CN112581158A - Information processing system and method for member to buyback commodity - Google Patents
Information processing system and method for member to buyback commodity Download PDFInfo
- Publication number
- CN112581158A CN112581158A CN201910973294.9A CN201910973294A CN112581158A CN 112581158 A CN112581158 A CN 112581158A CN 201910973294 A CN201910973294 A CN 201910973294A CN 112581158 A CN112581158 A CN 112581158A
- Authority
- CN
- China
- Prior art keywords
- buyback
- consumption
- time
- consumption data
- index
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000003672 processing method Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0236—Incentive or reward received by requiring registration or ID from user
-
- 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
- G06Q30/02—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)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an information processing system and method for a member to buyback commodities, wherein the method comprises the following steps: acquiring all member consumption data provided by a manufacturer; storing all member consumption data of the manufacturer; establishing a consumption data list of each member according to all member consumption data of the manufacturer, wherein the consumption data list comprises the last consumption day, consumption frequency, consumption amount and a buyback index; inputting the consumption data list of each member into a buyback model to obtain a rate of whether each member buybacks commodities; storing the probability of whether each member buys commodities back to the consumption data list of each member; and outputting a list of repurchase commodities including the consumption data list of each member for the manufacturer to browse.
Description
Technical Field
The present invention relates to an information processing system and method for a member to buyback merchandise, and more particularly, to an information processing system and method for a member to buyback merchandise, which can predict whether the member buyback merchandise.
Background
When a general member consumer consumes goods, a store or a manufacturer provides the goods according to the actual demand of the member consumer, and records all information such as a consumption list of the member consumer from the time of registering the member to the time.
Besides counting the consumption lists of all the member consumers, the store and the manufacturer provide the current season commodity types of all the member consumers for the reference of the member consumers, so that the member consumers can purchase according to the demands of the store or the manufacturer.
However, the store and the manufacturer cannot predict when the member consumer will make a purchase to grasp the need of the member consumer, and in view of the above disadvantages, the inventors of the present invention have made an idea and study on the above disadvantages to solve the current disadvantages and improve the disadvantages.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an information processing method for a member to buy a commodity again aiming at the deficiency of the prior art, which is characterized by comprising the following steps: acquiring all member consumption data provided by a manufacturer; storing all member consumption data of the manufacturer to a member database; transmitting all member consumption data of the manufacturer to a processor, and establishing a consumption data list of each member by the processor according to all the member consumption data of the manufacturer, wherein the consumption data list comprises a last consumption day (Recency), a consumption Frequency (Frequency), a consumption amount (Monerary) and a Repurchase Index (Repurchase Index); inputting the consumption data list of each member into a buyback model by using the processor to obtain a rate of whether each member buybacks commodities; storing the probability of whether each member buys commodities back to the consumption data list of each member by using the processor; and outputting a list of repurchase commodities including the consumption data list of each member by using the processor for browsing by the manufacturer.
Preferably, the method further comprises the following steps: obtaining the last consumption day, the consumption frequency, the consumption amount and the buyback index in a first time section in the consumption data list of each member by utilizing the processor to input the latest consumption day, the consumption frequency, the consumption amount and the buyback index into the buyback model so as to obtain the probability of whether each member buyback commodities in a second time section; the second time interval is smaller than the first time interval, and the second time interval is subsequent to the first time interval.
Preferably, the method further comprises the following steps: obtaining the total consumption times and the total consumption amount in a first time section in the consumption data list of each member by utilizing the processor to find out the maximum value of the total consumption times and the maximum value of the total consumption amount in the first time section in all member consumption data of the manufacturer; calculating a first ratio of the total consumption times of each member in the first time section to the maximum value of the total consumption times of the manufacturer in all member consumption data, and a second ratio of the total consumption amount of each member in the first time section to the maximum value of the total consumption amount of the manufacturer in all member consumption data; obtaining a first weighting index and a second weighting index by the processor according to the commodity characteristics or the industry characteristics; and calculating the first proportion weighted by the first weighted index and the second proportion weighted by the second weighted index by the processor to generate the buyback index; wherein the first weighted index is the merchandise preference index of each member, and the second weighted index is the consumption amount index of each member; wherein the sum of the first weighted index and the second weighted index is 1.
Preferably, the method further comprises the following steps: inputting all member consumption data of the manufacturer in a third time zone into the buyback model by utilizing the processor so as to train and optimize buyback model parameters of the buyback model; inputting the consumption data list of at least one member in the third time zone and a fourth time zone into the buyback model by using the processor so as to correct the buyback model parameters of the buyback model; establishing the buyback model by using the processor according to the corrected buyback model parameters; wherein the fourth time segment is smaller than the third time segment, and the fourth time segment is subsequent to the third time segment.
Preferably, the consumption data list of the at least one member in the third time period and the fourth time period further includes a value indicating whether the member has purchased merchandise in the third time period and the fourth time period; when the at least one member has bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 0, and when the at least one member has not bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 1.
The invention also provides an information processing system for the member to buyback commodities, which is characterized by comprising the following components: a receiver for acquiring all member consumption data provided by a manufacturer; a member database for storing all member consumption data of the manufacturer; the processor receives all member consumption data of the manufacturer, establishes a consumption data list of each member according to all member consumption data of the manufacturer, inputs the consumption data list of each member to a buyback model to obtain a probability of whether each member buyback commodities, stores the probability of whether each member buyback commodities to the consumption data list of each member, and outputs a buyback commodity list comprising the consumption data list of each member for the manufacturer to browse; the consumption data list includes a last consumption day (Recency), a consumption Frequency (Frequency), a consumption amount (Monerary), and a Repurchase Index (Repurchase Index).
Preferably, the processor obtains the last consumption day, the consumption frequency, the consumption amount and the buyback index in a first time zone of the consumption data list of each member to input the probability of whether buyback of commodities will be performed in a second time zone of each member into the buyback model; the second time interval is smaller than the first time interval, and the second time interval is subsequent to the first time interval.
Preferably, the processor obtains the total consumption times and the total consumption amount in a first time segment in the consumption data list of each member to find out the maximum value of the total consumption times and the maximum value of the total consumption amount in the first time segment in all the member consumption data of the manufacturer; the processor calculates a first ratio of the total consumption times of each member in the first time section to the maximum value of the total consumption times of the manufacturer in all member consumption data, and a second ratio of the total consumption amount of each member in the first time section to the maximum value of the total consumption amount of the manufacturer in all member consumption data; the processor obtains a first weighting index and a second weighting index according to the commodity characteristics or the industry characteristics; the processor calculates the first proportion weighted by the first weighted index and the second proportion weighted by the second weighted index to generate the buyback index; wherein the first weighted index is the merchandise preference index of each member, and the second weighted index is the consumption amount index of each member; wherein the sum of the first weighted index and the second weighted index is 1.
Preferably, the processor inputs all member consumption data of the manufacturer in a third time period into the buyback model to train and optimize buyback model parameters of the buyback model; the processor inputs the consumption data list of at least one member in the third time section and a fourth time section into the buyback model so as to correct the buyback model parameters of the buyback model; the processor establishes the buyback model according to the revised buyback model parameters; wherein the fourth time segment is smaller than the third time segment, and the fourth time segment is subsequent to the third time segment.
Preferably, the consumption data list of the at least one member in the third time period and the fourth time period further includes a value indicating whether the member has purchased merchandise in the third time period and the fourth time period; when the at least one member has bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 0, and when the at least one member has not bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 1.
The information processing system and the method for the member to buyback commodities can count the consumption data lists of all the members according to the past consumption records of all the members provided by a manufacturer, and obtain the key indexes such as the last consumption day, the consumption frequency, the consumption amount, the buyback index and the like in the consumption data of all the members so as to predict whether each member buyback commodities.
For a better understanding of the features and technical content of the present invention, reference should be made to the following detailed description and accompanying drawings, which are provided for purposes of illustration and description only and are not intended to limit the invention.
Drawings
Fig. 1 is a block diagram of an information processing system for a member to buyback merchandise according to an embodiment of the present invention.
Fig. 2 is a flowchart of an information processing method for a member to buy back a commodity according to an embodiment of the present invention.
FIG. 3 is a flow chart of the generation of a buyback indicator according to an embodiment of the present invention.
FIG. 4 is a flow chart of the buyback model establishment according to an embodiment of the present invention.
FIG. 5 is a flowchart illustrating a value generation process of whether each member buys merchandise again according to the embodiment of the present invention.
Detailed Description
The following is a description of embodiments of the information processing system and method for member buyback merchandise disclosed in the present invention, and those skilled in the art will understand the advantages and effects of the present invention from the disclosure of the present specification. The invention is capable of other and different embodiments and its several details are capable of modifications and various changes in detail, all without departing from the spirit and scope of the present invention. The drawings of the present invention are for illustrative purposes only and are not intended to be drawn to scale. The following embodiments will further explain the related art of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
It will be understood that, although the terms "first," "second," "third," etc. may be used herein to describe various components or signals, these components or signals should not be limited by these terms. These terms are used primarily to distinguish one element from another element or from one signal to another signal. In addition, the term "or" as used herein should be taken to include any one or combination of more of the associated listed items as the case may be.
Referring to fig. 1, a block diagram of an information processing system for a member to buyback merchandise according to an embodiment of the present invention is shown. The information processing system 1 for member to buy back merchandise of the present invention comprises a receiver 2, a member database 3 and a processor 4.
The transceiver 2 in the information processing system 1 for the member to buy back the commodity is connected to a manufacturer 6 through the internet 5 to obtain all member consumption data provided by the manufacturer 6, and the manufacturer 6 comprises a server or a database, the server or the database of the manufacturer stores the consumption data of all members, wherein all the member consumption data comprises member personal data and member consumption data of each member, such as member number, member registration date, consumed commodity amount, consumed commodity time, consumed commodity times, consumed commodity position and the like. It should be noted that the member consumption data may be set according to the actual requirements of the manufacturer 6, and the present invention is not limited thereto.
The member database 3 of the information processing system 1 for the member to buy back merchandise is connected to the transceiver 2 to store all the member consumption data provided by the manufacturer 6, wherein the member database 3 is a server or a database.
The processor 4 of the information processing system 1 for member to Repurchase commodities is connected to the member database 3 to receive all member consumption data of the manufacturer 6, and establishes a consumption data list of each member according to all member consumption data of the manufacturer 6, wherein the consumption data list comprises a last consumption day (Recency), a consumption Frequency (Frequency), a consumption amount (Monerary), and a Repurchase index (Repurchase index). The last consumption day refers to the time interval from the last consumption of the consumer to the last consumption, the consumption frequency refers to the total transaction number accumulated by the consumer in a specific time, the consumption amount refers to the total transaction amount of the consumer in the specific time, and the repurchase index refers to the index of repurchasing the commodities again by the consumer in the specific time.
In one embodiment, the processor 4 obtains the total number of consumptions and the total amount of consumption in a first time period from the consumption data list of each member to find the maximum value of the total number of consumptions and the maximum value of the total amount of consumption in the first time period from all the member consumption data of the manufacturer 6. The processor 4 calculates a first ratio of the total consumption times in the first time section of each member to the maximum value of the total consumption times in the first time section in all the member consumption data of the manufacturer, and calculates a second ratio of the total consumption amount in the first time section of each member to the maximum value of the total consumption amount in the first time section in all the member consumption data of the manufacturer 6. The processor 4 obtains a first weighting index and a second weighting index according to the product characteristics or the industry characteristics. The processor 4 calculates a first weighted-index-weighted first ratio and a second weighted-index-weighted second ratio to generate a buyback indicator. Wherein the first weighted index is a commodity preference index of the member, the second weighted index is a consumption amount index of the member, and the sum of the first weighted index and the second weighted index is 1. Wherein the commodity preference index is, for example, a preference of the member or an index of the commodity preferred to be purchased, and the consumption amount index is, for example, an index of which consumption amount interval the consumption amount of the member is located. It should be noted that the commodity preference index and the consumption amount index may be set according to the actual requirement of the manufacturer 6, and the invention is not limited thereto.
In one example, the first time segment is four seasons of 2018, the commercial property is, for example, the shoes and the shoe consumption cycle is half a year, the total number of times that a member consumes the shoes in the four seasons of 2018 is 2 times and the total amount of consumed shoes is 6000 yuan, the total number of times that a member consumes the shoes in all members in the four seasons of 2018 is 8 times, the maximum value of the total number of times that the member consumes the shoes is the maximum value of the total amount of consumed shoes, the manufacturer 6 sets the first weighting index to be 0.3 and the second weighting index to be 0.7 according to the commercial property, and the buyback index is equal to 0.3 (2/8) +0.7 (6000/30000) 0.215, wherein the larger the value of the buyback index represents the higher probability of buyback. It should be noted that the first time period, the commodity characteristics or the industry characteristics, the first weighting index and the second weighting index may be set according to the actual requirements of the manufacturer 6, and the invention is not limited thereto.
The processor 4 of the information processing system 1 for member to buyback merchandise inputs the consumption data list of each member to the buyback model to obtain a probability of whether each member will buyback merchandise.
In one embodiment, the processor 4 inputs all member consumption data of the manufacturer 6 in a third time period into the buyback model to train and optimize buyback model parameters of the buyback model, the processor 4 inputs at least one member consumption data list in the third time period and a fourth time period into the buyback model to modify buyback model parameters of the buyback model, and the processor 4 establishes the buyback model according to the modified buyback model parameters. Wherein the fourth time segment is smaller than the third time segment, and the fourth time segment is subsequent to the third time segment.
In addition, the consumption data list of at least one member in the third time zone and the fourth time zone also comprises a numerical value of whether the at least one member buys back the commodities in the third time zone and the fourth time zone simultaneously; when at least one member buys the commodities in the third time zone and the fourth time zone at the same time, the value of whether to buyback the commodities is 0, and when at least one member does not buyback the commodities in the third time zone and the fourth time zone at the same time, the value of whether to buyback the commodities is 1.
In one example, after the processor 4 obtains the last consumption day, consumption frequency, consumption amount, and the repurchase index, the processor 4 converts the last consumption day, consumption frequency, and consumption amount from the original percentage format to a score interval (1-5 points), as shown in table 1.
After the processor 4 receives all the member consumption data of the manufacturer 6, the processor 4 performs data preprocessing on all the member consumption data of the manufacturer 6 to obtain the latest consumption day, consumption frequency, consumption amount and buyback index of each member, converts the latest consumption day, consumption frequency and consumption amount from a percentage format into a fraction interval, the processor 4 inputs the member consumption data of all the members in a third time zone into a buyback model to train, iterate and optimize buyback model parameters through a machine learning algorithm (such as XGBoost), the processor 4 inputs consumption data lists of a plurality of members in the third time zone and a fourth time zone into the buyback model to correct the buyback model parameters of the buyback model, and the processor 4 determines and establishes the buyback model according to the corrected buyback model parameters. The machine learning algorithm obtains the characteristics of the consumer purchasing the commodity through a data exploration technology according to consumption data generated by the consumer individually or integrally, and generates a model for predicting whether the consumer buys the commodity or not through machine learning technology training. It should be noted that the machine learning algorithm in the buyback model may be selected according to the actual needs of the manufacturer 6, and the present invention is not limited thereto.
In one example, the third time segment is, for example, the fourth season of 2017 to the third season of 2018, the fourth time segment is, for example, the fourth season of 2018, the processor 4 obtains consumption data of all members and performs data preprocessing to obtain the last consumption day, consumption frequency, consumption amount and purchase-back index of each member, and converting the last consumption day, consumption frequency and consumption amount from percentage format to fraction interval, the processor 4 inputs the member consumption data of all members from the fourth season of 2017 to the third season of 2018 into the buyback model for training, iterating and optimizing buyback model parameters, and the processor 4 inputs the consumption data lists of the plurality of members from the fourth season of 2017 to the third season of 2018 and the fourth season of 2018 into the buyback model to correct buyback model parameters of the buyback model, and the processor 4 determines and establishes the buyback model according to the corrected buyback model parameters. Wherein, the consumption data lists of the members from the fourth season of 2017 to the third season of 2018 and from the fourth season of 2018 also comprise a numerical value of whether the members buy the commodities again from the fourth season of 2017 to the third season of 2018 and from the fourth season of 2018; when one of the members buys commodities from the fourth season of 2017 to the third season of 2018 and from the fourth season of 2018 at the same time, the value of whether the member buys commodities is 0, and when one of the members does not buys commodities from the fourth season of 2017 to the third season of 2018 and from the fourth season of 2018 at the same time, the value of whether the member buys commodities is 1. It should be noted that the third time period and the fourth time period can be set according to the actual requirements of the manufacturer 6, and the invention is not limited thereto.
