CN114692004B - Route recommendation method and system based on big data - Google Patents
Route recommendation method and system based on big data Download PDFInfo
- Publication number
- CN114692004B CN114692004B CN202210470459.2A CN202210470459A CN114692004B CN 114692004 B CN114692004 B CN 114692004B CN 202210470459 A CN202210470459 A CN 202210470459A CN 114692004 B CN114692004 B CN 114692004B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- module
- scenic spot
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Navigation (AREA)
Abstract
The invention discloses a route recommendation method and system based on big data, wherein the route recommendation system comprises an information collection database, an interconnection building module, a physical ability index analysis module and a big data route recommendation module, the information collection database is used for collecting and storing user information, intention scenic spot and scenic spot data, the interconnection building module is used for building connection between a fellow user and the intention scenic spot, quickly opening an information channel and providing comprehensive data support for route recommendation, the physical ability index analysis module is used for analyzing physical ability consumption in a fitting travel process, the big data route recommendation module is used for making and recommending the depth of a travel route of the user and providing intelligent adjustment, and the information collection database, the interconnection building module, the physical ability index analysis module and the big data route recommendation module are connected with one another.
Description
Technical Field
The invention relates to the technical field of big data route recommendation, in particular to a route recommendation method and system based on big data.
Background
Heretofore, if a user wants to travel to a strange place, much effort must be expended to plan the route. However, due to the fact that the user lacks practice for planning and making the route, cognitive deviation exists in an actual scene, and influence of the degree of fatigue in the travel on the travel route is often ignored. The main performance is as follows: the physical consumption is huge because of the massive hiking in the previous day, so that the inertia in the hotel is strong and tired in the next day, and the user does not need to complete the established travel route. The planning made before the travel is disturbed, so that the phenomenon of changing or abandoning the originally planned travel route is easy to occur, the recommended route is not accurate, the planning needs to be made again by the user in the later period, and the time and the labor are wasted. Therefore, it is necessary to design a route recommendation method and system based on big data, which is time-saving, labor-saving and accurate in recommendation.
Disclosure of Invention
The invention aims to provide a route recommendation method and a route recommendation system based on big data, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a route recommendation method and system based on big data are disclosed, the route recommendation system comprises an information collection database, an interconnection building module, a physical ability index analysis module and a big data route recommendation module, the information collection database is used for collecting and storing user information, intention scenic spot and scenic spot data, the interconnection building module is used for building connection between a fellow user and the intention scenic spot, quickly opening an information channel and providing comprehensive data support for route recommendation, the physical ability index analysis module is used for analyzing physical ability consumption in a fitting travel process, the big data route recommendation module is used for making and recommending the depth of a travel route of the user and providing intelligent adjustment, and the information collection database, the interconnection building module, the physical ability index analysis module and the big data route recommendation module are connected with one another.
According to the technical scheme, the information collection database comprises a physical ability big data acquisition module, a user travel data acquisition module and a scenic spot evaluation data acquisition module, wherein the physical ability big data acquisition module is used for acquiring historical exercise and fitness data of a user and basic physical conditions, and the basic physical conditions comprise: sex, age, height, weight, health condition, the user travel data acquisition module is used for acquiring basic information of a user travel plan, the basic information comprises travel time, an intention scenic spot type, a accompanied luggage weight and a companding mode, and the scenic spot evaluation data acquisition module is used for acquiring tourist evaluation data under the scenic spot category.
According to the technical scheme, the interconnection building module comprises a key verification module, a user data packet interconnection transmission module, a scenic spot label building module and a user intention label building module, the key verification module is used for conducting safety key verification on corresponding user data packets under different user accounts, the user data packet interconnection transmission module is electrically connected with the key verification module, the user data packet interconnection transmission module is used for conducting data packet data interconnection transmission between user accounts passing mutual key authentication, the scenic spot label building module is used for conducting semantic retrieval on evaluation data of scenic spots in an information collection database and building label vocabularies corresponding to the scenic spots, the user intention label building module is used for building intention label vocabularies according to user intention scene types in the information collection database, the scenic spot label building module and the user intention label building module both comprise matching submodules, and the matching submodules are used for matching the scenic spot labels and the intention label vocabularies and building the user data packet interconnection of the matched scenic spots.
According to the technical scheme, the physical ability index analysis module comprises an intention index analysis module and a fitting prediction module, the intention index analysis module carries out intention index analysis and judgment on the scenic region corresponding to the scenic region label vocabularies which are successfully matched, the fitting prediction module is connected with the intention index analysis module, and the fitting prediction module is used for fitting and analyzing the travel physical ability index trend curve according to the scenic region intention index, the scenic region evaluation data and the user travel comprehensive physical ability.
According to the technical scheme, the big data route recommending module comprises a route making module and an intelligent adjusting module, the route making module is used for comprehensively making the travel route after physical consumption corresponding to each scene area successfully matched is estimated according to the user intention and physical ability, and the intelligent adjusting module is suitable for intelligently changing the travel route in time under the condition of road network traffic big data and physical consumption prediction misjudgment.
According to the technical scheme, the route recommendation method comprises the following steps:
step S1: establishing an information collection database, and respectively collecting and inputting physical fitness data, user travel data and scenic spot evaluation data of a user;
step S2: starting to execute a travel route alternative formulation task, acquiring information of an information collection database, when the travel is in a multi-user companding mode, after key verification among user data packets, building a temporary transmission channel among the same-party user data packets to realize rapid intercommunication of user data, then softly arranging the user information collection database, formulating label vocabularies for scenic spot evaluation data in the aspects of position degree, type, estimated duration and scenic spot characteristics, analyzing the contents of user travel data in the data packets again to determine user intention selection, and formulating the label vocabularies for the user intention selection; finally, matching the label vocabulary to obtain a scenic spot which accords with the user alternative, and interconnecting scenic spot information with the built user data packet;
and step S3: starting to perform physical consumption index analysis on the scenic spots conforming to the user alternative based on the influence of scenic spot travel modes, scenic spot travel intentions and physical consumption data on physical consumption, and fitting the travel physical consumption index so as to select the scenic spots under the control of the intentions index;
and step S4: after the scenic spot is selected, planning and making a travel route according to a scenic spot selection sequence to complete a recommendation scheme; meanwhile, in the traveling process, the big data monitors and formulates a route, the route is automatically adjusted in time when accidents happen to weather, road network traffic passenger flow and scenic spot passenger flow, when the recommended route cannot meet the expected physical energy consumption of the user, the user can manually adjust the expected physical energy prediction deviation, the planned route after the subsequent current time node is modified according to the physical energy change, and the route is recorded in a user corresponding physical energy big database for the route recommendation system to learn.
According to the above technical solution, the step S1 further comprises:
the user physical fitness big data entry method comprises the following steps: accessing historical exercise fitness data of the exercise APP, importing the historical exercise data, performing self-evaluation under physical fitness big data, and referring to physical fitness consumption deviation of a user on a route recommended by a route recommendation system;
the method for collecting the user travel data comprises the following steps: respectively inputting data of travel time, an intention scenic spot type, a luggage counter weight and an affiliation mode in a user filling or voice input mode, simultaneously providing a free input window for a user to give play to freely, explaining the travel expectation as detailed as possible, analyzing and sorting semantic content by a route recommendation system in a semantic retrieval mode, and then collecting the sorted semantic content data;
the method for collecting the scenic spot evaluation data comprises the following steps: and acquiring and inputting tourist evaluation data under the scenic spot category by utilizing a network big data searching technology.
According to the technical scheme, the method for formulating the label vocabulary in the step S2 comprises the following steps:
for scenic spot evaluation data, searching keywords of 'position degree, type, estimated duration and characteristics of scenic spots' in corresponding scenic spots respectively, identifying semantic contents near the keywords in the evaluation contents semantically at the same time, generating basic words, sequencing the occurrence frequencies of all the basic words in the corresponding scenic spots, and determining the basic words with the highest word frequency as label words under the keywords of the scenic spots;
and for the user travel data, arranging the contents expected by the user into diffusion vocabularies according to the semantic content data arranged in the step, and sequencing the diffusion vocabularies according to the quantity of the arranged diffusion vocabularies to obtain all diffusion type label vocabularies from high to low of the user intention, wherein the diffusion type vocabularies comprise the vocabularies and vocabularies similar to the vocabularies in semantics.
According to the above technical solution, the step S3 further comprises:
step S31: firstly, analyzing the alternative scenic spot intention index by the user, wherein the analysis method comprises the following steps: all diffusion type label vocabularies with user intention from high to low are respectively given a specified coefficient a = { a = { (a) } 1 、a 2 ...a n In which a is 1 >a 2 >...>a n Then all the diffusion type label vocabularies of the users and all the alternative scenesMatching label words of the regions, outputting the matching degree p of each scenic region according to the ratio of the label words with the same characteristics to all diffusion type label words of the user, sequencing the label words in the same scenic region but under different keywords according to word frequency, locking the label words under the keywords with the highest word frequency, finally finding out the designated coefficient a of the locked words in the user intention, repeating the steps, and finally obtaining the intention index y of the user to the alternative scenic region comprehensively through the formula y = p × a;
step S32: then, the historical travel modes of the alternative scenic spots are investigated and researched, and basic physical ability consumption indexes t = { t } of each scenic spot are respectively output 1 、t 2 ...t n }；
Step S33: comprehensively outputting the prediction of the actual physical ability consumption index of the user according to a formula s =1.5y × t, wherein s is the predicted value of the actual physical ability consumption index of the user in the corresponding scenic spot;
step S34: when multiple persons travel together, the user physical ability data with the lowest physical ability data is used as a vertical coordinate, a single person travels by using the user physical ability data as the vertical coordinate, a time axis is used as an abscissa to establish a user physical ability index trend graph, intention indexes y of the user to alternative scenic spots are respectively filled in route travel classes, the user physical ability data after being filled in is the predicted value s of the actual physical ability consumption index of the user in the corresponding scenic spot needing to be subtracted from the vertical coordinate, meanwhile, when the user physical ability index in the user physical ability index trend graph is not arranged, the user physical ability index is restored according to a set restoring speed along with time, and finally the user physical ability index is always higher than the user lowest physical ability index unit set by a system when the user physical ability index finishes one day of travel.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, through fitting analysis of the physical fitness index, when a travel route is set for a user, the physical fitness consumption of scenic spots corresponding to travel can be estimated according to the user intention selection and the physical fitness index, the travel route can be set comprehensively, so that the recommended route is more accurate, and the phenomenon that the set travel route cannot be completed due to neglecting the physical fitness influence of different users in different physical constitutions in the actual travel route is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the system module composition of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: a route recommendation method and system based on big data are disclosed, the route recommendation system comprises an information collection database, an interconnection building module, a physical ability index analysis module and a big data route recommendation module, the information collection database is used for collecting and storing user information, intention scenic spot and scenic spot data, the interconnection building module is used for building connection between a fellow user and the intention scenic spot, an information channel is rapidly opened, comprehensive data support is provided for route recommendation, the physical ability index analysis module is used for analyzing physical ability consumption in a fitting travel process, the big data route recommendation module is used for making and recommending the depth of a user travel route and providing intelligent adjustment, and the information collection database, the interconnection building module, the physical ability index analysis module and the big data route recommendation module are connected with one another.
The information collection database comprises a physical ability big data acquisition module, a user travel data acquisition module and a scenic spot evaluation data acquisition module, wherein the physical ability big data acquisition module is used for acquiring historical exercise and fitness data of a user and basic physical conditions, and the basic physical conditions comprise: the system comprises a user travel data acquisition module, a scenic spot evaluation data acquisition module and a scenic spot evaluation data acquisition module, wherein the user travel data acquisition module is used for acquiring basic information of a user travel plan, the basic information comprises travel time, an intention scenic spot type, a luggage weight and an accompanying mode, and the scenic spot evaluation data acquisition module is used for acquiring tourist evaluation data in the scenic spot type.
The interconnection building module comprises a key verification module, a user data packet interconnection transmission module, a scenic spot label building module and a user intention label building module, wherein the key verification module is used for carrying out safety key verification on corresponding user data packets under different user accounts, the user data packet interconnection transmission module is electrically connected with the key verification module, the user data packet interconnection transmission module is used for carrying out data packet data interconnection transmission between user accounts which pass mutual key verification, the scenic spot label building module is used for carrying out semantic retrieval on evaluation data of scenic spots in an information collection database and building label vocabularies corresponding to the scenic spots, the user intention label building module is used for building intention label vocabularies according to user intention scene types in the information collection database, the scenic spot label building module and the user intention label building module respectively comprise matching submodules, and the matching submodules are used for matching the scenic spot label vocabularies and the intention scene label vocabularies, and the scenic spot label vocabularies which are successfully matched are interconnected with the built user data packets.
The physical ability index analysis module comprises an intention index analysis module and a fitting prediction module, the intention index analysis module carries out intention index analysis and judgment on a scenic region corresponding to scenic region label vocabularies which are successfully matched, the fitting prediction module is connected with the intention index analysis module, and the fitting prediction module is used for fitting and analyzing a travel physical ability index trend curve according to the intention index of the scenic region, scenic region evaluation data and user travel comprehensive physical ability; through the fitting analysis to the physical fitness index, when a travel route is set for a user, the physical fitness consumption of scenic spots corresponding to travel is estimated according to the user intention selection and the physical fitness index, the travel route is set comprehensively, the recommended route is more accurate, and the phenomenon that the set travel route cannot be completed due to the fact that the physical fitness influence of different users in the actual travel route is ignored is reduced.
The big data route recommending module comprises a route formulating module and an intelligent adjusting module, the route formulating module is used for comprehensively formulating a travel route after physical consumption prediction corresponding to each matching successful scenic spot is comprehensively considered according to the user intention and physical performance, and the intelligent adjusting module is suitable for intelligently changing the travel route in time under the condition of road network traffic big data and physical consumption prediction misjudgment; the intelligent change of the travel route mainly comprises the steps of monitoring real-time climate, road network traffic passenger flow and scenic spot passenger flow through big data and changing the physical ability index, so that original formulated scenic spot route options are timely discharged, scenic spots meeting travel requirements are sequentially selected from alternative scenic spots, the route is changed quickly, the trouble that the set route needs to be re-planned due to sudden condition disturbance after the route is recommended is reduced, and the effects of saving time and labor are achieved.
The route recommendation method comprises the following steps:
step S1: establishing an information collection database, and respectively collecting and inputting physical fitness data, user travel data and scenic spot evaluation data of a user;
step S2: starting to execute a travel route alternative formulation task, acquiring information of an information collection database, when the travel is in a multi-user companding mode, after key verification between user data packets, building a temporary transmission channel between the user data packets of the same party to realize rapid intercommunication of user data, then softly sorting the user information collection database, formulating label words for scenic area evaluation data in the aspects of position degree, type, estimated duration and scenic area characteristics, analyzing the contents of user travel data in the data packets again to determine user intention selection, and formulating label words for the user intention selection; finally, matching the label vocabulary to obtain a scene area which accords with the user alternative, and then interconnecting the scene area information with the set user data packet; by building a user data packet and carrying out interconnection transmission with alternative scenic spot information, the feasibility of alternative scenic spot data can be quickly and deeply analyzed, and the satisfaction degree of a user on a recommended route is improved;
and step S3: starting to perform physical consumption index analysis on the scenic spots conforming to the user alternative based on the influence of scenic spot travel modes, scenic spot travel intentions and physical consumption data on physical consumption, and fitting the travel physical consumption index so as to select the scenic spots under the control of the intentions index;
and step S4: after the scenic spot is selected, planning and making a travel route according to a scenic spot selection sequence to complete a recommendation scheme; meanwhile, in the traveling process, a route is established through big data monitoring, the route is automatically adjusted in time when accidents happen to weather, road network traffic passenger flow and scenic spot passenger flow, the recommended route cannot meet the expected physical ability consumption of a user, the user can manually adjust the expected physical ability prediction deviation, the planned route after the subsequent current time node is modified according to the physical ability after being modified, and the route is recorded in a big database of the physical ability corresponding to the user and is used for a route recommendation system to learn; the route recommendation is combined with the intelligent traffic technology on the basis of physical ability consumption of the weight user during traveling, more humanized recommendation and change are achieved, and the purpose of saving worry for the user is achieved.
The step S1 further includes:
the user physical ability big data entry method comprises the following steps: accessing historical exercise fitness data of the exercise APP, importing the historical exercise data, performing self-evaluation under physical fitness big data, and referring to physical fitness consumption deviation of a user on a route recommended by a route recommendation system;
the method for collecting the user travel data comprises the following steps: respectively inputting data of travel time, an intention scenic spot type, a luggage counter weight and an affiliation mode in a user filling or voice input mode, simultaneously providing a free input window for a user to give play to freely, explaining the travel expectation as detailed as possible, analyzing and sorting semantic content by a route recommendation system in a semantic retrieval mode, and then collecting the sorted semantic content data;
the method for collecting scenic spot evaluation data comprises the following steps: and acquiring and inputting tourist evaluation data under the scenic spot category by utilizing a network big data searching technology.
The method for making the label vocabulary in the step S2 comprises the following steps:
for scenic spot evaluation data, searching keywords of 'position degree, type, estimated duration and characteristics of scenic spots' in corresponding scenic spots respectively, identifying semantic contents near the keywords in the evaluation contents semantically at the same time, generating basic words, sequencing the occurrence frequencies of all the basic words in the corresponding scenic spots, and determining the basic words with the highest word frequency as label words under the keywords of the scenic spots;
and for the user travel data, arranging the contents expected by the user into diffused vocabularies according to the semantic content data arranged in the steps, and sequencing the diffused vocabularies according to the quantity of the arranged diffused vocabularies to obtain all diffused label vocabularies with the user intention from high to low, wherein the diffused vocabularies comprise the vocabularies and vocabularies similar to the vocabularies in semantics.
Step S3 further includes:
step S31: firstly, analyzing the alternative scenic spot intention index by the user, wherein the analysis method comprises the following steps: all diffusion type label vocabularies with user intention from high to low are respectively given a specified coefficient a = { a = { (a) } 1 、a 2 ...a n In which a is 1 >a 2 >...>a n Matching all the diffused label words of the user with the label words of all the alternative scenic spots, outputting the matching degree p of each scenic spot according to the ratio of the label words with the same characteristics to all the diffused label words of the user, sequencing the label words of the same scenic spot but under different keywords according to word frequency sequencing, locking the label words under the keyword with the highest word frequency, finding out the designated coefficient a of the locked words in the user intention, repeating the steps, and finally obtaining the intention index y of the user to the alternative scenic spots through the formula y = p × a in a comprehensive mode; the actual intention index of the user to the alternative scenic spots is analyzed and calculated by outputting the actual matching degree of each scenic spot label vocabulary and the expectation of the user and combining the weight priority consideration of the user to the expectation label, so that the intention index is more in line with the personalized recommendation of the user compared with the single matching degree;
step S32: then, the historical travel modes of the alternative scenic spots are investigated and researched, and basic physical ability consumption indexes t = { t } of each scenic spot are respectively output 1 、t 2 ...t n }；
Step S33: comprehensively outputting the prediction of the actual physical ability consumption index of the user according to a formula s =1.5y × t, wherein s is the predicted value of the actual physical ability consumption index of the user in the corresponding scenic spot; the historical travel mode of the alternative scenic spots is investigated to obtain a basic physical consumption index of each scenic spot, then according to the intention index of the user to the alternative scenic spots, when the user travels in the scenic spot with higher intention index, the consumption index of the physical consumption is estimated due to higher intention and higher travel energy and physical consumption, otherwise, the consumption index of the physical consumption is estimated for the scenic spot with lower intention, so that the analysis of the physical consumption index is more accurate;
step S34: when multiple persons travel together, the user physical ability data with the lowest physical ability data is used as a vertical coordinate, a single person travels by using the user physical ability data as the vertical coordinate, a time axis is used as a horizontal coordinate to establish a user physical ability index trend graph, the intention indexes y of the user to alternative scenic spots are respectively filled in route travel classes, the user physical ability data after being filled is the predicted value s of the actual physical ability consumption index of the user in the corresponding scenic spot needing to be subtracted from the vertical coordinate, meanwhile, when the user physical ability index in the user physical ability index trend graph is not arranged with a travel, the user physical ability index is restored according to a set restoration speed along with the time, and finally, the user physical ability index in the user physical ability index trend graph is always higher than the user lowest physical ability index unit set by a system when the user physical ability index finishes traveling one day.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. A big data based route recommendation system, characterized by: the route recommendation system comprises an information collection database, an interconnection building module, a physical ability index analysis module and a big data route recommendation module, wherein the information collection database is used for collecting and storing user information, intention scenic spot data and scenic spot data, the interconnection building module is used for building connection between a fellow user and the intention scenic spot, quickly opening an information channel and providing comprehensive data support for route recommendation, the physical ability index analysis module is used for analyzing and fitting physical ability consumption in a traveling process, the big data route recommendation module is used for deeply formulating and recommending a user traveling route and providing intelligent adjustment, and the information collection database, the interconnection building module, the physical ability index analysis module and the big data route recommendation module are connected with one another;
the information collection database comprises a physical ability big data acquisition module, a user travel data acquisition module and a scenic spot evaluation data acquisition module, wherein the physical ability big data acquisition module is used for acquiring historical exercise and fitness data of a user and basic physical conditions, and the basic physical conditions comprise: the system comprises a user travel data acquisition module, a tourist assessment data acquisition module and a tourist assessment data acquisition module, wherein the user travel data acquisition module is used for acquiring basic information of a user travel plan, the basic information comprises travel time, an intention scenic spot type, a accompanied luggage counter weight and an association mode, and the scenic spot assessment data acquisition module is used for acquiring tourist assessment data under the scenic spot type;
the interconnection building module comprises a key verification module, a user data packet interconnection transmission module, a scenic spot label building module and a user intention label building module, wherein the key verification module is used for carrying out safety key verification on corresponding user data packets under different user accounts, the user data packet interconnection transmission module is electrically connected with the key verification module, the user data packet interconnection transmission module is used for carrying out data packet data interconnection transmission on user accounts which pass mutual key authentication, the scenic spot label building module is used for carrying out semantic retrieval on evaluation data of scenic spots in an information collection database and building label vocabularies corresponding to the scenic spots, the user label building module is used for building intention label vocabularies according to user intention type in the information collection database, the scenic spot label building module and the user intention label building module both comprise matching sub-modules, and the matching sub-modules are used for matching the scenic spot label vocabularies and the intention label vocabularies and interconnecting the successfully matched scenic spot label vocabularies and the built user data packets;
the physical ability index analysis module comprises an intention index analysis module and a fitting prediction module, the intention index analysis module carries out intention index analysis and judgment on a scenic spot corresponding to scenic spot label words which are successfully matched, the fitting prediction module is connected with the intention index analysis module, and the fitting prediction module is used for fitting and analyzing a travel physical ability index trend curve according to the scenic spot intention index, scenic spot evaluation data and user travel comprehensive physical ability.
2. The big-data based route recommendation system according to claim 1, wherein: the big data route recommending module comprises a route formulating module and an intelligent adjusting module, the route formulating module is used for comprehensively formulating the travel route after physical consumption corresponding to each matched scenic spot is estimated according to the user intention and physical ability, and the intelligent adjusting module is suitable for making intelligent changes to the travel route in time under the condition of road network traffic big data and physical consumption prediction misjudgment.
3. A big data-based route recommendation method is characterized by comprising the following steps: the route recommendation method comprises the following steps:
step S1: establishing an information collection database, and respectively collecting and inputting physical fitness data, user travel data and scenic spot evaluation data of a user;
step S2: starting to execute a travel route alternative formulation task, acquiring information of an information collection database, when the travel is in a multi-user companding mode, after key verification among user data packets, building a temporary transmission channel among the same-party user data packets to realize rapid intercommunication of user data, then softly arranging the user information collection database, formulating label vocabularies for scenic spot evaluation data in the aspects of position degree, type, estimated duration and scenic spot characteristics, analyzing the contents of user travel data in the data packets again to determine user intention selection, and formulating the label vocabularies for the user intention selection; finally, matching the label vocabulary to obtain a scene area which accords with the user alternative, and then interconnecting the scene area information with the set user data packet;
and step S3: starting to perform physical consumption index analysis on the scenic spots conforming to the user alternative based on the influence of scenic spot travel modes, scenic spot travel intentions and physical consumption data on physical consumption, and fitting the travel physical consumption index so as to select the scenic spots under the control of the intentions index;
and step S4: after the scenic spot is selected, planning and making a travel route according to a scenic spot selection sequence to complete a recommendation scheme; meanwhile, in the traveling process, a route is established through big data monitoring, the route is automatically adjusted in time when accidents happen to weather, road network traffic passenger flow and scenic spot passenger flow, when the recommended route cannot meet the expected physical energy consumption of a user, the user can manually adjust the expected physical energy to estimate deviation, the planned route after the subsequent current time node is modified according to the physical energy after being modified, and the route is recorded in a physical energy big database corresponding to the user and is used for a route recommendation system to learn;
the step S1 further includes:
the user physical ability big data entry method comprises the following steps: accessing historical exercise fitness data of the exercise APP, importing the historical exercise data, performing self-evaluation under physical fitness big data, and referring to physical consumption deviation of a user on a route recommended by a route recommending system;
the method for collecting the user travel data comprises the following steps: respectively inputting data of travel time, an intention scenic spot type, a luggage counter weight and an affiliation mode in a user filling or voice input mode, simultaneously providing a free input window for a user to give play to freely, explaining the travel expectation as detailed as possible, analyzing and sorting semantic content by a route recommendation system in a semantic retrieval mode, and then collecting the sorted semantic content data;
the method for collecting scenic spot evaluation data comprises the following steps: utilizing a network big data search technology to obtain tourist evaluation data under the scenic spot category and recording the tourist evaluation data;
the method for formulating the label vocabulary in the step S2 comprises the following steps:
for scenic spot evaluation data, searching keywords of 'position degree, type, estimated duration and characteristics of scenic spots' in corresponding scenic spots respectively, identifying semantic contents near the keywords in the evaluation contents semantically at the same time, generating basic words, sequencing the occurrence frequencies of all the basic words in the corresponding scenic spots, and determining the basic words with the highest word frequency as label words under the keywords of the scenic spots;
for user travel data, arranging the contents expected by the user into diffused vocabularies according to the semantic content data arranged in the steps, and sequencing the diffused vocabularies according to the quantity of the arranged diffused vocabularies to obtain all diffused label vocabularies with the intention from high to low, wherein the diffused vocabularies comprise the vocabularies and vocabularies similar to the vocabularies in semantics;
the step S3 further includes:
step S31: firstly, analyzing the alternative scenic spot intention index by the user, wherein the analysis method comprises the following steps: all diffusion type label vocabularies with user intention from high to low are respectively given a specified coefficient a = { a = { (a) } 1 、a 2 ...a n In which a is 1 >a 2 >...>a n Matching all the diffused label words of the user with the label words of all the alternative scenic spots, outputting the matching degree p of each scenic spot according to the ratio of the label words with the same characteristics to all the diffused label words of the user, sequencing the label words of the same scenic spot but under different keywords according to word frequency sequencing, locking the label words under the keyword with the highest word frequency, finding out the designated coefficient a of the locked words in the user intention, repeating the steps, and finally obtaining the intention index y of the user to the alternative scenic spots through the formula y = p × a in a comprehensive mode;
step S32: then, the historical travel modes of the alternative scenic spots are investigated and researched, and basic physical ability consumption indexes t = { t } of each scenic spot are respectively output 1 、t 2 ...t n }；
Step S33: comprehensively outputting the prediction of the actual physical ability consumption index of the user according to a formula s =1.5y × t, wherein s is the predicted value of the actual physical ability consumption index of the user in the corresponding scenic spot;
step S34: when multiple persons travel together, the user physical ability data with the lowest physical ability data is used as a vertical coordinate, a single person travels by using the user physical ability data as the vertical coordinate, a time axis is used as an abscissa to establish a user physical ability index trend graph, intention indexes y of the user to alternative scenic spots are respectively filled in route travel classes, the user physical ability data after being filled in is the predicted value s of the actual physical ability consumption index of the user in the corresponding scenic spot needing to be subtracted from the vertical coordinate, meanwhile, when the user physical ability index in the user physical ability index trend graph is not arranged, the user physical ability index is restored according to a set restoring speed along with time, and finally the user physical ability index is always higher than the user lowest physical ability index unit set by a system when the user physical ability index finishes one day of travel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470459.2A CN114692004B (en) | 2022-04-28 | 2022-04-28 | Route recommendation method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470459.2A CN114692004B (en) | 2022-04-28 | 2022-04-28 | Route recommendation method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114692004A CN114692004A (en) | 2022-07-01 |
| CN114692004B true CN114692004B (en) | 2022-11-18 |
Family
ID=82144419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210470459.2A Active CN114692004B (en) | 2022-04-28 | 2022-04-28 | Route recommendation method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114692004B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117023674B (en) * | 2023-10-08 | 2024-01-09 | 山东世纪阳光科技有限公司 | Intelligent water outlet control system for water purifying equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168320A (en) * | 2017-06-05 | 2017-09-15 | 游尔（北京）机器人科技股份有限公司 | A kind of tourist guide service robot |
| CN109086919A (en) * | 2018-07-17 | 2018-12-25 | 新华三云计算技术有限公司 | A kind of sight spot route planning method, device, system and electronic equipment |
| CN110298772A (en) * | 2019-07-19 | 2019-10-01 | 赣南医学院 | The planning of health travel destination and management information system based on tourist's time-space behavior |
| CN110990703A (en) * | 2019-12-06 | 2020-04-10 | 重庆锐云科技有限公司 | Intelligent tourist destination recommendation system and method based on user health state |
| CN113343127A (en) * | 2021-04-25 | 2021-09-03 | 武汉理工大学 | Tourism route recommendation method, system, server and storage medium |
| CN113420210A (en) * | 2020-11-11 | 2021-09-21 | 喻丹 | Big data-based intelligent tourism analysis decision system |
| WO2021261987A1 (en) * | 2020-06-22 | 2021-12-30 | Mimos Berhad | System and method for providing destination recommendation to travelers |
| CN114267430A (en) * | 2021-12-24 | 2022-04-01 | 浙江力石科技股份有限公司 | Route and environment-based tourist physical ability and consumption estimation method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI346770B (en) * | 2007-11-26 | 2011-08-11 | Nat Univ Chung Hsing | Gps navigator with integrated manipulator fitness monitoring functions |
| CN104134115A (en) * | 2014-07-17 | 2014-11-05 | 南宁市锋威科技有限公司 | Intelligent traveling integrated service system |
| CN105069522B (en) * | 2015-07-24 | 2018-08-07 | 重庆大学 | Scenic spot Touring-line evaluation and improved method |
-
2022
- 2022-04-28 CN CN202210470459.2A patent/CN114692004B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168320A (en) * | 2017-06-05 | 2017-09-15 | 游尔（北京）机器人科技股份有限公司 | A kind of tourist guide service robot |
| CN109086919A (en) * | 2018-07-17 | 2018-12-25 | 新华三云计算技术有限公司 | A kind of sight spot route planning method, device, system and electronic equipment |
| CN110298772A (en) * | 2019-07-19 | 2019-10-01 | 赣南医学院 | The planning of health travel destination and management information system based on tourist's time-space behavior |
| CN110990703A (en) * | 2019-12-06 | 2020-04-10 | 重庆锐云科技有限公司 | Intelligent tourist destination recommendation system and method based on user health state |
| WO2021261987A1 (en) * | 2020-06-22 | 2021-12-30 | Mimos Berhad | System and method for providing destination recommendation to travelers |
| CN113420210A (en) * | 2020-11-11 | 2021-09-21 | 喻丹 | Big data-based intelligent tourism analysis decision system |
| CN113343127A (en) * | 2021-04-25 | 2021-09-03 | 武汉理工大学 | Tourism route recommendation method, system, server and storage medium |
| CN114267430A (en) * | 2021-12-24 | 2022-04-01 | 浙江力石科技股份有限公司 | Route and environment-based tourist physical ability and consumption estimation method and system |
Non-Patent Citations (2)
| Title |
|---|
| "A Joint Passenger Flow Inference and Path Recommender System for Deploying New Routes and Stations of Mass Transit Transportation";Fandel Lin等;《ACM Transactions on Knowledge Discovery from Data》;20220228;第16卷(第1期);全文 * |
| "面向智能旅游服务机器人的个性化推荐算法研究";孙彦鹏;《中国优秀硕士学位论文全文数据库》;20200115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114692004A (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103544663B (en) | The recommendation method of network open class, system and mobile terminal | |
| CN106940829B (en) | Personalized path recommendation method in Internet of vehicles environment | |
| US6801909B2 (en) | System and method for obtaining user preferences and providing user recommendations for unseen physical and information goods and services | |
| US7516225B2 (en) | Experience/preference information providing system | |
| CN109191896A (en) | Personalized parking stall recommended method and system | |
| US20230060713A1 (en) | Methods for recommending parking lots in smart cities, internet of things systems, and storage medium thereof | |
| CN107167156B (en) | A kind of multimode Trip chain preferred method and system towards integration trip | |
| CN110322738A (en) | A kind of course optimization method, device and system | |
| Ignaccolo et al. | Combining Analytic Hierarchy Process (AHP) with role-playing games for stakeholder engagement in complex transport decisions | |
| CN114692004B (en) | Route recommendation method and system based on big data | |
| CN103945236B (en) | Gathering method and system of on-line live channels | |
| KR102425748B1 (en) | Method for Determining Expected Area of Passenger Riding through Clustering Techniques for Riding Demand History Data, Managing Device Used Therein, and Medium Being Recorded with Program for Executing the Method | |
| CN110413886A (en) | A kind of point of interest methods of exhibiting and device | |
| CN113836441A (en) | Method and device for matching requirements and service contents through data analysis | |
| CN106372970A (en) | Private tour guide automatic recommendation method and system | |
| CN1996426B (en) | Method and apparatus for displaying traffic information | |
| CN111678531B (en) | Subway path planning method based on LightGBM | |
| US20020013780A1 (en) | Information retrieval system | |
| CN112765374A (en) | Education resource screening system and method for information push | |
| CN113095570B (en) | Bicycle riding path recommending method based on demand difference | |
| KR20170057985A (en) | System and method for estimating business of supporting inauguration | |
| CN111340555B (en) | Suggestion decision-making system and method based on legal field user portrait model | |
| CN114297530A (en) | Travel planning method and system based on big data | |
| CN110689158B (en) | Method, device and storage medium for predicting destination | |
| CN111583070A (en) | Shared experience type tourism system |
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 |