CN104599002B - Method and equipment for predicting order value - Google Patents
Method and equipment for predicting order value Download PDFInfo
- Publication number
- CN104599002B CN104599002B CN201510079224.0A CN201510079224A CN104599002B CN 104599002 B CN104599002 B CN 104599002B CN 201510079224 A CN201510079224 A CN 201510079224A CN 104599002 B CN104599002 B CN 104599002B
- Authority
- CN
- China
- Prior art keywords
- order
- value
- new
- historical
- user
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
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 disclosure discloses a method and equipment for predicting order value, wherein the method comprises the following steps: acquiring characteristics associated with order value in historical orders; generating a mapping model of the features and the order value; and predicting the order value of the new order based on the mapping model and the data of the new order. According to the embodiment of the disclosure, the problem that the taxi system in the related technology is difficult to sensitively and accurately estimate the order data of the system independently of the map can be solved.
Description
Technical Field
The embodiment of the disclosure relates to the field of system prediction, in particular to a method and equipment for predicting order value.
Background
At present, along with the improvement of living standard of people, the use amount of taxis is larger and larger, and urban taxis become important transportation means. With the popularization of intelligent devices, particularly intelligent navigation and smart phones, the use of taxi system platforms is more and more common, and great convenience is brought to people going out.
On a taxi system platform, due to the information asymmetry problem between a taxi driver and a passenger, the value of an order placed by a user needs to be estimated, wherein the value of the order comprises mileage and price information. The mileage and price information of the existing taxi system usually depends on map software, so the requirement on map data is high. And the prediction system based on map data cannot take into account the influence of other unpredictable factors, such as the complex situations of working days, rush hours, core road section traffic conditions and weather. Therefore, it is necessary to design and develop a method for accurately estimating the order in the taxi system independently of the map data.
Disclosure of Invention
The embodiment of the disclosure aims to provide a method and equipment for predicting order value, which can solve the problem that in the related art, a taxi system is difficult to sensitively and accurately predict order data of the system independently of a map.
According to one aspect of the present disclosure, there is provided a method of predicting order value, comprising: acquiring characteristics associated with order value in historical orders; generating a mapping model of the features and the order value; and predicting the order value of the new order based on the mapping model and the data of the new order.
In one embodiment, the method further comprises: and updating the mapping model by using the data of the new order.
In one embodiment, the characteristic associated with the order price value comprises at least one of: user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time.
In one embodiment, predicting the order value of the new order based on the mapping model and the data of the new order comprises: extracting features of the new order associated with order value; and determining the order value of the new order based on the characteristics of the new order and the mapping model.
In one embodiment, predicting the order value of the new order based on the mapping model and the data of the new order comprises: determining an order price value for the new order as an average of order values of historical orders associated with the new order.
In one embodiment, predicting the order value of the new order based on the mapping model and the data of the new order comprises: determining the order price value of the new order as a weighted average of order values of historical orders associated with the new order.
In one embodiment, the historical order is determined to be associated with the new order when a distance metric between the new order and a feature of the historical order is less than a threshold.
In one embodiment, the distance metric includes a mahalanobis distance and a euclidean distance.
In one embodiment, the threshold is set according to a gaussian distribution.
According to another aspect of an embodiment of the present disclosure, an apparatus for predicting order value is presented. The apparatus comprises: acquiring means configured to acquire a feature associated with an order value in a historical order; generating means configured to generate a mapping model of the features to the order value; and predicting means configured to predict an order value of a new order based on the mapping model and data of the new order.
In one embodiment, the apparatus further comprises: an updating device configured to update the mapping model with data of a new order.
In one embodiment, the characteristic associated with the order price value comprises at least one of: user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time.
In one embodiment, the prediction means comprises: an extraction module configured to extract features of the new order associated with an order value; and a determination module configured to determine an order value for the new order based on the characteristics of the new order and the mapping model.
In one embodiment, the prediction apparatus is configured to: determining an order price value for the new order as an average of order values of historical orders associated with the new order.
In one embodiment, the prediction apparatus is configured to: determining the order price value of the new order as a weighted average of order values of historical orders associated with the new order.
In one embodiment, the prediction apparatus is further configured to: determining that the historical order is associated with the new order when a distance metric between the new order and a feature of the historical order is less than a threshold.
In one embodiment, the distance metric includes a mahalanobis distance and a euclidean distance.
In one embodiment, the prediction means is further configured to set said threshold according to a gaussian distribution.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of predicting order value in accordance with an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating an implementation of a system for predicting order value according to FIG. 1; and
fig. 3 is a block diagram illustrating a structure of an apparatus for predicting order value according to an embodiment of the present disclosure.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a flowchart illustrating a method 100 of predicting order value according to an embodiment of the present disclosure, which includes steps S101 to S103 as follows.
As shown in FIG. 1, in step S101, characteristics associated with order value in a historical order are obtained. In step S102, a mapping model of the features and the order value is generated. Then, in step S103, an order value of the new order is predicted based on the mapping model and data of the new order. In one example, the order value includes mileage and price information
In the existing taxi platform system, as the number of users is increased, the taxi platform system accumulates a great amount of order information. The order information includes various information such as a departure place, a destination, departure time, mileage, and price. Therefore, the taxi platform system can establish a mathematical model through the acquired historical order data.
At step S101, the characteristics associated with the order value include at least one of: user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time, etc.
The set of order characteristics may be represented by the following equation,
Oi＝{sxi，syi，exi，eyi，ti} (formula 1)
Wherein i is 1, 2, 3. O isiA feature set representing an ith order; sx represents the order origin longitude; sy represents the starting point latitude of the order; ex represents the order end point longitude; ey represents the order terminal latitude and t represents the order start time.
At step S101, after obtaining the characteristics of a large number of orders, a mapping model of the characteristics and the order value is established, for example, a mapping relation { D between mileage of the order and the characteristics of the order is established respectivelyi，OiAnd a mapping (P) between the price of an order and the characteristics of the orderi，OiIn which D isiIndicating mileage of the ith order, PiIndicating the price of the ith order, OiIndicating the characteristics of the ith order.
Moreover, the method 100 may also update the mapping model with data for the new order. In one embodiment, the processing of the historical data by steps S101 and S102 may be performed offline.
In step S103, a new order is input to the taxi platform system, and the taxi system needs to predict the value of the new order. Wherein predicting the value of the new order based on the mapping model and the data of the new order comprises: extracting features of the new order associated with order value; and determining the order value of the new order based on the characteristics of the new order and the mapping model.
In one example, the characteristics of the new order sent by the user are extracted as:
Op＝{sxp，syp，exp，eyp，tp} (formula 2)
OpA feature set representing a new order; sx represents the order origin longitude; sy represents the starting point latitude of the order; ex represents the order end point longitude; ey represents the order terminal latitude and t represents the order start time.
In one embodiment, predicting the order value of the new order based on the mapping model and the data of the new order comprises: determining an order price value for the new order as an average of order values of historical orders associated with the new order.
For example, the mileage and price of a new order are shown as follows:
Wherein DpMileage representing new orders, PpIndicating the price of the new order, OpFeatures indicating new orders, OjFeatures indicating the jth order, DjIndicating mileage of the jth order, PjRepresents the price of the jth order, ω (O)p，Oj) A distance metric is represented, where the distance metric may include mahalanobis distance and euclidean distance, W being a constant value.
The euclidean distance is a commonly used distance definition, referring to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The euclidean distance in two and three dimensions is the actual distance between two points.
Mahalanobis distance is a covariance distance representing data. The method is an effective method for calculating the similarity of two unknown sample sets. Unlike euclidean distance, it allows for a link between various characteristics (e.g., start of order information may lead to user order start time related information, as both are related) and is scale-independent, i.e., independent of measurement scale.
As can be seen from (equation 5), when the distance metric between the new order and the characteristics of the historical orders is smaller than the set threshold, it is determined that the historical orders are associated with the new order, i.e., the value of the new order is calculated by these associated orders. The value of W in (equation 5) may be set by a gaussian distribution, that is, by determining the data value of the above-described mahalanobis distance or euclidean distance maximum probability distribution.
As can be seen from (equation 3) - (equation 5), in this embodiment, the value of the order data associated with the new order is 1, and the mileage and the price of the new order are calculated by using the average values of the order data.
In some cases, considering the weighting values makes the prediction more accurate, since historical orders are more closely related to new orders. For example, after determining that the mahalanobis or euclidean distance between the new order and the characteristics of the historical order is less than the set threshold, it may be set that the mahalanobis or euclidean distance is a different value, and the weighting value is taken differently, for example, to be the maximum when the starting and ending points of the historical order are the same as the new order. Considering different weight values may make the order prediction more accurate.
Thus, in one embodiment, the order price value is determined as a weighted average of the mileage and price of the historical order associated with the new order.
FIG. 2 is a schematic diagram illustrating an implementation of the system for predicting order value according to FIG. 1. As shown, a user takes a taxi via taxi platform system 201, accumulating historical order data. Thus, the order aggregation data 202 includes a large amount of historical order data.
According to one embodiment of the present disclosure, the forecasting system 203 comprises a system for forecasting order value. The forecasting system 203 forecasts the mileage and price of the new order by combining the historical order data and the new order data, and the forecasting process comprises the following steps: acquiring characteristics associated with order value in historical orders; generating a mapping model of the features and the order value; and predicting the order value of the new order based on the mapping model and the data of the new order.
The forecasting system 203 then feeds back the forecasted mileage and price for the new order to the user.
Fig. 3 is a block diagram illustrating a structure of an apparatus 300 for predicting order value according to an embodiment of the present disclosure.
The apparatus 300 comprises an obtaining device 301 configured to obtain a feature associated with an order value in a historical order; a generating device 302 configured to generate a mapping model of the features and the order value; and a predicting means 303 configured to predict an order value of a new order based on the mapping model and data of the new order.
In one embodiment, the apparatus 300 further comprises: the updating means is configured to update the mapping model with data of a new order.
In one embodiment, the characteristics associated with the order price value include at least one of: user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time.
In one embodiment, the predicting means 303 comprises: an extraction module configured to extract features of the new order associated with an order value; and a determination module configured to determine an order value for the new order based on the characteristics of the new order and the mapping model.
In one embodiment, the forecasting device 303 is further configured to determine the order price value of the new order as an average of order values of historical orders associated with the new order.
In one embodiment, the forecasting device 303 is further configured to determine the order price value of the new order as a weighted average of order values of historical orders associated with the new order.
In one embodiment, the predicting means 303 is further configured to: determining that the historical order is associated with the new order when a distance metric between the new order and a feature of the historical order is less than a threshold.
In one embodiment, the distance metric includes a mahalanobis distance and a euclidean distance.
In one embodiment, the predicting means 303 is further configured to set the threshold according to a gaussian distribution.
It will be apparent to those skilled in the art that the modules or steps of the present disclosure described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed over a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or they may be separately fabricated into various integrated circuit modules, or multiple modules or steps thereof may be fabricated into a single integrated circuit module. As such, the present disclosure is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. A method of predicting order value, comprising:
acquiring a characteristic in a historical order associated with an order value, wherein the order value comprises driving mileage;
generating a mapping model of the features and the order value; and
predicting the order value of the new order based on the mapping model and the data of the new order;
updating the mapping model by using the data of the new order;
wherein predicting an order value for a new order based on the mapping model and data for the new order comprises:
determining that a historical order is associated with the new order in response to a distance metric between the new order and a feature of the historical order being less than a threshold;
determining a unit price value of the new order as an average of order values of the historical orders associated with the new order;
wherein the characteristics associated with order value include at least one of:
user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time.
2. The method of claim 1, wherein predicting an order value for a new order based on the mapping model and data for the new order further comprises:
extracting features of the new order associated with an order value.
3. The method of claim 1, wherein the average of the order values of the historical orders is a weighted average of the order values of the historical orders.
4. The method of claim 1, wherein the distance metric comprises mahalanobis distance and euclidean distance.
5. The method of claim 1, wherein the threshold is set according to a gaussian distribution.
6. An apparatus for predicting order value, comprising:
an acquisition device configured to acquire a feature in a historical order associated with an order value, wherein the order value comprises mileage;
generating means configured to generate a mapping model of the features to the order value; and
a prediction device configured to predict an order value of a new order based on the mapping model and data of the new order;
an updating device configured to update the mapping model with data of a new order;
wherein the prediction apparatus is configured to:
determining that a historical order is associated with the new order in response to a distance metric between the new order and a feature of the historical order being less than a threshold;
determining a unit price value of the new order as an average of order values of the historical orders associated with the new order;
wherein the characteristics associated with order value include at least one of:
user order starting point longitude, user order starting point latitude, user order ending point longitude, user order ending point latitude, and user order starting time.
7. The apparatus of claim 6, wherein the predicting means further comprises:
an extraction module configured to extract features of the new order associated with an order value.
8. The apparatus of claim 6, wherein the average of the order values of the historical orders is a weighted average of the order values of the historical orders.
9. The apparatus of claim 6, wherein the distance metric comprises a mahalanobis distance and a euclidean distance.
10. The apparatus of claim 6, wherein the predicting means is further configured to set the threshold according to a Gaussian distribution.
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510079224.0A CN104599002B (en) | 2015-02-13 | 2015-02-13 | Method and equipment for predicting order value |
| US15/533,994 US20170364933A1 (en) | 2014-12-09 | 2015-12-09 | User maintenance system and method |
| GB1709115.8A GB2547395A (en) | 2014-12-09 | 2015-12-09 | User maintenance system and method |
| SG11201704715YA SG11201704715YA (en) | 2014-12-09 | 2015-12-09 | User maintenance system and method |
| PCT/CN2015/096820 WO2016091173A1 (en) | 2014-12-09 | 2015-12-09 | User maintenance system and method |
| PH12017501080A PH12017501080A1 (en) | 2014-12-09 | 2017-06-08 | User maintenance system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510079224.0A CN104599002B (en) | 2015-02-13 | 2015-02-13 | Method and equipment for predicting order value |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104599002A CN104599002A (en) | 2015-05-06 |
| CN104599002B true CN104599002B (en) | 2020-10-13 |
Family
ID=53124770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510079224.0A Active CN104599002B (en) | 2014-12-09 | 2015-02-13 | Method and equipment for predicting order value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104599002B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016091173A1 (en) * | 2014-12-09 | 2016-06-16 | 北京嘀嘀无限科技发展有限公司 | User maintenance system and method |
| CN109716383A (en) * | 2017-06-05 | 2019-05-03 | 北京嘀嘀无限科技发展有限公司 | The system and method for carrying out price estimation using machine learning techniques |
| AU2018282300B2 (en) | 2017-06-16 | 2020-11-12 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for allocating service requests |
| CN109146211A (en) * | 2017-06-16 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | The distribution of order, the training method of model and device |
| WO2019201344A1 (en) * | 2018-04-19 | 2019-10-24 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for transport pricing |
| CN111260103A (en) * | 2018-11-30 | 2020-06-09 | 北京嘀嘀无限科技发展有限公司 | Order information dynamic adjustment method and device |
| CN109508461A (en) * | 2018-12-29 | 2019-03-22 | 重庆猪八戒网络有限公司 | Order price prediction technique, terminal and medium based on Chinese natural language processing |
| CN113139803A (en) * | 2021-04-08 | 2021-07-20 | 北京京东振世信息技术有限公司 | Order information generation method and device, electronic equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298737A (en) * | 2011-08-16 | 2011-12-28 | 上海交通大学 | Customer commitment-oriented order management system and method thereof |
| CN103188598A (en) * | 2011-12-27 | 2013-07-03 | 中国电信股份有限公司 | Intelligent group call answer taxi appointment method, intelligent group call answer taxi appointment system and taxi appointment platform |
| US20140101024A1 (en) * | 2012-10-04 | 2014-04-10 | Sap Ag | Predicting financial outcome |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002037219A2 (en) * | 2000-11-02 | 2002-05-10 | Cybersource Corporation | Method and apparatus for evaluating fraud risk in an electronic commerce transaction |
| CN103310286A (en) * | 2013-06-25 | 2013-09-18 | 浙江大学 | Product order prediction method and device with time series characteristics |
| CN103942433A (en) * | 2014-04-21 | 2014-07-23 | 南京市测绘勘察研究院有限公司 | Building settlement prediction method based on historical data analysis |
| CN103984998A (en) * | 2014-05-30 | 2014-08-13 | 成都德迈安科技有限公司 | Sale forecasting method based on big data mining of cloud service platform |
-
2015
- 2015-02-13 CN CN201510079224.0A patent/CN104599002B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298737A (en) * | 2011-08-16 | 2011-12-28 | 上海交通大学 | Customer commitment-oriented order management system and method thereof |
| CN103188598A (en) * | 2011-12-27 | 2013-07-03 | 中国电信股份有限公司 | Intelligent group call answer taxi appointment method, intelligent group call answer taxi appointment system and taxi appointment platform |
| US20140101024A1 (en) * | 2012-10-04 | 2014-04-10 | Sap Ag | Predicting financial outcome |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104599002A (en) | 2015-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104599002B (en) | Method and equipment for predicting order value | |
| CN109658033B (en) | Method, system, device and storage medium for calculating similarity of goods source route | |
| CN108399564B (en) | Credit scoring method and device | |
| CN109308538B (en) | Method and device for predicting transaction conversion rate | |
| CN111435088A (en) | Road matching method and device, electronic equipment and storage medium | |
| CN107341166B (en) | Recommendation method and system for vehicle-mounted APP | |
| JP2017228091A (en) | Walking state learning method, walking state estimation method, road surface condition comprehension method, device and program | |
| CN112509317B (en) | Bus real-time arrival prediction method, device and equipment based on machine learning algorithm | |
| CN111476389A (en) | Method and device for pre-estimating order receiving waiting time | |
| CN116030617A (en) | Method and device for predicting traffic flow based on road OD data | |
| CN108665723B (en) | Information acquisition method and device | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN110751395B (en) | Passenger journey state determining method, device and server | |
| CN110674208A (en) | Method and device for determining position information of user | |
| CN111613052B (en) | Traffic condition determining method and device, electronic equipment and storage medium | |
| CN113284337B (en) | OD matrix calculation method and device based on vehicle track multidimensional data | |
| CN112685531B (en) | Vehicle matching method and device, computing device and computer-readable storage medium | |
| CN110837903A (en) | Rail transit short-term passenger flow prediction method and system and electronic equipment | |
| CN111310961A (en) | Data prediction method, data prediction device, electronic equipment and computer readable storage medium | |
| CN115206102A (en) | Method, apparatus, electronic device, and medium for determining traffic path | |
| CN112926630B (en) | Route planning method, route planning device, electronic equipment and computer readable medium | |
| CN113689125A (en) | Information pushing method and device | |
| CN111105284B (en) | Order processing method and device, M-layer order processing model, electronic equipment and storage medium | |
| CN110146102B (en) | Path planning method, device, equipment and storage medium | |
| CN113051490A (en) | Newly added interest point prediction model training method and device and newly added interest point prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |