CN104537502A - Method and device for processing orders - Google Patents
Method and device for processing orders Download PDFInfo
- Publication number
- CN104537502A CN104537502A CN201510020526.0A CN201510020526A CN104537502A CN 104537502 A CN104537502 A CN 104537502A CN 201510020526 A CN201510020526 A CN 201510020526A CN 104537502 A CN104537502 A CN 104537502A
- Authority
- CN
- China
- Prior art keywords
- order
- user
- feature
- current order
- history
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012545 processing Methods 0.000 title abstract description 11
- 230000004044 response Effects 0.000 claims abstract description 46
- 238000010801 machine learning Methods 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 36
- 239000013598 vector Substances 0.000 claims description 14
- 238000012549 training Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 14
- 230000015654 memory Effects 0.000 description 9
- 230000002354 daily effect Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002609 medium Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003442 weekly effect Effects 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"
-
- G06Q50/40—
Abstract
The embodiment of the invention relates to a method and device for processing orders. The method comprises the steps of obtaining at least one feature of previous orders and responses of users relevant to the previous orders, distributing a weight to each feature according to the responses of the users relevant to the previous orders, obtaining features of current orders, and selecting the current order to be shown to the users from the current orders according to the weights corresponding to the features of the current orders. According to the method and device for processing the orders, interference of order presentation to a driver can be reduced, and the utilization efficiency of order presentation media is improved.
Description
Technical field
The embodiments of the present invention relate generally to the process of order, and especially, the embodiments of the present invention relate to the method and apparatus of process order.
Background technology
The development of the universal and mobile Internet of smart machine, brings great convenience to the trip of people.Current demand of calling a taxi has been the common requirements of the members of all social strata, such as solves the problem of information asymmetry between taxi driver and passenger by the software of calling a taxi of " drip and call a taxi " and so on.
Software change tradition of calling a taxi is called a taxi mode, sets up and turns out passenger's modernization trip mode that the large mobile Internet epoch lead.Comparatively pick up than black phone car service and roadside, the birth of software of calling a taxi changes tradition especially and to call a taxi the market structure, overturn roadside pushing-off the wagons concept, utilize mobile Internet feature, merge on line with under line mutually, from calling a taxi, the starting stage uses line to pay fare to getting off, draw o2o (under line on line) the perfect closed loop that a passenger is closely connected with driver, optimize passenger to greatest extent to call a taxi experience, change the objective modes such as traditional taxi driver, allow driver master worker according to the destination of the passenger by wish " order " or " competition for orders ", saving driver and passenger link up cost, reduce rate of empty ride, maximize saving department and take advantage of both sides' resource and practice.
Software principle of calling a taxi is very simple, similar with phone dial-a-cab character, similar with micro-credit system.Namely passenger starts the software client of software of calling a taxi, click " existing in-use automotive ", pin and speak, the place sending concrete position, one section of present place of speech explanation and will go, unclamp chauffeur button, chauffeur information with this passenger for initial point, can automatically be pushed to the taxi driver within diameter 3 kilometers in 90 seconds, driver can hold a key to rob the software driver that calls a taxi and answer, and keeps in touch with passenger.Passenger arrive destination get off need pay fare time, the micro-letter payment of the software affiliate that calls a taxi and QQ wallet can be used to carry out line pays, both can enjoy and exempt from small change worry, it also avoid counterfeit money, the phenomenons such as bag that lose money occur, completing the perfect closed loop service paid from calling a taxi to, allowing the trip of passenger be all in oneself and grasping.
But, along with use call a taxi the driver of software and passengers quantity increasing, how to realize carrying out optimum matching fast to online large-scale order form and driver simultaneously, algorithm and framework be one and have challenging problem.Optimum matching refer to consider order feature, driver's feature, around after the factors such as driver's amount, time, road conditions, present (such as to each driver, broadcast by voice or picture display) current suitable order, and each order is obtained for and presents number of times fully.
But, exemplarily, consider that number broadcast by the order that driver can hear is certain in the online number of driver and driver's line duration certain scenario.If broadcast order to driver not possess accuracy, namely order is not broadcast with distinguishing, not only waste valuable order broadcast channel, make driver be ready to select the order of (be namely ready competition for orders) not broadcast fully, and interference is caused to driver.
In Internet advertising field, the clicking rate of user to advertisement can be predicted by machine-learning process.Specifically, a large amount of feature about user and advertisement and user can be recorded to the reaction (namely click or do not click advertisement) of advertisement as training data.In the training stage of machine learning, by utilizing machine learning model process training data, draw the weight of the characteristic allocation to user and advertisement.Then in the application stage, for the feature of active user and advertisement, the weight utilizing machine learning model He draw, can predict the clicking rate of user to advertisement.
But for various reasons, the machine-learning process relating to online advertisement can not be applicable to traffic order processing well, such as, because the selection of feature and application scenarios etc. are different.Thus, the method and apparatus of effective process order has good market outlook and objective marketable value.
Summary of the invention
Illustrative embodiments of the present invention relates to the method and apparatus of process order.
Basic conception of the present invention is, can store the order of every day in the server and present daily record and driver's competition for orders daily record in the process of long-term operation.Use the method for machine learning and data mining, utilize the daily record of these magnanimity to model training, can application model thus estimate out the competition for orders probability selecting the order at every turn presented about driver accurately.The driver's competition for orders probability estimating out is used for Order splitting, the especially phase sorting of Order splitting, the order that the order realizing high competition for orders probability has precedence over low competition for orders probability presents.
According to the embodiment of the present invention, provide a kind of method processing order, comprising: at least one feature obtaining History Order and the response of user be associated with History Order; According to the response of the user be associated with History Order, at least one characteristic allocation weight; Obtain the feature of current order; And according to the weight corresponding with the feature of current order, select the current order will presented to user in current order.
Alternatively, in the method, at least one feature obtaining History Order and the response of user be associated with History Order comprise: obtain the response whether user selects History Order.
Alternatively, in the method, according to the response of the user be associated with History Order, comprise at least one characteristic allocation weight: utilize machine learning model, the response of History Order whether is selected, at least one characteristic allocation weight according at least one feature of History Order and user.
Alternatively, in the method, according to the weight corresponding with the feature of current order, select being comprised by the current order presented to user in current order: utilize machine learning model, according to feature and the weight corresponding with the feature of current order of current order, determine that user selects the probability of current order.
Alternatively, in the method, according to the weight corresponding with the feature of current order, select also being comprised by the current order presented to user in current order: select the current order that the probability be easily selected by a user in current order is the highest, as the current order will presented to user.
Alternatively, in the method, machine learning model comprises Logic Regression Models or supporting vector machine model.
Alternatively, in the method, also comprise: utilize the feature of the current order presented to user and the response of user that is associated with current order, upgrade the weight corresponding with the feature of current order.
Alternatively, in the method, feature comprises at least one item in the following: the road conditions around the destination sending the distance of the position of order and user, the destination of order, the destination kind of order, order and order present number of times.
Alternatively, in the method, History Order, current order and user are associated with same geographic area.
According to the embodiment of the present invention, additionally provide a kind of equipment processing order, comprising: the first acquisition device, at least one feature of obtaining History Order and the response of user be associated with History Order; First distributor, for the response according to the user be associated with History Order, at least one characteristic allocation weight; Second acquisition device, for obtaining the feature of current order; And first selecting arrangement, for according to the weight corresponding with the feature of current order, select the current order will presented to user in current order.
Alternatively, in the device, also comprising: the 3rd acquisition device, whether selecting the response of History Order for obtaining user.
Alternatively, in the device, also comprising: the second distributor, for utilizing machine learning model, whether selecting the response of History Order according at least one feature of History Order and user, at least one characteristic allocation weight.
Alternatively, in the device, also comprising: determining device, for utilizing machine learning model, according to feature and the weight corresponding with the feature of current order of current order, determining that user selects the probability of current order.
Alternatively, in the device, also comprise: the second selecting arrangement, for selecting the current order that the probability be easily selected by a user in current order is the highest, as the current order will presented to user.
Alternatively, in the device, machine learning model comprises Logic Regression Models or supporting vector machine model.
Alternatively, in the device, also comprising: updating device, for utilizing the feature of the current order presented to user and the response of user that is associated with current order, upgrading the weight corresponding with the feature of current order.
Alternatively, in the device, feature comprises at least one item in the following: the road conditions around the destination sending the distance of the position of order and user, the destination of order, the destination kind of order, order and order present number of times.
Alternatively, in the device, History Order, current order and user are associated with same geographic area.
At least one during embodiments of the present invention tool has the following advantages: ensure present the accuracy of order to driver thus reduce interference to driver; And optimizing the sequence of Order splitting, the order that the order realizing high competition for orders probability has precedence over low competition for orders probability presents, thus improves the utilization ratio that order presents medium (such as, order broadcast channel).
Accompanying drawing explanation
By reference to the accompanying drawings and with reference to following detailed description, the feature of each embodiment of the present invention, advantage and other aspects will become more obvious, show some embodiments of the present invention by way of example, and not by way of limitation at this.In the accompanying drawings:
Fig. 1 is the process flow diagram of the method for process order according to an illustrative embodiment of the invention;
Fig. 2 is the block diagram of the equipment of process order according to an illustrative embodiment of the invention; And
Fig. 3 is the schematic block diagram of the mobile terminal be suitable for for putting into practice illustrative embodiments of the present invention; And
Fig. 4 is the schematic block diagram of the computing machine be suitable for for putting into practice illustrative embodiments of the present invention.
Embodiment
Each illustrative embodiments of the present invention is described in detail below with reference to accompanying drawing.Process flow diagram in accompanying drawing and block diagram show the architectural framework in the cards of the method and system according to various embodiment of the present invention, function and operation.It should be noted that, each square frame in process flow diagram or block diagram can represent a part for module, program segment or a code, and a part for described module, program segment or code can comprise the executable instruction of one or more logic function for realizing defined in each embodiment.Also it should be noted that at some as in alternative realization, the function marked in square frame also can according to being different from occurring in sequence of marking in accompanying drawing.Such as, in fact the square frame that two adjoining lands represent can perform substantially concurrently, or they also can perform according to contrary order sometimes, and this depends on involved function.Should be noted that equally, the combination of the square frame in each square frame in process flow diagram and/or block diagram and process flow diagram and/or block diagram, the special hardware based system of function or the operation put rules into practice can be used to realize, or the combination of specialized hardware and computer instruction can be used realize.
Should be appreciated that providing these illustrative embodiments is only used to enable those skilled in the art understand better and then realize the present invention, and not limit the scope of the invention by any way.
The method and apparatus of the process order of embodiments of the present invention at least goes for both passenger and freights.Simultaneously, although the present invention is mainly applicable to taxi taking service, but be to be understood that, the present invention is also applicable to any other transport instrument having existed or will there will be, and these transport instruments comprise water body and transport instrument (comprising the instrument of transport under water of water surface transport instrument cases such as submarine and so on of such as boats and ships and so on), aircraft (comprising the aircraft only run in earth environment and the aircraft that can run in space environment) and have any transport instrument conveyed goods with personnel ability.
Below be only described in detail for the method and apparatus of taxi taking service to process order of the present invention.
With reference to Fig. 1, it is the process flow diagram of the method 100 of process order according to an illustrative embodiment of the invention.
According to various illustrative embodiments of the present invention, the present invention can be implemented according to client-server architecture.Specifically, the passenger of taxi to be taken can use the client that can send order to send order to server.Then, server can process order and send order to the user be associated with order (such as driver).Order can present in the client that can receive order of user according to certain sequence afterwards.Client can be arranged on mobile device that client carries or on other electronic equipment, as being hereafter described in detail.
According to Fig. 1, in step s 110, at least one feature that can obtain History Order and the response of user be associated with History Order.Step S110 can comprise step S111, obtains the response whether user selects History Order.
According to the embodiment of the present invention, History Order can be to have presented and no longer to the order that user presents to user.During presenting History Order, depend on that whether user is interested in this History Order, user may select or not select this History Order.Process History Order in such as line server after, can the response of this History Order whether be selected to be stored in daily record History Order and user.
According to the embodiment of the present invention, can during the training stage of machine-learning process or before perform step S110 or S111.These steps can be performed in line server or in large data platform server.Specifically, daily record can be obtained in line server and the form being stored as the pairing of History Order-user ID as population sample.Alternatively, can in another server, such as large data platform server, from line server obtain daily record and the form being stored as the pairing of History Order-user ID as population sample.
According to the embodiment of the present invention, at least one feature obtaining History Order and the response of user be associated with History Order can comprise: first alternatively, in the population sample be associated with the feature of History Order, choose the sample be associated with specific geographical area, this specific geographical area is associated with by the current order occurred in the application stage.Such as, the transmission position of wherein order and the sample of position all in town of user is chosen.Carry out training from the samples selection part sample town after choosing the sample be associated with town and apply for the current order will sent in same city.Thus History Order, current order and user are associated with same geographic area.
Then, before training, alternatively pre-service is carried out to form training sample to the part sample selected.Pre-service can comprise text-processing.By text-processing, can from order, identify the text in order and it be presented in a particular form.
Then, for each History Order in training sample-user's pairing, the feature of History Order can be extracted, and extracts the response whether user selects History Order.The feature of History Order can comprise at least one item in the following: the destination sending the position of order and the distance of user or will go in the distance of the position at place and user, order when the personnel taking taxi wait for taxi, road conditions around the destination kind (such as, airport, hospital or school) of order, the destination of order or order present number of times.Wherein, according to some embodiments, order to present number of times can be order to same user repeat present number of times.The feature of History Order can also comprise: be ready pay extra tip, be ready wait for time, seating capacity, whether carry heavy luggage etc.Whether user selects the response of History Order can represent with the bit labeling in sample.
Should be appreciated that the personnel of taxi above-mentioned to be taken can be the software users using software of calling a taxi to carry out calling taxi, also can be the other staff of this software users on behalf of calling taxi.The position sending order can be represented by GPS (GPS) coordinate, also can be used for representing that the information of the position determined represents with other in appropriate circumstances, these information include but not limited to bus stop, subway station, certain crossing and certain specific buildings etc.When the position sending order is represented by the information except GPS coordinates, can by the take over party of order (such as, server) or third party (such as, other address translation mechanisms of such as certain professional website) be converted into GPS coordinates so that carry out subsequent operation.In addition, the information acquisition that road conditions can be issued from government department, or obtain according to the road vehicle density obtained by satellite view or road monitoring.
In addition, the feature of History Order can be that the content extracted from training sample is directly determined, or can be utilize server process extracted content and indirectly determine further.Exemplarily, the destination of order directly can be determined from the text message of History Order; As another example, could be able to determine to send the position of order and the distance of user in conjunction with the transmission position of order and the position of user; As another example, can process the text message about destination identified thus determine the kind of destination.
With reference to Fig. 1, perform step S120 after step silo.In the step s 120, can according to the response of the user be associated with History Order, at least one characteristic allocation weight.Step S120 can comprise step S121, utilizes machine learning model, whether selects the response of History Order, at least one characteristic allocation weight according at least one feature of History Order and user.
According to the embodiment of the present invention, step S120 or S121 can be performed in the training stage of machine-learning process.In line server or alternatively, can perform these steps in large data platform server, thus the training stage can off-line or carry out online.
According to the embodiment of the present invention, in the step s 120, extract the feature of the History Order in training sample in step s 110 and extract after whether user select the response of History Order, can by the information of at least one feature in each History Order in numerous training sample-user's pairing, and whether select the response of this History Order to form two groups of vectors respectively using as predictive variable and target variable with the driver in this pairing, and predictive variable and target variable are substituted into machine learning model train.Utilize machine learning model, according to predictive variable and target variable, can to each characteristic allocation weight at least one feature of History Order (such as, multiple predictive variable).The form of weight can be the vector corresponding with the vector of predictive variable.
In some embodiments, machine learning model can be logistic regression (Logistic Regression) model being widely used in two classification problems.In some embodiments, machine learning model can be supporting vector machine model.In other embodiments, other machine learning model can also be used according to test result.
Consider the situation using Logic Regression Models.Suppose feature or the predictive variable X=x of History Order, then whether user selects the boolean of the response of History Order to represent, namely the following formula of the probability of target variable Y=1 represents:
Wherein β is the weight to characteristic allocation, or is called model parameter.
In training sample, if user selects History Order, then Y=1; If user does not select History Order, then Y=0.Based on the predictive variable X determined and target variable Y, the predictive variable X of the information of the many groups History Order comprised in training data-user's pairing and target variable Y is substituted into formula, can determine the weight beta at least one characteristic allocation, β can be the vector corresponding with the vector of predictive variable X.In other words, each feature can have a weight corresponding to this feature.Exemplarily, position feature can have weight 0.5, and road conditions feature can have weight 0.3, and order presents number of times feature can have weight 0.1.
According to some embodiment, after the weight to characteristic allocation, the weight to characteristic allocation can be stored in the data file.When training in large data platform server, data file can be sent to line server so that line server loads this data file to obtain weight in the application stage.
With reference to Fig. 1, after step S120, perform step S30.In step s 130, which, the feature of current order can be obtained.
According to the embodiment of the present invention, step S130 can be performed in line server.
Current order refers to the order needing to present to user or presenting.Such as, current order can be not yet to the order that user presents, or to present and not yet to the order that other users present to some users.Current order can be obtained by line server.Obtain the mode of order can comprise and directly receive order from the personnel of the taxi to be taken of placing an order or receive the order forwarded by other intermediary agencies (such as, some websites etc.).
After acquisition current order, the one or more users be associated with current order can be selected in numerous user as the candidate user by presenting current order to it.Exemplarily, can select to be in the user alternatively user within the scope of the position sending current order.Candidate user can also be selected according to utilizing the travel direction etc. of other factors, such as user.In addition, can also selected candidate user further be filtered.
Notice, after the multiple current order of acquisition, multiple current order can be had to be associated with unique user, such as, in the particular range that this user is in the transmission position of multiple current order.Thus, in multiple current order preferred order can be selected to present to this user.
In order to obtain the feature of current order, can as above in step s 110, obtain the feature of current order for the mode described by the feature extracting History Order in the training stage.
