CN110188908A - The prediction technique and device of user's transmitting-receiving article mode - Google Patents
The prediction technique and device of user's transmitting-receiving article mode Download PDFInfo
- Publication number
- CN110188908A CN110188908A CN201810153846.7A CN201810153846A CN110188908A CN 110188908 A CN110188908 A CN 110188908A CN 201810153846 A CN201810153846 A CN 201810153846A CN 110188908 A CN110188908 A CN 110188908A
- Authority
- CN
- China
- Prior art keywords
- order
- article
- user
- mode
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 7
- 235000013399 edible fruits Nutrition 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 239000000047 product Substances 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000005291 magnetic effect Effects 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses prediction techniques and device that a kind of user receives and dispatches article mode, are related to field of computer technology.One specific embodiment of this method includes: the corresponding customer attribute information of subscriber identity data obtained in order information, the order information and the customer attribute information are inputted into the first prediction model pre-established, obtain the first prediction result that user receives and dispatches article mode in order；The characteristic information is inputted the second prediction model for pre-establishing by the characteristic information for determining any article for including in order, obtains the second prediction result that based on this kind of article, user receives and dispatches article mode in order；In conjunction with the first prediction result and the second prediction result, the final prediction result that user receives and dispatches article mode in order is obtained.The embodiment can receive and dispatch the mode of article according to order information Accurate Prediction user, to promote user experience.
Description
Technical field
The present invention relates to prediction techniques and dress that field of computer technology more particularly to a kind of user receive and dispatch article mode
It sets.
Background technique
With the fast development of computer technology and logistlcs technology, user can encounter more and more by receiving article
Order (hereinafter referred to as reception order) extracts article or the order by sending article (hereinafter referred to as transmission order) is passed
Send the scene of article.In order to meet user demand, service side is arranged a large amount of self-service facilities and is provided in user, and user can receive
When valuables, breakables, the article stored in advance is voluntarily extracted from self-service facilities in a manner of self-service；Or sending above-mentioned object
When product, article is voluntarily carried to self-service facilities in a manner of self-service and then completes to deliver, to avoid fast by occupation in usual manner
The personnel of passing, which visit, receives and dispatches the risk of article generation, also contributes to Logistics Operation efficiency.
In order to promote user experience, service side needs before user submits order, the information prediction filled according to user its
Transmitting-receiving article mode is transmitting-receiving mode or the self-service mode of visiting, and prediction result is pushed to user.In the prior art, above-mentioned
Prediction realizes typically merely by the history access times of self-service facilities of the analysis user in order around address, precision compared with
It is low, easily influence user experience.
Summary of the invention
In view of this, the embodiment of the present invention provides the prediction technique and device of a kind of user's transmitting-receiving article mode, Neng Gougen
The mode that article is received and dispatched according to order information Accurate Prediction user, to promote user experience.
To achieve the above object, according to an aspect of the invention, there is provided a kind of user receives and dispatches the prediction of article mode
Method.
The prediction technique that the user of the embodiment of the present invention receives and dispatches article mode includes: the user identifier obtained in order information
The corresponding customer attribute information of data, the first prediction that the order information and customer attribute information input are pre-established
Model obtains the first prediction result that user receives and dispatches article mode in order；Determine the spy for any article for including in order
The characteristic information is inputted the second prediction model for pre-establishing by reference breath, is obtained based on this kind of article, user's transmitting-receiving and is ordered
Second prediction result of article mode in list；And it in conjunction with the first prediction result and the second prediction result, obtains user's transmitting-receiving and orders
The final prediction result of article mode in list.
Optionally, it includes: visit transmitting-receiving mode and self-service mode that user, which receives and dispatches the mode of article in order,.
Optionally, it is certainly that the first prediction result and the second prediction result, which include: the mode of article in user's transmitting-receiving order,
Help the probability value of mode.
Optionally, the method further includes: determine the corresponding self-service facilities distribution of address date in order information
The self-service facilities distributed intelligence is inputted the first prediction model by information；Wherein, the self-service facilities distributed intelligence includes following
It is at least one: self-service facilities quantity in the preset range centered on address in order, within the scope of this each self-service facilities with
The distance of address in order.
Optionally, the method further includes: obtain with order information in subscriber identity data and address date pair
The user's history answered is received and sent messages, and the user's history is received and sent messages and inputs the first prediction model；Wherein, the user's history
Receive and send messages include: the self-service facilities that user uses in preset range centered on address in order number.
Optionally, first prediction result of combination and the second prediction result obtain user and receive and dispatch article mode in order
Final prediction result include: in the probability value in the first prediction result to be greater than preset threshold and based on each object in order
When probability value in second prediction result of product is all larger than preset threshold, final prediction result is self-service mode；Otherwise, final pre-
Surveying result is transmitting-receiving mode of visiting.
Optionally, the preset threshold is 0.5.
Optionally, the order information further comprises following at least one: order value data, freight charges data, gross weight
Measure data, overall volume data, breakable object flag data；The customer attribute information comprises at least one of the following: gender data, body
Part data, historical interaction data；The characteristic information comprises at least one of the following: the classification logotype data of article, Individual Items
Weight data, the price datas of Individual Items, Individual Items volume data.
Optionally, order specifically: receive order or send order；And when order is to receive order, user is to connect
Receipts person, the address in order are recipient address；When order is to send order, user is sender, and the address in order is
Sender address.
Optionally, the first prediction model and the second prediction model are deep neural network DNN model.
To achieve the above object, according to another aspect of the invention, a kind of prediction of user's transmitting-receiving article mode is provided
Device.
The user of the embodiment of the present invention receives and dispatches the prediction meanss of article mode can include: the first preparatory unit can be used for obtaining
The corresponding customer attribute information of the subscriber identity data in order information is taken, by the order information and the customer attribute information
The first prediction model pre-established is inputted, the first prediction result that user receives and dispatches article mode in order is obtained；Second prepares
Unit can be used for determining the characteristic information for any article for including in order, and characteristic information input is pre-established
Second prediction model obtains the second prediction result that based on this kind of article, user receives and dispatches article mode in order；And in advance
Unit is surveyed, can be used for combining the first prediction result and the second prediction result, article mode is final in acquisition user's transmitting-receiving order
Prediction result.
To achieve the above object, according to another aspect of the invention, a kind of electronic equipment is provided.
A kind of electronic equipment of the invention includes: one or more processors；Storage device, for storing one or more
Program, when one or more of programs are executed by one or more of processors, so that one or more of processors
Realize that user provided by the present invention receives and dispatches the prediction technique of article mode.
To achieve the above object, in accordance with a further aspect of the present invention, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium of the invention, is stored thereon with computer program, described program is by processor
Realize that user provided by the present invention receives and dispatches the prediction technique of article mode when execution.
According to the technique and scheme of the present invention, one embodiment in foregoing invention have the following advantages that or the utility model has the advantages that benefit
Customer attribute information is obtained with order information, the first prediction mould that order information and customer attribute information input are pre-established
Type calculates and user property and associated the first prediction result of transmitting-receiving mode of order detail；It is determined wherein from order information
Characteristic information is inputted the second prediction model pre-established, is calculated and article in order by the characteristic information of any article
The second prediction result of transmitting-receiving mode of feature association；By the first prediction result and the second prediction result according to preset identification tactic
In conjunction with to obtain the final prediction result that the higher user of accuracy receives and dispatches article mode；Utilizing the first prediction model meter
When calculation, in addition to input order information and customer attribute information, also according to order information obtain self-service distribution of facilities information and
User's history input model of receiving and sending messages is calculated, and by the way that reasonable identification tactic is arranged with prediction knot of both merging
Fruit realizes the further promotion of precision of prediction.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the key step schematic diagram of the prediction technique of middle user's transmitting-receiving article mode according to embodiments of the present invention；
Fig. 2 is the major part schematic diagram of the prediction meanss of middle user's transmitting-receiving article mode according to embodiments of the present invention；
Fig. 3 is to can be applied to exemplary system architecture figure therein according to embodiments of the present invention；
Fig. 4 is for realizing that the user of the embodiment of the present invention receives and dispatches the structure of the electronic equipment of the prediction technique of article mode
Schematic diagram.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
The technical solution of the embodiment of the present invention obtains customer attribute information using order information, and order information and user are belonged to
The first prediction model that property information input pre-establishes, calculates and user property and the associated transmitting-receiving mode first of order detail
Prediction result；The characteristic information that any article is determined from order information, second that characteristic information input is pre-established
Prediction model is calculated and associated the second prediction result of transmitting-receiving mode of article characteristics in order；By the first prediction result with
Second prediction result is combined according to preset identification tactic, so that obtaining the higher user of accuracy receives and dispatches the final of article mode
Prediction result；When being calculated using the first prediction model, in addition to input order information and customer attribute information, also according to order
The distributed intelligence of acquisition of information self-service facilities and user's history input model of receiving and sending messages are calculated, and reasonable by setting
Identification tactic realizes the further promotion of precision of prediction to merge both sides prediction result.
