CN108985898A - A kind of place methods of marking, device and computer readable storage medium - Google Patents
A kind of place methods of marking, device and computer readable storage medium Download PDFInfo
- Publication number
- CN108985898A CN108985898A CN201810763165.2A CN201810763165A CN108985898A CN 108985898 A CN108985898 A CN 108985898A CN 201810763165 A CN201810763165 A CN 201810763165A CN 108985898 A CN108985898 A CN 108985898A
- Authority
- CN
- China
- Prior art keywords
- place
- target place
- information
- score value
- target
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q50/12—Hotels or restaurants
Abstract
The embodiment of the invention discloses a kind of place methods of marking, device and computer readable storage mediums, obtain the data information of target place；Wherein, data information may include the data information that unmanned machine acquires and the historical data information collected from network；Using data classification model, classification processing is carried out to data information, to obtain sorted characteristic information；According to received user demand information and the corresponding initial characteristics score value of each characteristic information, the scoring vector of target place is determined；According to the scoring vector in the scoring vector sum starting place of target place, the score value of target place is finally determined.The score value of target place is the fractional value determined in the case where having fully considered user demand and having originated place to the influence degree of target place, fractional value is higher illustrate target place meet user's actual need probability it is higher.When carrying out the recommendation in place according to the score value, the place recommended is allowed to be more in line with user demand.
Description
Technical field
The present invention relates to resource recommendation technical fields, can more particularly to a kind of place methods of marking, device and computer
Read storage medium.
Background technique
With the continuous development of science and technology, the science and technology of the world today is widely used in terms of the side that we live
Face, people are also higher and higher for the construction requirements of spiritual culture.For example, festivals or holidays most people want to walk out door, with
Friend relatives travels play together.How to select the target place for meeting user demand is a problem.It or is to use
One dining in restaurant of selection is wanted at family, how to recommend to meet the restaurant of its taste to be a problem to user.
In the prior art, place marking mode tends to rely on historical user's scoring and is ranked up, and lacks one completely
Points-scoring system.The result that this way of recommendation often leads to recommend does not meet the demand of user.
It is those skilled in the art's urgent problem to be solved as it can be seen that how recommendation results to be made to be more in line with user demand.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of place methods of marking, device and computer readable storage medium are provided, it can
So that recommendation results are more in line with user demand.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of place methods of marking, comprising:
Obtain the data information of target place；Wherein, the data information include unmanned machine acquisition data information and
The historical data information collected from network；
Using data classification model, classification processing is carried out to the data information, to obtain sorted characteristic information；
According to received user demand information and the corresponding initial characteristics score value of each characteristic information, institute is determined
State the scoring vector of target place；
According to the scoring vector in the scoring vector sum starting place of the target place, commenting for the target place is determined
Score value.
Optionally, described according to received user demand information and each corresponding initial characteristics of the characteristic information point
Value, determines that the scoring vector of the target place includes:
According to received user demand information, each corresponding weighted value of the characteristic information is calculated；
According to the weighted value and the corresponding initial characteristics score value of each characteristic information, the target field is obtained
Scoring vector.
Optionally, described according to received user demand information, calculate each corresponding weight of the characteristic information
Value includes:
According to the following formula, received user demand information is handled, to determine that each characteristic information respectively corresponds to
Weighted value fDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
Optionally, the scoring vector in the scoring vector sum starting place according to the target place, is determined described
The score value of target place includes:
The scoring vector in the scoring vector sum starting place according to the target place, calculates the target place and institute
State the vector distance in starting place；
The vector distance is handled using following degree of correlation formula, determines the target place and the starting
The degree of correlation I in placeD(ik, jk),
Wherein, dD(ik, jk) indicates k-th of the characteristic component and k-th for originating place j of the target place i
The vector distance of characteristic component, dmaxIndicate the vector maximum distance of the target place i and the starting place j, α indicates to adjust
One parameter of whole relationship weight；
The degree of correlation is handled using following scoring more new formula, determines the score value of the target place i
Tr(Dik),
Wherein, Tr (Djk) indicate the score value for originating place j.
The embodiment of the invention also provides a kind of place scoring apparatus, including acquiring unit, taxon, the first determining list
Member and the second determination unit；
The acquiring unit, for obtaining the data information of target place；Wherein, the data information includes unmanned machine
The data information of acquisition and the historical data information collected from network；
The taxon carries out classification processing to the data information, to be divided for utilizing data classification model
Characteristic information after class；
First determination unit, for corresponding according to received user demand information and each characteristic information
Initial characteristics score value determines the scoring vector of the target place；
Second determination unit originates the scoring vector in place for the scoring vector sum according to the target place,
Determine the score value of the target place.
Optionally, first determination unit includes computation subunit and obtains subelement；
The computation subunit, for it is respectively right to calculate each characteristic information according to received user demand information
The weighted value answered；
It is described to obtain subelement, for according to the weighted value and each corresponding initial characteristics of the characteristic information
Score value obtains the scoring vector of the target place.
Optionally, the computation subunit is specifically used for according to the following formula, at received user demand information
Reason, to determine the corresponding weighted value f of each characteristic informationDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
Optionally, second determination unit includes apart from computation subunit, relatedness computation subelement and score value meter
Operator unit；
It is described apart from computation subunit, for the scoring vector sum starting place according to the target place scoring to
Amount calculates the vector distance of the target place and the starting place；
The relatedness computation subelement, for being handled using following degree of correlation formula the vector distance, really
Make the degree of correlation I of the target place and the starting placeD(ik, jk),
Wherein, dD(ik, jk) indicates k-th of the characteristic component and k-th for originating place j of the target place i
The vector distance of characteristic component, dmaxIndicate the vector maximum distance of the target place i and the starting place j, α indicates to adjust
One parameter of whole relationship weight；
The score value computation subunit, for being handled using following scoring more new formula the degree of correlation, really
Make the score value Tr (D of the target place iik),
Wherein, Tr (Djk) indicate the score value for originating place j.
The embodiment of the invention also provides a kind of place scoring apparatus, comprising:
Memory, for storing computer program；
Processor, for executing the computer program to realize such as the step of above-mentioned place methods of marking.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, is realized when the computer program is executed by processor such as the step of above-mentioned place methods of marking.
The data information of target place is obtained it can be seen from above-mentioned technical proposal；Wherein, the data information can wrap
The historical data information for including the data information of unmanned machine acquisition and being collected from network；Using data classification model, to data
Information carries out classification processing, to obtain sorted characteristic information；It is each according to received user demand information and each characteristic information
Self-corresponding initial characteristics score value can determine the scoring vector of target place；It is risen according to the scoring vector sum of target place
The scoring vector in beginning place, finally determines the score value of target place.The score value of target place is to fully consider use
Family demand and starting place are to the fractional value determined in the case where the influence degree of target place, the higher theory of fractional value
The probability that bright target place meets user's actual need is higher.When carrying out the recommendation in place according to the score value, so that recommend
Place can be more in line with user demand.
Detailed description of the invention
In order to illustrate the embodiments of the present invention more clearly, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of place methods of marking provided in an embodiment of the present invention；
Fig. 2 is a kind of structural schematic diagram of place scoring apparatus provided in an embodiment of the present invention；
Fig. 3 is a kind of hardware structural diagram of place scoring apparatus provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, those of ordinary skill in the art are without making creative work, obtained every other
Embodiment belongs to the scope of the present invention.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.
Next, a kind of place methods of marking provided by the embodiment of the present invention is discussed in detail.Fig. 1 is the embodiment of the present invention
A kind of flow chart of the place methods of marking provided, this method comprises:
S101: the data information of target place is obtained.
In embodiments of the present invention, the place that user is currently located can be referred to as and originates place, user wants arrival
Next place is referred to as target place.
Target place can be the regions such as market, tourist attraction, park, hotel, restaurant.Target place can be according to user
Demand determine that the number of target place can be one or more.
In embodiments of the present invention, by way of carrying out scoring to target place and estimating, to user's recommendation score highest
Target place either to user show target place score value, in order to user can according to the score value choose meet
The target place of demand.
It is similar that the score value of each target place estimates process, next by taking a target place as an example, to the target
The process expansion of estimating of place score value is introduced.
