 2; determining the corresponding relevance of each candidate user according to the target characteristic information corresponding to each candidate user in the candidate crowd and the target characteristic information corresponding to the M clustering center users; and determining target candidate groups of the candidate users corresponding to the first N relevance degrees according to the sequence of the relevance degrees from large to small.
Optionally, the processing module 602 is specifically configured to calculate association degrees between target feature information corresponding to any one candidate user in the candidate group and target feature information corresponding to each cluster center of the M cluster center users, so as to obtain M association degrees; and determining the average value of the M association degrees as the association degree corresponding to the candidate user.
Optionally, the obtaining module 603 is specifically configured to obtain an initial seed population; and screening the initial seed population according to the target characteristic information corresponding to each seed user in the initial seed population to obtain the seed population.
Optionally, if the operation instruction includes the configuration parameter, the candidate group includes a user corresponding to the configuration parameter; if the operation instruction comprises the service requirement parameter, the candidate crowd comprises the user corresponding to the service requirement parameter; if the operation instruction comprises the configuration parameter and the service requirement parameter, the candidate crowd comprises the intersection of the user corresponding to the configuration parameter and the user corresponding to the service requirement parameter.
Optionally, the processing module 602 is further configured to input, to the prediction model, a service feature corresponding to each preset user in the preset population, so as to obtain a probability that the preset user meets a service requirement; and determining the preset users with the probability larger than the preset threshold value as the users corresponding to the service demand parameters.
Optionally, the processing module 602 is specifically configured to obtain a plurality of attribute feature information; and determining the characteristic information corresponding to the configuration parameters and/or the characteristic information corresponding to the service requirement parameters and the plurality of attribute characteristic information as target characteristic information.
The information delivery device 60 provided in this embodiment of the application can implement the technical solution of the information delivery method in any embodiment, and the implementation principle and the beneficial effect thereof are similar to those of the information delivery method, and reference may be made to the implementation principle and the beneficial effect of the information delivery method, which is not described herein again.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the determining module may be a processing element that is separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the function of the determining module may be called and executed by a processing element of the apparatus. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Fig. 7 is a schematic structural diagram of an embodiment of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic device may include: the information delivery method includes a processor 701, a memory 702, and a computer program that is stored in the memory 702 and can run on the processor 701, and of course, the information delivery method may also include a communication interface 703 and a system bus 704, where the memory 702 and the communication interface 703 are connected to the processor 701 through the system bus 704 and complete mutual communication, the memory 702 is used to store the computer program, the communication interface 703 is used to communicate with other devices, and the processor 701 implements the technical solution of the information delivery method shown in the above embodiment when executing the computer program.
In fig. 7, the processor 701 may be a general-purpose processor, including a central processing unit CPU, a Network Processor (NP), and the like; but also a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
The memory 702 may comprise Random Access Memory (RAM), read-only memory (RAM), and non-volatile memory (non-volatile memory), such as at least one disk memory.
The communication interface 703 is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries).
The system bus 704 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
Optionally, an embodiment of the present application further provides a computer-readable storage medium, where a computer instruction is stored in the computer-readable storage medium, and when the computer instruction runs on an electronic device, the electronic device is enabled to execute the technical solution of the information delivery method shown in the foregoing embodiment, and an implementation principle and beneficial effects of the computer instruction are similar to those of the information delivery method, and reference may be made to the implementation principle and beneficial effects of the information delivery method, which is not described herein again.
Optionally, an embodiment of the present application further provides a chip for running the instruction, where the chip is configured to execute the technical scheme of the information delivery method shown in the foregoing embodiment, and an implementation principle and beneficial effects of the chip are similar to those of the information delivery method, and reference may be made to the implementation principle and beneficial effects of the information delivery method, which are not described herein again.
An embodiment of the present application further provides a program product, where the program product includes a computer program, where the computer program is stored in a computer-readable storage medium, and the computer program can be read from the computer-readable storage medium by at least one processor, and when the at least one processor executes the computer program, the technical solution of the information delivery method in the foregoing embodiment can be implemented.
Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. An information delivery method, comprising:
receiving an operation instruction input on an operation interface, wherein the operation instruction comprises configuration parameters and/or service requirement parameters;
determining candidate crowd and target characteristic information according to the configuration parameters and/or the service demand parameters; the candidate crowd comprises a plurality of candidate users;
acquiring a seed population; the seed crowd comprises a plurality of seed users;
determining a target candidate group in the candidate group according to the target characteristic information corresponding to each candidate user in the candidate group and the seed group;
and delivering information to the target candidate group.
2. The method of claim 1, wherein determining a target candidate population in the candidate population based on the target feature information corresponding to each candidate user in the candidate population and the seed population comprises:
clustering the plurality of seed users according to the target characteristic information corresponding to each seed user in the seed population to obtain M clusters; wherein, the central point of each cluster is used as a cluster central user; m is an integer greater than or equal to 2;
determining the association degree corresponding to each candidate user according to the target characteristic information corresponding to each candidate user in the candidate population and the target characteristic information corresponding to the M cluster center users;
and determining the target candidate group by the candidate users corresponding to the first N relevance degrees according to the sequence of the relevance degrees from large to small.
3. The method according to claim 2, wherein the determining the relevancy of each candidate user according to the target feature information corresponding to each candidate user in the candidate population and the target feature information corresponding to the M cluster center users comprises:
calculating the association degree between the target characteristic information corresponding to any one candidate user in the candidate population and the target characteristic information corresponding to each clustering center in the M clustering center users respectively to obtain M association degrees;
and determining the average value of the M association degrees as the association degree corresponding to the candidate user.
4. The method of claim 1, wherein said obtaining a population of seeds comprises:
acquiring an initial seed population;
and screening the initial seed population according to the target characteristic information corresponding to each seed user in the initial seed population to obtain the seed population.
5. The method according to any one of claims 1 to 4,
if the operation instruction comprises the configuration parameters, the candidate crowd comprises users corresponding to the configuration parameters; if the operation instruction comprises the service demand parameter, the candidate crowd comprises the user corresponding to the service demand parameter; if the operation instruction comprises the configuration parameter and the service demand parameter, the candidate crowd comprises an intersection of the user corresponding to the configuration parameter and the user corresponding to the service demand parameter.
6. The method of claim 5, further comprising:
inputting the service characteristics corresponding to each preset user in a preset population into a prediction model to obtain the probability that the preset user meets the service requirement;
and determining the preset users with the probability larger than a preset threshold value as the users corresponding to the service demand parameters.
7. The method according to any one of claims 1 to 4, wherein determining target feature information according to the configuration parameters and/or the traffic demand parameters comprises:
acquiring a plurality of attribute feature information;
and determining the characteristic information corresponding to the configuration parameters and/or the characteristic information corresponding to the service requirement parameters and the attribute characteristic information as the target characteristic information.
8. An information delivery apparatus, comprising:
the receiving module is used for receiving an operation instruction input on an operation interface, wherein the operation instruction comprises configuration parameters and/or service requirement parameters;
the processing module is used for determining candidate crowd and target characteristic information according to the configuration parameters and/or the service demand parameters; the candidate crowd comprises a plurality of candidate users;
the acquisition module is used for acquiring seed crowds; the seed crowd comprises a plurality of seed users;
the processing module is further configured to determine a target candidate group from the candidate groups according to the target feature information corresponding to each candidate user in the candidate groups and the seed group;
and the sending module is used for releasing information to the target candidate group.
9. An electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the information delivery method according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer instructions, which, when run on an electronic device, cause the electronic device to execute the information delivery method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010475888.XA CN113743968A (en) | 2020-05-29 | 2020-05-29 | Information delivery method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010475888.XA CN113743968A (en) | 2020-05-29 | 2020-05-29 | Information delivery method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113743968A true CN113743968A (en) | 2021-12-03 |
Family
ID=78724613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010475888.XA Pending CN113743968A (en) | 2020-05-29 | 2020-05-29 | Information delivery method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743968A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471256A (en) * | 2022-09-01 | 2022-12-13 | 深圳掌屿软件有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN115936719A (en) * | 2023-03-01 | 2023-04-07 | 北京淘友天下技术有限公司 | Identification method, identification device, electronic equipment and computer-readable storage medium |
-
2020
- 2020-05-29 CN CN202010475888.XA patent/CN113743968A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471256A (en) * | 2022-09-01 | 2022-12-13 | 深圳掌屿软件有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN115936719A (en) * | 2023-03-01 | 2023-04-07 | 北京淘友天下技术有限公司 | Identification method, identification device, electronic equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020135535A1 (en) | Recommendation model training method and related apparatus | |
| WO2019242331A1 (en) | User behavior prediction method and apparatus, and behavior prediction model training method and apparatus | |
| US10354184B1 (en) | Joint modeling of user behavior | |
| US8156138B2 (en) | System and method for providing targeted content | |
| WO2021174944A1 (en) | Message push method based on target activity, and related device | |
| US9805391B2 (en) | Determining whether to provide an advertisement to a user of a social network | |
| CN102737333B (en) | For calculating user and the offer order engine to the coupling of small segmentation | |
| CN110807655B (en) | Advertisement bidding method, device and equipment | |
| CN110147882B (en) | Neural network model training method, crowd diffusion method, device and equipment | |
| CN102737334B (en) | Micro-segment definition system | |
| US8209214B2 (en) | System and method for providing targeted content | |
| CN109299356B (en) | Activity recommendation method and device based on big data, electronic equipment and storage medium | |
| US20180247247A1 (en) | Method and system for search provider selection based on performance scores with respect to each search query | |
| CN108921587B (en) | Data processing method and device and server | |
| US10937070B2 (en) | Collaborative filtering to generate recommendations | |
| CN108153909A (en) | Word method, apparatus and electronic equipment, storage medium are opened up in keyword dispensing | |
| CN113032668A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN113743968A (en) | Information delivery method, device and equipment | |
| KR102585895B1 (en) | Method and system for increasing keyword marketing efficiency in open market | |
| CN112287208A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN115809889A (en) | Intelligent passenger group screening method, system, medium and equipment based on marketing effect | |
| CN110689032A (en) | Data processing method and system, computer system and computer readable storage medium | |
| CN116069959A (en) | Method and device for determining display data | |
| CN114119168A (en) | Information pushing method and device | |
| US20210056437A1 (en) | Systems and methods for matching users and entities |
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 |