WO2022127339A1

WO2022127339A1 - Website registration-based user portrait generating method and apparatus, device and medium

Info

Publication number: WO2022127339A1
Application number: PCT/CN2021/124602
Authority: WO
Inventors: 王天宇
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-12-15
Filing date: 2021-10-19
Publication date: 2022-06-23
Also published as: CN112417315A

Abstract

The present application relates to the technical field of big data, and in particular to a website registration-based user portrait generating method, comprising: acquiring a registered website list corresponding to a user, wherein the registered website list is obtained by crawling in advance, from a server of a preset website, a corresponding registration record that comprises a registered user identifier and a registration mark, and classifying the registration record which is characterized and registered with the registration mark according to the user identifier; comparing registered websites in the registered website list with an identifier of a preset classification standard website so as to classify the registered websites; counting the number of registered websites in each classification; and carrying out calculations to obtain a user portrait according to the number of registered websites in each classification.

Description

User portrait generation method, device, device and medium based on website registration

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application filed on December 15, 2020 with the application number 202011473435X and the application name is "method, device, equipment and medium for generating user portraits based on website registration", the entire contents of which are Incorporated herein by reference.

technical field

The present application relates to a method, device, device and medium for generating user portraits based on website registration.

Background technique

With the development of big data technology, various scenarios have appeared. Among them, the construction of user portraits is a relatively important Yangtze River. The construction of user portraits is done by tagging users, dividing customer groups, and building portraits. It helps to deepen the enterprise's understanding of users, so as to provide targeted services and marketing, reduce the marketing cost of the enterprise, and improve the quality and efficiency of the actual business.

However, the inventor realized that the current user portrait needs to extract the user's attribute label (such as education, gender, etc.), and the traditional user portrait method extracts the user's attribute label according to the user's social and usage data on a certain platform, which is easy to Due to the single data and data defects, the accuracy of extracting user attribute labels is low. How to improve the accuracy of extracting user attribute labels has become an urgent problem to be solved.

SUMMARY OF THE INVENTION

According to various embodiments disclosed in the present application, a method, apparatus, device and medium for generating user portraits based on website registration are provided.

A method for generating user portraits based on website registration, comprising:

Obtain a list of registered websites corresponding to the user, and the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID, the registration mark represents the registered registration record. classified;

Comparing the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website;

Count the number of registered websites in each category; and

User portraits are calculated based on the number of registered websites in each category.

A device for generating user portraits based on website registration, comprising:

The website list acquisition module is used to obtain the list of registered websites corresponding to the user, and the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID. The registration mark is obtained by classifying the registered registration records;

A classification module, for comparing the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website;

Statistics module for counting the number of registered websites in each category; and

The portrait generation module is used to calculate the user portrait according to the number of registered websites in each category.

A computer device comprising a memory and one or more processors, the memory having computer-readable instructions stored therein, the computer-readable instructions, when executed by the processor, cause the one or more processors to execute The following steps:

Count the number of registered websites in each category; and

One or more computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps:

Count the number of registered websites in each category; and

The above-mentioned method, device, equipment and medium for generating user portraits based on website registration fully consider the user's website registration situation, and quantify and structure each person's website registration situation, so that user portraits can be obtained according to the user's website registration situation, Improves the accuracy of user portraits.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the present application will be apparent from the description, drawings, and claims.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is an application scenario diagram of a method for generating user portraits based on website registration according to one or more embodiments.

FIG. 2 is a schematic flowchart of a method for generating user portraits based on website registration according to one or more embodiments.

FIG. 3 is a schematic diagram of classification of registration websites according to one or more embodiments.

FIG. 4 is a schematic flowchart according to one or more embodiments of step S208 in the embodiment shown in FIG. 2 .

FIG. 5 is a flowchart according to another or more embodiments of step S208 in the embodiment shown in FIG. 2 .

FIG. 6 is a block diagram of an apparatus for generating user portraits based on website registration according to one or more embodiments.

7 is a block diagram of a computer device in accordance with one or more embodiments.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The method for generating user portraits based on website registration provided by this application can be applied to the application environment shown in FIG. 1 . The terminal 102 communicates with the server 104 through the network. The server 104 can obtain the list of registered websites corresponding to the user from the terminal 102, for example, by traversing the applications installed in the terminal 102 to obtain the list of corresponding registered websites. Use time and installation time to obtain the corresponding registered website list, so that the server 104 can compare the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website, and count The number of registered websites in each category, so as to calculate the user portrait according to the number of registered websites in each category. In this way, the user's website registration situation is fully considered, and each person's website registration situation is quantified and structured, so that the user portrait can be obtained according to the user's website registration situation, which improves the accuracy of the user portrait. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

In one of the embodiments, as shown in FIG. 2 , a method for generating user portraits based on website registration is provided, and the method is applied to the server in FIG. 1 as an example to illustrate, including the following steps:

S202: Obtain a list of registered websites corresponding to the user. The list of registered websites is to crawl the corresponding registration records including the registered user ID and the registration logo from the server of the preset website in advance, and classify the registered registration records representing the registration according to the user ID. owned.

Specifically, the list of registered websites may be obtained according to a preset website, for example, crawling information on whether the corresponding user is registered from the server of each website. In order to ensure the security of the user's privacy, in this embodiment only Obtain the information about whether the user is registered. As for the specific information of registration, it will not be crawled. Preferably, the information about whether the user is registered can be set by means of a flag. If the flag is 0, the user is not registered. Otherwise, The user has been registered, and the registered information of the user is stored in the corresponding user's registered website list. For example, the registered website list is obtained by crawling the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and classifying the registration records representing the registration by the registration mark according to the user ID.

Specifically, the acquiring the list of registered websites corresponding to the user may be connected to the user terminal, acquiring the application programs that have been installed in the user terminal, or being connected to each website server, reading the registered users in each website server, and Generate a list of registered sites.

S204: Compare the registered website in the website registration list with the identification of the standard website of the preset classification, so as to classify the registered website.

Specifically, with reference to FIG. 3 , FIG. 3 is a schematic diagram of classification of registration websites in one embodiment. The server can preset the type of registered website, for example, according to the dimensions of the user portrait, such as four dimensions of wealth, risk, interest, and industry, each dimension includes several different types of website collections, and each collection covers several Register the website. The categories of the websites can be preset, for example, including: insurance practitioner websites, insurance websites, car club websites, programmer websites, movie websites, early childhood education websites, two-dimensional websites, legal websites , high-end hotel websites, public exam websites, airline websites, accounting websites, marriage and love websites, refueling and charging websites, construction websites, fitness websites, teacher websites, financial investment service/information websites, overseas Travel/Quality Tourism Websites, Financial Management Websites, International Students Websites, Papers and Periodical Websites, Travel Websites, Food Websites, Beauty and Skin Care Websites, Cute Pet Websites, Maternal and Baby Websites, Quality Life Websites, Cars Maintenance websites, automobile websites, comprehensive automobile portal websites, luxury websites, photography websites, online loan websites, health websites, doctor websites, game websites, primary and secondary education websites, comprehensive education websites, video site.

The server classifies registration sites according to the above categories. When classifying, the server can compare the logo of the registered website with the logo of the preset standard website to determine the classification of the registered website. The reason why the website logo is used is that the logo adopts the method of serial code, not complicated natural language, which can improve the efficiency of classification.

S206: Count the number of registered websites in each category.

Specifically, when classifying registered websites, the server can set a counter corresponding to each type. When there are registered websites that are classified into this type, the number of the counters is incremented, and after processing the registered website list of the same user is completed , the counter is cleared, so as to complete the statistical work of the number of registered websites.

S208: Calculate and obtain the user portrait according to the number of registered websites in each category.

Specifically, due to the different propaganda efforts of websites of different scales, the number of registrations of some websites is much larger than that of other websites, so it is meaningless to compare the number of registrations between websites. The larger the number of registrations, the more obvious the performance in this dimension. In different scenarios and different models, the data/modeler can introduce the number of registrations of different types of websites as a feature, or use it directly as the threshold of the rule. The specific usage method depends on the scenario. For details, please refer to the following. .

It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned list of registered websites and user portraits, the above-mentioned list of registered websites and user portraits can also be stored in a node of a blockchain.

The above-mentioned method, device, equipment and medium for generating user portraits based on website registration fully consider the user's website registration situation, and quantify and structure each person's website registration situation, so that the user portrait can be obtained according to the user's website registration situation, Improves the accuracy of user portraits.

In one embodiment, referring to FIG. 4 , FIG. 4 is a schematic flowchart of step S208 in the embodiment shown in FIG. 2 . In this embodiment, step S208 is based on the number of registered websites in each category. Calculate the user portrait, including:

S402: Acquire multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to the multiple tags.

S404: Acquire currently registered website types corresponding to each of the multiple scenarios.

Specifically, the corresponding relationship between scenarios and user portraits is established based on business experience in various industries and scenarios. In this embodiment, only four types of application scenarios are set: customer value, product demand, rights and interests, and channels, but the corresponding sub-scenarios are expanded based on 40 website categories. In other embodiments, the application scenarios can be set to more Multiple, wherein the category tags of each scene may include multiple categories, for example, each type of website corresponds to one, or multiple related types of websites correspond to one category tag.

S406: From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type.

S408: Compare the current registration number with a threshold to obtain a label.

Specifically, the method for generating the user portrait may include: if a user's registered website includes 3 luxury websites and 2 international student websites, and based on the accumulated historical data statistics, the average number of registered luxury websites is 1.5 The average number of registrations for international student websites is 0.3. (The specific threshold of each type of website can also be set according to business experience. If the customer's net worth level is required to be higher, the threshold can be appropriately increased before making a judgment), and The person registered well above average for both types of sites, so he added a "Potential High Net Worth Client" label to the user.

S410: Combine the obtained tags to obtain a user portrait.

Specifically, according to the above judgment, multiple tags can be added for the user, and the combination of the multiple tags is the user portrait.

In the above embodiment, the corresponding relationship between the scene and the user portrait is established, so that the scene can be used against the user's registration website, and then the user label can be obtained through the user's registration website, so that the user portrait can be obtained.

In one of the embodiments, referring to FIG. 5, FIG. 5 is a flowchart of another embodiment of step S208 in the embodiment shown in FIG. 2. In this embodiment, step S208, that is, according to each classification The number of registered websites in the user profile is calculated, including:

S502: Acquire the current scene and the currently registered website type corresponding to the current scene.

S504: From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type.

S506: Perform model training according to the current number of registrations to obtain a user portrait model, and obtain a user portrait according to the user portrait model.

Specifically, the current scenario can be set according to the needs of the model, such as a marketing scenario or a risk control scenario, etc. Each scenario corresponds to the corresponding registered website type, and the number of registrations corresponding to the registered website type corresponding to this scenario is obtained. , so that the user portrait model can be obtained by training the model according to the obtained data, for example, adding the obtained number of registered website types to the training data for model training, that is, including other types of features, and adding website Type this feature, which makes the model more complete. Finally, the user portrait is processed according to the model obtained by training.

In one embodiment, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a first feature vector of a first preset dimension according to the current number of registrations; acquiring a second preset dimension generated according to basic user information second feature vector; generating a user portrait model according to the first feature vector and the second feature vector; obtaining the user portrait according to the user portrait model, including: obtaining a user portrait representing the probability of product demand according to the user portrait model; the above method further includes: according to the product The demand probability sorts the users, and pushes the corresponding products to the users according to the sorting.

Specifically, in this embodiment, the number of registered website types is introduced into the model as a feature for prediction/recommendation in different scenarios. For example, if there is an existing demand, it is necessary to find out which people in a batch of customer samples have video membership requirements, that is, to predict who has a higher probability of getting a response by pushing video membership rights, then the "number of registered video websites" can be used as Features are introduced, and model training is performed in combination with other dimensional data. For example, a decision tree model is used to predict the probability of each person's response to the push of rights and interests, and then they are sorted by probability. The business side can choose the top X% of customers for key marketing.

In one embodiment, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a user portrait model based on a scorecard model according to the current number of registrations; obtaining a user portrait according to the user portrait model, including: comparing the current number of registrations with The number of websites in each segment in the scorecard model is compared to determine the user risk score; the corresponding user portrait is obtained according to the user risk score.

Specifically, the above-mentioned embodiment is a marketing scenario, and the marketing scenario uses more decision tree models, while the present embodiment is a risk control scenario, involving more scorecard models based on logistic regression. In the results of the scorecard model, different enumeration values for each feature will correspond to different scores, such as the field X of "number of online loan website registrations". If X=0, the score for this item is 10 points; if 0<X<=3, the score for this item is 7.5 points; if 3<x<=5, the score for this item is 5 points; if 8<x<=10, the score for this item is 2.5 points; if x> 10, the score for this item is 0. The larger the total score of the credit score, the better the credit of the customer, so the user portrait can be obtained according to this setting.

It should be understood that although the steps in the flowcharts of FIGS. 2 , 4 and 5 are sequentially displayed in accordance with the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIG. 2 , FIG. 4 and FIG. 5 may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The order of execution of the sub-steps or phases is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or phases of the other steps.

In one embodiment, as shown in FIG. 6 , a device for generating user portraits based on website registration is provided, including: a website list acquisition module 100, a classification module 200, a statistics module 300 and a portrait generation module 400, wherein:

The website list obtaining module 100 is used to obtain a list of registered websites corresponding to the user. The registered website list is to crawl the corresponding registration records including the registered user ID and the registered logo from the server of the preset website in advance, and to characterize the registered logo according to the user ID. The registered registration records are classified;

The classification module 200 is used to compare the registered website in the website registration list with the identifier of the standard website of the preset classification, so as to classify the registered website;

A statistics module 300 for counting the number of registered websites in each category; and

The portrait generation module 400 is configured to calculate and obtain the user portrait according to the number of registered websites in each category.

In one embodiment, the above-mentioned portrait generation module 400 includes:

a first scene acquisition unit, configured to acquire multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to the multiple tags;

The first currently registered website type acquiring unit is used to acquire the current registered website type corresponding to each of the multiple scenarios;

The quantity selection unit is used to select the current registration quantity corresponding to the current registration website type from the number of registered websites in each category of the statistics;

a comparison unit for comparing the current registration number with a threshold to obtain a label; and

The first portrait generation unit is used for combining the obtained tags to obtain the user portrait.

In one embodiment, the above-mentioned portrait generation module 400 includes:

The second scene obtaining unit is used to obtain the current scene and the currently registered website type corresponding to the current scene;

The second current registered website type acquisition unit is used to select the current registered number corresponding to the current registered website type from the number of registered websites in each category of the statistics; and

The model generation unit is used to perform model training according to the current number of registrations to obtain a user portrait model, and obtain a user portrait according to the user portrait model.

In one embodiment, the above-mentioned model generation unit may include:

The first feature vector generating subunit is used to generate the first feature vector of the first preset dimension according to the current registration quantity;

The second feature vector generating subunit is used to obtain the second feature vector of the second preset dimension generated according to the basic information of the user;

The first model generation subunit is used for generating a user portrait model according to the first feature vector and the second feature vector;

The above-mentioned model generation unit is further configured to obtain a user portrait representing the probability of product demand according to the user portrait model; and

The above-mentioned device for generating user portraits based on website registration may also include:

The push module is used to sort users according to the probability of product demand, and push corresponding products to users according to the sorting.

In one embodiment, the above-mentioned model generation unit may include:

The second model generation subunit is used to generate a user portrait model based on the scorecard model according to the current registration number;

A score calculation subunit for comparing the current number of registrations with the number of sites for each segment in the scorecard model to determine a user risk score; and

The portrait generation sub-unit is used to obtain the corresponding user portrait according to the user risk score.

For specific limitations on the device for generating user portraits based on website registration, please refer to the above limitations on the method for generating user portraits based on website registration, which will not be repeated here. Each module in the above-mentioned device for generating user portrait based on website registration can be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided, and the computer device can be a server, and its internal structure diagram can be as shown in FIG. 7 . The computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media, internal memory. The non-volatile storage medium stores an operating system, computer readable instructions and a database. The internal memory provides an environment for the execution of the operating system and computer-readable instructions in the non-volatile storage medium. The computer device's database is used to store a list of registered websites. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions, when executed by the processor, implement a method for generating user portraits based on website registration.

Those skilled in the art can understand that the structure shown in FIG. 7 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

A computer device, comprising a memory and one or more processors, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the one or more processors perform the following steps: obtaining user corresponding The registered website list, the registered website list is obtained by crawling the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and classifying the registration records representing the registration by the registration mark according to the user ID; The registered websites in the website registration list are compared with the identifiers of the standard websites in the preset classification, so as to classify the registered websites; and count the number of registered websites in each classification; calculate the user according to the number of registered websites in each classification. portrait.

In one embodiment, when the processor executes the computer-readable instructions, the user profile is calculated and obtained according to the number of registered websites in each category, including: acquiring a plurality of preset scenes, a plurality of tags corresponding to each scene, and Thresholds corresponding to multiple labels; obtain the currently registered website types corresponding to multiple scenarios; select the current registered website type corresponding to the current registered website type from the counted number of registered websites in each category; comparing with a threshold to obtain a label; and combining the obtained labels to obtain a user portrait.

In one embodiment, when the processor executes the computer-readable instructions, the user profile is calculated and obtained according to the number of registered websites in each category, including: obtaining the current scene and the current registered website type corresponding to the current scene; From the number of registered websites in each category of the statistics, select the current registration number corresponding to the current registered website type; and perform model training according to the current registration number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.

In one embodiment, when the processor executes the computer-readable instructions, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a first feature vector of a first preset dimension according to the current number of registrations; The second feature vector of the second preset dimension generated by the basic user information; the user portrait model is generated according to the first feature vector and the second feature vector; when the processor executes the computer-readable instruction, the user portrait is obtained according to the user portrait model, The method includes: obtaining user portraits representing product demand probability according to the user portrait model; and when the processor executes the computer-readable instructions, the processor further implements the following steps: sorting users according to the product demand probability, and pushing corresponding products to the users according to the sorting.

In one embodiment, when the processor executes the computer-readable instructions, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a user portrait model based on the scorecard model according to the current number of registrations; and the processor executing Obtaining the user portrait according to the user portrait model realized by the computer readable instruction includes: comparing the current registration number with the number of websites in each segment in the scorecard model to determine the user risk score; obtaining the corresponding user portrait according to the user risk score. .

One or more computer-readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, cause one or more processors to perform the following steps: acquiring a list of registered websites corresponding to the user, The registered website list is obtained by crawling the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and classifying the registration records representing the registration by the registration mark according to the user ID; Compare the registered website of the registered website with the identification of the standard website of the preset classification, so as to classify the registered website; count the number of registered websites in each classification; and calculate the user portrait according to the number of registered websites in each classification.

Wherein, the computer-readable storage medium may be non-volatile or volatile.

In one embodiment, when the computer-readable instructions are executed by the processor, the user profile is calculated and obtained according to the number of registered websites in each category, including: acquiring multiple preset scenes and multiple tags corresponding to each scene and the thresholds corresponding to multiple labels; obtain the current registered website types corresponding to multiple scenarios; select the current registered website type corresponding to the current registered website type from the counted number of registered websites in each category; The number is compared with the threshold to obtain a label; and the obtained labels are combined to obtain a user portrait.

In one embodiment, when the computer-readable instructions are executed by the processor, the user profile is calculated and obtained according to the number of registered websites in each category, including: obtaining the current scene and the current registered website type corresponding to the current scene; From the counted number of registered websites in each category, select the current registered number corresponding to the current registered website type; and perform model training according to the current registered number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.

In one of the embodiments, when the computer-readable instructions are executed by the processor, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a first feature vector of a first preset dimension according to the current number of registrations; obtaining The second feature vector of the second preset dimension generated according to the basic information of the user; the user portrait model is generated according to the first feature vector and the second feature vector; when the computer readable instruction is executed by the processor, the user is obtained according to the user portrait model. The portrait includes: obtaining a user portrait representing the product demand probability according to the user portrait model; and when the processor executes the computer-readable instruction, the processor further implements the following steps: sorting the users according to the product demand probability, and pushing corresponding products to the users according to the sorting.

In one embodiment, when the computer-readable instructions are executed by the processor, performing model training according to the current number of registrations to obtain a user portrait model includes: generating a user portrait model based on the scorecard model according to the current number of registrations; and the computer can Obtaining the user portrait according to the user portrait model realized when the read instruction is executed by the processor includes: comparing the current registration number with the number of websites in each segment in the scorecard model to determine the user risk score; obtaining the corresponding user risk score according to the user risk score. User portrait.

The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage In the medium, the computer-readable storage medium may be volatile or non-volatile, and when the computer-readable instructions are executed, they may include the processes of the foregoing method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

A method for generating user portraits based on website registration, comprising:

Obtain a list of registered websites corresponding to the user, and the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID, the registration mark represents the registered registration record. classified;

Comparing the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website;

Count the number of registered websites in each category; and

User portraits are calculated based on the number of registered websites in each category.
The method according to claim 1, wherein the calculating and obtaining the user portrait according to the number of registered websites in each category comprises:

Obtain multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to multiple tags;

obtaining the current registered website type corresponding to each of the multiple scenarios;

From the counted number of registered websites in each category, select the current registered number corresponding to the type of the current registered website;

comparing the current number of registrations to the threshold to obtain a label; and

The obtained tags are combined to obtain the user portrait.
The method according to claim 1, wherein the calculating and obtaining the user portrait according to the number of registered websites in each category comprises:

Obtain the current scene, and the current registered website type corresponding to the current scene;

From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type; and

Perform model training according to the current registration number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.
The method according to claim 3, wherein the user portrait model obtained by performing model training according to the current registration number comprises:

Generate a first feature vector of a first preset dimension according to the current registration number;

obtaining the second feature vector of the second preset dimension generated according to the basic information of the user;

generating a user portrait model according to the first feature vector and the second feature vector; and

The obtaining of the user portrait according to the user portrait model includes:

obtaining a user portrait representing the probability of product demand according to the user portrait model; and

The method also includes:

The users are sorted according to the product demand probability, and corresponding products are pushed to the users according to the sorting.
The method according to claim 3, wherein the user portrait model obtained by performing model training according to the current registration number comprises:

generating a user profile model based on the scorecard model according to the current number of registrations; and

The obtaining of the user portrait according to the user portrait model includes:

comparing the current number of registrations to the number of websites for each segment in the scorecard model to determine a user risk score;

A corresponding user portrait is obtained according to the user risk score.
A device for generating user portraits based on website registration, wherein the device comprises:

The website list acquisition module is used to obtain the list of registered websites corresponding to the user, and the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID. The registration mark is obtained by classifying the registered registration records;

A classification module, configured to compare the registered website in the website registration list with the identification of the standard website of the preset classification, so as to classify the registered website;

Statistics module for counting the number of registered websites in each category; and

The portrait generation module is used to calculate the user portrait according to the number of registered websites in each category.
The device according to claim 6, wherein the profile generation module comprises:

a first scene acquisition unit, configured to acquire multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to the multiple tags;

a first currently registered website type acquiring unit, configured to acquire the respective current registered website types corresponding to the multiple scenarios;

A quantity selection unit, used for selecting the current registration quantity corresponding to the type of the current registration website from the number of registered websites in each category of the statistics;

a comparison unit for comparing the current registration number with the threshold to obtain a label; and

The first portrait generation unit is used for combining the obtained tags to obtain the user portrait.
The device according to claim 6, wherein the profile generation module comprises:

a second scene acquisition unit, configured to acquire the current scene and the currently registered website type corresponding to the current scene;

The second current registered website type acquisition unit is used to select the current registered number corresponding to the currently registered website type from the counted number of registered websites in each category; and

A model generation unit, configured to perform model training according to the current registration number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.
The apparatus according to claim 8, wherein the model generating unit comprises:

a first feature vector generating subunit, for generating a first feature vector of a first preset dimension according to the current registration number;

The second feature vector generating subunit is used to obtain the second feature vector of the second preset dimension generated according to the basic information of the user;

a first model generation subunit for generating a user portrait model according to the first feature vector and the second feature vector; and

The model generation unit is further configured to obtain a user portrait representing the probability of product demand according to the user portrait model; and

The device for generating user portraits based on website registration also includes:

A push module is configured to sort the users according to the product demand probability, and push corresponding products to the users according to the sorting.
The apparatus according to claim 8, wherein the model generating unit comprises:

A second model generation subunit for generating a user portrait model based on the scorecard model according to the current registration number; and

a score calculation subunit for comparing the current registration number with the number of websites in each segment in the scorecard model to determine a user risk score;

The portrait generation subunit is used to obtain the corresponding user portrait according to the user risk score.
A computer device comprising a memory and one or more processors, the memory having computer-readable instructions stored in the memory that, when executed by the one or more processors, cause the one or more processors to Each processor performs the following steps:

Obtain a list of registered websites corresponding to the user, the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID, the registration mark represents the registered registration record. classified;

Comparing the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website;

Count the number of registered websites in each category; and

User portraits are calculated based on the number of registered websites in each category.
The computer device according to claim 10, wherein the calculating and obtaining the user portrait according to the number of registered websites in each category, which is implemented when the processor executes the computer-readable instructions, comprises:

Obtain multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to multiple tags;

obtaining the current registered website type corresponding to each of the multiple scenarios;

From the counted number of registered websites in each category, select the current registered number corresponding to the type of the current registered website;

comparing the current number of registrations to the threshold to obtain a label; and

The obtained tags are combined to obtain the user portrait.
The computer device according to claim 11, wherein the calculating and obtaining the user portrait according to the number of registered websites in each category, which is implemented when the processor executes the computer-readable instructions, comprises:

Obtain the current scene, and the current registered website type corresponding to the current scene;

From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type; and

Perform model training according to the current registration number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.
computer equipment according to claim 13, wherein, when the processor executes the computer-readable instruction, the described carrying out model training according to the current number of registrations realized to obtain a user portrait model, comprising:

Generate a first feature vector of a first preset dimension according to the current registration number;

obtaining the second feature vector of the second preset dimension generated according to the basic information of the user;

generating a user portrait model according to the first feature vector and the second feature vector; and

The obtaining of the user portrait according to the user portrait model, which is realized when the processor executes the computer-readable instructions, includes:

obtaining a user portrait representing the probability of product demand according to the user portrait model; and

The processor also performs the following steps when executing the computer-readable instructions:

The users are sorted according to the product demand probability, and corresponding products are pushed to the users according to the sorting.
The computer device according to claim 13, wherein the user portrait model obtained by performing model training according to the current registration number, which is implemented when the processor executes the computer-readable instructions, comprises:

generating a user profile model based on the scorecard model according to the current number of registrations; and

The obtaining of the user portrait according to the user portrait model, which is realized when the processor executes the computer-readable instructions, includes:

comparing the current number of registrations to the number of websites for each segment in the scorecard model to determine a user risk score;

A corresponding user portrait is obtained according to the user risk score.
One or more non-volatile computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps:

Obtain a list of registered websites corresponding to the user, the registered website list is to crawl the corresponding registration records including the registered user ID and the registration mark from the server of the preset website in advance, and according to the user ID, the registration mark represents the registered registration record. classified;

Comparing the registered website in the website registration list with the identification of the standard website of the preset classification, to classify the registered website;

Count the number of registered websites in each category; and

User portraits are calculated based on the number of registered websites in each category.
The storage medium according to claim 16, wherein the calculating and obtaining the user portrait according to the number of registered websites in each category, which is implemented when the computer-readable instructions are executed by the processor, comprises:

Obtain multiple preset scenes, multiple tags corresponding to each scene, and thresholds corresponding to multiple tags;

obtaining the current registered website type corresponding to each of the multiple scenarios;

From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type;

comparing the current number of registrations to the threshold to obtain a label; and

The obtained tags are combined to obtain the user portrait.
The storage medium according to claim 16, wherein, when the computer-readable instructions are executed by the processor, the user portrait is calculated according to the number of registered websites in each category, including:

Obtain the current scene, and the current registered website type corresponding to the current scene;

From the counted number of registered websites in each category, select the current registered number corresponding to the currently registered website type; and

Perform model training according to the current registration number to obtain a user portrait model, and obtain a user portrait according to the user portrait model.
The storage medium according to claim 18, wherein, when the computer-readable instructions are executed by the processor, the user portrait model obtained by performing model training according to the current registration number comprises:

Generate a first feature vector of a first preset dimension according to the current registration number;

obtaining the second feature vector of the second preset dimension generated according to the basic information of the user;

generating a user portrait model according to the first feature vector and the second feature vector; and

The obtaining the user portrait according to the user portrait model, which is realized when the computer-readable instructions are executed by the processor, includes:

obtaining a user portrait representing the probability of product demand according to the user portrait model; and

The computer-readable instructions, when executed by the processor, also perform the following steps:

The users are sorted according to the product demand probability, and corresponding products are pushed to the users according to the sorting.
The storage medium according to claim 18, wherein, when the computer-readable instructions are executed by the processor, the user portrait model obtained by performing model training according to the current registration number comprises:

generating a user profile model based on the scorecard model according to the current number of registrations; and

The obtaining the user portrait according to the user portrait model, which is realized when the computer-readable instructions are executed by the processor, includes:

comparing the current number of registrations to the number of websites for each segment in the scorecard model to determine a user risk score;

A corresponding user portrait is obtained according to the user risk score.