TW202312061A - User management devices and methods capable of identifying anonymous users belonging to specific user groups, and storing media storing the methods - Google Patents

Abstract

The purpose of the present invention is how to use anonymous user data to group anonymous users to know which specific user group the anonymous user belongs to. In this way, the enterprise cannot only know which specific user group the real-name user belongs to, but also know which specific user group the anonymous user belongs to. Thus, marketers can use it to facilitate accurate marketing. Specifically, the present invention is to use real-name user data to find out the characteristics of real-name users that are important and meaningful to the specific user group, and then use the real-name user characteristics to map out the anonymous user characteristics corresponding to the specific user group. In this way, whether an anonymous user belongs to the specific user group can be determined based on the anonymous user data.

Description

User management device, method and storage medium for storing the method capable of judging whether an anonymous user belongs to a specific user group

The present invention relates to a user management device, and in particular to a user management device and method capable of judging whether an anonymous user belongs to a specific user group (such as, but not limited to, a high-value user group, a frequent purchase user group, or a high-spending user group) and a storage medium for storing the method.

For online shopping services, during the purchase process, users may go through the process of watching advertisements (for example, advertisements pushed by Facebook or Google), searching the Internet, comparing plans, and deciding to purchase. During the process of viewing advertisements, searching on the Internet and comparing plans, users may not log in as a member, but browse the web in an anonymous manner. On the other hand, many online shopping companies currently allow users to directly purchase goods or services without registering or logging in as a member. Therefore, in a traditional user management system, it is impossible to know whether an anonymous user belongs to a specific user group, such as, but not limited to, a high-value user group, a frequent purchase user group, or a high-spending user group. In addition, general companies will use demographic group statistics methods to distinguish customer groups, and use member data to predict value users, but the two often work independently, so it is still impossible to know which anonymous users in the behavioral characteristics will be potential high-value user groups.

In view of the problems of the previous technology, if the anonymous user can log in to the member in advance, it can be predicted which specific user group the anonymous user belongs to, and the corresponding marketing strategy (such as, but not limited to, giving discounts, giving gifts or giving accumulated discounts), it can effectively increase the willingness of anonymous users to purchase goods or subscribe to services, thereby increasing the transaction amount.

According to the purpose of the present invention, the present invention provides a method capable of judging whether an anonymous user belongs to a specific user group, which is implemented in a user management device, and includes: for a first specific user group of multiple real-name users, obtain the information on all For the first specific user group, a plurality of real-name user features whose importance is greater than a threshold or whose importance is in the top few ranks are used as a plurality of first important real-name user feature sets of the first specific user group First real-name user features, wherein the feature engineering is to find out a plurality of first real-name users of the first important real-name user feature set of the first specific user group based on a machine learning algorithm through the user management device Features; according to the multiple first real-name user features of the first important real-name user feature set of the first specific user group, multiple first important anonymous user feature sets of the first specific user group are mapped A first anonymous user feature, wherein at least a part of the plurality of first anonymous user features is obtained from an anonymous profile of an anonymous user; and according to at least a part of the multiple features obtained from the anonymous profile of the anonymous user A first anonymous user feature determines whether the anonymous user belongs to the first specific user group.

Optionally, the method further includes: using multiple real-name user profiles of the multiple real-name users to group the multiple real-name users, wherein at least a part of the multiple real-name users belong to the first specific user group.

Optionally, using an RFM model (Recency Frequency Monetary Model) to group the multiple real-name users according to the multiple real-name user profiles of the multiple real-name users; A plurality of static features and/or a plurality of dynamic features acquired by the plurality of real-name user data are used to group the plurality of real-name users; or, using a K-MEANS algorithm, a support vector machine algorithm and/or a machine learning algorithm The multiple real-name user groups are grouped according to the multiple real-name user profiles.

Optionally, the method further includes: collecting the multiple real-name user materials of the multiple real-name users, and acquiring the multiple real-name user characteristics of the multiple real-name users according to the multiple real-name user materials .

Optionally, the method further includes: determining a marketing strategy for marketing the anonymous user according to whether the anonymous user belongs to the first specific user group.

Optionally, find out the plurality of first anonymous user characteristics that can be acquired through the anonymous data as a whole from the plurality of first real-name user characteristics.

Optionally, find out the plurality of first anonymous user characteristics that can be acquired through the anonymous data from the plurality of first real-name user characteristics, and combine the plurality of first real-name user characteristics The multiple first real-name user features and their values of the anonymous data acquirer cannot be used as the other multiple first anonymous user features and their values.

Optionally, a grouping model of the anonymous user is trained through the plurality of first anonymous user features, and the grouping model is used to A first anonymous user feature determines whether the anonymous user belongs to the first specific user group.

Optionally, a feature comparison is performed between the multiple first anonymous user features of the anonymous user and the corresponding multiple first real-name user features, so as to determine whether the anonymous user belongs to the first a specific group of users.

Optionally, the feature comparison is to calculate a cosine similarity.

According to the purpose of the present invention, the present invention provides a non-volatile storage medium, which stores a plurality of program codes, and the plurality of program codes are read by a computer device to perform the aforementioned determination of whether an anonymous user belongs to a specific user group Any of the methods of the family.

According to the purpose of the present invention, the present invention provides a user management device capable of judging whether an anonymous user belongs to a specific user group, which is realized by a pure hardware circuit or a computer device with a software, which is configured into multiple modules, and A plurality of modules operate to perform any one of the aforementioned methods capable of determining whether an anonymous user belongs to a specific user group.

Compared with the prior art that cannot conduct precise marketing to anonymous users, the present invention can further conduct precise marketing to anonymous users.

The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.

The user information collected by the enterprise's platform devices usually includes real-name user information (such as the membership information registered by the user on the company's shopping website or membership system) and anonymous user information (for example, the masked or deleted information purchased from a third party). identifiable information, the information of users who have not logged in as registered users or the information of users who have not registered in the company's shopping website or membership system). Furthermore, real-name user information is named user information (for example, member information or verified user information, which can be determined by logging in or third-party verification, etc.), and real-name user information includes unique identification, email, phone number, etc. or device number, which can be traced to a user's personal information, but authenticated user data also includes cookies, Internet Protocol addresses or device identifiers, browsing behavior, device information, interests, demographics, corresponding to a named user data, consumption records, interaction records and accounting records. In contrast, anonymous user data is anonymous user data, including only data such as cookies, Internet protocol addresses or device identification, browsing behavior, device information, interests, etc., and anonymous user data cannot be traced back to the user's personal information.

Generally, enterprises will use real-name user information to group real-name users to determine which specific user group the real-name users belong to. Although it is possible to know where the anonymous user comes from from the IP address of the anonymous user data, it is still impossible to effectively know which specific user group the anonymous user data belongs to. For example, the IP address of the anonymous user data is an overseas IP address, but it is still impossible to know whether the anonymous user must not belong to the high-value user group, frequent purchase user group, and high-spending user group.

The purpose of the present invention is how to use anonymous user data to group anonymous users, so as to know which group in the specific user group the anonymous user belongs to. In this way, the enterprise can not only know which specific user group the real-name user belongs to, but also know the anonymous user. Which specific user group they belong to, so that marketers can use it to facilitate precise marketing. To put it simply, the present invention solves the technical problem that the prior art cannot conduct accurate marketing to anonymous users because it is impossible to know which specific user group the anonymous users belong to.

In the present invention, the real-name user data of a plurality of real-name users is collected first, and then, according to a grouping algorithm (for example, through a machine learning algorithm, but not limited thereto) or using a specific model (for example, RFM model (Recency Frequency Monetary Model, that is, a classification model based on numerical grouping such as recent consumption, consumption frequency, and consumption amount) groups multiple real-name users, and each real-name user belongs to one of the specific user groups. Taking high-value user groups as an example, if you want to know Whether anonymous users also belong to the high-value user group, feature engineering can be performed on the high-value user group to extract the important real-name user feature set corresponding to the high-value user group (which includes multiple real-name users associated with the high-value user group feature). Then, collect the anonymous user data of multiple anonymous users, and obtain multiple anonymous user features that can correspond to one part of the multiple real-name user features of the important real-name user feature set as an important anonymous user feature set. Then, according to the anonymous A user's multiple anonymous user characteristics determine whether an anonymous user belongs to a high-value user group.

The aforementioned features refer to representative data, which can be understood as input parameters or variables. Significant input parameters or variables will affect the final user grouping results (that is, they will affect the prediction results for judging whether users belong to a specific user group). For example, features can be extracted from the user's browsing behavior. Furthermore, the browsing behavior that the user often clicks on the advertisement content after entering the webpage, likes to watch videos, or stays on the webpage for no more than 10 seconds may all be meaningful features.

In addition, the extracted common features can be divided into numerical type, category type and time type in terms of types. The three types of features can be converted to each other, for example, the features of the numerical type can be processed and converted into the features of the time type. The characteristic of the numerical type is to use the statistical description method to divide the overall data range into fractions. The feature of the category type refers to which category it belongs to. For example, the device information may be a laptop, a mobile phone, or a tablet, and which one of the device is a laptop, a mobile phone, or a tablet is the feature of the category type. In addition, the features of the numerical type can also be converted into the features of the category type, or the features of the category type can also be weighted according to the proportion of each category to convert into the features of the numeric type. The characteristics of the time type can be the frequency, number of times or size of numerical characteristics calculated according to methods such as weekly/monthly/quarterly, etc. There are many calculation methods and are not limited by the methods described in the present invention. Simply put, any of the three types of features can be processed to generate features of the other.

First, please refer to FIG. 1 of the present invention. FIG. 1 is a schematic diagram of the corresponding relationship between real-name user features and anonymous user features in an embodiment of the present invention. In this figure, anonymous user data may include device information 301, browsing behavior 302, interests and preferences 303, IP address or device identification 304, and through training algorithms or artificial rules of analysts, it can be defined how to obtain from Device information 301 , browsing behavior 302 , interests 303 , IP address or device identification 304 capture multiple anonymous user characteristics. In addition, real-name user data may include device information 321, browsing behavior 322, interests and preferences 323, IP addresses or device identification 324, demographic data 325, consumption records 326, interaction records 327 and account records 328, and through training Algorithms or artificial rules of analysts can define how to obtain device information 321, browsing behavior 322, interests and preferences 323, IP address or device identification 324, demographic data 325, consumption records 326, interaction records 327 and The account record 328 captures multiple real-name user characteristics.

In a specific user group, multiple real-name users may have some real-name user features that are important and meaningful for a specific user group. Through feature engineering, these real-name user features can be extracted as a specific user group The important real-name user feature set 33 of a specific user group includes, for example, N real-name user features 331-33N. Generally speaking, the number of anonymous user features that can be obtained from anonymous user data will be less than the number of real-name user features that can be obtained from real-name user data. N real-name user features 331-33N are selected to find out the features of the corresponding anonymous user data that can also be obtained. For example, the M anonymous user features 311-31M of the important anonymous user feature set 31 of a specific user group can be obtained from An anonymous user data acquirer, and may also be important and meaningful to a specific user group, where M is usually less than or equal to N, and M and N are positive integers. In this way, it is possible to judge whether an anonymous customer belongs to a specific user group according to the M anonymous user characteristics 311~31M of the anonymous user, and further formulate marketing strategies to promote the success rate of transactions and subscriptions, so as to realize precise marketing of anonymous users the goal of.

Please refer to FIG. 2. FIG. 2 is a block diagram of an online real-name/anonymous user service system using a user management device according to an embodiment of the present invention. The real-name/anonymous user service system 4 shown in Figure 2 can not only provide services to real-name users and anonymous users, but also can provide services to anonymous users by checking whether the anonymous users belong to which specific user group of real-name users. Users conduct precise marketing. The online real-name/anonymous user service system 4 includes a platform device 41, an anonymous user data retrieval device 42, an anonymous user database 43, a real-name user data retrieval device 44 and a user management device 45, wherein the anonymous user data retrieval device 42 signals Connect platform device 41, anonymous user database 43 and real-name user data capture device 44, user management device 45 signal connection anonymous user database 43, real-name user data capture device 44 and platform device 41, and real-name user data capture device 44 signal connection platform device 41. In addition, "signal connection" in the present invention refers to a wireless or wired connection through software or hardware, so that signals or information can be transmitted to each other among multiple components connected by signals.

The anonymous user connects to the platform device 41 via a user terminal device (such as, but not limited to, a mobile phone, a laptop or a tablet), and the platform device 11 can receive data sent by the anonymous user. The platform device 41 may be a Software as a Service (SaaS) server, a web server, or a server that provides services based on applications installed on user terminal devices. The platform device 41 of the online real-name/anonymous user service system 4 can provide services to anonymous users and real-name users, such as online shopping, online transactions, online investment, online subscription or online consultation, etc., and the present invention is not limited thereto . Through the operation of the user terminal device, the user can choose to use the provided services after logging in as a member, or can choose not to log in as a member and use the provided services anonymously.

The anonymous user data capture device 42 will capture the data sent by the anonymous user to obtain anonymous user data, such as small text files, Internet protocol address or device identification, browsing behavior, device information, interests and preferences, etc. , and anonymous user data refers to data that cannot be traced back to the user's personal information. The anonymous user database 43 can be an unstructured database (but the present invention is not limited thereto, it can also be a structured database), and is used to store anonymous user data.

The real-name user data retrieval device 44 is used to retrieve the data sent by the real-name user to obtain the real-name user data, or, the real-name user data retrieval device 44 retrieves the previously anonymously browsed Anonymous user data extracted as part of the real-name user data. The user management device 45 records and analyzes the real-name user information, and based on this, the real-name user can be grouped according to the real-name user information to determine which specific user group the real-name user belongs to.

The user management device 45 can further process the anonymous user data of the anonymous user to find out the characteristics of multiple real-name users of the specific user group of the real-name user that can also be calculated from the anonymous user data, that is, to find out those who can be calculated through the anonymous user data and Anonymous user features corresponding to real-name user features of a specific user group of real-name users. Next, the user management device 45 judges whether the anonymous user belongs to the specific user group of the real-name user according to the characteristics of these anonymous users, and labels these anonymous users (that is, marks the anonymous user as belonging to the specific user group), so as to decide to carry out the anonymous user. Marketing strategy for precise marketing.

The user management device 45 is usually implemented through software in cooperation with a computer device. For example, a computer device includes a computing unit, a storage unit and a communication unit, wherein the computing unit is electrically connected to the storage unit and the communication unit. The computing unit reads multiple program codes stored in the non-volatile storage medium. After the multiple program codes are executed, a method capable of judging whether the anonymous user belongs to a specific user group can be executed. In addition, the user management device 45 can also be realized through hardware circuits, for example, by designing Verilog or VHDL codes to burn Field Programmable Array (FPGA) chips to realize the user management device 45 of pure hardware circuits, and for example , realize the user management device 45 of pure hardware circuit by making an application-specific chip (ASIC). In a word, whether the user management device 45 is implemented by software or hardware is not used to limit the present invention.

Please refer to FIG. 3 of the present invention. FIG. 3 is a block diagram of a user management device capable of judging whether an anonymous user belongs to a specific user group according to an embodiment of the present invention. Regardless of whether the user management device is realized by software or hardware, it can be divided into multiple modules as shown in FIG. 3 . In FIG. 3 , the user management device 5 includes a real-name user grouping module 51, a real-name user feature engineering module 52, an anonymous user feature acquisition module 53, an anonymous/real-name user feature mapping module 54 and an anonymous user grouping module 55, Among them, the real-name user grouping module 51 is signal-connected to the real-name user feature engineering module 52, and the anonymous/real-name user feature mapping module 54 is signal-connected to the real-name user feature engineering module 52, the anonymous user feature acquisition module 53 and the anonymous user grouping module 55, and the anonymous user feature acquisition module 53 is electrically connected to the anonymous user grouping module 55. Of course, the module division in FIG. 3 is only one way to implement the present invention, and the approach in FIG. 3 is not intended to limit the present invention.

Please refer to FIG. 3 and FIG. 4 at the same time. FIG. 4 is a flowchart of a method for determining whether an anonymous user belongs to a specific user group in an embodiment of the present invention. Of course, the flowchart in FIG. 4 is also one of the ways to implement the present invention, and In fact, the execution sequence and details of the entire method flow may be slightly changed according to actual needs, that is, the approach in FIG. 4 is not intended to limit the present invention.

First, in the process S61, the real-name user grouping module 51 performs a step of collecting real-name user data. Specifically, the real-name user grouping module 51 will collect the real-name user data of multiple real-name users and process the real-name user data according to the system calculation results or artificially defined rules to obtain real-name user characteristics, wherein the real-name user data is for example but not limited to It is the above-mentioned various real-name user information, and can also include information such as age, gender, occupation, registration time, RFM parameters, membership level or promotion status, account balance, and the pick-up/delivery method of the products used. Real-name user characteristics are, for example, weekly login frequency, average stay time, weekly home page stay times, or weekly consumption amount, and the present invention is not limited thereto. In different situations, there will be different types of real-name user characteristics.

Next, in the process S62, the real-name user grouping module 51 performs the real-name user grouping step. Specifically, the real-name user grouping module 51 can use a defined model to group a plurality of real-name users, for example, using the RFM model grouping, real-name users can be classified into high-value user groups and high-consumption user groups according to real-name user data. , frequent purchase user group, recent highly active user group or other user groups. In addition to using the RFM model to group real-name users, other model grouping methods can also be used, such as grouping by static features (age, gender, occupation, registration time point), or by dynamic features (RFM parameters, membership levels or promotions) status, account balance, pickup/delivery method of the product used). The way of grouping may be to use algorithms such as K-MEANS algorithm, support vector machine or machine learning (for example, similar neural network) to carry out grouping directly according to the real-name user information of multiple real-name users.

The above-mentioned grouping can be divided into multiple specific user groups, or it can be determined only whether the real-name user belongs to a certain specific user group (for example, only care about whether it is a high-value user group). The above-mentioned grouping can also be grouped for specific activities or single activities. For example, the grouping is to determine whether the real-name user belongs to a specific user group that has participated in various long-term promotional activities for a long time or whether it belongs to a specific user group that participates in a limited amount of one-time idol commodity purchase activities. . In short, neither the grouping method nor the grouping type of the real-name users is used to limit the present invention.

For example, in the case of the membership system commonly used by e-commerce, each real-name user will get a user account after registration, and all future behaviors and activities of the user in the system will be recorded in the system, such as when the user consumes and how much he consumes Money, consumption time, location and items, which pages were clicked before consumption, how many items were put into the shopping cart, how many items were actually purchased, and so on. After obtaining these real-name user data, through grouping methods (for example, RFM model, commodity hobby grouping or activity participation grouping, etc.), it is possible to define which real-name users spend the most, which real-name users spend most often, and which real-name users are very active recently, so that It is possible to define a specific user group that currently has a high degree of contribution to the enterprise.

Afterwards, in the process 63, the real-name user feature engineering module 52 performs the real-name user feature engineering step, so as to extract an important real-name user feature set associated with a specific user group that is interested in the specific user group. Specifically, feature engineering can be implemented through machine learning or statistical algorithms, and the present invention is not limited thereto, as long as at least one real-name user feature associated with a specific user group can be extracted.

Generally speaking, different real-name user characteristics have different importance on whether a real-name user belongs to a specific user group. Therefore, this step is mainly to pick out the important and meaningful real-name user characteristics for a specific user group as the important characteristics of a specific user group. A collection of real-name user features. For example, the real-name user features with the top importance can be selected as the real-name user features in the important real-name user feature set of a specific user group, or the real-name user features whose importance exceeds a certain threshold can be selected as the important real-name user features of a specific user group. The real-name user features in the real-name user feature set.

After knowing which real-name users belong to, for example, high-value user groups and which real-name users do not belong to high-value user groups, you can extract multiple features of real-name users to understand which features are the characteristics of real-name users owned by high-value user groups (that is, to select the important real-name user characteristics for high-value user groups). For example, after feature engineering, the real-name users belonging to the high-value user group are characterized by browsing the web for more than 10 seconds a day, staying on the home page for more than 5 seconds every week, spending more than 1,000 yuan per week, and high-value users. The real-name users of the user group often log in through mobile applications instead of operating computers and logging in on the web, so these real-name user characteristics can be used as an important collection of real-name user characteristics for high-value user groups.

For example, one of the real-name user information may be "ID:0001; 2020-9-1 10:00:05; log in to the homepage; device=iphone12", "ID: 0001; 2020-9-1 10:00:15 ;Leave the homepage; device=iphone12", "ID: 0001; 2020-9-5 14:08:30; log in to the homepage; device=iphone12", "ID: 0001; 2020-9-5 14:08:30; consumption ;Consumption amount=1,000; device=iphone12" and "ID: 0001; 2020-9-1 14: 08:50; leave the homepage; device=iphone12". Through the process S62, the real-name user grouping module 51 can obtain the characteristics of multiple real-name users of "ID:0001" as "weekly login frequency = 2", "average stay time = 15", "weekly home page stay times = 2" and "Weekly consumption amount = 1,000".

After the real-name user information of each real-name user is converted into features, and after each real-name user is grouped (after the execution of process S62), in process S63, machine learning algorithms or statistical algorithms can be used to perform feature engineering, extraction and Confirm what real-name user characteristics are important and meaningful for a specific user group (such as a high-value user group). Usually, feature selection can be carried out, and the first few real-name user features are selected according to the importance score as the important real-name user feature set of a specific user group, and these important real-name user feature sets of a specific user group are important and meaningful for a specific user group Characteristics. Taking the above example as an example, through feature engineering, it can be found that the important and meaningful features of real-name users for high-value user groups are weekly login frequency, average stay time, and weekly consumption amount. For real-name users, the weekly login frequency is greater than 2, the average stay time is greater than 10, and the weekly consumption amount is greater than 100. Important and meaningful features of real-name users for high-value user groups can be used in the subsequent process S66.

In the process S64, the anonymous user feature acquisition module 53 executes the step of collecting anonymous user data to collect the anonymous user data of each anonymous user. Then, in the process S65, the anonymous user feature acquisition module 53 processes the anonymous user data to obtain the anonymous user features, wherein the anonymous user feature is obtained by processing the anonymous user data according to the system operation result or artificially defined rules. Anonymous user characteristics are, for example, weekly login frequency, average stay time, or weekly home page stay times, and the present invention is not limited thereto. In different situations, there will be different types of anonymous user characteristics. Some real-name user characteristics cannot be obtained through anonymous user data. For example, the aforementioned weekly consumption amount is a real-name user characteristic, but anonymous user characteristics do not include weekly consumption amount.

After obtaining the important real-name user feature set of the specific user group and the anonymous user feature of each anonymous user, in the process S66, the anonymous/real-name user feature mapping module 54 finds out one of the important real-name user feature sets in the specific user group What are the characteristics of real-name users that can be acquired through anonymous user data, and the anonymous user characteristics corresponding to these real-name user characteristics are taken as the anonymous user characteristics of the important anonymous user characteristic set in a specific user group (for example, by comparing anonymous user characteristics name and the name of the real-name user feature). For example, for real-name users in the high-value user group, the weekly login frequency is greater than 2, the average stay time is greater than 10, and the weekly consumption amount is greater than 100, but only the weekly login frequency and average The anonymous user characteristics of the dwell time, therefore, the value of the anonymous user characteristics of the anonymous user's weekly login frequency and average dwell time can be used to determine whether the anonymous user also belongs to the high-value user group.

Preferably, in the process S66, the anonymous user features of the important anonymous user feature set can be used for model training, so as to establish a grouping model for judging whether the anonymous user belongs to a specific user group. To put it simply, the process S66 is mainly to find out the important anonymous user feature set that is important and meaningful for a specific user group and can be obtained through the anonymous user data, and use it to train a set of anonymous user features based on the anonymous user A grouping model that judges whether an anonymous user belongs to a specific user group based on the anonymous user characteristics obtained from the data.

Please note here that in the process S66, it is not necessary to additionally train the grouping model, but directly apply the grouping model of real-name users. acquirer) to do feature filling. For example, set the weekly consumption amount to more than 100. In this way, the grouping model of real-name users can be directly applied to group anonymous users to determine whether anonymous users belong to the high-value user group. However, the present invention is not limited thereto. Another approach is to directly compare the features of the approximate parts of the anonymous user data with the real-name user data (for example, calculate the cosine similarity), and directly compare the approximate parts according to the feature comparison results. The corresponding real-name user features are given to anonymous users as anonymous user features to further determine whether anonymous users belong to high-value user groups. Taking Figure 1 as an example, if the feature comparison result of the anonymous user profile and the approximate part of the real-name user profile is highly consistent, then the approximate part of the real-name user profile, such as the corresponding real-name user feature 33N (which cannot be obtained from the anonymous user profile or), directly set the value and provide it to the anonymous user as the feature of the anonymous user.

In short, the method of performing anonymous/real-name user feature mapping in the process S66 is not intended to limit the present invention. The feature set of important anonymous users of a specific user group obtained in process S66 may have the same or different dimensions as the feature set of important real-name users of a specific user group, and may be less than or equal to the dimension of the feature set of important real-name users . Finally, in the process S67, the anonymous user grouping module 55 performs the anonymous user grouping step, which is to determine whether the anonymous user belongs to a specific user group according to the aforementioned anonymous user characteristics and grouping model of the anonymous user. If it is judged that the anonymous user belongs to a specific user group, precise marketing can be carried out on the anonymous user, such as placing advertisements, discount coupons, discounts or promotional activities that are interested in the anonymous user. The method of grouping anonymous users can be achieved by using the grouping model established by the machine learning algorithm mentioned above, or by using a feature comparison algorithm to calculate the similarity between the characteristics of anonymous users and the characteristics of real-name users (for example, cosine similarity) To determine whether an anonymous user belongs to a specific user group.

For example, in process S66, the important real-name user feature set of the high-priced user group includes weekly login frequency, average stay time and weekly consumption amount, and the weekly login frequency is greater than 2, the average stay time and weekly consumption amount are greater than 15 Real-name users with a weekly consumption amount greater than 100 belong to the high-value user group, but because the weekly consumption amount cannot be obtained from anonymous user data, the important anonymous user feature set of the high-value user group includes weekly login frequency and average stay time.

Assume that the anonymous user characteristics of multiple anonymous users may be "ID: COOK0001; weekly login frequency = 2; average stay time = 15", "ID: COOK0002; weekly login frequency = 0.5; average stay time = 7", "ID: COOK0003; weekly login frequency = 1; average stay time = 50", "ID: COOK0004; weekly login frequency = 3; average stay time = 25" and "ID: COOK0005; weekly login frequency = 10; Average dwell time = 50". Then in process S67, the weekly login frequency and average stay time of anonymous user features can be taken to calculate the cosine similarity with the weekly login frequency and average stay time of real-name user features. In this embodiment, the cosine similarity The higher ones are the anonymous users of "ID:COOK0004" and "ID:COOK0005", so the anonymous users of "ID:COOK0004" and "ID:COOK0005" can be determined to belong to the high-value user group.

In addition, in the embodiment of the present invention, each specific user group may have two grouping models. Although the grouping model can be updated at regular intervals, if you do not want to update frequently, you can design one of the grouping models without considering any characteristics related to the event, and the other grouping model considers the characteristics related to the event. For example, if an animation festival is held, the majority of the user group may be students. Therefore, through the Internet address in the anonymous user data, it can be known whether the anonymous user is from a school. If so, then the anonymous user is identified as Students, and the anonymous user characteristics whose occupation is a student are important and meaningful for this grouping model.

