CN108549649A - It is a kind of that method and system is recommended based on the rural tourism of seasonal characteristic and position feature - Google Patents
It is a kind of that method and system is recommended based on the rural tourism of seasonal characteristic and position feature Download PDFInfo
- Publication number
- CN108549649A CN108549649A CN201810166021.9A CN201810166021A CN108549649A CN 108549649 A CN108549649 A CN 108549649A CN 201810166021 A CN201810166021 A CN 201810166021A CN 108549649 A CN108549649 A CN 108549649A
- Authority
- CN
- China
- Prior art keywords
- latitude
- user
- longitude
- sight spot
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Abstract
The present invention provide it is a kind of based on the rural tourism of seasonal characteristic and position feature recommend method and system, the method includes：Historical user's evaluation based on each sight spot, extracts the user's evaluation time, and be based on the user's evaluation time, extracts seasonal characteristic；According to the Name ＆ Location information at each sight spot, the latitude and longitude information at each sight spot is obtained, and by the way that the latitude and longitude information is mapped to corresponding label block, build the geospatial location feature at each sight spot；According to the user's evaluation time, seasonal characteristic and geospatial location feature, constitutive characteristic vector, and is scored and recorded as label using the user in historical user evaluation；Based on described eigenvector and the label, using the Factorization machine algorithm model pre-established, estimation user scores to the prediction at each sight spot, and generates recommending scenery spot strategy based on prediction scoring.The present invention can more reasonably carry out rural tourism recommending scenery spot, to be effectively improved recommending scenery spot effect and user experience.
Description
Technical field
The present invention relates to technical field of data processing, more particularly, to a kind of based on seasonal characteristic and position feature
Rural tourism recommends method and system.
Background technology
Rural tourism is using travel in holiday as objective, and village field is space, humane noiseless, ecological without destruction, You Ju
With the boorish forms of tourism of wild behavior characteristic.With the rapid development of rural tourism, rural tourism is surrounded in recent years and is proposed more
Original new concept and new theory, such as：You Ju, wild row occupy trip, Home Collection, light constructions, scene epoch etc., new concept with newly
Theoretical proposition keeps the content of rural tourism more rich, and form is more polynary.
The diversification of the abundantization and form of rural tourism content, make tourist when selecting sight spot can because option is excessive and
Generate selection obstacle.In famous sites tourism and cities and towns tourism, recommending scenery spot technology has obtained significant effect.But
Rural tourism is characteristically had any different the notable feature traveled in cities and towns, e.g., it is larger by seasonal effect, geographical location is remoter,
Floating population's rareness etc..
Therefore, directly rural tourism, the townshiies Hui Shou will be applied to for the recommended technology of famous sites tourism and cities and towns tourism
The limitation of village's tourism self-characteristic, is not achieved desired effect, influences user experience.
Invention content
In order to overcome the above problem or solve the above problems at least partly, the present invention provides a kind of based on seasonal characteristic
Method and system is recommended to be effectively improved more reasonably to carry out rural tourism recommending scenery spot with the rural tourism of position feature
Recommending scenery spot effect and user experience.
On the one hand, the present invention provides a kind of based on the rural tourism of seasonal characteristic and position feature recommendation method, including：
S1, historical user's evaluation based on each sight spot, extracts the user's evaluation time, and be based on the user's evaluation time, extracts season
Feature；S2 obtains the latitude and longitude information at each sight spot according to the Name ＆ Location information at each sight spot, and by by institute
It states latitude and longitude information and is mapped to corresponding label block, build the geospatial location feature at each sight spot；S3, according to the user
Evaluation time, the seasonal characteristic and the geospatial location feature, constitutive characteristic vector, and evaluated with the historical user
In user score record be used as label；S4 is based on described eigenvector and the label, utilizes the Factorization pre-established
Machine algorithm model, estimation user score to the prediction at each sight spot, and generate recommending scenery spot strategy based on prediction scoring.
Wherein, the user's evaluation time described in step S1 is specially the character string of the String types comprising month information；
Correspondingly, the step of being based on the user's evaluation time described in step S1, extracting seasonal characteristic further comprises：Utilize JAVA
String.substring () function in development environment extracts the month information in the user's evaluation time, and root
According to seasonal characteristic described in the month information extraction.
Wherein, described according to further comprising the step of seasonal characteristic described in the month information extraction：Extract the moon
Part information is as the seasonal characteristic, and to the different seasonal characteristics respectively with 1,2,3,4,5,6,7,8,9,10,11,12
It is marked.
Wherein, the longitude and latitude at each sight spot is obtained according to the Name ＆ Location information at each sight spot described in step S2
The step of spending information further comprises：According to the Name ＆ Location information, the detail location description at each sight spot is synthesized；Profit
Universal map interface API is called with interfacing, and is described based on the detail location, the universal map interface API is utilized
Return to the latitude and longitude information.
