CN108038647A - A kind of source of goods of arterial highway logistics recommends method - Google Patents
A kind of source of goods of arterial highway logistics recommends method Download PDFInfo
- Publication number
- CN108038647A CN108038647A CN201711399758.7A CN201711399758A CN108038647A CN 108038647 A CN108038647 A CN 108038647A CN 201711399758 A CN201711399758 A CN 201711399758A CN 108038647 A CN108038647 A CN 108038647A
- Authority
- CN
- China
- Prior art keywords
- source
- goods
- driver
- mrow
- city
- 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.)
- Pending
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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Abstract
A kind of source of goods of arterial highway logistics disclosed by the invention recommends method, drivers ' behavior data and source of goods data are gathered by intelligent mobile terminal, associated databases are established on arterial highway physical distribution transaction system backstage, by carrying out extraction and analysis, the label stamped by corresponding computing engines (1) to the source of goods to driver's real time data feature on offline driver's historical behavior data characteristics, line and source of goods data characteristics；(2) judge preference degree of the driver to a source of goods, and the source of goods is ranked up；(3) source of goods is scored and is sorted；Final recommendation results are calculated using Weighting type mixing Generalization bounds, the present invention not only increases the probability that the source of goods is consulted or called, also avoid driver in order to consult a large amount of information of freight source and cause the substantial amounts of time to waste, driver is also improved to obtain the efficiency of the source of goods needed for oneself, add the probability of transaction of shipping, reduce zero phone feedback rates of arterial highway physical distribution transaction system at the same time, add the shopping experience of the owner of cargo.
Description
Technical field
The invention belongs to field of computer technology, is related to a kind of source of goods and recommends method, a kind of source of goods of arterial highway logistics
Recommendation method.
Background technology
With the rapid development of arterial highway logistics, the uneven presentation of matching of truck man and the source of goods is intensification to become
Gesture, such as the imbalance of the both sides of supply and demand (vehicle and cargo) of different zones different time, the preference of different circuit different automobile types
Matching is difficult, and the cold and hot difference of circuit is huge, and the pageview cun of fine or not cargo is in serious Matthew effect.At present, done in highway
In line field, method that this part solves is only to rely on the recommendation method of search or advertisement to solve.
Shown according to the data of arterial highway physical distribution transaction system, end the source of goods amount of daily intelligent mobile terminal displaying
Up to 600,000 or so, the source of goods issues the characteristics of time focusing is presented again in addition, so as to cause tight in source of goods issue peak period appearance
The overload of heavy cargo source information, so that substantial amounts of resource information can not be consulted or called by driver.Meanwhile driver
The waste that the source of goods needed for oneself will also result in the plenty of time is filtered out from the information of freight source of overload.Therefore, for each goods
For car driver, realize that the efficient matchings of the source of goods and high-quality recommendation are extremely urgent.
The content of the invention
To solve the above-mentioned problems, the source of goods the invention discloses a kind of arterial highway logistics recommends method, passes through the party
Law office machine can find the source of goods needed for oneself faster, increase the matching degree of source of goods both sides, while the owner of cargo can also be as early as possible
Enter delivery flow, saved the substantial amounts of time, improved efficiency and success rate that both sides conclude the transaction.
In order to achieve the above object, technical scheme is as follows：A kind of source of goods of arterial highway logistics recommends method,
Comprise the following steps：
S1, by intelligent mobile terminal gather drivers ' behavior data and source of goods data, and in arterial highway physical distribution trading system
Associated databases are established on system backstage, and it is real that the drivers ' behavior data include driver on offline driver's historical behavior data characteristics and line
When data characteristics, the city of setting out of source of goods data including the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, fortune
Defeated distance, transaction guaranty；
S2, extraction offline driver's historical behavior data characteristics, offline driver's historical behavior data characteristics include
The subscription route information of driver, click on and check information, call information and sequence information；
S3, extract driver expectation carrying source of goods city from the subscription route of the driver, terminate city；
S4, according to the click of the driver check information, calls information and sequence information, is carried from the database
Take the city of setting out of the corresponding source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, guarantee transaction, Man Yun
Precious feature is simultaneously stored into Redis memory databases；
Driver's real time data feature on S5, the extraction line, real time data feature includes the department gathered in real time on the line
Machine is called, browsed, clicking on, changing and subscribe to route behavior record information；
S6, the behavior record information called according to the driver gathered in real time, extract corresponding goods from database
The city of setting out in source, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, transaction guaranty, the precious feature of full fortune, and
The behavioural characteristic that driver's history is called in renewal Redis；
S7, the extraction source of goods data characteristics, the source of goods is calculated from the light exposure after issue, click by computing engines
Measure and the amount of calling, and it is tagged for the source of goods, and the label includes isHot, isFeedback, cargoRank；
S8, the behavioural characteristic called according to driver's history judge preference degree of the driver to a source of goods, and right
The source of goods is ranked up；
S9, according to the city of setting out of the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range,
The feature of guarantee transaction, the computation model to be scored by the source of goods, makes the source of goods scoring, and according to institute's appraisal result to the source of goods into
Row sequence；
S10, comprehensive source of goods label, driver score preference degree, the source of goods of a source of goods, export last recommendation results.
Preferably, the decision logic of isHot is described in step (7)：Assuming that current time is t1, the issuing time of the source of goods
For t0, and there are all source of goods time interval t0~t1Ordered set P={ the p of the exposure frequency of unit interval (minute) in section1,
p2,…pi,pi+1,…pn, pi≤pi+1AndIf in time interval t0~t1The source of goods has phone feedback in section, then
The source of goods is the popular source of goods, labeled as 1.If in time interval t0~t1The source of goods does not have phone feedback, and exposure frequency in section
For pk.If pk≥pi, then the source of goods is the popular source of goods, is otherwise 0 for unexpected winner indication of source labeled as 1；
The decision logic of the isFeedback is：If the source of goods was rung on line, isFeedback 1, such as
The source of goods was not rung on fruit line, then isFeedback is 0；
The decision logic of the cargoRank is：
A) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are high
Double standard deviation in average, then labeled as the high quality source of goods (0)；
B) source of goods within 30 days by auditing and being popular route, if same day phone feedback rates be 0, labeled as non-
The normal poor source of goods (1)；
C) source of goods is not limited within 30 days by examination ＆ verification, but popular route, if same day phone feedback rates are 0, is marked
It is denoted as the poor source of goods (2)；
D) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are 0,
Then it is labeled as the general source of goods (3).
Preferably, the behavioural characteristic that driver's history is called described in step (8) judges happiness of the driver to a source of goods
Good degree is to be based on naive Bayesian probabilistic model, and the naive Bayesian probabilistic model posterior probability formula is as follows：
Wherein P (Y | X) represent on the premise of source of goods feature vector, X occurs, the general of the label event Y that driver likes occur
Rate, is posterior probability.P (Y) represents that a source of goods sample is the probability that driver likes, and is known as prior probability, P (Xi| Y) it is to take charge of
The source of goods feature X of classification Y is observed in the source of goods source of goods sample that machine is likediProbability, P (X) be source of goods sample in observe X's
Probability.
Preferably, the computation model of the scoring of the source of goods described in step (9), includes the following steps：
A) city of setting out of the source of goods is inputted first, terminates city, vehicle commander, vehicle, weight, source of goods type, transportation range, friendship
Easily any feature in guarantee；
B) judged subsequently into Layer1 layers, the behavior if this feature value occurred in the historical behavior of driver
Scoring add 1；
C) then multiplied again with the weight wi of each behavior and scored in the behavior；
D) finally each behavior scoring is added up at Layer2 layers, obtains the appraisal result of the current source of goods.
Preferably, by scoring of the driver in step (8) to the source of goods in the preference degree and step (9) of source of goods using weighting
Formula mixes Generalization bounds, calculates final recommendation results, and weighted blend processing is the result by calculating multiple recommended engines
Fraction weighted sum, represents as follows by formula：
Wherein n=2, reckTo recommend k-th of recommended engine recommendation results, βkCorresponded to for k-th of recommended engine recommendation results
Weights, and
Compared with prior art, the beneficial effects of the invention are as follows：
A kind of source of goods of arterial highway logistics of the present invention recommends method, and driver's row is gathered by intelligent mobile terminal
For data and source of goods data, associated databases are established on arterial highway physical distribution transaction system backstage, by offline driver's history
Driver's real time data feature and source of goods data characteristics carry out extraction and analysis in behavioral data feature, line, by corresponding computing engines
(1) source of goods is stamped isHot (whether overheating), isFeedback (whether the source of goods has phone feedback), cargoRank (source of goods
Credit rating) label；(2) judge preference degree of the driver to a source of goods, and the source of goods is ranked up；(3) source of goods is carried out
Scoring；Calculate final recommendation results using Weighting type mixing Generalization bounds, the present invention not only increase the source of goods consulted or
Probability that person calls, the matching degree for adding shipping both sides, also avoid driver in order to consult a large amount of information of freight source and cause
The substantial amounts of time wastes, and also improves driver and obtains the efficiency of the source of goods needed for oneself, adds the probability of transaction of shipping, reduces at the same time
Zero phone feedback rates of arterial highway physical distribution transaction system, add the shopping experience of the owner of cargo.
Brief description of the drawings
Fig. 1 is the flow diagram of the present invention.
Fig. 2 is source of goods scoring computation model figure in the present invention.
Fig. 3 is Weighting type mixing Generalization bounds illustraton of model in the present invention.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Substantially
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment, belongs to the scope of protection of the invention.
As shown in Figs. 1-3, the source of goods the invention discloses a kind of arterial highway logistics recommends method, comprises the following steps：
S1, by intelligent mobile terminal gather drivers ' behavior data and source of goods data, and in arterial highway physical distribution trading system
Associated databases are established on system backstage, and it is real that the drivers ' behavior data include driver on offline driver's historical behavior data characteristics and line
When data characteristics, the city of setting out of source of goods data including the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, fortune
Defeated distance, transaction guaranty；
S2, extraction offline driver's historical behavior data characteristics, offline driver's historical behavior data characteristics include
The subscription route information of driver, click on and check information, call information and sequence information；
S3, extract driver expectation carrying source of goods city from the subscription route of the driver, terminate city；
S4, according to the click of the driver check information, calls information and sequence information, is carried from the database
Take the city of setting out of the corresponding source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, guarantee transaction, Man Yun
Precious feature is simultaneously stored into Redis memory databases；
Driver's real time data feature on S5, the extraction line, real time data feature includes the department gathered in real time on the line
Machine is called, browsed, clicking on, changing and subscribe to route behavior record information；
S6, the behavior record information called according to the driver gathered in real time, extract corresponding goods from database
The city of setting out in source, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, transaction guaranty, the precious feature of full fortune, and
The behavioural characteristic that driver's history is called in renewal Redis；
S7, the extraction source of goods data characteristics, the source of goods is calculated from the light exposure after issue, click by computing engines
Measure and the amount of calling, and tagged for the source of goods, the label includes isHot (whether overheating), (source of goods is isFeedback
It is no to have phone feedback), cargoRank (credit rating of the source of goods)；
S8, the behavioural characteristic called according to driver's history judge preference degree of the driver to a source of goods, and right
The source of goods is ranked up；
S9, according to the city of setting out of the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range,
The feature of guarantee transaction, the computation model to be scored by the source of goods, makes the source of goods scoring, and according to institute's appraisal result to the source of goods into
Row sequence
S10, comprehensive source of goods label, driver score preference degree, the source of goods of a source of goods, export last recommendation results.
As a further improvement on the present invention, the decision logic of isHot is described in step (7)：Assuming that current time is
t1, the issuing time of the source of goods is t0, and there are all source of goods time interval t0~t1The exposure frequency of unit interval (minute) in section
Ordered set P={ p1,p2,…pi,pi+1,…pn, pi≤pi+1AndIf in time interval t0~t1The goods in section
There is phone feedback in source, then the source of goods is the popular source of goods, labeled as 1.If in time interval t0~t1The source of goods does not have phone in section
Feedback, and exposure frequency is pk.If pk≥pi, then the source of goods is the popular source of goods, is otherwise 0 for unexpected winner indication of source labeled as 1；
IsHot labels avoid the popular source of goods while are called by multiple drivers primarily to prevent the recommendation to overheating the source of goods
Situation occurs.
The decision logic of the isFeedback is：If the source of goods was rung on line, isFeedback 1, such as
The source of goods was not rung on fruit line, then isFeedback is 0；
The decision logic of the cargoRank is (as shown in table 1)：
A) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are high
Double standard deviation in average, then labeled as the high quality source of goods (0)；
B) source of goods within 30 days by auditing and being popular route, if same day phone feedback rates be 0, labeled as non-
The normal poor source of goods (1)；
C) source of goods is not limited within 30 days by examination ＆ verification, but popular route, if same day phone feedback rates are 0, is marked
It is denoted as the poor source of goods (2)；
D) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are 0,
Then it is labeled as the general source of goods (3)；
The decision logic relation of table 1cargoRank
As a further improvement on the present invention, the behavioural characteristic judgement department that driver's history described in step (8) is called
Machine is to be based on naive Bayesian probabilistic model to the preference degree of a source of goods, and history calls the source of goods feature such as table 2 of behavior
It is shown：
| Source of goods ID | startCity | endCity | truckLen | truckType | weight | distanceType | isAssure | label |
| 1 | 310110 | 110130 | 12 | 1 | 30 | 3 | 1 | 1 |
| 2 | 310106 | 110102 | 12 | 1 | 20 | 3 | 0 | 1 |
| 3 | 310105 | 110120 | 17 | 1 | 25 | 3 | 1 | 1 |
| 4 | 320203 | 410602 | 12 | 1 | 15 | 2 | 1 | 1 |
| 5 | 320104 | 110130 | 5 | 1 | 20 | 3 | 0 | 1 |
| 6 | 310106 | 110130 | 12 | 1 | 20 | 3 | 1 |
2 history of table calls the source of goods feature of behavior
The naive Bayesian probabilistic model posterior probability formula is as follows：
Wherein P (Y | X) represent on the premise of source of goods feature vector, X occurs, the general of the label event Y that driver likes occur
Rate, is posterior probability.P (Y) represents that a source of goods sample is the probability that driver likes, and is known as prior probability, P (Xi| Y) it is to take charge of
The source of goods feature X of classification Y is observed in the source of goods source of goods sample that machine is likediProbability, P (X) be source of goods sample in observe X's
Probability.
The list conditional probability of the feature vector, X of the source of goods 6 in table 2 can be calculated according to above-mentioned formula (1), it is final to determine
Whether driver " likes " source of goods, is " liking " if final probability is more than threshold value 0.7, " is not liked less than threshold value
Vigorously ".Finally to the source of goods of " liking " according to probability from greatly to small order sort.
As a further improvement on the present invention, the computation model of the scoring of the source of goods described in step (9), includes the following steps：
A) city of setting out of the source of goods is inputted first, terminates city, vehicle commander, vehicle, weight, source of goods type, transportation range, friendship
Easily any feature in guarantee；
B) judged subsequently into Layer1 layers, the behavior if this feature value occurred in the historical behavior of driver
Scoring add 1；
C) then multiplied again with the weight wi of each behavior and scored in the behavior；
D) finally each behavior scoring is added up at Layer2 layers, obtains the appraisal result of the current source of goods；
This computation model can carry out the source of goods according to appraisal result arrangement from big to small.
As a further improvement on the present invention, by driver in step (8) to goods in the preference degree and step (9) of source of goods
The scoring in source uses Weighting type mixing Generalization bounds, calculates final recommendation results, and weighted blend processing is more by calculating
The result fraction weighted sum of a recommended engine, represents as follows by formula：
Wherein n=2, reckTo recommend k-th of recommended engine recommendation results, βkCorresponded to for k-th of recommended engine recommendation results
Weights, and
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of changes, modification, replace
And modification, the scope of the present invention have the following claims and their equivalents restriction.
Claims (5)
1. a kind of source of goods of arterial highway logistics recommends method, it is characterised in that：Comprise the following steps：
S1, by intelligent mobile terminal gather drivers ' behavior data and source of goods data, and after arterial highway physical distribution transaction system
Platform establishes associated databases, and the drivers ' behavior data include driver on offline driver's historical behavior data characteristics and line and count in real time
According to feature, the city of setting out of source of goods data including the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transport away from
From, transaction guaranty；
S2, extraction offline driver's historical behavior data characteristics, offline driver's historical behavior data characteristics include driver
Subscription route information, click on check information, call information and sequence information；
S3, extract driver expectation carrying source of goods city from the subscription route of the driver, terminate city；
S4, according to the click of the driver check information, calls information and sequence information, the extraction pair from the database
The city of setting out of the source of goods is answered, terminates city, vehicle commander, vehicle, weight, source of goods type, transportation range, guarantee transaction, completely transport Bao Te
Levy and store in Redis memory databases；
S5, extract driver's real time data feature on the line, and real time data feature is dialled including the driver gathered in real time on the line
Make a phone call, browse, clicking on, changing and subscribe to route behavior record information；
S6, the behavior record information called according to the driver gathered in real time, extract the corresponding source of goods from database
Set out city, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, transaction guaranty, the precious feature of full fortune, and update
The behavioural characteristic that driver's history is called in Redis；
S7, the extraction source of goods data characteristics, by computing engines come calculate light exposure of the source of goods from after issuing, click volume and
The amount of calling, and it is tagged for the source of goods, and the label includes isHot, isFeedback, cargoRank；
S8, the behavioural characteristic called according to driver's history judge preference degree of the driver to a source of goods, and to the source of goods
It is ranked up；
S9, according to the city of setting out of the source of goods, terminate city, vehicle commander, vehicle, weight, source of goods type, transportation range, guarantee
The feature of transaction, the computation model to be scored by the source of goods, makes the source of goods scoring, and the source of goods is arranged according to institute's appraisal result
Sequence；
S10, comprehensive source of goods label, driver score preference degree, the source of goods of a source of goods, export last recommendation results.
2. a kind of source of goods of arterial highway logistics according to claim 1 recommends method, it is characterised in that：
The decision logic of isHot is described in step (7)：Assuming that current time is t1, the issuing time of the source of goods is t0, and exist
All source of goods time interval t0~t1Ordered set P={ the p of the exposure frequency of unit interval (minute) in section1,p2,…pi,…
pi+1,…pn}pi≤pi+1AndFruit is in time interval t0~t1The source of goods has phone feedback in section, then the source of goods is hot topic
The source of goods, labeled as 1.If in time interval t0~t1The source of goods does not have phone feedback in section, and exposure frequency is pk.If pk≥
pi, then the source of goods is the popular source of goods, is otherwise 0 for unexpected winner indication of source labeled as 1；
The decision logic of the isFeedback is：If the source of goods was rung on line, isFeedback 1, if line
The upper source of goods was not rung, then isFeedback is 0；
The decision logic of the cargoRank is：
A) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are higher than equal
Value doubles standard deviation, then labeled as the high quality source of goods (0)；
B) source of goods within 30 days by auditing and being popular route, if same day phone feedback rates be 0, labeled as excessively poor
The source of goods (1)；
C) source of goods is not limited within 30 days by examination ＆ verification, but popular route, if same day phone feedback rates are 0, is labeled as
The poor source of goods (2)；
D) source of goods is not limited to by auditing and being not limited to popular route within 30 days, if same day phone feedback rates are 0, is marked
It is denoted as the general source of goods (3).
3. a kind of source of goods of arterial highway logistics according to claim 1 recommends method, it is characterised in that：In step (8)
The behavioural characteristic that driver's history is called judges that driver is to be based on naive Bayesian probability to the preference degree of a source of goods
Model, the naive Bayesian probabilistic model posterior probability formula are as follows：
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>Y</mi>
<mo>|</mo>
<mi>X</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>d</mi>
</msubsup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>Y</mi>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>Y</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>X</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
Wherein P (Y | X) represent on the premise of source of goods feature vector, X occurs, the probability for the label event Y that driver likes occur,
For posterior probability.P (Y) represents that a source of goods sample is the probability that driver likes, and is known as prior probability, P (Xi| Y) it is in driver
The source of goods feature X of classification Y is observed in the source of goods source of goods sample likediProbability, P (X) be source of goods sample in observe that X's is general
Rate.
4. a kind of source of goods of arterial highway logistics according to claim 1 recommends method, it is characterised in that：In step (9)
The computation model of the source of goods scoring, includes the following steps：
A) city of setting out of the source of goods is inputted first, terminates city, vehicle commander, vehicle, weight, source of goods type, transportation range, transaction load
Any feature in guarantor；
B) judged subsequently into Layer1 layers, the behavior commented if this feature value occurs in the historical behavior of driver
Divide and add 1；
C) then multiplied again with the weight wi of each behavior and scored in the behavior；
D) finally each behavior scoring is added up at Layer2 layers, obtains the appraisal result of the current source of goods.
5. a kind of source of goods of arterial highway logistics according to claim 1 recommends method, it is characterised in that：By step (8)
Scoring of the middle driver to the source of goods in the preference degree and step (9) of source of goods uses Weighting type mixing Generalization bounds, calculates most
Whole recommendation results, weighted blend processing are the result fraction weighted sums by calculating multiple recommended engines, pass through formula table
Show as follows：
<mrow>
<msub>
<mi>rec</mi>
<mrow>
<mi>w</mi>
<mi>e</mi>
<mi>i</mi>
<mi>g</mi>
<mi>h</mi>
<mi>t</mi>
<mi>e</mi>
<mi>d</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
<msub>
<mi>&beta;</mi>
<mi>k</mi>
</msub>
<mo>&times;</mo>
<msub>
<mi>rec</mi>
<mi>k</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein n=2, reckTo recommend k-th of recommended engine recommendation results, βkFor the corresponding power of k-th of recommended engine recommendation results
Value, and
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711399758.7A CN108038647A (en) | 2017-12-22 | 2017-12-22 | A kind of source of goods of arterial highway logistics recommends method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711399758.7A CN108038647A (en) | 2017-12-22 | 2017-12-22 | A kind of source of goods of arterial highway logistics recommends method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108038647A true CN108038647A (en) | 2018-05-15 |
Family
ID=62100663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711399758.7A Pending CN108038647A (en) | 2017-12-22 | 2017-12-22 | A kind of source of goods of arterial highway logistics recommends method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038647A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920689A (en) * | 2018-07-12 | 2018-11-30 | 江苏满运软件科技有限公司 | Source of goods recommended method and system |
| CN109117989A (en) * | 2018-07-26 | 2019-01-01 | 北京云鸟科技有限公司 | Prediction technique and device when a kind of task matches |
| CN109242044A (en) * | 2018-09-30 | 2019-01-18 | 江苏满运软件科技有限公司 | Training method, device, storage medium and the electronic equipment of vehicle and goods matching model |
| CN109447334A (en) * | 2018-10-19 | 2019-03-08 | 江苏满运软件科技有限公司 | The Method of Data with Adding Windows of information of freight source, device, electronic equipment, storage medium |
| CN109658033A (en) * | 2018-12-26 | 2019-04-19 | 江苏满运软件科技有限公司 | Source of goods route similarity calculating method, system, equipment and storage medium |
| CN109886620A (en) * | 2019-01-24 | 2019-06-14 | 好生活农产品集团有限公司 | Logistics transportation dispatching method and platform |
| CN110119928A (en) * | 2019-05-07 | 2019-08-13 | 宏图物流股份有限公司 | A kind of vehicle match recommended method based on driver's feature |
| CN110310064A (en) * | 2019-06-29 | 2019-10-08 | 江苏满运软件科技有限公司 | A kind of control method, device, storage medium and the electronic equipment of source of goods flow |
| CN110400060A (en) * | 2019-07-08 | 2019-11-01 | 拉货宝网络科技有限责任公司 | A kind of Highway Logistics source of goods recommended method based on vehicle Geographic mapping |
| CN110598989A (en) * | 2019-08-14 | 2019-12-20 | 江苏满运软件科技有限公司 | Goods source quality evaluation method, device, equipment and storage medium |
| CN111126909A (en) * | 2019-12-20 | 2020-05-08 | 贵阳货车帮科技有限公司 | Data processing method, device and equipment for goods source route and storage medium |
| CN111209473A (en) * | 2019-12-26 | 2020-05-29 | 武汉物易云通网络科技有限公司 | Vehicle and goods matching method and system based on big data |
| CN111222822A (en) * | 2020-01-07 | 2020-06-02 | 贵阳货车帮科技有限公司 | Goods source pushing method and device, electronic equipment and readable storage medium |
| CN111242535A (en) * | 2020-01-07 | 2020-06-05 | 贵阳货车帮科技有限公司 | Transportation route pushing method and device, electronic equipment and readable storage medium |
| CN111353732A (en) * | 2018-12-21 | 2020-06-30 | 北京中交兴路信息科技有限公司 | Vehicle transportation mode identification method, device, equipment and storage medium |
| CN111369186A (en) * | 2020-02-27 | 2020-07-03 | 成都运力科技有限公司 | Logistics pushing method and device, server and readable storage medium |
| CN111444436A (en) * | 2020-05-08 | 2020-07-24 | 惠龙易通国际物流股份有限公司 | Goods source recommendation method and device |
| CN112561412A (en) * | 2019-09-10 | 2021-03-26 | 顺丰科技有限公司 | Method and device for determining target object identifier, server and storage medium |
| CN112668969A (en) * | 2020-12-25 | 2021-04-16 | 江苏满运物流信息有限公司 | User tag processing method, system, electronic device and storage medium |
| CN116433138A (en) * | 2023-06-13 | 2023-07-14 | 长沙争渡网络科技有限公司 | Logistics platform information pushing method and system based on genetic algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930580A (en) * | 2010-08-19 | 2010-12-29 | 北京中交兴路信息科技有限公司 | Method and system for matching freight transaction |
| CN103793419A (en) * | 2012-10-31 | 2014-05-14 | 深圳市世纪光速信息技术有限公司 | Information push method and device |
| CN104866997A (en) * | 2015-06-10 | 2015-08-26 | 南京大学 | Intelligent pairing method applied to online stowage of vehicles and goods |
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
| CN106651122A (en) * | 2016-11-07 | 2017-05-10 | 南京大学 | Freight source information screening and pushing method |
-
2017
- 2017-12-22 CN CN201711399758.7A patent/CN108038647A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930580A (en) * | 2010-08-19 | 2010-12-29 | 北京中交兴路信息科技有限公司 | Method and system for matching freight transaction |
| CN103793419A (en) * | 2012-10-31 | 2014-05-14 | 深圳市世纪光速信息技术有限公司 | Information push method and device |
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| CN104866997A (en) * | 2015-06-10 | 2015-08-26 | 南京大学 | Intelligent pairing method applied to online stowage of vehicles and goods |
| CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
| CN106651122A (en) * | 2016-11-07 | 2017-05-10 | 南京大学 | Freight source information screening and pushing method |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920689A (en) * | 2018-07-12 | 2018-11-30 | 江苏满运软件科技有限公司 | Source of goods recommended method and system |
| CN109117989A (en) * | 2018-07-26 | 2019-01-01 | 北京云鸟科技有限公司 | Prediction technique and device when a kind of task matches |
| CN109117989B (en) * | 2018-07-26 | 2021-06-11 | 北京云鸟科技有限公司 | Prediction method and device during task matching |
| CN109242044A (en) * | 2018-09-30 | 2019-01-18 | 江苏满运软件科技有限公司 | Training method, device, storage medium and the electronic equipment of vehicle and goods matching model |
| CN109447334A (en) * | 2018-10-19 | 2019-03-08 | 江苏满运软件科技有限公司 | The Method of Data with Adding Windows of information of freight source, device, electronic equipment, storage medium |
| CN109447334B (en) * | 2018-10-19 | 2021-07-16 | 江苏满运物流信息有限公司 | Data dimension reduction method and device for goods source information, electronic equipment and storage medium |
| CN111353732A (en) * | 2018-12-21 | 2020-06-30 | 北京中交兴路信息科技有限公司 | Vehicle transportation mode identification method, device, equipment and storage medium |
| CN109658033A (en) * | 2018-12-26 | 2019-04-19 | 江苏满运软件科技有限公司 | Source of goods route similarity calculating method, system, equipment and storage medium |
| CN109658033B (en) * | 2018-12-26 | 2021-03-16 | 江苏满运物流信息有限公司 | Method, system, device and storage medium for calculating similarity of goods source route |
| CN109886620A (en) * | 2019-01-24 | 2019-06-14 | 好生活农产品集团有限公司 | Logistics transportation dispatching method and platform |
| CN110119928A (en) * | 2019-05-07 | 2019-08-13 | 宏图物流股份有限公司 | A kind of vehicle match recommended method based on driver's feature |
| CN110119928B (en) * | 2019-05-07 | 2021-01-01 | 宏图物流股份有限公司 | Vehicle matching recommendation method based on driver characteristics |
| CN110310064B (en) * | 2019-06-29 | 2022-10-04 | 江苏满运软件科技有限公司 | Control method and device for goods source flow, storage medium and electronic equipment |
| CN110310064A (en) * | 2019-06-29 | 2019-10-08 | 江苏满运软件科技有限公司 | A kind of control method, device, storage medium and the electronic equipment of source of goods flow |
| CN110400060A (en) * | 2019-07-08 | 2019-11-01 | 拉货宝网络科技有限责任公司 | A kind of Highway Logistics source of goods recommended method based on vehicle Geographic mapping |
| CN110598989A (en) * | 2019-08-14 | 2019-12-20 | 江苏满运软件科技有限公司 | Goods source quality evaluation method, device, equipment and storage medium |
| CN110598989B (en) * | 2019-08-14 | 2022-09-23 | 江苏满运软件科技有限公司 | Goods source quality evaluation method, device, equipment and storage medium |
| CN112561412B (en) * | 2019-09-10 | 2022-07-08 | 顺丰科技有限公司 | Method, device, server and storage medium for determining target object identifier |
| CN112561412A (en) * | 2019-09-10 | 2021-03-26 | 顺丰科技有限公司 | Method and device for determining target object identifier, server and storage medium |
| CN111126909A (en) * | 2019-12-20 | 2020-05-08 | 贵阳货车帮科技有限公司 | Data processing method, device and equipment for goods source route and storage medium |
| CN111126909B (en) * | 2019-12-20 | 2023-08-08 | 贵阳货车帮科技有限公司 | Data processing method, device, equipment and storage medium for goods source route |
| CN111209473B (en) * | 2019-12-26 | 2021-05-07 | 武汉物易云通网络科技有限公司 | Vehicle and goods matching method and system based on big data |
| CN111209473A (en) * | 2019-12-26 | 2020-05-29 | 武汉物易云通网络科技有限公司 | Vehicle and goods matching method and system based on big data |
| CN111222822B (en) * | 2020-01-07 | 2023-04-07 | 贵阳货车帮科技有限公司 | Goods source pushing method and device, electronic equipment and readable storage medium |
| CN111242535A (en) * | 2020-01-07 | 2020-06-05 | 贵阳货车帮科技有限公司 | Transportation route pushing method and device, electronic equipment and readable storage medium |
| CN111222822A (en) * | 2020-01-07 | 2020-06-02 | 贵阳货车帮科技有限公司 | Goods source pushing method and device, electronic equipment and readable storage medium |
| CN111242535B (en) * | 2020-01-07 | 2023-04-07 | 贵阳货车帮科技有限公司 | Transportation route pushing method and device, electronic equipment and readable storage medium |
| CN111369186A (en) * | 2020-02-27 | 2020-07-03 | 成都运力科技有限公司 | Logistics pushing method and device, server and readable storage medium |
| CN111369186B (en) * | 2020-02-27 | 2023-05-30 | 成都运力科技有限公司 | Logistics pushing method, device, server and readable storage medium |
| CN111444436A (en) * | 2020-05-08 | 2020-07-24 | 惠龙易通国际物流股份有限公司 | Goods source recommendation method and device |
| CN111444436B (en) * | 2020-05-08 | 2024-03-22 | 惠龙易通国际物流股份有限公司 | Goods source recommendation method and device |
| CN112668969B (en) * | 2020-12-25 | 2022-07-08 | 江苏满运物流信息有限公司 | User tag processing method, system, electronic device and storage medium |
| CN112668969A (en) * | 2020-12-25 | 2021-04-16 | 江苏满运物流信息有限公司 | User tag processing method, system, electronic device and storage medium |
| CN116433138A (en) * | 2023-06-13 | 2023-07-14 | 长沙争渡网络科技有限公司 | Logistics platform information pushing method and system based on genetic algorithm |
| CN116433138B (en) * | 2023-06-13 | 2023-09-22 | 长沙争渡网络科技有限公司 | Logistics platform information pushing method and system based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038647A (en) | A kind of source of goods of arterial highway logistics recommends method | |
| Dat et al. | A new integrated fuzzy QFD approach for market segments evaluation and selection | |
| Millar | The Little Deal: Brezhnev's contribution to acquisitive socialism | |
| CN103188626B (en) | Mobile phone advertisement distribution system, method and device, data maintaining method and device | |
| CN108076237B (en) | Telephone customer service data processing method and device | |
| KR102011028B1 (en) | Method for providing shopping mall service compensating margin to seller and customer | |
| Vahdani et al. | Selecting suppliers using a new fuzzy multiple criteria decision model: the fuzzy balancing and ranking method | |
| CN106570718A (en) | Information releasing method and releasing system | |
| CN105608617A (en) | Linked display method and system of detailed commodity page | |
| US20160335726A1 (en) | Quote exchange system and method for offering comparative rates for an insurance product | |
| Kahraman et al. | Selection Among GSM Operators Using Pythagorean Fuzzy WASPAS Method. | |
| Louviere | Modeling single individuals: the journey from psych lab to the app store | |
| Liao et al. | Multi-behavior RFM model based on improved SOM neural network algorithm for customer segmentation | |
| CN105281959A (en) | Mobile communication user loss prediction method based on hidden Markov model | |
| CN107688901B (en) | Data adjusting method and device | |
| Damoense et al. | An analysis of the impact of the first phase of South Africa's motor industry development programme (midp), 1995–2000 | |
| Inoue et al. | Behavior analysis on mobile-carrier choice considering Mobile Virtual Network Operators | |
| Mohammed et al. | Customer Satisfaction towards Telecommunication mobile services: A case study in Asiacell Telecommunications in Sulaymaniyah city | |
| Fernández-de-Sevilla | Growth amid a storm: Renault in Spain during the stagflation crisis, 1974–1985 | |
| CN106682936A (en) | Multi-service data processing method, apparatus and electronic equipment thereof | |
| Hwang et al. | Tariff and quota equivalence in vertically related markets | |
| Pham et al. | A recommendation system for offers in telecommunications | |
| Wang et al. | Multi-objective Dynamic Auction Mechanism for Online Advertising | |
| Ge et al. | Bank Loan Strategy Based on Evaluation and Decision Model | |
| Panda et al. | Adoption of supply chain management strategies as a response to bull whip effect: From the perspective of indian retailers |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180515 |
|
| WD01 | Invention patent application deemed withdrawn after publication |