In some embodiments, the present invention can implement the modules or methods of the present disclosure through a computer software program, wherein the computer software program is stored in a non-volatile storage medium. The non-volatile storage medium stores the computer software program used to determine the anonymous user data as belonging to the cluster of real-name user data, and after loading the computer software program through the computer, the following steps are performed: obtaining and storing the first real-name user data set, marking the first real-name user data set as the first user cluster, the first real-name user data set contains a plurality of real-name user original data; feature extraction is performed on the first real-name user data set to obtain from the first real-name user data set The real-name user data set generates a first real-name user feature set, wherein the feature extraction of the first real-name user data set includes performing feature importance analysis on the first real-name user data set with a machine learning algorithm to generate the first real-name user data set. Real-name user feature set; obtain and store a first anonymous user data set, the first anonymous user data set includes a plurality of anonymous user original data, perform feature extraction on the first anonymous user data set based on the first real-name user feature set, To generate the first anonymous user feature set, make the first anonymous user feature set as a subset of the first real-name user feature set; perform feature selection on the first anonymous user data set based on the first anonymous user feature set, to generate a second anonymous user data set with the first anonymous user feature set; use the machine learning algorithm to fit the second anonymous user data set to generate an anonymous user grouping model; and use the anonymous user grouping The model predicts the third anonymous user data set, the third anonymous user data set includes at least one anonymous user data, and the anonymous user data predicted as positive cases in the third anonymous user data set are marked as belonging to the first user cluster.

In some embodiments, the present invention can obtain and store the first real-name user data set and the second real-name user data set through a computer program. The first real-name user data set and the second real-name user data set can reflect records of interaction between a plurality of real-name users and a software service, and the software service can be executed by a server. The first real-name user data set and the second real-name user data set may include a first periodic data set and a second periodic data set of a plurality of real-name users respectively corresponding to the first real-name user data set and the second real-name user data set sex dataset. The computer program can perform feature extraction on the first real-name user data set and the second real-name user data set to obtain the first periodic data set and the second periodic data set. The computer program can perform feature engineering on the first real-name user data set and the second real-name user data set respectively, so as to obtain a first feature data set respectively corresponding to the first real-name user data set and the second real-name user data set and the second feature data set. During the feature engineering stage, the computer program can respectively use the first machine learning algorithm to fit the first real-name user data set and the second real-name user data to generate the first feature data set and the A second feature dataset. For the first real-name user data set and the second real-name user data, the computer program can determine the importance of feature data by calculating or finding out the importance of features to perform feature selection to generate the first feature data set and The second characteristic data set. The first feature data set may include a third periodic data set, and the third periodic data set may serve as a subset of the first periodic data set. The second characteristic data set may include a fourth periodic data set, and the fourth periodic data set may serve as a subset of the second periodic data set. The computer program can obtain and store an anonymous user data set, which can include multiple anonymous user data. The anonymous user data set may reflect the records of multiple anonymous users interacting with the software service. The computer program can perform feature comparison between the anonymous user data set and the first feature data set to generate a first anonymous feature data set. The first anonymous feature data set may include a plurality of anonymous features, and these anonymous features may be the same as some features of the first feature data set. The computer program can use a second machine learning algorithm to fit the first anonymous feature data set to generate a first anonymous user grouping model. The second machine learning algorithm can be the same as the first machine learning algorithm. The computer program can perform feature comparison between the anonymous user data set and the second feature data set to generate a second anonymous feature data set. The second anonymous feature data set may include a plurality of anonymous features, and the anonymous features may be the same as some features of the second feature data set. The computer program can use a third machine learning algorithm to fit the second anonymous feature data set to generate a second anonymous user grouping model. The third machine learning algorithm can be the same as the first machine learning algorithm and/or the second machine learning algorithm. The computer program can respectively use the first anonymous user grouping model and the second anonymous user grouping model to predict the anonymous user data set, so as to obtain the first prediction result and the second prediction result respectively corresponding to the two anonymous user grouping models . The computer program can determine that the anonymous user data set is similar to the first anonymous user data set similar to the first real-name user data set according to the first prediction result, and can determine that the anonymous user data set is similar to the first real-name user data set based on the second prediction result. The second anonymous user similar data set to the second real-name user data set. In some examples, the computer program can compare the data quantity of the first anonymous user-similar data set with the data quantity of the second anonymous user-similar data set to determine which anonymous user-similar data set to select for subsequent processing or application. For example, if the amount of data in the second anonymous user similar data set is large, the computer program can select the second anonymous user similar data set. Taking the aforementioned high-value users as an example, the computer program can select the second anonymous user similar data set. Similar datasets are judged to contain anonymous user profiles belonging to high-value user groups.

In some embodiments, the computer program may flag a profile of real-named users as belonging to a particular group of users. Continuing the above example of high-value users, the computer program can mark the first real-name user data set as a high-value user group data set, and the computer program can optionally mark the second real-name user data set as another A data set of a specific user group, such as a data set of a specific group in an RFM group. The computer program can mark the first real-name user data set and the second real-name user data set according to the existing grouping results, so that the first real-name user data set and the second real-name user data set belong to different user groups. In some examples, the computer program predicts the new anonymous user data according to the first anonymous user grouping model and/or the second anonymous user grouping model, and according to the judgment of the above prediction results, the new anonymous user Profiles are tagged to a specific group of users corresponding to their similar set of real-named user profiles. For example, the new anonymous user data can be a single anonymous user data. As another example, the computer program can predict new anonymous user data in real time, near real time and in batches. For another example, the aforementioned batch prediction can be carried out after accumulating several data of a single anonymous user.

In some embodiments, the first feature data set and the second feature data set may include a plurality of feature fields of different data attributes, each of the feature fields includes a plurality of feature values, and each of the plurality of feature fields eigenvalues can form an eigenvalue range. The computer program can calculate or select a characteristic threshold value according to the characteristic value range of each characteristic field. The data in the aforementioned feature data set may include a feature threshold. Each characteristic threshold value can be the maximum value, minimum value, average value, median, mode, percentile, quartile, standard deviation, etc. in the characteristic value range of each characteristic field. According to the attributes of different feature values, the computer program can use different feature threshold judgment rules to determine the feature threshold. For example, the computer program can determine the correlation between the feature value and the target variable or label fitted by the first machine learning algorithm. If the correlation is judged to be positive correlation, the minimum value in the range of feature values can be calculated or selected as the The characteristic threshold value, and if the correlation is judged to be negative correlation, the maximum value in the characteristic value range can be calculated or selected as the characteristic threshold value. Take the feature selection of the above-mentioned high-value users as an example, if the target variable is the consumption amount, the feature is the weekly login frequency, and the minimum value of the feature value range is 2, the computer program can judge that the consumption amount is positively correlated with the weekly login frequency Correlation, the minimum value can be selected as the feature threshold. In some examples, if there is a weak correlation between the target variable and the feature, the computer program can calculate or select the arithmetic mean of the feature value range as the feature threshold. In some examples, if the feature is a count attribute, the computer program may calculate or select the mode of the feature value range as the feature threshold. In some examples, the computer program can set a threshold coefficient h=0, 0.5, 1, 1.8, 2, ... and calculate the product of the statistical data of the characteristic value range and the threshold coefficient as the characteristic threshold value; for example, If h=0.5 is set, the characteristic threshold value of the aforementioned weekly login frequency is 1. The computer program can set the threshold coefficient to adjust the similarity between the characteristics of anonymous users and real-name users, that is, to adjust the relationship between the anonymous user data set and the first real-name user data set and/or the second real-name user data set. similarity, so as to determine the similar information of the first anonymous user and/or the similar information of the second anonymous user. In some examples, the computer program may receive a setting instruction of a characteristic threshold, so as to set the characteristic threshold according to the setting instruction.

In some embodiments, when the computer program determines that the anonymous user data set is similar to the anonymous user similar data set to the real-name user data set based on the aforementioned prediction results, it may determine that the feature data set is at least A characteristic threshold value of a characteristic field, which is used as the basis for judging the similarity between the anonymous user data set and the real-name user data set. In some embodiments, when the computer program performs feature selection, it can determine the feature threshold value of at least one feature field in the feature data set according to the above-mentioned feature threshold value judging rules, so as to perform the anonymous user data set and the first 1. Basis for feature comparison of feature datasets. Taking the aforementioned high-value user as an example, if the feature threshold value of the weekly login frequency is 2, the computer program can determine that the weekly login frequency is greater than The feature threshold data are "ID:COOK0004" and "ID:COOK0005". It should be noted that under normal circumstances, the above-mentioned anonymous feature data set will contain multiple features, so the anonymous feature data set can be an anonymous feature union. When generating the aforementioned anonymous user similar data set or comparing the aforementioned features, you can use The data satisfying the threshold value of all the features of the anonymous feature set is used as the condition for similarity judgment or feature comparison.

In some embodiments, the computer program can use impurity model, entropy model, filtering method, packing method, embedding method, other statistical methods, etc. to calculate the aforementioned feature importance. For example, the computer program can use the feature_importances_ attribute of the scikit-learn machine learning expression library to derive important features. In some embodiments, the aforementioned machine learning algorithm, machine learning model, or anonymous user grouping model is used in a classification method recognized by those skilled in the art. For example, machine learning algorithms or models may include regression models and classification models.

In some embodiments, the aforementioned periodic data set may include data generated by the computer program through iterative calculations for different periods. Different periods may include periods in units of seconds, minutes, hours, days, weeks, months, quarters, years, etc. Different cycles can be obtained by time series analysis such as seasonal analysis. Periodic and/or time-series analysis may be performed by a third-party system or service, and the computer program may obtain different periods, periodic data, or time-series analysis results from the third-party system or service.

Accordingly, the present invention mainly uses the real-name user data of real-name users to obtain a set of important real-name user features of a specific user group, and finds out the anonymous user data of anonymous users to find out whether there are corresponding anonymous user features to determine whether an anonymous user belongs to Specific user groups, in order to further achieve the purpose of precise marketing for anonymous users.

The above descriptions such as "the present invention..." or "the present invention mainly...", the descriptions in the embodiments, the modifications, and the contents disclosed in the drawings are only used to illustrate one or more of the inventions described in the claims. The embodiments or implementation features only express the principle or spirit of the present invention, and are not intended to limit the present invention, nor are they intended to be the only or necessary implementations of the present invention, and there may also be various types of implementations that include different features or implementations according to the spirit of the present invention. Combinations are implemented, so the invention described in the claims is not limited by the content disclosed in the above-mentioned "present invention..." description, embodiments, or drawings. The descriptions in the first claims of this application are merely examples, and the descriptions in the claims can be appropriately changed based on the descriptions in the specification, drawings, and the like.

301: Device Information 302: Browsing behavior 303: hobbies 304: Internet protocol address or device identification 31: Collection of important anonymous user characteristics of specific user groups 311～31M: Anonymous user features 321: Device information 322: Browsing behavior 323: hobbies 324: Internet protocol address or device identification 325: Demographics 326: Consumption record 327: Interactive record 328: Account records 33: Collection of important real-name user characteristics of a specific user group 331～33N: Features of real-name users 4: Online real-name/anonymous user service system 41: Platform device 42: Anonymous user data acquisition device 43:Anonymous user database 44: real-name user data acquisition device 45: User management device 5: User management device 51:Real-name user grouping module 52:Real-name user feature engineering module 53: Anonymous user feature acquisition module 54: Anonymous/real-name user feature mapping module 55: Anonymous user grouping module S61～S67: Process

FIG. 1 is a schematic diagram of the corresponding relationship between real-name user features and anonymous user features in an embodiment of the present invention.

FIG. 2 is a block diagram of an online real-name/anonymous user service system using a user management device according to an embodiment of the present invention.

FIG. 3 is a block diagram of a user management device capable of judging whether an anonymous user belongs to a specific user group according to an embodiment of the present invention.

FIG. 4 is a flowchart of a method capable of judging whether an anonymous user belongs to a specific user group according to an embodiment of the present invention.

S61~S67: Process

Claims (13)

A method capable of judging whether an anonymous user belongs to a specific user group is implemented in a user management device, comprising: Aiming at a first specific user group of a plurality of real-name users, through a feature engineering, a plurality of real-name user features whose importance is greater than a threshold value or whose importance is in the top few ranks for the first specific user group are obtained A plurality of first real-name user features as a first important set of real-name user features of the first specific user group, wherein the feature engineering is to find out the first real-name user features based on a machine learning algorithm through the user management device A plurality of first real-name user characteristics of the first important real-name user characteristic set of a specific user group; According to the multiple first real-name user features of the first important real-name user feature set of the first specific user group, a plurality of first important anonymous user feature sets of the first specific user group are mapped. an anonymous user profile, wherein at least a portion of said plurality of first anonymous user profiles is obtained from an anonymous profile of an anonymous user; and judging whether the anonymous user belongs to the first specific user group according to at least a part of the characteristics of the plurality of first anonymous users obtained from the anonymous information of the anonymous user. The method capable of judging whether an anonymous user belongs to a specific user group as described in claim 1 further includes: grouping the plurality of real-name users by using a plurality of real-name user profiles of the plurality of real-name users, wherein at least a part of the plurality of real-name users belong to the first specific user group. The method for judging whether an anonymous user belongs to a specific user group as described in claim 1, wherein an RFM model (Recency Frequency Monetary Model) is used to analyze the multiple real-name user profiles of the multiple real-name users according to the multiple grouping of real-name users; or, grouping the multiple real-name users according to multiple static features and/or multiple dynamic features obtained from the multiple real-name user profiles of the multiple real-name users; or, using a The K-MEANS algorithm, a support vector machine algorithm and/or a machine learning algorithm group the multiple real-name user groups according to the multiple real-name user profiles. The method capable of judging whether an anonymous user belongs to a specific user group as described in claim 1 further includes: Collecting multiple real-name user materials of the multiple real-name users, and acquiring the multiple real-name user characteristics of the multiple real-name users according to the multiple real-name user materials. The method capable of judging whether an anonymous user belongs to a specific user group as described in claim 1 further includes: A marketing strategy for marketing the anonymous user is determined according to whether the anonymous user belongs to the first specific user group. The method for judging whether an anonymous user belongs to a specific user group as described in claim 1, wherein the multiple first real-name user features that can be acquired through the anonymous data are found as a whole The first anonymous user characteristic. The method for judging whether an anonymous user belongs to a specific user group as described in claim 1, wherein the multiple first real-name user features that can be obtained through the anonymous data as a part are found out. The characteristics of the first anonymous user, and using the characteristics of the first real-name users and their values that cannot pass through the anonymous data acquirer among the characteristics of the first real-name users as other characteristics of the plurality of first anonymous users and its value. The method for judging whether an anonymous user belongs to a specific user group as described in claim 1, wherein a grouping model of the anonymous user is trained through the plurality of first anonymous user characteristics, and the grouping model is used according to the Judging whether the anonymous user belongs to the first specific user group based on at least a part of the characteristics of the plurality of first anonymous users obtained from the anonymous information of the anonymous user. The method capable of judging whether an anonymous user belongs to a specific user group as described in claim 1, wherein the first anonymous user features of the anonymous user are compared with the corresponding first real-name user features feature comparison, so as to determine whether the anonymous user belongs to the first specific user group. The method for judging whether an anonymous user belongs to a specific user group as described in Claim 9, wherein the feature comparison is to calculate a cosine similarity. A non-volatile storage medium, storing a plurality of program codes, the plurality of program codes are read by a computer device to execute the method capable of judging whether an anonymous user belongs to a specific Methods for user groups. A user management device capable of judging whether an anonymous user belongs to a specific user group is realized by a pure hardware circuit or a computer device combined with a software, which is configured into a plurality of modules, and the plurality of modules operate to perform the requested item The method described in one of 1-10 can determine whether an anonymous user belongs to a specific user group. A computer software program product for judging anonymous user data as belonging to a cluster of real-name user data sets, which includes the following steps after being loaded into a computer: Obtaining and storing a first real-name user data set, marking the first real-name user data set as a first user cluster, the first real-name user data set includes a plurality of real-name user original data; performing feature extraction on the first real-name user data set to generate a first real-name user feature set from the first real-name user data set, wherein the feature extraction on the first real-name user data set includes the first real-name user data set Perform feature importance analysis with a machine learning algorithm to generate the first real-name user feature set; Obtaining and storing a first anonymous user data set, the first anonymous user data set includes a plurality of anonymous user raw data, and performing feature extraction on the first anonymous user data set based on the first real-name user feature set to generate a first anonymous user data set A user feature set, making the first anonymous user feature set a subset of the first real-name user feature set; performing feature selection on the first anonymous user data set based on the first anonymous user feature set to generate a second anonymous user data set having the first anonymous user feature set; fitting the second anonymous user data set using the machine learning algorithm to generate an anonymous user segmentation model; and Use the anonymous user grouping model to predict the third anonymous user data set, the third anonymous user data set contains at least one anonymous user data, and mark the anonymous user data predicted as positive cases in the third anonymous user data set as belonging to the The first user cluster.

Images