Wherein, the format of the detail location description further comprises：Province+city+county/area+township/town+village+scenic spot name+scape
Point title.
Wherein, the latitude and longitude information includes longitude coordinate information and latitude coordinate information, correspondingly, described in step S2
By the step of latitude and longitude information is mapped to corresponding label block, builds the geospatial location feature at each sight spot into
One step includes：It determines setting step-length, and calculates separately every longitude distance under the setting step-length and every latitude distance；It is based on
The setting step-length, described per longitude distance and per latitude distance, the longitude step-length on calculating Same Latitude and same longitude
On latitude step-length；Based on the longitude step-length on the Same Latitude, the maximum block number of the tag block in longitudinal is calculated
K；Based on the longitude step-length on the Same Latitude, longitude coordinate x of each sight spot in longitudinal is calculated, and be based on institute
The latitude step-length on same longitude is stated, latitude coordinate y of each sight spot on latitude direction is calculated；Based on the longitude coordinate
The latitude and longitude information at each sight spot, is mapped to by x, the maximum block number K of the latitude coordinate y and the tag block according to the following formula
Corresponding tag block：
BlockNumber=y*K+x；
In formula, blockNumber indicates tag block label.
Wherein, Factorization machine algorithm model described in step S4 is specially further second-order factor disassembler model, and
Pattern function is as follows：
In formula,Indicate scoring label, ω0Indicate integral biased, ωiIndicate xiAmount of bias, V indicate decompose square
Battle array, x indicate feature vector.
Wherein, the step for generating recommending scenery spot strategy based on the prediction scoring described in step S4 further comprises：It is right
The prediction scoring is ranked up, and recommends corresponding sight spot to user by the sequence of scoring from high to low according to ranking results.
Further, the method further includes：Area involved by rural tourism is defined as a closed area, it is described
The boundary of closed area is minimum longitude, maximum longitude, minimum latitude value and the maximum latitude value in the area being related to.
On the other hand, the present invention provides a kind of rural tourism commending system based on seasonal characteristic and position feature, including：
Fisrt feature extraction module extracts the user's evaluation time, and be based on the user for historical user's evaluation based on each sight spot
Evaluation time extracts seasonal characteristic；Second feature extraction module is obtained for the Name ＆ Location information according to each sight spot
The latitude and longitude information at each sight spot is taken, and by the way that the latitude and longitude information is mapped to corresponding label block, builds each scape
The geospatial location feature of point；Feature vector build module, for according to the user's evaluation time, the seasonal characteristic and
The geospatial location feature, constitutive characteristic vector, and scored and recorded as mark using the user in historical user evaluation
Label；Decision-making module, for being based on described eigenvector and the label, using the Factorization machine algorithm model pre-established,
Estimate that user scores to the prediction at each sight spot, and recommending scenery spot strategy is generated based on prediction scoring
It is provided by the invention a kind of based on the rural tourism of seasonal characteristic and position feature recommendation method and system, by examining
Consider seasonal factor and scenic spot location factor, predicts that user scores to the prediction at each sight spot using Factorization machine, and according to prediction
Score decision recommending scenery spot strategy, can more reasonably carry out rural tourism recommending scenery spot, to be effectively improved recommending scenery spot effect
Fruit and user experience.
Description of the drawings
Fig. 1 is a kind of flow for recommending method based on the rural tourism of seasonal characteristic and position feature of the embodiment of the present invention
Figure；
Fig. 2 is according to fixed in a kind of rural tourism recommendation method based on seasonal characteristic and position feature of the embodiment of the present invention
The schematic diagram of the closed area of justice；
Fig. 3 is that a kind of structure of the rural tourism commending system based on seasonal characteristic and position feature of the embodiment of the present invention is shown
It is intended to.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, is clearly and completely described the technical solution in the present invention, it is clear that described embodiment is one of the present invention
Divide embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained under the premise of creative work, shall fall within the protection scope of the present invention.
As the one side of the embodiment of the present invention, the present embodiment provides a kind of township based on seasonal characteristic and position feature
Village's tourism recommendation method, with reference to figure 1, be that the embodiment of the present invention is a kind of is recommended based on the rural tourism of seasonal characteristic and position feature
The flow chart of method, including：
S1, historical user's evaluation based on each sight spot, is extracted the user's evaluation time, and be based on the user's evaluation time,
Extract seasonal characteristic；
S2 obtains the latitude and longitude information at each sight spot according to the Name ＆ Location information at each sight spot, and pass through by
The latitude and longitude information is mapped to corresponding label block, builds the geospatial location feature at each sight spot；
S3, according to the user's evaluation time, the seasonal characteristic and the geospatial location feature, constitutive characteristic to
Amount, and scored and recorded as label using the user in historical user evaluation；
S4 is based on described eigenvector and the label, and using the Factorization machine algorithm model pre-established, estimation is used
Family scores to the prediction at each sight spot, and generates recommending scenery spot strategy based on prediction scoring.
