CN117077901B - Travel data processing method and system - Google Patents
Travel data processing method and system Download PDFInfo
- Publication number
- CN117077901B CN117077901B CN202311340547.1A CN202311340547A CN117077901B CN 117077901 B CN117077901 B CN 117077901B CN 202311340547 A CN202311340547 A CN 202311340547A CN 117077901 B CN117077901 B CN 117077901B
- Authority
- CN
- China
- Prior art keywords
- emotion
- representing
- user
- data
- travel
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 230000008451 emotion Effects 0.000 claims abstract description 172
- 238000003066 decision tree Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000000638 solvent extraction Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 238000009499 grossing Methods 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 32
- 230000000694 effects Effects 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 15
- 230000002996 emotional effect Effects 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 11
- 230000001932 seasonal effect Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 230000000737 periodic effect Effects 0.000 claims description 8
- 238000012300 Sequence Analysis Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 4
- 230000000630 rising effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 239000004615 ingredient Substances 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a travel data processing method and a travel data processing system, which relate to the technical field of data processing and comprise the following steps: acquiring travel data, performing feature extraction and fusion on the original data by using a self-encoder, and performing smoothing treatment on the travel data and predicting trend by time sequence data analysis; carrying out emotion analysis on comment data, constructing an emotion similarity matrix, constructing an emotion network by using graph theory technology, and dividing the emotion network; constructing a predicted scenic spot popularity model based on the LSTM deep learning structure; optimizing a prediction model based on the partitioning result of the emotion network; performing multi-objective optimization on strategy generation by using an evolutionary algorithm; generating a strategy decision tree according to the emotion network, the prediction model and the optimization result; and generating an optimal travel path according to the current situation of the user and the dynamic adjustment strategy of the decision tree. The travel data processing method provided by the invention has more accurate prediction results, and enhances user experience and travel satisfaction.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a travel data processing method and system.
Background
As the number of business trips increases, a large amount of business trip data is generated and saved, including but not limited to scenic spot base information, user rating data, history of classical accesses, user behavior data, and user current context data. Traditional travel data processing methods rely mainly on simple statistical analysis or underlying time series prediction techniques, lacking in a thorough understanding of complex emotions and user behavior. These approaches have significant shortcomings in terms of prediction accuracy, data fusion capability, and personalized recommendations, resulting in a potentially suboptimal travel recommendation path and thus a limited user experience.
Aiming at the defects of the traditional method, the technology provides a new travel data processing method. The method combines deep learning, time sequence analysis, emotion analysis and graph theory technology, and can deeply mine and analyze travel data from multiple dimensions. In particular, it can more accurately predict popular trends of scenic spots, better understand the emotional trends of users through emotion analysis, and provide more accurate personalized travel route recommendations.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the existing traditional travel data processing method has the problems that the accuracy is not high, the emotion of a user cannot be deeply understood, personalized recommendation is lacked, various technical means are effectively integrated, the prediction accuracy is improved, and accurate travel path recommendation is realized.
In order to solve the technical problems, the invention provides the following technical scheme: a travel data processing method comprising:
acquiring travel data, performing feature extraction and fusion on the original data by using a self-encoder, and performing smoothing treatment on the travel data and predicting trend by time sequence data analysis; carrying out emotion analysis on comment data, constructing an emotion similarity matrix, constructing an emotion network by using graph theory technology, and dividing the emotion network; constructing a predicted scenic spot popularity model based on the LSTM deep learning structure; optimizing a prediction model based on the partitioning result of the emotion network; performing multi-objective optimization on strategy generation by using an evolutionary algorithm;
generating a strategy decision tree according to the emotion network, the prediction model and the optimization result; and generating an optimal travel path according to the current situation of the user and the dynamic adjustment strategy of the decision tree.
As a preferable mode of the travel data processing method according to the present invention, wherein: the acquired travel data comprise scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user; the feature extraction includes converting travel data into feature vectors V using a self-encoder; the fusion includes weighting and combining feature vectors extracted from the encoder, and normalizing to form a unified feature representation.
As a preferable mode of the travel data processing method according to the present invention, wherein: the prediction trend comprises the steps of carrying out trend, season and residual decomposition on smoothed data by using STL, fitting trend components in the STL decomposition by adopting ARIMA model, determining parameters and establishing a model, and predicting the trend of preset time by using the ARIMA model;
the decomposition of the trend, season and residual is expressed as,
；
wherein,indicate the time point +.>Is the smoothed travel data, +.>Represents the trend component of time point , +.>Seasonal ingredient representing the time point, +.>Indicate the time point +.>Residual components of (2);
the build model is represented as a set-up model,
；
wherein,representing weight parameters->Indicate the time point +.>Feature vector of>Representing feature vector +.>Is used for the weight of the (c),representing autoregressive parameters,/->Representing the moving average parameter, +.>Representing a shift operation +.>Representing the number of differences;
the prediction is made byJudging whether the seasonal components are continuous or not in the presence of the periodic mode within the preset time, and acquiring +.>A future prediction value, which determines a periodicity trend if the prediction shows that the future seasonal component remains periodic, and determines a future +.>The value of +.>The increment is larger than the preset threshold, and the rise trend is judged to be in the rising trend, if the increment is +.>The increment is smaller than the preset threshold, and the increment is judged to be in a descending trend, if the increment is within the continuous preset time point +.>And the increment is equal to a preset threshold value, and the stable trend is judged.
As a preferable mode of the travel data processing method according to the present invention, wherein: the emotion analysis is expressed as that,
；
wherein,representing an emotion analysis function->Representing the ith user comment, < >>Emotion score representing ith user comment, < ->Representation->Is (are) emotion score>Trend weights representing travel data;
when (when)Judging as negative emotion when +.>Neutral emotion when->Judging the positive emotion;
the constructed emotion similarity matrix is expressed as,
；
wherein,indicate->Word embedding vector of comment, ++>Representing emotion similarity matrix, < >>Indicate->User comment, ->Comment->And->Emotional similarity between->Indicate->Emotional scores of the comments;
the partitioning of the affective network is expressed as,
；
wherein,comment->And->The emotion similarity weight after the whole is +.>Representing the weight-adjustment parameters of the system,comment +.>Is used for adjusting the emotion score;
the partitioning of the emotion network comprisesAnd->Judging emotion similarity weight when emotion scores are identicalAnd (5) classifying the topics in the comments.
As a preferable mode of the travel data processing method according to the present invention, wherein: the construction of the predictive attraction popularity model is expressed as,
；
wherein,indicate the time point +.>Scenic spot popularity prediction value of +.>Indicate the time point +.>LSTM hidden state of (b);
the optimized predictive model is expressed as,
；
wherein,representing true sight popularity, +.>Represents the mean square error loss function, ">Representing regularization coefficients, +.>Is indicated at->Time->Emotional score of a user comment, +.>Is indicated at->Time->User commentsEmotion score.
As a preferable mode of the travel data processing method according to the present invention, wherein: the multi-objective optimization includes predicting popularity of attractions based on the predicted attraction popularity modelObtaining actual scenic spot popularity +.>Calculating difference measure of predicted and actual popularity +.>If->Greater than a preset threshold, entering a decision adjustment stage, if +.>Maintaining the optimization prediction model adjustment strategy when the optimization prediction model adjustment strategy is smaller than or equal to a preset threshold value;
the decision adjustment stage includes based on a difference metricAdjusting emotion network division strategy, calculating decision adjustment value of strategy +.>If->Highlighting feature activities and cultural displays of scenic spots, providing interactive games related to the scenic spots for users, providing coupons and discount information related to the scenic spots, skipping people stream peak time, recommending tour routes by utilizing navigation to avoid congestion areas, and if yes>Considering scenic spots with slightly lower recommendation scores but unique cultural or historical background, a higher-end or unique travel experience is provided for users, and the tour time is increasedProviding interpretation of local culture and custom;
the emotion network partitioning strategy adjustment comprises the steps of calculating emotion score variation, and adjusting an emotion score threshold value according to the variation;
the emotion score variation amount is expressed as,
；
wherein,adjusted emotion score representing current comment, +.>An adjusted emotion score representing the previous comment,/->Representing the difference of emotion scores of the current comment and the previous comment;
the adjusted emotion score threshold value is expressed as,
；
wherein,representing positive emotion threshold value adjusted according to variation of emotion score, < ->Representing a new frontal threshold,/->Representing an old front threshold;
reevaluating emotion based on the adjusted emotion score threshold usingAnd->Line contrast, if->Updating the tag to be positive emotion, if +.>Updating the tag to be negative emotion, if +.>Updating the label to be neutral emotion, recording the original emotion label and the adjusted emotion label of the comment, and continuously monitoring emotion scores;
the decision adjustment value is represented as,
；
wherein,representing the popularity of the optimized predicted scenic spot, < + >>Representing original predicted sight popularity, +.>Representing the difference between the optimized and the original predictions, < ->Representing decision adjustment values->Representing objective functions representing satisfaction, cost, tour time, respectively, < >>Representing the weight value assigned by the user.
As a preferable mode of the travel data processing method according to the present invention, wherein: the strategy decision tree generation method comprises the steps of analyzing emotion preference data of a user based on a user emotion network, predicting future user emotion change by using a prediction model, identifying potential travel strategies by combining the prediction data and the emotion preference data, and constructing nodes and branches of the decision tree according to preset weights;
the dynamic adjustment strategy according to the current situation of the user and the decision tree comprises the steps of collecting real-time emotion feedback of the user in the traveling process, calculating deviation between the real-time emotion feedback and the prediction satisfaction degree in the original prediction model, positioning related scenic spot nodes in the decision tree when the deviation exceeds a preset threshold value, adjusting the priority of the scenic spots to the strategy of the related nodes, and updating the traveling strategy according to the adjusted decision tree;
the generation of the optimal travel path comprises the steps of listing travel path combinations according to an adjusted decision tree, comprehensively evaluating emotion satisfaction degree, travel cost and time consumption of each path, screening candidate paths meeting the conditions from the evaluated paths according to the current position, time and budget limit of a user, selecting the paths with the highest score from the screened candidate paths for detail optimization, and determining the optimized paths as optimal paths;
the detail optimization comprises the steps of identifying scenic spots and restaurants focused by a user and increasing the weight of the scenic spots and restaurants in a path decision, adjusting the route of the user according to the expected arrival time and the open time of the scenic spots or restaurants, arranging rest periods or relaxed activities between activities with high physical exertion, optimizing the traffic path to ensure that the movement between scenic spots interested by the user is convenient and quick, adjusting the restaurants or activity selection according to the specific food or cultural activity preference of the user, preparing alternative schemes for emergency conditions such as weather changes, and providing a mechanism for fine adjustment of the interesting points for the user in the journey.
It is another object of the present invention to provide a travel data processing system that solves the problems of accuracy, emotion understanding and personalized recommendation of conventional methods by incorporating a variety of advanced techniques.
In order to solve the technical problems, the invention provides the following technical scheme: a travel data processing system comprising: the system comprises a data acquisition module, a feature extraction module, a time sequence analysis module, an emotion analysis module, a scenic spot popularity prediction module, a strategy decision tree module and a path recommendation module; the data acquisition module is used for collecting scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user; the characteristic extraction module is used for processing the original data obtained from the data acquisition module and extracting the characteristics by using the self-encoder; the time sequence analysis module is used for analyzing the time-related travel data, carrying out trend, season and residual decomposition on the data after smoothing treatment by using STL, and predicting future trend by using ARIMA model; the emotion analysis module is used for analyzing user comments, identifying emotion tendencies of users for scenic spots and providing emotion scores for subsequent modules; the scenic spot popularity prediction module is used for predicting popularity of each scenic spot based on the LSTM deep learning structure and providing a prediction result for the strategy decision tree module; the strategy decision tree module is used for constructing a strategy decision tree by utilizing the output of the previous module and dynamically adjusting the strategy; the path recommending module is used for recommending an optimal travel path for the user by combining the emotion analysis result, the popularity prediction result and other related information.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the travel data processing method as described above.
A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the travel data processing method as described above.
The invention has the beneficial effects that: the travel data processing method provided by the invention combines the self-encoder, LSTM and ARIMA technologies, so that the prediction result is more accurate, and the scenic spot management and resource allocation are facilitated. The emotion analysis module helps enterprises capture real feedback and feelings of users to scenic spots, and provides basis for optimizing service and improving user satisfaction. And recommending the most suitable travel path according to the real-time situation, the historical behavior and the emotion tendency of the user, so that the user experience and the travel satisfaction are enhanced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a general flow chart of a travel data processing method according to an embodiment of the present invention.
FIG. 2 is a block diagram of a travel data processing system according to a second embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided a travel data processing method including:
and acquiring travel data, performing feature extraction and fusion on the original data by using a self-encoder, and performing smoothing treatment on the travel data through time sequence data analysis to predict trend.
And carrying out emotion analysis on the comment data, constructing an emotion similarity matrix, constructing an emotion network by using a graph theory technology, and dividing the emotion network.
Constructing a predicted scenic spot popularity model based on the LSTM deep learning structure; and optimizing a prediction model based on the division result of the emotion network.
Multi-objective optimization of policy generation is performed using an evolutionary algorithm.
And generating a strategy decision tree according to the emotion network, the prediction model and the optimization result.
And generating an optimal travel path according to the current situation of the user and the dynamic adjustment strategy of the decision tree.
Acquiring travel data including scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user; the feature extraction includes converting travel data into feature vectors V using a self-encoder; the fusion includes weighting and combining feature vectors extracted from the encoder, and normalizing to form a unified feature representation.
The trend prediction comprises the steps of carrying out trend, season and residual decomposition on smoothed data by using STL, fitting trend components in STL decomposition by adopting ARIMA model, determining parameters and establishing a model, and predicting the trend of preset time by using the ARIMA model.
The decomposition of trends, seasons and residuals is expressed as,
；
wherein,indicate the time point +.>Is the smoothed travel data, +.>Represents the trend component of time point , +.>Seasonal ingredient representing the time point, +.>Indicate the time point +.>Residual components of (2);
the build-up model is represented as,
；
wherein,representing weight parameters->Indicate the time point +.>Feature vector of>Representing feature vector +.>Is used for the weight of the (c),representing autoregressive parameters,/->Representing the moving average parameter, +.>Representing a shift operation +.>Representing the number of differences.
Making predictions includesJudging whether the seasonal components are continuous or not in a periodic mode in a preset time, and acquiringIn the future prediction value, if the prediction shows that the future seasonal component remains periodic, determining that the seasonal component is periodicIf the periodicity of the predicted display season component does not remain periodic, determining the future +.>Value, if continuously pre->The increment in the set time point is larger than the preset threshold, and the rise trend is judged to be in the rising trend, if the increment is +.>The increment is smaller than the preset threshold, and the increment is judged to be in a descending trend, if the increment is within the continuous preset time point +.>And the increment is equal to a preset threshold value, and the stable trend is judged.
The emotion analysis is represented as,
；
wherein,representing an emotion analysis function->Representing the ith user comment, < >>Emotion score representing ith user comment, < ->Representation->Is (are) emotion score>Trend weight representing travel data, +.>-1 represents a decreasing trend, 0 represents a steady trend, 1 represents an increasing trend, ++>Representing a periodic trend;
when in the downward trend the liquid level is,threshold value is 1.2, when in stationary trend, < > in>The threshold value is 1, when in rising trend, < > is given>The threshold is 0.8, when in a periodic trend, the +.>The threshold is 1.1.
When (when)Judging as negative emotion when +.>Neutral emotion when->Judging the positive emotion;
constructing an emotion similarity matrix is expressed as,
；
wherein,indicate->Word embedding vector of comment, ++>Representing emotion similarity matrix, < >>Indicate->User comment, ->Comment->And->Emotional similarity between->Indicate->Emotional scores of the comments;
the partitioning of the affective network is denoted as,
；
wherein,comment->And->Adjusted emotion similarity weight, +.>Represents a weight adjustment parameter, represents comment +.>Adjustment of (2)Post emotion score;
partitioning emotion networks includesAnd->Judging emotion similarity weight when emotion scores are identical>And classifying the topics in the comment.
Constructing a model of predicted sight popularity is expressed as,
；
wherein,indicate the time point +.>Scenic spot popularity prediction value of +.>Indicate the time point +.>LSTM hidden state of (b);
the optimized predictive model is expressed as,
；
wherein,representing true sight popularity, +.>Represents the mean square error loss function, ">Representing regularization coefficients, +.>Is indicated at->Time->Emotional score of a user comment, +.>Is indicated at->Time->Emotional scores of the user comments.
The multi-objective optimization includes predicting popularity of attractions based on a predictive attraction popularity modelObtaining actual scenic spot popularity +.>Calculating difference measure of predicted and actual popularity +.>If->Greater than a preset threshold, entering a decision adjustment stage, if +.>Maintaining an optimization prediction model adjustment strategy when the preset threshold value is equal to or less than the preset threshold value;
the decision adjustment stage includes a decision adjustment stage based on a difference metricAdjusting emotion network partitioning strategy and calculating strategyDecision adjustment value->If->Highlighting feature activities and cultural displays of scenic spots, providing interactive games related to the scenic spots for users, providing coupons and discount information related to the scenic spots, skipping people stream peak time, recommending tour routes by utilizing navigation to avoid congestion areas, and if yes>Considering scenic spots with slightly low recommendation scores but unique culture or history background, providing higher-end or unique travel experience for users, increasing tour time and providing interpretation of local culture and custom habit;
adjusting the emotion network division strategy comprises calculating emotion score variation, and adjusting an emotion score threshold according to the variation;
the emotion score variation amount is expressed as,
；
wherein,adjusted emotion score representing current comment, +.>An adjusted emotion score representing the previous comment,/->Representing the difference of emotion scores of the current comment and the previous comment;
the adjustment of the emotion score threshold is expressed as,
；
wherein,representing positive emotion threshold value adjusted according to variation of emotion score, < ->A new front-face threshold value is shown,representing an old front threshold;
reevaluating emotion based on adjusting emotion score threshold, useAnd->For comparison, if->Updating the tag to be positive emotion, if +.>Updating the tag to be negative emotion, if +.>Updating the label to be neutral emotion, recording the original emotion label and the adjusted emotion label of the comment, and continuously monitoring emotion scores;
the decision adjustment value is expressed as,
；
wherein,representing the popularity of the optimized predicted scenic spot, < + >>Representing original predicted sight popularity, +.>Representing the difference between the optimized and the original predictions, < ->Representing decision adjustment values->Representing objective functions representing satisfaction, cost, tour time, respectively, < >>Representing the weight value assigned by the user.
Generating a strategy decision tree comprises analyzing emotion preference data of a user based on a user emotion network, predicting future user emotion change by using a prediction model, identifying a potential travel strategy by combining the prediction data and the emotion preference data, and constructing nodes and branches of the decision tree according to preset weights;
the dynamic adjustment strategy according to the current situation of the user and the decision tree comprises the steps of collecting real-time emotion feedback of the user in the traveling process, calculating deviation between the real-time emotion feedback and the prediction satisfaction degree in the original prediction model, locating relevant scenic spot nodes in the decision tree when the deviation exceeds a preset threshold value, adjusting the priority of the scenic spots to the strategy of the relevant nodes, and updating the traveling strategy according to the adjusted decision tree;
generating an optimal travel path comprises listing travel path combinations according to an adjusted decision tree, comprehensively evaluating emotion satisfaction degree, travel cost and time consumption of each path, screening candidate paths meeting the conditions from the evaluated paths according to the current position, time and budget limit of a user, selecting the paths with highest scores from the screened candidate paths for detail optimization, and determining the optimized paths as optimal paths;
the current context of the user comprises current time information, location information and interest information of the user.
The detail optimization comprises the steps of identifying scenic spots and restaurants focused by a user and improving the weight of the scenic spots and restaurants in a path decision, adjusting the route of the user according to the expected arrival time and the open time of the scenic spots or restaurants, arranging rest periods or relaxed activities between activities with high physical exertion, optimizing the traffic path to ensure that the movement between scenic spots interested by the user is convenient and quick, adjusting the restaurants or activity selection according to the specific food or cultural activity preference of the user, preparing alternative schemes for emergency conditions such as weather changes, and providing a mechanism for fine-tuning the interesting points for the user in the journey.
The reinforcement learning method is used, the path planning system is allowed to carry out self-adjustment and learning based on real-time feedback of a user, the online learning technology is used for continuously updating the model, the system is ensured to process newly-appearing data and conditions, the model is subjected to fine adjustment and overhaul periodically by combining the comparison of the user feedback and a model prediction result, fine adjustment is carried out every week, and overhaul is carried out every quarter.
The strategy is validated against possible future scenarios using the Monte Carlo method or other simulation techniques, and if a strategy fails to achieve the expected effect in multiple simulations, the predictive model is re-optimized.
By adopting the meta learning method, the system can be quickly adapted and learned on different travel data sets, and when the system faces new and unseen data distribution, the strategy is quickly adjusted based on previous experience.
Example 2
Referring to FIG. 2, for one embodiment of the present invention, there is provided a travel data processing system comprising: the system comprises a data acquisition module, a feature extraction module, a time sequence analysis module, an emotion analysis module, a scenic spot popularity prediction module, a strategy decision tree module and a path recommendation module; the data acquisition module is used for collecting scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user.
The feature extraction module is used for processing the original data obtained from the data acquisition module and extracting features by using the self-encoder.
The time sequence analysis module is used for analyzing the time-related travel data, smoothing the data by using STL, decomposing the trend, season and residual error, and predicting the future trend by using ARIMA model.
The emotion analysis module is used for analyzing user comments, identifying emotion tendencies of the user for scenic spots and providing emotion scores for subsequent modules.
The scenic spot popularity prediction module is used for predicting popularity of each scenic spot based on the LSTM deep learning structure and providing a prediction result for the policy decision tree module.
The strategy decision tree module is used for constructing a strategy decision tree by utilizing the output of the previous module and dynamically adjusting the strategy.
The path recommending module is used for recommending an optimal travel path for the user by combining the emotion analysis result, the popularity prediction result and other related information.
Example 3
One embodiment of the present invention, which is different from the first two embodiments, is:
the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Example 4
For one embodiment of the invention, a travel data processing method is provided, and in order to verify the beneficial effects of the invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
Experimental environment: constructing a data set: 6 months of data are captured from 3 hot trips including scenic spot basic information, user evaluation data, history of classical accesses, user behavior data and user current context data.
And (3) a tool: python, tensorFlow (for LSTM and self-encoder), statsmode (for ARIMA model)
The experimental steps are as follows: the data set described above was used to split into training (70%) and test (30%).
Training is performed by using the proposed method and the traditional method respectively.
And predicting the test set, and evaluating the prediction effect.
User comment data are analyzed, and the emotion recognition capacities of the two methods are compared.
And recommending travel paths for users in the test set, and performing user satisfaction investigation, wherein the experimental results are shown in table 1.
Table 1 comparison of experimental results
| Measurement standard/method | The proposed method | Conventional method |
| Prediction accuracy | 93% | 85% |
| Emotion analysis accuracy | 91% | 83% |
| User satisfaction (recommended route) | 88% | 75% |
The method of the invention has obvious advantages in predicting the popularity of scenic spots, and the accuracy reaches 93 percent, which is higher than 85 percent of that of the traditional method. Due to the combination of the self-encoder, LSTM and ARIMA techniques, long, short-term dependencies and non-linear trends in the time series are effectively captured. The trend, season and residual decomposition of the smoothed data through STL increases the prediction robustness, so that the model can well represent the data of different tourist attractions.
In emotion analysis of user comments, the proposed method achieves 91% accuracy, and compared with 83% of the traditional method, the method is more excellent in performance. Due to the emotion similarity matrix and emotion network, the model can more accurately identify and classify the emotion of the user, and particularly, the interpretation of ambiguous or neutral comments is more accurate. The improvement of emotion analysis means that the scenic spot can capture dissatisfaction and advice of tourists more quickly and accurately, so that adjustment is performed in time, and the experience of the tourists is further optimized.
From the user satisfaction, the travel path recommendation of the my invention method obtains 88% of satisfaction, which is obviously higher than 75% of the traditional method. This demonstrates that my inventive approach can better combine the real-time context, historical behavior and emotional tendency of the user, providing a more personalized travel path. Further analyzing the recommended path, the new method can be found to avoid hot spots in peak time, and places which are possibly liked by some users but are less crowded are recommended, so that the travel experience of the users is enhanced.
It is to be understood that the above embodiments are only for illustrating the technical scheme of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical scheme of the present invention, which is intended to be covered by the scope of the claims of the present invention.
Claims (7)
1. A method of processing travel data, comprising:
acquiring travel data, performing feature extraction and fusion on the original data by using a self-encoder, and performing smoothing treatment on the travel data and predicting trend by time sequence data analysis;
carrying out emotion analysis on comment data, constructing an emotion similarity matrix, constructing an emotion network by using graph theory technology, and dividing the emotion network;
constructing a predicted scenic spot popularity model based on the LSTM deep learning structure; optimizing a prediction model based on the partitioning result of the emotion network;
performing multi-objective optimization on strategy generation by using an evolutionary algorithm;
generating a strategy decision tree according to the emotion network, the prediction model and the optimization result;
generating an optimal travel path according to the current situation of the user and the dynamic adjustment strategy of the decision tree;
the prediction trend comprises the steps of carrying out trend, season and residual decomposition on smoothed data by using STL, fitting trend components in the STL decomposition by adopting ARIMA model, determining parameters and establishing a model, and predicting the trend of preset time by using the ARIMA model;
the decomposition of the trend, season and residual is expressed as,
；
wherein,indicate the time point +.>Is the smoothed travel data, +.>Represents the trend component of time point , +.>Seasonal ingredient representing the time point, +.>Indicate the time point +.>Residual components of (2);
the build model is represented as a set-up model,
；
wherein,representing weight parameters->Feature vector representing time point t, +.>Representing feature vector +.>Is used for the weight of the (c),representing autoregressive parameters,/->Representing the moving average parameter, +.>Representing a shift operation +.>Representing the number of differences;
the prediction is made byJudging whether the seasonal components are continuous or not in a periodic mode in a preset time, and acquiringIn the future predicted value, if the predicted display of the future seasonal component keeps periodicity, the periodicity trend is determined, and if the predicted display of the periodicity of the seasonal component does not keep periodicity, the future +.>The value of +.>The increment is larger than the preset threshold, and the rise trend is judged to be in the rising trend, if the increment is +.>The increment is smaller than the preset threshold, and the increment is judged to be in a descending trend, if the increment is within the continuous preset time point +.>And judging that the length is in a stable trend when the length is equal to a preset threshold value.
2. A travel data processing method as claimed in claim 1, wherein: the acquired travel data comprise scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user;
the feature extraction includes converting travel data into feature vectors using a self-encoderThe method comprises the steps of carrying out a first treatment on the surface of the The fusing includes weighted combining using the feature vectors extracted from the encoder,normalization is performed to form a unified feature representation.
3. A travel data processing method as claimed in claim 2, wherein: the emotion analysis is expressed as that,
；
wherein,representing an emotion analysis function->Representing the ith user comment, < >>Emotion score representing ith user comment, < ->Representation->Is (are) emotion score>Trend weights representing travel data;
when (when)Judging as negative emotion when +.>Neutral emotion when->Judging the positive emotion;
the constructed emotion similarity matrix is expressed as,
；
wherein,indicate->Word embedding vector of comment, ++>Representing emotion similarity matrix, < >>Indicate->User comment, ->Comment->And->Emotional similarity between->Indicate->Emotional scores of the comments;
the partitioning of the affective network is expressed as,
；
wherein,comment->And->Adjusted emotion similarity weight, +.>Representing weight adjustment parameters ∈ ->Comment +.>Is used for adjusting the emotion score;
the partitioning of the emotion network comprisesAnd->Judging emotion similarity weight when emotion scores are identical>And (5) classifying the topics in the comments.
4. A travel data processing method as claimed in claim 3, wherein: the construction of the predictive attraction popularity model is expressed as,
；
wherein,indicate the time point +.>Scenic spot popularity prediction value of +.>Indicate the time point +.>LSTM hidden state of (b);
the optimized predictive model is expressed as,
；
wherein,representing true sight popularity, +.>Represents the mean square error loss function, ">Representing regularization coefficients, +.>Is indicated at->Time->Emotional score of a user comment, +.>Is indicated at->Time->Emotional scores of the user comments.
5. A travel data processing method as defined in claim 4, wherein: the multi-objective optimization includes predicting popularity of attractions based on the predicted attraction popularity modelObtaining actual scenic spot popularity +.>Calculating difference measure of predicted and actual popularity +.>If->Greater than a preset threshold, entering a decision adjustment stage, if +.>Maintaining the optimization prediction model adjustment strategy when the optimization prediction model adjustment strategy is smaller than or equal to a preset threshold value;
the decision adjustment stage includes based on a difference metricAdjusting emotion network division strategy, calculating decision adjustment value of strategy +.>If->Highlighting feature activities and cultural displays of scenic spots, providing interactive games related to the scenic spots for users, providing coupons and discount information related to the scenic spots, skipping people stream peak time, recommending tour routes by utilizing navigation to avoid congestion areas, and if yes>Considering scenic spots with slightly low recommendation scores but unique culture or history background, providing higher-end or unique travel experience for users, increasing tour time and providing interpretation of local culture and custom habit;
the emotion network partitioning strategy adjustment comprises the steps of calculating emotion score variation, and adjusting an emotion score threshold value according to the variation;
the emotion score variation amount is expressed as,
；
wherein,adjusted emotion score representing current comment, +.>Adjusted emotion score showing previous comment,/->Representing the difference of emotion scores of the current comment and the previous comment;
the adjusted emotion score threshold value is expressed as,
；
wherein,representing positive emotion threshold value adjusted according to variation of emotion score, < ->Representing a new frontal threshold,/->Representing an old front threshold;
reevaluating emotion based on the adjusted emotion score threshold usingAnd->For comparison, if-> Updating the tag to be positive emotion, if +.>Updating the tag to be negative emotion, if +.>Updating the label to be neutral emotion, recording the original emotion label and the adjusted emotion label of the comment, and continuously monitoring emotion scores;
the decision adjustment value is represented as,
；
wherein,representing the popularity of the optimized predicted scenic spot, < + >>Representing original predicted sight popularity, +.>Representing the difference between the optimized and the original predictions, < ->Representing decision adjustment values->Representing objective functions representing satisfaction, cost, tour time, respectively, < >>Representing the weight value assigned by the user.
6. A travel data processing method as claimed in claim 5, wherein: the strategy decision tree generation method comprises the steps of analyzing emotion preference data of a user based on a user emotion network, predicting future user emotion change by using a prediction model, identifying potential travel strategies by combining the prediction data and the emotion preference data, and constructing nodes and branches of the decision tree according to preset weights;
the dynamic adjustment strategy according to the current situation of the user and the decision tree comprises the steps of collecting real-time emotion feedback of the user in the traveling process, calculating deviation between the real-time emotion feedback and the prediction satisfaction degree in the original prediction model, positioning related scenic spot nodes in the decision tree when the deviation exceeds a preset threshold value, adjusting the priority of the scenic spots to the strategy of the related nodes, and updating the traveling strategy according to the adjusted decision tree;
the generation of the optimal travel path comprises the steps of listing travel path combinations according to an adjusted decision tree, comprehensively evaluating emotion satisfaction degree, travel cost and time consumption of each path, screening candidate paths meeting the conditions from the evaluated paths according to the current position, time and budget limit of a user, selecting the paths with the highest score from the screened candidate paths for detail optimization, and determining the optimized paths as optimal paths;
the detail optimization comprises the steps of identifying scenic spots and restaurants focused by a user and increasing the weight of the scenic spots and restaurants in a path decision, adjusting the route of the user according to the expected arrival time and the open time of the scenic spots or restaurants, arranging rest periods or relaxed activities between activities with high physical exertion, optimizing the traffic path to ensure that the movement between scenic spots interested by the user is convenient and quick, adjusting the restaurants or activity selection according to the specific food or cultural activity preference of the user, preparing alternative schemes for emergency conditions such as weather changes, and providing a mechanism for fine adjustment of the interesting points for the user in the journey.
7. A system employing the travel data processing method according to any one of claims 1 to 6, comprising: the system comprises a data acquisition module, a feature extraction module, a time sequence analysis module, an emotion analysis module, a scenic spot popularity prediction module, a strategy decision tree module and a path recommendation module;
the data acquisition module is used for collecting scenic spot basic information, user evaluation data, classical access history records, user behavior data and current scene data of a user;
the characteristic extraction module is used for processing the original data obtained from the data acquisition module and extracting the characteristics by using the self-encoder;
the time sequence analysis module is used for analyzing the time-related travel data, carrying out trend, season and residual decomposition on the data after smoothing treatment by using STL, and predicting future trend by using ARIMA model;
the emotion analysis module is used for analyzing user comments, identifying emotion tendencies of users for scenic spots and providing emotion scores for subsequent modules;
the scenic spot popularity prediction module is used for predicting popularity of each scenic spot based on the LSTM deep learning structure and providing a prediction result for the strategy decision tree module;
the strategy decision tree module is used for constructing a strategy decision tree by utilizing the output of the previous module and dynamically adjusting the strategy;
the path recommending module is used for recommending an optimal travel path for the user by combining the emotion analysis result, the popularity prediction result and other related information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311340547.1A CN117077901B (en) | 2023-10-17 | 2023-10-17 | Travel data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311340547.1A CN117077901B (en) | 2023-10-17 | 2023-10-17 | Travel data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117077901A CN117077901A (en) | 2023-11-17 |
| CN117077901B true CN117077901B (en) | 2024-01-05 |
Family
ID=88704673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311340547.1A Active CN117077901B (en) | 2023-10-17 | 2023-10-17 | Travel data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077901B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245286A (en) * | 2019-05-08 | 2019-09-17 | 特斯联（北京）科技有限公司 | A kind of travelling recommended method and device based on data mining |
| US11023953B1 (en) * | 2020-03-11 | 2021-06-01 | Capital One Services, Llc | Recommendation engine that integrates customer social review-based data to understand preferences and recommend products |
| CN114022176A (en) * | 2021-09-26 | 2022-02-08 | 上海电信工程有限公司 | Method for predicting commodity sales on e-commerce platform and electronic equipment |
| CN116257618A (en) * | 2022-09-09 | 2023-06-13 | 中国计量大学 | Multi-source intelligent travel recommendation method based on fine granularity emotion analysis |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180047071A1 (en) * | 2012-07-24 | 2018-02-15 | Ebay Inc. | System and methods for aggregating past and predicting future product ratings |
| US20220019946A1 (en) * | 2020-07-20 | 2022-01-20 | UST Global Inc | Systems and methods for generating and updating travel itineraries |
| US20220058489A1 (en) * | 2020-08-19 | 2022-02-24 | The Toronto-Dominion Bank | Two-headed attention fused autoencoder for context-aware recommendation |
-
2023
- 2023-10-17 CN CN202311340547.1A patent/CN117077901B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245286A (en) * | 2019-05-08 | 2019-09-17 | 特斯联（北京）科技有限公司 | A kind of travelling recommended method and device based on data mining |
| US11023953B1 (en) * | 2020-03-11 | 2021-06-01 | Capital One Services, Llc | Recommendation engine that integrates customer social review-based data to understand preferences and recommend products |
| CN114022176A (en) * | 2021-09-26 | 2022-02-08 | 上海电信工程有限公司 | Method for predicting commodity sales on e-commerce platform and electronic equipment |
| CN116257618A (en) * | 2022-09-09 | 2023-06-13 | 中国计量大学 | Multi-source intelligent travel recommendation method based on fine granularity emotion analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117077901A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112199608B (en) | Social media rumor detection method based on network information propagation graph modeling | |
| CN105225135B (en) | Potential customer identification method and device | |
| CN111369299A (en) | Method, device and equipment for identification and computer readable storage medium | |
| CN112288455A (en) | Label generation method and device, computer readable storage medium and electronic equipment | |
| Gu et al. | [Retracted] Application of Fuzzy Decision Tree Algorithm Based on Mobile Computing in Sports Fitness Member Management | |
| KR20200052412A (en) | Artificial intelligence employment system and employing method of thereof | |
| CN109472030A (en) | A kind of system replys the evaluation method and device of quality | |
| KR20140120416A (en) | Method and system for prediction of future stock price using analysis of aggregate market value of listed stock | |
| Putranto et al. | Topic modelling and hotel rating prediction based on customer review in Indonesia | |
| KR101575779B1 (en) | Program rating prediction method and apparatus, and system based on sentiment analysis of viewers comments | |
| CN113672797A (en) | Content recommendation method and device | |
| CN109460474B (en) | User preference trend mining method | |
| Abdelaziz et al. | Convolutional neural network with genetic algorithm for predicting energy consumption in public buildings | |
| CN117668205A (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
| CN117522172A (en) | Technology maturity evaluation method and system | |
| CN117077901B (en) | Travel data processing method and system | |
| CN111221915B (en) | Online learning resource quality analysis method based on CWK-means | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| Yang et al. | From intangible to tangible: The role of big data and machine learning in walkability studies | |
| CN115660695A (en) | Customer service personnel label portrait construction method and device, electronic equipment and storage medium | |
| CN113792945B (en) | Dispatching method, device, equipment and readable storage medium of commercial vehicle | |
| CN113032688A (en) | Method for predicting access position of social network user at given future time | |
| CN113344747A (en) | Tourist attraction evaluation method based on latent classification Logit model | |
| CN114331304A (en) | Construction method of comprehensive recruitment difficulty model and recruitment difficulty evaluation method | |
| CN113570455A (en) | Stock recommendation method and device, computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |