CN108875005A - A kind of tourist's preferential learning system and method based on visit behavior - Google Patents
A kind of tourist's preferential learning system and method based on visit behavior Download PDFInfo
- Publication number
- CN108875005A CN108875005A CN201810620123.3A CN201810620123A CN108875005A CN 108875005 A CN108875005 A CN 108875005A CN 201810620123 A CN201810620123 A CN 201810620123A CN 108875005 A CN108875005 A CN 108875005A
- Authority
- CN
- China
- Prior art keywords
- tourist
- visit
- value
- sightseeing spot
- acceleration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of tourist's preferential learning system based on visit behavior, which includes iBeacon module, intelligent terminal, application program and server；The iBeacon module is used to identify the location information of sightseeing spot or exhibition room inside showpiece inside scenic spot；The application program is used to receive and parse through the broadcast data packet of iBeacon module, the distance between computational intelligence terminal and iBeacon equipment, the sightseeing spot that identification tourist is presently in；The intelligent terminal acquires tourist in the visit behavioral data of some sightseeing spot and uploads visit behavioral data to server；The server is used to handle and store the visit behavioral data of tourist, and obtains tourist to the preference of different sightseeing spots according to preferential learning model.It is proposed by the present invention that iBeacon module and intelligent terminal are combined to the method for obtaining tourist and going sight-seeing behavior, the available fine-grained visit behavior of tourist, the tourist's preferential learning system proposed according to the present invention can obtain tourist for the fine granularity visit preference of each sightseeing spot in a certain scenic spot.
Description
Technical field
The present invention relates to mobile Internet terminal technical fields, and in particular to a kind of tourist's preference based on visit behavior
Learning system and method.
Background technique
Tourist is often used in register number or the label of point of interest in the correlative study of tourist's tourism favor study at present
For the sequence arrived as tourist to the preference of point of interest, tourist is higher in the frequency that a certain point of interest is registered, and shows tourist couple
The preference of the point of interest is higher.The social network for being all based on position that the correlative study of most of tourist's preferential learning uses
Network data set can only learn tourist to the coarseness preference of scenic spot rank；Secondly, in the actual environment, tourist will not be total in real time
The location information of oneself is enjoyed, therefore data set of registering only includes tourist's pieces of position information, leads to Sparse, tourism favor is commented
Valence is incomplete；And tourist often scores to scenic spot after tour schedule, evaluates, therefore will scoring, evaluation data
There are certain subjectivity hysteresis qualitys for learning tourist's preference for collection.Existing method is without calligraphy learning visitor in tourist's preferential learning
It sees and fine-grained tourist's preference.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of tourists based on visit behavior
Preferential learning system and method lacks real-time, objectivity and preferential learning not to solve acquisition preference existing for current techniques
The problems such as enough comprehensively careful.
In order to achieve the above objects and other related objects, the present invention provides a kind of tourist's preferential learning based on visit behavior
System, the system include iBeacon module, intelligent terminal, application program and server；
The iBeacon module is used to identify the location information of sightseeing spot or exhibition room inside showpiece inside scenic spot；
The application program is used to receive and parse through the broadcast data packet of iBeacon module, what identification tourist was currently located
Location information, the distance between computational intelligence terminal and iBeacon module；
The intelligent terminal acquires tourist in the visit behavioral data of some sightseeing spot and uploads visit behavioral data to clothes
Business device；
The server is used to handle and store the visit behavioral data of tourist, and obtains tourist according to preferential learning model
To the preference of different sightseeing spots.
Preferably, the visit behavioral data for obtaining tourist in some sightseeing spot includes obtaining iBeacon module and visitor
The distance between family end d.
D=10^ ((abs (Rssi)-A)/(10*n))
Rssi is the intensity for the iBeacon broadcast singal that intelligent terminal receives, and A is intelligent terminal and iBeacon module
The distance between be 1m when signal intensity, n be the environmental attenuation factor.
Preferably, the visit behavioral data includes play time of the tourist at scenic spot, take pictures number and dwell times.
Preferably, tourist is in the time of playing of sightseeing spot i:Ti=Li/ f, wherein LiAdd for tourist in sightseeing spot i synthesis
The item number of speed data, f are the frequency acquisition of acceleration information.
Preferably, the item number that number is the broadcast of taking pictures that the application program in intelligent terminal receives of taking pictures.
Preferably, the dwell times method is：
Acceleration information sliding window value is set；
The average value of acceleration value in calculation window, acceleration in cycling among windows and make with mean value it is poor, if result
Absolute value is respectively less than preset acceleration float value, then it is assumed that tourist is static within the period of the window；
Obtain the index of each first acceleration value of stationary window；
Stationary window acceleration index is traversed, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number adds 1；
If the difference of consecutive value is equal to 1, static number is remained unchanged；
It is final to obtain tourist in the static number of all sightseeing spots.
Preferably, preference Pop of the tourist to sightseeing spot iiFor：
For tourist's visiting time total in scenic spot；TiFor tourist's playing the time in sightseeing spot i；
For the total degree taken pictures；Imgi is take pictures number of the tourist in sightseeing spot i；For the total degree of stop；Si is that tourist exists
The dwell times of sightseeing spot i；w1,w2,w3It is different visit behaviors to the impact factor and w of sightseeing spot preference1+w2+w3=1.
In order to achieve the above objects and other related objects, the present invention also provides a kind of tourist's preferences based on visit behavior
Learning method, this method are：
Tourist is obtained in the visit behavioral data of some sightseeing spot；The visit behavioral data includes trip of the tourist at scenic spot
Play time, take pictures number and dwell times；
Tourist is obtained to the preference of different sightseeing spots according to time of playing, the visits behavior such as number and dwell times of taking pictures.
Preferably, play time T of the tourist in sightseeing spot iiFor:Ti=Li/ f, wherein LiIt is synthesized for tourist in sightseeing spot i
The item number of acceleration information, f are the frequency acquisition of acceleration information；
The number of taking pictures is that the system that receives of application program in intelligent terminal is taken pictures the item number of broadcast；
The dwell times method is：
Acceleration information sliding window value is set；
The average value of acceleration value in calculation window, acceleration in cycling among windows and make with mean value it is poor, if result
Absolute value is respectively less than preset acceleration float value, then it is assumed that tourist is static, acquisition within the period of the window
The index of each first acceleration value of stationary window；
Above-mentioned stationary window acceleration index is traversed, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number
Add 1；If the difference of consecutive value is equal to 1, static number is remained unchanged；It is final to obtain tourist in the static number of all sightseeing spots.
Preferably, preference Pop of the tourist to sightseeing spot iiFor：
For tourist's visiting time total in scenic spot；TiFor tourist's playing the time in sightseeing spot i；
For the total degree taken pictures；Imgi is take pictures number of the tourist in sightseeing spot i；For the total degree of stop；SiExist for tourist
The dwell times of sightseeing spot i；w1,w2,w3It is different visit behaviors to the impact factor and w of sightseeing spot preference1+w2+w3=1.
As described above, a kind of tourist's preferential learning system and method based on visit behavior of the invention, has with following
Beneficial effect：
(1) it is concentrated in location-based social network data, the frequency for using tourist to register at sight spot is as tourist to scape
The evaluation of point preference, using tourist the scoring of scenic spot entirety or evaluation are learnt tourist's preference there are it is subjective, compared with cage
The disadvantages of system, can not carry out fine-grained visit and recommend.Proposed by the present invention combine iBeacon module and intelligent terminal is obtained
The method for taking tourist to go sight-seeing behavior, available tourist fine-grained visit behavior inside scenic spot propose according to the present invention
Tourist's preferential learning model can obtain tourist for the fine granularity visit preference of each sightseeing spot in a certain scenic spot.
(2) location-based social network data collection, usually tourist are published on social networks after tour schedule,
Lack real-time and validity, the excessively unilateral inadequate objective reality of tourist's preference obtained can not obtain tourist's personalization
Tourism favor.And the method in the present invention can use the visit behavioral data of the objective of tourist, tourist's preference of acquisition is more
Personalization；Using only register number or residence time length as the evaluation of tourist's preference, evaluation criterion is single, Wu Faquan
The tourism favor of the acquisition tourist in face.Other than the register frequency and visit track data, tourist's takes pictures, stays during visit
The behaviors such as foot stop contain the preference to sightseeing spot of tourist.Therefore tourist's preferential learning model set that the present invention designs
Take pictures a variety of behaviors such as number, time of playing, dwell times, with comprehensively objectively study tourist to the inclined of the scenic spot sightseeing spot Nei Ge
It is good.
(3) tourist will not usually share the location information of oneself in real time in tourism process, using location-based
When social network data set analysis tourist's preference, lead to Sparse, tourist's preference of acquisition is not comprehensive enough.It is proposed by the present invention
The available tourist of method that iBeacon module and intelligent terminal are combined acquisition tourist's visit behavior is complete in scenic spot
The visit preference of visit behavior, acquisition is more comprehensive.
Detailed description of the invention
In order to which the present invention is further explained, described content, with reference to the accompanying drawing makees a specific embodiment of the invention
Further details of explanation.It should be appreciated that these attached drawings are only used as typical case, and it is not to be taken as to the scope of the present invention
It limits.
Fig. 1 is tourist's preferential learning system schematic；
Fig. 2 is that application data acquires general flow chart；
Fig. 3 is that acceleration information obtains flow chart；
Fig. 4 is to monitor to take pictures to broadcast flow chart；
Fig. 5 is that dwell times obtain flow chart；
Fig. 6 is time acquisition flow chart of playing；
Fig. 7 is preferential learning flow chart.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
As shown in Figure 1, the present invention proposes a kind of tourist's preferential learning system based on visit behavior.The system by
The part such as iBeacon module, intelligent terminal, application program, server forms.Wherein, iBeacon module is mounted in scenic spot respectively
In sightseeing spot, for identifying each sightseeing spot specific location；Application program is according to receiving the strong of iBeacon module broadcast singal
It spends (Rssi) and calculates the distance between intelligent terminal and iBeacon module of tourist, set in advance if distance between the two is less than
Fixed distance threshold then acquires visitor behavior data using equipment such as camera, the acceleration transducers of intelligent terminal, by wireless
The behavioral data of acquisition is uploaded to server by network.Server is used for pretreatment, storage and the tourist's preference of behavioral data
Study.
Specifically, application program is worked as according to the broadcast singal according to low-power consumption bluetooth protocol analysis iBeacon module, acquisition
Major, Minor of preceding iBeacon module and the intensity Rssi for receiving broadcast singal, the trip that tourist is presently in for identification
It lookes at a little and the distance between computational intelligence terminal and iBeacon module.Major value identifies different scenic spots, in same scenic spot
Major value it is identical；Minor value is for identifying sightseeing spot different in same scenic spot.
IBeacon is a series of general designation of bluetooth low energy devices, can provide base in the system of Android and iOS
Service in position has the characteristics that low-power consumption, low cost, is easy to lay.Fixed equipment, mobile device and office may be implemented
Short-range data exchange between the net of domain, iBeacon module is used to identify the location information of sightseeing spot in the present invention.
With popularizing for smart phone, tourist can generally carry during visit and use smart phone.By intelligence
Mobile phone can record the visit behavior of tourist comprehensively.Utilize the camera of smart phone, acceleration transducer, then available trip
A variety of tourist image design data of visitor.These behavioral datas can objectively reflect the preference of tourist and the visit valence of sightseeing spot itself
Value.It is mainly broadcasted in the present invention using the acceleration transducer of smart phone and android system, is respectively used to acquisition tourist
It takes pictures broadcast in the acceleration information of the sightseeing spot of iBeacon mark and monitoring.Sole requirement branch of the present invention to smart phone
Hold low-power consumption bluetooth agreement.This example is illustrated using smart phone as intelligent terminal.It is to be appreciated that the present embodiment
Intelligent terminal be not merely smart phone, other can into realize acceleration analysis and monitor android system take pictures extensively
The equipment broadcast all should belong to intelligent terminal described in the present embodiment.
Application development environment of the invention is Android studio2.3.3, JDK version 1.7.It answers in the present invention
Can receive and parse the broadcast message of iBeacon module with program, first program can iBeacon module based on the received broadcast
Signal strength (Rssi) calculates the distance between iBeacon module and smart phone using formula (1) and judges whether tourist arrives
Up to sightseeing spot.And according to Major the and Minor value visit that tourist is currently located for identification in the iBeacon of parsing broadcast
Point.Secondly, the visit behavioral data acquired in sightseeing spot can be uploaded to server by smart phone.
D=10^ ((abs (Rssi)-A)/(10*n)) (1)
Wherein, d is to calculate resulting distance, and Rssi is the intensity of the iBeacon broadcast singal received, and A is intelligent hand
The intensity of signal when the distance between machine and iBeacon module are 1m, n are the environmental attenuation factor.
Parameter A can be demarcated by experiment, and before laying iBeacon module, available configuration tool is to iBeacon module
It is demarcated.IBeacon module is placed at the distance 1m apart from smart phone, is received at this time by special configuration measurement
The intensity of the signal of iBeacon module.
N represents the environmental attenuation factor, be for the different bluetooth equipments value it is different, same equipment is different
Its signal strength is also different in the case where transmission power, and for being both 1 meter in the case where, environment is strong for signal
It is also influential for spending, related with natural environment.The broadcast singal of iBeacon module will receive each in environment in practical applications
The interference of kind of factor, when laying iBeacon module should in the environment of laying, after calibration distance and received signal intensity,
The environmental attenuation factor in the case where laying environment, the application scenarios of less demanding for range accuracy are measured, n can use empirical value.
Distance threshold parameters d is added in the design of application programt, when the distance between tourist and iBeacon module are small
In threshold value dtWhen start tourist go sight-seeing behavioral data acquisition, when the distance between tourist and iBeacon module be greater than threshold value dtWhen
Stop the acquisition that tourist goes sight-seeing behavioral data.dtIt can be arranged according to the flexible in size of scenic spot sightseeing spot, therefore this system is both applicable in
In the open space such as scenic spot, amusement park, it is also applied for the place of the relative closures such as museum, show room.
Server of the invention be by Window10 system processor (Intel (R) Xeon (R) CPU) Myeclipse and
Tomcat builds web server, for analyzing the visit behavior and tourist's preferential learning and the storage of data of tourist.The present invention
In tourist go sight-seeing behavior and have dwell times of the tourist in sightseeing spot, play time and number of taking pictures, wherein dwell times and
Time of playing can be obtained by acceleration information, and number of taking pictures can direct tourist's taking pictures in sightseeing spot for receiving of statistical server
The item number of broadcast.
In this present embodiment, the visit behavioral data of tourist include tourist the dwell times of sightseeing spot, the time of playing, with
And number of taking pictures.According to dwell times, play the time and number of taking pictures is obtained with tourist to the preference of sightseeing spot i.Tool
Body, the tourist is to the preference of sightseeing spot i：
PopiIt is tourist to the preference of sightseeing spot i,Total visiting time for tourist at scenic spot,For
The total degree taken pictures,For the total degree of stop；w1,w2,w3It is different visit behaviors to the impact factor of sightseeing spot preference
And w1+w2+w3=1.
More specifically, play time T of the tourist in sightseeing spot iiFor:Ti=Li/ f, wherein LiIt is tourist in sightseeing spot i
The item number of resultant acceleration data, f are the frequency acquisition of acceleration information.
Number of taking pictures is the item number for the broadcast of taking pictures that the application program in smart phone receives.
Dwell times method is：
Acceleration information sliding window value is set；
The average value of acceleration value in calculation window, acceleration in cycling among windows and make with mean value it is poor, if result
Absolute value is respectively less than preset acceleration float value, then it is assumed that tourist is static within the period of the window；
Obtain the index of each first acceleration value of stationary window；
Stationary window acceleration index is traversed, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number adds 1；
If the difference of consecutive value is equal to 1, static number is remained unchanged；
It is final to obtain tourist in the static number of all sightseeing spots.In this present embodiment, server is also used to tourist's
Visit behavioral data is pre-processed, and is included mainly rejecting abnormalities data, is specifically merged to 3-axis acceleration, specifically
Can be calculated according to the following formula.
Wherein, AcciIndicate set of the tourist in the resultant acceleration data of sightseeing spot i, Accx,Accy,AcczTable respectively
Show the acceleration of x-axis, y-axis, z-axis.
The present embodiment also provides a kind of tourist's preferential learning method based on visit behavior, and the step of specific implementation is as follows：
Step 1 calibrates the iBeacon module that will be arranged in scenic spot, then will be same using configuration tool
The identical Major value of iBeacon module configuration in one scenic spot, configures different in the different sightseeing spots at same scenic spot
IBeacon module Major, Minor value after configuration calibration is stored in server by Minor value, for identification the position letter of tourist
Breath.The calibration of iBeacon module is fairly simple, can carry out range calibration, nothing to iBeacon with special configuration tool (App)
Need complicated calculations.
Application program is downloaded and run to smart phone before step 2, tourist enter scenic spot, opens bluetooth and network switching, uses
In the location information and upload behavioral data of identification tourist.The smart phone that server identifies tourist before tourist enters scenic spot is used
In the visit behavior for storing different tourists.
After step 3, tourist's carrying smart phone enter scenic spot, smart phone receives the broadcast message of iBeacon module, answers
With program according to the broadcast message of parsing, identify the current position of tourist and calculate tourist and iBeacon mark sightseeing spot it
Between distance, if calculate distance be less than pre-set distance threshold, start the acquisition of acceleration information and broadcast of taking pictures
Monitoring.
Using the broadcast of taking pictures of acceleration transducer and android system in smart phone in step 4, the present invention, adopt
Collect the behavioral data of tourist.The data of acceleration acquire and the monitoring for broadcast of taking pictures does not need frequently to be interacted with user,
Acquisition data carry out in the background service of application program, even if application program is switched to backstage or opened another by tourist
An outer application program, the acquisition for going sight-seeing behavioral data also will continue to carry out.Original behavioral data includes tourist in sightseeing spot
Neighbouring acceleration information and broadcast of taking pictures, wherein acceleration information is for analyzing tourist in play time and the stop of sightseeing spot
Number, broadcast of taking pictures is then for obtaining take pictures number of the tourist near sightseeing spot.
Step 5, visit behavioral data upload server, go sight-seeing the acquisition of behavioral data and upload is synchronous progress, intelligence
Energy mobile phone sends network request, and data are uploaded to server.Server is to acceleration information and broadcast of taking pictures after data upload
Classification storage.
Step 6, data are the accurate visit behavior for obtaining tourist after uploading, and need to pre-process data, data
Pretreatment include delete deviate normal value acceleration information and synthesize 3-axis acceleration obtain tourist total acceleration.
Step 7, visit behavior obtain, and obtain tourist in the visit behavior of sightseeing spot using pretreated acceleration information
It such as dwell times, plays the time, number of taking pictures then can the direct item number of the broadcast of taking pictures of tourist that receives of statistical server.
Step 8, tourist sightseeing spot time of playing, the behaviors such as stop and take pictures and embody tourist to the preference journey at scenic spot
Degree, preferential learning model then convert tourist to the preference of sightseeing spot for the visit behavior of tourist.
It is as follows that the visit behavior of step 7 tourist obtains main process：
Step 7-1 obtains the dwell times of tourist first.
The fluctuation range of the static brief acceleration of tourist is smaller, and the method for sliding window can be used, and the big of sliding window is arranged
Small is K, indicates the number of the static the smallest data point of tourist；Data in window are averaged, all numbers in window
It is poor that strong point and mean value are made, if difference thinks that tourist is static when being both less than 0.2, counts tourist in the static secondary of some sightseeing spot with this
Number.
Step 7-2 counts the tourist in the original visit data of tourist in the number of taking pictures of i-th of sightseeing spot.
The camera program of android system can send broadcast when tourist is taken pictures using camera every time
Android.hardware.action.NEW_PICTURE, client main program according to the number of the broadcast of taking pictures received simultaneously
In conjunction with the iBeacon module position identifier obtained before, take pictures action frequency of the tourist in each sightseeing spot can be obtained.
Step 7-3 obtains tourist's playing the time in sightseeing spot.
Play time T of the tourist in sightseeing spot iiIt calculates as follows
Ti=Li/f
LiIt is tourist in the item number of sightseeing spot i resultant acceleration data, f (Hz) is the frequency acquisition of acceleration information.
Tourist's preference acquisition process is specific as follows in above-mentioned steps 8：
Tourist has been obtained in step 7 in each sightseeing spot tourist image design, and tourist can be obtained according to preferential learning model
To the tourism favor of sightseeing spot.
The main function of preferential learning model is the visit preference that tourist is obtained by the visit behavioural analysis of tourist, by right
The building of tourist's preferential learning model is realized in the processing that tourist goes sight-seeing behavioral data.The building process of tourist's tourism favor model
It is the treatment process to visitor behavior data, tourist is defined as Pop to the preference of sightseeing spot ii。
PopiIt is tourist to the preference of sightseeing spot i,For tourist's visiting time total in scenic spot；TiExist for tourist
Sightseeing spot i's plays the time；For the total degree taken pictures；imgiFor tourist sightseeing spot i number of taking pictures；For
The total degree of stop；SiFor tourist sightseeing spot i dwell times；w1,w2,w3It is different visit behaviors to sightseeing spot preference
Impact factor and w1+w2+w3=1.
Fig. 2,3,4 are that application program operational flow diagram and tourist go sight-seeing behavioral data and obtain flow chart, and detailed process is such as
Under：
Step 11), application program obtain the acceleration transducer service list of smart phone, and it is blue to open rights management registration
Tooth permission allows smart phone to find and match bluetooth equipment, smart phone is allowed to be connected to the bluetooth equipment matched；Addition
Network legal power allows program that data are uploaded to server；Add the broadcast of taking pictures that camera permission allows program to obtain system；Just
Beginningization Bluetooth adapter is used to obtain the bluetooth service of system, and detects whether current device supports bluetooth.
Step 12), tourist open application program, unlatching bluetooth and network switching, application initialization and sky are locally stored
Between, for storing the acceleration of tourist and broadcast of taking pictures, initialize Bluetooth adapter, the low-power consumption arrived for showing Current Scan
The distance between Rssi, UUID, Major, Minor and smart phone of bluetooth equipment and iBeacon module.
Step 13), application program open the Bluetooth protocol that bluetooth scanning parsing scans, and first determine whether the low function scanned
Consume whether bluetooth equipment is to be deployed to the bluetooth equipment at scenic spot, and acquire all configured low-power consumption bluetooths in Bluetooth adapter
The distance between smart phone is obtained apart from nearest iBeacon module information.
Step 14), by the distance of the nearest iBeacon module and smart phone obtained in step 12) and setting away from
From threshold comparison, starts the acceleration information for acquiring tourist if the distance is less than distance threshold and monitoring is taken pictures broadcast.
If whether step 15), application program detect the distance between user and iBeacon module, which is less than threshold value, is less than threshold
Value, then continue to execute step 13), and acceleration value and take pictures broadcast of the tourist in the identified areas are then uploaded if more than threshold value, with
And identification information Major and the Minor value in the region.
If whether application program detects the distance between user and iBeacon module, which is less than threshold value, is less than threshold value, repeat
Above-mentioned steps 13), 14), 15), if more than threshold value, then client uploads visit behavioral data to server.
The flow chart that tourist goes sight-seeing behavior is is analyzed by acceleration information in Fig. 5,6, and detailed process is as follows：
Step 21), server receive the primitive behavior data of application program, pre-process first to data, including delete
Except exceptional value, 3-axis acceleration is synthesized.
Specifically, synthesis 3-axis acceleration can be calculated according to the following formula.
Wherein, AcciIndicate set of the tourist in the resultant acceleration data of sightseeing spot i, Accx,Accy,AcczTable respectively
Show the acceleration of x-axis, y-axis, z-axis.
Step 22) carries out sliding average processing to the 3-axis acceleration data after synthesis, improves the accurate of preferential learning
Rate, detailed process is as follows for dwell times of the algorithm statistics tourist of sliding average in sightseeing spot：
Step 221 inputs pretreated acceleration information, and sliding window value is arranged.
It is poor that acceleration and mean value in step 222 calculation window in the average value, cycling among windows of acceleration value are made, if knot
The absolute value of fruit is respectively less than preset acceleration float value, then illustrates that tourist is static within the period of the window.
The index of each first acceleration value of stationary window of step 223 acquisition；Traverse stationary window acceleration rope
Draw, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number adds 1；If the difference of consecutive value is equal to 1, static number
It remains unchanged；It is final to obtain tourist in the static number of all sightseeing spots.
The acceleration item number of step 23), acquisition tourist in different sightseeing spots can be obtained divided by the frequency acquisition of acceleration information
Take tourist in the visiting time of different sightseeing spots.
Step 24), statistics tourist take pictures in the visit behavioral data of each sightseeing spot broadcast item number acquisition tourist exist
The number of taking pictures of different sightseeing spots.
Fig. 7 is the flow chart of tourist's preferential learning, and the visitor behavior obtained in above-mentioned steps includes tourist in each trip
Look at time of playing a little, dwell times, number of taking pictures.Tourist is obtained to trip according to the visit behavior of tourist by preferential learning model
The preference for the sightseeing spot look at.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (10)
1. a kind of tourist's preferential learning system based on visit behavior, which is characterized in that the system includes iBeacon module, intelligence
It can terminal, application program and server；
The iBeacon module is used to identify the location information of sightseeing spot or exhibition room inside showpiece inside scenic spot；
The application program is used to receive and parse through the broadcast data packet of iBeacon module, the visit that identification tourist is presently in
Point, the distance between computational intelligence terminal and iBeacon equipment；
The intelligent terminal acquires tourist in the visit behavioral data of some sightseeing spot and uploads visit behavioral data to server；
The server is used to handle and store the visit behavioral data of tourist, and obtains tourist to not according to preferential learning model
With the preference of sightseeing spot.
2. a kind of tourist's preferential learning system based on visit behavior according to claim 1, which is characterized in that described to obtain
Taking visit behavioral data of the tourist in some sightseeing spot includes obtaining iBeacon module distance d between intelligent terminal,
D=10^ ((abs (Rssi)-A)/(10*n))
Rssi is the intensity for the iBeacon broadcast singal that intelligent terminal receives, and A is between intelligent terminal and iBeacon module
Distance be 1m when iBeacon broadcast singal intensity, n be the environmental attenuation factor.
3. a kind of tourist's preferential learning system based on visit behavior according to claim 1, which is characterized in that the trip
Behavioral data of looking at includes play time of the tourist at scenic spot, take pictures number and dwell times.
4. a kind of tourist's preferential learning system based on visit behavior according to claim 3, which is characterized in that You Ke
The time T that plays of sightseeing spot iiFor:Ti=Li/ f, wherein LiIt is tourist in the item number of sightseeing spot i resultant acceleration data, f is
The frequency acquisition of acceleration information.
5. a kind of tourist's preferential learning system based on visit behavior according to claim 4, which is characterized in that the bat
It is the item number for the broadcast of taking pictures that application program receives in intelligent terminal according to number.
6. a kind of tourist's preferential learning system based on visit behavior according to claim 5, which is characterized in that described to stop
Time counting method is stayed to be：
Acceleration information sliding window value is set；
The average value of acceleration value in calculation window, acceleration in cycling among windows and make with mean value it is poor, if result is absolute
Value is respectively less than preset acceleration float value, then it is assumed that tourist is static within the period of the window；
Obtain the index of each first acceleration value of stationary window；
Stationary window acceleration index is traversed, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number adds 1；If phase
The difference of neighbour's value is equal to 1, then static number remains unchanged；
It is final to obtain tourist in the static number of all sightseeing spots.
7. a kind of tourist's preferential learning system based on visit behavior according to claim 6, which is characterized in that tourist couple
The preference Pop of sightseeing spot iiFor：
For tourist's visiting time total in scenic spot；TiFor tourist's playing the time in sightseeing spot i；To clap
According to total degree；imgiFor tourist sightseeing spot i number of taking pictures；For the total degree of stop；SiIt is tourist in sightseeing spot
The dwell times of i；w1,w2,w3It is different visit behaviors to the impact factor and w of sightseeing spot preference1+w2+w3=1.
8. a kind of tourist's preferential learning method based on visit behavior, which is characterized in that this method is：
Tourist is obtained in the visit behavioral data of some sightseeing spot；The visit behavioral data includes tourist at scenic spot when playing
Between, take pictures number and dwell times；
Tourist is obtained to the preference of different sightseeing spots according to time of playing, take pictures number and dwell times.
9. a kind of tourist's preferential learning method based on visit behavior according to claim 8, which is characterized in that
Play time T of the tourist in sightseeing spot iiFor:Ti=Li/ f, wherein LiIt is tourist in sightseeing spot i resultant acceleration data
Item number, f are the frequency acquisition of acceleration information；
The item number that number is the broadcast of taking pictures that the application program in intelligent terminal receives of taking pictures；
The dwell times method is：
Acceleration information sliding window value is set；
The average value of acceleration value in calculation window, acceleration in cycling among windows and make with mean value it is poor, if result is absolute
Value is respectively less than preset acceleration float value, then it is assumed that tourist is static within the period of the window；
Obtain the index of each first acceleration value of stationary window；
Stationary window acceleration index is traversed, it is poor that consecutive value is made, if the difference of consecutive value is greater than 1, static number adds 1；If phase
The difference of neighbour's value is equal to 1, then static number remains unchanged；
It is final to obtain tourist in the static number of all sightseeing spots.
10. a kind of tourist's preferential learning method based on visit behavior according to claim 9, which is characterized in that tourist
To the preference Pop of sightseeing spot iiFor：
For tourist's visiting time total in scenic spot；TiFor tourist's playing the time in sightseeing spot i；To clap
According to total degree；imgiFor tourist sightseeing spot i number of taking pictures；For the total degree of stop；SiIt is tourist in sightseeing spot
The dwell times of i；w1,w2,w3It is different visit behaviors to the impact factor and w of sightseeing spot preference1+w2+w3=1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810620123.3A CN108875005B (en) | 2018-06-15 | 2018-06-15 | Tourist preference learning system and method based on touring behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810620123.3A CN108875005B (en) | 2018-06-15 | 2018-06-15 | Tourist preference learning system and method based on touring behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108875005A true CN108875005A (en) | 2018-11-23 |
| CN108875005B CN108875005B (en) | 2021-03-26 |
Family
ID=64339163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810620123.3A Active CN108875005B (en) | 2018-06-15 | 2018-06-15 | Tourist preference learning system and method based on touring behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875005B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177451A (en) * | 2020-01-03 | 2020-05-19 | 重庆特斯联智慧科技股份有限公司 | Tourist attraction photo album automatic generation system and method based on face recognition |
| CN111415198A (en) * | 2020-03-19 | 2020-07-14 | 桂林电子科技大学 | Visitor behavior preference modeling method based on reverse reinforcement learning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110077919A1 (en) * | 2009-09-29 | 2011-03-31 | Industry Academic Cooperation Foundation Of Kyung Hee University | Method of recognizing activity on basis of semi-markov conditional random field model |
| CN103183005A (en) * | 2011-12-30 | 2013-07-03 | 中国移动通信集团公司 | Vehicle state detection method, device and system and vehicle anti-theft terminal |
| CN103886715B (en) * | 2014-02-28 | 2016-02-10 | 南京邮电大学 | A kind of tumble detection method for human body |
| CN106021618A (en) * | 2016-07-13 | 2016-10-12 | 桂林电子科技大学 | System and method for inquiring and managing touring information of scenic spot |
| US20170059327A1 (en) * | 2015-09-02 | 2017-03-02 | Apple Inc. | Device state estimation under periodic motion |
| CN107358471A (en) * | 2017-07-17 | 2017-11-17 | 桂林电子科技大学 | A kind of tourist resources based on visit behavior recommends method and system |
| CN107509175A (en) * | 2017-09-19 | 2017-12-22 | 深圳市深层互联科技有限公司 | Bluetooth indoor orientation method, system, storage medium and terminal |
| CN107680010A (en) * | 2017-09-29 | 2018-02-09 | 桂林电子科技大学 | A kind of scenic spot route recommendation method and its system based on visit behavior |
-
2018
- 2018-06-15 CN CN201810620123.3A patent/CN108875005B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110077919A1 (en) * | 2009-09-29 | 2011-03-31 | Industry Academic Cooperation Foundation Of Kyung Hee University | Method of recognizing activity on basis of semi-markov conditional random field model |
| CN103183005A (en) * | 2011-12-30 | 2013-07-03 | 中国移动通信集团公司 | Vehicle state detection method, device and system and vehicle anti-theft terminal |
| CN103886715B (en) * | 2014-02-28 | 2016-02-10 | 南京邮电大学 | A kind of tumble detection method for human body |
| US20170059327A1 (en) * | 2015-09-02 | 2017-03-02 | Apple Inc. | Device state estimation under periodic motion |
| CN106021618A (en) * | 2016-07-13 | 2016-10-12 | 桂林电子科技大学 | System and method for inquiring and managing touring information of scenic spot |
| CN107358471A (en) * | 2017-07-17 | 2017-11-17 | 桂林电子科技大学 | A kind of tourist resources based on visit behavior recommends method and system |
| CN107509175A (en) * | 2017-09-19 | 2017-12-22 | 深圳市深层互联科技有限公司 | Bluetooth indoor orientation method, system, storage medium and terminal |
| CN107680010A (en) * | 2017-09-29 | 2018-02-09 | 桂林电子科技大学 | A kind of scenic spot route recommendation method and its system based on visit behavior |
Non-Patent Citations (3)
| Title |
|---|
| CHIEH-YUAN TSAI ET AL: "A Location-Item-Time sequential pattern mining algorithm for route recommendation", 《KNOWLEDGE-BASED SYSTEMS》 * |
| JUN YANG ET AL: "Toward physical activity diary: motion recognition using simple acceleration features with mobile phones", 《IMCE "09: PROCEEDINGS OF THE 1ST INTERNATIONAL WORKSHOP ON INTERACTIVE MULTIMEDIA FOR CONSUMER ELECTRONICS》 * |
| 孙彦鹏 等: "基于多重隐语义表示模型的旅游路线挖掘", 《模式识别与人工智能》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177451A (en) * | 2020-01-03 | 2020-05-19 | 重庆特斯联智慧科技股份有限公司 | Tourist attraction photo album automatic generation system and method based on face recognition |
| CN111177451B (en) * | 2020-01-03 | 2023-01-24 | 重庆特斯联智慧科技股份有限公司 | Tourist attraction photo album automatic generation system and method based on face recognition |
| CN111415198A (en) * | 2020-03-19 | 2020-07-14 | 桂林电子科技大学 | Visitor behavior preference modeling method based on reverse reinforcement learning |
| CN111415198B (en) * | 2020-03-19 | 2023-04-28 | 桂林电子科技大学 | Tourist behavior preference modeling method based on reverse reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108875005B (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Cognitive information measurements: A new perspective | |
| Chianese et al. | SmARTweet: A location-based smart application for exhibits and museums | |
| CN104335564B (en) | For identify and analyze user personal scene system and method | |
| Mandula et al. | Mobile based home automation using Internet of Things (IoT) | |
| Gu et al. | Paws: Passive human activity recognition based on wifi ambient signals | |
| Miluzzo et al. | CenceMe–injecting sensing presence into social networking applications | |
| CN104798419B (en) | Geographic location signal fingerprint recognition | |
| CN103809536B (en) | A kind of guest room intelligent management system | |
| US8578415B2 (en) | Information providing method, content display terminal, portable terminal, server device, information providing system and program | |
| KR20220156134A (en) | Method for Providing Home Rehabilitation Service With Rotator Cuff Exercise Rehabilitation Device | |
| CN110199321A (en) | Positioning for mixed reality system determines | |
| CN107968689A (en) | Perception recognition methods and device based on wireless communication signals | |
| CN110427462A (en) | With method, apparatus, storage medium and the service robot of user interaction | |
| CN106705972B (en) | A kind of indoor semantic map updating method and system based on user feedback | |
| CN104770054B (en) | The location aware management of uniform resource locator (URL) list for mobile device | |
| CN108965609A (en) | The recognition methods of mobile terminal application scenarios and device | |
| CN106127247B (en) | Image classification method based on the more example support vector machines of multitask | |
| WO2018076181A1 (en) | Fitness management terminal, server, method and system based on two-dimensional code | |
| CN109543844A (en) | Learn situation via pattern match | |
| Draghici et al. | A survey of techniques for automatically sensing the behavior of a crowd | |
| Li et al. | An experimental study for tracking crowd in smart cities | |
| CN104584601A (en) | Discovery method and apparatuses and system for discovery | |
| CN108875005A (en) | A kind of tourist's preferential learning system and method based on visit behavior | |
| WO2021000485A1 (en) | Positioning method and apparatus, and storage medium and electronic device | |
| CN107645772A (en) | Human body positioning method, human body positioning system and positioning server |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20181123 Assignee: Guilin ruiweisaide Technology Co.,Ltd. Assignor: GUILIN University OF ELECTRONIC TECHNOLOGY Contract record no.: X2022450000191 Denomination of invention: A tourist preference learning system and method based on tour behavior Granted publication date: 20210326 License type: Common License Record date: 20221125 |
|
| EE01 | Entry into force of recordation of patent licensing contract |