It should be pointed out that in the absence of conflict, the technical characteristic in the embodiment of the present invention and embodiment can
To be combined with each other.
Fig. 1 is the key step schematic diagram of the prediction technique of middle user's transmitting-receiving article mode according to embodiments of the present invention.
As shown in Figure 1, the prediction technique that the user of the embodiment of the present invention receives and dispatches article mode can be executed according to following steps:
Step S101: obtaining the corresponding customer attribute information of subscriber identity data in order information, by order information and
Customer attribute information inputs the first prediction model pre-established, obtains the first prediction knot that user receives and dispatches article mode in order
Fruit.
In embodiments of the present invention, order can be reception order for extracting article or for the transmission of delivery items
Order.Such as: user need to determine in internet more than one piece article to be bought including recipient's title, recipient address, article letter
The reception order of the contents such as breath is submitted to Internet service side；User's more than one piece article to be delivered, need to fill in including sender's title,
The transmission order of the contents such as sender address, recipient's title, recipient address, Item Information is submitted to logistics service side.This
Invention is i.e. for before user submits and receives order or send order, the mode that prediction user receives or sends article to be pushed away to it
It send, avoids it from forgeing selection transmitting-receiving mode, promote its Experience Degree.
In practical application, a large amount of self-service facilities are arranged for users to use in service side, by means of self-service facilities, user's transmitting-receiving
Visit transmitting-receiving mode or self-service mode may be selected when article.Transmitting-receiving mode of visiting refers to traditional complete by professional courier
The mode of journey transmitting-receiving, and in self-service mode: when user receives article, article is placed in self-service set in advance by professional courier
It applies, user voluntarily extracts to self-service facilities；When user sends article, it is about to article certainly and is placed in self-service facilities, occupation is fast
Pass remaining process that personnel complete delivering.As the useful supplement for the mode of receiving and dispatching of visiting, it is valuable that self-service mode, which is suitable for article,
The situations such as product or fragile article, professional courier lazy weight.
It is understood that the order, user, transmitting-receiving article in the embodiment of the present invention and the address in order are mutual
It is associated.Wherein, transmitting-receiving article refers to receiving or sending article.When order is to receive order: user refers in particular to recipient,
Do not refer to sender；Transmitting-receiving article refers to reception article, and the address in order is recipient address.It is to send order in order
When: user refers in particular to sender, does not refer to recipient；Transmitting-receiving article refers to sending article, and the address in order is sender
Location.The prediction technique that user of the invention receives and dispatches article mode be applicable to user by receive the scene of order reception article with
And user sends the scene of article by sending order.
Particularly, in embodiments of the present invention, it before the order information in step S101 refers to that user submits order, embodies
Information in the order.User equipment can be used for different user to be distinguished in subscriber identity data in practical application
Mark, such as International Mobile Equipment Identity code IMEI (the International Mobile Equipment of user mobile phone
Identity).In concrete scene, order information may include following at least one: order note identification data, are ordered subscriber identity data
Single value data, freight charges data, total weight data, overall volume data, address date, breakable object flag data.Illustratively, it orders
Single information can be as shown in the table:
In upper table, first is classified as order note identification data, second be classified as subscriber identity data, third and fourth be classified as order gold
Specified number evidence, the 5th is classified as freight charges data, the 6th is classified as total weight data, the 7th is classified as overall volume data, the 8th is classified as number of addresses
According to, the 9th be classified as breakable object flag data.In the order information that the above order number is 9: user identifier 3333, article is preferential
The amount of money of front and back is 2000 yuan, 1500 yuan, and 40 yuan of freight charges, total weight 25KG, total volume is 44 volume units, and station address is compiled
Number it is 1256, contains breakable object in article.
Customer attribute information can be provided by service database, may include following at least one: subscriber identity data, gender
Data, identity data, historical interaction data.Wherein, identity data can be characterization user whether be campus user data, go through
History interaction data can be the historical trading data of user.
Such as: the user attribute data of certain user is as follows:
| User identifier | Whether campus user | Gender | Transaction count | Transaction amount |
| 3333 | 1 | 1 | 569 | 8963 |
In upper table, first is classified as subscriber identity data, and second is classified as identity data, and third is classified as gender data, the 4th,
Five are classified as historical interaction data.The user for being identified as 3333 is campus user, male, historical trading 569 times, transaction amount
8963 yuan.
In this step, the subscriber identity data contained in order information and customer attribute information is associated with, can be obtained
Take the user attribute data corresponding to subscriber identity data.Later, order information is inputted with the customer attribute information got
The first prediction model pre-established.
As a preferred embodiment, the first prediction model, which can be, utilizes deep neural network DNN (Deep Neural
Network) the mathematical model of algorithm building.First prediction model is before use, a large amount of using what is obtained from service database
Training data is trained to establish.It is understood that each training of each mathematical model in the embodiment of the present invention
Data contain the data of each dimension of information to be predicted, and the mode of article is received and dispatched containing determining user.Meanwhile if to pre-
Measurement information increases the data of one or more dimensions, then prediction model can be used increase the dimension data training data again
Training.Such as: each training data that above-mentioned first prediction model uses contains order information and customer attribute information is all
The data of dimension and the user of determination receive and dispatch the mode of article.In practical application, the first prediction model can also be used other points
Class algorithm such as random forests algorithm etc. is established, the invention is not limited in this regard.
It is appreciated that term " first " used in the present invention, " second " etc. are only used for indicating herein.Citing and
Speech, without departing from the present invention, can be known as the second prediction model for the first prediction model, can also be by second
Prediction model is known as the first prediction model, and the first prediction model and the second prediction model are all prediction models, but the two is not same
One prediction model.
In this step, order information and customer attribute information are inputted after the first prediction model, the can be calculated
One prediction result.Preferably, the first prediction result may is that the mode of article in user's transmitting-receiving order is the probability of self-service mode
Value.
In order to further increase precision of prediction, in an optional implementation, it can choose and more receive and dispatch article with user
Input of the relevant information of mode as the first prediction model.Specifically, using the address date in order information from business
The self-service facilities distributed intelligence for corresponding to the address date is obtained in database, is inputted the first prediction model.Wherein, self-service
Distribution of facilities information may include following at least one: self-service facilities quantity in the preset range centered on address in order,
Each self-service facilities are at a distance from address in order within the scope of this.In concrete application, preset range can be round or rectangle region
Domain.
In addition, in embodiments of the present invention, it can also be from acquisition in service database and the user identifier number in order information
It receives and sends messages according to user's history corresponding with address date, is inputted the first prediction model.Wherein, user's history is received and sent messages
It may is that the number of self-service facilities of user's use in the preset range centered on address in order in prefixed time interval.
It is understood that for the first prediction model, if it is order information, user property letter that it, which inputs information,
Breath, self-service facilities distributed intelligence and user's history are received and sent messages, then when the first prediction model is established, are needed using comprising above-mentioned
The training data of four kinds of all dimensions of information is trained.
By step S101, the present invention can obtain a variety of information relevant to user's transmitting-receiving article mode: order information, use
Family attribute information, self-service facilities distributed intelligence and user's history are received and sent messages, and the first prediction model is inputted, to calculate
The higher user of precision receives and dispatches the first prediction result of article mode out.
Step S102: it determines the characteristic information for any article for including in order, this feature information input is built in advance
The second vertical prediction model obtains the second prediction result that based on this kind of article, user receives and dispatches article mode in order.
In actual scene, various article is generally comprised in order, different types of article can pass through keeper unit SKU
(Stock Keeping Unit) is distinguished.It in this step, can be for any article for including in order, from business number
Its characteristic information is obtained according to library.Preferably, the characteristic information of certain article may include following at least one: the classification of this kind of article
Mark data, the weight data of Individual Items, the price data of Individual Items, Individual Items volume data.Characteristic information can
It is as shown in the table:
| Classification | Piece weight | Single-piece price | Single-piece volume |
| 56 | 5 | 98 | 8 |
In upper table: first is classified as classification logotype data, and second is classified as the weight data of Individual Items, and third is classified as single-piece
The price data of article, the 4th is classified as the volume data of Individual Items.The classification logotype of article is 56 in table, and piece weight is
5KG, single-piece price are 98 yuan, and single-piece volume is 8 volume units.
In this step, after the characteristic information for getting any article, it is inputted the second prediction pre-established
Model.Wherein, the second prediction model can be is constructed using deep neural network DNN (Deep Neural Network) algorithm
Mathematical model.Second prediction model using a large amount of training datas obtained from service database before use, be trained
To be established.Each training data that above-mentioned second prediction model uses contain all dimensions of characteristic information data and
Determining user receives and dispatches the mode of article.In practical application, it is such as random gloomy that other sorting algorithms can also be used in the second prediction model
Woods algorithm etc. is established, the invention is not limited in this regard.
In this step, it after the characteristic information of article any in order being inputted the second prediction model, can calculate
Based on this kind of article, user receives and dispatches the second prediction result of article mode.Second prediction result may is that user receives and dispatches order
The mode of middle article is the probability value of self-service mode.
It, can be by each article for including in order according to step in order to further increase precision of prediction in concrete application
Rapid S102 processing, obtains multiple second prediction results based on each article.
By step S102, user can be obtained and receive and dispatch second prediction knot of the article mode in terms of article characteristics in order
Fruit, it is to be understood that when specific execution, step S102 can be executed before, after or at the same time in step S101.
Step S103: it in conjunction with the first prediction result and the second prediction result, obtains user and receives and dispatches article mode in order
Final prediction result.
In this step, the both sides prediction result that front obtains can be merged according to preset identification tactic,
Obtain the final prediction result that user receives and dispatches article mode in order.
Preferably, following identification tactic can be performed in practical application: the probability value in the first prediction result is greater than default
Threshold value such as 0.5, while when the probability value in the second prediction result based on each article in order is all larger than preset threshold, most
Whole prediction result is self-service mode；Otherwise, final prediction result is transmitting-receiving mode of visiting.
Such as: containing there are three types of the article of SKU in order, the second prediction result is respectively: 0.55,0.7,0.8, and first
Prediction result is 0.6, then final prediction result are as follows: the mode that user receives and dispatches article in order is self-service mode.If the first prediction
As a result or a certain second prediction result is less than or equal to 0.5, then final prediction result are as follows: user receives and dispatches the mode of article in order
It is transmitting-receiving mode of visiting.
Reasonable identification tactic is set to merge both sides prediction result, it can be achieved that pre- in this way, passing through in this step
Survey the further promotion of precision.
In the technical solution of the embodiment of the present invention, the related data that can choose multiple dimensions inputs respectively to be pre-established
First prediction model of user oriented attribute and order detail and the second prediction model towards article characteristics in order, from
Two aspects consider to receive and dispatch the related information of article mode with user comprehensively and be merged, and it is higher final pre- to obtain accuracy
It surveys as a result, this result is pushed to promote user experience to user.
Fig. 2 is the major part schematic diagram for the prediction meanss that user receives and dispatches article mode in the embodiment of the present invention.
As shown in Fig. 2, the user of the embodiment of the present invention receives and dispatches the prediction meanss 200 of article mode can include: first prepares
Unit 201, the second preparatory unit 202 and predicting unit 203.Wherein:
First preparatory unit 201 can be used for obtaining the corresponding customer attribute information of subscriber identity data in order information,
The order information and the customer attribute information are inputted into the first prediction model pre-established, user is obtained and receives and dispatches in order
First prediction result of article mode；
Second preparatory unit 202 can be used for determining the characteristic information for any article for including in order, by the feature
The second prediction model that information input pre-establishes obtains based on this kind of article, user receives and dispatches article mode in order the
Two prediction results；
Predicting unit 203 can be used for combining the first prediction result and the second prediction result, obtains user and receives and dispatches object in order
The final prediction result of product mode.
In practical application, the mode that user receives and dispatches article in order includes: visit transmitting-receiving mode and self-service mode.
In embodiments of the present invention, the first prediction result and the second prediction result may each comprise: user receives and dispatches object in order
The mode of product is the probability value of self-service mode.
Preferably, the first preparatory unit 201 can be further used for: determining that the address date in order information is corresponding self-service
The self-service facilities distributed intelligence is inputted the first prediction model by distribution of facilities information；Wherein, the self-service facilities distributed intelligence
Comprise at least one of the following: self-service facilities quantity in the preset range centered on address in order, within the scope of this it is each from
Help facility at a distance from address in order.
As a preferred embodiment, the first preparatory unit 201 can be further used for: obtaining and mark with the user in order information
Know data and the corresponding user's history of address date is received and sent messages, the user's history is received and sent messages and inputs the first prediction mould
Type；Wherein, it includes: that user's use is self-service in the preset range centered on address in order that the user's history, which is received and sent messages,
The number of facility.
In concrete application, predicting unit 203 can be further used for: the probability value in the first prediction result is greater than default threshold
When probability value in value and the second prediction result based on each article in order is all larger than preset threshold, final prediction knot
Fruit is self-service mode；Otherwise, final prediction result is transmitting-receiving mode of visiting.
Illustratively, the preset threshold is 0.5.
In addition, in embodiments of the present invention, the order information further comprises following at least one: order amount of money number
According to, freight charges data, total weight data, overall volume data, breakable object flag data；The customer attribute information include it is following at least
It is a kind of: gender data, identity data, historical interaction data；The characteristic information comprises at least one of the following: the classification mark of article
Know data, the weight data of Individual Items, the price data of Individual Items, Individual Items volume data.And order is specific
It can are as follows: receive order or send order；When order is to receive order, user is recipient, and the address in order is recipient
Address；When order is to send order, user is sender, and the address in order is sender address.First prediction model with
Second prediction model is deep neural network DNN model.
In the technical solution of the embodiment of the present invention, the related data that can choose multiple dimensions inputs respectively to be pre-established
First prediction model of user oriented attribute and order detail and the second prediction model towards article characteristics in order, from
Two aspects consider to receive and dispatch the related information of article mode with user comprehensively and be merged, and it is higher final pre- to obtain accuracy
It surveys as a result, this result is pushed to promote user experience to user.
Fig. 3, which is shown, can receive and dispatch the prediction technique of article mode using the user of the embodiment of the present invention or user receives and dispatches object
The exemplary system architecture 300 of the prediction meanss of product mode.
As shown in figure 3, system architecture 300 may include terminal device 301,302,303, network 304 and server 305
(this framework is only example, and the component for including in specific framework can be according to the adjustment of application concrete condition).Network 304 to
The medium of communication link is provided between terminal device 301,302,303 and server 305.Network 304 may include various connections
Type, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 301,302,303 and be interacted by network 304 with server 305, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 301,302,303
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 301,302,303 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 305 can be to provide the server of various services, such as utilize terminal device 301,302,303 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to reception
To the data such as information query request analyze etc. processing, and by processing result (such as target push information, product letter
Breath -- merely illustrative) feed back to terminal device.
It should be noted that user provided by the embodiment of the present invention receives and dispatches the prediction technique of article mode generally by servicing
Device 305 executes, and correspondingly, the prediction meanss that user receives and dispatches article mode are generally positioned in server 305.
It should be understood that the number of terminal device, network and server in Fig. 3 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
The present invention also provides a kind of electronic equipment.The electronic equipment of the embodiment of the present invention includes: one or more processing
Device；Storage device, for storing one or more programs, when one or more of programs are by one or more of processors
It executes, so that one or more of processors realize that user provided by the present invention receives and dispatches the prediction technique of article mode.
Below with reference to Fig. 4, it illustrates the computer systems 400 for the electronic equipment for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.Electronic equipment shown in Fig. 4 is only an example, function to the embodiment of the present invention and should not use model
Shroud carrys out any restrictions.
As shown in figure 4, computer system 400 includes central processing unit (CPU) 401, it can be read-only according to being stored in
Program in memory (ROM) 402 or be loaded into the program in random access storage device (RAM) 403 from storage section 408 and
Execute various movements appropriate and processing.In RAM403, be also stored with computer system 400 operate required various programs and
Data.CPU401, ROM 402 and RAM 403 is connected with each other by bus 404.Input/output (I/O) interface 405 also connects
To bus 404.
I/O interface 405 is connected to lower component: the importation 406 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 408 including hard disk etc.；
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also connected to I/O interface 405 as needed.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. be mounted on as needed on driver 410, so as to from reading thereon
Computer program is mounted into storage section 408 as needed.
Particularly, disclosed embodiment, the process of key step figure description above may be implemented as according to the present invention
Computer software programs.For example, the embodiment of the present invention includes a kind of computer program products comprising be carried on computer-readable
Computer program on medium, the computer program include the program code for executing method shown in key step figure.?
In above-described embodiment, which can be downloaded and installed from network by communications portion 409, and/or from removable
Medium 411 is unloaded to be mounted.When the computer program is executed by central processing unit 401, executes and limited in system of the invention
Above-mentioned function.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.In this hair
In bright, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, wherein
Carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to electric
Magnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable storage medium
Any computer-readable medium other than matter, the computer-readable medium can be sent, propagated or transmitted for being held by instruction
Row system, device or device use or program in connection.The program code for including on computer-readable medium
It can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any conjunction
Suitable combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depending on related function.?
It should be noted that the combination of block diagram or each box in flow chart and the box in block diagram or flow chart, can use execution
The dedicated hardware based systems of defined functions or operations realizes, or can use specialized hardware and computer instruction
Combination is to realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include the first preparatory unit, the second preparatory unit and predicting unit.Wherein, the title of these units not structure under certain conditions
The restriction of the pairs of unit itself, for example, the first preparatory unit is also described as " sending the first prediction knot to predicting unit
The unit of fruit ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned meter
Calculation machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, so that
The step of equipment executes includes: the corresponding customer attribute information of subscriber identity data obtained in order information, is ordered described
Single information and the customer attribute information input the first prediction model pre-established, obtain user and receive and dispatch article mode in order
The first prediction result；The characteristic information for determining any article for including in order builds characteristic information input in advance
The second vertical prediction model obtains the second prediction result that based on this kind of article, user receives and dispatches article mode in order；With
And in conjunction with the first prediction result and the second prediction result, obtain the final prediction result that user receives and dispatches article mode in order.
In the technical solution of the embodiment of the present invention, the related data that can choose multiple dimensions inputs respectively to be pre-established
First prediction model of user oriented attribute and order detail and the second prediction model towards article characteristics in order, from
Two aspects consider to receive and dispatch the related information of article mode with user comprehensively and be merged, and it is higher final pre- to obtain accuracy
It surveys as a result, this result is pushed to promote user experience to user.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (13)
1. the prediction technique that a kind of user receives and dispatches article mode characterized by comprising
The corresponding customer attribute information of subscriber identity data in order information is obtained, the order information and the user are belonged to
Property the first prediction model for pre-establishing of information input, obtain the first prediction result that user receives and dispatches article mode in order；
The characteristic information for determining any article for including in order, the second prediction that characteristic information input is pre-established
Model obtains the second prediction result that based on this kind of article, user receives and dispatches article mode in order；And
In conjunction with the first prediction result and the second prediction result, the final prediction result that user receives and dispatches article mode in order is obtained.
2. the method according to claim 1, wherein the mode that user receives and dispatches article in order includes: receipts of visiting
Originating party formula and self-service mode.
3. according to the method described in claim 2, it is characterized in that, the first prediction result and the second prediction result include: use
The mode of article is the probability value of self-service mode in family transmitting-receiving order.
4. the method according to claim 1, wherein the method further includes:
It determines the corresponding self-service facilities distributed intelligence of address date in order information, the self-service facilities distributed intelligence is inputted
First prediction model；
Wherein, the self-service facilities distributed intelligence comprises at least one of the following: in the preset range centered on address in order
Self-service facilities quantity, within the scope of this each self-service facilities at a distance from address in order.
5. the method according to claim 1, wherein the method further includes:
Obtain in order information subscriber identity data and the corresponding user's history of address date receive and send messages, by the user
History, which is received and sent messages, inputs the first prediction model；
Wherein, the user's history receive and send messages include: user use in preset range centered on address in order from
Help the number of facility.
6. according to the method described in claim 3, it is characterized in that, the first prediction result of the combination and the second prediction result,
The final prediction result of article mode includes: in acquisition user's transmitting-receiving order
It is greater than preset threshold and the second prediction result based on each article in order in the probability value in the first prediction result
In probability value when being all larger than preset threshold, final prediction result is self-service mode；Otherwise, final prediction result is transmitting-receiving of visiting
Mode.
7. according to the method described in claim 6, it is characterized in that, the preset threshold is 0.5.
8. -7 any method according to claim 1, which is characterized in that
The order information further comprises following at least one: order value data, freight charges data, total weight data, totality
Volume data, breakable object flag data；
The customer attribute information comprises at least one of the following: gender data, identity data, historical interaction data；
The characteristic information comprises at least one of the following: the classification logotype data of article, the weight data of Individual Items, single-piece object
The volume data of the price datas of product, Individual Items.
9. -7 any method according to claim 1, which is characterized in that
Order specifically: receive order or send order；And
When order is to receive order, user is recipient, and the address in order is recipient address；
When order is to send order, user is sender, and the address in order is sender address.
10. -7 any method according to claim 1, the first prediction model and the second prediction model are depth nerve net
Network DNN model.
11. the prediction meanss that a kind of user receives and dispatches article mode characterized by comprising
First preparatory unit is ordered for obtaining the corresponding customer attribute information of the subscriber identity data in order information by described
Single information and the customer attribute information input the first prediction model pre-established, obtain user and receive and dispatch article mode in order
The first prediction result；
Second preparatory unit inputs the characteristic information for determining the characteristic information for any article for including in order
The second prediction model pre-established obtains the second prediction knot that based on this kind of article, user receives and dispatches article mode in order
Fruit；And
Predicting unit obtains user and receives and dispatches article mode in order for combining the first prediction result and the second prediction result
Final prediction result.
12. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-10.
13. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
The method as described in any in claim 1-10 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810153846.7A CN110188908B (en) | 2018-02-22 | 2018-02-22 | Method and device for predicting article receiving and sending modes of users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810153846.7A CN110188908B (en) | 2018-02-22 | 2018-02-22 | Method and device for predicting article receiving and sending modes of users |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110188908A true CN110188908A (en) | 2019-08-30 |
| CN110188908B CN110188908B (en) | 2024-07-19 |
Family
ID=67704634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810153846.7A Active CN110188908B (en) | 2018-02-22 | 2018-02-22 | Method and device for predicting article receiving and sending modes of users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188908B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488199A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Logistics distribution mode prediction method, system, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160502A (en) * | 2015-07-01 | 2015-12-16 | 浪潮集团有限公司 | Express delivery distribution device and method based on cloud computing |
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| CN107248012A (en) * | 2017-06-08 | 2017-10-13 | 北京惠赢天下网络技术有限公司 | Dispense processing method, device and the terminal device of order |
| CN107301576A (en) * | 2016-04-14 | 2017-10-27 | 苏宁云商集团股份有限公司 | The processing method and system of a kind of sequence information |
| CN107330647A (en) * | 2017-05-18 | 2017-11-07 | 中科富创（北京）科技有限公司 | Express delivery dispatching method, storage device, processing system |
| CN107341640A (en) * | 2017-07-14 | 2017-11-10 | 递易（上海）智能科技有限公司 | A kind of work station express delivery method |
| CN107622369A (en) * | 2017-09-29 | 2018-01-23 | 绿源美味（天津）网络科技有限公司 | Part method is posted in a kind of express delivery |
-
2018
- 2018-02-22 CN CN201810153846.7A patent/CN110188908B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160502A (en) * | 2015-07-01 | 2015-12-16 | 浪潮集团有限公司 | Express delivery distribution device and method based on cloud computing |
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| CN107301576A (en) * | 2016-04-14 | 2017-10-27 | 苏宁云商集团股份有限公司 | The processing method and system of a kind of sequence information |
| CN107330647A (en) * | 2017-05-18 | 2017-11-07 | 中科富创（北京）科技有限公司 | Express delivery dispatching method, storage device, processing system |
| CN107248012A (en) * | 2017-06-08 | 2017-10-13 | 北京惠赢天下网络技术有限公司 | Dispense processing method, device and the terminal device of order |
| CN107341640A (en) * | 2017-07-14 | 2017-11-10 | 递易（上海）智能科技有限公司 | A kind of work station express delivery method |
| CN107622369A (en) * | 2017-09-29 | 2018-01-23 | 绿源美味（天津）网络科技有限公司 | Part method is posted in a kind of express delivery |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488199A (en) * | 2020-11-30 | 2021-03-12 | 上海寻梦信息技术有限公司 | Logistics distribution mode prediction method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110188908B (en) | 2024-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019095883A1 (en) | Information generation method and apparatus | |
| CN109003028A (en) | Method and apparatus for dividing logistics region | |
| CN107609890A (en) | A kind of method and apparatus of order tracking | |
| CN107909261A (en) | Order method for pushing and device | |
| CN108520324A (en) | Method and apparatus for generating information | |
| CN109063935B (en) | Method, device and storage medium for predicting task processing time | |
| CN107908666A (en) | A kind of method and apparatus of identification equipment mark | |
| CN108776692A (en) | Method and apparatus for handling information | |
| CN111311147B (en) | Packing box recycling method, client, server and system | |
| CN107506958A (en) | Information generating method, medium, system and computing device | |
| CN110858347A (en) | Method and device for logistics distribution and order distribution | |
| CN110750697B (en) | Merchant classification method, device, equipment and storage medium | |
| CN109961306A (en) | A kind of inventory allocation method and apparatus of article | |
| CN110232487A (en) | A kind of task allocating method and device | |
| CN107908662A (en) | The implementation method and realization device of search system | |
| CN109345166A (en) | Method and apparatus for generating information | |
| CN109902986A (en) | Method and apparatus for output information | |
| CN109784407A (en) | The method and apparatus for determining the type of literary name section | |
| KR101410873B1 (en) | System and method for inquiring into position of courier items map-based | |
| CN109934427A (en) | The method and apparatus for generating article allocation plan | |
| CN109978213A (en) | A kind of task path planning method and device | |
| CN107464057A (en) | Method and apparatus for pushed information | |
| CN113762674B (en) | Order distribution method and device | |
| CN107844932B (en) | Order processing method and device | |
| CN109815266A (en) | Express delivery batch query method and apparatus based on big data platform |
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 |