CN109426983A - Dodge purchase activity automatic generation method and device, storage medium, electronic equipment - Google Patents
Dodge purchase activity automatic generation method and device, storage medium, electronic equipment Download PDFInfo
- Publication number
- CN109426983A CN109426983A CN201710778696.4A CN201710778696A CN109426983A CN 109426983 A CN109426983 A CN 109426983A CN 201710778696 A CN201710778696 A CN 201710778696A CN 109426983 A CN109426983 A CN 109426983A
- Authority
- CN
- China
- Prior art keywords
- purchase
- muscle
- sudden strain
- data
- commodity
- 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
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
-
- 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
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure is directed to a kind of sudden strain of a muscle purchase activity automatic generation method and devices, belong to technical field of electronic commerce, this method comprises: obtaining history commodity data and dodging purchase historical act data and to the history commodity data and sudden strain of a muscle purchase historical act data carry out that sudden strain of a muscle purchase motility model is calculated；It obtains multiple merchandise newss and is picked out in the multiple merchandise news and meet the merchandise news for dodging purchase motility model；It is generated according to the merchandise news dodged purchase motility model and meet the sudden strain of a muscle purchase motility model and meets the sudden strain of a muscle purchase activity for dodging purchase motility model.This method can greatly reduce the creation activity time of operation personnel, improve and dodge the efficiency that purchase activity generates.
Description
Technical field
This disclosure relates to which technical field of electronic commerce, in particular to a kind of sudden strain of a muscle purchase activity automatic generation method, dodges and purchases
Movable automatically generating device, computer readable storage medium and electronic equipment.
Background technique
With the fast development of Internet technology, there is a large amount of electric business platform.In the commodity page of each electric business platform
In, it is often promoted in brand preferential mode of prescribing a time limit, to promote the sales volume of various brands.
In the prior art, when progress brand prescribes a time limit preferential dealing, want to buy in order to enable each user can buy
Article, it is online to require a large amount of activity daily.Therefore, brand prescribe a time limit preferential operation personnel require to spend daily it is a large amount of
Time go setting activity or find brand marketers be configured activity.
Aforesaid way is due to needing to carry out manual operation, and there are higher costs, time-consuming and laborious, and not can guarantee quotient
The timely switching of product information, there are merchandise news update it is inefficient, lag the problems such as；Further, people is carried out by operation personnel
Work selects brand, accurately can cannot provide the brand and product of needs with a large amount of personal emotions for user.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of sudden strain of a muscle purchase activity automatic generation method, dodges purchase activity automatically generating device, meter
Calculation machine readable storage medium storing program for executing and electronic equipment, and then the limitation and defect due to the relevant technologies is overcome at least to a certain extent
Caused by one or more problem.
According to one aspect of the disclosure, a kind of sudden strain of a muscle purchase activity automatic generation method is provided, comprising:
It obtains history commodity data and dodges purchase historical act data and history is purchased to the history commodity data and sudden strain of a muscle
Activity data carries out that sudden strain of a muscle purchase motility model is calculated；
It obtains multiple merchandise newss and is picked out in the multiple merchandise news and meet the quotient for dodging purchase motility model
Product information；
Meet the sudden strain of a muscle according to the merchandise news generation dodged purchase motility model and meet the sudden strain of a muscle purchase motility model
Purchase the sudden strain of a muscle purchase activity of motility model.
In a kind of exemplary embodiment of the disclosure, to the history commodity data and dodge purchase historical act data into
Sudden strain of a muscle purchase motility model is calculated in row
It determines the model feature for dodging purchase motility model and obtains the corresponding history commodity number of the model feature
Accordingly and historical act data are purchased in sudden strain of a muscle；
The characteristic value of the history commodity data is obtained according to the action message classification for dodging purchase historical act；Wherein,
The characteristic value includes positive characteristic value and negative feature value；
It obtains respectively and is worth the commodity data of corresponding preset quantity with the positive characteristic value and negative feature and utilizes each institute
Commodity data is stated to be trained the model feature to obtain the sudden strain of a muscle purchase motility model.
In a kind of exemplary embodiment of the disclosure, institute is obtained according to the action message classification for dodging purchase historical act
The characteristic value for stating history commodity data includes:
The action message classification of sudden strain of a muscle purchase historical act according to belonging to history commodity data, in the history commodity data
Commodity classify to obtain the characteristic value of the commodity.
In a kind of exemplary embodiment of the disclosure, classify to the commodity in the history commodity data to obtain
To after the characteristic value of commodity, the sudden strain of a muscle purchase activity automatic generation method further include:
Classified to the commodity data according to the action message classification to obtain positive and negative sample data；
Classification polymerization is carried out to the positive and negative sample data to calculate to obtain the mark sheet collection of positive negative sample.
In a kind of exemplary embodiment of the disclosure, the field of the mark sheet collection includes characteristic value, commodity default
The price of period, commodity are in the sales volume of preset time period, the brand grade of commodity, the gross profit of the stockpile number of commodity, commodity
Rate, commodity are a variety of in independent visitor's number of preset time period.
In a kind of exemplary embodiment of the disclosure, obtain respectively corresponding with the positive characteristic value and negative feature value
The commodity data of preset quantity is simultaneously trained the model feature using each commodity data to obtain the sudden strain of a muscle purchase and live
Movable model includes:
The corresponding commodity data of positive characteristic value and negative feature for obtaining preset quantity respectively are worth corresponding commodity data；
The corresponding commodity data of the positive characteristic value and negative feature are worth corresponding commodity data and carry out random integration, and
Commodity data after random integration is divided into first part and second part；
The model feature is trained using the commodity data of first part, utilizes the commodity data pair of second part
Model feature after training is verified to obtain the sudden strain of a muscle purchase motility model.
In a kind of exemplary embodiment of the disclosure, the quotient of the commodity data of the first part and the second part
The ratio of product data is 7:3.
In a kind of exemplary embodiment of the disclosure, the sudden strain of a muscle purchase activity automatic generation method further include:
The importance values of the corresponding commodity data of the positive characteristic value are calculated separately using random forests algorithm and bear spy
The importance values of the corresponding commodity data of value indicative.
In a kind of exemplary embodiment of the disclosure, the sudden strain of a muscle purchase activity automatic generation method further include:
The importance values are ranked up and judge whether the importance values are greater than preset value；
When judging that the importance values are greater than the preset value, the corresponding commodity of the importance values are saved.
According to one aspect of the disclosure, a kind of sudden strain of a muscle purchase activity automatically generating device is provided, comprising:
Computing module purchases historical act data and to the history commodity data for obtaining history commodity data and dodging
And it dodges purchase historical act data and carries out that sudden strain of a muscle purchase motility model is calculated；
Choosing module meets the sudden strain of a muscle purchase for obtaining multiple merchandise newss and picking out in the multiple merchandise news
The merchandise news of motility model；
Purchase activity generation module is dodged, for according to the quotient for dodging purchase motility model and meeting the sudden strain of a muscle purchase motility model
Product information, which generates, meets the sudden strain of a muscle purchase activity for dodging purchase motility model.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
The computer program realizes sudden strain of a muscle purchase activity automatic generation method described in above-mentioned any one when being executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising:
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to execute sudden strain of a muscle described in above-mentioned any one via the executable instruction is executed
Purchase activity automatic generation method.
A kind of sudden strain of a muscle purchase activity automatic generation method of the disclosure and device, by living to history commodity data and sudden strain of a muscle purchase history
Dynamic data carry out that sudden strain of a muscle purchase motility model is calculated；Then it picks out to meet in multiple merchandise newss and dodges purchase motility model
Merchandise news；Meet sudden strain of a muscle purchase motility model further according to dodging purchase motility model and meeting to dodge the merchandise news for purchasing motility model and generate
Sudden strain of a muscle purchase activity；On the one hand, since the merchandise news generation for purchasing motility model can be dodged according to dodging purchase motility model and meeting
Meet the sudden strain of a muscle purchase activity for dodging purchase motility model, the creation activity time of operation personnel can be greatly reduced, improves and dodge purchase activity
The efficiency of generation；On the other hand, movable generation is purchased due to that can carry out dodging according to historical data, it can be to avoid due to runing people
Member's hand picking thus have offset issue caused by personal emotion, greatly improve sudden strain of a muscle and purchase movable quality, Ke Yijin
The raising of one step, which is dodged, purchases movable sales volume.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of topology example figure for dodging purchase activity system platform.
Fig. 2 schematically shows a kind of flow chart for dodging purchase activity automatic generation method.
Fig. 3 schematically shows a kind of method flow diagram for dodging purchase motility model and generating.
Fig. 4 schematically shows a kind of flow example figure that characteristic value generates.
Fig. 5 schematically shows a kind of method flow diagram for dodging purchase motility model training.
Fig. 6 schematically shows a kind of flow example figure of model training.
Fig. 7 schematically shows a kind of flow example figure of random forests algorithm.
Fig. 8 schematically shows a kind of flow example figure that sudden strain of a muscle purchase activity automatically generates.
Fig. 9 schematically shows a kind of block diagram for dodging purchase activity automatically generating device.
Figure 10 schematically shows a kind of electronic equipment that the above-mentioned automatic lifting method of sudden strain of a muscle purchase activity may be implemented.
Figure 11 schematically shows a kind of computer readable storage medium that the above-mentioned automatic lifting method of sudden strain of a muscle purchase activity may be implemented.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Firstly, sudden strain of a muscle purchase activity system platform is explained and is illustrated.Refering to what is shown in Fig. 1, sudden strain of a muscle purchase activity system is flat
Platform may include history commodity data analysis module, dodge purchase historical act data analysis module, dodge purchase motility model management module,
It dodges purchase activity generation module and dodges purchase activity audit module；Can also include multiple clusters: Hadoop cluster, Spark cluster,
Presto cluster and Elasticsearch cluster etc..Wherein:
Hadoop cluster: the cluster built based on Hadoop, can store sudden strain of a muscle purchase in history all movable data informations,
Merchandise news and user data information etc..
Spark cluster: the cluster built based on Spark, can use Spark cluster can carry out quickly mass data
The ability of calculating to history commodity data and dodges the calculating purchased historical act data and carry out machine learning algorithm, obtains sudden strain of a muscle purchase
Motility model construction and reserving model.
Presto cluster: the cluster built based on presto can use it and can be carried out quick search to mass data
Function；The movable merchandise news of purchase is dodged to that can participate in the merchandise news for dodging purchase recently and be inquired and obtain to participate in.
Elasticsearch cluster: the cluster built based on Elasticsearch can provide efficiently quickly search
Or query function；Can inquire or search the merchandise news for meeting some motility model.
History commodity data analysis module: the module can be by original using the history commodity stored in Hadoop cluster
After data are processed, the information such as the daily sales volumes of commodity, amount of access, positive rating, promotion are obtained, these data are mentioned
Supply dodge purchase motility model carry out using.
Dodge purchase historical act analysis module: the module can be by dodging purchase activity using the history stored in Hadoop cluster
After initial data is processed, obtain movable sku information, sales volume information, amount of access information, the dynamic pin sku information of activity,
Promotion etc. information, with these data be supplied to sudden strain of a muscle purchase motility model carry out using.
Dodge purchase motility model management module: can be by obtaining the analysis of history commodity data and dodging purchase historical act analysis two
The data that a module provides are carried out a variety of sudden strains of a muscle obtained using machine learning algorithm using Spark cluster and purchase motility model.
Dodge purchase activity generation module: what can be provided by existing model in sudden strain of a muscle purchase motility model and Presto cluster can
Movable commodity data is purchased to participate in sudden strain of a muscle, recycles Spark cluster to carry out machine calculating, then generates the work for meeting model needs
Dynamic information.
Dodge purchase activity audit module: the module can carry out the activity automatically generated by sudden strain of a muscle purchase operation personnel further
Manual examination and verification, to ensure that activity can obtain preferable effect.
Activity system platform is purchased based on above-mentioned sudden strain of a muscle, a kind of sudden strain of a muscle purchase activity is provided firstly in this example embodiment and is given birth to automatically
At method.Refering to what is shown in Fig. 2, the sudden strain of a muscle purchase activity automatic generation method may comprise steps of:
Step S210. obtain history commodity data and dodge purchase historical act data and to the history commodity data and
Purchase historical act data are dodged to carry out that sudden strain of a muscle purchase motility model is calculated.
Step S220., which obtains multiple merchandise newss and picks out in the multiple merchandise news, meets the sudden strain of a muscle purchase activity
The merchandise news of model.
Step S230. generates symbol according to the merchandise news dodged purchase motility model and meet the sudden strain of a muscle purchase motility model
Close the sudden strain of a muscle purchase activity for dodging purchase motility model.
In above-mentioned sudden strain of a muscle purchase activity automatic generation method, on the one hand, since according to sudden strain of a muscle purchase motility model and sudden strain of a muscle can be met
The merchandise news of purchase motility model generates the sudden strain of a muscle purchase activity for meeting and dodging purchase motility model, can greatly reduce the creation of operation personnel
Activity time improves and dodges the efficiency that purchase activity generates；On the other hand, movable since sudden strain of a muscle purchase can be carried out according to historical data
Generate, can to avoid due to operation personnel's hand picking thus have offset issue caused by personal emotion, greatly improve
It dodges and purchases movable quality, can further improve sudden strain of a muscle and purchase movable sales volume.
In the following, will be carried out to each step in sudden strain of a muscle purchase activity automatic generation method above-mentioned in this example embodiment detailed
Explanation and explanation.
In step S210, obtains history commodity data and dodge and purchase historical act data and to the history commodity data
And it dodges purchase historical act data and carries out that sudden strain of a muscle purchase motility model is calculated.
In this example embodiment, above-mentioned history commodity data and sudden strain of a muscle purchase historical act data can be from Hadoop collection
It is obtained in group；Further, available a period of time (such as can be the first quarter or half a year, be also possible to 1 year
Etc.) in history commodity data and dodge purchase historical act data；Also available whole history commodity data and sudden strain of a muscle
Historical act data are purchased, there is no special restriction on this for this example.Further, refering to what is shown in Fig. 3, to the history commodity data
And it dodges purchase historical act data and carries out that sudden strain of a muscle purchase motility model is calculated to may include step S310- step S330.Wherein:
In step s310, it determines the model feature for dodging purchase motility model and obtains the corresponding institute of the model feature
It states history commodity data and dodges purchase historical act data.
In this example embodiment, the model feature of above-mentioned sudden strain of a muscle purchase motility model may include inventory action model,
Abatement amount motility model improves new product exposure rate motility model and balance motility model etc., also may include other moulds
Type feature, such as can be member privilege motility model etc., there is no special restriction on this for this example.It needs to add explanation herein
, it also may include multiple model features, this example is to this that it may include a model feature that a sudden strain of a muscle, which is purchased in motility model,
Special limitation is not done.Further, the model feature based on abatement amount motility model further illustrates to step S310 progress
It is bright.For example:
Firstly, determining that the model feature of abatement amount motility model purchases movable model as the sudden strain of a muscle；Then, abatement amount is obtained
The corresponding history commodity data of motility model and sudden strain of a muscle purchase historical act data.Herein it should be added that, history commodity
Whether data may include: the daily sales volumes of commodity, amount of access, positive rating and promote etc.；Dodging purchase historical act data can
To include: commodity (sku, stock keeping unit) information, sales volume information, amount of access (uv, unique visitor) letter
Breath, every time movable offtake and whether promote etc..
In step s 320, the history commodity data is obtained according to the action message classification for dodging purchase historical act
Characteristic value；Wherein, the characteristic value includes positive characteristic value and negative feature value.
In this example embodiment, the characteristic value for obtaining history commodity data may include: according to history commodity data
The action message classification of affiliated sudden strain of a muscle purchase historical act, classifies to the commodity in the history commodity data described to obtain
The characteristic value of commodity.Specifically:
Refering to what is shown in Fig. 4, firstly, to " dodging purchase historical act data " and " the history quotient being stored in Hadoop cluster
Product data " are associated inquiry, corresponding merchandise news during available each sudden strain of a muscle purchase historical act；Then, by activity
Information is classified, and positive and negative sample data detail is generated；Wherein, positive sample data can be defined as: the activity belongs to manually
The abatement amount type of setting, 7 days historical datas are just before corresponding sku merchandise news and the sku participate in the activity during the activity
Belong to positive sample；Negative sample data can be defined as: what the activity was manually arranged is not belonging to abatement amount type, during the activity
7 days historical datas just belong to negative sample before corresponding sku merchandise news and the sku participate in the activity.Wherein, positive characteristic value can be with
It is marked with 1, negative feature value can be marked with 0, can also use other numbers, such as can be 1 or -1, this example
There is no special restriction on this.
Further, after obtaining the characteristic value of commodity data, can also commodity data be classified and is classified
Polymerization calculate, specifically may include: classified according to the action message classification to the commodity data it is positive and negative to obtain
Sample data；Classification polymerization is carried out to the positive and negative sample data to calculate to obtain the mark sheet collection of positive negative sample.Specifically:
Refering to what is shown in Fig. 4, (such as may include the abatement being manually arranged according to the action message classification for dodging purchase historical act
Amount type or what is be manually arranged be not belonging to abatement amount type etc.) if the corresponding commodity of abatement amount activity are classified and are obtained
Do positive and negative sample data；After the completion of classification, classification polymerization is carried out to the positive and negative sample data and is calculated to obtain positive negative sample
Mark sheet collection.The field of this feature table collection may include: characteristic value (label), such as may include 0 or 1, wherein 0 represents
Negative sample, 1 represents positive sample；Commodity such as may include: befor_sku_price_1 (sku in the price of preset time period
Price at 1 day before activity), befor_sku_price_2 (sku before activity at 2 days price), befor_sku_
Price_3 (sku before activity at 3 days price), befor_sku_price_4 (sku 4 days current prices before activity
Lattice), befor_sku_price_5 (sku before activity at 5 days price), (sku is participating in work to befor_sku_price_6
Price when moving first 6 days), befor_sku_price_7 (sku before activity at 7 days price), befor_sku_price_
Avg7 (sku 7 days average prices before activity), act_sku_price (price during activity)；Commodity are in preset time period
Sales volume, such as may include: befor_sku_ord_1 (sku 1 day sales volume before activity), befor_sku_ord_2
(sku 2 days sales volumes before activity), befor_sku_ord_3 (sku 3 days sales volumes before activity), befor_
(sku is sold for 5 days before activity by sku_ord_4 (sku 4 days sales volumes before activity), befor_sku_ord_5
Amount), befor_sku_ord_6 (sku 6 days sales volumes before activity), (sku is before activity by befor_sku_ord_7
7 days sales volumes), befor_sku_ord_avg7 (sku before activity 7 days average sales volume), (sku's act_sku_ord exists
Average sales volume during activity)；The brand grade of commodity, such as may include: sku_brand_level (Brand
Grade)；The stockpile number of commodity, such as may include: sku_store (stockpile number before commodity activity)；The hair of commodity
Interest rate, such as may include: sku_gross_profit (commodity rate of gross profit)；Commodity preset time period independent visitor's number,
It such as may include: befor_sku_uv_1 (independent visitor number of the sku before activity at 1 day), befor_sku_uv_2
(independent visitor number of the sku before activity at 2 days), befor_sku_uv_3 (independence of the sku before activity at 3 days
Visitor's number), befor_sku_uv_4 (independent visitor number of the sku before activity at 4 days), (sku's befor_sku_uv_5 exists
Independent visitor's number before activity at 5 days), befor_sku_uv_6 (independent visitor number of the sku before activity at 6 days)
Befor_sku_uv_7 (independent visitor number of the sku before activity at 7 days), (sku is being participated in befor_sku_uv_avg_7
Average independent visitor's number before activity at 7 days) etc., it also may include: sku_good (commodity positive rating), sku_like_num
(commodity are by collection number) etc., there is no special restriction on this for this example.It further, will after the completion of the generation of mark sheet collection
This feature table collection is stored into hadoop cluster, and follow-up process is facilitated to read the data.
In step S330, the commodity number for being worth corresponding preset quantity with the positive characteristic value and negative feature is obtained respectively
The model feature is trained according to and using each commodity data to obtain the sudden strain of a muscle purchase motility model.Wherein, it refers to
Shown in Fig. 5, being trained to model may include step S3302- step S3306.Wherein:
In step S3302, the corresponding commodity data of positive characteristic value and negative feature value pair of preset quantity are obtained respectively
The commodity data answered.Specifically:
Refering to what is shown in Fig. 6, acquisition and the associated feature field of characteristic value from Spark cluster, then recycle spark-
Sql writes hql, and selection meets feature field from " abatement amount active samples characteristic value data " table in " hadoop cluster "
Data, then respectively selection return 30W positive sample data and 30W negative sample data.It needs to add explanation herein
It is that the quantity of sample data can be 30W, is also possible to other quantity, such as can be 40W or 50W etc., this example pair
This does not do specifically limited.
In step S3304, the corresponding commodity data of the positive characteristic value and negative feature are worth corresponding commodity data
Random integration is carried out, and the commodity data after random integration is divided into first part and second part.Specifically:
The negative sample data of positive sample data and 30W to above-mentioned 30W upset at random and are combined, then at random
It is divided into two large divisions, a part is the training data (being denoted as trainingSample) for accounting for 70%, and a part is to account for 30% to test
It demonstrate,proves data (being denoted as testSample)；Then by the map function using the RDD in spark, the data upset at random are converted
It can recognize format for subsequent algorithm.Wherein, identifiable format for example may include: [label, vector [befor_sku_
price_1、befor_sku_price_2、、befor_sku_price_avg_7、befor_sku_ord_1、befor_sku_
ord_2、befor_sku_ord_avg_7、befor_sku_uv_1、befor_sku_uv_2、befor_sku_uv_3、befor_
sku_uv_avg_7、act_sku_price、act_sku_ord、sku_store、sku_gross_profit、sku_good]。
Herein it should be further noted that the ratio of above-mentioned first part's data and second part data can be 7:3；It can also be with
It is other ratios, such as can be 6:4 or 8:2 etc., there is no special restriction on this for this example.
In step S3306, the model feature is trained using the commodity data of first part, utilizes second
The commodity data divided is verified the model feature after training to obtain the sudden strain of a muscle purchase motility model.Specifically:
By the logistic regression algorithm in spark-MLLib, then model is trained using 70% sample data, so
30% sample data is recycled to be verified to the model after training to obtain more complete model afterwards.Further, right
It may include: val LRModel=new that model, which is trained the key code api used,
LogisticRegressionWithLBFGS () .run (trainingSku Sample)), then trained logic is returned
Model (being denoted as: CL-LRModel) is returned to carry out the test to verify data；It is secondary by being repeated as many times, choose a verifying rate highest
It is primary.Then the model is saved in spark and (can specify a directory path to save).
Further, in order to improve the precision of model training, it can use the higher commodity data of importance values to model
It is trained, specifically may include: to calculate separately the corresponding commodity data of the positive characteristic value using random forests algorithm
Importance values and negative feature are worth the importance values of corresponding commodity data.Specifically: refering to what is shown in Fig. 7, firstly, utilizing
Then spark-sql technology returns to positive sample by inquiring " abatement amount active samples characteristic value " data from hadoop cluster
This 30W data, negative sample 30W data；The positive sample data and negative sample data are saved in specified file and are stored to finger
Determine under catalogue；Secondly, reading positive sample data and negative sample data, and generate the training data that random forests algorithm can identify
P, the format of the training data may include: [label, vector [befor_sku_price_1, befor_sku_price_2,
befor_sku_price_3、befor_sku_price_4、befor_sku_price_5、befor_sku_price_6、
befor_sku_price_7、befor_sku_price_avg_7、befor_sku_ord_1、befor_sku_ord_2、
befor_sku_ord_3、befor_sku_ord_4、befor_sku_ord_5、befor_sku_ord_6、befor_sku_
ord_7、befor_sku_ord_avg_7、befor_sku_uv_1、befor_sku_uv_2、befor_sku_uv_3、befor_
sku_uv_4、befor_sku_uv_5、befor_sku_uv_6、befor_sku_uv_7、befor_sku_uv_avg_7、act_
sku_price、act_sku_ord、sku_brand_level、sku_store、sku_gross_profit、sku_good、
Sku_like_num] etc.；Finally, using the random forests algorithm in spark_sklearn to training data in previous step into
Row training, then calls importances=forest.feature_importances_ after training；importances
[feature field] can export the importance values (value between 0 to 1) of " feature field ", such as: importances [sku_
Gross_profit]=0.65, indicate this feature of sku_gross_profit or important.Wherein, random forest
Algorithm can be api packaged in the library sklearn, can directly call, and the class and method of calling may include: forest=
RandomForestClassifier (n_estimators=10000, random_state=0, n_jobs=-1)；
Forest.fit (training data P)).
Further, after importance values calculate completion, importance values can also be ranked up, is specifically can wrap
It includes: the importance values is ranked up and judge whether the importance values are greater than preset value；Judging the importance values
When greater than the preset value, the corresponding commodity of the importance values are saved.Specifically: above-mentioned importance values are ranked up,
Then will be greater than preset value (such as can be 0.65, be also possible to other values, such as can be 0.7 etc., this example to this not
Do specifically limited) before the corresponding commodity data of several importance values saved.By calculating importance values and to importance
Value is ranked up, and can be found out most important several characteristic values as final mask training, further be improved the essence of model
Degree allows to more preferably generate the sudden strain of a muscle purchase activity of high quality.
In step S220, obtains multiple merchandise newss and picked out in the multiple merchandise news and meet sudden strain of a muscle purchase
The merchandise news of motility model.Specifically:
Refering to what is shown in Fig. 8, " can be participated in recently from presto cluster firstly, write hql sentence by spark-sql
Dodge purchase merchandise news " and " commodity historical data " table in find out and can participate in the movable commodity detailed data of sudden strain of a muscle purchase, then again
These detailed datas are converted into the corresponding data value of front Features these fields, and then obtaining from Presto cluster again can
Movable merchandise news is purchased to participate in sudden strain of a muscle, and according to the movable preset condition of abatement amount, picks out and meets from the merchandise news
The movable merchandise news of abatement amount；Secondly, screening to select merchandise news, it is only stored in spark memory
In the corresponding Value Data of feature field, be data；Finally, Data data are passed through the map method of spark, conversion
At the data format that model can identify, format may include: (sku_id, feature), wherein the format of feature can be with
It include: [befor_sku_price_1, befor_sku_price_2, befor_sku_price_avg_7, befor_sku_
ord_1、befor_sku_ord_2、befor_sku_ord_avg_7、befor_sku_uv_1、befor_sku_uv_2、
befor_sku_uv_3、befor_sku_uv_avg_7、act_sku_price、act_sku_ord、sku_store、sku_
Gross_profit, sku_good] etc.；Further, the MODEL C L- being stored in front of can recalling in spark cluster
LRModel returns to 0 or 1 value, if what is returned is 1, just representing the commodity can be used as punching by calling predict method
Amount activity；Then the sku_id of this commodity is stored into elasticsearch cluster, follow-up process is facilitated to call.
It is raw according to the merchandise news dodged purchase motility model and meet the sudden strain of a muscle purchase motility model in step S230
At the sudden strain of a muscle purchase activity for meeting the sudden strain of a muscle purchase motility model.Specifically:
Refering to what is shown in Fig. 8, " the meeting momentum motility model commodity data " being stored in elasticsearch cluster
Data query comes out, and then carries out random generation activity according to multiple rules；After having generated, if there are also commodity to be not engaged in
It arrives, just in commodity deposit " surplus commodities " table being not engaged in, is continued to use when being conveniently subsequently generated activity again；Further
, the activity automatically generated can be pushed to evaluation list, audit to operation personnel, auditing the activity passed through will participate in automatically
The sudden strain of a muscle purchase activity issued next time；Wherein, above-mentioned rule may include: that the sku of regular 1: one detachable lining must belong to 2 grades
Classification；The sku quantity of regular 2: one detachable linings cannot be greater than 600；Rule 3: the amount of activity automatically generated every time is not more than
50；Also may include other rule, such as can be detachable lining sku quantity cannot less than 50 etc., this example to this not
It does specifically limited.
This example embodiment additionally provides a kind of sudden strain of a muscle purchase activity automatically generating device.Refering to what is shown in Fig. 9, the sudden strain of a muscle purchase activity
Automatically generating device may include computing module 910, Choosing module 920 and sudden strain of a muscle purchase activity generation module 930.Wherein:
Computing module 910, which can be used for obtaining history commodity data and dodge, purchases historical act data and to the history quotient
Product data and sudden strain of a muscle purchase historical act data carry out that sudden strain of a muscle purchase motility model is calculated.
Choosing module 920, which can be used for obtaining multiple merchandise newss and pick out in the multiple merchandise news, meets institute
State the merchandise news for dodging purchase motility model.
Dodging purchase activity generation module 930 can be used for purchasing motility model according to the sudden strain of a muscle and meets the sudden strain of a muscle purchase movable mold
The merchandise news of type, which generates, meets the sudden strain of a muscle purchase activity for dodging purchase motility model.
The detail of each module is given birth in corresponding sudden strain of a muscle purchase activity automatically in above-mentioned sudden strain of a muscle purchase activity automatically generating device
At having carried out wanting to describe in detail in method, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Figure 10.The electricity that Figure 10 is shown
Sub- equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in Figure 10, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can be with
Including but not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 630 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute step S210 as shown in Figure 2: acquisition is gone through
History commodity data and sudden strain of a muscle purchase historical act data simultaneously count the history commodity data and sudden strain of a muscle purchase historical act data
Calculation obtains sudden strain of a muscle purchase motility model；S220: multiple merchandise newss are obtained and are picked out in the multiple merchandise news meet institute
State the merchandise news for dodging purchase motility model；Step S230: motility model is purchased according to the sudden strain of a muscle and meets the sudden strain of a muscle and purchases movable mold
The merchandise news of type, which generates, meets the sudden strain of a muscle purchase activity for dodging purchase motility model.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
With reference to shown in Figure 11, the program product for realizing the above method of embodiment according to the present invention is described
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (12)
1. a kind of sudden strain of a muscle purchase activity automatic generation method characterized by comprising
It obtains history commodity data and dodges purchase historical act data and historical act is purchased to the history commodity data and sudden strain of a muscle
Data carry out that sudden strain of a muscle purchase motility model is calculated；
It obtains multiple merchandise newss and is picked out in the multiple merchandise news and meet the commodity letter for dodging purchase motility model
Breath；
Meet the sudden strain of a muscle purchase according to the merchandise news generation dodged purchase motility model and meet the sudden strain of a muscle purchase motility model to live
The sudden strain of a muscle purchase activity of movable model.
2. sudden strain of a muscle purchase activity automatic generation method according to claim 1, which is characterized in that the history commodity data with
And it dodges purchase historical act data and be calculated sudden strain of a muscle purchase motility model and include:
Determine it is described dodge purchase motility model model feature and obtain the corresponding history commodity data of the model feature with
And dodge purchase historical act data；
The characteristic value of the history commodity data is obtained according to the action message classification for dodging purchase historical act；Wherein, described
Characteristic value includes positive characteristic value and negative feature value；
It obtains respectively and is worth the commodity data of corresponding preset quantity with the positive characteristic value and negative feature and utilizes each quotient
Product data are trained the model feature to obtain the sudden strain of a muscle purchase motility model.
3. sudden strain of a muscle purchase activity automatic generation method according to claim 2, which is characterized in that purchase historical act according to the sudden strain of a muscle
Action message classification obtain the characteristic value of the history commodity data and include:
The action message classification of sudden strain of a muscle purchase historical act according to belonging to history commodity data, to the quotient in the history commodity data
Product are classified to obtain the characteristic value of the commodity.
4. sudden strain of a muscle purchase activity automatic generation method according to claim 3, which is characterized in that the history commodity data
In commodity classify to obtain the characteristic value of commodity after, the sudden strain of a muscle purchase activity automatic generation method further include:
Classified to the commodity data according to the action message classification to obtain positive and negative sample data；
Classification polymerization is carried out to the positive and negative sample data to calculate to obtain the mark sheet collection of positive negative sample.
5. sudden strain of a muscle purchase activity automatic generation method according to claim 4, which is characterized in that the field packet of the mark sheet collection
Characteristic value, commodity are included in the price of preset time period, commodity in the sales volume of preset time period, the brand grade of commodity, commodity
Stockpile number, the rate of gross profit of commodity, commodity are a variety of in independent visitor's number of preset time period.
6. sudden strain of a muscle purchase activity automatic generation method according to claim 2, which is characterized in that obtain and the positive feature respectively
Value and negative feature are worth the commodity data of corresponding preset quantity and are carried out using each commodity data to the model feature
It trains to obtain the sudden strain of a muscle purchase motility model and include:
The corresponding commodity data of positive characteristic value and negative feature for obtaining preset quantity respectively are worth corresponding commodity data；
The corresponding commodity data of the positive characteristic value and negative feature are worth corresponding commodity data and carry out random integration, and will be with
Commodity data after machine integration is divided into first part and second part；
The model feature is trained using the commodity data of first part, using the commodity data of second part to training
Model feature afterwards is verified to obtain the sudden strain of a muscle purchase motility model.
7. sudden strain of a muscle purchase activity automatic generation method according to claim 6, which is characterized in that the commodity number of the first part
Ratio according to the commodity data with the second part is 7:3.
8. sudden strain of a muscle purchase activity automatic generation method according to claim 2, which is characterized in that the sudden strain of a muscle purchase activity automatically generates
Method further include:
The importance values and negative feature value of the corresponding commodity data of the positive characteristic value are calculated separately using random forests algorithm
The importance values of corresponding commodity data.
9. sudden strain of a muscle purchase activity automatic generation method according to claim 8, which is characterized in that the sudden strain of a muscle purchase activity automatically generates
Method further include:
The importance values are ranked up and judge whether the importance values are greater than preset value；
When judging that the importance values are greater than the preset value, the corresponding commodity of the importance values are saved.
10. a kind of sudden strain of a muscle purchase activity automatically generating device characterized by comprising
Computing module, for obtain history commodity data and dodge purchase historical act data and to the history commodity data and
Purchase historical act data are dodged to carry out that sudden strain of a muscle purchase motility model is calculated；
Choosing module meets the sudden strain of a muscle purchase activity for obtaining multiple merchandise newss and picking out in the multiple merchandise news
The merchandise news of model；
Purchase activity generation module is dodged, for believing according to the commodity for dodging purchase motility model and meeting the sudden strain of a muscle purchase motility model
Breath, which generates, meets the sudden strain of a muscle purchase activity for dodging purchase motility model.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 1-9 described in any item sudden strain of a muscle purchase activity automatic generation methods are realized when being executed by processor.
12. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to require 1-9 described in any item via executing the executable instruction and carry out perform claim
Dodge purchase activity automatic generation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710778696.4A CN109426983A (en) | 2017-09-01 | 2017-09-01 | Dodge purchase activity automatic generation method and device, storage medium, electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710778696.4A CN109426983A (en) | 2017-09-01 | 2017-09-01 | Dodge purchase activity automatic generation method and device, storage medium, electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109426983A true CN109426983A (en) | 2019-03-05 |
Family
ID=65512764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710778696.4A Pending CN109426983A (en) | 2017-09-01 | 2017-09-01 | Dodge purchase activity automatic generation method and device, storage medium, electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109426983A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189200A (en) * | 2019-05-27 | 2019-08-30 | 深圳远航股份有限公司 | A method of based on big data and search engine fast construction electric business sales field |
| CN110189187A (en) * | 2019-04-15 | 2019-08-30 | 深圳平安综合金融服务有限公司 | Merchandise control method, apparatus, computer equipment and storage medium |
| CN112837076A (en) * | 2021-02-24 | 2021-05-25 | 上海悦易网络信息技术有限公司 | Method, system and equipment for automatically generating commodity order |
| CN112967109A (en) * | 2021-03-15 | 2021-06-15 | 杭州邻汇网络科技有限公司 | Intelligent flash shop product selection method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100179855A1 (en) * | 2009-01-09 | 2010-07-15 | Ye Chen | Large-Scale Behavioral Targeting for Advertising over a Network |
| US20140310001A1 (en) * | 2013-04-16 | 2014-10-16 | Sri International | Using Intents to Analyze and Personalize a User's Dialog Experience with a Virtual Personal Assistant |
| CN105426467A (en) * | 2015-11-16 | 2016-03-23 | 北京京东尚科信息技术有限公司 | SQL query method and system for Presto |
| CN106056427A (en) * | 2016-05-25 | 2016-10-26 | 中南大学 | Spark-based big data hybrid model mobile recommending method |
| CN106127525A (en) * | 2016-06-27 | 2016-11-16 | 浙江大学 | A kind of TV shopping Method of Commodity Recommendation based on sorting algorithm |
| CN106204239A (en) * | 2016-07-24 | 2016-12-07 | 广东聚联电子商务股份有限公司 | A kind of ecommerce Method of Commodity Recommendation based on big data multiple labeling |
| CN106600302A (en) * | 2015-10-19 | 2017-04-26 | 玺阅信息科技（上海）有限公司 | Hadoop-based commodity recommendation system |
| CN106649503A (en) * | 2016-10-11 | 2017-05-10 | 北京集奥聚合科技有限公司 | Query method and system based on sql |
| CN107038190A (en) * | 2016-10-28 | 2017-08-11 | 厦门大学 | A kind of intelligent promotion plan modeling method applied to Taobao |
-
2017
- 2017-09-01 CN CN201710778696.4A patent/CN109426983A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100179855A1 (en) * | 2009-01-09 | 2010-07-15 | Ye Chen | Large-Scale Behavioral Targeting for Advertising over a Network |
| US20140310001A1 (en) * | 2013-04-16 | 2014-10-16 | Sri International | Using Intents to Analyze and Personalize a User's Dialog Experience with a Virtual Personal Assistant |
| CN106600302A (en) * | 2015-10-19 | 2017-04-26 | 玺阅信息科技（上海）有限公司 | Hadoop-based commodity recommendation system |
| CN105426467A (en) * | 2015-11-16 | 2016-03-23 | 北京京东尚科信息技术有限公司 | SQL query method and system for Presto |
| CN106056427A (en) * | 2016-05-25 | 2016-10-26 | 中南大学 | Spark-based big data hybrid model mobile recommending method |
| CN106127525A (en) * | 2016-06-27 | 2016-11-16 | 浙江大学 | A kind of TV shopping Method of Commodity Recommendation based on sorting algorithm |
| CN106204239A (en) * | 2016-07-24 | 2016-12-07 | 广东聚联电子商务股份有限公司 | A kind of ecommerce Method of Commodity Recommendation based on big data multiple labeling |
| CN106649503A (en) * | 2016-10-11 | 2017-05-10 | 北京集奥聚合科技有限公司 | Query method and system based on sql |
| CN107038190A (en) * | 2016-10-28 | 2017-08-11 | 厦门大学 | A kind of intelligent promotion plan modeling method applied to Taobao |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189187A (en) * | 2019-04-15 | 2019-08-30 | 深圳平安综合金融服务有限公司 | Merchandise control method, apparatus, computer equipment and storage medium |
| CN110189200A (en) * | 2019-05-27 | 2019-08-30 | 深圳远航股份有限公司 | A method of based on big data and search engine fast construction electric business sales field |
| CN112837076A (en) * | 2021-02-24 | 2021-05-25 | 上海悦易网络信息技术有限公司 | Method, system and equipment for automatically generating commodity order |
| CN112967109A (en) * | 2021-03-15 | 2021-06-15 | 杭州邻汇网络科技有限公司 | Intelligent flash shop product selection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN107590688A (en) | The recognition methods of target customer and terminal device | |
| CN109754200A (en) | Bill of material management method, apparatus and computer readable storage medium | |
| WO2019037391A1 (en) | Method and apparatus for predicting customer purchase intention, and electronic device and medium | |
| CN109360012A (en) | The selection method and device, storage medium, electronic equipment of advertisement dispensing channel | |
| CN109840730B (en) | Method and device for data prediction | |
| US20210142249A1 (en) | Consolidated resource management across multiple services | |
| CN109426983A (en) | Dodge purchase activity automatic generation method and device, storage medium, electronic equipment | |
| CN109784978A (en) | Advertisement competition power calculation method, device, medium and equipment based on big data | |
| CN109559138A (en) | Dodge purchase activity sales volume prediction technique and device, storage medium, electronic equipment | |
| CN104166920A (en) | Online biding method and system | |
| CN107679103B (en) | Attribute analysis method and system for entity | |
| CN109615504A (en) | Products Show method, apparatus, electronic equipment and computer readable storage medium | |
| CN112214508B (en) | Data processing method and device | |
| CN110009229A (en) | Supply chain management method, device, storage medium and equipment based on block chain | |
| CN108595507A (en) | Data circulation method, apparatus and system, storage medium, terminal | |
| CN108647239A (en) | Talk with intension recognizing method and device, equipment and storage medium | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| Agarwal et al. | Machine Learning and Natural Language Processing in Supply Chain Management: A Comprehensive Review and Future Research Directions. | |
| CN106600360B (en) | Method and device for sorting recommended objects | |
| CN109785147A (en) | Insurance kind sort method and device, electronic equipment and computer readable storage medium | |
| CN109598410A (en) | Presell methods of risk assessment, system, computer installation and readable storage medium storing program for executing | |
| CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
| CN110889716A (en) | Method and device for identifying potential registered user | |
| CN111768218A (en) | Method and device for processing user interaction information |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190305 |