When being estimated to target place progress score value, it is necessary first to obtain the data information of target place.Wherein, data
Information may include the data information that unmanned machine acquires and the historical data information collected from network.
The data information of unmanned machine acquisition may include the flow of the people information of target place, Current traffic operation conditions etc.
Information.
The historical data information collected from network may include the geographical location information of target place, humanity history letter
Breath, frastructure state information, scale information etc..
In practical applications, the data information of unmanned machine acquisition and the historical data information collected from network may
There are the intersections of data, i.e., include the data information of same type in both data informations.
For example, the data information acquired by unmanned machine is available to arrive for the place of some tourist attractions types
The flow of the people information in the place.Correspondingly, the Internet ticket sales situation in the place can be collected into from network, according to Internet ticket sales
Situation carries out preliminary evaluation to the flow of the people in the place, obtains the flow of the people information in the place.
The data information of target place is the data basis for carrying out target place score value and estimating, in the embodiment of the present invention
In, summarized by the data information for acquiring unmanned machine and the historical data information collected from network as target field
Data information so that data information more comprehensively, it is accurate.When being estimated to carry out score value according to the data information, make
Obtain the actual conditions that score value can more be bonded target place.
S102: utilizing data classification model, classification processing is carried out to data information, to obtain sorted characteristic information.
When carrying out classification processing to data information, it can be divided according to the data type belonging to data information.For
The data information of same type can carry out comprehensive analysis, so that it is determined that corresponding characteristic information out.
The corresponding characteristic information of same type of data information.It, can be with according to the difference of the affiliated type of data information
Obtain multiple characteristic informations.
S103: it according to received user demand information and the corresponding initial characteristics score value of each characteristic information, determines
The scoring vector of target place.
By taking a target place as an example, the corresponding characteristic information of the target place often has multiple in S102.
In practical applications, user can set different score values to different characteristic informations according to their own needs.
For example, the fractional value corresponding to traffic conditions can be then arranged when traffic conditions of the user to target place are more paid attention to
It is higher；It, then can will be corresponding to humanity history information when humanity history information of the user to target place is less paid attention to
Fractional value setting it is lower.
User can set corresponding fractional value to all characteristic informations of target place, can also be only to Partial Feature
The corresponding fractional value of information setting, the other feature information for not setting fractional value then can be set as default fractional value,
Wherein, default fractional value can be zero, be also possible to the lesser numerical value of value.
The fractional value that user sets characteristic information reflects this feature information to the influence degree of target place, score
Value is higher, illustrates that its influence degree is bigger.According to fractional value set by user, power shared by each characteristic information can be determined
Weight.
In the concrete realization, received user demand information can be handled according to the following formula, it is each to determine
The corresponding weighted value f of characteristic informationDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
Weighted value corresponding to each characteristic information is determine one in the case where considering user's actual need
Rate of specific gravity.Other than weighted value, each characteristic information has its corresponding initial characteristics score value.
Wherein, initial characteristics score value is identified fractional value when carrying out ranking to characteristic information.
In practical applications, each characteristic information can be directed to, one table of grading is set, be stored in the table of grading
Different grades of division range and corresponding fractional value can determine this feature according to division range locating for characteristic information
The initial characteristics score value of information.
For example, geographical location information can be divided into downtown, the suburbs and 3, remote suburb grade, corresponding point
Numerical value is followed successively by 3,2,1；Humanity history information is divided into level-one, second level and three-level according to state utility function protection class, it is right
The fractional value answered, which is followed successively by, is divided into 3,2,1.
After determining in target place the corresponding weighted value of each characteristic information and initial characteristics score value, according to the weight
Value and initial characteristics fractional value, can determine the scoring vector of target place.
Specifically, weighted value corresponding to each feature vector can be multiplied with initial characteristics fractional value, the spy is obtained
The score value of vector is levied, the set of the score value of all feature vectors of target place is the scoring vector A of target placei=
[fi1·gi1,…,fik·gik,…,fiM·giM]。
Wherein, fikIndicate weighted value corresponding to k-th of characteristic information of target place, gikIndicate the kth of target place
Initial characteristics fractional value corresponding to a characteristic information, k=1, M, M indicate total of the characteristic information of target place
Number.
S104: according to the scoring vector in the scoring vector sum starting place of target place, the scoring of target place is determined
Value.
Starting place is the place that user is currently located, and corresponding scoring vector is referred to above-mentioned S101-S103's
Step is determined.
In embodiments of the present invention, it on the basis of each characteristic information is assessed in target place, also fully considers
Influence situation of the starting place to target place, so that the score value for the target place estimated out is more bonded user's
Actual demand.
In the concrete realization, mesh can be calculated according to the scoring vector in the scoring vector sum starting place of target place
It marks place and originates the vector distance d in placeD(ik, jk)=| | Aik-Ajk||；
Wherein, AikIndicate the score value of k-th of characteristic information in the scoring vector of target place i, AjkIndicate starting place
The score value of k-th of characteristic information in the scoring vector of j.
Vector distance is handled using following degree of correlation formula, determine target place and originates the degree of correlation in place
ID(ik, jk),
Wherein, dD(ik, jk) indicates k-th of characteristic component of target place i and k-th of characteristic component of starting place j
Vector distance, dmaxIt indicates target place i and originates the vector maximum distance of place j, α indicates one of adjustment relationship weight
Parameter.The specific value of α can be set according to actual needs, it is not limited here.
After determining target place and originating the degree of correlation in place, can use following scoring more new formula to the degree of correlation into
Row processing, determines the score value Tr (D of target place iik),
Wherein, Tr (Djk) indicate to originate the score value of place j, Tr (Djk) can be according to Aj=[fj1·gj1,…,fjk·
gjk,…,fjM·gjM] determination obtain.
The score value of target place is higher, illustrate target place meet user demand probability it is higher.
When carrying out place recommendation, when target field is all multiple, then the highest target place of score value can be recommended
To user；Either by these target places, user is successively showed according to the sequence of score value from high to low, for user's choosing
It selects.
The data information of target place is obtained it can be seen from above-mentioned technical proposal；Wherein, the data information can wrap
The historical data information for including the data information of unmanned machine acquisition and being collected from network；Using data classification model, to data
Information carries out classification processing, to obtain sorted characteristic information；It is each according to received user demand information and each characteristic information
Self-corresponding initial characteristics score value can determine the scoring vector of target place；It is risen according to the scoring vector sum of target place
The scoring vector in beginning place, finally determines the score value of target place.The score value of target place is to fully consider use
Family demand and starting place are to the fractional value determined in the case where the influence degree of target place, the higher theory of fractional value
The probability that bright target place meets user's actual need is higher.When carrying out the recommendation in place according to the score value, so that recommend
Place can be more in line with user demand.
Fig. 2 is a kind of structural schematic diagram of place scoring apparatus provided in an embodiment of the present invention, and described device includes obtaining
Unit 21, taxon 22, the first determination unit 23 and the second determination unit 24；
Acquiring unit 21, for obtaining the data information of target place；Wherein, data information includes what unmanned machine acquired
Data information and the historical data information collected from network；
Taxon 22 carries out classification processing to data information for utilizing data classification model, sorted to obtain
Characteristic information；
First determination unit 23, for according to received user demand information and the corresponding initial spy of each characteristic information
Score value is levied, determines the scoring vector of target place；
Second determination unit 24 originates the scoring vector in place for the scoring vector sum according to target place, determines
The score value of target place.
Optionally, the first determination unit includes computation subunit and obtains subelement；
Computation subunit, for calculating the corresponding weight of each characteristic information according to received user demand information
Value；
Subelement is obtained, for obtaining mesh according to weighted value and the corresponding initial characteristics score value of each characteristic information
Mark the scoring vector in place.
Optionally, computation subunit is specifically used for according to the following formula, handling received user demand information, with
Determine the corresponding weighted value f of each characteristic informationDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
Optionally, the second determination unit includes calculating son apart from computation subunit, relatedness computation subelement and score value
Unit；
It is calculated apart from computation subunit for the scoring vector in the scoring vector sum starting place according to target place
The vector distance of target place and starting place；
Relatedness computation subelement determines target for handling using following degree of correlation formula vector distance
The degree of correlation I in place and starting placeD(ik, jk),
Wherein, dD(ik, jk) indicates k-th of characteristic component of target place i and k-th of characteristic component of starting place j
Vector distance, dmaxIt indicates target place i and originates the vector maximum distance of place j, α indicates one of adjustment relationship weight
Parameter；
Score value computation subunit determines target for handling using following scoring more new formula the degree of correlation
Score value Tr (the D of place iik),
Wherein, Tr (Djk) indicate to originate the score value of place j.
The explanation of feature may refer to the related description of embodiment corresponding to Fig. 1 in embodiment corresponding to Fig. 2, here no longer
It repeats one by one.
The data information of target place is obtained it can be seen from above-mentioned technical proposal；Wherein, the data information can wrap
The historical data information for including the data information of unmanned machine acquisition and being collected from network；Using data classification model, to data
Information carries out classification processing, to obtain sorted characteristic information；It is each according to received user demand information and each characteristic information
Self-corresponding initial characteristics score value can determine the scoring vector of target place；It is risen according to the scoring vector sum of target place
The scoring vector in beginning place, finally determines the score value of target place.The score value of target place is to fully consider use
Family demand and starting place are to the fractional value determined in the case where the influence degree of target place, the higher theory of fractional value
The probability that bright target place meets user's actual need is higher.When carrying out the recommendation in place according to the score value, so that recommend
Place can be more in line with user demand.
Fig. 3 is a kind of hardware structural diagram of place scoring apparatus 30 provided in an embodiment of the present invention, and the place is commented
Separating device 30 includes:
Memory 31, for storing computer program；
Processor 32, for executing computer program to realize such as the step of above-mentioned place methods of marking.
The embodiment of the invention also provides a kind of computer readable storage medium, it is stored on computer readable storage medium
Computer program is realized when computer program is executed by processor such as the step of above-mentioned place methods of marking.
Be provided for the embodiments of the invention above a kind of place methods of marking, device and computer readable storage medium into
It has gone and has been discussed in detail.Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts in each embodiment may refer to each other.For disclosed in embodiment
For device, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method portion
It defends oneself bright.It should be pointed out that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, it can be with several improvements and modifications are made to the present invention, these improvement and modification also fall into the protection of the claims in the present invention
In range.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Claims (10)
1. a kind of place methods of marking characterized by comprising
Obtain the data information of target place；Wherein, the data information includes the data information of unmanned machine acquisition and from net
The historical data information collected in network；
Using data classification model, classification processing is carried out to the data information, to obtain sorted characteristic information；
According to received user demand information and the corresponding initial characteristics score value of each characteristic information, the mesh is determined
Mark the scoring vector in place；
According to the scoring vector in the scoring vector sum starting place of the target place, the scoring of the target place is determined
Value.
2. the method according to claim 1, wherein described according to received user demand information and each spy
Reference ceases corresponding initial characteristics score value, determines that the scoring vector of the target place includes:
According to received user demand information, each corresponding weighted value of the characteristic information is calculated；
According to the weighted value and the corresponding initial characteristics score value of each characteristic information, the target place is obtained
Score vector.
3. according to the method described in claim 2, calculating each it is characterized in that, described according to received user demand information
The corresponding weighted value of characteristic information includes:
According to the following formula, received user demand information is handled, to determine the corresponding power of each characteristic information
Weight values fDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
4. according to the method described in claim 3, it is characterized in that, described originate according to the scoring vector sum of the target place
The scoring vector in place determines that the score value of the target place includes:
The scoring vector in the scoring vector sum starting place according to the target place, calculates the target place and described
The vector distance in beginning place；
The vector distance is handled using following degree of correlation formula, determines the target place and the starting place
Degree of correlation ID(ik, jk),
Wherein, dD(ik, jk) indicates k-th of characteristic component of the target place i and k-th of feature point of the starting place j
The vector distance of amount, dmaxIndicate the vector maximum distance of the target place i and the starting place j, α indicates adjustment relationship
One parameter of weight；
The degree of correlation is handled using following scoring more new formula, determines the score value Tr of the target place i
(Dik),
Wherein, Tr (Djk) indicate the score value for originating place j.
5. a kind of place scoring apparatus, which is characterized in that really including acquiring unit, taxon, the first determination unit and second
Order member；
The acquiring unit, for obtaining the data information of target place；Wherein, the data information includes unmanned machine acquisition
Data information and the historical data information collected from network；
The taxon carries out classification processing to the data information, after obtaining classification for utilizing data classification model
Characteristic information；
First determination unit, for corresponding initial according to received user demand information and each characteristic information
Feature score value determines the scoring vector of the target place；
Second determination unit originates the scoring vector in place for the scoring vector sum according to the target place, determines
The score value of the target place out.
6. device according to claim 5, which is characterized in that first determination unit includes computation subunit and obtains
Subelement；
The computation subunit, for it is corresponding to calculate each characteristic information according to received user demand information
Weighted value；
It is described to obtain subelement, for according to the weighted value and each corresponding initial characteristics of the characteristic information point
Value, obtains the scoring vector of the target place.
7. device according to claim 6, which is characterized in that the computation subunit is specifically used for according to the following formula,
Received user demand information is handled, to determine the corresponding weighted value f of each characteristic informationDk,
Wherein, akIndicate that the score value of k-th of characteristic information in user demand information, M indicate the total number of characteristic information.
8. device according to claim 7, which is characterized in that second determination unit include apart from computation subunit,
Relatedness computation subelement and score value computation subunit；
It is described to be counted apart from computation subunit for the scoring vector in the scoring vector sum starting place according to the target place
Calculate the vector distance of the target place and the starting place；
The relatedness computation subelement is determined for being handled using following degree of correlation formula the vector distance
The degree of correlation I of the target place and the starting placeD(ik, jk),
Wherein, dD(ik, jk) indicates k-th of characteristic component of the target place i and k-th of feature point of the starting place j
The vector distance of amount, dmaxIndicate the vector maximum distance of the target place i and the starting place j, α indicates adjustment relationship
One parameter of weight；
The score value computation subunit is determined for being handled using following scoring more new formula the degree of correlation
Score value Tr (the D of the target place iik),
Wherein, Tr (Djk) indicate the score value for originating place j.
9. a kind of place scoring apparatus characterized by comprising
Memory, for storing computer program；
Processor, for executing the computer program to realize the place methods of marking as described in Claims 1-4 any one
The step of.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the step of the place methods of marking as described in any one of Claims 1-4 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763165.2A CN108985898B (en) | 2018-07-12 | 2018-07-12 | Site scoring method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763165.2A CN108985898B (en) | 2018-07-12 | 2018-07-12 | Site scoring method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108985898A true CN108985898A (en) | 2018-12-11 |
| CN108985898B CN108985898B (en) | 2022-02-15 |
Family
ID=64537794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810763165.2A Active CN108985898B (en) | 2018-07-12 | 2018-07-12 | Site scoring method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985898B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861139A (en) * | 2020-06-28 | 2020-10-30 | 深圳壹账通智能科技有限公司 | Merchant recommendation method and device and computer equipment |
| CN112785185A (en) * | 2021-02-02 | 2021-05-11 | 青岛港国际股份有限公司 | Automatic wharf air rail scheduling method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
| CN103530416A (en) * | 2013-10-28 | 2014-01-22 | 海南大学 | Project data forecasting grading library generating and project data pushing method and project data forecasting grading library generating and project data pushing system |
| CN103631813A (en) * | 2012-08-24 | 2014-03-12 | 富士通株式会社 | Device and method for site searching and electronic device |
| CN103868690A (en) * | 2014-02-28 | 2014-06-18 | 中国人民解放军63680部队 | Rolling bearing state automatic early warning method based on extraction and selection of multiple characteristics |
| CN105608121A (en) * | 2015-12-14 | 2016-05-25 | 东软集团股份有限公司 | Personalized recommendation method and apparatus |
| CN105808666A (en) * | 2016-02-29 | 2016-07-27 | 奇瑞汽车股份有限公司 | Information pushing method, apparatus and system |
| CN106354859A (en) * | 2016-09-06 | 2017-01-25 | 北京易游华成科技有限公司 | Scenic spot recommendation device, method and system |
| CN107122447A (en) * | 2017-04-25 | 2017-09-01 | 南京邮电大学 | The network searching system and control method of a kind of multi-data source fusion based on preference |
| CN107527303A (en) * | 2017-07-20 | 2017-12-29 | 中国农业大学 | A kind of rural tourism visualized recommendation method and system |
-
2018
- 2018-07-12 CN CN201810763165.2A patent/CN108985898B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
| CN103631813A (en) * | 2012-08-24 | 2014-03-12 | 富士通株式会社 | Device and method for site searching and electronic device |
| CN103530416A (en) * | 2013-10-28 | 2014-01-22 | 海南大学 | Project data forecasting grading library generating and project data pushing method and project data forecasting grading library generating and project data pushing system |
| CN103868690A (en) * | 2014-02-28 | 2014-06-18 | 中国人民解放军63680部队 | Rolling bearing state automatic early warning method based on extraction and selection of multiple characteristics |
| CN105608121A (en) * | 2015-12-14 | 2016-05-25 | 东软集团股份有限公司 | Personalized recommendation method and apparatus |
| CN105808666A (en) * | 2016-02-29 | 2016-07-27 | 奇瑞汽车股份有限公司 | Information pushing method, apparatus and system |
| CN106354859A (en) * | 2016-09-06 | 2017-01-25 | 北京易游华成科技有限公司 | Scenic spot recommendation device, method and system |
| CN107122447A (en) * | 2017-04-25 | 2017-09-01 | 南京邮电大学 | The network searching system and control method of a kind of multi-data source fusion based on preference |
| CN107527303A (en) * | 2017-07-20 | 2017-12-29 | 中国农业大学 | A kind of rural tourism visualized recommendation method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861139A (en) * | 2020-06-28 | 2020-10-30 | 深圳壹账通智能科技有限公司 | Merchant recommendation method and device and computer equipment |
| CN112785185A (en) * | 2021-02-02 | 2021-05-11 | 青岛港国际股份有限公司 | Automatic wharf air rail scheduling method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108985898B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104123398B (en) | A kind of information-pushing method and device | |
| CN106303955B (en) | For carrying out matched method and apparatus to hotspot and POI | |
| CN110726418A (en) | Method, device and equipment for determining interest point region and storage medium | |
| CN104182517B (en) | The method and device of data processing | |
| JP6937776B2 (en) | Methods and devices for identifying geographic location attribute information | |
| CN106776930B (en) | A kind of location recommendation method incorporating time and geographical location information | |
| CN106096047B (en) | User partition preference calculation method and system based on Information Entropy | |
| CN103826299B (en) | The indoor augmented reality implementation method perceived based on wireless signal | |
| CN110390045B (en) | Interest point recommendation method and device based on location service | |
| WO2013179071A1 (en) | Interest profile of a user of a mobile application | |
| WO2013071773A1 (en) | Method and server for searching for nearby user in social network | |
| CN105243098B (en) | The clustering method and device of facial image | |
| CN108984561A (en) | Site selecting method and equipment | |
| CN107688955A (en) | A kind of city commercial circle group variety division methods based on adaptive DBSCAN Density Clusterings | |
| CN108960562A (en) | A kind of regional influence appraisal procedure and device | |
| CN102572924A (en) | Quality evaluation method and system for mobile internet network | |
| WO2017008653A1 (en) | Poi service provision method, poi data processing method and device | |
| CN108985898A (en) | A kind of place methods of marking, device and computer readable storage medium | |
| CN109211259A (en) | Display methods, device, terminal and the storage medium of path | |
| CN106899644A (en) | Processing method of taking pictures and server | |
| CN111667095A (en) | Method for predicting economic state and establishing economic state prediction model and corresponding device | |
| CN104135718B (en) | The acquisition methods and device of a kind of location information | |
| CN110781256B (en) | Method and device for determining POI matched with Wi-Fi based on sending position data | |
| CN107133689B (en) | Position marking method | |
| CN106528559B (en) | Method and device for providing position information |
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 |