CN111814052A - Mobile internet user management method, device, server and readable storage medium - Google Patents
Mobile internet user management method, device, server and readable storage medium Download PDFInfo
- Publication number
- CN111814052A CN111814052A CN202010657112.XA CN202010657112A CN111814052A CN 111814052 A CN111814052 A CN 111814052A CN 202010657112 A CN202010657112 A CN 202010657112A CN 111814052 A CN111814052 A CN 111814052A
- Authority
- CN
- China
- Prior art keywords
- information
- recommendation
- feature
- characteristic
- recommended
- 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.)
- Withdrawn
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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a mobile internet user management method, a device, a server and a readable storage medium, after the user management characteristic data list of the target internet user is acquired from the data collection area of the target internet user and the key recommendation characteristic is determined to be contained in the user management characteristic data list, performing decision classification calculation on the key recommendation characteristics to obtain information recommendation characteristic information of the key recommendation characteristics, matching the information recommendation characteristic information with a plurality of preset user behavior label information, judging recommendation frequent characteristics of target internet users, and then configuring an information recommendation process of a target internet user, and recommending information for the user terminal of the target internet user according to the information recommendation process of the target internet user so as to carry out targeted and effective information recommendation for the mobile internet user.
Description
Technical Field
The application relates to the technical field of computers, in particular to a mobile internet user management method, a mobile internet user management device, a mobile internet user management server and a readable storage medium.
Background
How to carry out targeted and effective information recommendation aiming at mobile internet users is a current big problem.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, an object of the present invention is to provide a method, an apparatus, a server and a readable storage medium for managing a mobile internet user, which can perform targeted and effective information recommendation for the mobile internet user.
In a first aspect, the present application provides a mobile internet user management method applied to a server, where the server establishes a unique management list for each user behavior tag information in advance according to a plurality of user behavior tag information, so that the unique management list of each user behavior tag information and information recommendation feature information of a key recommendation feature corresponding to the unique management list establish a one-to-one correspondence, and establishes a user management list in advance according to the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation feature, and each user behavior tag information is matched with information recommendation feature information of at least one key recommendation feature, the method includes:
acquiring a user management characteristic data list of a target internet user from a data collection area of the target internet user, and determining whether the user management characteristic data list contains key recommendation characteristics or not by using an artificial intelligence model;
if the key recommendation features are included, performing decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features;
matching the information recommendation characteristic information of the key recommendation characteristics obtained by calculation with a plurality of preset user behavior label information, and judging recommendation frequent characteristics of the target internet user;
and outputting the information recommendation process of the target internet user according to the recommendation frequency characteristic of the target internet user, and recommending information for the user terminal of the target internet user according to the information recommendation process of the target internet user.
In a possible design of the first aspect, the step of determining whether the user management feature data list includes a key recommendation feature by using an artificial intelligence model includes:
reading common key recommendation characteristic samples from a key recommendation characteristic sample database;
determining key recommendation feature samples to be used from the common key recommendation feature samples according to the service range of the management tag in the user management feature data list;
determining the mobile internet user management range of the information of the object to be recommended according to the key recommendation characteristic sample to be used;
and matching in the user management characteristic data list by utilizing the mobile internet user management range, and if the matching is successful, determining that the user management characteristic data list contains key recommendation characteristics.
In one possible design of the first aspect, the artificial intelligence model is trained by:
reading initial key recommendation characteristic data, wherein each initial key recommendation characteristic data comprises an initial key recommendation characteristic database and various information recommendation characteristic information of the initial key recommendation characteristic database;
extracting key recommendation features from an initial key recommendation feature database;
performing decision classification calculation on the key recommendation characteristics of each initial key recommendation characteristic database according to submodels corresponding to different information recommendation characteristic information in the initial model to obtain the prediction values of a plurality of information recommendation characteristic information of each initial key recommendation characteristic database;
calculating loss degrees of the plurality of information recommendation characteristic information according to the prediction values and the values of the information recommendation characteristic information and different service application types of the information recommendation characteristic information;
summing the loss degrees of the plurality of information recommendation characteristic information to obtain the total loss degree of the plurality of information recommendation characteristic information;
and adjusting parameters of the submodels corresponding to different information recommendation characteristic information in the initial model until the adjusted parameters enable the total loss degree of the information recommendation characteristic information to be smaller than or equal to a preset threshold value, and stopping adjusting to obtain the artificial intelligence model.
In a possible design of the first aspect, the step of outputting the information recommendation process of the target internet user according to the recommended frequent feature of the target internet user includes:
acquiring page access record information on each information recommendation search page accessed by the target internet user according to the recommendation frequency characteristics of the target internet user;
acquiring associated page access record information of each information recommendation search page for other similar target users matched with the target internet user according to the page access record information on each information recommendation search page accessed by the target internet user;
performing decision classification calculation on the associated page access record information to obtain category recommendation characteristic information of the associated page access record information;
judging whether first information recommendation characteristic information and second information recommendation characteristic information exist in the category recommendation characteristic information or not; the matching degree of the first information recommendation characteristic information and the information recommendation characteristic information of the target internet user is greater than a first set matching degree, and the matching degree of the second information recommendation characteristic information and the information recommendation characteristic information of the target internet user is less than a second set matching degree;
if the first information recommendation characteristic information and the second information recommendation characteristic information exist, acquiring a first recommendation frequent characteristic corresponding to the first information recommendation characteristic information of the related internet access user on each information recommendation search page and a second recommendation frequent characteristic corresponding to the second information recommendation characteristic information of the related internet access user;
splicing and fusing the first recommended frequent feature and the second recommended frequent feature to obtain a matched recommended frequent feature;
and matching the matched recommended frequent features with the marked recommended frequent features corresponding to the information recommended search pages, and outputting the information recommendation process of the target internet user according to the matching result.
In a possible design of the first aspect, the step of performing stitching fusion on the first recommended frequent feature and the second recommended frequent feature to obtain a matching recommended frequent feature includes:
determining a common feature node between the first recommended frequent feature and the second recommended frequent feature; the common characteristic node is a starting node for splicing and fusing the first recommended frequent characteristic and the second recommended frequent characteristic;
and splicing and fusing the first recommended frequent feature and the second recommended frequent feature into a matched recommended frequent feature according to the common feature node.
In one possible design of the first aspect, the step of determining a common feature node between the first recommended frequent feature and the second recommended frequent feature includes:
calculating a first frequent feature degree of the first recommended frequent feature and a second frequent feature degree of the second recommended frequent feature;
calculating a difference between the first frequent feature and the second frequent feature; judging whether the difference value is smaller than or equal to a preset value;
if yes, updating any recommended frequent feature in the first recommended frequent feature and the second recommended frequent feature on a feature bit axis to obtain a first recommended frequent feature and a second recommended frequent feature which are identical in final continuous frequent feature degree, and taking the first recommended frequent feature position of the first recommended frequent feature and the second recommended frequent feature which are identical in final continuous frequent feature degree as a common feature node;
if not, respectively crawling the first recommended frequent feature and the second recommended frequent feature by using the same default crawling manner to obtain a first recommended frequent feature position group and a second recommended frequent feature position group;
generating an information recommendation object sequence according to the default crawling mode, the first recommendation frequent feature position group, the second recommendation frequent feature position group and the cross-correlation frequent feature degree; the cross-correlation frequent feature degree is positively correlated with the difference value, and the information recommendation object sequence comprises a plurality of information recommendation object features;
comparing the characteristics of the plurality of information recommendation objects in the information recommendation object sequence, and searching the information recommendation object characteristic with the maximum frequent characteristic degree of the characteristic position;
and taking the recommended frequent feature position corresponding to the information recommendation object feature as a common feature node.
In a possible design of the first aspect, the step of performing feature bit axis update on any one of the first recommended frequent feature and the second recommended frequent feature includes:
if the first frequent feature degree of the first recommended frequent feature is smaller than the second frequent feature degree of the second recommended frequent feature, determining the proportion of the difference value in the first frequent feature degree of the first recommended frequent feature according to the difference value;
calculating a segmentation numerical value of the first recommended frequent feature, and calculating an updating coefficient according to the segmentation numerical value and the proportion;
and according to the updating coefficient, updating any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature on a feature bit axis.
In a second aspect, an embodiment of the present application provides a mobile internet user management apparatus, which is applied to a server, where the server establishes a unique management list for each user behavior tag information in advance according to multiple user behavior tag information, so that the unique management list of each user behavior tag information and information recommendation feature information of a key recommendation feature corresponding to the unique management list are established in a one-to-one correspondence relationship, so as to establish a user management list in advance according to the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation feature, and each user behavior tag information is matched with information recommendation feature information of at least one key recommendation feature, where the apparatus includes:
the acquisition module is used for acquiring a user management characteristic data list of a target internet user from a data collection area of the target internet user and determining whether the user management characteristic data list contains key recommendation characteristics or not by using an artificial intelligence model;
the decision module is used for carrying out decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features if the key recommendation features are included;
the judging module is used for matching the information recommendation characteristic information of the key recommendation characteristics obtained through calculation with a plurality of preset user behavior label information and judging the recommendation frequent characteristics of the target internet user;
and the information recommendation module is used for outputting the information recommendation process of the target internet user according to the recommendation frequency characteristic of the target internet user and recommending information for the user terminal of the target internet user according to the information recommendation process of the target internet user.
In a third aspect, an embodiment of the present application provides a server, including a processor, a memory, and a network interface. The memory and the network interface processor can be connected through a bus system. The network interface is configured to receive a message, the memory is configured to store a program, instructions or code, and the processor is configured to execute the program, instructions or code in the memory to perform the operations of the first aspect or any possible design of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where instructions are stored, and when the instructions are detected on a computer, the instructions cause the computer to perform the method of the first aspect or any possible design manner of the first aspect.
Based on any one aspect, the method comprises the steps of obtaining a user management characteristic data list of a target internet user from a data collection area of the target internet user, determining that the user management characteristic data list contains key recommendation characteristics, carrying out decision classification calculation on the key recommendation characteristics to obtain information recommendation characteristic information of the key recommendation characteristics, matching the information recommendation characteristic information with a plurality of preset user behavior label information, judging recommendation frequent characteristics of the target internet user, configuring an information recommendation process of the target internet user, carrying out information recommendation on a user terminal of the target internet user according to the information recommendation process of the target internet user, and carrying out targeted effective information recommendation on the mobile internet user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic view of an application scenario of a mobile internet user management method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a mobile internet user management method according to an embodiment of the present application;
FIG. 3 is a flow diagram illustrating various sub-steps included in step S140 in one possible design shown in FIG. 2;
fig. 4 is a functional block diagram of a mobile internet user management apparatus according to an embodiment of the present application;
fig. 5 is a block diagram schematically illustrating a structure of a server for performing the above-mentioned mobile internet user management method according to an embodiment of the present invention.
Detailed Description
The present application will now be described in detail with reference to the drawings, and the specific operations in the method embodiments may also be applied to the apparatus embodiments or the system embodiments.
Please refer to fig. 1, which is a schematic view of an application scenario of a mobile internet user management method according to an embodiment of the present application. In this embodiment, the application scenario may include a server 100 and a plurality of user terminals 200 communicatively connected to the server 100. Wherein the server 100 may provide a service to the user terminals 200 of a plurality of internet users. Each user terminal 200 stores a user management feature data list of the internet user.
The server 100 establishes a unique management list for each user behavior tag information in advance according to a plurality of user behavior tag information, so that the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation feature corresponding to the unique management list are established in a one-to-one correspondence relationship, establishes a user management list in advance according to the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation feature, and each user behavior tag information is matched with the information recommendation feature information of at least one key recommendation feature.
Fig. 2 is a flowchart illustrating a mobile internet user management method according to an embodiment of the present application. In this embodiment, the mobile internet user management method may be performed by the server 100 shown in fig. 1, and the mobile internet user management method will be described in detail below.
Step S110, acquiring a user management characteristic data list of the target Internet user from the data collection area of the target Internet user, and determining whether the user management characteristic data list contains key recommendation characteristics or not by using an artificial intelligence model.
And step S120, if the key recommendation features are included, performing decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features.
And step S130, matching the information recommendation characteristic information of the key recommendation characteristics obtained by calculation with a plurality of preset user behavior label information, and judging the recommendation frequent characteristics of the target Internet user.
And step S140, outputting the information recommendation process of the target Internet user according to the recommendation frequency characteristic of the target Internet user, and recommending information for the user terminal of the target Internet user according to the information recommendation process of the target Internet user.
Based on the steps, the user management feature data list of the target internet user is obtained from the data collection area of the target internet user, after the fact that the user management feature data list contains the key recommendation features is determined, decision classification calculation is conducted on the key recommendation features to obtain information recommendation feature information of the key recommendation features, the information recommendation feature information is matched with a plurality of preset user behavior label information, recommendation frequent features of the target internet user are judged, an information recommendation process of the target internet user is configured, information recommendation is conducted on a user terminal of the target internet user according to the information recommendation process of the target internet user, and targeted and effective information recommendation is conducted on the mobile internet user.
In a possible design, for step S110, the following implementation may be specifically implemented:
reading a common key recommendation characteristic sample from a key recommendation characteristic sample database, determining a key recommendation characteristic sample to be used from the common key recommendation characteristic sample according to a management label service range in a user management characteristic data list, then determining a mobile internet user management range of object information to be recommended according to the key recommendation characteristic sample to be used, matching in the user management characteristic data list by utilizing the mobile internet user management range, and if the matching is successful, determining that the user management characteristic data list contains key recommendation characteristics.
In one possible design, the artificial intelligence model may be trained by:
the method comprises the steps of firstly, reading initial key recommendation characteristic data, wherein each initial key recommendation characteristic data comprises an initial key recommendation characteristic database and various information recommendation characteristic information of the initial key recommendation characteristic database. And then, extracting key recommendation features from the initial key recommendation feature database, and performing decision classification calculation on the key recommendation features of each initial key recommendation feature database according to submodels corresponding to different information recommendation feature information in the initial model to obtain the prediction values of the information recommendation feature information of each initial key recommendation feature database. And then, calculating loss degrees of the plurality of information recommendation characteristic information according to the predicted values and the values of the information recommendation characteristic information and different service application types of the information recommendation characteristic information, and summing the loss degrees of the plurality of information recommendation characteristic information to obtain a total loss degree of the plurality of information recommendation characteristic information. And then, adjusting parameters of the submodels corresponding to different information recommendation characteristic information in the initial model until the adjusted parameters enable the total loss degree of the information recommendation characteristic information to be smaller than or equal to a preset threshold value, and stopping adjusting to obtain the artificial intelligence model.
In a possible design, on the basis of the foregoing embodiment, the present embodiment further considers that the recommendation process of the target users of the same type is comprehensively evaluated, so as to improve the accuracy of the information recommendation process, and for step S140, the following describes exemplary sub-steps of step S140 with reference to fig. 3.
And a substep S141 of obtaining page access record information on each information recommendation search page accessed by the target Internet user according to the recommendation frequency characteristic of the target Internet user.
And the substep S142, acquiring the associated page access record information of other similar target users matched with the target Internet user on each information recommendation search page according to the page access record information on each information recommendation search page accessed by the target Internet user.
And the substep S143, performing decision classification calculation on the associated page access record information to obtain the category recommendation characteristic information of the associated page access record information.
And a substep S144 of determining whether the category recommendation characteristic information includes the first information recommendation characteristic information and the second information recommendation characteristic information. The matching degree of the first information recommendation characteristic information and the information recommendation characteristic information of the target internet user is greater than a first set matching degree, and the matching degree of the second information recommendation characteristic information and the information recommendation characteristic information of the target internet user is less than a second set matching degree.
And a substep S145, if the first information recommendation characteristic information and the second information recommendation characteristic information exist, acquiring a first recommendation frequent characteristic corresponding to the first information recommendation characteristic information of the related internet access user on each information recommendation search page and a second recommendation frequent characteristic corresponding to the second information recommendation characteristic information of the related internet access user.
And a substep S146, performing splicing fusion on the first recommended frequent feature and the second recommended frequent feature to obtain a matching recommended frequent feature.
And a substep S147, matching the matched recommended frequent features with the marked recommended frequent features corresponding to the information recommended search pages, and outputting the information recommendation process of the target Internet user according to the matching result.
Therefore, based on the steps, the embodiment considers the recommendation process of the target users of the same type to perform comprehensive evaluation, and improves the accuracy of the information recommendation process.
In one possible design, in order to improve the accuracy of feature matching, for sub-step S146, a common feature node between the first recommended frequent feature and the second recommended frequent feature may be specifically determined; the common characteristic node refers to an initial node for splicing and fusing the first recommended frequent characteristic and the second recommended frequent characteristic. And then, splicing and fusing the first recommended frequent feature and the second recommended frequent feature into a matched recommended frequent feature according to the common feature node, so that after the first recommended frequent feature and the second recommended frequent feature are obtained, the two recommended frequent features are not matched one by one, but are spliced and fused to obtain the matched recommended frequent feature, and then matching is performed, more matchable parameters (such as alignment, difference value and the like) can be generated after the recommended frequent features are spliced and fused, and the accuracy of feature matching is improved.
In one possible design, the common feature node between the first recommended frequent feature and the second recommended frequent feature may be determined by: calculating a first frequent feature degree of the first recommended frequent feature and a second frequent feature degree of the second recommended frequent feature, and calculating a difference value between the first frequent feature degree and the second frequent feature degree; and judging whether the difference value is less than or equal to a preset value. And if the difference is smaller than or equal to a preset numerical value, updating the feature bit axis of any one recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature to obtain the first recommended frequent feature and the second recommended frequent feature with the same final continuous frequent feature degree, and taking the first recommended frequent feature position of the first recommended frequent feature and the second recommended frequent feature with the same final continuous frequent feature degree as a common feature node. If the difference is larger than a preset value, respectively crawling the first recommended frequent feature and the second recommended frequent feature by using the same default crawling manner to obtain a first recommended frequent feature position group and a second recommended frequent feature position group, and then generating an information recommended object sequence according to the default crawling manner, the first recommended frequent feature position group, the second recommended frequent feature position group and the cross-correlation frequent feature degree; the frequent cross-correlation characteristic degree is positively correlated with the difference value, and the information recommendation object sequence comprises a plurality of information recommendation object characteristics. And then, comparing the plurality of information recommendation object features in the information recommendation object sequence, and searching the information recommendation object feature with the maximum frequent feature degree of the feature position, so that the recommended frequent feature position corresponding to the information recommendation object feature is used as a common feature node.
Therefore, the frequent feature degree of the recommended frequent features is further considered in the embodiment, so that the frequent feature degree of the recommended frequent features can be further referred to when feature matching is performed, and the accuracy of feature matching is improved.
In a possible design, the manner of performing feature bit axis update on any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature may be: if the first frequent feature degree of the first recommended frequent feature is smaller than the second frequent feature degree of the second recommended frequent feature, determining the proportion of the difference value in the first frequent feature degree of the first recommended frequent feature according to the difference value, then calculating a segmentation numerical value of the first recommended frequent feature, and calculating an updating coefficient according to the segmentation numerical value and the proportion, so that the feature bit axis of any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature is updated according to the updating coefficient.
Fig. 4 is a schematic functional module diagram of the mobile internet user management device 300 according to an embodiment of the present application, and the embodiment may divide the functional module of the mobile internet user management device 300 according to the foregoing method embodiment. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the mobile internet user management apparatus 300 shown in fig. 4 is only a schematic diagram of an apparatus. The mobile internet user management device 300 may include an obtaining module 310, a decision module 320, a determining module 330, and an information recommending module 340, and the functions of the functional modules of the mobile internet user management device 300 are described in detail below.
The obtaining module 310 is configured to obtain a user management feature data list of the target internet user from the data collection area of the target internet user, and determine whether the user management feature data list includes a key recommendation feature by using an artificial intelligence model.
And the decision module 320 is configured to, if the key recommendation features are included, perform decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features.
The determining module 330 is configured to match the information recommendation feature information of the calculated key recommendation features with a plurality of preset user behavior tag information, and determine recommendation frequent features of the target internet user.
And the information recommendation module 340 is configured to output an information recommendation process of the target internet user according to the recommendation frequency characteristic of the target internet user, and perform information recommendation for the user terminal of the target internet user according to the information recommendation process of the target internet user.
In one possible design, the obtaining module 310 may determine whether the user management feature data list includes the key recommended features by using an artificial intelligence model in the following manner:
reading common key recommendation characteristic samples from a key recommendation characteristic sample database;
determining key recommendation feature samples to be used from common key recommendation feature samples according to the service range of a management tag in a user management feature data list;
determining the mobile internet user management range of the information of the object to be recommended according to the key recommendation characteristic sample to be used;
and matching in the user management characteristic data list by utilizing the mobile internet user management range, and if the matching is successful, determining that the user management characteristic data list contains the key recommendation characteristics.
In one possible design, the artificial intelligence model may be trained by:
reading initial key recommendation characteristic data, wherein each initial key recommendation characteristic data comprises an initial key recommendation characteristic database and various information recommendation characteristic information of the initial key recommendation characteristic database;
extracting key recommendation features from an initial key recommendation feature database;
performing decision classification calculation on the key recommendation characteristics of each initial key recommendation characteristic database according to submodels corresponding to different information recommendation characteristic information in the initial model to obtain the prediction values of a plurality of information recommendation characteristic information of each initial key recommendation characteristic database;
calculating loss degrees of a plurality of pieces of information recommendation characteristic information according to the predicted values and the values of the information recommendation characteristic information and different service application types of the information recommendation characteristic information;
summing the loss degrees of the information recommendation characteristic information to obtain the total loss degree of the information recommendation characteristic information;
and adjusting parameters of the submodels corresponding to different information recommendation characteristic information in the initial model until the adjusted parameters enable the total loss degree of the information recommendation characteristic information to be smaller than or equal to a preset threshold value, and stopping adjusting to obtain the artificial intelligence model.
In one possible design, the information recommendation module 340 may output the information recommendation process of the target internet user by:
acquiring page access record information on each information recommendation search page accessed by the target internet user according to the recommendation frequent characteristics of the target internet user;
acquiring associated page access record information of each information recommendation search page for other similar target users matched with the target internet user according to the page access record information on each information recommendation search page accessed by the target internet user;
performing decision classification calculation on the associated page access record information to obtain category recommendation characteristic information of the associated page access record information;
judging whether first information recommendation characteristic information and second information recommendation characteristic information exist in the category recommendation characteristic information or not; the matching degree of the first information recommendation characteristic information and the information recommendation characteristic information of the target internet user is greater than a first set matching degree, and the matching degree of the second information recommendation characteristic information and the information recommendation characteristic information of the target internet user is less than a second set matching degree;
if the first information recommendation characteristic information and the second information recommendation characteristic information exist, acquiring a first recommendation frequent characteristic corresponding to the first information recommendation characteristic information of the related internet access users on each information recommendation search page and a second recommendation frequent characteristic corresponding to the second information recommendation characteristic information of the related internet access users;
splicing and fusing the first recommended frequent feature and the second recommended frequent feature to obtain a matched recommended frequent feature;
and matching the matched recommended frequent features with the marked recommended frequent features corresponding to the information recommended search pages, and outputting the information recommendation process of the target internet user according to the matching result.
In one possible design, the information recommendation module 340 may obtain the matching recommended frequent feature by performing stitching fusion on the first recommended frequent feature and the second recommended frequent feature in the following manner:
determining a common feature node between the first recommended frequent feature and the second recommended frequent feature; the common characteristic node is an initial node formed by splicing and fusing the first recommended frequent characteristic and the second recommended frequent characteristic;
and splicing and fusing the first recommended frequent feature and the second recommended frequent feature into a matched recommended frequent feature according to the common feature node.
In one possible design, the information recommendation module 340 may determine the common feature node between the first recommended frequent feature and the second recommended frequent feature by:
calculating a first frequent feature degree of the first recommended frequent feature and a second frequent feature degree of the second recommended frequent feature;
calculating a difference between the first frequent feature degree and the second frequent feature degree; judging whether the difference value is less than or equal to a preset value;
if yes, updating a feature bit axis of any one recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature to obtain a first recommended frequent feature and a second recommended frequent feature which are identical in final continuous frequent feature degree, and taking the first recommended frequent feature position of the first recommended frequent feature and the second recommended frequent feature which are identical in final continuous frequent feature degree as a common feature node;
if not, respectively crawling the first recommended frequent feature and the second recommended frequent feature by using the same default crawling manner to obtain a first recommended frequent feature position group and a second recommended frequent feature position group;
generating an information recommendation object sequence according to a default crawling mode, the first recommendation frequent feature position group, the second recommendation frequent feature position group and the cross-correlation frequent feature degree; the cross-correlation frequent feature degree is positively correlated with the difference value, and the information recommendation object sequence comprises a plurality of information recommendation object features;
comparing a plurality of information recommendation object characteristics in the information recommendation object sequence, and searching the information recommendation object characteristic with the maximum frequent characteristic degree at the characteristic position;
and taking the recommended frequent feature position corresponding to the information recommendation object feature as a common feature node.
In one possible design, the information recommendation module 340 may perform the feature bit axis update on any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature by:
if the first frequent feature degree of the first recommended frequent feature is smaller than the second frequent feature degree of the second recommended frequent feature, determining the proportion of the difference value in the first frequent feature degree of the first recommended frequent feature according to the difference value;
calculating a segmentation numerical value of the first recommended frequent feature, and calculating an updating coefficient according to the segmentation numerical value and the proportion;
and according to the updating coefficient, updating any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature on a feature bit axis.
Fig. 5 is a schematic structural diagram of a server 100 for performing the above-mentioned mobile internet user management method according to an embodiment of the present invention, and as shown in fig. 5, the server 100 may include a network interface 110, a machine-readable storage medium 120, a processor 130, and a bus 140. The number of the processors 130 may be one or more, and one processor 130 is taken as an example in fig. 5; the network interface 110, the machine-readable storage medium 120, and the processor 130 may be connected by a bus 140 or otherwise, as exemplified by the connection by the bus 140 in fig. 5.
The machine-readable storage medium 120 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for establishing a knowledge base of robot auto-quiz in the embodiment of the present application (for example, the obtaining module 310, the decision module 320, the judgment module 330, and the information recommendation module 340 in the mobile internet user management device 300 shown in fig. 4). The processor 130 detects software programs, instructions and modules stored in the machine-readable storage medium 120 to execute various functional applications and data processing of the server 100, that is, to implement the above-mentioned mobile internet user management method, which is not described herein again.
The machine-readable storage medium 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the machine-readable storage medium 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to comprise, without being limited to, these and any other suitable memories at any other time. In some examples, the machine-readable storage medium 120 may further include memory located remotely from the processor 130, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, internet user intranets, local area networks, mobile communication networks, and combinations thereof.
The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The processor 130 may be a general-purpose processor, a digital signal processor (digital signal processor dsp), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
The server 100 may interact with other devices via the communication interface 110. Communication interface 110 may be a circuit, bus, transceiver, or any other device that may be used to exchange information. Processor 130 may send and receive information using communication interface 110.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.
Claims (10)
1. A mobile internet user management method is applied to a server, the server establishes a unique management list for each user behavior tag information in advance according to a plurality of user behavior tag information, so that the unique management list of each user behavior tag information and information recommendation feature information of key recommendation features corresponding to the unique management list are established in a one-to-one correspondence mode, a user management list is established in advance according to the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation features, and each user behavior tag information is matched with the information recommendation feature information of at least one key recommendation feature, the method comprises the following steps:
acquiring a user management characteristic data list of a target internet user from a data collection area of the target internet user, and determining whether the user management characteristic data list contains key recommendation characteristics or not by using an artificial intelligence model;
if the key recommendation features are included, performing decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features;
matching the information recommendation characteristic information of the key recommendation characteristics obtained by calculation with a plurality of preset user behavior label information, and judging recommendation frequent characteristics of the target internet user;
and outputting the information recommendation process of the target internet user according to the recommendation frequency characteristic of the target internet user, and recommending information for the user terminal of the target internet user according to the information recommendation process of the target internet user.
2. The method for managing a mobile internet user as claimed in claim 1, wherein the step of determining whether the user management characteristic data list includes a key recommendation characteristic using an artificial intelligence model includes:
reading common key recommendation characteristic samples from a preset key recommendation characteristic sample database;
determining key recommendation feature samples to be used from the common key recommendation feature samples according to the service range of the management tag in the user management feature data list;
determining the mobile internet user management range of the information of the object to be recommended according to the key recommendation characteristic sample to be used;
and matching in the user management characteristic data list by utilizing the mobile internet user management range, and if the matching is successful, determining that the user management characteristic data list contains key recommendation characteristics.
3. The mobile internet user management method of claim 1, wherein the artificial intelligence model is trained by:
reading initial key recommendation characteristic data, wherein each initial key recommendation characteristic data comprises an initial key recommendation characteristic database and various information recommendation characteristic information of the initial key recommendation characteristic database;
extracting key recommendation features from an initial key recommendation feature database;
performing decision classification calculation on the key recommendation characteristics of each initial key recommendation characteristic database according to submodels corresponding to different information recommendation characteristic information in the initial model to obtain the prediction values of a plurality of information recommendation characteristic information of each initial key recommendation characteristic database;
calculating loss degrees of the plurality of information recommendation characteristic information according to the prediction values and the values of the information recommendation characteristic information and different service application types of the information recommendation characteristic information;
summing the loss degrees of the plurality of information recommendation characteristic information to obtain the total loss degree of the plurality of information recommendation characteristic information;
and adjusting parameters of the submodels corresponding to different information recommendation characteristic information in the initial model until the adjusted parameters enable the total loss degree of the information recommendation characteristic information to be smaller than or equal to a preset threshold value, and stopping adjusting to obtain the artificial intelligence model.
4. The mobile internet user management method of claim 1, wherein the step of outputting the information recommendation process of the target internet user according to the recommended frequent feature of the target internet user comprises:
acquiring page access record information on each information recommendation search page accessed by the target internet user according to the recommendation frequency characteristics of the target internet user;
acquiring associated page access record information of each information recommendation search page for other similar target users matched with the target internet user according to the page access record information on each information recommendation search page accessed by the target internet user;
performing decision classification calculation on the associated page access record information to obtain category recommendation characteristic information of the associated page access record information;
judging whether first information recommendation characteristic information and second information recommendation characteristic information exist in the category recommendation characteristic information or not; the matching degree of the first information recommendation characteristic information and the information recommendation characteristic information of the target internet user is greater than a first set matching degree, and the matching degree of the second information recommendation characteristic information and the information recommendation characteristic information of the target internet user is less than a second set matching degree;
if the first information recommendation characteristic information and the second information recommendation characteristic information exist, acquiring a first recommendation frequent characteristic corresponding to the first information recommendation characteristic information of the related internet access user on each information recommendation search page and a second recommendation frequent characteristic corresponding to the second information recommendation characteristic information of the related internet access user;
splicing and fusing the first recommended frequent feature and the second recommended frequent feature to obtain a matched recommended frequent feature;
and matching the matched recommended frequent features with the marked recommended frequent features corresponding to the information recommended search pages, and outputting the information recommendation process of the target internet user according to the matching result.
5. The mobile internet user management method according to claim 1, wherein the step of splicing and fusing the first recommended frequent feature and the second recommended frequent feature to obtain a matching recommended frequent feature includes:
determining a common feature node between the first recommended frequent feature and the second recommended frequent feature; the common characteristic node is a starting node for splicing and fusing the first recommended frequent characteristic and the second recommended frequent characteristic;
and splicing and fusing the first recommended frequent feature and the second recommended frequent feature into a matched recommended frequent feature according to the common feature node.
6. The mobile internet user management method of claim 5, wherein the step of determining a common feature node between the first recommended frequent feature and the second recommended frequent feature comprises:
calculating a first frequent feature degree of the first recommended frequent feature and a second frequent feature degree of the second recommended frequent feature;
calculating a difference value between the first frequent feature degree and the second frequent feature degree, and judging whether the difference value is smaller than or equal to a preset value;
if yes, updating any recommended frequent feature in the first recommended frequent feature and the second recommended frequent feature on a feature bit axis to obtain a first recommended frequent feature and a second recommended frequent feature which are identical in final continuous frequent feature degree, and taking the first recommended frequent feature position of the first recommended frequent feature and the second recommended frequent feature which are identical in final continuous frequent feature degree as a common feature node;
if not, respectively crawling the first recommended frequent feature and the second recommended frequent feature by using the same default crawling manner to obtain a first recommended frequent feature position group and a second recommended frequent feature position group;
generating an information recommendation object sequence according to the default crawling mode, the first recommendation frequent feature position group, the second recommendation frequent feature position group and the cross-correlation frequent feature degree; the cross-correlation frequent feature degree is positively correlated with the difference value, and the information recommendation object sequence comprises a plurality of information recommendation object features;
comparing the characteristics of the plurality of information recommendation objects in the information recommendation object sequence, and searching the information recommendation object characteristic with the maximum frequent characteristic degree of the characteristic position;
and taking the recommended frequent feature position corresponding to the information recommendation object feature as a common feature node.
7. The mobile internet user management method according to claim 6, wherein the step of updating on a feature bit axis any one of the first recommended frequent feature and the second recommended frequent feature includes:
if the first frequent feature degree of the first recommended frequent feature is smaller than the second frequent feature degree of the second recommended frequent feature, determining the proportion of the difference value in the first frequent feature degree of the first recommended frequent feature according to the difference value;
calculating a segmentation numerical value of the first recommended frequent feature, and calculating an updating coefficient according to the segmentation numerical value and the proportion;
and according to the updating coefficient, updating any recommended frequent feature of the first recommended frequent feature and the second recommended frequent feature on a feature bit axis.
8. A mobile internet user management device is applied to a server, the server establishes a unique management list for each user behavior tag information in advance according to a plurality of user behavior tag information, so that the unique management list of each user behavior tag information and information recommendation feature information of a key recommendation feature corresponding to the unique management list are established in a one-to-one correspondence relationship, a user management list is established in advance according to the unique management list of each user behavior tag information and the information recommendation feature information of the key recommendation feature, and each user behavior tag information is matched with the information recommendation feature information of at least one key recommendation feature, the device comprises:
the acquisition module is used for acquiring a user management characteristic data list of a target internet user from a data collection area of the target internet user and determining whether the user management characteristic data list contains key recommendation characteristics or not by using an artificial intelligence model;
the decision module is used for carrying out decision classification calculation on the key recommendation features to obtain information recommendation feature information of the key recommendation features if the key recommendation features are included;
the judging module is used for matching the information recommendation characteristic information of the key recommendation characteristics obtained through calculation with a plurality of preset user behavior label information and judging the recommendation frequent characteristics of the target internet user;
and the information recommendation module is used for outputting the information recommendation process of the target internet user according to the recommendation frequency characteristic of the target internet user and recommending information for the user terminal of the target internet user according to the information recommendation process of the target internet user.
9. A server, characterized in that the server comprises a machine-readable storage medium storing machine-executable instructions and a processor, and when the processor executes the machine-executable instructions, the server implements the mobile internet user management method according to any one of claims 1 to 7.
10. A readable storage medium having stored therein machine executable instructions which when executed perform a mobile internet user management method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010657112.XA CN111814052A (en) | 2020-07-09 | 2020-07-09 | Mobile internet user management method, device, server and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010657112.XA CN111814052A (en) | 2020-07-09 | 2020-07-09 | Mobile internet user management method, device, server and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814052A true CN111814052A (en) | 2020-10-23 |
Family
ID=72842848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010657112.XA Withdrawn CN111814052A (en) | 2020-07-09 | 2020-07-09 | Mobile internet user management method, device, server and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814052A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344147A (en) * | 2021-08-04 | 2021-09-03 | 北京世纪好未来教育科技有限公司 | Feature sharing modeling method, device, equipment and storage medium thereof |
| CN116257791A (en) * | 2023-05-10 | 2023-06-13 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
-
2020
- 2020-07-09 CN CN202010657112.XA patent/CN111814052A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344147A (en) * | 2021-08-04 | 2021-09-03 | 北京世纪好未来教育科技有限公司 | Feature sharing modeling method, device, equipment and storage medium thereof |
| CN116257791A (en) * | 2023-05-10 | 2023-06-13 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
| CN116257791B (en) * | 2023-05-10 | 2023-08-11 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652615B (en) | Safety identification method based on block chain big data and artificial intelligence cloud service platform | |
| CN111132145B (en) | Network communication safety monitoring method, device, server and network communication system | |
| CN110442762B (en) | Big data processing method based on cloud platform big data | |
| CN111814052A (en) | Mobile internet user management method, device, server and readable storage medium | |
| CN110442623B (en) | Big data mining method and device and data mining server | |
| CN110855529B (en) | Network information security monitoring method, device, server and readable storage medium | |
| CN113468404A (en) | Push resource determination method based on big data mining and cloud computing AI (Artificial Intelligence) service system | |
| CN111680645B (en) | Garbage classification treatment method and device | |
| CN111079175B (en) | Data processing method, data processing device, computer readable storage medium and computer equipment | |
| CN110880150A (en) | Community discovery method, device, equipment and readable storage medium | |
| CN107203545B (en) | Data processing method and device | |
| CN111680293A (en) | Information monitoring management method and device based on Internet and server | |
| CN111667190B (en) | Electric power construction grounding monitoring method, device and server | |
| CN113239272B (en) | Intention prediction method and intention prediction device of network management and control system | |
| CN112055076A (en) | Multifunctional intelligent monitoring method and device based on Internet and server | |
| CN112380771A (en) | Soil erosion assessment method and device and server | |
| CN111988187B (en) | Internet connection method and device of central management server | |
| CN111488490A (en) | Video clustering method, device, server and storage medium | |
| CN111526333A (en) | Security monitoring method and device, server and readable storage medium | |
| CN112055075B (en) | Internet product monitoring method, device, server and readable storage medium | |
| CN112364515B (en) | Ecological environment intelligent monitoring method and device and server | |
| CN111652323B (en) | Water quality monitoring method, device and server | |
| CN112039994B (en) | Internet-based remote monitoring method, device and server | |
| CN116521761B (en) | Sensor operation behavior mining method and system based on artificial intelligence | |
| CN111800482B (en) | Dynamic security protection, device and server of industrial internet |
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 | ||
| CB02 | Change of applicant information |
Address after: No. 205, Beichen Avenue, Panlong District, Kunming City, Yunnan Province Applicant after: Zhang Defu Address before: 301-320, 3rd floor, Fuchang Industrial Park, 259 huxinan Road, Maanshan economic and Technological Development Zone, Anhui Province 243000 Applicant before: Zhang Defu |
|
| CB02 | Change of applicant information | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201023 |
|
| WW01 | Invention patent application withdrawn after publication |