It can be understood as, it is contemplated that rural tourism is characteristically had any different the significant properties traveled in cities and towns, such as：Season is special
Property, it is usually related to natural environment style and features to be embodied in rural view, and natural environment style and features changes generating period with season
Variation, corresponding view can be just enjoyed in corresponding season, to which the ability that Various Seasonal attracts tourists also is not quite similar, because
This rural tourism is larger by seasonal effect.
On the other hand, due to the rotation of the earth, revolution rule, the view at diverse geographic location is not quite similar, and not
With area usually there is different humanistic environments, rural tourism also to show the difference of region, be presented as different geographical locations
Characteristic.Previous rural tourism studies have shown that is the frequent generation area of rural tourism apart from cities and towns 20-100km.Therefore, directly will
Cities and towns tourism recommended technology is applied to rural tourism recommendation and optimal effectiveness is not achieved.
The typical characteristics of the present embodiment combination rural tourism itself extract corresponding characteristic, and utilize Factorization
Machine algorithm model handles the characteristic of extraction, finally obtains corresponding Generalization bounds, to be measured according to the recommendation
Recommend corresponding sight spot to corresponding user.
Specifically in step sl, due in advance do not know 1 year in when be most suitable for some sight spot go to watch
Travelling does not know which type of view annual some time sight spot is yet, thus can not determine optimal travel time and
Place.For this problem, all sight spots known to some area are obtained in step S1, and historical time is obtained from big data
Interior user evaluates the evaluation information at these sight spots, i.e. historical user.
For every user's evaluation, there is the evaluation content of corresponding evaluation time and essence, can also include scoring note
Record.This step extracts the information of user's evaluation time from the information that the historical user of acquisition evaluates, and according to the user's evaluation
Time obtains corresponding characteristic element, and extract seasonal characteristic according to all characteristic elements by certain Processing Algorithm.
Based on above description, the geospatial location that the present embodiment also considers sight spot while considering Seasonal Characteristics is special
Property, therefore in step s 2, according to all sight spots in this area of above-mentioned acquisition, title and the position at these sight spots can be obtained
Description information is set, the corresponding detailed latitude and longitude information in sight spot is determined then in conjunction with the location expression information and title at sight spot.
Later, step-length is set according to application demand, and according to the setting step-length by the corresponding detailed longitude and latitude in each sight spot
Information corresponds to corresponding tag block.It is corresponding geographical empty using tag block information extraction one in conjunction with the seasonal characteristic of acquisition
Between position feature.
Wherein, in one embodiment, the method further includes：Area involved by rural tourism is defined as an envelope
Closed region, the boundary of the closed area be the minimum longitude in the area being related to, maximum longitude, minimum latitude value and
Maximum latitude value.
It is to be understood that with reference to figure 2, for according to a kind of rural area based on seasonal characteristic and position feature of the embodiment of the present invention
The schematic diagram of closed area defined in recommendation method of travelling.A closed area is drawn a circle to approve with latitude and longitude information in figure, as this
Area involved by embodiment will be handled rural tourism sight spot all in the region.In defined area when range,
A minimum latitude coordinate and a maximum latitude coordinate are limited on north-south, and a minimum longitude is limited on east-west direction and is sat
Mark, a maximum longitude coordinate.Then sight spot is selected to carry out recommendation process in the region defined by four limit values.
In step s3, by above-mentioned steps obtain user's evaluation time, seasonal characteristic and geospatial location feature into
Row merges.An incidence relation feature vector between user and sight spot is obtained after merging, that is, reacting user can or can not select respectively
The interconnection vector at sight spot.Meanwhile the user in evaluating above-mentioned historical user scores to record and makes corresponding multiple and different marks
Label.
In step s 4, Factorization machine is characterized as with the seasonal characteristic and geospatial location that are obtained according to above-mentioned steps
The factor, using Factorization machine algorithm model to feature vector carry out Factorization, obtain prediction of the user to each sight spot
Scoring.Then it scores according to the prediction at each sight spot, by given rule, generates corresponding recommending scenery spot strategy.
It is provided in an embodiment of the present invention a kind of based on the rural tourism of seasonal characteristic and position feature recommendation method, by examining
Consider seasonal factor and scenic spot location factor, predicts that user scores to the prediction at each sight spot using Factorization machine, and according to prediction
Score decision recommending scenery spot strategy, can more reasonably carry out rural tourism recommending scenery spot, to be effectively improved recommending scenery spot effect
Fruit and user experience.
Wherein optional, the user's evaluation time described in step S1 is specially the word of the String types comprising month information
Symbol string；
Correspondingly, the step of being based on the user's evaluation time described in step S1, extracting seasonal characteristic further comprises：
Using String.substring () function in JAVA development environments, the institute in the user's evaluation time is extracted
Month information is stated, and according to seasonal characteristic described in the month information extraction.
It is to be understood that the present embodiment develops recommending scenery spot system using JAVA development platforms.It is previous according to user first
Evaluation information, i.e., historical user evaluate, extract evaluation time.The string representation of one String type of time, and
Include month information in the character string.In one embodiment, the format of user's evaluation time be " year-month-day-when-point-
Second ".
Then, using String.substring () function in JAVA development environments, from the above-mentioned user's evaluation time
Month information is extracted, and vectorial as seasonal characteristic structure seasonal characteristic using the month information of extraction.
Wherein, described according to further comprising the step of seasonal characteristic described in the month information extraction：Extract the moon
Part information is as the seasonal characteristic, and to the different seasonal characteristics respectively with 1,2,3,4,5,6,7,8,9,10,11,12
It is marked.Seasonal characteristic is divided by 12 season according to above-described embodiment, and respectively with 1,2 ..., 12 natural data into
Line flag.
It is wherein optional, according to the Name ＆ Location information at each sight spot described in step S2, obtain each sight spot
Latitude and longitude information the step of further comprise：
According to the Name ＆ Location information, the detail location description at each sight spot is synthesized；
Using interfacing call universal map interface API, and based on the detail location describe, using it is described universally
Figure interface API returns to the latitude and longitude information.
It is to be understood that the present embodiment is first according to information composition algorithm, by the corresponding name information in same sight spot and position
It sets description information to merge, generates the detail location description at the sight spot.Wherein, in one embodiment, the detail location
The format of description further comprises：Province+city+county/area+township/town+village+scenic spot name+sight name.
Then, universal map interface API is called using JavaScript technologies, detail location description is sent to universally
Figure interface API.Also, it is handled according to details description using universal map interface API, returns to the longitude and latitude letter at sight spot
Breath.Wherein, universal map interface API such as, Baidu map, Google Maps and Amap etc.,
Wherein optional, the latitude and longitude information includes longitude coordinate information and latitude coordinate information, correspondingly, step S2
Described in by the way that the latitude and longitude information is mapped to corresponding label block, build the geospatial location feature at each sight spot
Step further comprises：
It determines setting step-length, and calculates separately every longitude distance under the setting step-length and every latitude distance；
Based on the setting step-length, described per longitude distance and per latitude distance, the longitude step-length on calculating Same Latitude
And the latitude step-length on same longitude；
Based on the longitude step-length on the Same Latitude, the maximum block number K of the tag block in longitudinal is calculated；
Based on the longitude step-length on the Same Latitude, longitude coordinate x of each sight spot in longitudinal is calculated, and
Based on the latitude step-length on the same longitude, latitude coordinate y of each sight spot on latitude direction is calculated；
Based on the maximum block number K of the longitude coordinate x, the latitude coordinate y and the tag block, according to the following formula by each institute
The latitude and longitude information for stating sight spot is mapped to corresponding tag block：
BlockNumber=y*K+x；
In formula, blockNumber indicates tag block label.
Wherein, the supposed premise of above-mentioned algorithm is：The earth is a spheroid, and the equatorial radius of the earth is R1, the pole of the earth
Radius is R2.Therefore, the specific algorithm process carried out using computer thought is as shown in table 1, for according to the embodiment of the present invention one
The acquisition of tag block label is realized in rural tourism recommendation method of the kind based on seasonal characteristic and position feature.
Table 1, in the embodiment of the present invention acquisition of tag block label realize
In table 1, lat indicates that latitude, lng indicate that longitude, dot (lng, lat) indicate the ground indicated by latitude and longitude
Spatial position point is managed, maxLng and minLng indicate maximum longitude and minimum longitude respectively, and maxLat and minLat are indicated respectively
Maximum latitude and minimum latitude, perLng and perLat be illustrated respectively in every longitude distance under setting step-length and often latitude away from
From stepSize indicates setting step-length, and stepSizeLng and stepSizeLat indicate the longitude step-length on Same Latitude respectively
With the latitude step-length on same longitude, blockNumber indicates tag block label.
The distance therein per longitude indicates per unit longitude (unit：Degree) corresponding spherical distance (unit：km).Equally
, per latitude, distance indicates per unit latitude (unit：Degree) corresponding spherical distance (unit：km).Longitude on Same Latitude
Latitude step-length in step-length and same longitude is illustrated respectively in the step-length that is indicated with longitude under setting step-length and is indicated with latitude
Step-length.
It, can be by above-mentioned process flow when the latitude and longitude information at sight spot is mapped to corresponding label block according to above-described embodiment
Carry out correspondent transform.
Wherein optional, Factorization machine algorithm model described in step S4 is specially further second-order factor disassembler mould
Type, and pattern function is as follows：
In formula,Indicate scoring label, ω0Indicate integral biased, ωiIndicate xiAmount of bias, V indicate decompose square
Battle array, x indicate feature vector.
It is to be understood that for the feature vector obtained according to above-described embodiment, above-mentioned second-order factor disassembler mould is utilized
Type carries out internal data operation, is scored by the prediction of model output estimation.
Wherein optional, the step for generating recommending scenery spot strategy based on the prediction scoring described in step S4 is further wrapped
It includes：Prediction scoring is ranked up, and is recommended to user to doing something for the occasion by the sequence of scoring from high to low according to ranking results
Point.
It is to be understood that after according to above-described embodiment to all sight spots carry out prediction scoring in this area, according to commenting
The height divided is ranked up each sight spot.Then the sequence in sequence from high to low is pressed, the several corresponding of front is selected
Recommending scenery spot is to client.And when user does not receive to recommend, the pointer of iteration more new sort, by posterior recommending scenery spot in sequence
To user.For example, selection scoring is highest several from sequence, such as first three, it is pushed to client.When push is ignored in client's selection
When, recommend in sequence the 4th~6 to user, if user continues selection and ignores, recommends 7~9 in sequence, such iteration
Cycle is until recommend successfully.
As the other side of the embodiment of the present invention, the present embodiment provides a kind of based on seasonal characteristic and position feature
Rural tourism commending system is pushed away with reference to figure 3 for a kind of rural tourism based on seasonal characteristic and position feature of the embodiment of the present invention
The structural schematic diagram of system is recommended, including：Fisrt feature extraction module 1, second feature extraction module 2, feature vector build module 3
With decision-making module 4.Wherein,
Fisrt feature extraction module 1 extracts the user's evaluation time, and be based on for historical user's evaluation based on each sight spot
The user's evaluation time extracts seasonal characteristic；
Second feature extraction module 2 is used for the Name ＆ Location information according to each sight spot, obtains each sight spot
Latitude and longitude information, and by the way that the latitude and longitude information is mapped to corresponding label block, build the geographical space position at each sight spot
Set feature；
Feature vector builds module 3 and is used for according to the user's evaluation time, the seasonal characteristic and the geographical space
Position feature, constitutive characteristic vector, and scored and recorded as label using the user in historical user evaluation；
Decision-making module 4 is used to be based on described eigenvector and the label, utilizes the Factorization machine algorithm pre-established
Model, estimation user score to the prediction at each sight spot, and generate recommending scenery spot strategy based on prediction scoring.
It can be understood as, it is contemplated that rural tourism is characteristically had any different the significant properties traveled in cities and towns, such as：Season is special
Property, it is usually related to natural environment style and features to be embodied in rural view, and natural environment style and features changes generating period with season
Variation, corresponding view can be just enjoyed in corresponding season, to which the ability that Various Seasonal attracts tourists also is not quite similar, because
This rural tourism is larger by seasonal effect.
On the other hand, due to the rotation of the earth, revolution rule, the view at diverse geographic location is not quite similar, and not
With area usually there is different humanistic environments, rural tourism also to show the difference of region, be presented as different geographical locations
Characteristic.Previous rural tourism studies have shown that is the frequent generation area of rural tourism apart from cities and towns 20-100km.Therefore, directly will
Cities and towns tourism recommended technology is applied to rural tourism recommendation and optimal effectiveness is not achieved.
Above-mentioned processing module is arranged in the present embodiment in commending system, to combine the typical characteristics of rural tourism itself, carries
Corresponding characteristic is taken, and the characteristic of extraction is handled using Factorization machine algorithm model, finally obtains phase
The Generalization bounds answered recommend corresponding sight spot to be measured to corresponding user according to the recommendation.
Wherein, fisrt feature extraction module 1 is specifically used for obtaining all sight spots known to some area, and from big data
User in historical time is obtained to evaluate the evaluation information at these sight spots, i.e. historical user.
Meanwhile for every user's evaluation, there is the evaluation content of corresponding evaluation time and essence, can also include commenting
Member record.Fisrt feature extraction module 1 extracts the information of user's evaluation time from the information that the historical user of acquisition evaluates, and
Corresponding characteristic element is obtained, and carry according to all characteristic elements by certain Processing Algorithm according to the user's evaluation time
Take seasonal characteristic.
All sight spots in this area of the second feature extraction module 2 according to above-mentioned acquisition, can obtain the name at these sight spots
Claim and location expression information, location expression information and the title determination then in conjunction with sight spot correspond to the detailed longitude and latitude letter in sight spot
Breath.
Later, second feature extraction module 2 sets step-length according to application demand, and according to the setting step-length by each sight spot
Corresponding detailed latitude and longitude information corresponds to corresponding tag block.In conjunction with the seasonal characteristic of acquisition, 2 profit of second feature extraction module
Go out the geospatial location feature at each sight spot with tag block information extraction.
User's evaluation time, seasonal characteristic and the geography that feature vector structure module 3 will be obtained according to above functions module
Spatial position feature merges.An incidence relation feature vector between user and sight spot is obtained after merging, i.e. reaction is used
Family can or can not select the vector at each sight spot.Meanwhile feature vector structure module 3 comments the user in above-mentioned historical user's evaluation
Member record makes corresponding multiple and different labels.
Decision-making module 4 using using above-mentioned function module obtain seasonal characteristic and position feature as Factorization machine because
Son carries out Factorization using Factorization machine algorithm model to feature vector, obtains user and scores the prediction at each sight spot.
Then decision-making module 4, by given rule, generates corresponding recommending scenery spot strategy according to the prediction scoring to each sight spot.
A kind of rural tourism commending system based on seasonal characteristic and position feature provided in an embodiment of the present invention, by
Corresponding function module is set in system, while considering seasonal factor and scenic spot location factor, predicts to use using Factorization machine
Family scores to the prediction at each sight spot, and according to prediction scoring decision recommending scenery spot strategy, can more reasonably carry out rural tourism
Recommending scenery spot, to be effectively improved recommending scenery spot effect and user experience.
In addition, those skilled in the art it should be understood that the present invention application documents in, term " comprising ",
"comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process including a series of elements,
Method, article or equipment include not only those elements, but also include other elements that are not explicitly listed, or are also wrapped
It includes as elements inherent to such a process, method, article, or device.In the absence of more restrictions, by sentence " including
One ... " limit element, it is not excluded that there is also another in the process, method, article or apparatus that includes the element
Outer identical element.
In the specification of the present invention, numerous specific details are set forth.It should be understood, however, that the embodiment of the present invention can
To put into practice without these specific details.In some instances, well known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it should be understood that disclose in order to simplify the present invention and helps to understand respectively
One or more of a inventive aspect, in the above description of the exemplary embodiment of the present invention, each spy of the invention
Sign is grouped together into sometimes in single embodiment, figure or descriptions thereof.
It is intended in reflection is following however, should not explain the method for the disclosure：That is the claimed invention requirement
The more features of feature than being expressly recited in each claim.More precisely, as claims are reflected
Like that, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows the power of specific implementation mode
Thus sharp claim is expressly incorporated in the specific implementation mode, wherein independent reality of each claim as the present invention itself
Apply example.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, and those skilled in the art should understand that：It still can be right
Technical solution recorded in foregoing embodiments is modified or equivalent replacement of some of the technical features；And this
A little modification or replacements, the spirit and model of various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (10)
1. a kind of recommending method based on the rural tourism of seasonal characteristic and position feature, which is characterized in that including：
S1, historical user's evaluation based on each sight spot, is extracted the user's evaluation time, and be based on the user's evaluation time, extraction
Seasonal characteristic；
S2 obtains the latitude and longitude information at each sight spot according to the Name ＆ Location information at each sight spot, and by will be described
Latitude and longitude information is mapped to corresponding label block, builds the geospatial location feature at each sight spot；
S3, according to the user's evaluation time, the seasonal characteristic and the geospatial location feature, constitutive characteristic is vectorial,
And the user in being evaluated using the historical user is scored and is recorded as label；
S4 is based on described eigenvector and the label, using the Factorization machine algorithm model pre-established, estimates user couple
The prediction at each sight spot is scored, and generates recommending scenery spot strategy based on prediction scoring.
2. according to the method described in claim 1, it is characterized in that, the user's evaluation time described in step S1 is specially to include the moon
The character string of the String types of part information；
Correspondingly, the step of being based on the user's evaluation time described in step S1, extracting seasonal characteristic further comprises：
Using String.substring () function in JAVA development environments, the moon in the user's evaluation time is extracted
Part information, and according to seasonal characteristic described in the month information extraction.
3. according to the method described in claim 2, it is characterized in that, described according to seasonal characteristic described in the month information extraction
The step of further comprise：The month information is extracted as the seasonal characteristic, and the different seasonal characteristics is distinguished
It is marked with 1,2,3,4,5,6,7,8,9,10,11,12.
4. according to the method described in claim 1, it is characterized in that, according to the title at each sight spot and position described in step S2
The step of confidence ceases, the latitude and longitude information for obtaining each sight spot further comprises：
According to the Name ＆ Location information, the detail location description at each sight spot is synthesized；
Universal map interface API is called using interfacing, and is described based on the detail location, is connect using the universal map
Mouth API returns to the latitude and longitude information.
5. according to the method described in claim 4, it is characterized in that, the format of detail location description further comprises：Save+
City+county/area+township/town+village+scenic spot name+sight name.
6. according to the method described in claim 1, it is characterized in that, the latitude and longitude information includes longitude coordinate information and latitude
Coordinate information, correspondingly, building each scape by the way that the latitude and longitude information is mapped to corresponding label block described in step S2
The step of geospatial location feature of point, further comprises：
It determines setting step-length, and calculates separately every longitude distance under the setting step-length and every latitude distance；
Based on the setting step-length, described per longitude distance and per latitude distance, calculate longitude step-length on Same Latitude and
Latitude step-length on same longitude；
Based on the longitude step-length on the Same Latitude, the maximum block number K of the tag block in longitudinal is calculated；
Based on the longitude step-length on the Same Latitude, longitude coordinate x of each sight spot in longitudinal is calculated, and be based on
Latitude step-length on the same longitude calculates latitude coordinate y of each sight spot on latitude direction；
Based on the maximum block number K of the longitude coordinate x, the latitude coordinate y and the tag block, according to the following formula by each scape
The latitude and longitude information of point is mapped to corresponding tag block：
BlockNumber=y*K+x；
In formula, blockNumber indicates tag block label.
7. according to the method described in claim 1, it is characterized in that, Factorization machine algorithm model described in step S4 is further
Specially second-order factor disassembler model, and pattern function is as follows：
In formula,Indicate scoring label, ω0Indicate integral biased, ωiIndicate xiAmount of bias, V indicate split-matrix, x tables
Show feature vector.
8. according to the method described in claim 1, it is characterized in that, generating sight spot based on prediction scoring described in step S4
The step of Generalization bounds, further comprises：
Prediction scoring is ranked up, and is recommended to user to doing something for the occasion by the sequence of scoring from high to low according to ranking results
Point.
9. according to the method described in claim 1, it is characterized in that, further including：Area involved by rural tourism is defined as
The boundary of one closed area, the closed area is the minimum longitude, maximum longitude, minimum latitude in the area being related to
Angle value and maximum latitude value.
10. a kind of rural tourism commending system based on seasonal characteristic and position feature, which is characterized in that including：
Fisrt feature extraction module extracts the user's evaluation time, and for historical user's evaluation based on each sight spot based on described
The user's evaluation time extracts seasonal characteristic；
Second feature extraction module obtains the longitude and latitude at each sight spot for the Name ＆ Location information according to each sight spot
Information is spent, and by the way that the latitude and longitude information is mapped to corresponding label block, the geospatial location for building each sight spot is special
Sign；
Feature vector builds module, for according to the user's evaluation time, the seasonal characteristic and the geospatial location
Feature, constitutive characteristic vector, and scored and recorded as label using the user in historical user evaluation；
Decision-making module, for being based on described eigenvector and the label, using the Factorization machine algorithm model pre-established,
Estimate that user scores to the prediction at each sight spot, and recommending scenery spot strategy is generated based on prediction scoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810166021.9A CN108549649B (en) | 2018-02-28 | 2018-02-28 | Rural tourism recommendation method and system based on seasonal characteristics and position characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810166021.9A CN108549649B (en) | 2018-02-28 | 2018-02-28 | Rural tourism recommendation method and system based on seasonal characteristics and position characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549649A true CN108549649A (en) | 2018-09-18 |
| CN108549649B CN108549649B (en) | 2021-01-15 |
Family
ID=63515833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810166021.9A Expired - Fee Related CN108549649B (en) | 2018-02-28 | 2018-02-28 | Rural tourism recommendation method and system based on seasonal characteristics and position characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549649B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284443A (en) * | 2018-11-28 | 2019-01-29 | 四川亨通网智科技有限公司 | A kind of tourism recommended method and system based on crawler technology |
| CN110648256A (en) * | 2019-09-18 | 2020-01-03 | 四川省绵阳太古软件有限公司 | Health product management system applied to spring and autumn and old people |
| CN113094603A (en) * | 2021-06-10 | 2021-07-09 | 湖南中惠旅智能科技有限责任公司 | Tourist attraction recommendation method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325587A1 (en) * | 2009-01-21 | 2013-12-05 | Truaxis, Inc. | System and method for managing campaign effectiveness by a merchant |
| CN104615790A (en) * | 2015-03-09 | 2015-05-13 | 百度在线网络技术（北京）有限公司 | Characteristic recommendation method and device |
| CN104657509A (en) * | 2015-03-18 | 2015-05-27 | 苏州大学 | Method and system for recommending tourist destinations based on historical photo information |
| CN105069717A (en) * | 2015-07-29 | 2015-11-18 | 陕西师范大学 | Personalized travel route recommendation method based on tourist trust |
| CN105979376A (en) * | 2015-12-02 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Recommendation method and device |
| CN106447547A (en) * | 2016-11-01 | 2017-02-22 | 合肥华贝信息科技有限公司 | Intelligent tourism platform and running method |
| CN106997549A (en) * | 2017-02-14 | 2017-08-01 | 火烈鸟网络(广州)股份有限公司 | The method for pushing and system of a kind of advertising message |
| CN107527303A (en) * | 2017-07-20 | 2017-12-29 | 中国农业大学 | A kind of rural tourism visualized recommendation method and system |
| CN107609003A (en) * | 2017-07-20 | 2018-01-19 | 中国农业大学 | A kind of rural tourism recommendation information method for visualizing and device |
| 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
- 2018-02-28 CN CN201810166021.9A patent/CN108549649B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325587A1 (en) * | 2009-01-21 | 2013-12-05 | Truaxis, Inc. | System and method for managing campaign effectiveness by a merchant |
| CN104615790A (en) * | 2015-03-09 | 2015-05-13 | 百度在线网络技术（北京）有限公司 | Characteristic recommendation method and device |
| CN104657509A (en) * | 2015-03-18 | 2015-05-27 | 苏州大学 | Method and system for recommending tourist destinations based on historical photo information |
| CN105069717A (en) * | 2015-07-29 | 2015-11-18 | 陕西师范大学 | Personalized travel route recommendation method based on tourist trust |
| CN105979376A (en) * | 2015-12-02 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Recommendation method and device |
| CN106447547A (en) * | 2016-11-01 | 2017-02-22 | 合肥华贝信息科技有限公司 | Intelligent tourism platform and running method |
| CN106997549A (en) * | 2017-02-14 | 2017-08-01 | 火烈鸟网络(广州)股份有限公司 | The method for pushing and system of a kind of advertising message |
| CN107527303A (en) * | 2017-07-20 | 2017-12-29 | 中国农业大学 | A kind of rural tourism visualized recommendation method and system |
| CN107609003A (en) * | 2017-07-20 | 2018-01-19 | 中国农业大学 | A kind of rural tourism recommendation information method for visualizing and device |
| 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 (1)
| Title |
|---|
| 高万林 等: ""WebGIS 在农业灌溉信息管理中的应用研究"", 《地理信息世界》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284443A (en) * | 2018-11-28 | 2019-01-29 | 四川亨通网智科技有限公司 | A kind of tourism recommended method and system based on crawler technology |
| CN110648256A (en) * | 2019-09-18 | 2020-01-03 | 四川省绵阳太古软件有限公司 | Health product management system applied to spring and autumn and old people |
| CN113094603A (en) * | 2021-06-10 | 2021-07-09 | 湖南中惠旅智能科技有限责任公司 | Tourist attraction recommendation method and system |
| CN113094603B (en) * | 2021-06-10 | 2021-08-17 | 湖南中惠旅智能科技有限责任公司 | Tourist attraction recommendation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549649B (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145169B (en) | Address matching method based on statistical word segmentation | |
| Spohrer | Information in places | |
| CN104598506B (en) | Address generation, querying method and the device of geographical location point | |
| CN102639961A (en) | Navigation system with map compression and method of operation thereof | |
| US20150356088A1 (en) | Tile-based geocoder | |
| CN108549649A (en) | It is a kind of that method and system is recommended based on the rural tourism of seasonal characteristic and position feature | |
| CN104981681A (en) | Displaying location preview | |
| CN103857989A (en) | Method and apparatus for presenting search results in an active user interface element | |
| Arlinghaus et al. | Spatial mathematics: Theory and practice through mapping | |
| Thurston et al. | Integrated geospatial technologies: a guide to GPS, GIS, and data logging | |
| Liu et al. | Pinpointing the sources and measuring the lengths of the principal rivers of the world | |
| Rutherford et al. | Interpretation as a vital ingredient of geotourism in coastal environments: The geology of sea level change, Rottnest Island, Western Australia | |
| Choudhury | An introduction to geographic information technology | |
| Perttola | Digital navigator on the seas of the Selden Map of China: Sequential least-cost path analysis using dynamic wind data | |
| Bearman | GIS: Research Methods | |
| EP1876576B1 (en) | Method and device for position finding | |
| KR101459872B1 (en) | Indexing system of space object for combination object of SOI and content | |
| CN106023128B (en) | The fusion method and device of topographic map data and chart data | |
| Goodchild et al. | Data quality in massive data sets | |
| CN117556158B (en) | User peripheral location visualization method and system for coupling place name label and contour line | |
| KR20010113196A (en) | Method For Indication Of Advertisement In Electronic Map | |
| Kumar et al. | Geographic Information Systems in Urban Planning and Management | |
| CN1979477A (en) | Image displaying system for mobile device | |
| Wunsch et al. | The TOPEX/POSEIDON data | |
| Richards et al. | Changing Coastlines: Putting Australia on the World Map, 1493-1993 |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210115 |