CN114124724A - User behavior analysis method, device, NWDAF and storage medium - Google Patents
User behavior analysis method, device, NWDAF and storage medium Download PDFInfo
- Publication number
- CN114124724A CN114124724A CN202010803067.4A CN202010803067A CN114124724A CN 114124724 A CN114124724 A CN 114124724A CN 202010803067 A CN202010803067 A CN 202010803067A CN 114124724 A CN114124724 A CN 114124724A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- behavior
- configuration information
- user behavior
- 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- Withdrawn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
- 238000004458 analytical method Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 230000006399 behavior Effects 0.000 claims description 223
- 238000012549 training Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 16
- 210000002569 neuron Anatomy 0.000 description 8
- 238000012545 processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Abstract
The invention provides a user behavior analysis method, a device, a NWDAF and a storage medium, wherein the method is applied to a network data analysis function NWDAF and comprises the following steps: configuring parameter acquisition configuration information corresponding to the user identification; when behavior analysis is carried out, user parameters corresponding to the user identification are obtained according to the parameter acquisition configuration information; and predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information. The method, the device, the NWDAF and the storage medium can pertinently call the relevant user information, avoid calling irrelevant information and reduce calling irrelevant information; the user behavior prediction model is used for analyzing the user behavior, so that the speed of analyzing the user behavior is increased, the user behavior is accurately analyzed, and the transmission resources and the computing resources of the network are saved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for user behavior analysis, an NWDAF, and a storage medium.
Background
In the 5G architecture, the user plane and the control plane are completely separated. In a 5G network, the number of network elements and interfaces will increase, and at the same time, the number and variety of users in the network will grow greatly. The behavior habits of different types of users and different users of the same type can be quite different, and the existing information acquisition mode of 'subscription-event report based' can not meet the requirements of user behavior analysis of mobile communication networks with huge user quantity and complex user behaviors. At present, when user information is stored in a current network, common behaviors of a user are not stored, because the complex behaviors of the user are difficult to describe by a language which can be understood by the network; therefore, for each user, the network does not know the behavior habit of the user, when the network judges the behavior of the user, each user is used as a strange user to start judgment from '0', the judgment efficiency is low, the accuracy is not high, and a large amount of network computing and storage resources are occupied.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a user behavior analysis method, apparatus, NWDAF and storage medium.
According to a first aspect of the present disclosure, there is provided a user behavior analysis method applied in a network data analysis function NWDAF, including: configuring parameter acquisition configuration information corresponding to the user identification; when behavior analysis is carried out, acquiring user parameters corresponding to the user identification according to the parameter acquisition configuration information; and predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information.
Optionally, when a preset user behavior model is trained, acquiring a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information, and acquiring a user behavior set corresponding to the user parameter set; and generating a training sample based on the user parameter set and the user behavior set, and training the user behavior model by using a deep learning method and based on the training sample to obtain a trained user behavior prediction model.
Optionally, the obtaining a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information, and obtaining a user behavior set corresponding to the user parameter set includes: collecting user information corresponding to the user identification from a network element and/or a network management system; extracting the user parameter set from the user information according to the parameter acquisition configuration information; and acquiring the user behavior set corresponding to the user parameter set based on a preset behavior analysis strategy.
Optionally, the obtaining, according to the parameter acquisition configuration information, a user parameter corresponding to the user identifier includes: and acquiring the latest user parameters corresponding to the user identification from a network element and/or a network management system according to the parameter acquisition configuration information.
Optionally, when performing behavior analysis, obtaining a user identifier corresponding to an analysis target user; judging whether the parameter acquisition configuration information is configured for the user identifier; if yes, acquiring a user parameter corresponding to the corresponding user identifier according to the parameter acquisition configuration information; if not, acquiring user information corresponding to the user identification from the network element and/or the network management system, and acquiring user behavior information according to the user information based on a preset behavior analysis strategy.
Optionally, if the parameter acquisition configuration information changes, the user behavior prediction model is trained according to new parameter acquisition configuration information.
According to a second aspect of the present disclosure, there is provided a user behavior analysis apparatus provided in a network data analysis function NWDAF, comprising: the information configuration module is used for configuring parameter acquisition configuration information corresponding to the user identification; the data acquisition module is used for acquiring user parameters corresponding to the user identification according to the parameter acquisition configuration information during behavior analysis; and the behavior prediction module is used for predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information.
Optionally, the model training module comprises: the sample acquisition unit is used for acquiring a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information and acquiring a user behavior set corresponding to the user parameter set when a preset user behavior model is trained; and the training execution unit is used for generating a training sample based on the user parameter set and the user behavior set, training the user behavior model by using a deep learning method and based on the training sample, and obtaining a trained user behavior prediction model.
Optionally, the sample obtaining unit is configured to collect user information corresponding to the user identifier from a network element and/or a network management system; extracting the user parameter set from the user information according to the parameter acquisition configuration information; and acquiring the user behavior set corresponding to the user parameter set based on a preset behavior analysis strategy.
Optionally, the data obtaining module is configured to collect, according to the parameter collection configuration information, the latest user parameter corresponding to the user identifier from a network element and/or a network management system.
Optionally, the behavior prediction module is configured to, when performing behavior analysis, obtain a user identifier corresponding to an analysis target user; judging whether the parameter acquisition configuration information is configured for the user identifier; if so, the data acquisition module acquires the user parameters corresponding to the corresponding user identification according to the parameter acquisition configuration information; if not, the data acquisition module acquires user information corresponding to the user identification from a network element and/or a network management system, and the behavior prediction module acquires user behavior information according to the user information based on a preset behavior analysis strategy
Optionally, the model updating module is configured to train the user behavior prediction model according to new parameter acquisition configuration information if the parameter acquisition configuration information changes.
According to a third aspect of the present disclosure, there is provided a user behavior analysis apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the method as described above based on instructions stored in the memory.
According to a fourth aspect of the present disclosure, there is provided a network data analysis function, NWDAF, comprising: the user behavior analysis device as described above.
According to a fifth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by one or more processors, implement the steps of the method as described above.
The disclosed user behavior analysis method, device, NWDAF and storage medium configure parameter acquisition configuration information corresponding to a user identifier, acquire a user parameter corresponding to the user identifier according to the parameter acquisition configuration information, and acquire user behavior prediction information according to the user parameter by using a user behavior prediction model; relevant user information can be called in a targeted manner, so that the calling of irrelevant information is avoided, and the calling of irrelevant information is reduced; the user behavior prediction model is used for analyzing the user behavior, so that the speed of analyzing the user behavior is increased, the user behavior is accurately analyzed, and the transmission resources and the computing resources of the network are saved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive exercise.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a user behavior analysis method according to the present disclosure;
FIG. 2 is a schematic data collection diagram of one embodiment of a user behavior analysis method according to the present disclosure;
FIG. 3 is a schematic flow diagram of model training in accordance with one embodiment of a user behavior analysis method of the present disclosure;
FIG. 4A is a schematic flow chart diagram illustrating another embodiment of a user behavior analysis method according to the present disclosure;
FIG. 4B is a message diagram of subscription data for an NWDAF;
fig. 4C is a schematic view of an application scenario of the user behavior analysis method of the present disclosure;
FIG. 5 is a block diagram of one embodiment of a user behavior analysis device according to the present disclosure;
FIG. 6 is a block diagram representation of another embodiment of a user behavior analysis device according to the present disclosure;
FIG. 7 is a block diagram of a model training module in one embodiment of a user behavior analysis apparatus according to the present disclosure;
fig. 8 is a block diagram of a further embodiment of a user behavior analysis apparatus according to the present disclosure.
Detailed Description
The present disclosure now will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the disclosure are shown. The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The terms "first", "second", and the like are used hereinafter only for descriptive distinction and not for other specific meanings.
Fig. 1 is a schematic flow chart of an embodiment of a user behavior analysis method according to the present disclosure, which is applied to a network Data analysis function nwdaf (network Data analysis function), as shown in fig. 1:
In one embodiment, the parameter collection configuration information includes user parameter information that needs to be collected, for example, the parameter collection configuration information includes time, place, user trajectory information, and the like. For the user track information, the network element or the network management system in the network can obtain the position or area information of the user terminal and the moving speed of the user terminal by obtaining the base station information connected with the user terminal, and the user track information can be obtained based on the position or area information of the user terminal and the moving speed of the user terminal.
The user identification can be a mobile phone number and the like, an Analytic ID corresponding to the mobile phone number of the user is set, and the corresponding relation between the Analytic ID and the parameter acquisition configuration information is set.
And 102, acquiring user parameters corresponding to the user identification according to the parameter acquisition configuration information during behavior analysis.
In one embodiment, when a user is subjected to behavior analysis, an Analytic ID of the user is obtained, stored parameter acquisition configuration information corresponding to the Analytic ID is obtained based on a corresponding relation between the Analytic ID and the parameter acquisition configuration information, and a user parameter corresponding to a mobile phone number of the user is obtained from a network element or a network management system based on the parameter acquisition configuration information.
For example, the parameter acquisition configuration information includes time, place, user track information, and the like, and the user parameters obtained from a network element or a network management system in the network and corresponding to the mobile phone number of the user include time, place, user track, and the like corresponding to the mobile phone number of the user.
And 103, predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information.
In one embodiment, parameters such as time, place, user track and the like corresponding to the mobile phone number of the user are input into a trained user behavior prediction model, and user behavior prediction information output by the user behavior prediction model is obtained, wherein the user behavior can be behaviors such as returning home, working, ball games, dining out and the like.
As shown in fig. 2, the NWDAF can obtain user information from network elements such as PCF (Policy Control Function), UDM (Unified Data Management Function), SMF (Session Management Function), and the like, and a network Management system.
By using the user behavior analysis method disclosed by the invention, the defects of the traditional user behavior analysis scheme can be solved, the trained user behavior model and the parameter acquisition configuration information are stored in the NWDAF, and the information quantity acquired by the NWDAF during user behavior analysis is reduced; when user behavior analysis is subsequently performed, relevant user parameters are called only according to the parameter acquisition configuration information, so that irrelevant information is greatly reduced, network burden is reduced, and the speed of user behavior analysis is greatly increased.
Fig. 3 is a schematic flowchart of model training according to an embodiment of the user behavior analysis method of the present disclosure, as shown in fig. 3:
In one embodiment, user information corresponding to a user identifier is collected from a network element and/or a network management system, a user parameter set is extracted from the user information according to parameter collection configuration information, and a user behavior set corresponding to the user parameter set is obtained based on a preset behavior analysis strategy.
For example, the parameter acquisition configuration information includes time, place, user trajectory information, and the like, and the user identifier may be a mobile phone number of the user terminal. When a preset user behavior model is trained, the NWDAF collects user information corresponding to user identification from a network element and a network management system, wherein the user information comprises all parameter information of a user.
And acquiring a user parameter set corresponding to the user identifier from the user information according to the time, the place, the user track information and the like of the parameter acquisition configuration information. And analyzing the user information by the NWDAF according to the existing behavior analysis method to obtain a user behavior set corresponding to the user parameter set.
And 302, generating a training sample based on the user parameter set and the user behavior set, and training the user behavior model by using a deep learning method and based on the training sample to obtain a trained user behavior prediction model.
In one embodiment, the user behavior prediction model may be a deep learning model, and the deep learning model may be various, for example, the deep learning model includes CNN (convolutional neural network), DBN (deep belief network), RNN (recurrent neural network), RNTN, auto-encoder, GAN (generate-confrontation network), and the like. The user behavior prediction model may include a multi-layer neuron model including an input layer neuron model, a middle layer neuron model, and an output layer neuron model, an output of each layer of the neuron model being an input of a next layer of the neuron model, the multi-layer neuron model may be a sub-network structure of a plurality of neural network layers having a full connection structure, and the middle layer neuron model is a full connection layer.
Training samples are generated based on the user parameter set and the user behavior set. For example, each user parameter in the user parameter set includes user identification, time, place, and user trajectory information, and each user behavior in the user behavior set is home, work, a ball game, or a meal while out. The user behavior model can be trained based on the training samples by using various existing model training methods, and the user behavior model is used for obtaining a trained user behavior prediction model.
After the user behavior prediction model is trained, acquiring the latest user parameters corresponding to the user identification from the network element and the network management system according to the parameter acquisition configuration information, wherein the user parameters comprise time, place, user track and other parameters, inputting the latest user parameters into the trained user behavior prediction model, and obtaining the user behavior prediction information output by the user behavior prediction model, and the user behavior prediction information can be behaviors such as returning home, working, watching a ball game, going out for dining and the like.
In one embodiment, during behavior analysis, the NWDAF acquires a user identifier corresponding to an analysis target user, determines whether parameter acquisition configuration information is configured for the user identifier, and if so, acquires a user parameter corresponding to the corresponding user identifier according to the parameter acquisition configuration information; if not, acquiring user information corresponding to the user identification from the network element and the network management system, and acquiring user behavior information according to the user information based on a preset behavior analysis strategy.
For example, the NWDAF acquires and analyzes the user identifier of the target user as a mobile phone number, and determines whether the NWDAF is configured with an Analytic ID corresponding to the mobile phone number and whether the NWDAF is configured with a corresponding relationship between the Analytic ID and the parameter acquisition configuration information; and if the Analytic ID corresponding to the mobile phone number and the parameter acquisition configuration information corresponding to the Analytic ID are configured on the NWDAF, judging that the parameter acquisition configuration information is configured for the user identification.
The parameter acquisition configuration information includes time, place, user track information, and the like, and the user parameters corresponding to the user identifier, including time, place, user track information, and the like, are acquired according to the parameter acquisition configuration information, that is, the NWDAF may correspondingly invoke relevant information according to the content to be analyzed.
If no Analytic ID corresponding to the mobile phone number is configured on the NWDAF, user information corresponding to the user identification is acquired from the network element and the network management system, and the user behavior information is acquired according to the user information based on a preset behavior analysis strategy, wherein the user information comprises all information about the user, such as time, place, user track information, call duration, identity information and the like, namely if the parameter acquisition configuration information is not configured before the NWDAF, the NWDAF does not know which related information needs to be called, and all information about the user needs to be called. The NWDAF may obtain user behavior information based on existing various behavior analysis policies and from the user information.
In one embodiment, if the parameter acquisition configuration information changes, the user behavior prediction model is trained according to the new parameter acquisition configuration information. For example, the original parameter collection configuration information includes time, place, user track information, and the like, and the new parameter collection configuration information includes time, place, user track information, phone record, contact, call duration, and the like. When the parameter acquisition configuration information changes, the user behavior prediction model needs to be retrained, and the model training method can be adopted to retrain the user behavior prediction model.
For example, the NWDAF acquires user information corresponding to the user identifier from the network element and the network management system, and acquires a user parameter set corresponding to the user identifier from the user information according to information such as time, place, user track information, telephone record, contact, call duration, and the like of parameter acquisition configuration information. And analyzing the user information by the NWDAF according to the existing behavior analysis method to obtain a user behavior set corresponding to the user parameter set. And generating a training sample based on the user parameter set and the user behavior set, and training the user behavior model by using a deep learning method and based on the training sample to obtain a trained user behavior prediction model.
The NWDAF collects information required by user behavior judgment from various network elements, AF, NEF (network capability exposure Function), NRF (NF repetition Function, NF storage Function) and OAM (operation, management and maintenance), trains collected data through machine learning methods such as distributed machine learning, deep neural network, federal learning and the like, and obtains the user behavior analysis model for the user behavior judgment.
The storage on the NWDAF stores the user behavior analysis model, reconfigures the user information parameters collected by the network according to the information required by the user behavior analysis model, and collects only the information related to the user row (for example, only the related user parameters matched with the parameter collection configuration information are called), so that the information collection irrelevant to the user behavior judgment is reduced, and the collection of new information can be increased according to the requirement (for example, when some information is found to play an important role in the analysis of some user behavior, the collected user parameters can be properly increased), thereby greatly improving the efficiency of information collection required by the user behavior judgment and rapidly analyzing the user behavior.
Compared with the prior NWDAF which needs to acquire all information from other network elements for user analysis each time, the NWDAF in the user behavior analysis method only calls the user behavior related information according to the parameter acquisition configuration information when the user behavior analysis is performed, thereby avoiding calling a large amount of irrelevant information and realizing the rapid analysis of the user behavior.
Fig. 4A is a schematic flowchart of another embodiment of a user behavior analysis method according to the present disclosure, as shown in fig. 4A:
step 401, 402, when the NWDAF needs to train the user behavior prediction model, a whole set of user related information required by the model training is called from the network element or the network manager.
Step 403, performing data training by the NWDAF based on the collected data to obtain and store a trained user behavior prediction model; based on a trained user behavior prediction model, the NWDAF determines relevant information required for user behavior analysis, sets parameter acquisition configuration information for the user behavior analysis, and establishes a corresponding relation between Analytic ID and the parameter acquisition configuration information.
And steps 404 and 405, when user behavior analysis is needed or model training is continued, calling related user parameter information based on the parameter acquisition configuration information according to the corresponding relation between the Analytic ID and the parameter acquisition configuration information, and performing behavior analysis or user behavior prediction model training by using a trained user behavior prediction model according to the called user parameter information. The information acquisition mode and the used messages of the NWDAF 'subscription-event report-based' are shown in fig. 4B, where NF is a network function.
In one embodiment, as shown in fig. 4C, the user is a person who gets on and off duty on time, the person is a common behavior of the person, the NWDAF stores a user behavior prediction model for analyzing the judgment of the person's behavior after training the user behavior prediction model, and configures parameter acquisition configuration information, where the parameter acquisition configuration information includes time, place, and user trajectory; the location and the user trajectory can be obtained from the base station information connected to the user terminal. If the user behavior needs to be analyzed at the time point of going off duty, the NWDAF may acquire user parameter information required for the behavior analysis according to the parameter acquisition configuration information, and analyze and predict the user behavior by using a user behavior prediction model.
In one embodiment, as shown in fig. 5, the present disclosure provides a user behavior analysis apparatus 50, provided in a network data analysis function NWDAF, including: an information configuration module 51, a data acquisition module 52 and a behavior prediction module 53.
The information configuration module 51 configures parameter acquisition configuration information corresponding to the user identification. The data obtaining module 52 obtains the user parameter corresponding to the user identifier according to the parameter collecting configuration information when performing the behavior analysis. The behavior prediction module 53 uses the trained user behavior prediction model and performs prediction processing on the user behavior according to the user parameters to obtain user behavior prediction information.
In one embodiment, as shown in fig. 6, the user behavior analysis device 50 further includes: a model training module 54 and a model update model 55. As shown in fig. 7, the model training module 54 includes a sample acquisition unit 541 and a training execution unit 542. When training a preset user behavior model, the sample acquisition unit 541 acquires a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information, and acquires a user behavior set corresponding to the user parameter set.
The training execution unit 542 generates training samples based on the user parameter set and the user behavior set, and trains the user behavior model based on the training samples by using a deep learning method to obtain a trained user behavior prediction model.
The sample acquiring unit 541 acquires user information corresponding to the user identifier from the network element and/or the network management system, extracts a user parameter set from the user information according to the parameter acquisition configuration information, and acquires a user behavior set corresponding to the user parameter set based on a preset behavior analysis policy.
The data obtaining module 52 collects the latest user parameters corresponding to the user identifier from the network element and/or the network management system according to the parameter collecting configuration information. When performing behavior analysis, the behavior prediction module 53 acquires a user identifier corresponding to an analysis target user, and determines whether parameter acquisition configuration information is configured for the user identifier; if yes, the data obtaining module 52 obtains the user parameter corresponding to the corresponding user identifier according to the parameter acquisition configuration information; if not, the data obtaining module 52 collects the user information corresponding to the user identifier from the network element and/or the network management system, and the behavior predicting module 53 obtains the user behavior information based on the preset behavior analysis policy and according to the user information. If the parameter acquisition configuration information changes, the model update module 55 trains the user behavior prediction model according to the new parameter acquisition configuration information.
Fig. 8 is a block diagram of a further embodiment of a user behavior analysis apparatus according to the present disclosure. As shown in fig. 8, the apparatus may include a memory 81, a processor 82, a communication interface 83, and a bus 84. The memory 81 is used for storing instructions, the processor 82 is coupled to the memory 81, and the processor 82 is configured to execute the user behavior analysis method based on the instructions stored in the memory 81.
The memory 81 may be a high-speed RAM memory, a nonvolatile memory (NoN-volatile memory), or the like, and the memory 81 may be a memory array. The storage 81 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules. The processor 82 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement the user behavior analysis methods disclosed herein.
In one embodiment, the present disclosure provides a network data analysis function NWDAF comprising a user behavior analysis device as in any of the above embodiments.
In one embodiment, the present disclosure also provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions, when executed by a processor, implement the user behavior analysis method according to any of the above embodiments.
The user behavior analysis method and apparatus, the NWDAF, and the storage medium provided in the embodiments above configure parameter acquisition configuration information corresponding to the user identifier, obtain a user parameter corresponding to the user identifier according to the parameter acquisition configuration information, and obtain user behavior prediction information according to the user parameter by using a user behavior prediction model; relevant user information can be called in a targeted manner, so that the calling of irrelevant information is avoided, and the calling of irrelevant information is reduced; the user behavior prediction model is used for analyzing the user behavior, so that the speed of analyzing the user behavior is increased, the user behavior is accurately analyzed, and the transmission resources and the computing resources of the network are saved.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. 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.
Thus far, the present disclosure has been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
The description of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the disclosure in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (15)
1. A user behavior analysis method is applied to a network data analysis function (NWDAF) and comprises the following steps:
configuring parameter acquisition configuration information corresponding to the user identification;
when behavior analysis is carried out, acquiring user parameters corresponding to the user identification according to the parameter acquisition configuration information;
and predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information.
2. The method of claim 1, further comprising:
when a preset user behavior model is trained, acquiring a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information, and acquiring a user behavior set corresponding to the user parameter set;
and generating a training sample based on the user parameter set and the user behavior set, and training the user behavior model by using a deep learning method and based on the training sample to obtain a trained user behavior prediction model.
3. The method of claim 2, wherein the obtaining a set of user parameters corresponding to the user identifier according to the parameter collection configuration information, and obtaining a set of user behaviors corresponding to the set of user parameters comprises:
collecting user information corresponding to the user identification from a network element and/or a network management system;
extracting the user parameter set from the user information according to the parameter acquisition configuration information;
and acquiring the user behavior set corresponding to the user parameter set based on a preset behavior analysis strategy.
4. The method of claim 1, wherein the obtaining the user parameter corresponding to the user identifier according to the parameter collection configuration information comprises:
and acquiring the latest user parameters corresponding to the user identification from a network element and/or a network management system according to the parameter acquisition configuration information.
5. The method of claim 1, further comprising:
when behavior analysis is carried out, acquiring a user identifier corresponding to an analysis target user;
judging whether the parameter acquisition configuration information is configured for the user identifier;
if yes, acquiring a user parameter corresponding to the corresponding user identifier according to the parameter acquisition configuration information; if not, acquiring user information corresponding to the user identification from the network element and/or the network management system, and acquiring user behavior information according to the user information based on a preset behavior analysis strategy.
6. The method of claim 1, further comprising:
and if the parameter acquisition configuration information is changed, training the user behavior prediction model according to the new parameter acquisition configuration information.
7. A user behavior analysis device provided in a network data analysis function (NWDAF) includes:
the information configuration module is used for configuring parameter acquisition configuration information corresponding to the user identification;
the data acquisition module is used for acquiring user parameters corresponding to the user identification according to the parameter acquisition configuration information during behavior analysis;
and the behavior prediction module is used for predicting the user behavior by using the trained user behavior prediction model according to the user parameters to obtain user behavior prediction information.
8. The apparatus of claim 7, further comprising:
a model training module comprising:
the sample acquisition unit is used for acquiring a user parameter set corresponding to the user identifier according to the parameter acquisition configuration information and acquiring a user behavior set corresponding to the user parameter set when a preset user behavior model is trained;
and the training execution unit is used for generating a training sample based on the user parameter set and the user behavior set, training the user behavior model by using a deep learning method and based on the training sample, and obtaining a trained user behavior prediction model.
9. The apparatus of claim 8, wherein,
the sample acquisition unit is used for acquiring user information corresponding to the user identification from a network element and/or a network management system; extracting the user parameter set from the user information according to the parameter acquisition configuration information; and acquiring the user behavior set corresponding to the user parameter set based on a preset behavior analysis strategy.
10. The apparatus of claim 7, wherein,
and the data acquisition module is used for acquiring the latest user parameters corresponding to the user identification from a network element and/or a network management system according to the parameter acquisition configuration information.
11. The apparatus of claim 7, further comprising:
the behavior prediction module is used for acquiring a user identifier corresponding to an analysis target user during behavior analysis; judging whether the parameter acquisition configuration information is configured for the user identifier;
if so, the data acquisition module acquires the user parameters corresponding to the corresponding user identification according to the parameter acquisition configuration information; if not, the data acquisition module acquires user information corresponding to the user identification from a network element and/or a network management system, and the behavior prediction module acquires the user behavior information based on a preset behavior analysis strategy and according to the user information.
12. The apparatus of claim 7, further comprising:
and the model updating module is used for training the user behavior prediction model according to the new parameter acquisition configuration information if the parameter acquisition configuration information changes.
13. A user behavior analysis device, comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of any of claims 1-6 based on instructions stored in the memory.
14. A network data analysis function, NWDAF, comprising:
a user behaviour analysis apparatus according to any one of claims 7 to 13.
15. A computer readable storage medium having stored thereon computer program instructions which, when executed by one or more processors, implement the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010803067.4A CN114124724A (en) | 2020-08-11 | 2020-08-11 | User behavior analysis method, device, NWDAF and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010803067.4A CN114124724A (en) | 2020-08-11 | 2020-08-11 | User behavior analysis method, device, NWDAF and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114124724A true CN114124724A (en) | 2022-03-01 |
Family
ID=80373568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010803067.4A Withdrawn CN114124724A (en) | 2020-08-11 | 2020-08-11 | User behavior analysis method, device, NWDAF and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114124724A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953724A (en) * | 2023-03-14 | 2023-04-11 | 智因科技(深圳)有限公司 | User data analysis and management method, device, equipment and storage medium |
| CN116017742A (en) * | 2023-02-14 | 2023-04-25 | 广州爱浦路网络技术有限公司 | Data processing method, system and storage medium based on multistage NWDAF |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109600243A (en) * | 2017-09-30 | 2019-04-09 | 华为技术有限公司 | Data analysing method and device |
| CN110312279A (en) * | 2018-03-27 | 2019-10-08 | 电信科学技术研究院有限公司 | A kind of monitoring method and device of network data |
| CN110519795A (en) * | 2018-05-21 | 2019-11-29 | 华为技术有限公司 | A kind of method and device of determining background traffic transmission strategy |
| CN110620822A (en) * | 2019-09-27 | 2019-12-27 | 腾讯科技（深圳）有限公司 | Network element determination method and device |
| CN110650034A (en) * | 2018-06-26 | 2020-01-03 | 华为技术有限公司 | Information processing method and device |
| CN110769455A (en) * | 2018-07-26 | 2020-02-07 | 华为技术有限公司 | Data collection method, equipment and system |
| CN110912723A (en) * | 2018-09-17 | 2020-03-24 | 华为技术有限公司 | Communication method and device |
-
2020
- 2020-08-11 CN CN202010803067.4A patent/CN114124724A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109600243A (en) * | 2017-09-30 | 2019-04-09 | 华为技术有限公司 | Data analysing method and device |
| CN110312279A (en) * | 2018-03-27 | 2019-10-08 | 电信科学技术研究院有限公司 | A kind of monitoring method and device of network data |
| CN110519795A (en) * | 2018-05-21 | 2019-11-29 | 华为技术有限公司 | A kind of method and device of determining background traffic transmission strategy |
| CN110650034A (en) * | 2018-06-26 | 2020-01-03 | 华为技术有限公司 | Information processing method and device |
| CN110769455A (en) * | 2018-07-26 | 2020-02-07 | 华为技术有限公司 | Data collection method, equipment and system |
| CN110912723A (en) * | 2018-09-17 | 2020-03-24 | 华为技术有限公司 | Communication method and device |
| CN110620822A (en) * | 2019-09-27 | 2019-12-27 | 腾讯科技（深圳）有限公司 | Network element determination method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116017742A (en) * | 2023-02-14 | 2023-04-25 | 广州爱浦路网络技术有限公司 | Data processing method, system and storage medium based on multistage NWDAF |
| CN116017742B (en) * | 2023-02-14 | 2024-01-30 | 广州爱浦路网络技术有限公司 | Data processing method, system and storage medium based on multistage NWDAF |
| CN115953724A (en) * | 2023-03-14 | 2023-04-11 | 智因科技(深圳)有限公司 | User data analysis and management method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977208B (en) | Dialogue system integrating FAQ (failure-based query language) and task and active guidance | |
| CN114124724A (en) | User behavior analysis method, device, NWDAF and storage medium | |
| CN111400596B (en) | Information sharing method and device | |
| CN109743286A (en) | A kind of IP type mark method and apparatus based on figure convolutional neural networks | |
| CN104427547B (en) | Business and network associate method of testing, apparatus and system | |
| CN107256428A (en) | Data processing method, data processing equipment, storage device and the network equipment | |
| CN109086276B (en) | Data translation method, device, terminal and storage medium | |
| CN111611351B (en) | Control method and device for online customer service session and electronic equipment | |
| CN107395404B (en) | The method and apparatus for prompting network environment for network application, predicting service quality | |
| CN110751215A (en) | Image identification method, device, equipment, system and medium | |
| CN108768695A (en) | The problem of KQI localization method and device | |
| CN109815319A (en) | Information processing method and information processing unit | |
| CN108039173A (en) | Voice messaging input method, mobile terminal, system and readable storage medium storing program for executing | |
| CN109448710A (en) | Method of speech processing and device, household appliance, storage media electronic device | |
| CN111163482A (en) | Data processing method, device and storage medium | |
| CN109726808B (en) | Neural network training method and device, storage medium and electronic device | |
| CN107770730B (en) | Determine method, server and the storage medium of information of vehicles | |
| CN109976852A (en) | Game APP login interface setting method and equipment | |
| CN104915355B (en) | A kind of user classification method, device and server | |
| CN106843461B (en) | Interactive output method for robot and robot | |
| CN107196979A (en) | Pre- system for prompting of calling out the numbers based on speech recognition | |
| CN102129575B (en) | Pornographic image analysis system based on color space skin color model | |
| CN115390678B (en) | Virtual human interaction method and device, electronic equipment and storage medium | |
| CN110969240A (en) | Pruning method, device, equipment and medium for deep convolutional neural network | |
| CN112333756B (en) | Regional network quality monitoring method, system, electronic 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220301 |