CN110781379A - Information recommendation method and device, computer equipment and storage medium - Google Patents

Information recommendation method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN110781379A
CN110781379A CN201910847988.8A CN201910847988A CN110781379A CN 110781379 A CN110781379 A CN 110781379A CN 201910847988 A CN201910847988 A CN 201910847988A CN 110781379 A CN110781379 A CN 110781379A
Authority
CN
China
Prior art keywords
user
information
mobile phone
phone number
feature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910847988.8A
Other languages
Chinese (zh)
Inventor
张超亚
蔡健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Priority to CN201910847988.8A priority Critical patent/CN110781379A/en
Publication of CN110781379A publication Critical patent/CN110781379A/en
Priority to PCT/CN2020/106209 priority patent/WO2021047326A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an information recommendation method and device based on data analysis, computer equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining a target recommending user and a mobile phone number of the target recommending user, extracting relevant information of the mobile phone number, wherein the relevant information comprises registration information and interactive data, carrying out feature analysis on the mobile phone number according to the registration information to obtain number features of the mobile phone number, obtaining user feature categories of the target recommending user corresponding to the mobile phone number according to the number features and the interactive data, obtaining main feature labels of old users meeting preset conditions, determining the feature labels of the target recommending user based on the main feature labels of the old users when the preset conditions are met, obtaining information to be recommended corresponding to the feature labels, and recommending the information to the target recommending user. By adopting the method, the accuracy of information popularization aiming at the target recommending user and the acceptance degree of the information to be recommended by the target recommending user can be improved.

Description

Information recommendation method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to an information recommendation method and apparatus, a computer device, and a storage medium.
Background
With the development of computer technology and the popularization of intelligent mobile terminals, more and more application programs are developed and applied to the mobile terminals, and convenience is provided for the life of people. The application background can obtain the user representation by collecting the behavior data of the user using the developed application, including the data of the concrete information, living habits, consumption habits and the like of the user, and further abstract to obtain the user label. In the process that a user uses the application program, the application program background can push information corresponding to the user label to the user based on the user portrait so as to promote the information and improve the viscosity of the user.
However, for some users, such as a newly registered user who just becomes an application, there is not a large amount of behavior data of the newly registered user on the application, so that the user portrait cannot be obtained by the conventional method for the newly registered user, and further, targeted information recommendation cannot be performed for the newly registered user.
Disclosure of Invention
In view of the above, it is necessary to provide an information recommendation method, an apparatus, a computer device, and a storage medium capable of improving the accuracy of sending recommendation information to a target recommendation user in response to the above technical problem.
An information recommendation method, the method comprising:
acquiring a target recommending user, and acquiring a mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
performing feature analysis on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number;
analyzing and processing the number characteristics and the interactive data of the mobile phone number to obtain the user characteristic category of the target recommendation user corresponding to the mobile phone number;
acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class of the old user is the same as that of the target recommendation user when the preset condition is met;
determining a feature tag of the target recommendation user based on the main feature tag of the old user;
and obtaining information to be recommended corresponding to the feature tag according to the feature tag of the target recommending user, and recommending the information to be recommended to the target recommending user.
In one embodiment, the analyzing and processing the number features and the interaction data of the mobile phone number to obtain the user feature category of the target recommended user corresponding to the mobile phone number includes:
acquiring a pre-trained user characteristic category classification model, and inputting the number characteristic of the mobile phone number and the interactive data into the pre-trained user characteristic category classification model; the number features include: operator, home, number segment release time, package promotion feature and number composition feature; the interactive data is interactive data of the mobile phone number and each application platform;
analyzing and processing the number characteristics of the mobile phone number and the interactive data by using the user characteristic category classification model to generate an output result;
and acquiring an output result of the user characteristic category classification model, and taking the output result as the user characteristic category of the mobile phone number.
In one embodiment, the analyzing and processing the mobile phone number feature and the interaction data by using the user feature classification model to generate an output result includes:
acquiring a labeling classification result preset by the user characteristic classification model; the preset labeling classification result comprises a flow user, a call user, a young user and a business user;
acquiring category parameters corresponding to each preset labeling and classifying result; the category parameters comprise a preset operator, a preset attribution, a preset number section release time, a preset package publicity characteristic and a preset number composition characteristic;
comparing the category parameters corresponding to each preset labeling classification result with the number characteristics of the mobile phone number;
and when the number characteristics of the mobile phone number are consistent with the category parameters of the preset labeling classification result, classifying the target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification, and generating an output result.
In one embodiment, the obtaining of the subject feature tag of the old user meeting the predetermined condition includes:
acquiring old users under the same user feature category according to the user feature category to which the target recommendation user belongs;
obtaining the searched user portrait information of each old user, and extracting portrait labels of each old user from the user portrait information;
and determining the main feature label of the old user belonging to the same user feature category according to the portrait label of each old user.
In one embodiment, the obtaining the user portrait information of each of the old users found and extracting the portrait label of each of the old users from the user portrait information includes:
acquiring behavior data of each old user;
performing user portrait according to the behavior data to obtain user portrait information of the old user;
and extracting portrait labels of the old users from the user portrait information.
In one embodiment, the determining the feature tag of the target recommended user based on the subject feature tag of the old user includes:
calculating the similarity between portrait labels of the old users to obtain a distance index;
classifying the portrait labels of the old users according to the distance indexes to obtain portrait label groups;
analyzing and evaluating the portrait label groups of the old users according to a preset evaluation rule to obtain corresponding evaluation results; the preset evaluation rule comprises a cluster analysis rule; the evaluation result is used for representing the quality of a clustering result obtained by clustering analysis of the portrait labels in different portrait label groups;
determining a subject feature tag of each old user from each evaluation result;
and determining the main characteristic label of each old user as the characteristic label of the target recommended user in the same user characteristic category.
In one embodiment, the obtaining, according to the feature tag of the target recommending user, information to be recommended corresponding to the feature tag, and recommending the information to be recommended to the target recommending user includes:
determining a corresponding relation between the feature tag and the message to be recommended from a mapping relation table of the feature tag and the message to be recommended of the target recommending user;
determining and acquiring information to be recommended corresponding to the feature tag according to the corresponding relation between the feature tag and the information to be recommended;
sending the information to be recommended to a target recommending user corresponding to the feature tag; the information to be recommended includes, but is not limited to, application promotion information and product promotion information.
An information recommendation apparatus, the apparatus comprising:
the target recommending user obtaining module is used for obtaining a target recommending user and obtaining the mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
the associated information extraction module is used for extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
the number characteristic acquisition module is used for carrying out characteristic analysis on the mobile phone number according to the registration information to acquire the number characteristic of the mobile phone number;
the user characteristic category acquisition module is used for analyzing and processing the number characteristics and the interactive data of the mobile phone number to acquire the user characteristic category of the target recommendation user corresponding to the mobile phone number;
the main feature tag acquisition module is used for acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class meeting the preset condition is the same as that of the target recommended user;
the characteristic label determining module is used for determining the characteristic label of the target recommendation user based on the main characteristic label of the old user;
and the information recommendation module is used for acquiring information to be recommended corresponding to the feature tag according to the feature tag of the target recommendation user and recommending the information to be recommended to the target recommendation user.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a target recommending user, and acquiring a mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
performing feature analysis on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number;
analyzing and processing the number characteristics and the interactive data of the mobile phone number to obtain the user characteristic category of the target recommendation user corresponding to the mobile phone number;
acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class of the old user is the same as that of the target recommendation user when the preset condition is met;
determining a feature tag of the target recommendation user based on the main feature tag of the old user;
and obtaining information to be recommended corresponding to the feature tag according to the feature tag of the target recommending user, and recommending the information to be recommended to the target recommending user.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a target recommending user, and acquiring a mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
performing feature analysis on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number;
analyzing and processing the number characteristics and the interactive data of the mobile phone number to obtain the user characteristic category of the target recommendation user corresponding to the mobile phone number;
acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class of the old user is the same as that of the target recommendation user when the preset condition is met;
determining a feature tag of the target recommendation user based on the main feature tag of the old user;
and obtaining information to be recommended corresponding to the feature tag according to the feature tag of the target recommending user, and recommending the information to be recommended to the target recommending user.
According to the information recommendation method, the information recommendation device, the computer equipment and the storage medium, the target recommendation user is obtained, when the target recommendation user does not have user portrait information, the mobile phone number of the target recommendation user is obtained, the associated information of the mobile phone number is extracted, the associated information comprises the registration information and the interaction data of the mobile phone number, and the number feature of the mobile phone number is obtained by performing feature analysis on the mobile phone number according to the registration information. The method comprises the steps of analyzing and processing number features and interactive data of a mobile phone number to obtain user feature categories of target recommendation users corresponding to the mobile phone number, and obtaining main feature labels of old users meeting preset conditions, wherein the old users are users with user portrait information, and the user feature categories meeting the preset conditions are the same as those of the target recommendation users. By acquiring the main feature labels of old users in the same user feature category as the target recommending user and taking the acquired main feature labels as the feature labels of the target recommending user, the information to be recommended corresponding to the feature labels is recommended to the target recommending user, so that the accuracy of information popularization for the target recommending user and the acceptance degree of the information to be recommended to the target recommending user are improved.
Drawings
FIG. 1 is a diagram of an application scenario of an information recommendation method in one embodiment;
FIG. 2 is a flow diagram illustrating a method for information recommendation in one embodiment;
FIG. 3 is a block diagram showing an exemplary configuration of an information recommendation apparatus;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The information recommendation method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 and the server 104 communicate via a network. The server 104 acquires a target recommended user, and when the target recommended user does not have user portrait information, acquires a mobile phone number of the target recommended user from the terminal 102, and extracts associated information of the mobile phone number, wherein the associated information comprises registration information and interactive data of the mobile phone number. And performing feature analysis on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number, and performing analysis processing on the number feature and the interactive data of the mobile phone number to obtain the user feature category of the target recommended user corresponding to the mobile phone number. The server 104 obtains the main feature tags of the old users meeting the predetermined conditions, wherein the old users are users with user portrait information, the user feature categories of the old users meeting the predetermined conditions are the same as the user feature categories of the target recommendation users, and the feature tags of the target recommendation users are determined based on the main feature tags of the old users. And then according to the feature tag of the target recommending user, obtaining information to be recommended corresponding to the feature tag, and recommending the information to be recommended to the target recommending user of the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an information recommendation method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s202, a target recommending user is obtained, and when the target recommending user does not have user portrait information, the mobile phone number of the target recommending user is obtained.
Specifically, the user needs to fill in information required for registration through the terminal, register with the server, and become a registered user of the application program. Currently, when registering a user to become an application, it is generally necessary to register the user using a mobile phone number. The mobile phone number has uniqueness, and real-name authentication is performed when the mobile phone number is handled, so that the registration is performed through the mobile phone number, an application program operator can conveniently count the number of users, and real-name information of the users can be acquired. And when registering, the short message verification code is obtained through the mobile phone number, and the server passes the verification according to the short message verification code, so that the user is successfully registered. And when the server detects the successful registration information, acquiring the mobile phone number of the new registered user.
Further, the server acquires a target recommended user within a preset detection time, judges whether the wood recommended user has user portrait information or not, and judges whether the user portrait information is detected or not by detecting the registration information of the terminal and comparing the acquired registration information with all the registration information stored after the last detection is finished, so that whether the detection is carried out or not is judged, and new successful registration information which is not included in the registration information stored last time appears. When new registration information is detected at the terminal and corresponding user portrait information does not exist in a user corresponding to the new registration information, the fact that a new registered user appears in the application program is indicated, the new registered user can be determined as a target recommended user, and then the server can obtain the mobile phone number of the target recommended user.
And S204, extracting the associated information of the mobile phone number, wherein the associated information comprises the registration information and the interactive data of the mobile phone number.
The method comprises the steps that association information corresponding to the mobile phone number is extracted from a terminal, wherein the association information comprises registration information and interactive data of the mobile phone number, and specifically, the registration information comprises an operator, a home location, number section release time, package promotion characteristics and number composition characteristics of the mobile phone number. The interactive data comprises the mobile phone number and interactive information of each large application platform, and comprises application programs, websites, platforms and the like in which the mobile phone number is specifically registered, and even if the registration time is short and the behavior data of the mobile phone number is not obtained, the registration information of the mobile phone number on different platforms or programs can still be used as the interactive information between the target recommendation user and each platform.
And S206, performing characteristic analysis on the mobile phone number according to the registration information to obtain the number characteristic of the mobile phone number.
Specifically, the server analyzes the mobile phone number according to a preset corresponding rule to obtain an operator and an attribution of the mobile phone number, and further can crawl number section release time and package publicity characteristics of the mobile phone number from an official network of the operator. And evaluating the number composition characteristics of the mobile phone number according to the arrangement structure by analyzing the arrangement structure of the mobile phone number.
The preset corresponding rule indicates that the mobile phone number has a certain corresponding rule, the first three digits of the mobile phone number are operators (mobile, linkage and telecommunication), the fourth digit to the seventh digit are area allocation, and the number attribution can be determined according to the four digits. The server can crawl number sections corresponding to mobile phone numbers to release time and package propaganda characteristics from the official network (mobile, communication and telecommunication) of an operator in a network crawler mode. The number section release time is not fixed, a judgment time node can be preset to lock the state of the number section release time, so that the service time length of the corresponding mobile phone number is judged, package propaganda characteristics such as China, world communication, a flow card, a call card and the like can be realized, the flow can be used as a main propaganda characteristic, and the call duration can be used as a main propaganda characteristic.
Further, by analyzing the arrangement structure of the mobile phone number, it is determined whether the mobile phone number has a preset structure or preset continuous digits, and further, the composition characteristics of the number, such as the structures of tail number rules AABB, AAAA, ABAB, or the numbers have continuous digits corresponding to specific harmonic sounds, such as 1314 (one life), 520 (i love you), 1573 (one round the way), 3344 (birth), 888 (hair), etc., are evaluated.
And S208, analyzing and processing the number characteristics and the interactive data of the mobile phone number to obtain the user characteristic category of the target recommendation user corresponding to the mobile phone number.
Specifically, a pre-trained user feature category classification model is obtained, and the number features and the interactive data of the mobile phone number are input into the pre-trained user feature category classification model, wherein the number features comprise: the system comprises an operator, a home location, a number section release time, package propaganda characteristics and number composition characteristics, and interactive data is interactive data of a mobile phone number and each application platform. And analyzing and processing the number features and the interactive data of the mobile phone number by using the user feature category classification model to generate an output result, acquiring the output result of the user feature category classification model, and taking the output result as the user feature category of the mobile phone number.
The server can obtain the user characteristic category of the target recommended user corresponding to the mobile phone number according to the operator, the attribution, the number section release time, the package publicity characteristic and the number composition characteristic of the mobile phone number. The user feature categories include traffic users, call users, young users, and business users.
Further, the server combines the operator, the attribution, the number section release time, the package publicity characteristics and the number of the mobile phone number into a user characteristic category classification model with characteristic input pre-trained, the user characteristic category classification model is obtained according to the labeling classification result of the sample data and the sample data training, and the user characteristic category of the mobile phone number output by the user characteristic category classification model is obtained. The sample data comprises an operator of a sample mobile phone number, a home location, number segment release time, package publicity characteristics and number composition characteristics, and the labeling and classifying result comprises a flow user, a call user, a young user and a business user.
The user feature class classification model is obtained by training according to the labeling classification result of the sample data and the sample data, that is, the server obtains the labeling classification result of the user feature class to which the mobile phone number of the old user belongs by obtaining the user feature classes to which the mobile phone numbers of the old user belong on the application program platform and performing labeling classification respectively. And training by using the obtained labeling classification result of the user characteristic class to which the mobile phone number of the old user belongs and the user characteristic class to which the mobile phone number of the old user belongs to obtain a user characteristic class classification model.
S210, acquiring a main feature label of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature type meeting the preset adjustment is the same as that of a target recommendation user.
Specifically, the server acquires old users under the same user feature category according to the user feature category to which the target recommendation user belongs, acquires the found user portrait information of each old user, extracts portrait tags of each old user from the user portrait information, and determines the main feature tags of the old users belonging to the same user feature category according to the portrait tags of each old user. Wherein the old user is a user who has successfully registered and used the application for a period of time, with corresponding user portrait information. And analyzing the number features of the old users by adopting the same number feature analysis method in advance to obtain the number features of the old users in the platform. Since the old user has used the application for a while, the behavior data of the old user is accumulated during the use of the application by the old user. By acquiring behavior data of an old user and adopting a traditional user portrait method, portrait of the old user is performed according to the behavior data to obtain portrait information of the old user, portrait tags of the old user are obtained according to the portrait information of the user, and the obtained portrait tags of the old user are stored and can be acquired in time when needed. The behavior data of the old user includes specific user information, living habits, consumption habits and other data of the old user.
Further, for the portrait labels of the old users belonging to the same user feature category as the target recommended user, the main feature labels of the old users of the same user feature category can be determined by adopting a median, clustering and mode method. The main feature labels refer to feature labels which are satisfied by users in a certain proportion in old users with the same number features, and can be determined by adopting a median, clustering and subordinate number method.
S212, determining the feature label of the target recommendation user based on the main feature label of the old user. Specifically, a distance index is obtained by calculating the similarity between portrait labels of the old users, and the portrait labels of the old users are classified according to the distance index to obtain a portrait label group. And further, analyzing and evaluating portrait label groups of the old users according to preset evaluation rules to obtain corresponding evaluation results, wherein the preset evaluation rules comprise clustering analysis rules, and the evaluation results are used for expressing the quality of clustering results obtained by clustering analysis of portrait labels in different portrait label groups. And finally, determining the main characteristic label of each old user from each evaluation result, and determining the main characteristic label of each old user as the characteristic label of the target recommended user of the same user characteristic category.
S214, according to the feature tag of the target recommending user, obtaining information to be recommended corresponding to the feature tag, and recommending the information to be recommended to the target recommending user.
Specifically, the corresponding relation between the feature tag and the message to be recommended is determined from a mapping relation table of the feature tag and the message to be recommended of the target recommending user, the message to be recommended corresponding to the feature tag is determined and acquired according to the corresponding relation between the feature tag and the message to be recommended, and then the message to be recommended is sent to the target recommending user corresponding to the feature tag; the information to be recommended includes, but is not limited to, application promotion information and product promotion information.