The feature of current order can be with in the training stage to the corresponding feature of its feature assigned weight.Thus, the feature of current order can also comprise: the destination sending the position of order and the distance of user or will go in the distance of the position at place and user, order when the personnel taking taxi wait for taxi, road conditions around the destination kind (such as, airport, hospital or school) of order, the destination of order or order present number of times.The feature of current order and user can also comprise: be ready pay extra tip, be ready wait for time, seating capacity, whether carry heavy luggage etc.In addition, as being described about History Order, the feature of current order directly can be determined from the determined content of current order, or server can be utilized to process determined content and indirectly determine further.For the feature of current order, the weight corresponding with the feature of current order can be utilized, the weight namely in the training stage to the characteristic allocation corresponding with the feature of current order.
With reference to Fig. 1, perform step S140 after step s 130.In step S140, according to the weight corresponding with the feature of current order, the current order will presented to user in current order can be selected.
According to the embodiment of the present invention, step S140 can be performed in line server.
Step S140 can comprise step S141 and S142.In step s 141, can machine learning model be utilized, according to feature and the weight corresponding with the feature of current order of current order, determine that user selects the probability of current order.
According to the embodiment of the present invention, after the feature obtaining current order, the information composition of vector of the feature in current order-user that current order and the candidate user be associated with current order form can being matched using as predictive variable, and by predictive variable and substitute into machine learning model together with vector representation, corresponding with the feature in predictive variable weight and apply.Utilize machine learning model, according to predictive variable and corresponding weight, can determine that user selects the probability of current order.
In some embodiments, the machine learning model used in the application stage can be with in training stage identical machine learning model, such as Logic Regression Models.In some embodiments, machine learning model can be supporting vector machine model.In other embodiments, other machine learning model can also be used according to test result.
Still consider the situation using Logic Regression Models.By at the feature of current order or predictive variable X=x, and the weight beta of correspondence substitutes into the formula shown in the training stage.Then can show whether user selects the probability of current order, i.e. target variable Y, wherein Y can be from the real number between 0 to 1.
Then, alternatively, if user selects the probability of current order higher than predetermined threshold, then current order can be added order list for sequence.
According to the embodiment of the present invention, the multiple current order for a user received at different time by server can be formed order list for sequence by line server.Select the probability of current order and predetermined threshold to compare this user, if probability is higher than predetermined threshold, then current order is added order list for sequence; If probability is lower than predetermined threshold, do not add order list.By this step, can filtering user obviously do not wish select current order.According to some embodiments, predetermined threshold can be stored in the configuration file of the corresponding program in line server.Can also as required, based on the response of user, order in the whole matching situation etc. of special time because usually regularly or dynamically adjusting this threshold value.In some embodiments, the candidate user that previously described selection is associated with current order can not be carried out, and directly screen by probability the user be associated with current order.
Then step S142 is performed.In step S142, the current order that the probability be easily selected by a user in current order is the highest can be selected, as the current order will presented to user.
According to the embodiment of the present invention, according to some embodiments, line server can select the probability of multiple current order according to user, sort to these current order, and the current order then selecting the probability that is easily selected by a user the highest is as the current order will presented to user.
According to some embodiments, in selection by after the current order that user presents, current order can be sent to the client of user to present to user.Such as, in the client of user (such as, mobile device), can be broadcast by voice or present current order in the mode of picture display on user interface (such as, touch-sensitive display etc.).User can depend on that whether it is interested in this current order, and selects this current order responsively by user interface.
Alternatively, according to some embodiments, send to user together with the probability that multiple current order and user can be selected current order by line server, and realize the sequence of multiple current order in the client of user.
Visible according to content described above, the order with the higher probability be easily selected by a user can be presented and exist, thus realization preferentially presents the order that user is more ready to select.
According to some embodiments, after user selects current order, or after the non-selected current order of user thus order be presented the schedule time, step S130 can be returned, to obtain new current order for selection; Or return step S140, based on the feature that part upgrades, reselect the order will presented to user.Here notice, same current order, in its valid period, repeatedly may be presented to same user by the probability selected due to higher.Thus, number of times that same current order repeats to same user the to present feature as this current order can be recorded.
With reference to Fig. 1, perform step S150 alternatively after step s 140.In step S150, can utilize the feature of the current order presented to user and the response of user that is associated with current order, upgrade the weight corresponding with the feature of current order.
According to the embodiment of the present invention, as being described about History Order, the response of each current order presented to it whether can be selected by recording user.Then can by current order, and the related data whether characteristic sum the comprising current order user that is presented current order have selected the response of current order is stored in daily record.Notice that current order can become History Order, and the user be associated with current order can become the user be associated with History Order herein.
Get back to step S120 afterwards.In line server or large data platform server, utilize the Data Update weight in daily record.When upgrading, can according to every day, weekly or other frequency upgrade, also can come again to classify to sample according to the geographic area be associated with order or further feature, so as to obtain optimize selection result.
The method of process order is according to an illustrative embodiment of the invention described above with reference to Fig. 1.Be to be understood that, although describe the operation of the method according to particular order (step S110, step S111, step S120, step S121, step S130, step S140, step S141, step S142, step S150), but, this is not that requirement or hint must perform these operations according to this particular order, or must perform the result that all shown operation could realize expectation.On the contrary, the step described in process flow diagram can change execution sequence.Additionally or alternatively, some step can be omitted, multiple step be merged into a step and perform, and/or a step is decomposed into multiple step and perform.Such as, in some embodiments, step S110 to S130 can perform according to random order or simultaneously, can omit one or two steps in step S141 to S142, step S141 and S142 can be merged into a step to perform, and/or step S121 or S141 is decomposed.
With reference to Fig. 2, it is the block diagram of the equipment of process order according to an illustrative embodiment of the invention.
According to Fig. 2, the equipment 200 of process order comprises the first acquisition device 201, first distributor 202, second acquisition device 203, first selecting arrangement 204, the 3rd acquisition device 205, second distributor 206, determining device 207, second selecting arrangement 208 and updating device 209.
According to an illustrative embodiment of the invention, in the equipment 200 of process order, the first acquisition device 201, at least one feature of obtaining History Order and the response of user be associated with History Order; First distributor 202, for the response according to the user be associated with History Order, at least one characteristic allocation weight; Second acquisition device 203, for obtaining the feature of current order; First selecting arrangement 204, for according to the weight corresponding with the feature of current order, selects the current order will presented to user in current order; Whether the 3rd acquisition device 205, select the response of History Order for obtaining user; Whether the second distributor 206, for utilizing machine learning model, select the response of History Order, at least one characteristic allocation weight according at least one feature of History Order and user; Determining device 207, for utilizing machine learning model, according to feature and the weight corresponding with the feature of current order of current order, determines that user selects the probability of current order; Second selecting arrangement 208, for selecting the current order that the probability be easily selected by a user in current order is the highest, as the current order will presented to user; And updating device 209, for utilizing the feature of the current order presented to user and the response of user that is associated with current order, upgrade the weight corresponding with the feature of current order.
In addition, in the equipment 200 of process order, machine learning model can comprise Logic Regression Models or supporting vector machine model.And wherein feature comprises at least one item in the following: the road conditions around the destination sending the distance of the position of order and user, the destination of order, the destination kind of order, order and order present number of times.And wherein History Order, current order and user are associated with same geographic area.
It should be noted that illustrative embodiments of the present invention can be realized by the combination of hardware, software or software and hardware.Wherein, hardware components can utilize special logic to realize; Software section then can store in memory, and by suitable instruction execution system, such as microprocessor or special designs hardware perform.Those having ordinary skill in the art will appreciate that above-mentioned method and system can use computer executable instructions and/or be included in processor control routine to realize, such as, on the programmable memory of mounting medium, such as ROM (read-only memory) (firmware) or the data carrier of such as optics or electrical signal carrier of such as disk, CD or DVD-ROM, provide such code.System of the present invention and module thereof not only can be realized by the hardware circuit of the programmable hardware device of the semiconductor of such as VLSI (very large scale integrated circuit) or gate array, such as logic chip, transistor etc. or such as field programmable gate array, programmable logic device etc., also with the software simulating such as performed by various types of processor, can also can be realized by the combination (such as firmware) of above-mentioned hardware circuit and software.
Although it should be noted that in the detailed description above some devices of the equipment that is referred to or sub-device, this division is only exemplary but not enforceable.In fact, according to an illustrative embodiment of the invention, the Characteristic and function of an above-described device can Further Division for be specialized by multiple device, such as the first distributor 202 and the second acquisition device 203 can be arranged in different equipment.
Below with reference to Fig. 3, it illustrates the schematic block diagram specifically of the mobile terminal 300 be suitable for for putting into practice embodiment of the present invention.
According to exemplary embodiment of the present invention, mobile terminal 300 can be used by user 220 usually.But, should be appreciated that the present invention does not get rid of situation about being used as the equipment 200 processing order by mobile terminal 300.
In the example depicted in fig. 3, mobile terminal 300 is mobile devices with radio communication function.But, be appreciated that this is only exemplary and nonrestrictive.The mobile terminal of other types also easily can adopt embodiments of the present invention, the voice of such as portable digital-assistant (PDA), pager, mobile computer, mobile TV, game station, laptop computer, camera, video recorder, GPS device and other types and text communication system.The fixed mobile terminal of such as vehicle moving terminal and so on easily can use embodiments of the present invention equally.
Mobile terminal 300 comprises one or more antenna 311, and it operationally communicates with receiver 316 with transmitter 314.Mobile terminal 300 also comprises processor 312 or other treatment elements, and it provides the signal going to transmitter 314 and the signal received from receiver 316 respectively.Signal comprises the signaling information of the air-interface standard according to suitable cellular system, and comprises user speech, the data of reception and/or the data of user's generation.In this regard, mobile terminal 300 can utilize one or more air-interface standard, communication protocol, modulation type and access style to operate.Exemplarily, mobile terminal 300 can operate according to any agreement in multiple first generation, the second generation, the third generation and/or forth generation communication protocol etc.Such as, mobile terminal 300 can operate according to the second generation (G) wireless communication protocol IS-136 (TDMA), GSM and IS-95 (CDMA), or operate according to the third generation (G) wireless communication protocol of such as UMTS, CDMA2000, WCDMA and TD-SCDMA, or operate according to forth generation (4G) wireless communication protocol and/or similar agreement.
Be appreciated that processor 312 comprises the circuit needed for the function realizing mobile terminal 300.Such as, processor 312 can comprise digital signal processor device, micro processor device, various analog to digital converter, digital to analog converter and other support circuit.The control of mobile terminal 300 and signal processing function distribute betwixt according to these equipment ability separately.Processor 312 can also be included in the function of modulating and before transmission, message and data being carried out to convolutional encoding and intertexture thus.Processor 312 can also comprise internal voice coder in addition, and can comprise internal data modem.In addition, processor 312 can comprise the function operated one or more software programs that can store in memory.Such as, processor 312 can operate linker, such as traditional Web browser.Linker can allow mobile terminal 300 such as to transmit and receive web content (such as location-based content and/or other web page contents) according to WAP (wireless application protocol) (WAP), HTML (Hypertext Markup Language) (HTTP) etc. then.
Mobile terminal 300 can also comprise user interface, and it such as can comprise earphone or loudspeaker 324, ringer 322, microphone 326, display screen 328 and input interface 331, and all these equipment are all coupled to processor 312.Mobile terminal 300 can comprise keypad 330.Keypad 330 can comprise traditional numerical key (0-9) and relative keys (#, *), and for other keys of operating mobile terminal 300.Alternatively, keypad 330 can comprise traditional QWERTY arrangements of keypad.Keypad 330 can also comprise the various soft keys be associated with function.Mobile terminal 300 can also comprise camera model 336, for catching static state and/or dynamic image.
Especially, display screen 328 can comprise touch-screen and/or contiguous formula screen, user can by direct control screen operating mobile terminal 300.Now, display screen 328 serves as both input equipment and output device simultaneously.In such embodiment, input interface 331 can be configured for the input receiving user and provided on display screen 328 by such as common pen, special stylus and/or finger, comprises and gives directions input and gesture input.Processor 312 is configurable for detecting this type of input, and identifies the gesture of user.
In addition, mobile terminal 300 can comprise the interfacing equipment of such as operating rod or other are for input interface.Mobile terminal 300 also comprises battery 334, such as vibrating battery group, powers for the various circuit needed for operating mobile terminal 300, and provides mechanical vibration as detecting output alternatively.
Mobile terminal 300 may further include Subscriber Identity Module (UIM) 338.UIM 338 normally has the memory devices of internal processor.UIM 338 such as can comprise subscriber identity module (SIM), Universal Integrated Circuit Card (UICC), Universal Subscriber Identity module (USIM), removable Subscriber Identity Module (R-UIM) etc.UIM 338 stores the cell relevant to mobile subscriber usually.
Mobile terminal 300 can also have storer.Such as, mobile terminal 300 can comprise volatile storage 340, such as, comprise the volatile Random Access Memory (RAM) of the cache area temporarily stored for data.Mobile terminal 300 can also comprise other nonvolatile memorys 342, and it can be Embedded and/or moveable.Nonvolatile memory 342 additionally or alternatively can comprise such as EEPROM and flash memory etc.Storer can Arbitrary Term in multiple information segment of using of memory mobile terminal 300 and data, to realize the function of mobile terminal 300.Such as, storer 340 and 342 can be configured for the computer program instructions of the method stored for realizing the real-time process order that composition graphs 1 above describes.
Should be appreciated that the structured flowchart described in Fig. 3 illustrates just to the object of example, instead of limitation of the scope of the invention.In some cases, can increase or reduce some equipment as the case may be.
Below with reference to Fig. 4, it illustrates the schematic block diagram of the computer system 400 be suitable for for putting into practice embodiment of the present invention.As shown in Figure 4, computer system 400 can comprise: CPU (CPU (central processing unit)) 401, RAM (random access memory) 402, ROM (ROM (read-only memory)) 403, bus system 404, hard disk controller 405, keyboard controller 406, serial interface controller 407, parallel interface controller 408, display controller 409, hard disk 410, keyboard 411, serial peripheral 412, parallel peripheral hardware 413 and display 414.In such devices, what be coupled with system bus 404 has CPU 401, RAM 402, ROM 403, hard disk controller 405, keyboard controller 406, serialization controller 407, parallel controller 408 and display controller 409.Hard disk 410 is coupled with hard disk controller 405, keyboard 411 is coupled with keyboard controller 406, serial peripheral equipment 412 is coupled with serial interface controller 407, and concurrent peripheral equipment 413 is coupled with parallel interface controller 408, and display 414 is coupled with display controller 409.Should be appreciated that the structured flowchart described in Fig. 4 illustrates just to the object of example, instead of limitation of the scope of the invention.In some cases, can increase or reduce some equipment as the case may be.
Although describe the present invention with reference to some embodiments, should be appreciated that, the present invention is not limited to disclosed embodiment.The present invention is intended to be encompassed in the interior included various amendment of spirit and scope and the equivalent arrangements of claims.The scope of claims meets the most wide in range explanation, thus comprises all such amendments and equivalent structure and function.
Claims (18)
1. process a method for order, comprising:
At least one feature obtaining History Order and the response of user be associated with described History Order;
According to the response of the user be associated with described History Order, at least one characteristic allocation weight described;
Obtain the feature of current order; And
According to the weight corresponding with the feature of described current order, select the current order will presented to user in described current order.
2. method according to claim 1, at least one feature wherein obtaining History Order and the response of user be associated with described History Order comprise:
Obtain the response whether described user selects described History Order.
3. method according to claim 2, wherein according to the response of the user be associated with described History Order, comprises at least one characteristic allocation weight described:
Utilize machine learning model, whether select the described response of described History Order according at least one feature of described History Order and described user, at least one characteristic allocation weight described.
4. method according to claim 1, wherein according to the weight corresponding with the feature of described current order, select being comprised by the current order presented to user in described current order:
Utilize machine learning model, according to feature and the weight corresponding with the feature of described current order of described current order, determine that user selects the probability of described current order.
5. method according to claim 4, also comprises:
Select the current order that the probability be easily selected by a user in described current order is the highest, as the current order will presented to user.
6. the method according to claim 3 or 4, wherein said machine learning model comprises Logic Regression Models or supporting vector machine model.
7. method according to claim 1, also comprises:
Utilize the feature of the current order presented to user and the response of user that is associated with described current order, upgrade the weight corresponding with the feature of described current order.
8. method according to claim 1, wherein said feature comprises at least one item in the following:
Road conditions around the destination sending the distance of the position of order and user, the destination of order, the destination kind of order, order and order present number of times.
9. method according to claim 1, wherein said History Order, described current order and described user are associated with same geographic area.
10. process an equipment for order, comprising:
First acquisition device, at least one feature of obtaining History Order and the response of user be associated with described History Order;
First distributor, for the response according to the user be associated with described History Order, at least one characteristic allocation weight described;
Second acquisition device, for obtaining the feature of current order; And
First selecting arrangement, for according to the weight corresponding with the feature of described current order, selects the current order will presented to user in described current order.
11. equipment according to claim 10, also comprise:
Whether the 3rd acquisition device, select the response of described History Order for obtaining described user.
12. equipment according to claim 11, also comprise:
Whether the second distributor, for utilizing machine learning model, select the described response of described History Order, at least one characteristic allocation weight described according at least one feature of described History Order and described user.
13. equipment according to claim 10, also comprise:
Determining device, for utilizing machine learning model, according to feature and the weight corresponding with the feature of described current order of described current order, determines that user selects the probability of described current order.
14. equipment according to claim 13, also comprise:
Second selecting arrangement, for selecting the current order that the probability be easily selected by a user in described current order is the highest, as the current order will presented to user.
15. equipment according to claim 12 or 13, wherein said machine learning model comprises Logic Regression Models or supporting vector machine model.
16. equipment according to claim 10, also comprise:
Updating device, for utilizing the feature of the current order presented to user and the response of user that is associated with described current order, upgrades the weight corresponding with the feature of described current order.
17. equipment according to claim 10, wherein said feature comprises at least one item in the following:
Road conditions around the destination sending the distance of the position of order and user, the destination of order, the destination kind of order, order and order present number of times.
18. equipment according to claim 10, wherein said History Order, described current order and described user are associated with same geographic area.
Priority Applications (10)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510020526.0A CN104537502A (en) | 2015-01-15 | 2015-01-15 | Method and device for processing orders |
| KR1020187037289A KR20190000400A (en) | 2014-08-04 | 2015-08-04 | Service distribution system and method |
| SG11201700895YA SG11201700895YA (en) | 2014-08-04 | 2015-08-04 | Methods and systems for distributing orders |
| SG10201901024TA SG10201901024TA (en) | 2014-08-04 | 2015-08-04 | Methods and systems for distributing orders |
| PCT/CN2015/086075 WO2016019857A1 (en) | 2014-08-04 | 2015-08-04 | Service distribution system and method |
| MYPI2017000173A MY188692A (en) | 2014-08-04 | 2015-08-04 | Methods and systems for distributing orders |
| KR1020177003867A KR20180006871A (en) | 2014-08-04 | 2015-08-04 | Service distribution system and method |
| US15/501,824 US20170228683A1 (en) | 2014-08-04 | 2015-08-04 | Methods and systems for distributing orders |
| EP15829451.2A EP3179420A4 (en) | 2014-08-04 | 2015-08-04 | Service distribution system and method |
| PH12017500192A PH12017500192B1 (en) | 2014-08-04 | 2017-02-01 | Methods and systems for distributing orders |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510020526.0A CN104537502A (en) | 2015-01-15 | 2015-01-15 | Method and device for processing orders |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104537502A true CN104537502A (en) | 2015-04-22 |
Family
ID=52853021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510020526.0A Pending CN104537502A (en) | 2014-08-04 | 2015-01-15 | Method and device for processing orders |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104537502A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118013A (en) * | 2015-07-29 | 2015-12-02 | 北京嘀嘀无限科技发展有限公司 | Order distributing method and apparatus |
| CN105279688A (en) * | 2015-10-23 | 2016-01-27 | 上海钢富电子商务有限公司 | Order form data processing method and system |
| CN106126880A (en) * | 2016-06-14 | 2016-11-16 | 广州视睿电子科技有限公司 | The system of selection of targeted customer, system and equipment |
| CN106844367A (en) * | 2015-12-03 | 2017-06-13 | 阿里巴巴集团控股有限公司 | A kind of processing method and processing device of Internet service |
| CN106993330A (en) * | 2016-01-21 | 2017-07-28 | 滴滴（中国）科技有限公司 | The distribution method and system of talk channel |
| WO2017133149A1 (en) * | 2016-02-06 | 2017-08-10 | 京东方科技集团股份有限公司 | Order processing method, apparatus and system |
| CN107203789A (en) * | 2017-06-23 | 2017-09-26 | 北京小度信息科技有限公司 | Distribution model method for building up, distribution method and relevant apparatus |
| CN107230122A (en) * | 2016-03-25 | 2017-10-03 | 滴滴（中国）科技有限公司 | Passenger calls a taxi order switching method and device |
| CN107357852A (en) * | 2017-06-28 | 2017-11-17 | 镇江五八到家供应链管理服务有限公司 | A kind of determination methods of shipping driver to order wish |
| CN107358386A (en) * | 2017-06-23 | 2017-11-17 | 镇江五八到家供应链管理服务有限公司 | A kind of shipping driver and the matching process and matching system of order |
| WO2017202112A1 (en) * | 2016-05-23 | 2017-11-30 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for distributing request for service |
| CN107451878A (en) * | 2017-06-01 | 2017-12-08 | 北京小度信息科技有限公司 | order processing method and device |
| CN109886603A (en) * | 2019-03-12 | 2019-06-14 | 北京同城必应科技有限公司 | Order method for pushing, device, equipment and storage medium |
| CN110211369A (en) * | 2017-08-16 | 2019-09-06 | 北京嘀嘀无限科技发展有限公司 | For dispatching the method, equipment and medium of idle transport power |
| CN110520912A (en) * | 2018-03-22 | 2019-11-29 | 东芝存储器株式会社 | Information processing unit, information processing method and message handling program |
| CN110766505A (en) * | 2018-11-09 | 2020-02-07 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying urgent order requests |
| CN111052158A (en) * | 2017-07-20 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing service requests |
| CN111144676A (en) * | 2018-11-05 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Vehicle order distribution method, device, server and computer readable storage medium |
| CN111353676A (en) * | 2018-12-24 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Order distribution method, system, computer device and computer readable storage medium |
| CN111476389A (en) * | 2019-01-24 | 2020-07-31 | 北京嘀嘀无限科技发展有限公司 | Method and device for pre-estimating order receiving waiting time |
| WO2020244081A1 (en) * | 2019-06-05 | 2020-12-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | Constrained spatiotemporal contextual bandits for real-time ride-hailing recommendation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
| CN102779193A (en) * | 2012-07-16 | 2012-11-14 | 哈尔滨工业大学 | Self-adaptive personalized information retrieval system and method |
| CN103489117A (en) * | 2012-06-12 | 2014-01-01 | 深圳市腾讯计算机系统有限公司 | Method and system for information releasing |
| CN103996290A (en) * | 2014-06-09 | 2014-08-20 | 北京东方车云信息技术有限公司 | Taxi service providing method, server and system |
| US8886576B1 (en) * | 2012-06-22 | 2014-11-11 | Google Inc. | Automatic label suggestions for albums based on machine learning |
-
2015
- 2015-01-15 CN CN201510020526.0A patent/CN104537502A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
| CN103489117A (en) * | 2012-06-12 | 2014-01-01 | 深圳市腾讯计算机系统有限公司 | Method and system for information releasing |
| US8886576B1 (en) * | 2012-06-22 | 2014-11-11 | Google Inc. | Automatic label suggestions for albums based on machine learning |
| CN102779193A (en) * | 2012-07-16 | 2012-11-14 | 哈尔滨工业大学 | Self-adaptive personalized information retrieval system and method |
| CN103996290A (en) * | 2014-06-09 | 2014-08-20 | 北京东方车云信息技术有限公司 | Taxi service providing method, server and system |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118013A (en) * | 2015-07-29 | 2015-12-02 | 北京嘀嘀无限科技发展有限公司 | Order distributing method and apparatus |
| CN105279688A (en) * | 2015-10-23 | 2016-01-27 | 上海钢富电子商务有限公司 | Order form data processing method and system |
| CN106844367A (en) * | 2015-12-03 | 2017-06-13 | 阿里巴巴集团控股有限公司 | A kind of processing method and processing device of Internet service |
| CN106993330B (en) * | 2016-01-21 | 2021-04-02 | 北京嘀嘀无限科技发展有限公司 | Method and system for allocating call channels |
| CN106993330A (en) * | 2016-01-21 | 2017-07-28 | 滴滴（中国）科技有限公司 | The distribution method and system of talk channel |
| WO2017133149A1 (en) * | 2016-02-06 | 2017-08-10 | 京东方科技集团股份有限公司 | Order processing method, apparatus and system |
| CN107230122A (en) * | 2016-03-25 | 2017-10-03 | 滴滴（中国）科技有限公司 | Passenger calls a taxi order switching method and device |
| CN107230122B (en) * | 2016-03-25 | 2020-10-23 | 滴滴（中国）科技有限公司 | Passenger taxi taking order switching method and device |
| GB2570626A (en) * | 2016-05-23 | 2019-08-07 | Beijing Didi Infinity Technology & Dev Co Ltd | Systems and methods for distributing request for service |
| WO2017202112A1 (en) * | 2016-05-23 | 2017-11-30 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for distributing request for service |
| CN106126880A (en) * | 2016-06-14 | 2016-11-16 | 广州视睿电子科技有限公司 | The system of selection of targeted customer, system and equipment |
| CN109118334B (en) * | 2017-06-01 | 2022-04-01 | 北京星选科技有限公司 | Order processing method and device |
| CN107451878A (en) * | 2017-06-01 | 2017-12-08 | 北京小度信息科技有限公司 | order processing method and device |
| WO2018218946A1 (en) * | 2017-06-01 | 2018-12-06 | 北京小度信息科技有限公司 | Order processing method and device |
| CN109118334A (en) * | 2017-06-01 | 2019-01-01 | 北京小度信息科技有限公司 | order processing method and device |
| CN107203789A (en) * | 2017-06-23 | 2017-09-26 | 北京小度信息科技有限公司 | Distribution model method for building up, distribution method and relevant apparatus |
| CN107358386A (en) * | 2017-06-23 | 2017-11-17 | 镇江五八到家供应链管理服务有限公司 | A kind of shipping driver and the matching process and matching system of order |
| CN107203789B (en) * | 2017-06-23 | 2020-10-02 | 北京星选科技有限公司 | Distribution model establishing method, distribution method and related device |
| CN107357852A (en) * | 2017-06-28 | 2017-11-17 | 镇江五八到家供应链管理服务有限公司 | A kind of determination methods of shipping driver to order wish |
| CN111052158A (en) * | 2017-07-20 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing service requests |
| CN111052158B (en) * | 2017-07-20 | 2023-09-22 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing service requests |
| CN110211369A (en) * | 2017-08-16 | 2019-09-06 | 北京嘀嘀无限科技发展有限公司 | For dispatching the method, equipment and medium of idle transport power |
| CN110520912A (en) * | 2018-03-22 | 2019-11-29 | 东芝存储器株式会社 | Information processing unit, information processing method and message handling program |
| CN111144676A (en) * | 2018-11-05 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Vehicle order distribution method, device, server and computer readable storage medium |
| CN110766505A (en) * | 2018-11-09 | 2020-02-07 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying urgent order requests |
| CN111353676A (en) * | 2018-12-24 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Order distribution method, system, computer device and computer readable storage medium |
| CN111353676B (en) * | 2018-12-24 | 2022-09-09 | 北京嘀嘀无限科技发展有限公司 | Order distribution method, system, computer device and computer readable storage medium |
| CN111476389A (en) * | 2019-01-24 | 2020-07-31 | 北京嘀嘀无限科技发展有限公司 | Method and device for pre-estimating order receiving waiting time |
| CN109886603B (en) * | 2019-03-12 | 2020-11-06 | 北京同城必应科技有限公司 | Order pushing method, device, equipment and storage medium |
| CN109886603A (en) * | 2019-03-12 | 2019-06-14 | 北京同城必应科技有限公司 | Order method for pushing, device, equipment and storage medium |
| WO2020244081A1 (en) * | 2019-06-05 | 2020-12-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | Constrained spatiotemporal contextual bandits for real-time ride-hailing recommendation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104537502A (en) | Method and device for processing orders | |
| CN104715285A (en) | Method and equipment for processing orders | |
| CN104867065A (en) | Method and equipment for processing orders | |
| CN103959282B (en) | For the selective feedback of text recognition system | |
| CN104737565B (en) | Method about the to-be of prediction mobile device users | |
| CN104657933A (en) | Method and equipment for informing order supply and demand density | |
| CN104574947A (en) | Order handling method and equipment | |
| CN107491825A (en) | A kind of about car processing method and system | |
| CN104794889A (en) | Method and equipment for pushing order forms | |
| CN109947989B (en) | Method and apparatus for processing video | |
| CN110086877A (en) | Application program sharing, sharing information display methods, device, equipment and medium | |
| CN111753551B (en) | Information generation method and device based on word vector generation model | |
| US9521522B2 (en) | Mobile apparatus with search function | |
| CN112070310A (en) | Loss user prediction method and device based on artificial intelligence and electronic equipment | |
| CN111459569A (en) | Fast traffic method, device, electronic equipment and storage medium | |
| CN110573837A (en) | Navigation method, navigation device, storage medium and server | |
| CN105300398A (en) | Method, device and system for acquiring site information | |
| CN108140055A (en) | Trigger application message | |
| CN113392018A (en) | Traffic distribution method, traffic distribution device, storage medium, and electronic device | |
| CN110751395B (en) | Passenger journey state determining method, device and server | |
| CN104778554A (en) | Method and device for identifying multiple matched users | |
| CN104599218A (en) | Method and device used for determining order reception range | |
| CN116894188A (en) | Service tag set updating method and device, medium and electronic equipment | |
| CN113868538B (en) | Information processing method, device, equipment and medium | |
| CN111369029A (en) | Service selection prediction method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150422 |