In one embodiment, the processor 4 obtains the last consumption day, consumption frequency, consumption amount, and buyback index in the first time period of the consumption data list of each member to input the obtained data into the buyback model to obtain the probability of whether each member buyback the merchandise in a second time period. The second time interval is smaller than the first time interval, and the second time interval is subsequent to the first time interval.
In one example, the first time segment is the four seasons of 2018, the second time segment is the first season of 2019, and the processor 4 obtains the last consumption day, consumption frequency, consumption amount, and buyback index of the four seasons of 2018 in the consumption data list of each member to input the obtained consumption date, consumption frequency, consumption amount, and buyback index into the buyback model to obtain the probability of whether the member buyback the product in the first season of 2019. It should be noted that the first time segment, the second time segment, the third time segment and the fourth time segment may be set according to the actual requirements of the manufacturer 6, for example, the units of year, month, day, hour, etc. may be used as the time segments, and the invention is not limited thereto.
The processor 4 of the information processing system 1 for member to buy back merchandise stores the probability of whether each member will buy back merchandise into the consumption data list of each member.
The processor 4 of the information processing system 1 for member buys back commodities outputs a buys-back commodity list including a consumption data list of each member for the vendor 6 to browse. The buyback commodity list includes consumption data of all members provided by the manufacturer 6 and also includes a probability of whether each member buybacks commodities in a next time zone, so that the manufacturer 6 can know the probability of whether the members can not buyback commodities in the next time zone according to the buyback commodity list, and the manufacturer 6 counts the proportion of buyback and buyback of the members in the next time zone, the proportion of buyback commodities in actual buyback commodities among members which actually buyback commodities, the proportion of members which predict actual buyback commodities among members which purchase commodities, and the like.
Referring to fig. 1 and fig. 2, fig. 2 is a flowchart illustrating an information processing method for a member to buy a commodity again according to an embodiment of the present invention. The information processing method for the member to buyback the commodities comprises the following steps: s1: acquiring all member consumption data provided by a manufacturer 6; s2: storing all member consumption data of the manufacturer 6 into a member database 3; s3: transmitting all member consumption data of a manufacturer 6 to a processor 4, the processor 4 establishing a consumption data list of each member according to all member consumption data of the manufacturer 6, wherein the consumption data list comprises a last consumption day (Recency), a consumption Frequency (Frequency), a consumption amount (Monerary) and a Repurchase index (Repurchase index); s4: inputting the consumption data list of each member into a buyback model by using the processor 4 to obtain a rate of whether each member buybacks commodities; s5: storing the probability of whether each member buys the commodities back to the consumption data list of each member by using the processor 4; and S6: a list of buyback items including a list of consumption data for each member is output by the processor 4 for viewing by the vendor 6. In addition, the examples of the method for the member to buy the merchandise again according to the embodiment of the present invention are the same as those described above, and therefore, the description thereof is omitted.
In step S3, please refer to fig. 1, fig. 2, and fig. 3, in which fig. 3 is a flowchart illustrating a generation process of a buyback index according to an embodiment of the present invention. The process of generating the buyback index by the processor 4 of the information processing system 1 for member buyback of commodities includes: s21: obtaining the total consumption times and the total consumption amount in a first time section in the consumption data list of each member by using the processor 4 to find out the maximum value of the total consumption times and the maximum value of the total consumption amount in the first time section in all the member consumption data of the manufacturer 6; s22: calculating a first ratio of the total consumption times in the first time section of each member to the maximum value of the total consumption times in the first time section in all the member consumption data of the manufacturer by using the processor 4, and calculating a second ratio of the total consumption amount in the first time section of each member to the maximum value of the total consumption amount in the first time section in all the member consumption data of the manufacturer 6; s23: obtaining a first weighting index and a second weighting index by the processor 4 according to the commodity characteristics or the industry characteristics; and S24: the processor 4 is utilized to calculate a first weighted-index-weighted first ratio and a second weighted-index-weighted second ratio to generate a buyback indicator. In addition, the examples of generating the buyback index according to the embodiments of the present invention are the same as those described above, and therefore, are not described herein again.
In step S4, please refer to fig. 1, fig. 2, and fig. 4, in which fig. 4 is a flowchart illustrating the establishment of a buyback model according to an embodiment of the present invention. The process of establishing the buyback model by the processor 4 of the information processing system 1 for member buyback of commodities comprises the following steps: s41: inputting all member consumption data of the manufacturer 6 in a third time section into the buyback model by using the processor 4 so as to train and optimize buyback model parameters of the buyback model; s42: the processor 4 inputs the consumption data list of at least one member in the third time section and the fourth time section into the buyback model so as to correct the buyback model parameters of the buyback model; and S43: and establishing a buyback model by using the processor 4 according to the corrected buyback model parameters. In addition, the examples of establishing the buyback model according to the embodiments of the present invention are the same as those described above, and therefore, are not described herein again.
In step S4, please refer to fig. 1, fig. 2, and fig. 5, in which fig. 5 is a flowchart illustrating a value of whether each member buys a commodity again according to the embodiment of the present invention. The process of the processor 4 of the information processing system 1 for member to buyback commodities to generate a rate of whether each member buybacks commodities includes: s51: the processor 4 is used to obtain the last consumption day, consumption frequency, consumption amount and the buyback index in the first time section of the consumption data list of each member to input the last consumption day, consumption frequency, consumption amount and buyback index into the buyback model so as to obtain a probability of whether each member buyback the commodities in a second time section. In addition, the example of generating a value indicating whether each member buys a commodity is the same as the above, and therefore, the description thereof is omitted.
The information processing system and the method for the member to buyback commodities can count the consumption data lists of all the members according to the past consumption records of all the members provided by a manufacturer, and obtain the key indexes such as the last consumption day, the consumption frequency, the consumption amount, the buyback index and the like in the consumption data of all the members so as to predict whether each member buyback commodities.
The disclosure provided above is only a preferred embodiment of the present invention, and is not intended to limit the scope of the claims, so that all equivalent technical changes made by using the disclosure of the present invention and the drawings are included in the scope of the claims.
Claims (10)
1. An information processing method for a member to buyback a commodity, comprising:
acquiring all member consumption data provided by a manufacturer;
storing all member consumption data of the manufacturer to a member database;
transmitting all member consumption data of the manufacturer to a processor, and establishing a consumption data list of each member by the processor according to all the member consumption data of the manufacturer, wherein the consumption data list comprises the latest consumption day, consumption frequency, consumption amount and a buyback index;
inputting the consumption data list of each member into a buyback model by using the processor to obtain a rate of whether each member buybacks commodities;
storing the probability of whether each member buys commodities back to the consumption data list of each member by using the processor; and
outputting a list of repurchase products including the consumption data list of each member by the processor for browsing by the manufacturer.
2. The member buyback information processing method as claimed in claim 1, further comprising:
obtaining the last consumption day, the consumption frequency, the consumption amount and the buyback index in a first time section in the consumption data list of each member by utilizing the processor, and inputting the consumption date, the consumption frequency, the consumption amount and the buyback index into the buyback model to obtain the probability of whether each member buybacks commodities in a second time section;
the second time interval is smaller than the first time interval, and the second time interval is subsequent to the first time interval.
3. The member buyback information processing method as claimed in claim 1, further comprising:
obtaining the total consumption times and the total consumption amount in a first time section in the consumption data list of each member by utilizing the processor to find out the maximum value of the total consumption times and the maximum value of the total consumption amount in the first time section in all member consumption data of the manufacturer;
calculating a first ratio of the total consumption times of each member in the first time section to the maximum value of the total consumption times of all member consumption data of the manufacturer in the first time section and a second ratio of the total consumption amount of each member in the first time section to the maximum value of the total consumption amount of all member consumption data of the manufacturer in the first time section by using the processor;
obtaining a first weighting index and a second weighting index by the processor according to the commodity characteristics or the industry characteristics; and
calculating the first proportion weighted by the first weighted index and the second proportion weighted by the second weighted index by the processor to generate the buyback index;
wherein the first weighted index is the merchandise preference index of each member, and the second weighted index is the consumption amount index of each member;
wherein the sum of the first weighted index and the second weighted index is 1.
4. The member buyback information processing method as claimed in claim 1, further comprising:
inputting all member consumption data of the manufacturer in a third time zone into the buyback model by using the processor so as to train and optimize buyback model parameters of the buyback model;
inputting the consumption data list of at least one member in the third time zone and a fourth time zone into the buyback model by using the processor so as to correct the buyback model parameters of the buyback model; and
establishing the buyback model by using the processor according to the revised buyback model parameters;
wherein the fourth time segment is smaller than the third time segment, and the fourth time segment is subsequent to the third time segment.
5. The method as claimed in claim 4, wherein the consumption data list of the at least one member in the third time period and the fourth time period further comprises a value indicating whether the member buys merchandise in the third time period and the fourth time period at the same time; when the at least one member has bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 0, and when the at least one member has not bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 1.
6. An information processing system for a member to buyback merchandise, comprising:
a receiver for acquiring all member consumption data provided by a manufacturer;
a member database for storing all member consumption data of the manufacturer; and
a processor, receiving all member consumption data of the manufacturer, establishing a consumption data list of each member according to all member consumption data of the manufacturer, inputting the consumption data list of each member to a buyback model to obtain a probability of whether each member buyback commodities, storing the probability of whether each member buyback commodities to the consumption data list of each member, and outputting a buyback commodity list comprising the consumption data list of each member for the manufacturer to browse;
the consumption data list comprises the last consumption day, consumption frequency, consumption amount and a buyback index.
7. The system as claimed in claim 6, wherein the processor obtains the last consumption day, the consumption frequency, the consumption amount, and the buyback index in the consumption data list of each member in a first time period for inputting to the buyback model to obtain the probability of whether each member buyback merchandise in a second time period; the second time interval is smaller than the first time interval, and the second time interval is subsequent to the first time interval.
8. The system as claimed in claim 6, wherein the processor obtains the total number of times of consumption and the total amount of consumption of each member in the consumption data list of each member in a first time period to find the maximum value of the total number of times of consumption and the maximum value of the total amount of consumption in the first time period in all the member consumption data of the vendor;
the processor calculates a first proportion of the total consumption times of each member in the first time section to the maximum value of the total consumption times of all member consumption data of the manufacturer in the first time section, and a second proportion of the total consumption amount of each member in the first time section to the maximum value of the total consumption amount of all member consumption data of the manufacturer in the first time section;
the processor obtains a first weighting index and a second weighting index according to the commodity characteristics or the industry characteristics; and
the processor calculates the first proportion weighted by the first weighted index and the second proportion weighted by the second weighted index to generate the buyback index;
wherein the first weighted index is the merchandise preference index of each member, and the second weighted index is the consumption amount index of each member;
wherein the sum of the first weighted index and the second weighted index is 1.
9. The system as claimed in claim 6, wherein the processor inputs all member consumption data of the manufacturer in a third time period into the buyback model to train and optimize buyback model parameters of the buyback model;
the processor inputs the consumption data list of at least one member in the third time section and a fourth time section into the buyback model so as to correct the buyback model parameters of the buyback model; and
the processor establishes the buyback model according to the revised buyback model parameters;
wherein the fourth time segment is smaller than the third time segment, and the fourth time segment is subsequent to the third time segment.
10. The system as claimed in claim 9, wherein the consumption data list of the at least one member in the third time period and the fourth time period further comprises a value indicating whether the member buys merchandise in the third time period and the fourth time period at the same time; when the at least one member has bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 0, and when the at least one member has not bought back merchandise in the third time zone and the fourth time zone at the same time, the value is 1.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW108135123 | 2019-09-27 | ||
| TW108135123A TW202113721A (en) | 2019-09-27 | 2019-09-27 | Information processing system and method for member repurchasing product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112581158A true CN112581158A (en) | 2021-03-30 |
Family
ID=75117003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910973294.9A Pending CN112581158A (en) | 2019-09-27 | 2019-10-14 | Information processing system and method for member to buyback commodity |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112581158A (en) |
| TW (1) | TW202113721A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030086526A (en) * | 2003-10-16 | 2003-11-10 | 권영직 | Method and apparatus for automatically calculating repurchasing time in shopping mall and sale management system through internet |
| CN108269118A (en) * | 2017-01-03 | 2018-07-10 | 中兴通讯股份有限公司 | A kind of method and apparatus of data analysis |
| CN109255645A (en) * | 2018-07-20 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of consumption predictions method, apparatus and electronic equipment |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN110210913A (en) * | 2019-06-14 | 2019-09-06 | 重庆邮电大学 | A kind of businessman frequent customer's prediction technique based on big data |
-
2019
- 2019-09-27 TW TW108135123A patent/TW202113721A/en unknown
- 2019-10-14 CN CN201910973294.9A patent/CN112581158A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030086526A (en) * | 2003-10-16 | 2003-11-10 | 권영직 | Method and apparatus for automatically calculating repurchasing time in shopping mall and sale management system through internet |
| CN108269118A (en) * | 2017-01-03 | 2018-07-10 | 中兴通讯股份有限公司 | A kind of method and apparatus of data analysis |
| CN109255645A (en) * | 2018-07-20 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of consumption predictions method, apparatus and electronic equipment |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN110210913A (en) * | 2019-06-14 | 2019-09-06 | 重庆邮电大学 | A kind of businessman frequent customer's prediction technique based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202113721A (en) | 2021-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Inventory policies for perishable products with expiration dates and advance-cash-credit payment schemes | |
| US20230018311A1 (en) | Systems and methods for quantity determinations without predicting out of stock events | |
| US10572912B2 (en) | System and method for integrating retail price optimization for revenue and profit with business rules | |
| US10181138B2 (en) | System and method for determining retail-business-rule coefficients from current prices | |
| JP5337174B2 (en) | Demand prediction device and program thereof | |
| US20190180301A1 (en) | System for capturing item demand transference | |
| CN102282551A (en) | Automated decision support for pricing entertainment tickets | |
| CN106803179A (en) | Instant method and system of sharing in the benefit | |
| JP6780992B2 (en) | Judgment device, judgment method and judgment program | |
| CN113327152A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| JP2009251779A (en) | Sales estimation system, method and program | |
| JP2021056839A (en) | Electronic commerce device, electronic commerce method and computer program | |
| CN112651805B (en) | Commodity recommendation method and system for online mall | |
| Sharma et al. | Best seller rank (bsr) to sales: An empirical look at amazon. com | |
| JP5819363B2 (en) | Demand prediction apparatus and program | |
| JP2015032267A (en) | Demand prediction apparatus and program | |
| CN112581158A (en) | Information processing system and method for member to buyback commodity | |
| CN113421148B (en) | Commodity data processing method, commodity data processing device, electronic equipment and computer storage medium | |
| WO2021065289A1 (en) | Store assistance system, store assistance method, and program | |
| WO2021065290A1 (en) | Store supporting system, learning device, store supporting method, generation method of learned model, and program | |
| KR100955631B1 (en) | Method and system of recommanding adequate price and delivery information associated with time gap information in online market | |
| Hirogaki | Key factors in successful online grocery retailing: Empirical evidence from Tokyo, Japan | |
| KR20220168311A (en) | Method and server for providing information on the distribution of agricultural products | |
| Buchwitz et al. | Should I buy my new iPhone now? Predictive Event Forecasting for Zero-Inflated Consumer Goods Prices | |
| TWM591667U (en) | Information processing system for member repurchasing product |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220930 Address after: Chinese Taiwan New Taipei City Applicant after: DATA SYSTEMS CONSULTING CO.,LTD. Address before: TaiWan, China Applicant before: Zhilue Information Integration Co.,Ltd. |
|
| TA01 | Transfer of patent application right |