CN105719145B - Method and device for acquiring commodity arrival time - Google Patents
Method and device for acquiring commodity arrival time Download PDFInfo
- Publication number
- CN105719145B CN105719145B CN201410735060.8A CN201410735060A CN105719145B CN 105719145 B CN105719145 B CN 105719145B CN 201410735060 A CN201410735060 A CN 201410735060A CN 105719145 B CN105719145 B CN 105719145B
- Authority
- CN
- China
- Prior art keywords
- commodity
- information
- preset
- arrival time
- current
- 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
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
- G06Q30/00—Commerce
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for acquiring commodity arrival time, and belongs to the technical field of computer communication. The method comprises the following steps: acquiring login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a preset first time period; extracting current buyer-side characteristic information from the login information of the current buyer side, and extracting preset characteristic information from the first transaction log information; and according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, carrying out predictive calculation on the commodity arrival time from the selling end to the current buying end to obtain the commodity arrival time. The device comprises: the device comprises a first obtaining module, a first extracting module and a first predicting module. The invention improves the accuracy of the commodity arrival time.
Description
Technical Field
The invention relates to the technical field of computer communication, in particular to a method and a device for acquiring commodity arrival time.
Background
With the development of computer communication technology, more and more users buy commodities via the network, and when buying commodities via the network, in addition to paying attention to the efficacy and quality of the commodities, the arrival time of the commodities is also more concerned by the users.
However, in the current commodity transaction system, the method of obtaining the commodity arrival time is that the buying end obtains the commodity arrival time estimated by the selling end through inquiry; or the buying end obtains the goods arrival time of the sale end for taking promise according to the guarantee express delivery information of the sale end.
The existing method for acquiring the arrival time of the commodity is obtained by manually estimating or committing at a seller, and the accuracy of the acquired arrival time of the commodity is very low.
Disclosure of Invention
The invention aims to solve the technical problem that the accuracy of commodity arrival time obtained by the prior art is very low. In order to solve the technical problem, the invention provides a method and a device for acquiring the commodity arrival time, the commodity arrival time from a selling end to a current purchasing end is predicted and calculated according to the characteristic information of the current purchasing end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current purchasing end can be intuitively reflected by the characteristic information of the current purchasing end, the actual condition of the selling end can be intuitively reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved.
In order to solve the above problems, the present invention discloses a method for obtaining the arrival time of a commodity, which comprises:
acquiring login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a preset first time period;
extracting current buyer-side characteristic information from the login information of the current buyer side, and extracting preset characteristic information from the first transaction log information;
and according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, carrying out predictive calculation on the commodity arrival time from the selling end to the current buying end to obtain the commodity arrival time.
Further, before obtaining the login information of the current buyer end of the login commodity transaction system, the method further comprises:
acquiring second transaction log information of the selling end in a preset second time period;
dividing the second transaction log information into two parts, and extracting the preset characteristic information and the actual commodity arrival time from the first part of the second transaction log information;
and taking the preset feature information extracted from the first transaction log information and the actual commodity arrival time as training data, and training the training data through a regression training model established by using a regression prediction method to obtain the feature weight corresponding to the preset feature information.
Further, the regression prediction method comprises the following steps: a hybrid logistic regression method, a gradient boosting decision tree method, or a logistic regression method.
Further, after obtaining the feature weight corresponding to the preset feature information, the method further includes:
extracting the preset characteristic information and the actual commodity arrival time from a second transaction log information;
taking the preset feature information extracted from the second transaction log information as prediction data, and performing prediction calculation on the prediction data through a regression prediction model according to feature weight corresponding to the preset feature information to obtain the predicted commodity arrival time;
according to the actual commodity arrival time extracted from the second transaction log information, estimating the predicted commodity arrival time through a regression estimation model to obtain an estimation result;
and judging whether the regression training model is adjusted or not according to the evaluation result.
Further, after obtaining the arrival time of the goods, the method further comprises:
and displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity search page associated with the selling end.
Further, after obtaining the arrival time of the goods, the method further comprises:
taking the commodity arrival time as logistics capacity data of the selling end;
and determining the sequence of the commodities associated with the selling end in the commodity search result according to the logistics capacity data.
Further, according to the characteristic information of the current buying end, the preset characteristic information and the pre-obtained characteristic weight, performing predictive calculation on the commodity arrival time from the selling end to the current buying end to obtain the commodity arrival time, and the method comprises the following steps:
normalizing the current buyer-side characteristic value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
normalizing the preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information with the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain commodity arrival normalization time;
and multiplying the normalized commodity arrival time by a preset arrival time threshold value to obtain the commodity arrival time.
Further, the preset feature information includes: the system comprises seller-side characteristic information, transaction-side characteristic information of all transaction-sides transacting with the seller-side, commodity characteristic information and/or order characteristic information.
In order to solve the above problem, the present invention also discloses a device for acquiring the arrival time of a commodity, the device comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a preset first time period;
the first extraction module is used for extracting characteristic information of the current purchasing end from the login information of the current purchasing end and extracting preset characteristic information from the first transaction log information;
and the first prediction module is used for predicting and calculating the commodity arrival time from the selling end to the current purchasing end according to the current purchasing end characteristic information, the preset characteristic information and the pre-acquired characteristic weight to obtain the commodity arrival time.
Further, the apparatus further comprises:
the second acquisition module is used for acquiring second transaction log information of the selling terminal in a preset second time period before acquiring the login information of the current buying terminal of the commodity transaction system;
the second extraction module is used for dividing the second transaction log information into two parts and extracting the preset characteristic information and the actual commodity arrival time from the first part of the second transaction log information;
and the training module is used for taking the preset feature information and the actual commodity arrival time extracted from the first transaction log information as training data, and training the training data through a regression training model established by a regression prediction device to obtain the feature weight corresponding to the preset feature information.
Further, the regression prediction method comprises the following steps: a hybrid logistic regression method, a gradient boosting decision tree method, or a logistic regression method.
Further, the apparatus further comprises:
the third extraction module is used for extracting the preset characteristic information and the actual commodity arrival time from a second transaction log information;
the second prediction module is used for taking the preset feature information extracted from the second transaction log information as prediction data, and performing prediction calculation on the prediction data through a regression prediction model according to the feature weight corresponding to the preset feature information to obtain the predicted commodity arrival time;
the evaluation module is used for evaluating the predicted commodity arrival time through a regression evaluation model according to the actual commodity arrival time extracted from the second transaction log information to obtain an evaluation result;
and the judging module is used for judging whether to adjust the regression training model according to the evaluation result.
Further, the apparatus further comprises:
and the display module is used for displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity search page associated with the selling end.
Further, after obtaining the arrival time of the goods, the device further comprises:
the processing module is used for taking the commodity arrival time as the logistics capacity data of the selling end;
and the determining module is used for determining the sequence of the commodities associated with the selling end in the commodity search result according to the logistics capacity data.
Further, the first prediction module comprises:
the first processing unit is used for carrying out normalization processing on the current buyer-side characteristic numerical value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
the second processing unit is used for carrying out normalization processing on a preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
the third processing unit is used for adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information with the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain the commodity arrival normalization time;
and the acquisition unit is used for multiplying the normalized commodity arrival time by a preset arrival time threshold value to obtain the commodity arrival time.
Further, the preset feature information includes: the system comprises seller-side characteristic information, transaction-side characteristic information of all transaction-sides transacting with the seller-side, commodity characteristic information and/or order characteristic information.
Compared with the prior art, the invention can obtain the following technical effects:
1) the commodity arrival time from the selling end to the current buying end is predicted and calculated according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current buying end can be visually reflected by the characteristic information of the current buying end, the actual condition of the selling end can be visually reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved.
2) And displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity search page associated with the selling end, so that the purchasing end can visually acquire the commodity arrival time and make a purchasing decision.
3) And taking the commodity arrival time as logistics capacity data of the selling end, determining the sequence of commodities related to the selling end in a commodity search result according to the logistics capacity data, and supporting searching for time sequence.
4) Training the training data by using a regression training model established by a regression prediction method to obtain the characteristic weight corresponding to the preset characteristic information, wherein the accuracy of the obtained characteristic weight is higher, and the accuracy of the predicted commodity arrival time can be improved.
5) According to the actual commodity arrival time, the predicted commodity arrival time is evaluated through the regression evaluation model, and the accuracy of the predicted commodity arrival time can be guaranteed.
Of course, it is not necessary for any one product in which the invention is practiced to achieve all of the above-described technical effects simultaneously.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a method for obtaining a commodity arrival time according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for obtaining a commodity arrival time according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for obtaining a commodity arrival time according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a first apparatus for obtaining a commodity arrival time according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a second apparatus for obtaining a commodity arrival time according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a third apparatus for obtaining a commodity arrival time according to a fourth embodiment of the present invention;
fig. 7 is a schematic structural diagram of a fourth apparatus for obtaining a commodity arrival time according to a fourth embodiment of the present invention;
fig. 8 is a schematic structural diagram of a fifth apparatus for acquiring a commodity arrival time according to a fourth embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the accompanying drawings and examples, so that how to implement the embodiments of the present invention by using technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
As used in the specification and in the claims, certain terms are used to refer to particular components. As one skilled in the art will appreciate, manufacturers may refer to a component by different names. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. "substantially" means within an acceptable error range, and a person skilled in the art can solve the technical problem within a certain error range to substantially achieve the technical effect. Furthermore, the term "coupled" is intended to encompass any direct or indirect electrical coupling. Thus, if a first device couples to a second device, that connection may be through a direct electrical coupling or through an indirect electrical coupling via other devices and couplings. The following description is of the preferred embodiment for carrying out the invention, and is made for the purpose of illustrating the general principles of the invention and not for the purpose of limiting the scope of the invention. The scope of the present invention is defined by the appended claims.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
Example one
Fig. 1 is a method for obtaining a commodity arrival time according to an embodiment of the present invention; as shown in fig. 1, it may specifically include:
s101: the method comprises the steps of obtaining login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a preset first time period.
The commodity transaction system is a system capable of providing a network commodity purchasing service. The current buyer can log in through a webpage provided by the commodity transaction system. The system can be registered as a member in advance, and can log in through the member identity, and can also directly log in with the common identity. When logging in with the member identity, the obtained login information may include the name, ID number, IP address, login time, etc. of the current buyer. When logging in with a common identity, the obtained login information may include an IP address of the current buyer, login time, and the like.
The selling end associated with the current buying end can be a selling end displayed in a login page of the current buying end after the current buying end logs in, a selling end obtained by searching after the current buying end logs in, and the like.
The preset first time period may be a preset time period before the preset current customer login time, and if the preset first time period is 50 days before the current customer login time and the current customer login time is 2014-5-1, the preset first time period is 2014-3-12 to 2014-4-30. The size of the first time period may be set according to an actual application condition, and is not particularly limited.
Specifically, acquiring the first transaction log information may implement generation and collection of the transaction log by causing the browser to execute a data collection script or the like.
S102: and extracting the characteristic information of the current purchasing end from the login information of the current purchasing end, and extracting preset characteristic information from the first transaction log information.
The current buyer characteristic information may include the location of the current buyer, the historical payment time information of the current buyer, and the like.
The preset characteristic information comprises seller-end characteristic information, transaction buyer-end characteristic information of all transaction buyers transacting with the seller-end, commodity characteristic information and/or order characteristic information. The vendor characteristic information may include a vendor location, a vendor monthly volume, vendor shipping capacity evaluation data, vendor order taking time, vendor selected logistics company capacity data, vendor shipping time, commodity transportation time, and the like. The transaction-buyer-side characteristic information may include a location of the transaction-buyer side, historical payment time information of the transaction-buyer side, and the like. The commodity characteristic information may include commodity price, commodity category, commodity sales amount, and the like. The order characteristic information comprises commodity arrival time and the like corresponding to the order.
Specifically, in order to facilitate calculation of the arrival time of the commodity, a corresponding current buyer-side characteristic value is set for the current buyer-side characteristic information in advance, and a corresponding preset characteristic value is set for the preset characteristic information. For example: the city number can be set according to the position of the current buying end and the city where the position of the selling end is located, the city number corresponding to the position of the current buying end is used as the characteristic numerical value of the position of the current buying end, and the city number corresponding to the position of the selling end is used as the characteristic numerical value of the position of the selling end. Another example is: the commodity arrival time corresponding to the order can be directly used as the characteristic numerical value of the commodity arrival time corresponding to the order. The current buyer-side characteristic value corresponding to the current buyer-side characteristic information and the preset characteristic value corresponding to the preset characteristic information can be set according to the actual application condition, and no specific limitation is made on the preset characteristic value.
S103: and according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, carrying out prediction calculation on the commodity arrival time from the selling end to the current buying end to obtain the commodity arrival time.
The commodity arrival time comprises the time length required by the commodity from the selling end to the current purchasing end, the date when the commodity arrives at the current purchasing end and the like.
Specifically, according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time from the selling end to the current buying end is subjected to prediction calculation to obtain the commodity arrival time, and the method comprises the following steps:
normalizing the current buyer-side characteristic value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
normalizing the preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information and the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain the commodity arrival normalization time;
and multiplying the normalized time of commodity arrival with a preset arrival time threshold value to obtain the commodity arrival time.
The preset normalization formula is as follows:
f(χ)＝1/(1+e-x)
and the chi represents a current buyer end characteristic numerical value corresponding to the current buyer end characteristic information or represents a preset characteristic numerical value corresponding to the preset characteristic information. f (x) represents the current buyer-side characteristic normalization value or the preset characteristic normalization value.
Specifically, the purpose of normalizing the current buyer-side characteristic value corresponding to the current buyer-side characteristic information and the preset characteristic value corresponding to the preset characteristic information is to enable different characteristic values to have the same characteristic dimension, so that the problem that convergence cannot be achieved when an optimal value is solved through gradient reduction in the subsequent process of determining the weight value corresponding to the characteristic information is solved.
The preset arrival time threshold may be set according to the maximum time from one selling end to one buying end in the actual purchase, or may be set according to the maximum commodity arrival time required by the commodity transaction system, and if the time of 10 days in the current actual purchase is enough to be from any selling end to any buying end, or the maximum commodity arrival time required by the commodity transaction system is 10 days, the arrival time threshold may be set to 10 × 24 — 240 hours. The time threshold of arrival is not limited to 240 hours, and may be flexibly set according to the actual application condition, which is not limited to this.
Specifically, the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information is added to the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain the commodity arrival normalization time Score, which is as follows:
wherein K represents the number of the characteristic information of the current purchasing end, xkRepresenting the current buyer end characteristic corresponding to the kth current buyer end characteristic informationNumerical value, f (χ)k) Representing the characteristic normalization value of the kth current purchasing end, and omega (k) representing the characteristic weight corresponding to the characteristic information of the kth current purchasing end; m represents the number of preset feature information, χmA preset characteristic value, f (χ), corresponding to the mth preset characteristic informationm) And the m-th preset feature normalized value is represented, and omega (m) represents the feature weight corresponding to the m-th preset feature information.
It should be noted that the feature weight corresponding to the current buyer-side feature information may be set according to the feature weight corresponding to the transaction buyer-side feature information of all transaction buyers transacting with the seller-side in the preset feature information.
Specifically, after the arrival time of the commodity is obtained, the method further comprises the following steps:
displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity searching page related to a selling end; or the like, or, alternatively,
taking the commodity arrival time as logistics capacity data of a selling end;
and determining the ordering of the commodities associated with the selling end in the commodity search result according to the logistics capacity data.
Specifically, after the arrival time of the commodity is obtained, the Delivery is updated (the commodity online server provides data such as attributes of some commodities), the arrival time of the commodity is used as logistics capacity data of the selling end, and according to the logistics capacity data, the sequence of the commodity related to the selling end in the commodity search result is determined so as to influence the online display of the commodity.
According to the method for acquiring the commodity arrival time, the commodity arrival time from the selling end to the current buying end is predicted and calculated according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current buying end can be visually reflected by the characteristic information of the current buying end, the actual condition of the selling end can be visually reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved. And displaying the commodity arrival time on a commodity detail page, a commodity ordering page, a commodity logistics detail page and/or a commodity searching page associated with the selling end, so that the purchasing end can visually acquire the commodity arrival time and make a purchasing decision. The commodity arrival time is used as logistics capacity data of the selling end, the sorting of commodities related to the selling end in the commodity searching result is determined according to the logistics capacity data, and searching can be supported for time sorting.
Example two
Fig. 2 is a method for obtaining a commodity arrival time according to a second embodiment of the present invention; before the first embodiment S101 obtains the login information of the current buyer of the login commodity transaction system, as shown in fig. 2, it may further specifically include:
s104: and acquiring second transaction log information of the selling end in a preset second time period.
The preset second time period may be a preset time period before the second transaction log information is acquired, and if the preset second time period is within 50 days before the second transaction log information is acquired, the time for acquiring the second transaction log information is 2014-2-28, and the preset second time period is 2014-1-9 to 2014-2-27. The size of the second time period may be set according to an actual application condition, and is not particularly limited. The size of the second time period may be the same as or different from the size of the first time period.
Specifically, in order to enable the first embodiment S103 to obtain the arrival time of the commodity according to the feature weight obtained in advance, the first embodiment S103 may obtain and train the second transaction log information of the seller in advance to obtain the feature weight.
S105: and dividing the second transaction log information into two parts, and extracting preset characteristic information and actual commodity arrival time from the first part of the second transaction log information.
Specifically, the second transaction log information is divided into two parts, one part is used for training to obtain the characteristic weight, and the other part is used for evaluating the obtained characteristic weight so as to verify the accuracy of the characteristic weight.
Specifically, the second transaction log information may be divided into two parts, which may be an average of the second transaction log information divided into two parts, each part including half of the second transaction log information. The second transaction log information may also be divided into two parts according to other proportions according to the actual application condition, which is not specifically limited. In the following description, the first and second shares are used for description, and the processing is performed based on the first share of the second transaction log information in steps S105 to S106, and the processing is performed based on the second share of the second transaction log information in steps S107 to S110, but those skilled in the art should understand that the first and second shares are referred to as relative terms and are not in strict order, but are different from each other, so the processing may be performed based on the second share of the second transaction log information in steps S105 to S106, and the processing is performed based on the first share of the second transaction log information in steps S107 to S110. The first part can be understood as one of the two parts and the second part as the other of the two parts.
The preset characteristic information comprises seller-end characteristic information, transaction buyer-end characteristic information of all transaction buyers transacting with the seller-end, commodity characteristic information and/or order characteristic information. The vendor characteristic information may include a vendor location, a vendor monthly volume, vendor shipping capacity evaluation data, vendor order taking time, vendor selected logistics company capacity data, vendor shipping time, commodity transportation time, and the like. The transaction-buyer-side characteristic information may include a location of the transaction-buyer side, historical payment time information of the transaction-buyer side, and the like. The commodity characteristic information may include commodity price, commodity category, commodity sales amount, and the like. The order characteristic information comprises commodity arrival time and the like corresponding to the order.
Specifically, in order to facilitate calculation of the arrival time of the commodity, a corresponding preset characteristic value is set for the preset characteristic information in advance. For example: the city number can be set according to the city where the position of the selling end is located, and the city number corresponding to the position of the selling end is used as the characteristic numerical value of the position of the selling end. Another example is: the commodity arrival time corresponding to the order can be directly used as the characteristic numerical value of the commodity arrival time corresponding to the order. The preset characteristic value corresponding to the preset characteristic information may be set according to the actual application condition, which is not specifically limited.
S106: and taking the preset feature information extracted from the first second transaction log information and the actual commodity arrival time as training data, and training the training data through a regression training model established by using a regression prediction method to obtain the feature weight corresponding to the preset feature information.
The regression prediction method comprises the following steps: a Mixed Logistic Regression (MLR) method, a Gradient Boosting Decision Tree (GBDT) method, or a Logistic Regression (Logistic Regression) method.
Hybrid logistic regression is a nonlinear model used to fit nonlinear data, and belongs to a modeling approach where complexity can be controlled.
The gradient raising decision tree method is to build a next model in the gradient descending direction of the loss function of the previous model, wherein an iterative process exists. The larger the loss function (loss function), the more error prone the model is. If the modeling process can make the loss function continuously decrease, the modeling is improved continuously, and the best mode is to make the loss function decrease in the direction of the Gradient (Gradient). Regression prediction can be performed through the modeling mode.
The logistic regression method is a nonlinear model, and through an iterative process, the descending direction of the objective function is calculated and updated in each iteration until the objective function is stabilized at a minimum point.
Specifically, in this embodiment, a logistic regression method is used to establish a regression training model, and a process of obtaining the feature weight corresponding to the preset feature information is as follows:
a) and converting the regression problem into a classification probability problem, normalizing the predicted commodity arrival time (namely a predicted target) by adopting a preset normalization formula to obtain the commodity arrival normalization time (namely a predicted target value) with the numerical value of (0,1), and defining the predicted target value as the timeliness probability.
b) Let S be a sample set (assumed to contain N samples) of the preset feature information X and the actual commodity arrival time t extracted from the first second transaction log information. For S (S ═ S)1、s2....sNH) of the ith sample set si，i∈[1,N]，siRepresenting a set of samples xi,tiIs vector xi＝{xi1、xi2....xiJ}，JAnd the number of the preset feature information contained in the ith sample set is represented. Suppose 0 < tiT (preset arrival time threshold) or less, and classification C in classification probability1Let t be 1i0, or tiClass C in class probability > T00, thereby the aging probability p (C)1|Si,θi) The following were used:
wherein x isiAs input to a regression training model; thetaiTraining the parameters of the model for regression, with xi＝{xi1、xi2....xiJIs relative to, thetai＝{θi1、θi2....θiJ}; σ () is a logistic sigmmod function (sigmoidal function) defined as follows:
c) taking S as training data, and assuming that N samples accord with independent same distribution, likelihood function p (t)i|Si,θi) The following were used:
wherein, yi＝p(C1|xi). As can be seen from the equation, the likelihood function p (t)i|Si,θi) For Bernoulli distribution, the likelihood function p (t)i|Si,θi) Error function E (θ)i) Can be expressed as:
d) e is determined using either a gradient descent or a random gradient descent.
Finally, the parameter theta is obtainediWill thetaiAs xiCorresponding feature weights ω (i).
It should be noted that, after the feature weight corresponding to the preset feature information is obtained, at a preset time interval, the newly generated second transaction log information may be obtained again according to the method of this embodiment, and the model is updated through iterative training to obtain the feature weight corresponding to the new preset feature information, so as to prompt the vendor end to perform benign improvement of the self-logistics service capability, thereby affecting the overall logistics service capability of the transaction system.
According to the method for acquiring the commodity arrival time, the commodity arrival time from the selling end to the current buying end is predicted and calculated according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current buying end can be visually reflected by the characteristic information of the current buying end, the actual condition of the selling end can be visually reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved. And displaying the commodity arrival time on a commodity detail page, a commodity ordering page, a commodity logistics detail page and/or a commodity searching page associated with the selling end, so that the purchasing end can visually acquire the commodity arrival time and make a purchasing decision. The commodity arrival time is used as logistics capacity data of the selling end, the sorting of commodities related to the selling end in the commodity searching result is determined according to the logistics capacity data, and searching can be supported for time sorting. Training the training data by using a regression training model established by a regression prediction method to obtain the characteristic weight corresponding to the preset characteristic information, wherein the accuracy of the obtained characteristic weight is higher, and the accuracy of the predicted commodity arrival time can be improved.
EXAMPLE III
Fig. 3 is a method for obtaining a commodity arrival time according to a third embodiment of the present invention; after the second embodiment S106 obtains the feature weight corresponding to the preset feature information, as shown in fig. 3, the method may further include:
s107: and extracting preset characteristic information and actual commodity arrival time from the second transaction log information.
The actual commodity arrival time is the arrival time, the arrival date and the like corresponding to each trading buyer end in all the trading buyer ends traded by the seller end and obtained from the order information.
The preset characteristic information comprises seller-end characteristic information, transaction buyer-end characteristic information of all transaction buyers transacting with the seller-end, commodity characteristic information and/or order characteristic information. The vendor characteristic information may include a vendor location, a vendor monthly volume, vendor shipping capacity evaluation data, vendor order taking time, vendor selected logistics company capacity data, vendor shipping time, commodity transportation time, and the like. The transaction-buyer-side characteristic information may include a location of the transaction-buyer side, historical payment time information of the transaction-buyer side, and the like. The commodity characteristic information may include commodity price, commodity category, commodity sales amount, and the like. The order characteristic information comprises commodity arrival time and the like corresponding to the order.
Specifically, in order to facilitate calculation of the arrival time of the commodity, a corresponding preset characteristic value is set for the preset characteristic information in advance. For example: the city number can be set according to the city where the position of the selling end is located, and the city number corresponding to the position of the selling end is used as the characteristic numerical value of the position of the selling end. Another example is: the commodity arrival time corresponding to the order can be directly used as the characteristic numerical value of the commodity arrival time corresponding to the order. The preset characteristic value corresponding to the preset characteristic information may be set according to the actual application condition, which is not specifically limited.
S108: and taking the preset feature information extracted from the second transaction log information as prediction data, and performing prediction calculation on the prediction data through a regression prediction model according to the feature weight corresponding to the preset feature information to obtain the predicted commodity arrival time.
Specifically, the regression prediction model uses all transaction buyers transacted with the seller in the preset feature information as current buyers respectively, and performs prediction calculation according to the method of step S103 in the embodiment to obtain the predicted commodity arrival time corresponding to each transaction buyer.
S109: and evaluating the predicted commodity arrival time through a regression evaluation model according to the actual commodity arrival time to obtain an evaluation result.
Specifically, the regression evaluation model compares the actual commodity arrival time corresponding to each transaction buyer with the predicted commodity arrival time corresponding to each transaction buyer, and determines whether the actual commodity arrival time is consistent with the predicted commodity arrival time. And obtaining an evaluation result according to the predicted total number of the transaction buyers and the number of the actual commodity arrival time consistent with the predicted commodity arrival time.
S110: and judging whether the regression training model is adjusted or not according to the evaluation result.
Specifically, if the number of actual arrival times of the commodities coinciding with the predicted arrival times of the commodities is small, the regression training model needs to be adjusted. If the actual goods arrival time is consistent with the predicted goods arrival time, the regression training model does not need to be adjusted. An adjustment proportion threshold value can be set, and when the proportion of the number of the actual commodity arrival time and the predicted commodity arrival time in the total number of the predicted transaction purchasing ends is smaller than the adjustment proportion threshold value, the regression training model is adjusted; and when the ratio of the number of the actual commodity arrival time consistent with the predicted commodity arrival time in the total number of the predicted transaction buyers is greater than or equal to the adjustment ratio threshold value, the regression training model is not adjusted.
Specifically, the regression training model may be adjusted by adjusting the number of preset feature information, adjusting a feature value corresponding to the preset feature information, and the like.
According to the method for acquiring the commodity arrival time, the commodity arrival time from the selling end to the current buying end is predicted and calculated according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current buying end can be visually reflected by the characteristic information of the current buying end, the actual condition of the selling end can be visually reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved. And displaying the commodity arrival time on a commodity detail page, a commodity ordering page, a commodity logistics detail page and/or a commodity searching page associated with the selling end, so that the purchasing end can visually acquire the commodity arrival time and make a purchasing decision. The commodity arrival time is used as logistics capacity data of the selling end, the sorting of commodities related to the selling end in the commodity searching result is determined according to the logistics capacity data, and searching can be supported for time sorting. Training the training data by using a regression training model established by a regression prediction method to obtain the characteristic weight corresponding to the preset characteristic information, wherein the accuracy of the obtained characteristic weight is higher, and the accuracy of the predicted commodity arrival time can be improved. According to the actual commodity arrival time, the predicted commodity arrival time is evaluated through the regression evaluation model, and the accuracy of the predicted commodity arrival time can be guaranteed.
Example four
As shown in fig. 4, it is a structural diagram of an apparatus for acquiring arrival time of a commodity according to an embodiment of the present invention, the apparatus includes:
the first obtaining module 201 is configured to obtain login information of a current buyer that logs in the commodity transaction system, and first transaction log information of a seller that is associated with the current buyer within a preset first time period;
the first extraction module 202 is configured to extract current buyer-side feature information from login information of a current buyer side, and extract preset feature information from first transaction log information;
the first prediction module 203 is configured to perform prediction calculation on the commodity arrival time from the selling end to the current buying end according to the current buying end feature information, preset feature information, and a feature weight obtained in advance, so as to obtain the commodity arrival time.
Preferably, referring to fig. 5, the apparatus further comprises:
a second obtaining module 204, configured to obtain second transaction log information of the seller within a preset second time period before obtaining login information of a current buyer of the commodity transaction system;
the second extraction module 205 is configured to divide the second transaction log information into two parts, and extract preset feature information and actual commodity arrival time from the first part of the second transaction log information;
the training module 206 is configured to train the training data by using a regression training model established by the regression prediction device, with preset feature information extracted from the first second transaction log information and actual commodity arrival time as training data, to obtain a feature weight corresponding to the preset feature information.
Preferably, the regression prediction method comprises: a hybrid logistic regression method, a gradient boosting decision tree method, or a logistic regression method.
Preferably, referring to fig. 6, the apparatus further comprises:
the third extraction module 207 is used for extracting preset characteristic information and actual commodity arrival time from the second transaction log information;
the second prediction module 208 is configured to use preset feature information extracted from the second transaction log information as prediction data, and perform prediction calculation on the prediction data through a regression prediction model according to feature weights corresponding to the preset feature information to obtain the predicted commodity arrival time;
the evaluation module 209 is used for evaluating the predicted commodity arrival time through a regression evaluation model according to the actual commodity arrival time extracted from the second transaction log information to obtain an evaluation result;
and the judging module 210 is configured to judge whether to adjust the regression training model according to the evaluation result.
Preferably, referring to fig. 7, the apparatus further comprises:
and the display module 211 is configured to display the commodity arrival time on a commodity detail page, a commodity ordering page, a commodity logistics detail page, and/or a commodity search page associated with the selling end.
Preferably, referring to fig. 8, the apparatus further comprises:
the processing module 212 is used for taking the commodity arrival time as logistics capacity data of a selling end;
and the determining module 213 is configured to determine, according to the logistics capacity data, the ranking of the commodities associated with the seller in the commodity search result.
Preferably, the first prediction module 203 comprises:
the first processing unit is used for carrying out normalization processing on the current buyer-side characteristic numerical value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
the second processing unit is used for carrying out normalization processing on a preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
the third processing unit is used for adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information with the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain the commodity arrival normalization time;
and the acquisition unit is used for multiplying the normalized time of the commodity arrival with a preset arrival time threshold value to obtain the commodity arrival time.
Preferably, the preset feature information includes: the seller-side characteristic information, the trading buyer-side characteristic information of all trading buyers trading with the seller-side, the commodity characteristic information and/or the order characteristic information.
According to the device for acquiring the commodity arrival time, the commodity arrival time from the selling end to the current buying end is predicted and calculated according to the characteristic information of the current buying end, the preset characteristic information and the pre-acquired characteristic weight, the commodity arrival time is obtained, the actual condition of the current buying end can be visually reflected by the characteristic information of the current buying end, the actual condition of the selling end can be visually reflected by the preset characteristic information, and the accuracy of the commodity arrival time can be improved. And displaying the commodity arrival time on a commodity detail page, a commodity ordering page, a commodity logistics detail page and/or a commodity searching page associated with the selling end, so that the purchasing end can visually acquire the commodity arrival time and make a purchasing decision. The commodity arrival time is used as logistics capacity data of the selling end, the sorting of commodities related to the selling end in the commodity searching result is determined according to the logistics capacity data, and searching can be supported for time sorting. Training the training data by using a regression training model established by a regression prediction method to obtain the characteristic weight corresponding to the preset characteristic information, wherein the accuracy of the obtained characteristic weight is higher, and the accuracy of the predicted commodity arrival time can be improved. According to the actual commodity arrival time, the predicted commodity arrival time is evaluated through the regression evaluation model, and the accuracy of the predicted commodity arrival time can be guaranteed.
The device corresponds to the description of the method flow, and the description of the method flow is referred for the deficiency, and is not repeated.
The foregoing description shows and describes several preferred embodiments of the invention, but as aforementioned, it is to be understood that the invention is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (14)
1. A method for obtaining arrival time of a commodity, the method comprising:
acquiring login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a first time period preset before the login time of the current buying end;
extracting current buyer-side characteristic information from the login information of the current buyer side, wherein the current buyer-side characteristic information comprises: at least one of the position of the current purchasing end and the historical payment time information of the current purchasing end;
extracting preset feature information from the first transaction log information, wherein the preset feature information comprises: at least one of the characteristic information of the selling terminal, the characteristic information of the trading terminal of all the trading terminals traded with the selling terminal, the characteristic information of the commodity and the characteristic information of the order; the characteristic information of the seller at least comprises the delivery capacity evaluation data of the seller and the order interception time of the seller;
and predicting and calculating the commodity arrival time from the selling end to the current purchasing end according to the characteristic information of the current purchasing end, the preset characteristic information and the pre-acquired characteristic weight to obtain the commodity arrival time, wherein the characteristic weight is obtained by training second transaction log information of the selling end, the commodity arrival time is obtained by multiplying the normalized commodity arrival time by a preset arrival time threshold, and the normalized commodity arrival time is obtained by weighting and summing the normalized characteristic information of the current purchasing end and the normalized preset characteristic information.
2. The method of claim 1, wherein prior to obtaining login information for a current buyer end to a merchandise transaction system, the method further comprises:
acquiring second transaction log information of the selling end in a preset second time period;
dividing the second transaction log information into two parts, and extracting the preset characteristic information and the actual commodity arrival time from the first part of the second transaction log information;
and taking the preset feature information extracted from the first transaction log information and the actual commodity arrival time as training data, and training the training data through a regression training model established by using a regression prediction method to obtain the feature weight corresponding to the preset feature information.
3. The method of claim 2, wherein the regression prediction method comprises: a hybrid logistic regression method, a gradient boosting decision tree method, or a logistic regression method.
4. The method as claimed in claim 2, wherein after obtaining the feature weight corresponding to the preset feature information, before obtaining the login information of the current buyer end of the login commodity transaction system, further comprising:
extracting the preset characteristic information and the actual commodity arrival time from a second transaction log information;
taking the preset feature information extracted from the second transaction log information as prediction data, and performing prediction calculation on the prediction data through a regression prediction model according to feature weight corresponding to the preset feature information to obtain the predicted commodity arrival time;
according to the actual commodity arrival time extracted from the second transaction log information, estimating the predicted commodity arrival time through a regression estimation model to obtain an estimation result;
and judging whether the regression training model is adjusted or not according to the evaluation result.
5. The method of claim 1, wherein after obtaining the time to arrival of the good, the method further comprises:
and displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity search page associated with the selling end.
6. The method of claim 1, wherein after obtaining the time to arrival of the good, the method further comprises:
taking the commodity arrival time as logistics capacity data of the selling end;
and determining the sequence of the commodities associated with the selling end in the commodity search result according to the logistics capacity data.
7. The method according to any one of claims 1 to 6, wherein the step of performing predictive calculation on the commodity arrival time from the seller to the current buyer according to the current buyer characteristic information, the preset characteristic information and the pre-obtained characteristic weight to obtain the commodity arrival time comprises:
normalizing the current buyer-side characteristic value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
normalizing the preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information with the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain commodity arrival normalization time;
and multiplying the normalized commodity arrival time by a preset arrival time threshold value to obtain the commodity arrival time.
8. An apparatus for obtaining arrival time of an article, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring login information of a current buying end of a login commodity transaction system and first transaction log information of a selling end associated with the current buying end in a first preset time period before the login time of the current buying end;
a first extraction module, configured to extract current buyer-side feature information from the login information of the current buyer side, and extract preset feature information from the first transaction log information, where the current buyer-side feature information includes: at least one of the position of the current purchasing end and the historical payment time information of the current purchasing end, wherein the preset characteristic information comprises: at least one of the characteristic information of the selling terminal, the characteristic information of the trading terminal of all the trading terminals traded with the selling terminal, the characteristic information of the commodity and the characteristic information of the order; the characteristic information of the seller at least comprises the delivery capacity evaluation data of the seller and the order interception time of the seller;
the first prediction module is used for predicting and calculating the commodity arrival time from the selling end to the current purchasing end according to the current purchasing end characteristic information, the preset characteristic information and the pre-acquired characteristic weight to obtain the commodity arrival time, wherein the characteristic weight is obtained by training second transaction log information of the selling end, the commodity arrival time is obtained by multiplying the commodity arrival normalized time by a preset arrival time threshold, and the commodity arrival normalized time is obtained by performing weighted summation on the normalized current purchasing end characteristic information and the normalized preset characteristic information.
9. The apparatus of claim 8, wherein the apparatus further comprises:
the second acquisition module is used for acquiring second transaction log information of the selling terminal in a preset second time period before acquiring the login information of the current buying terminal of the commodity transaction system;
the second extraction module is used for dividing the second transaction log information into two parts and extracting the preset characteristic information and the actual commodity arrival time from the first part of the second transaction log information;
and the training module is used for taking the preset feature information extracted from the first transaction log information and the actual commodity arrival time as training data, and training the training data through a regression training model established by using a regression prediction method to obtain the feature weight corresponding to the preset feature information.
10. The apparatus of claim 9, wherein the regression prediction method comprises: a hybrid logistic regression method, a gradient boosting decision tree method, or a logistic regression method.
11. The apparatus of claim 9, wherein the apparatus further comprises:
the third extraction module is used for extracting the preset characteristic information and the actual commodity arrival time from a second transaction log information;
the second prediction module is used for taking the preset feature information extracted from the second transaction log information as prediction data, and performing prediction calculation on the prediction data through a regression prediction model according to the feature weight corresponding to the preset feature information to obtain the predicted commodity arrival time;
the evaluation module is used for evaluating the predicted commodity arrival time through a regression evaluation model according to the actual commodity arrival time extracted from the second transaction log information to obtain an evaluation result;
and the judging module is used for judging whether to adjust the regression training model according to the evaluation result.
12. The apparatus of claim 8, wherein the apparatus further comprises:
and the display module is used for displaying the commodity arrival time on a commodity detail page, a commodity lower order page, a commodity logistics detail page and/or a commodity search page associated with the selling end.
13. The apparatus of claim 8, wherein the apparatus further comprises:
the processing module is used for taking the commodity arrival time as the logistics capacity data of the selling end;
and the determining module is used for determining the sequence of the commodities associated with the selling end in the commodity search result according to the logistics capacity data.
14. The apparatus of any one of claims 8-13, wherein the first prediction module comprises:
the first processing unit is used for carrying out normalization processing on the current buyer-side characteristic numerical value corresponding to the current buyer-side characteristic information by using a preset normalization formula to obtain a current buyer-side characteristic normalization value;
the second processing unit is used for carrying out normalization processing on a preset characteristic value corresponding to the preset characteristic information by using a preset normalization formula to obtain a preset characteristic normalization value corresponding to the preset characteristic value;
the third processing unit is used for adding the product of the current buyer-side feature normalization value and the feature weight corresponding to the current buyer-side feature information with the product of the preset feature normalization value and the feature weight corresponding to the preset feature information to obtain the commodity arrival normalization time;
and the acquisition unit is used for multiplying the normalized commodity arrival time by a preset arrival time threshold value to obtain the commodity arrival time.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410735060.8A CN105719145B (en) | 2014-12-04 | 2014-12-04 | Method and device for acquiring commodity arrival time |
| PCT/CN2015/095835 WO2016086803A1 (en) | 2014-12-04 | 2015-11-27 | Product arrival time acquisition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410735060.8A CN105719145B (en) | 2014-12-04 | 2014-12-04 | Method and device for acquiring commodity arrival time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105719145A CN105719145A (en) | 2016-06-29 |
| CN105719145B true CN105719145B (en) | 2020-11-03 |
Family
ID=56091010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410735060.8A Active CN105719145B (en) | 2014-12-04 | 2014-12-04 | Method and device for acquiring commodity arrival time |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105719145B (en) |
| WO (1) | WO2016086803A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726843B (en) * | 2017-10-30 | 2023-09-15 | 阿里巴巴集团控股有限公司 | Method, device and terminal for predicting distribution data |
| CN108364085B (en) * | 2018-01-02 | 2020-12-15 | 拉扎斯网络科技（上海）有限公司 | Takeout delivery time prediction method and device |
| CN108345958A (en) * | 2018-01-10 | 2018-07-31 | 拉扎斯网络科技（上海）有限公司 | A kind of order goes out to eat time prediction model construction, prediction technique, model and device |
| CN113762547A (en) * | 2020-06-29 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN113034075A (en) * | 2021-03-29 | 2021-06-25 | 上海寻梦信息技术有限公司 | Logistics waybill timeliness pushing method, system, equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011008309A (en) * | 2009-06-23 | 2011-01-13 | Hitachi Ltd | Supplier evaluation method in electronic commerce and system thereof |
| CN102270309B (en) * | 2011-07-27 | 2013-05-01 | 华北电力大学 | Short-term electric load prediction method based on ensemble learning |
| CN103294677A (en) * | 2012-02-22 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Searching method of electronic commerce search engine and electronic commerce search engine |
| US10134066B2 (en) * | 2012-03-30 | 2018-11-20 | Ebay Inc. | Personalized delivery time estimate system |
| CN103383762A (en) * | 2012-05-03 | 2013-11-06 | 上海乐顾网络技术有限公司 | Electronic business system with price changing dynamically in real time |
| CN102982480A (en) * | 2012-12-21 | 2013-03-20 | 江苏乐买到网络科技有限公司 | Commodity group purchase system for online trade platform |
| US20140330741A1 (en) * | 2013-05-03 | 2014-11-06 | Iwona Bialynicka-Birula | Delivery estimate prediction and visualization system |
-
2014
- 2014-12-04 CN CN201410735060.8A patent/CN105719145B/en active Active
-
2015
- 2015-11-27 WO PCT/CN2015/095835 patent/WO2016086803A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN105719145A (en) | 2016-06-29 |
| WO2016086803A1 (en) | 2016-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107465741B (en) | Information pushing method and device | |
| CN105719145B (en) | Method and device for acquiring commodity arrival time | |
| US11210716B2 (en) | Predicting a status of a transaction | |
| JP6134444B2 (en) | Method and system for recommending information | |
| US20140279263A1 (en) | Systems and methods for providing product recommendations | |
| KR102006900B1 (en) | Method for providing information method for online shopping and the intergration server thereof | |
| US20150199746A1 (en) | Recommendation machine | |
| US20140180882A1 (en) | Pay-per-sale system, method and computer program product therefor | |
| CN105354719A (en) | Credit evaluating system and method applied to electronic commerce platform | |
| JP6417002B1 (en) | Generating device, generating method, and generating program | |
| CN109213936B (en) | Commodity searching method and device | |
| US20150178768A1 (en) | System and method for intermediating electronic commerce using offline transaction information | |
| Lin et al. | Monetary discount strategies for real-time promotion campaign | |
| CN106600360B (en) | Method and device for sorting recommended objects | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN112085537A (en) | Method and system for analyzing commodities based on big data | |
| CN114219547B (en) | Method, device, equipment and storage medium for determining store ordering amount | |
| CN111639989B (en) | Commodity recommendation method and readable storage medium | |
| KR101865521B1 (en) | Pricing method of online sale product | |
| KR20140047198A (en) | Method of sharing customer rate of merchandise based on social network | |
| JP2019032827A (en) | Generation device, method for generation, and generation program | |
| CN113421148B (en) | Commodity data processing method, commodity data processing device, electronic equipment and computer storage medium | |
| Lixandroiu et al. | An analysis on choosing a proper ecommerce platform | |
| Panchal et al. | Residential Property Price Prediction Using Machine Learning: MakanSETU | |
| KR102418015B1 (en) | Server providing credit risk tracking accessment service for e-commerce small business owners and its operation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180323 Address after: Four story 847 mailbox of the capital mansion of Cayman Islands, Cayman Islands, Cayman Applicant after: CAINIAO SMART LOGISTICS HOLDING Ltd. Address before: Cayman Islands Grand Cayman capital building a four storey No. 847 mailbox Applicant before: ALIBABA GROUP HOLDING Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |