CN112529638A - Service demand dynamic prediction method and system based on user classification and deep learning - Google Patents

Service demand dynamic prediction method and system based on user classification and deep learning Download PDF

Info

Publication number
CN112529638A
CN112529638A CN202011526423.9A CN202011526423A CN112529638A CN 112529638 A CN112529638 A CN 112529638A CN 202011526423 A CN202011526423 A CN 202011526423A CN 112529638 A CN112529638 A CN 112529638A
Authority
CN
China
Prior art keywords
user
service
service demand
data
model
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.)
Granted
Application number
CN202011526423.9A
Other languages
Chinese (zh)
Other versions
CN112529638B (en
Inventor
刘志中
丰凯
初佃辉
王莹洁
王鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yantai University
Original Assignee
Yantai University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yantai University filed Critical Yantai University
Priority to CN202011526423.9A priority Critical patent/CN112529638B/en
Publication of CN112529638A publication Critical patent/CN112529638A/en
Application granted granted Critical
Publication of CN112529638B publication Critical patent/CN112529638B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The scheme firstly classifies large-scale users based on a k-means algorithm and carries out service demand based on service use data of each type of users, so that the problems of data sparseness and cold start can be solved; secondly, a depth interaction neural network model with an enhanced attention mechanism is constructed in the embodiment, and service demand prediction is carried out based on the AMEDIN model, wherein the AMEDIN model firstly captures interaction relations between different scenes and service demands in a self-adaptive manner through an interaction unit, so that the influence of the different scenes on the service demands is explicitly modeled; then, combining scene characteristics, interaction relations and service requirement characteristics, and acquiring influence weights of different scenes on service requirements based on an attention mechanism; and finally, training an AMEDIN model based on the user characteristics, the weighted scene characteristics and the service requirement characteristics, and realizing the dynamic prediction of the service requirement of the context awareness based on the trained AMEDIN model.

Description

Service demand dynamic prediction method and system based on user classification and deep learning
Technical Field
The disclosure relates to the technical field of computer application, in particular to a service demand dynamic prediction method and system based on user classification and deep learning.
Background
In recent years, with the rapid development and popularization of service computing, the internet of things, intelligent terminals and 5G networks, more and more users can access services with rich functions from different fields at any time and any place to complete work and daily life affairs. With the rapid increase of the number of available services on the network, it is difficult for users to quickly and timely find the services meeting their needs, which seriously affects the satisfaction of users and reduces the utilization rate of service resources. Active service recommendation gradually becomes a key technology for realizing intelligent service, and dynamic prediction of service requirements is a basis for realizing active service recommendation. How to realize dynamic prediction of service requirements has become one of the key problems to be solved urgently in the field of intelligent services.
In recent years, researchers at home and abroad have made researches for the problem and have obtained certain research results. The inventor finds that, on one hand, in practical application, since the records of the service usage of a single user are less, the service demand prediction based on the data of the single user is difficult to realize; most of the existing research works are based on collaborative filtering, support vector machines, matrix decomposition and machine learning methods to realize the prediction of user service requirements; although the research work obtains good results, the precision of the existing method is seriously dependent on the data volume of a training set, and the problems of data sparseness and cold start often exist, so that the problem of low service prediction precision of a single-class user is caused; on the other hand, the influence of different scenes on the service requirement of the user is generally regarded as important by the existing research work, so that the model cannot fully learn the influence of different scenes on the service requirement, and the accuracy of service requirement prediction is reduced; meanwhile, the influence of the scene where the user is located on the service requirement of the user is not fully considered in the existing research work, so that the service requirement prediction precision is not high.
Disclosure of Invention
In order to overcome the defects of the prior art, the scheme well overcomes the problems of data sparseness and cold start by clustering large-scale users and predicting the service demand based on service use data of the same class of users; meanwhile, an attention mechanism enhanced deep interaction neural network model is provided to obtain the interaction relation between different scenes and the service requirements, so that the influence weight of the different scenes on the service requirements is obtained, and the interpretability and the accuracy of service requirement prediction are effectively improved.
According to a first aspect of the embodiments of the present disclosure, there is provided a service demand dynamic prediction method based on user classification and deep learning, including:
acquiring relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information; classifying users by utilizing a pre-trained classification model, and dynamically predicting service requirements by utilizing a pre-trained attention mechanism enhanced deep interaction neural network model according to a classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
Further, the specific step of classifying the user includes: acquiring a user training sample set, and randomly selecting a preset number of samples as a clustering center; clustering users in the training samples; and calculating the mean value of the samples in the current classes as a new clustering center, and sequentially iterating until the iteration center is unchanged or the maximum iteration number is reached.
Further, after the user finishes clustering, combining the user category labels and the user characteristics after the user clustering to form user characteristic data, sequencing the user characteristic data in an ascending order according to the user category labels, finally combining the sequenced user characteristic data, the scene characteristic data and the service characteristic data to form training data of a model, and training the attention mechanism enhanced deep interaction neural network model by using the training data.
Furthermore, in order to obtain the interaction relationship between different scenes and service requirements, data needs to be preprocessed before being input into the interaction unit, and firstly, data with the same service requirements are divided into a group for each user; and then, extracting different scene characteristics in the same group of data, and combining the scene characteristics with the user characteristics and the service requirement characteristics to form a piece of sample data.
Further, after the interactive relation between different scene features and service requirement features is obtained, pooling is carried out on the scene features in an average pooling mode to obtain pooled scene features of a plurality of scene features, and the pooled scene features represent main scene features of a plurality of scenes initiating service requirements; and acquiring an interactive relation between the pooling scene characteristics and the service requirement characteristics through the interactive unit.
Further, when calculating the influence weight of different scenes on the service demand, the scene features and the interaction relation corresponding to the pooling features are combined into a new splicing vector, the vector output through the attention mechanism is the weighted sum of the splicing vector and the influence weight, and the vector represents the scene features with obvious influence degree on the service demand initiated by the user.
According to a second aspect of the embodiments of the present disclosure, there is provided a service demand dynamic prediction system based on user classification and deep learning, including:
the data acquisition unit is configured to acquire relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information;
the service demand prediction unit is configured to classify the users by utilizing the pre-trained classification model and dynamically predict the service demand by utilizing the pre-trained attention mechanism enhanced deep interaction neural network model according to the classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the memory, where the processor implements the method for dynamically predicting service demand based on user classification and deep learning when executing the program.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements the method for dynamic prediction of service demand based on user classification and deep learning.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) according to the scheme, large-scale users are classified based on a K-means algorithm, so that users with similar attributes are classified into one class, similar users have similar service using behaviors, the problems of data sparseness and cold start can be well solved based on service using data of one class of users, and high-precision service demand prediction is achieved.
(2) According to the scheme disclosed by the disclosure, an attention mechanism enhanced deep interaction neural network model AMEDIN is constructed, and a context-aware service demand dynamic prediction method is provided based on the AMEDIN. The method captures the interaction relation between different scenes and the service requirements, and obtains the influence weight of the different scenes on the service requirements, so that the scenes with strong relevance with the service requirements obtain higher influence weight, and the method plays a leading role in predicting the context-aware service requirements.
(3) The scheme of the present disclosure introduces an interaction unit. The interaction relation between a plurality of scenes and the service requirements can be explicitly modeled through the interaction unit, the nonlinear relation between different scenes and the service requirements can be fully captured, and the accuracy of service requirement prediction can be improved.
(4) According to the scheme, through the combination of the interaction unit and the attention mechanism, the influence weight of different scenes on the service demand is dynamically acquired, and the scene characteristics with large influence on the user service demand are mined, so that the interpretability and the precision of service demand prediction are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a diagram of an amedn model structure according to a first embodiment of the present disclosure;
fig. 2(a) -2 (d) are graphs illustrating loss values of the amedn model on Movielens data sets according to the first embodiment of the disclosure;
fig. 3(a) -3 (d) are graphs illustrating loss values of the amedn model on the Alibaba data set according to the first embodiment of the disclosure;
fig. 4 is a graph illustrating the accuracy of different models in the Movielens data set according to the first embodiment of the disclosure;
FIG. 5 is a graph illustrating the accuracy of different models in the Alibaba data set according to the first embodiment of the disclosure;
FIG. 6 is a schematic diagram of RMSE on a Movielens dataset for different models described in the first embodiment of the present disclosure;
fig. 7 is a schematic MAE of different models on Movielens data set according to the first embodiment of the disclosure;
FIG. 8 is a schematic diagram of RMSE on an Alibaba data set for different models according to one embodiment of the present disclosure;
fig. 9 is a schematic diagram of MAE of different models on an Alibaba data set according to the first embodiment of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless otherwise defined, all technical and scientific terms used in the present examples have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The first embodiment is as follows:
the embodiment aims to provide a service demand dynamic prediction method based on user classification and deep learning.
A dynamic service demand prediction method based on user classification and deep learning comprises the following steps:
acquiring relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information; classifying users by utilizing a pre-trained classification model, and dynamically predicting service requirements by utilizing a pre-trained attention mechanism enhanced deep interaction neural network model according to a classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
In order to improve the accuracy of dynamic prediction of context-aware service demand, in this embodiment, large-scale users are classified based on a K-means algorithm; and then, designing an attention mechanism enhanced deep interaction neural network model AMEDIN to obtain the interaction relation between different scenes and the service requirements, and further obtaining the influence weight of the different scenes on the service requirements. The amedn model and its main operation mechanism are introduced below.
In service use, the characteristic information, the scene information and the proposed service requirement information of a user can be obtained through the intelligent terminal, the Internet of things and the intelligent wearable device, so that relevant data when the user proposes a service requirement can be formed, and data support is provided for realizing context-aware service requirement prediction. For the problem of dynamic prediction of service demand of context awareness, a service usage data model is defined as shown in formula (1):
SAR＝<UF，CF,SRF>#(1)
wherein UF ═ is<uf1,…,ufk>The user characteristics are represented, and mainly comprise the gender, age, occupation, income and the like of the user. CF ═<cf1,…cfh>And representing scene characteristics, mainly comprising time, position, weather, event, companions and the like set forth by service demands. SRF ═<srf1,…,srfl>The service requirement characteristics are represented and mainly comprise the domain to which the service belongs, the service name, the service function, the service level and the like. The user characteristics, the scene characteristics and the service requirement characteristic vector have good expansibility, and related characteristics can be added or subtracted according to needs.
The method for dynamically predicting the service demand based on user classification and deep learning in the embodiment comprises the following steps:
(1) user classification
In real life, there are different kinds of services available in different fields, but the kinds and the number of services used by a single user are limited with respect to the available services, and it is difficult for a single user to use services in different scenarios to cover all service usage information. However, when a plurality of users use services under different situations, a large amount of service use data is generated, and the service use data of the plurality of users under different situations are classified, so that similar users are classified into the same category, and similar users in the same category often have similar service requirements under different situations, so that the service use data of the similar users are abundant compared with a single user, and the accuracy of the service requirement prediction model is improved. In this embodiment, the value intervals of each feature of the user are different, so that the features with higher value intervals dominate the model prediction process, and the user classification effect is seriously affected. The calculation formula for the user characteristic normalization is shown in formula (2).
Figure BDA0002850727530000051
Wherein x isiFeatures, mean, representing each dimension of the user's featuresiMean, std, representing each dimension in the user's featuresiAnd the standard deviation of each dimension in the user characteristics is represented, and the normalized user characteristic data conforms to normal distribution with the mean value of 0 and the standard deviation of 1. After user characteristic data are standardized, a user classification center m and the number k of the user classification centers are initialized randomly, and k samples are selected randomly from the user characteristic data to serve as the centers of user classification
Figure BDA0002850727530000052
After the user classification center is obtained, calculating the distance between each user feature in the training sample and the user classification center through the Euclidean distance, and classifying the users in the training sample into the class closest to the user classification center, wherein the calculation formula of the Euclidean distance is shown as a formula (3).
Figure BDA0002850727530000061
Wherein x isiRepresenting the user characteristic data after normalizationUser characteristics of i users, mlRepresenting the user classification center, diRepresenting a user xiTo the user classification centre mlA smaller distance indicates a user xiBelongs to a user classification center mlThe greater the probability of (a), the greater the distance, the smaller the probability. According to the Euclidean distance, dividing each user into user classification centers with the nearest distance to form a user classification result C(t). Then, a new user classification center m is calculated for the user classification resultt+1And calculating the mean value of the samples in each user classification as a new user classification center, wherein the calculation formula is shown as a formula (4).
Figure BDA0002850727530000062
Wherein x isiRepresenting the user profile of the ith user in the normalized user profile data.
Figure BDA0002850727530000063
Representing the ith user classification center in the t +1 th iteration. After obtaining a new user classification center, classifying each user into the user classification center with the nearest distance according to a formula (3) to form a new user classification result C(t+1)If in the iterative process, the user classification center mtAnd user classification result C(t)The iteration times which are not changed or trained reach the maximum iteration times to obtain the optimal user classification result C*Otherwise, recalculating the distance from each user to the user classification center and the new user classification center until obtaining the optimal user classification result C*。
Figure BDA0002850727530000064
Figure BDA0002850727530000071
(2) Attention mechanism enhanced deep interaction neural network model (AMEDIN)
The specific structure of the attention mechanism enhanced deep interaction bible network model in this embodiment includes:
1) interactive relationship acquisition based on interactive units
In order to obtain the interaction relationship between different scenes and service requirements, the data needs to be preprocessed before being input into the interaction unit. Firstly, aiming at the ith user, dividing data with the same service requirement into a group; then, different scene features (noted as different scene features in the same group of data) are extracted
Figure BDA0002850727530000072
) From CFiCombining with user characteristics and service requirement characteristics to form a sample data Xi，
Figure BDA0002850727530000073
Wherein, UFiA feature vector representing an ith user; SRFiIndicating that a user is present in a scene
Figure BDA0002850727530000074
Feature vectors of the proposed service requirements are set down; for the service usage history dataset, it is preprocessed as described above, resulting in an input dataset D ═ X for the model1,…,Xi,…,Xn}。
When inputting data to AMEDIN model, data X is inputiMultiple scene features in
Figure BDA0002850727530000075
And service requirement feature SRFiInputting the scene characteristics to an interactive unit, and acquiring each scene characteristic through the interactive unit
Figure BDA0002850727530000076
And service requirement feature SRFiThe interaction relationship between them. The obtaining formula of the interaction relationship is shown as formula (2):
Figure BDA0002850727530000077
wherein the content of the first and second substances,
Figure BDA0002850727530000078
representing scene features for the output of interactive elements
Figure BDA0002850727530000079
And service requirement feature SRFiSigma denotes the ReLU (rectifier activation function) activation function, W1Representing a weight matrix, b1A vector of the offset is represented, and,
Figure BDA00028507275300000710
representing the vector splicing operator.
After the interactive relation between different scene characteristics and service requirement characteristics is obtained, the scene characteristics are subjected to average pooling
Figure BDA00028507275300000711
Pooling to obtain pooled scene features of multiple scene features
Figure BDA00028507275300000712
The pooled scene features represent main scene features of a plurality of scenes initiating service demands, and the interaction relation between the pooled scene features and the service demand features is obtained through the interaction unit
Figure BDA00028507275300000713
The measurement formula is shown in formula (3):
Figure BDA00028507275300000714
wherein the content of the first and second substances,
Figure BDA00028507275300000715
mean poolingScene features
Figure BDA00028507275300000716
And service requirement feature SRFiThe mutual relationship between the two, sigma denotes the ReLU activation function, W2Representing a weight matrix, b2A vector of the offset is represented, and,
Figure BDA00028507275300000717
representing the vector splicing operator. Based on the method, the interactive relation between the scene characteristics with the incidence relation and the service requirement characteristics and the interactive relation between the pooling scene characteristics and the service requirement characteristics can be obtained.
2) Influence weight learning based on attention mechanism
Inspired by the human visual attention running mechanism, some scholars propose an attention mechanism. In recent years, attention mechanisms have been successfully applied in the fields of computer vision, natural language processing, and service recommendation. In the embodiment, the influence weight of different scenes on the service demand is acquired by introducing an attention mechanism, so that the model can effectively capture scene characteristics having important influence on the service demand, and the prediction capability and the interpretability of the model are improved. When calculating the influence weight of different scenes on service requirements, the scene characteristics are calculated
Figure BDA0002850727530000081
And the corresponding interaction relation
Figure BDA0002850727530000082
Interaction relation corresponding to pooled features
Figure BDA0002850727530000083
Splicing into a new vector, noted
Figure BDA0002850727530000084
As shown in equation (4):
interaction ei polHigh-order features between the represented scene and the service requirements, in reaction toThe high-order interaction relation of scenes and services is increased to improve the prediction precision of the model
Figure BDA0002850727530000085
Wherein the content of the first and second substances,
Figure BDA0002850727530000086
representing the concatenation of the vectors. Is provided with
Figure BDA0002850727530000087
Is composed of
Figure BDA0002850727530000088
Feature on service demand SRFiThe impact weight of (a) is, according to the attention mechanism,
Figure BDA0002850727530000089
the calculation formula (2) is shown in formula (5):
Figure BDA00028507275300000810
where n represents the number of service demands historically placed by the user. The formula (5) includes two operations, one is composed of
Figure BDA00028507275300000811
And the inner product operation between vectors is represented, and the second is softmax function operation. The relation between the scene characteristics and the service requirement characteristics can be extracted through inner product operation; generating weight through the result of the standard inner product operation of the softmax function
Figure BDA00028507275300000812
Similarly, according to the formula (5), the scene characteristics can be obtained
Figure BDA00028507275300000813
Feature on service demand SRFiInfluence weight of
Figure BDA00028507275300000814
In acquiring each scene feature
Figure BDA00028507275300000815
Feature on service demand SRFiAfter the influence weight of (c), the output of the attention mechanism is shown in equation (6):
Figure BDA00028507275300000816
output of attention mechanism
Figure BDA00028507275300000817
As a spliced vector
Figure BDA00028507275300000818
And the weighted sum of the influence weights, the vector represents the scene characteristics with large influence on the user initiated service demand.
3) Dynamic prediction of service demand
After scene characteristics which have large influence on user initiated service requirements are obtained, the prediction module based on the AMEDIN model realizes prediction of the service requirements. When the service demand forecasting module is trained, the input data of the model is defined as
Figure BDA0002850727530000091
Wherein, UFiA feature vector representing the user is generated,
Figure BDA0002850727530000092
representing weighted scene features derived from attention mechanisms, SRFiRepresenting a service demand characteristic; y isiLabels representing input data, yiE {0,1}, when yiWhen equal to 0, it means that the user does not have the current SRFiA corresponding service requirement; when y isiWhen 1, it indicates that the user has the current SRFiA corresponding service requirement; the learning function of the service demand prediction module is shown in equation (7):
Figure BDA0002850727530000093
where σ denotes the ReLU activation function, W denotes the weight matrix, IiRepresenting the input data and b representing the offset vector.
In the amedn model, a cross entropy loss function (CrossEntropyLoss) is selected to optimize the constructed model, and the cross entropy loss function is shown as formula (8):
Figure BDA0002850727530000094
where M represents the data set, N is the number of data samples, I represents the input to the model, y represents the actual label of the input data,
Figure BDA0002850727530000095
representing a predicted label. In view of the fact that the Adam optimization algorithm has a good optimization effect, in the service demand prediction model, Adam is selected as the optimization algorithm of the amedn model in the embodiment. In each update of the model, the Adam algorithm calculates and corrects the first moment deviation and the second moment deviation of the model parameters, and then moves along the negative direction of the parameter gradient until the model is updated to be optimal, wherein the model is updated as shown in the formula (9):
Figure BDA0002850727530000096
wherein theta represents a trainable model parameter, t-1 represents a previous time step, eta is a learning rate,
Figure BDA0002850727530000097
and
Figure BDA0002850727530000098
respectively, the deviation of the first moment corrected at the last time step and the deviation of the second moment correctedThe difference,. epsilon.is a constant. The context-aware service demand dynamic prediction algorithm is shown as algorithm 1. When the AMEDIN model carries out service requirement prediction of context awareness, the input data of the AMEDIN model is set as
Figure BDA0002850727530000099
Wherein, UFoA feature that is representative of the current user,
Figure BDA00028507275300000910
representing a plurality of scene features, wherein only one scene feature in the m scene features is the scene feature where the user is located currently, and the rest scene features are empty; SRFtIs the t-th service requirement characteristic.
During data processing, scenes are already processed, 50 scenes used by the same user when the same service is used are taken, and less than 50 scenes are filled with 0 in the back. The 50 scenes of the user are not time series, so that which position the current scene is placed has no influence on the prediction result.
Figure BDA0002850727530000101
Figure BDA0002850727530000111
Further, in this embodiment, experiments and analysis of experimental results are performed on the service demand dynamic prediction method based on context awareness, which are specifically as follows:
1) experimental data preparation
Currently, there is no data set for validating context-aware dynamic predictions of service demand. In order to verify the effectiveness of the method provided in this embodiment, a MovieLens dataset and an Alibaba dataset provided by a sky pool website are used in this embodiment. Wherein the Movielens data contains 100 ten thousand sample data from 6000 users scoring 18 categories of 4000 movies; the Alibaba dataset is data for a large number of users' advertisement click-through rates provided by the company arizaba. Regarding the MovieLens data, regarding the user characteristics as the user characteristics in service demand prediction, mapping the scene characteristics as the scene characteristics in service demand prediction, mapping the movie characteristics as the service demand characteristics in service demand prediction, and mapping the evaluation value of the movie of the user as a label of the user service demand; regarding the Alibaba data, the user characteristics are regarded as the user characteristics in service demand prediction, the scene characteristics are mapped to the scene characteristics in service demand prediction, the advertisement characteristics are mapped to the service demand characteristics in service demand prediction, and the value of whether the user clicks the advertisement is mapped to the label in user service demand prediction. In the experiment, the scoring category in the Movielens data is converted into two categories in the present embodiment, the original user score of the movie is a continuous value from 1 to 5, the samples with the scores of 4 and 5 are marked as positive in the present embodiment, and the rest are marked as negative. Since the data size of Alibaba is relatively large, 100 ten thousand pieces of data are randomly sampled from the data to serve as experimental data in the embodiment. In the experiment, 5 scene features in each data set are considered with emphasis, information in the Movielens data is shown in table 1, and information in the Alibaba data is shown in table 2.
Table 1 information in Movielens data
Figure BDA0002850727530000112
Figure BDA0002850727530000121
TABLE 2 information in Alibaba data
Figure BDA0002850727530000122
Figure BDA0002850727530000131
The experimental environment is a personal computer, the operating system is 64 bits of Windows 10 professional edition, the CPU is Intel i 78750H, and the RAM is 8 GB. In the experiment, an open-source TensorFlow 2.0GPU is selected as an implementation framework of a prediction model, and a Python 3.6 programming is adopted to implement the prediction model.
2) Evaluation index
In this embodiment, the deviation between the predicted value and the true value of the service requirement is calculated by using the root mean square error RMSE, the average absolute error MAE, and the accuracy Acc, so as to measure the effectiveness of the prediction method provided in this embodiment. The formula for calculating RMSE and MAE is shown in formula (10) and formula (11).
Figure BDA0002850727530000132
Figure BDA0002850727530000133
Wherein, the smaller the values of RMSE and MAE are, the higher the prediction precision of the model is; a larger value of Acc indicates a higher prediction accuracy of the model.
3) User data packet
In order to improve the prediction accuracy of service requirements, users are clustered, and similar users are classified into the same user group. Firstly, the user characteristics in the data sets of the Alibaba provided by the MovieLens data set and the skyscraper website adopted in the embodiment are standardized, so that the user characteristics with different dimensions have comparability, and the accuracy of user clustering is improved. The calculation formula for user characteristic normalization is shown in formula (12).
Figure BDA0002850727530000134
Wherein x isiFeatures, mean, representing each dimension of the user's featuresiMean, std, representing each dimension in the user's featuresiRepresenting the standard deviation of each dimension in the user feature, normalized user featureThe data fit a normal distribution with a mean of 0 and a standard deviation of 1. And then, clustering the users by using a K-means algorithm on the standardized user characteristic data, wherein the clustering algorithm is an unsupervised learning method, the optimal user clustering number is obtained by carrying out iterative training on training data for multiple times, the training is repeated for 10 times in the embodiment, 2 to 10 user clustering centers are obtained in each training, and the maximum number of iterations is 1000. For each training, a different CH (Calinski-Harabaz Index) Index was calculated for a different user cluster center. The formula for calculating the CH index is shown in formula (13).
Figure BDA0002850727530000141
Wherein m is the number of samples in the training set, and k is the number of categories in the user clustering center. B iskAs a covariance matrix between classes, WkTr () is the trace of the class matrix for the covariance matrix of the data inside the class. The larger the value of the CH index is, the smaller the covariance of data in the user classes is, and the larger the covariance between the user classes is, the better the user clustering effect is. Through 10 times of repeated training, similar users in the MovieLens data set are clustered into 7 user categories, and similar users in the Alibaba data set are clustered into 8 user categories. After the user finishes clustering, merging the user category labels and the user characteristics after the user clustering together to form user characteristic data, sequencing the user characteristic data in an ascending order according to the user category labels, and finally merging the sequenced user characteristic data, scene characteristic data and service characteristic data together to form training data of the AMEDIN model.
4) AMEDIN model parameter setting
In the AMEDIN model, an interaction unit is used for learning interaction relations between a plurality of scenes and service requirements, the number of network layers of the interaction unit has important influence on the performance of the model, and in order to enable the AMEDIN model to have better performance, the optimal value of the number of layers is determined through an experimental method. In the experiment, Adam is adopted as an optimization algorithm, and the initial learning rate is 0.00001. And observing the performance of the AMEDIN model by setting different layer numbers, and further determining the optimal value of the network layer number in the interaction unit. The results of the experiment are shown in table 3.
TABLE 3 Effect of the number of layers of the Interactive element network on the AMEDIN model Performance
Figure BDA0002850727530000142
As can be seen from table 3, increasing the number of layers of the interactive units helps to improve the model prediction accuracy. However, as the number of layers increases, the degree of improvement in model performance is limited. Meanwhile, the increase of the number of layers of the interaction units brings more parameter learning overhead to the model, so that the complexity of model training and the overfitting risk are increased. Based on the above experimental results, the performance and training consumption of the model are considered comprehensively, and in this embodiment, the number of network layers of the interaction unit is determined to be 4.
In addition, in the user service demand prediction model, the number of neuron nodes in each layer of the interaction unit has a large influence on the performance of the model, and in order to enable the model to have a good prediction capability, in the amedn model, the number of neuron nodes in each layer of the network is respectively set to be 16, 32, 64, 128 and 256, the model is executed, and the experimental result is recorded, and is shown in table 4.
TABLE 4 influence of interaction unit node number on AMEDIN model Performance
Figure BDA0002850727530000151
As can be seen from table 4, as the number of neuron nodes increases, the performance of the model is gradually improved; when the number of the nodes reaches 128, the performance of the model reaches the optimum; thereafter, as the number of nodes increases, the performance of the model all degrades. Meanwhile, increasing the number of nodes of the neuron increases the overhead of model training and the risk of overfitting. Based on the experimental result, in this embodiment, the number of nodes of each layer of network neurons in the amedn model interaction unit is set to 128.
In the user service demand prediction model, parameters of the model are optimized through an Adam algorithm, wherein the learning rate of the Adam algorithm has a large influence on the stability of the prediction model, in order to enable the model to have good prediction capability, the learning rate of the experiment is respectively set to be 1e-2, 1e-3, 1e-4 and 1e-5 in the AMEDIN model, the model is executed, and the experiment result is recorded, wherein the experiment result is shown in fig. 2 and fig. 3.
As can be seen from fig. 2 and 3, as the learning rate pair decreases, the behavior of the model gradually stabilizes; as can be seen from FIG. 2, when the learning rate of the AMEDIN model on the Movielens data set is greater than 1e-5, the model is overfitting, and the model parameters cannot be optimized. As can be seen from fig. 3, although the amedan model does not have a serious overfitting phenomenon on the Alibaba data set, the difference between the verification loss of the model and the training loss is large, and the optimal model parameters cannot be learned by better fitting the data distribution. Based on the experimental results, the learning rate of the amedn model is set to 1e-5 in the present embodiment.
5) Setting of contrast model parameters
To verify the effectiveness of the proposed method, five typical deep neural networks were selected for comparison with the amedn model constructed in this example. Five typical deep neural networks are: deep Neural Networks (DNNs), deep fms, Attention Interaction Networks (AIN), Attention Factorization Machines (AFMs), and Nerve Factorization Machines (NFMs).
For the deep neural network DNN, user characteristics, scene characteristics and service requirement characteristics are input into a full-connection network after passing through an Embedding layer (Embedding) respectively, and the service requirement of a user is predicted. In the experiment, the number of hidden layers is set to be 3, the number of nodes of the hidden layers is set to be 32, a cross entropy loss function is adopted, an Adam optimization algorithm is adopted, and the initial learning rate is set to be 0.001. For deep FM, after the user characteristics, the scene characteristics, and the service requirement characteristics are processed by an embedding layer, a Factorization Machine (FM) is used to extract low-order characteristics, and then DNN is used to perform high-order characteristic extraction, and then the extracted low-order characteristics are input to a full-connection network to predict the service requirement of the user. In the experiment, parameter setting of deep fm is consistent with that of the original paper, Dropout is set to be 0.5, Adam is selected as an optimization algorithm, and the initial learning rate is set to be 0.001. For AIN, the number of hidden layers is set to be 2, the number of nodes of the hidden layers is set to be 128, Adam is adopted as an optimization algorithm, and the initial learning rate is set to be 0.001.
For the AFM model, Dropout is set to be 0.5 according to the original paper, a batch training strategy with the size of 512 is used, Adam is selected as an optimization algorithm, and the initial value of the learning rate is set to be 0.001. The NFM is a neural network model for sparse data prediction, a factorization machine is enhanced under the neural network model to learn high-order interactive features, a batch training strategy with the size of 512 is set, Adam is adopted as an optimization algorithm, and the initial learning rate is 0.01. For the amedn model proposed in this embodiment, the number of layers of the interactive unit is set to 4, the number of nodes of the hidden layer is set to 128, Adam is used as an optimization algorithm, and the initial learning rate is 0.00001. For each network model, an Alibaba data set and a Movielens data set are used as experimental data, and the maximum iteration number is set to be 300.
6) Comparison of Performance of different models
In order to verify the effectiveness of the method proposed in this embodiment, the experiment uses 80% of the data set as training data and 20% of the data set as test data, and multiple models are trained and tested. Use is made of 4. The evaluation index given in section 2 measures the performance of each model. The results of the experiment are shown in Table 5.
TABLE 5 Performance evaluation of different models on two sets of data sets
Figure BDA0002850727530000161
Figure BDA0002850727530000171
As can be seen from table 5, when service demand prediction is performed, the amedn model provided in this embodiment is superior to other methods in the evaluation indexes Acc, RMSE, and MAE. In the Movielens data set, the AMEDIN model is respectively superior to the optimal result 1 in other methods in the evaluation index Acc. 14 percent; on the indices RMSE and MAE, 0.51% and 0.5% lead the suboptimal results, respectively. In the Alibaba data set, the AMEDIN model is respectively superior to the optimal result of 1.48% in other methods on the evaluation index Acc, and respectively leads to the suboptimal result of 1.06% and 1.6% on the indexes RMSE and MAE. According to the experimental results, the AMEDIN model provided by the embodiment can effectively capture different influences of a plurality of scenes on service requirements through the interaction unit and the attention mechanism; meanwhile, by extracting the interactive characteristics of a plurality of scenes and service requirements, the loss of the nonlinear relation between the scenes and the service requirements can be effectively reduced; on the other hand, the scene characteristics with the largest influence weight on the user service demand are obtained through the attention mechanism, and the prediction precision of the model is improved.
7) Convergence verification of different models
In order to verify the convergence of the method proposed in this embodiment, a plurality of models are trained and tested, respectively, and the parameter settings of the plurality of models are consistent with the above settings. The results of the experiment are shown in fig. 4 and 5. Wherein the ordinate represents the prediction accuracy and the abscissa represents the number of iterations of the model.
As can be seen from fig. 4 and 5, as the number of iterations increases, the prediction accuracy of the plurality of deep neural networks is continuously improved. As can be seen from fig. 4, the NFM model performed the weakest in the Movielens dataset. As can be seen from fig. 5, the performance of the DNN model is the weakest in the Alibaba dataset. The AMEDIN model provided in the embodiment has better prediction accuracy on two data sets. The AMEDIN model has good learning ability, and higher prediction accuracy can be obtained with fewer iterations.
8) Analysis of influence of different modules on AMEDIN model performance
In order to verify the effectiveness of obtaining the interactive relationship and the influence weight on improving the service demand prediction accuracy, different variants of the AMEDIN model are obtained by removing related operations, and the influence of different modules on the AMEDIN model performance is verified by comparing the variants of the AMEDIN model with the AMEDIN model. The AMEDIN model is consistent with the parameter settings of other variant models, the four models are trained and tested based on the same data set and an experimental platform, and the experimental results are shown in fig. 6 to 9, wherein the ordinate represents RMSE and MAE respectively, and the abscissa represents the iteration times of the algorithm.
From fig. 6 to fig. 9, it can be seen that, when the AMEDIN model does not consider the interaction relationship and does not use the attention mechanism with the AMEDIN model, the values of the RMSE and MAE evaluation indexes of the variant model of the AMEDIN are increased, and the AMEDIN model is superior to the other three variant models in the RMSE and MAE indexes.
In order to realize context-aware dynamic prediction of service requirements and further improve the initiative and intelligence of service recommendation, the embodiment provides a context-aware dynamic prediction method of service requirements. The research work constructs an attention mechanism enhanced deep interaction neural network model AMEDIN, and firstly, the interaction relation between a plurality of different scenes and service requirements is captured through an interaction unit in the AMEDIN model; then, acquiring the influence weight of a plurality of scenes on the service demand through an attention mechanism; and finally, constructing training data based on the output of the attention mechanism, and dynamically predicting the service requirement through a full-connection network. A large number of experiments are carried out based on a real data set, and the effectiveness of the method provided by the embodiment is verified; meanwhile, the effectiveness of the interaction unit and the attention mechanism on improving the model prediction accuracy is verified through experiments. In subsequent research work, main factors influencing the service demand prediction precision are further analyzed, influence rules of the factors on the service demand prediction are mined, and research on the service demand prediction is carried out based on the rules, so that the flexibility and the accuracy of the service demand prediction are improved.
Example two:
the embodiment aims to provide a service demand dynamic prediction system based on user classification and deep learning
A system for dynamic prediction of service demand based on user classification and deep learning, comprising:
the data acquisition unit is configured to acquire relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information;
the service demand prediction unit is configured to classify the users by utilizing the pre-trained classification model and dynamically predict the service demand by utilizing the pre-trained attention mechanism enhanced deep interaction neural network model according to the classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
Example three:
the embodiment aims at providing an electronic device.
An electronic device comprising a memory, a processor and a computer program stored in the memory for execution by the processor, wherein the processor implements a method for dynamic prediction of service demand based on user classification and deep learning, the method comprising:
acquiring relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information; classifying users by utilizing a pre-trained classification model, and dynamically predicting service requirements by utilizing a pre-trained attention mechanism enhanced deep interaction neural network model according to a classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
Example four:
it is an object of the present embodiments to provide a non-transitory computer-readable storage medium.
A non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method for dynamic prediction of service demand based on user classification and deep learning, comprising:
acquiring relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information; classifying users by utilizing a pre-trained classification model, and dynamically predicting service requirements by utilizing a pre-trained attention mechanism enhanced deep interaction neural network model according to a classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.

Claims (10)

1. A dynamic service demand prediction method based on user classification and deep learning is characterized by comprising the following steps:
acquiring relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information; classifying users by utilizing a pre-trained classification model, and dynamically predicting service requirements by utilizing a pre-trained attention mechanism enhanced deep interaction neural network model according to a classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
2. The method as claimed in claim 1, wherein the step of dynamically predicting the service demand based on the user classification and the deep learning comprises: acquiring a user training sample set, and randomly selecting a preset number of samples as a clustering center; clustering users in the training samples; and calculating the mean value of the samples in the current classes as a new clustering center, and sequentially iterating until the iteration center is unchanged or the maximum iteration number is reached.
3. The dynamic service demand prediction method based on user classification and deep learning as claimed in claim 1, characterized in that after the user completes the clustering, the user category labels and the user features after the user clustering are combined together to form user feature data, the user feature data are sorted in an ascending order according to the user category labels, finally, the sorted user feature data, the scene feature data and the service feature data are combined together to form training data of a model, and the training data are used for training the attention mechanism enhanced deep interaction neural network model.
4. The method as claimed in claim 1, wherein for obtaining the interaction relationship between different scenarios and service requirements, the data needs to be preprocessed before being input into the interaction unit, and first, for each user, the data with the same service requirements are grouped into one group; and then, extracting different scene characteristics in the same group of data, and combining the scene characteristics with the user characteristics and the service requirement characteristics to form a piece of sample data.
5. The dynamic service demand prediction method based on user classification and deep learning as claimed in claim 1, wherein after the interactive relationship between different scene features and service demand features is obtained, the scene features are pooled in an average pooling manner to obtain pooled scene features of a plurality of scene features, and the pooled scene features represent main scene features of a plurality of scenes initiating a service demand; and acquiring an interactive relation between the pooling scene characteristics and the service requirement characteristics through the interactive unit.
6. The method as claimed in claim 1, wherein when calculating the influence weights of different scenes on the service demand, the scene features and the interaction relationships corresponding to the interaction relationships and pooling features are combined into a new stitching vector, the output vector through the attention mechanism is the weighted sum of the stitching vector and the influence weights, and the vector represents the scene features with obvious influence degree on the service demand initiated by the user.
7. The dynamic service demand prediction method based on user classification and deep learning as claimed in claim 6, wherein after the scene features having a large influence on the user initiated service demand are obtained, the prediction of the service demand is realized based on the prediction module of the attention mechanism enhanced deep interaction neural network model.
8. A dynamic prediction system of service demand based on user classification and deep learning, comprising:
the data acquisition unit is configured to acquire relevant data when a user puts forward a service demand, wherein the relevant data comprises characteristic information of the user, scene information of the user and the service demand information;
the service demand prediction unit is configured to classify the users by utilizing the pre-trained classification model and dynamically predict the service demand by utilizing the pre-trained attention mechanism enhanced deep interaction neural network model according to the classification result;
the network model comprises an interaction unit, an influence weight learning module and a service demand prediction module, and the interaction relation between different scenes and service demands is captured through the interaction unit; further learning influence weights of different scenes on service requirements based on an attention mechanism through an influence weight learning module; and finally, realizing service demand prediction according to the influence weight through a service demand prediction module.
9. An electronic device comprising a memory, a processor and a computer program stored and executed on the memory, wherein the processor implements a method for dynamic prediction of service demand based on user classification and deep learning according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a method for dynamic prediction of service demand based on user classification and deep learning according to any one of claims 1 to 7.
CN202011526423.9A 2020-12-22 2020-12-22 Service demand dynamic prediction method and system based on user classification and deep learning Active CN112529638B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011526423.9A CN112529638B (en) 2020-12-22 2020-12-22 Service demand dynamic prediction method and system based on user classification and deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011526423.9A CN112529638B (en) 2020-12-22 2020-12-22 Service demand dynamic prediction method and system based on user classification and deep learning

Publications (2)

Publication Number Publication Date
CN112529638A true CN112529638A (en) 2021-03-19
CN112529638B CN112529638B (en) 2023-04-18

Family

ID=75002433

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011526423.9A Active CN112529638B (en) 2020-12-22 2020-12-22 Service demand dynamic prediction method and system based on user classification and deep learning

Country Status (1)

Country Link
CN (1) CN112529638B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113065698A (en) * 2021-03-25 2021-07-02 珠海大横琴科技发展有限公司 Service processing method and device
CN113095570A (en) * 2021-04-14 2021-07-09 上海市城市建设设计研究总院（集团）有限公司 Bicycle riding path recommendation method based on demand difference
CN113537623A (en) * 2021-07-30 2021-10-22 烟台大学 Attention mechanism and multi-mode based dynamic service demand prediction method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110880006A (en) * 2018-09-05 2020-03-13 广州视源电子科技股份有限公司 User classification method and device, computer equipment and storage medium
CN110995487A (en) * 2019-12-03 2020-04-10 深圳市物语智联科技有限公司 Multi-service quality prediction method and device, computer equipment and readable storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110880006A (en) * 2018-09-05 2020-03-13 广州视源电子科技股份有限公司 User classification method and device, computer equipment and storage medium
CN110995487A (en) * 2019-12-03 2020-04-10 深圳市物语智联科技有限公司 Multi-service quality prediction method and device, computer equipment and readable storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MEI L等: "An Attentive Interaction Network for Context-aware Recommendations", 《CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113065698A (en) * 2021-03-25 2021-07-02 珠海大横琴科技发展有限公司 Service processing method and device
CN113095570A (en) * 2021-04-14 2021-07-09 上海市城市建设设计研究总院（集团）有限公司 Bicycle riding path recommendation method based on demand difference
CN113537623A (en) * 2021-07-30 2021-10-22 烟台大学 Attention mechanism and multi-mode based dynamic service demand prediction method and system
CN113537623B (en) * 2021-07-30 2023-08-18 烟台大学 Attention mechanism and multi-mode based service demand dynamic prediction method and system

Also Published As

Publication number Publication date
CN112529638B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN112529638B (en) Service demand dynamic prediction method and system based on user classification and deep learning
CN107122375B (en) Image subject identification method based on image features
CN109376242B (en) Text classification method based on cyclic neural network variant and convolutional neural network
CN107683469A (en) A kind of product classification method and device based on deep learning
CN109492748B (en) Method for establishing medium-and-long-term load prediction model of power system based on convolutional neural network
CN111680147A (en) Data processing method, device, equipment and readable storage medium
CN112256866A (en) Text fine-grained emotion analysis method based on deep learning
CN113128671B (en) Service demand dynamic prediction method and system based on multi-mode machine learning
CN111859010A (en) Semi-supervised audio event identification method based on depth mutual information maximization
WO2023159756A1 (en) Price data processing method and apparatus, electronic device, and storage medium
CN112215629B (en) Multi-target advertisement generating system and method based on construction countermeasure sample
CN114881173A (en) Resume classification method and device based on self-attention mechanism
CN112529637B (en) Service demand dynamic prediction method and system based on context awareness
CN116452241B (en) User loss probability calculation method based on multi-mode fusion neural network
CN113743079A (en) Text similarity calculation method and device based on co-occurrence entity interaction graph
CN116050419A (en) Unsupervised identification method and system oriented to scientific literature knowledge entity
CN112463964B (en) Text classification and model training method, device, equipment and storage medium
CN114881172A (en) Software vulnerability automatic classification method based on weighted word vector and neural network
CN113837266A (en) Software defect prediction method based on feature extraction and Stacking ensemble learning
CN114357284A (en) Crowdsourcing task personalized recommendation method and system based on deep learning
CN113935413A (en) Distribution network wave recording file waveform identification method based on convolutional neural network
CN114187966A (en) Single-cell RNA sequence missing value filling method based on generation countermeasure network
CN113821571A (en) Food safety relation extraction method based on BERT and improved PCNN
Dražić et al. Technology matching of the patent documents using clustering algorithms
CN113590908A (en) Information recommendation method based on attention mechanism

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
GR01 Patent grant
GR01 Patent grant