The server determines the feature label of the target recommendation user according to the main feature labels of the old users of the same user feature category. The target recommending user and the old user have the same user feature type, so that the target recommending user and the old user have commonality in the dimension of the mobile phone number, the feature tag of the target recommending user with the same user feature type is pushed through the main feature tag of the old user, the feature tag can be determined for the target recommending user in the dimension of the number feature under the condition that the behavior data of the target recommending user is less, the corresponding information to be recommended is obtained according to the determined feature tag of the target recommending user, and the information to be recommended is sent to the corresponding target recommending user.
Further, after the feature tag of the target recommending user is determined, production marketing and risk control can be performed on the target recommending user according to the feature tag, for example, promotion information corresponding to the feature tag is acquired and sent to the target recommending user, and the promotion information can be marketing products (various insurance) or advertisements. Because the popularization is carried out based on the characteristic tags, namely the popularization products correspond to the characteristic tags of the target recommendation users, the popularization effect can be improved, and the risk is reduced.
According to the information recommendation method, the target recommendation user is obtained, when the target recommendation user does not have user portrait information, the mobile phone number of the target recommendation user is obtained, the associated information of the mobile phone number is extracted, the associated information comprises registration information and interactive data of the mobile phone number, and feature analysis is carried out on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number. The method comprises the steps of analyzing and processing number features and interactive data of a mobile phone number to obtain user feature categories of target recommendation users corresponding to the mobile phone number, and obtaining main feature labels of old users meeting preset conditions, wherein the old users are users with user portrait information, and the user feature categories meeting the preset conditions are the same as those of the target recommendation users. By acquiring the main feature labels of old users in the same user feature category as the target recommending user and taking the acquired main feature labels as the feature labels of the target recommending user, the information to be recommended corresponding to the feature labels is recommended to the target recommending user, so that the accuracy of information popularization for the target recommending user and the acceptance degree of the information to be recommended to the target recommending user are improved.
In one embodiment, the step of analyzing and processing the number features and the interactive data of the mobile phone number to obtain the user feature category to which the target recommendation user corresponding to the mobile phone number belongs includes:
acquiring a pre-trained user characteristic category classification model, and inputting the number characteristics of the mobile phone number and interactive data into the pre-trained user characteristic category classification model; the number features include: operator, home, number segment release time, package promotion feature and number composition feature; the interactive data is interactive data of the mobile phone number and each application platform;
analyzing and processing the number characteristics and the interactive data of the mobile phone number by using a user characteristic category classification model to generate an output result;
and acquiring an output result of the user characteristic category classification model, and taking the output result as the user characteristic category of the mobile phone number.
Specifically, the preset labeling classification results of the user characteristic classification model are obtained, wherein the preset labeling classification results comprise flow users, call users, young users and business users, and the classification parameters corresponding to the preset labeling classification results are obtained, wherein the classification parameters comprise preset operators, preset attributions, preset number segment release time, preset package publicity characteristics and preset number composition characteristics. And when the number characteristics of the mobile phone number are consistent with the category parameters of the preset labeling classification results, classifying the target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification to generate an output result.
The mobile phone number has a certain corresponding rule, the first three digits of the mobile phone number are operators (mobile, linkage and telecommunication), the fourth digit to the seventh digit are area allocation, and the number attribution can be determined according to the four digits. The server can crawl number sections corresponding to mobile phone numbers to release time and package propaganda characteristics from the official network (mobile, communication and telecommunication) of an operator in a network crawler mode. The number section release time is not fixed, a judgment time node can be preset to lock the state of the number section release time, so that the service time length of the corresponding mobile phone number is judged, package propaganda characteristics such as China, world communication, a flow card, a call card and the like can be realized, the flow can be used as a main propaganda characteristic, and the call duration can be used as a main propaganda characteristic.
Further, the user feature class classification model is obtained by training according to the labeling classification result of the sample data and the sample data, that is, the server obtains the labeling classification result of the user feature class to which the mobile phone number of the old user belongs by obtaining the user feature class to which the mobile phone numbers of the old user belong on the application platform and performing labeling classification respectively. And training by using the obtained labeling classification result of the user characteristic class to which the mobile phone number of the old user belongs and the user characteristic class to which the mobile phone number of the old user belongs to obtain a user characteristic class classification model.
In the above steps, the server may analyze and process the operator, the attribution, the number segment release time, the package publicity characteristics and the number composition characteristics of the mobile phone number by using a preset user characteristic category classification model, to obtain the user characteristic category to which the new registered user of the mobile phone number belongs. The method realizes the preliminary inference on the target recommendation user, obtains the user characteristic category to which the target recommendation user belongs, and is beneficial to subsequently realizing the information recommendation on the target recommendation user.
In one embodiment, the step of generating an output result by analyzing and processing the operator, the attribution, the number segment release time, the package publicity feature and the number composition feature respectively by using the user feature classification model includes:
acquiring a labeling classification result preset by a user characteristic classification model; the preset labeling classification result comprises a flow user, a call user, a young user and a business user; acquiring category parameters corresponding to each preset labeling and classifying result; the category parameters comprise a preset operator, a preset attribution, a preset number section release time, a preset package propaganda characteristic and a preset number composition characteristic; comparing the category parameters corresponding to the preset labeling classification results with the number characteristics of the mobile phone number; and when the number characteristics of the mobile phone number are consistent with the category parameters of the preset labeling classification result, classifying the target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification, and generating an output result.
Specifically, the user feature category classification model is preset with labeling classification results, including traffic users, call users, young users and business users, and the classification parameters corresponding to different labeling classification results are different. For example, for a traffic user, the preset package advertisement feature of the traffic user should be mainly based on traffic, and relatively speaking, the preset advertisement feature of the call user should be mainly based on call duration. The preset number segment playing time of the young user is a newer date, and the number segment playing time of the business user is before the number segment playing time of the young user. By comparing the category parameter corresponding to each preset labeling classification result with the number characteristic of the mobile phone number, when the number characteristic of the mobile phone number accords with the category parameter of the preset labeling classification result, the new registered user corresponding to the mobile phone number can be classified into the corresponding preset labeling classification. That is, if the number feature of the mobile phone number conforms to any one of the traffic user, the call user, the young user or the business user in the labeling classification result, the new registered user of the mobile phone number is classified into the corresponding labeling classification.
And when the number characteristics of the mobile phone number are consistent with the preset category parameters of the labeling classification results, classifying a target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification to generate an output result. The method and the device realize the rapid classification of the target recommendation users of the mobile phone numbers, can obtain the user characteristic categories to which the target recommendation users belong according to the obtained output results, and improve the working efficiency.
In one embodiment, the step of obtaining the user portrait information of each old user found and extracting the portrait label of each old user from the user portrait information includes:
the server acquires behavior data of the old user; performing user portrait according to the behavior data to obtain user portrait information of an old user; the portrait label of each old user is extracted from the user portrait information.
Specifically, the behavior data of the old user includes data such as specific user information, living habits, consumption habits and the like of the old user, the specific user information of the old user includes, for example, a user name, registration time, a registration reason and the like when the old user registers, the living habits of the old user include a common living place, a login address, login time, usage duration, usage frequency and the like of the old user, and the consumption habits of the old user include data such as a product purchase record, a product browsing record and a product collection record of the old user. The user portrait method of obtaining portrait label of old user is the traditional user portrait method.
In the above step, the portrait label of the old user is obtained by obtaining the behavior data of the old user and performing user portrait on the old user according to the obtained behavior data, so that higher accuracy of the obtained main body feature label of the old user can be realized, and the situation that the obtained main body feature label is not matched with the portrait label of the old user is avoided.
In one embodiment, there is provided a method for obtaining a user feature category to which a new registered user of a mobile phone number belongs according to an operator, a home location, a number segment release time, a package promotion feature and a number composition feature of the mobile phone number, the method comprising the steps of:
the server acquires a preset judgment time node and compares the number section release time with the preset judgment time node;
acquiring a preset grade judgment rule, and judging the number composition characteristics by using the grade judgment rule; the number composition characteristics comprise a first number composition characteristic and a second number composition characteristic;
when the number section release time is behind a preset judgment time node, analyzing package propaganda characteristics; when the package propaganda feature is flow, determining the user feature category to which the corresponding new registered user belongs as a flow user; when the number composition characteristic is judged to be the first number composition characteristic, determining that the user characteristic category to which the corresponding new registered user belongs is a young user;
or
When the number section release time is before a preset judgment time node, analyzing package propaganda characteristics; when the package publicity characteristics are the call time, determining the user characteristic category to which the corresponding new registered user belongs as a call user; and when the number composition characteristic is judged to be the second number composition characteristic, determining the user characteristic category to which the corresponding new registered user belongs as the business user.
The preset judging time node is not unique and can be modified according to the user requirement, and the user characteristic category to which the mobile phone number belongs can be judged according to the set judging time node. The preset grade judgment rules comprise a tail number rule and a harmonic rule, and when the mobile phone numbers with the arrangement structures of AABB, AAAA, ABAB and the like are judged according to the tail number rule, the mobile phone numbers can be 3344 (birth) and 888 (transmission), and can be determined as the second number composition characteristics. Meanwhile, according to the harmony rule, the mobile phone numbers with the arrangement structures such as 1314 (lifetime), 520 (I love you), 1573 (I have a great deal of emotion) and the like are judged to be the first number composition characteristics.
In the above steps, the server judges the user characteristic type according to the number segment release time, package publicity characteristics and number composition characteristics of the mobile phone number, so that the operation of presuming the user characteristic type to which the new registered user of the mobile phone number belongs is realized, and the working efficiency is improved.
In one embodiment, the step of determining the feature tag of the target recommendation user based on the subject feature tag of the old user comprises:
calculating the similarity between portrait labels of old users to obtain a distance index;
classifying the portrait labels of the old users according to the distance indexes to obtain portrait label groups;
analyzing and evaluating the portrait label groups of the old users according to a preset evaluation rule to obtain corresponding evaluation results; the preset evaluation rule comprises a clustering analysis rule; the evaluation result is used for representing the quality of the clustering result obtained by clustering analysis of the portrait labels in different portrait label groups;
determining a main feature label of each old user from each evaluation result;
and determining the main characteristic label of each old user as the characteristic label of the target recommendation user in the same user characteristic category.
Specifically, the portrait labels of the old users may be analyzed by a cluster analysis method to obtain the main feature labels of the old users belonging to the same user feature category as the newly registered user, including a median cluster analysis method, a secondary cluster analysis method, and the like.
The clustering represents a process of classifying unknown data into different classes or clusters according to the similarity degree, and the clustering analysis is used for researching 'class by class', and different statistics and clustering methods can be selected for different purposes and requirements when the clustering analysis is carried out. The system clustering is a common clustering method, and the basic idea is as follows: firstly, respectively regarding n samples (or variables) to be clustered as one type, wherein n types are shared; then, calculating the clustering statistic between every two classes according to a selected method, namely a certain distance (or a similarity coefficient), combining the two classes with the closest relationship into one class, and keeping the rest unchanged to obtain an n-1 class; calculating the distance (or similarity coefficient) between the new class and other classes according to the calculation method, combining the two classes with the closest relationship into one class, and keeping the rest unchanged to obtain n-2 classes; in so doing, each iteration reduces one class until all the last samples (or variables) are classified as one.
Further, the server calculates the similarity between portrait labels of the old users to obtain a distance index. The distance index is a distance function defined for measuring the similarity between data points. Typically, distance metrics need to be more accurate due to the diversity of feature types and feature scales. Just as the dissimilarity between different objects can be assessed by defining a distance metric in the feature space, the idea for characterizing different data can also be applied to image clusters.
Clustering or grouping is the process of dividing data objects into different classes, and the dividing method usually starts with initial division and optimizing a clustering criterion, which can be used to measure the similarity between different classes or measure the separability of a column to merge or classify a class. Similarly, the portrait tags of the old users are classified according to the distance index, and a portrait tag group is obtained.
The preset evaluation rule obtained by the server is a rule for evaluating the quality of the clustering result, and generally, the quality of the clustering result is evaluated by using a class effective index, and the optimal value of the class effective index is expected to be obtained from the real class number. The best value for a particular class valid index, which truly gives the number of classes, is the criterion for determining whether the index is valid. Meanwhile, the portrait label groups can be evaluated according to a preset evaluation rule to obtain a corresponding evaluation result, namely an evaluation result of the quality of the clustering result, and the main feature labels of old users belonging to the same user feature category can be extracted from the obtained evaluation results.
The server obtains a distance index by calculating the similarity between the portrait labels of the old users, and classifies the portrait labels of the old users according to the distance index to obtain portrait label groups. And evaluating the portrait label groups according to preset clustering analysis by acquiring a preset evaluation rule to obtain a corresponding evaluation result, and extracting the main characteristic labels of the old users belonging to the same user characteristic category from the evaluation result. The method and the device realize that the main characteristic labels of the old users belonging to the same user characteristic category are determined according to the portrait labels of the old users, provide a foundation for subsequent user portrait, and further improve the working efficiency of user portrait.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 3, there is provided an information recommendation apparatus including: a target recommended user obtaining module 302, an associated information extracting module 304, a number feature obtaining module 306, a user feature category obtaining module 308, a main feature tag obtaining module 310, a feature tag determining module 312, and an information recommending module 314, wherein: and the target recommended user obtaining module 302 is configured to obtain a target recommended user, and obtain a mobile phone number of the target recommended user when the target recommended user does not have user portrait information.
The associated information extraction module 304 is used for extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number.
The number feature obtaining module 306 is configured to perform feature analysis on the mobile phone number according to the registration information, so as to obtain a number feature of the mobile phone number.
The user characteristic category obtaining module 308 is configured to analyze and process the number characteristics of the mobile phone number and the interaction data, and obtain a user characteristic category of the target recommended user corresponding to the mobile phone number.
The main feature tag obtaining module 310 is configured to obtain a main feature tag of an old user meeting a predetermined condition, where the old user is a user with user portrait information, and the user feature category of the old user meeting the predetermined condition is the same as the user feature category of the target recommended user.
And a feature tag determining module 312, configured to determine a feature tag of the target recommended user based on the main feature tag of the old user.
And the information recommendation module 314 is configured to obtain information to be recommended corresponding to the feature tag according to the feature tag of the target recommendation user, and recommend the information to be recommended to the target recommendation user.
According to the information recommendation device, the main characteristic labels of the old users in the same user characteristic category as the target recommendation user are obtained, the obtained main characteristic labels are used as the characteristic labels of the target recommendation user, and the information to be recommended corresponding to the characteristic labels is recommended to the target recommendation user, so that the accuracy of information popularization for the target recommendation user is improved, and the acceptance degree of the information to be recommended by the target recommendation user is improved.
In one embodiment, the user feature category obtaining module is further configured to:
acquiring a pre-trained user characteristic category classification model, and inputting the number characteristics of the mobile phone number and interactive data into the pre-trained user characteristic category classification model; the number features include: operator, home, number segment release time, package promotion feature and number composition feature; the interactive data is interactive data of the mobile phone number and each application platform; analyzing and processing the number characteristics and the interactive data of the mobile phone number by using a user characteristic category classification model to generate an output result; and acquiring an output result of the user characteristic category classification model, and taking the output result as the user characteristic category of the mobile phone number.
The server can presume the user characteristic category of the target recommended user of the mobile phone number according to the operator, the attribution, the number section release time, the package propaganda characteristic and the number composition characteristic of the mobile phone number. The method realizes the preliminary inference of the target recommended user, obtains the user characteristic category to which the target recommended user belongs, and is beneficial to the subsequent realization of user portrayal of a new registered user.
In one embodiment, the output result generation unit is to:
acquiring a labeling classification result preset by a user characteristic classification model; the preset labeling classification result comprises a flow user, a call user, a young user and a business user; acquiring category parameters corresponding to each preset labeling and classifying result; the category parameters comprise a preset operator, a preset attribution, a preset number section release time, a preset package propaganda characteristic and a preset number composition characteristic; comparing the category parameters corresponding to the preset labeling classification results with the number characteristics of the mobile phone number; and when the number characteristics of the mobile phone number are consistent with the category parameters of the preset labeling classification result, classifying the target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification, and generating an output result.
The output result generating unit may compare the category parameter corresponding to the labeling classification result preset by the user characteristic category classification model with the number characteristic of the mobile phone number, and when the number characteristic of the mobile phone number is consistent with the category parameter of the preset labeling classification result, classify the target recommended user corresponding to the mobile phone number into the corresponding preset labeling classification to obtain the output result.
In one embodiment, the subject feature tag obtaining module is further configured to:
according to the user feature category to which the target recommendation user belongs, acquiring old users under the same user feature category; acquiring the found user portrait information of each old user, and extracting portrait labels of each old user from the user portrait information; and determining the main feature labels of the old users belonging to the same user feature category according to the portrait labels of the old users.
The main characteristic label acquisition module realizes the relation between the new registered user and the old user, can acquire the portrait label of the old user with the same user characteristic category by acquiring the old user with the same user characteristic category as the new registered user, further acquires the main characteristic label of the old user, and improves the working efficiency of subsequent portrait of the user.
In one embodiment, the subject feature tag obtaining module is further configured to:
acquiring behavior data of each old user; performing user portrait according to the behavior data to obtain user portrait information of an old user; the portrait label of each old user is extracted from the user portrait information. The main body feature tag acquisition module acquires the behavior data of the old user, and performs user portrait on the old user according to the acquired behavior data to obtain the portrait tag of the old user, so that higher accuracy of the acquired main body feature tag of the old user can be realized, and the situation that the acquired main body feature tag is not matched with the portrait tag of the old user is avoided.
In one embodiment, the user feature category determination module is to:
acquiring a preset judgment time node, and comparing the number segment release time with the preset judgment time node; acquiring a preset grade judgment rule, and judging the number composition characteristics by using the grade judgment rule; the number composition characteristics comprise a first number composition characteristic and a second number composition characteristic;
when the number section release time is behind a preset judgment time node, analyzing package propaganda characteristics; when the package propaganda feature is flow, determining the user feature category to which the corresponding new registered user belongs as a flow user; when the number composition characteristic is judged to be the first number composition characteristic, determining that the user characteristic category to which the corresponding new registered user belongs is a young user;
or
When the number section release time is before a preset judgment time node, analyzing package propaganda characteristics; when the package publicity characteristics are the call time, determining the user characteristic category to which the corresponding new registered user belongs as a call user; and when the number composition characteristic is judged to be the second number composition characteristic, determining the user characteristic category to which the corresponding new registered user belongs as the business user.
According to the user characteristic type determining module, the server judges the user characteristic type according to the number section release time, package propaganda characteristics and number composition characteristics of the mobile phone number, so that the determining operation of the user characteristic type of the newly registered user of the mobile phone number is realized, and the working efficiency is improved.
In one embodiment, the feature tag determination module is further to:
calculating the similarity between portrait labels of old users to obtain a distance index; classifying the portrait labels of the old users according to the distance indexes to obtain portrait label groups; analyzing and evaluating the portrait label groups of the old users according to a preset evaluation rule to obtain corresponding evaluation results; the preset evaluation rule comprises a clustering analysis rule; the evaluation result is used for representing the quality of the clustering result obtained by clustering analysis of the portrait labels in different portrait label groups; determining a main feature label of each old user from each evaluation result; and determining the main characteristic label of each old user as the characteristic label of the target recommendation user in the same user characteristic category.
The characteristic label determining module realizes that the main characteristic labels of the old users belonging to the same user characteristic category are determined according to the portrait labels of the old users, provides a foundation for subsequent user portrait, and further improves the working efficiency of user portrait.
In one embodiment, the information recommendation module is further to:
determining a corresponding relation between a feature tag and a message to be recommended from a mapping relation table of the feature tag and the message to be recommended of a target recommending user; determining and acquiring information to be recommended corresponding to the feature tag according to the corresponding relation between the feature tag and the information to be recommended; sending the information to be recommended to a target recommending user corresponding to the feature tag; the information to be recommended includes, but is not limited to, application promotion information and product promotion information.
The information recommendation module sends the information to be recommended corresponding to the feature tag to the target recommendation user by acquiring the corresponding relation between the feature tag of the target recommendation user and the information to be recommended, so that targeted information popularization can be realized, and the acceptability of the information to be recommended is improved.
For specific limitations of the information recommendation device, reference may be made to the above limitations of the information recommendation method, which are not described herein again. The modules in the information recommendation device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is for storing user portrait data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an information recommendation method.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the above-described method embodiments when the processor executes the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the respective method embodiment as described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. An information recommendation method, the method comprising:
acquiring a target recommending user, and acquiring a mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
performing feature analysis on the mobile phone number according to the registration information to obtain the number feature of the mobile phone number;
analyzing and processing the number characteristics and the interactive data of the mobile phone number to obtain the user characteristic category of the target recommendation user corresponding to the mobile phone number;
acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class of the old user is the same as that of the target recommendation user when the preset condition is met;
determining a feature tag of the target recommendation user based on the main feature tag of the old user;
and obtaining information to be recommended corresponding to the feature tag according to the feature tag of the target recommending user, and recommending the information to be recommended to the target recommending user.
2. The method according to claim 1, wherein the analyzing the number features and the interaction data of the mobile phone number to obtain the user feature category of the target recommended user corresponding to the mobile phone number comprises:
acquiring a pre-trained user characteristic category classification model, and inputting the number characteristic of the mobile phone number and the interactive data into the pre-trained user characteristic category classification model; the number features include: operator, home, number segment release time, package promotion feature and number composition feature; the interactive data is interactive data of the mobile phone number and each application platform;
analyzing and processing the number characteristics of the mobile phone number and the interactive data by using the user characteristic category classification model to generate an output result;
and acquiring an output result of the user characteristic category classification model, and taking the output result as the user characteristic category of the mobile phone number.
3. The method according to claim 2, wherein the analyzing the mobile phone number feature and the interaction data by using the user feature classification model to generate an output result comprises:
acquiring a labeling classification result preset by the user characteristic classification model; the preset labeling classification result comprises a flow user, a call user, a young user and a business user;
acquiring category parameters corresponding to each preset labeling and classifying result; the category parameters comprise a preset operator, a preset attribution, a preset number section release time, a preset package publicity characteristic and a preset number composition characteristic;
comparing the category parameters corresponding to each preset labeling classification result with the number characteristics of the mobile phone number;
and when the number characteristics of the mobile phone number are consistent with the category parameters of the preset labeling classification result, classifying the target recommendation user corresponding to the mobile phone number into the corresponding preset labeling classification, and generating an output result.
4. The method of claim 1, wherein the obtaining of the subject feature labels of the old users meeting the predetermined condition comprises:
acquiring old users under the same user feature category according to the user feature category to which the target recommendation user belongs;
obtaining the searched user portrait information of each old user, and extracting portrait labels of each old user from the user portrait information;
and determining the main feature label of the old user belonging to the same user feature category according to the portrait label of each old user.
5. The method of claim 4, wherein the obtaining of the user portrait information of each of the old users located and extracting the portrait label of each of the old users from the user portrait information comprises:
acquiring behavior data of each old user;
performing user portrait according to the behavior data to obtain user portrait information of the old user;
and extracting portrait labels of the old users from the user portrait information.
6. The method of claim 4, wherein the determining the feature label of the target recommended user based on the subject feature label of the old user comprises:
calculating the similarity between portrait labels of the old users to obtain a distance index;
classifying the portrait labels of the old users according to the distance indexes to obtain portrait label groups;
analyzing and evaluating the portrait label groups of the old users according to a preset evaluation rule to obtain corresponding evaluation results; the preset evaluation rule comprises a cluster analysis rule; the evaluation result is used for representing the quality of a clustering result obtained by clustering analysis of the portrait labels in different portrait label groups;
determining a subject feature tag of each old user from each evaluation result;
and determining the main characteristic label of each old user as the characteristic label of the target recommended user in the same user characteristic category.
7. The method according to claim 1, wherein the obtaining information to be recommended corresponding to the feature tag according to the feature tag of the target recommending user and recommending the information to be recommended to the target recommending user comprises:
determining a corresponding relation between the feature tag and the message to be recommended from a mapping relation table of the feature tag and the message to be recommended of the target recommending user;
determining and acquiring information to be recommended corresponding to the feature tag according to the corresponding relation between the feature tag and the information to be recommended;
sending the information to be recommended to a target recommending user corresponding to the feature tag; the information to be recommended includes, but is not limited to, application promotion information and product promotion information.
8. An information recommendation apparatus, characterized in that the apparatus comprises:
the target recommending user obtaining module is used for obtaining a target recommending user and obtaining the mobile phone number of the target recommending user when the target recommending user does not have user portrait information;
the associated information extraction module is used for extracting the associated information of the mobile phone number; the associated information comprises registration information and interactive data of the mobile phone number;
the number characteristic acquisition module is used for carrying out characteristic analysis on the mobile phone number according to the registration information to acquire the number characteristic of the mobile phone number;
the user characteristic category acquisition module is used for analyzing and processing the number characteristics and the interactive data of the mobile phone number to acquire the user characteristic category of the target recommendation user corresponding to the mobile phone number;
the main feature tag acquisition module is used for acquiring a main feature tag of an old user meeting a preset condition, wherein the old user is a user with user portrait information, and the user feature class meeting the preset condition is the same as that of the target recommended user;
the characteristic label determining module is used for determining the characteristic label of the target recommendation user based on the main characteristic label of the old user;
and the information recommendation module is used for acquiring information to be recommended corresponding to the feature tag according to the feature tag of the target recommendation user and recommending the information to be recommended to the target recommendation user.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN201910847988.8A 2019-09-09 2019-09-09 Information recommendation method and device, computer equipment and storage medium Pending CN110781379A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910847988.8A CN110781379A (en) 2019-09-09 2019-09-09 Information recommendation method and device, computer equipment and storage medium
PCT/CN2020/106209 WO2021047326A1 (en) 2019-09-09 2020-07-31 Information recommendation method and apparatus, computer device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910847988.8A CN110781379A (en) 2019-09-09 2019-09-09 Information recommendation method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN110781379A true CN110781379A (en) 2020-02-11

Family

ID=69384083

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910847988.8A Pending CN110781379A (en) 2019-09-09 2019-09-09 Information recommendation method and device, computer equipment and storage medium

Country Status (2)

Country Link
CN (1) CN110781379A (en)
WO (1) WO2021047326A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111753203A (en) * 2020-06-24 2020-10-09 中国建设银行股份有限公司 Card number recommendation method, device, equipment and medium
CN112306517A (en) * 2020-03-30 2021-02-02 尼尔森网联媒介数据服务有限公司 Method, device, storage medium and electronic equipment for processing data of application program
WO2021047326A1 (en) * 2019-09-09 2021-03-18 深圳壹账通智能科技有限公司 Information recommendation method and apparatus, computer device, and storage medium
CN113763057A (en) * 2020-05-28 2021-12-07 北京金山云网络技术有限公司 User identity portrait data processing method and device
CN114363216A (en) * 2021-12-31 2022-04-15 上海淇玥信息技术有限公司 Embedded system full-channel flow mapping method and device and electronic equipment
CN114662007A (en) * 2022-05-25 2022-06-24 太平金融科技服务(上海)有限公司深圳分公司 Data recommendation method and device, computer equipment and storage medium
CN114692007A (en) * 2022-06-01 2022-07-01 腾讯科技（深圳）有限公司 Method, device, equipment and storage medium for determining representation information

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113724038A (en) * 2021-08-02 2021-11-30 泰康保险集团股份有限公司 Method, device, equipment and medium for personalized recommendation of insurance products
CN113657941A (en) * 2021-08-20 2021-11-16 北京沃东天骏信息技术有限公司 Policy generation method, generation device, electronic device, and readable storage medium
CN116049553A (en) * 2023-01-28 2023-05-02 北京安录国际技术有限公司 User portrait construction method and system based on multi-source information
CN116484091A (en) * 2023-03-10 2023-07-25 湖北天勤伟业企业管理有限公司 Card information program interaction method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108510402A (en) * 2018-06-06 2018-09-07 中国平安人寿保险股份有限公司 Insurance kind information recommendation method, device, computer equipment and storage medium
CN109493199A (en) * 2019-01-04 2019-03-19 深圳壹账通智能科技有限公司 Products Show method, apparatus, computer equipment and storage medium
CN110097066A (en) * 2018-01-31 2019-08-06 阿里巴巴集团控股有限公司 A kind of user classification method, device and electronic equipment

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190139063A1 (en) * 2017-11-03 2019-05-09 Cars.Com, Llc Methodology of analyzing incidence and behavior of customer personas among users of digital environments
CN109784961A (en) * 2017-11-13 2019-05-21 阿里巴巴集团控股有限公司 A kind of data processing method and device
CN108133013B (en) * 2017-12-22 2021-02-09 平安养老保险股份有限公司 Information processing method, information processing device, computer equipment and storage medium
CN109672986A (en) * 2018-12-18 2019-04-23 成都方未科技有限公司 A kind of space-time big data analysis system
CN110033031B (en) * 2019-03-27 2023-04-18 创新先进技术有限公司 Group detection method, device, computing equipment and machine-readable storage medium
CN110781379A (en) * 2019-09-09 2020-02-11 深圳壹账通智能科技有限公司 Information recommendation method and device, computer equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110097066A (en) * 2018-01-31 2019-08-06 阿里巴巴集团控股有限公司 A kind of user classification method, device and electronic equipment
CN108510402A (en) * 2018-06-06 2018-09-07 中国平安人寿保险股份有限公司 Insurance kind information recommendation method, device, computer equipment and storage medium
CN109493199A (en) * 2019-01-04 2019-03-19 深圳壹账通智能科技有限公司 Products Show method, apparatus, computer equipment and storage medium

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021047326A1 (en) * 2019-09-09 2021-03-18 深圳壹账通智能科技有限公司 Information recommendation method and apparatus, computer device, and storage medium
CN112306517A (en) * 2020-03-30 2021-02-02 尼尔森网联媒介数据服务有限公司 Method, device, storage medium and electronic equipment for processing data of application program
CN113763057A (en) * 2020-05-28 2021-12-07 北京金山云网络技术有限公司 User identity portrait data processing method and device
CN111753203A (en) * 2020-06-24 2020-10-09 中国建设银行股份有限公司 Card number recommendation method, device, equipment and medium
CN114363216A (en) * 2021-12-31 2022-04-15 上海淇玥信息技术有限公司 Embedded system full-channel flow mapping method and device and electronic equipment
CN114363216B (en) * 2021-12-31 2024-02-27 上海淇玥信息技术有限公司 Method and device for mapping all-channel flow of embedded system and electronic equipment
CN114662007A (en) * 2022-05-25 2022-06-24 太平金融科技服务(上海)有限公司深圳分公司 Data recommendation method and device, computer equipment and storage medium
CN114662007B (en) * 2022-05-25 2022-09-02 太平金融科技服务(上海)有限公司深圳分公司 Data recommendation method and device, computer equipment and storage medium
CN114692007A (en) * 2022-06-01 2022-07-01 腾讯科技（深圳）有限公司 Method, device, equipment and storage medium for determining representation information
WO2023231542A1 (en) * 2022-06-01 2023-12-07 腾讯科技（深圳）有限公司 Representation information determination method and apparatus, and device and storage medium

Also Published As

Publication number Publication date
WO2021047326A1 (en) 2021-03-18

Similar Documents

Publication Publication Date Title
CN110781379A (en) Information recommendation method and device, computer equipment and storage medium
CN109241427B (en) Information pushing method, device, computer equipment and storage medium
CN109345302B (en) Machine learning model training method and device, storage medium and computer equipment
CN108711110B (en) Insurance product recommendation method, apparatus, computer device and storage medium
CN109829020B (en) Method and device for pushing place resource data, computer equipment and storage medium
CN109582876B (en) Tourist industry user portrait construction method and device and computer equipment
CN111291264A (en) Access object prediction method and device based on machine learning and computer equipment
CN111192025A (en) Occupational information matching method and device, computer equipment and storage medium
CN110544109A (en) user portrait generation method and device, computer equipment and storage medium
CN112035611B (en) Target user recommendation method, device, computer equipment and storage medium
CN106095939B (en) The acquisition methods and device of account authority
CN112417315A (en) User portrait generation method, device, equipment and medium based on website registration
CN114881712B (en) Intelligent advertisement putting method, device, equipment and storage medium
CN114638633A (en) Abnormal flow detection method and device, electronic equipment and storage medium
CN111192153A (en) Crowd relation network construction method and device, computer equipment and storage medium
CN112685635A (en) Item recommendation method, device, server and storage medium based on classification label
CN113420018A (en) User behavior data analysis method, device, equipment and storage medium
CN112487284A (en) Bank customer portrait generation method, equipment, storage medium and device
CN112258238A (en) User life value cycle detection method and device and computer equipment
WO2021081914A1 (en) Pushing object determination method and apparatus, terminal device and storage medium
CN115311042A (en) Commodity recommendation method and device, computer equipment and storage medium
CN112990989B (en) Value prediction model input data generation method, device, equipment and medium
CN112866295B (en) Big data crawler-prevention processing method and cloud platform system
CN110610378A (en) Product demand analysis method and device, computer equipment and storage medium
CN113742576B (en) Cross-platform-based content recommendation method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination