CN110866625A - Promotion index information generation method and device - Google Patents
Promotion index information generation method and device Download PDFInfo
- Publication number
- CN110866625A CN110866625A CN201810988605.4A CN201810988605A CN110866625A CN 110866625 A CN110866625 A CN 110866625A CN 201810988605 A CN201810988605 A CN 201810988605A CN 110866625 A CN110866625 A CN 110866625A
- Authority
- CN
- China
- Prior art keywords
- prediction
- value
- promotion
- training sample
- residual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims description 105
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 238000003066 decision tree Methods 0.000 claims description 11
- 230000001737 promoting effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 238000004088 simulation Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000012417 linear regression Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 150000001875 compounds Chemical class 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000006467 substitution reaction 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"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for generating promotion index information, and relates to the technical field of computers. One embodiment of the method comprises: replacing the value of each preset characteristic in the promotion data with the historical average value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index; inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index; and determining the sales index of the promotion data according to the baseline predicted value and the residual predicted value. The implementation mode can rapidly determine the sales index of the promotion activity based on the promotion data of the real-time promotion activity, and has good real-time performance; high accuracy and wide application range.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for generating promotion index information.
Background
The prediction of sales volume is increasingly paid more and more by enterprises and research institutions as a big edge of the e-commerce platform to compete for off-line merchants and the cost saving of the supply chain. Whether it is a web merchant or e-commerce platform, various aspects of adjustment, such as inventory planning, purchasing, clearing, etc., may be made based on the forecasted sales. The existing method mainly uses a machine learning model, and mainly adopts a Linear Regression model (Linear Regression), a Gradient boosting decision Tree (GBDT for short), and the like. With the support of existing data, increasing sales prediction accuracy increasingly relies on the input of additional information, the most important of which is promotional information.
The technical scheme of the prior art for giving a prediction result according to a promotion plan mainly comprises the following steps:
1) the existing method is mainly a simulation scheme based on promotion elasticity:
a. elastic prediction formula: pred = Qmean+Qo*[exp(α*dreal)-exp(α*dmean)]
b.QoIs a sales baseline for the commodity; qmeanThe prediction value obtained by using a sales prediction model under the historical average promotion level is α, the promotion elasticity coefficient is drealObtaining the quantified discount strength after the promotion plan, dmeanAverage discount strength calculated according to historical promotion data; pred is the predicted value;
2) and (3) carrying out promotion prediction by using a Gradient Boosting Decision Tree (GBDT for short).
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
1) the simulation scheme based on the promotion elasticity is sensitive to the promotion information of the commodity, namely, the promotion elasticity coefficient can become more fluctuated along with more frequent promotion activities, so that the final sales prediction deviation is larger; in addition, unreasonable sales promotion elasticity can be calculated for the commodities with lower sales promotion activity, so that sales promotion simulation cannot cover all commodities;
2) the GBDT-based promotion prediction method cannot meet real-time performance, and the results of promotion simulations cannot show explicit relationships between sales and promotion information.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for generating promotion index information, which can quickly determine a sales index of a real-time promotion activity based on promotion data of the real-time promotion activity, and have good real-time performance; high accuracy and wide application range.
To achieve the above object, according to an aspect of an embodiment of the present invention, a method for generating promotion guide information is provided.
The method for generating the promotion index information comprises the following steps:
replacing the value of each preset characteristic in the promotion data with the historical average value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index;
inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index;
and determining the sales index of the promotion data according to the baseline predicted value and the residual predicted value.
Optionally, the regression model is trained as follows:
for each training sample in the training set: inputting the training sample into a prediction model to obtain a prediction value corresponding to the training sample; replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into a prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain a trained regression model.
Optionally, the regression model is:
in the formula (I), the compound is shown in the specification,
representing a residual prediction value;
respectively represent the 1 st, the 2 nd, the … … th and the n th preset characteristics; w is a1、w2、……、wnRespectively representing the weights of the 1 st, 1 nd, 2 nd, … … th and n th preset characteristics; b represents the intercept of the regression model.
Optionally, the predictive model is trained as follows:
and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain a trained prediction model.
Optionally, determining the sales indicator for the promotional data based on the baseline predictive value and the residual predictive value comprises: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data.
According to still another aspect of an embodiment of the present invention, there is provided a sales promotion index information generation apparatus.
The promotion index information generation device according to the embodiment of the present invention includes:
the base line prediction module is used for replacing the value of each preset characteristic in the promotion data with the historical mean value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain the base line prediction value of the sales index;
the residual prediction module is used for inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index;
and the sales prediction module determines sales indexes of the promotion data according to the base line prediction value and the residual error prediction value.
Optionally, the residual prediction module is further configured to: the regression model was trained as follows:
for each training sample in the training set: inputting the training sample into a prediction model to obtain a prediction value corresponding to the training sample; replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into a prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain a trained regression model.
Optionally, the regression model is:
in the formula (I), the compound is shown in the specification,
representing a residual prediction value;
respectively represent the 1 st, the 2 nd, the … … th and the n th preset characteristics; w is a1、w2、……、wnRespectively representing the weights of the 1 st, 1 nd, 2 nd, … … th and n th preset characteristics; b represents the intercept of the regression model.
Optionally, the baseline prediction module is further configured to: the prediction model was trained as follows:
and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain a trained prediction model.
Optionally, the determining, by the sales prediction module, the sales indicator of the promotion data according to the baseline prediction value and the residual prediction value includes: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data.
According to another aspect of an embodiment of the present invention, there is provided an electronic device for generating promotion indicator information.
The promotion index information generation electronic device according to the embodiment of the present invention includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating promotion target information according to the first aspect of the embodiments of the present invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
According to the computer readable medium of the embodiment of the present invention, a computer program is stored thereon, and when being executed by a processor, the program implements the promotion indicator information generation method provided by the first aspect of the embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: by adopting a method of superposing baseline prediction and residual prediction, the sales index of the promotion activity can be rapidly determined based on the promotion data of the real-time promotion activity, and the real-time property is good; high accuracy and wide application range. The relation between the sales promotion data and the residual prediction value is fitted through a linear regression model, so that the sales index is predicted, the linear relation is obvious, and the relation between the sales index and the sales promotion data can be displayed.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of a main flow of a promotion indicator information generation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a promotional indicia information generation method according to an alternative embodiment of the present invention;
FIG. 3 is a schematic diagram of the main modules of a promotional index information generation apparatus according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
According to an aspect of an embodiment of the present invention, there is provided a method for generating promotion target information.
Fig. 1 is a schematic diagram of a main flow of a promotion index information generation method according to an embodiment of the present invention, and as shown in fig. 1, the promotion index information generation method according to the embodiment of the present invention includes: step S101, step S102, and step S103.
And S101, replacing the value of each preset feature in the promotion data with the historical average value of the preset feature, and inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index.
The baseline value can be understood as the sales index of the commodity without promotion, and the baseline predicted value refers to the baseline value obtained by prediction by using a prediction model.
In practical application, those skilled in the art can train the prediction model by selecting a suitable algorithm according to different application scenarios, such as Regression algorithm (Regression Algorithms), example-based algorithm (instant-based Algorithms), Decision Tree algorithm (Decision Tree Algorithms), bayesian algorithm (bayesian Algorithms), Clustering algorithm (Clustering Algorithms), Association rule algorithm (Association rule Algorithms), Artificial Neural network algorithm (Artificial Neural network Algorithms), Deep Learning (Deep Learning Algorithms), dimension reduction algorithm (dimensional reduction Algorithms), and so on.
In some embodiments, the predictive model is trained as follows: and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain a trained prediction model. The Gradient Boosting Decision Tree (GBDT) can be used for almost all regression problems including linear or nonlinear regression, and has a wide application range, so that the method can be applied to various commodities.
Each training sample as a training set may be promotional data for a respective promotional program in the historical data. In order to make the prediction accuracy of the trained model better, each training sample can contain preset characteristics, and the preset characteristics comprise characteristics such as holiday effect, seasonal effect, historical sales trend, promotion information and the like. There are two techniques in data mining, one called Feature Extraction (Feature Extraction) and the other called Feature selection (Feature selection). The characteristic selection is to select a plurality of variables with larger relevance to a target variable from a large number of original variables, and the selected variables are not changed; and the characteristic extraction is to integrate and recombine a large amount of original variables and generate fewer new variables with characteristic representativeness. Various feature extraction methods and/or feature selection methods may be adopted by those skilled in the art to obtain the preset features in the embodiments of the present invention, and the feature extraction and feature selection methods for obtaining the preset features are not particularly limited in the embodiments of the present invention.
And S102, inputting the promotion data into the trained regression model to obtain the residual prediction value of the sales index.
The residual value can be understood as the amount of change in the sales index of the goods with the promotion as compared with the case without the promotion. The residual prediction value is a residual value obtained by adopting regression model prediction. The regression model is obtained by training according to each training sample in the training set and the corresponding residual error value.
In some embodiments, optionally, the regression model is trained as follows:
for each training sample in the training set: inputting the training sample into a prediction model to obtain a prediction value corresponding to the training sample; replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into a prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain a trained regression model.
Optionally, the regression model is:
in the formula (I), the compound is shown in the specification,
representing a residual prediction value;
respectively represent the 1 st, the 2 nd, the … … th and the n th preset characteristics; w is a1、w2、……、wnRespectively representing the weights of the 1 st, 1 nd, 2 nd, … … th and n th preset characteristics; b represents the intercept of the regression model.
The relation between the sales promotion data and the residual prediction value is fitted through a linear regression model, so that the sales index is predicted, the linear relation is obvious, and the relation between the sales index and the sales promotion data can be displayed.
And S103, determining the sales index of the promotion data according to the base line predicted value and the residual error predicted value.
In the practical application process, the base line predicted value and the residual error predicted value can be subjected to weighted summation, and then the value after weighted summation is used as the sales index of the promotion data. Of course, the baseline predicted value and the residual predicted value can also be substituted into a preset certain algorithm model to obtain the sales index of the promotion data. In an alternative embodiment of the present invention, determining a sales indicator for the promotional data based on the baseline predictive value and the residual predictive value comprises: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data. The method for determining the sales index of the promotion data is simple and convenient, has obvious linear relation and is convenient for displaying the relation between the sales index and the promotion data.
FIG. 2 is a schematic diagram of a promotional indicator information generation method according to an alternative embodiment of the present invention. The method for generating promotion index information according to the embodiment of the present invention is described below with reference to fig. 2.
(1) Training the training samples in the training Set by adopting a GBDT algorithm to obtain a prediction model, and screening preset features with higher importance to form a promotion feature Setpromotion；
(2) Statistics of historical data and related characteristics of promotion information, and calculation of a Set of promotion characteristicspromotionThe mean value of each preset characteristic;
(3) replacing the value of the preset characteristic of each test sample in the test set with the mean value calculated in the step (2), and calling the prediction model in the step (1) to obtain the sales prediction Q of the prediction setmean；
(3) Inputting each training sample in the training set into the prediction model in the step (1) to obtain the sales prediction Q of the training sethistory(ii) a Replacing the value of the preset characteristic of each training sample in the training set with the mean value calculated in the step (2), and calling the prediction model in the step (1) again to predict the training set to obtain a baseline sales prediction Q of the training setmean_history(ii) a Computing training set residuals, i.e. Resihistory=Qhistory-Qmean_history；
4) Constructing a regression model to obtain the regression model: from SetpromotionScreening feature combination featurepromotion_1,featurepromoyion_2,…,featurepromotion_nAnd fitting a linear relation between the feature combination of the training set and the residual error of the training set, namely:
w1、w2、……、wnand b is the model parameters determined during the training process, and after the training is completed, is a set of determined values.
(5) And obtaining a promotion simulation result: inputting each test sample in the test set into the regression model in the step (4) to obtain a residual error predicted value Resi of the test setfuture. The test is concentrated, and for each preset characteristic, a value set and a feature can be set manuallypromotion_k∈[a,b]And different regression prediction results are obtained by taking different values of the characteristics, the model responds to input information in real time, the prediction is rapid, and the feedback result can be used as a basis for selecting the promotion activities.
For the commodities which are not sensitive to promotion, the regression model in the step (4) can train a weight coefficient which approaches to 0 for the relevant preset features, namely, the rapid change of promotion strength cannot greatly influence the simulation result, so that the condition of large prediction deviation is avoided, and all commodities can be covered.
(6) And outputting a prediction result, and superposing the test set baseline prediction and the promotion simulation result to obtain a prediction result pred', namely: pred' = Qmean+Resifuture。
According to still another aspect of an embodiment of the present invention, there is provided a sales promotion index information generation apparatus.
Fig. 3 is a schematic diagram of the main modules of a promotion indicator information generation apparatus according to an embodiment of the present invention. As shown in fig. 3, the promotion index information generation apparatus 300 according to the embodiment of the present invention includes:
the baseline prediction module 301 is used for replacing the value of each preset feature in the promotion data with the historical average value of the preset feature, and then inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index;
the residual error prediction module 302 is used for inputting the promotion data into the trained regression model to obtain a residual error prediction value of the sales index;
and the sales prediction module 303 determines sales indicators of the promotion data according to the base line prediction value and the residual error prediction value.
Optionally, the residual prediction module is further configured to: the regression model was trained as follows:
for each training sample in the training set: inputting the training sample into a prediction model to obtain a prediction value corresponding to the training sample; replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into a prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain a trained regression model.
Optionally, the regression model is:
in the formula (I), the compound is shown in the specification,
representing a residual prediction value;
respectively represent the 1 st, the 2 nd, the … … th and the n th preset characteristics; w is a1、w2、……、wnRespectively representing the weights of the 1 st, 1 nd, 2 nd, … … th and n th preset characteristics; b represents the intercept of the regression model.
Optionally, the baseline prediction module is further configured to: the prediction model was trained as follows:
and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain a trained prediction model.
Optionally, the determining, by the sales prediction module, the sales indicator of the promotion data according to the baseline prediction value and the residual prediction value includes: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data.
According to another aspect of an embodiment of the present invention, there is provided an electronic device for generating promotion indicator information.
The promotion index information generation electronic device according to the embodiment of the present invention includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating promotion target information according to the first aspect of the embodiments of the present invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
According to the computer readable medium of the embodiment of the present invention, a computer program is stored thereon, and when being executed by a processor, the program implements the promotion indicator information generation method provided by the first aspect of the embodiment of the present invention.
FIG. 4 illustrates an exemplary system architecture 400 to which the promotional index information generation method or apparatus of an embodiment of the invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 401, 402, 403 may be various electronic devices having an explicit screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 401, 402, 403. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the promotion index information generation method provided by the embodiment of the present invention is generally executed by the server 405, and accordingly, the promotion index information generation device is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output section 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprising: the base line prediction module is used for replacing the value of each preset characteristic in the promotion data with the historical mean value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain the base line prediction value of the sales index; the residual prediction module is used for inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index; and the sales prediction module determines sales indexes of the promotion data according to the base line prediction value and the residual error prediction value. Where the names of these modules do not in some cases constitute a limitation on the module itself, for example, the sales prediction module may also be described as a "module that inputs promotional data into a trained regression model to yield a residual prediction of the sales indicator".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: replacing the value of each preset characteristic in the promotion data with the historical average value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index; inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index; and determining the sales index of the promotion data according to the baseline predicted value and the residual predicted value.
According to the technical scheme of the embodiment of the invention, a method of superposing the base line prediction and the residual prediction is adopted, so that the sales index of the promotion activity can be rapidly determined based on the promotion data of the real-time promotion activity, and the real-time performance is good; high accuracy and wide application range. The relation between the sales promotion data and the residual prediction value is fitted through a linear regression model, so that the sales index is predicted, the linear relation is obvious, and the relation between the sales index and the sales promotion data can be displayed.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for generating promotion index information, comprising:
replacing the value of each preset characteristic in the promotion data with the historical average value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain a baseline prediction value of the sales index;
inputting the promotion data into a trained regression model to obtain a residual prediction value of the sales index;
and determining the sales index of the promotion data according to the baseline predicted value and the residual predicted value.
2. The method of claim 1, wherein the regression model is trained as follows:
for each training sample in the training set: inputting the training samples into the prediction model to obtain a prediction value corresponding to the training samples;
replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into the prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain the trained regression model.
3. The method of claim 1, wherein the predictive model is trained as follows:
and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain the trained prediction model.
4. The method of claim 1, wherein determining a sales indicator for the promotional data based on the baseline predictor and the residual predictor comprises: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data.
5. A promotion indicator information generation apparatus, comprising:
the base line prediction module is used for replacing the value of each preset characteristic in the promotion data with the historical mean value of the preset characteristic, and then inputting the promotion data into a trained prediction model to obtain the base line prediction value of the sales index;
the residual prediction module is used for inputting the promotion data into the trained regression model to obtain a residual prediction value of the sales index;
and the sales prediction module is used for determining the sales index of the promotion data according to the baseline prediction value and the residual prediction value.
6. The apparatus of claim 5, wherein the residual prediction module is further to: the regression model was trained as follows:
for each training sample in the training set: inputting the training samples into the prediction model to obtain a prediction value corresponding to the training samples; replacing the value of each preset feature in the training sample with the historical mean value of the preset feature, and then inputting the training sample into the prediction model to obtain a baseline prediction value corresponding to each training sample; determining a residual error predicted value corresponding to the training sample according to the predicted value corresponding to the training sample and the base line predicted value;
and carrying out regression fitting on each training sample and the residual prediction value corresponding to the training sample to obtain the trained regression model.
7. The apparatus of claim 5, wherein the baseline prediction module is further to: the prediction model is trained as follows:
and training all training samples in the training set by adopting a gradient lifting decision tree algorithm to obtain the trained prediction model.
8. The apparatus of claim 5, wherein the sales prediction module determining the sales indicator for the promotion data based on the baseline prediction value and the residual prediction value comprises: and taking the sum of the baseline predicted value and the residual predicted value as the sales index of the promotion data.
9. An electronic device for generating promotion indicator information, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-4.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810988605.4A CN110866625A (en) | 2018-08-28 | 2018-08-28 | Promotion index information generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810988605.4A CN110866625A (en) | 2018-08-28 | 2018-08-28 | Promotion index information generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866625A true CN110866625A (en) | 2020-03-06 |
Family
ID=69651416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810988605.4A Pending CN110866625A (en) | 2018-08-28 | 2018-08-28 | Promotion index information generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866625A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420202A (en) * | 2021-07-15 | 2021-09-21 | 上海明略人工智能(集团)有限公司 | Method and device for predicting keyword search times, electronic equipment and storage medium |
| CN113538038A (en) * | 2021-06-17 | 2021-10-22 | 宁波权智科技有限公司 | Sales feedback method and device based on artificial intelligence |
| CN113743969A (en) * | 2020-05-29 | 2021-12-03 | 北京京东智能城市大数据研究院 | Method, device, equipment and storage medium for sales data prediction |
| WO2022009013A1 (en) * | 2020-07-09 | 2022-01-13 | International Business Machines Corporation | Automated data linkages across datasets |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140200992A1 (en) * | 2013-01-14 | 2014-07-17 | Oracle International Corporation | Retail product lagged promotional effect prediction system |
| CN106056239A (en) * | 2016-05-24 | 2016-10-26 | 北京京东尚博广益投资管理有限公司 | Product inventory predicting method and product inventory predicting device |
| CN106408341A (en) * | 2016-09-21 | 2017-02-15 | 北京小米移动软件有限公司 | Goods sales volume prediction method and device, and electronic equipment |
| CN107330741A (en) * | 2017-07-07 | 2017-11-07 | 北京京东尚科信息技术有限公司 | Graded electron-like certificate uses Forecasting Methodology, device and electronic equipment |
| CN108053242A (en) * | 2017-12-12 | 2018-05-18 | 携程旅游信息技术（上海）有限公司 | Sight spot admission ticket ticket amount Forecasting Methodology, system, equipment and storage medium |
| CN108345958A (en) * | 2018-01-10 | 2018-07-31 | 拉扎斯网络科技（上海）有限公司 | Order meal delivery time prediction model construction method, prediction method, model and device |
-
2018
- 2018-08-28 CN CN201810988605.4A patent/CN110866625A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140200992A1 (en) * | 2013-01-14 | 2014-07-17 | Oracle International Corporation | Retail product lagged promotional effect prediction system |
| CN106056239A (en) * | 2016-05-24 | 2016-10-26 | 北京京东尚博广益投资管理有限公司 | Product inventory predicting method and product inventory predicting device |
| CN106408341A (en) * | 2016-09-21 | 2017-02-15 | 北京小米移动软件有限公司 | Goods sales volume prediction method and device, and electronic equipment |
| CN107330741A (en) * | 2017-07-07 | 2017-11-07 | 北京京东尚科信息技术有限公司 | Graded electron-like certificate uses Forecasting Methodology, device and electronic equipment |
| CN108053242A (en) * | 2017-12-12 | 2018-05-18 | 携程旅游信息技术（上海）有限公司 | Sight spot admission ticket ticket amount Forecasting Methodology, system, equipment and storage medium |
| CN108345958A (en) * | 2018-01-10 | 2018-07-31 | 拉扎斯网络科技（上海）有限公司 | Order meal delivery time prediction model construction method, prediction method, model and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743969A (en) * | 2020-05-29 | 2021-12-03 | 北京京东智能城市大数据研究院 | Method, device, equipment and storage medium for sales data prediction |
| WO2022009013A1 (en) * | 2020-07-09 | 2022-01-13 | International Business Machines Corporation | Automated data linkages across datasets |
| US11586520B2 (en) | 2020-07-09 | 2023-02-21 | International Business Machines Corporation | Automated data linkages across datasets |
| GB2611967A (en) * | 2020-07-09 | 2023-04-19 | Ibm | Automated data linkages across datasets |
| CN113538038A (en) * | 2021-06-17 | 2021-10-22 | 宁波权智科技有限公司 | Sales feedback method and device based on artificial intelligence |
| CN113420202A (en) * | 2021-07-15 | 2021-09-21 | 上海明略人工智能(集团)有限公司 | Method and device for predicting keyword search times, electronic equipment and storage medium |
| CN113420202B (en) * | 2021-07-15 | 2024-04-02 | 上海明略人工智能(集团)有限公司 | Method and device for predicting keyword search times, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109840730B (en) | Method and device for data prediction | |
| EP4242955A1 (en) | User profile-based object recommendation method and device | |
| CN110866625A (en) | Promotion index information generation method and device | |
| CN112016796B (en) | Comprehensive risk score request processing method and device and electronic equipment | |
| CN110119445B (en) | Method and device for generating feature vector and classifying text based on feature vector | |
| CN107517251B (en) | Information pushing method and device | |
| CN110390408A (en) | Trading object prediction technique and device | |
| CN110070382B (en) | Method and device for generating information | |
| CN110135871B (en) | Method and device for calculating user repurchase period | |
| CN109961299A (en) | The method and apparatus of data analysis | |
| CN107274209A (en) | The method and apparatus for predicting advertising campaign sales data | |
| CN110309142B (en) | Method and device for rule management | |
| CN109961328B (en) | Method and device for determining order cool-still period | |
| CN110929136A (en) | Personalized recommendation method and device | |
| CN116541610B (en) | Training method and device for recommendation model | |
| CN111967543A (en) | User resource quota determining method and device and electronic equipment | |
| CN113743971A (en) | Data processing method and device | |
| CN116091110A (en) | Resource demand prediction model training method, prediction method and device | |
| CN114663015A (en) | Replenishment method and device | |
| US10678800B2 (en) | Recommendation prediction based on preference elicitation | |
| CN109978306B (en) | Data processing method and device | |
| CN112231299B (en) | Method and device for dynamically adjusting feature library | |
| CN117573973A (en) | Resource recommendation method, device, electronic equipment and storage medium | |
| CN113792952A (en) | Method and apparatus for generating a model | |
| US20170249697A1 (en) | System and method for machine learning based line assignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |