Information processing system and method for member repurchase of goods

Abstract

The present invention provides an information processing system and method for member repurchase of goods, the method comprising: obtaining all member consumption data provided by a manufacturer; storing all member consumption data of the manufacturer; establishing a consumption data list for each member based on all member consumption data of the manufacturer, wherein the consumption data list includes the most recent consumption date, consumption frequency, consumption amount, and repurchase index; inputting the consumption data list of each member into a repurchase model to obtain a probability of whether each member will repurchase goods; storing the probability of whether each member will repurchase goods in the consumption data list of each member; and outputting a repurchased goods list including the consumption data list of each member for the manufacturer to browse.

Description

Technical Field

[0001] The present invention relates to an information processing system and method for member repurchase of goods, and in particular to an information processing system and method for member repurchase of goods capable of predicting whether a member will repurchase the goods. Background Art

[0002] When general member consumers consume goods, stores or manufacturers will provide suitable goods according to the actual needs of member consumers and record all consumption lists and other information of member consumers from the time they register as members to this point.

[0003] In addition to compiling the consumption lists of all member consumers, stores and manufacturers will provide all member consumers with the current season's product catalogs for reference, so that member consumers can go to stores or manufacturers to purchase according to their needs.

[0004] However, stores and manufacturers are unable to predict when member consumers will make purchases in order to understand the purchasing needs of member consumers. In view of the above shortcomings, the inventors of the present invention have conducted ideas and research on the above shortcomings to solve the current shortcomings and make improvements. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a member repurchase commodity information processing method in view of the shortcomings of the prior art, characterized in that it includes: obtaining all member consumption data provided by a manufacturer; storing all member consumption data of the manufacturer in a member database; transmitting all member consumption data of the manufacturer to a processor, the processor establishing a consumption data list for each member based on all member consumption data of the manufacturer, wherein the consumption data list includes the most recent consumption date (recency), consumption frequency (frequency), consumption amount (monerary), and repurchase index (repurchase index); using the processor to input the consumption data list of each member into a repurchase model to obtain a probability of whether each member will repurchase the commodity; using the processor to store the probability of whether each member will repurchase the commodity in the consumption data list of each member; and using the processor to output a repurchase commodity list including the consumption data list of each member for the manufacturer to browse.

[0006] Preferably, it also includes: using the processor to obtain the most recent consumption date, the consumption frequency, the consumption amount, and the repurchase index within a first time period in the consumption data list of each member to input into the repurchase model to obtain the probability of whether each member will repurchase the product within a second time period; wherein the second time period is smaller than the first time period, and the second time period follows the first time period.

[0007] Preferably, the method further includes: using the processor to obtain the total number of consumptions and the total amount of consumption in a first time period in the consumption data list of each member to find the maximum total number of consumptions and the maximum total amount of consumption in the first time period in the consumption data of all members of the manufacturer; using the processor to calculate a first ratio of the total number of consumptions of each member in the first time period to the maximum total number of consumptions in the first time period in the consumption data of all members of the manufacturer, and a second ratio of the total amount of consumption of each member in the first time period to the maximum total amount of consumption in the first time period in the consumption data of all members of the manufacturer; using the processor to obtain a first weighted index and a second weighted index based on commodity characteristics or industry characteristics; and using the processor to calculate the first weighted index weighted by the first ratio and the second weighted index weighted by the second ratio to generate the repurchase index; wherein the first weighted index is the commodity 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.

[0008] Preferably, it also includes: using the processor to input all member consumption data of the manufacturer within a third time period into the repurchase model to train and optimize the repurchase model parameters of the repurchase model; using the processor to input the consumption data list of at least one member within the third time period and a fourth time period into the repurchase model to correct the repurchase model parameters of the repurchase model; and using the processor to establish the repurchase model based on the corrected repurchase model parameters; wherein the fourth time period is smaller than the third time period, and the fourth time period follows the third time period.

[0009] Preferably, the consumption data list of the at least one member within the third time period and the fourth time period further includes a value indicating whether the member repurchases goods within both the third time period and the fourth time period; when the at least one member repurchases goods within both the third time period and the fourth time period, the value is 0, and when the at least one member does not repurchase goods within both the third time period and the fourth time period, the value is 1.

[0010] The present invention also provides an information processing system for member repurchase of goods, characterized in that it includes: a transceiver, which obtains all member consumption data provided by a manufacturer; a member database, which stores all member consumption data of the manufacturer; and a processor, which receives all member consumption data of the manufacturer, establishes a consumption data list for each member based on all member consumption data of the manufacturer, inputs the consumption data list of each member into a repurchase model to obtain a probability of whether each member will repurchase goods, stores the probability of whether each member will repurchase goods in the consumption data list of each member, and outputs a repurchased goods list including the consumption data list of each member for the manufacturer to browse; wherein the consumption data list includes the most recent consumption date (recency), consumption frequency (frequency), consumption amount (monerary), and repurchase index (repurchase index).

[0011] Preferably, the processor obtains the most recent consumption date, the consumption frequency, the consumption amount, and the repurchase index within a first time period in the consumption data list of each member to input into the repurchase model to obtain the probability of whether each member will repurchase the product within a second time period; wherein the second time period is smaller than the first time period, and the second time period follows the first time period.

[0012] Preferably, the processor obtains the total number of consumptions and the total amount of consumption within a first time period in the consumption data list of each member to find the maximum total number of consumptions and the maximum total amount of consumption within the first time period in the consumption data of all members of the manufacturer; the processor calculates a first ratio of the total number of consumptions of each member in the first time period to the maximum total number of consumptions within the first time period in the consumption data of all members of the manufacturer, and a second ratio of the total amount of consumption of each member in the first time period to the maximum total amount of consumption within the first time period in the consumption data of all members of the manufacturer; the processor obtains a first weighted index and a second weighted index based on product characteristics or industry characteristics; and the processor calculates the first weighted index weighted by the first ratio and the second weighted index weighted by the second ratio to generate the repurchase index; wherein the first weighted index is the product 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.

[0013] Preferably, the processor inputs all member consumption data within a third time period of the manufacturer into the repurchase model to train and optimize the repurchase model parameters of the repurchase model; the processor inputs the consumption data list of at least one member within the third time period and a fourth time period into the repurchase model to correct the repurchase model parameters of the repurchase model; and the processor establishes the repurchase model based on the corrected repurchase model parameters; wherein the fourth time period is smaller than the third time period, and the fourth time period follows the third time period.

[0014] Preferably, the consumption data list of the at least one member within the third time period and the fourth time period also includes a value indicating whether the member repurchases goods within both the third time period and the fourth time period; when the at least one member repurchases goods within both the third time period and the fourth time period, the value is 0, and when the at least one member does not repurchase goods within both the third time period and the fourth time period, the value is 1.

[0015] The information processing system and method for member repurchase of goods provided by the present invention can compile a list of consumption data of all members based on the past consumption records of all members provided by the manufacturer, and obtain key indicators such as the most recent consumption date, consumption frequency, consumption amount, and repurchase index in the consumption data of all members, so as to predict whether each member will repurchase goods.

[0016] To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and description and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a block diagram of an information processing system for member repurchase of goods according to an embodiment of the present invention.

[0018] Figure 2 The present invention is a flowchart of a method for processing information of member repurchase products according to an embodiment of the present invention.

[0019] Figure 3 This is a flow chart of generating a repurchase indicator according to an embodiment of the present invention.

[0020] Figure 4 It is a flow chart for establishing a repurchase model according to an embodiment of the present invention.

[0021] Figure 5 This is a flow chart of generating a numerical value of whether each member will repurchase a product in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following is an explanation of the implementation of the information processing system and method for member repurchase of goods disclosed in the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual dimensions. It is stated in advance. The following implementations will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0023] It should 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 mainly used to distinguish one component from another component, or one signal from another signal. In addition, the term "or" used herein may include any one or more combinations of the associated listed items depending on the actual situation.

[0024] See also Figure 1 , is a block diagram of an information processing system for member repurchase of goods according to an embodiment of the present invention. The information processing system 1 for member repurchase of goods according to the present invention comprises a transceiver 2, a member database 3 and a processor 4.

[0025] The transceiver 2 in the information processing system 1 for member repurchase of goods is connected to a manufacturer 6 via the Internet 5 to obtain all member consumption data provided by the manufacturer 6, and the manufacturer 6 includes a server or a database. The manufacturer's server or database stores all member consumption data, wherein all member consumption data includes each member's member number, member registration date, amount of goods consumed, time of consumption, number of times of consumption, location of consumption, and other member personal data and member consumption data. It is worth noting that the member consumption data can be set according to the actual needs of the manufacturer 6, and the present invention is not limited thereto.

[0026] The member database 3 of the information processing system 1 for member repurchase of commodities is connected to the transceiver 2 to store all member consumption data provided by the manufacturer 6, wherein the member database 3 is a server or a database.

[0027] The processor 4 of the information processing system 1 for member repurchase of goods is connected to the member database 3 to receive all member consumption data of the manufacturer 6, and establishes a consumption data list for each member based on all member consumption data of the manufacturer 6, wherein the consumption data list includes the most recent consumption date (recency), consumption frequency (frequency), consumption amount (monerary), and repurchase index (repurchase index). The most recent consumption date refers to the time interval between the last consumption of the consumer and the last consumption, the consumption frequency refers to the total number of transactions accumulated by the consumer within a specific time, the consumption amount refers to the total amount of transactions of the consumer within a specific time, and the repurchase index refers to the index of the consumer repurchasing goods within a specific time.

[0028] In one embodiment, the processor 4 obtains the total number of consumptions and the total amount of consumption in a first time segment in the consumption data list of each member to find the maximum total number of consumptions and the maximum total amount of consumption in the first time segment in all member consumption data of the manufacturer 6. The processor 4 calculates a first ratio of the total number of consumptions in the first time segment of each member to the maximum total number of consumptions in the first time segment in all member consumption data of the manufacturer, and calculates a second ratio of the total amount of consumption in the first time segment of each member to the maximum total amount of consumption in the first time segment in all member consumption data of the manufacturer 6. The processor 4 obtains a first weighted index and a second weighted index based on the characteristics of the product or the characteristics of the industry. The processor 4 calculates the first weighted index weighted first ratio and the second weighted index weighted second ratio to generate a repurchase index. The first weighted index is the member's product preference index, the second weighted index is the member's consumption amount index, and the sum of the first weighted index and the second weighted index is 1. The product preference index is, for example, an indicator of the member's preference or preferred purchase of the product, and the consumption amount index is, for example, an indicator of which consumption amount range the member's consumption amount is in. It is worth noting that the product preference index and the consumption amount index can be set according to the actual needs of the manufacturer 6, and the present invention is not limited thereto.

[0029] In one example, the first time segment is, for example, the four seasons of 2018, the product characteristics are, for example, sneakers and the sneaker consumption cycle is half a year, the total number of sneaker consumptions by a member in the four seasons of 2018 is 2 times and the total amount of sneaker consumption is 6,000 yuan, the total number of sneaker consumptions by a member among all members in the four seasons of 2018 is 8 times, which is the maximum number of sneaker consumptions and the total amount of sneaker consumption is 30,000 yuan, which is the maximum amount of sneaker consumption, and the manufacturer 6 sets the first weighted index to 0.3 and the second weighted index to 0.7 according to the product characteristics, and the repurchase index is equal to 0.3*(2 / 8)+0.7*(6000 / 30000)=0.215, wherein the larger the value of the repurchase index is, the higher the probability of repurchase is. It is worth noting that the first time segment, product characteristics or industry characteristics, the first weighted index and the second weighted index can be set according to the actual needs of the manufacturer 6, and the present invention is not limited thereto.

[0030] The processor 4 of the information processing system 1 for member repurchase of goods inputs each member's consumption data list into a repurchase model to obtain a probability of whether each member will repurchase the goods.

[0031] In one embodiment, the processor 4 inputs all member consumption data of the manufacturer 6 within a third time segment into the repurchase model to train and optimize the repurchase model parameters of the repurchase model, the processor 4 inputs the consumption data list of at least one member within the third time segment and a fourth time segment into the repurchase model to modify the repurchase model parameters of the repurchase model, and the processor 4 establishes the repurchase model according to the modified repurchase model parameters. The fourth time segment is shorter than the third time segment, and the fourth time segment follows the third time segment.

[0032] In addition, the consumption data list of at least one member within the third time period and the fourth time period also includes a value indicating whether at least one member repurchases goods within both the third time period and the fourth time period; when at least one member repurchases goods within both the third time period and the fourth time period, the value of whether the goods are repurchased is 0, and when at least one member does not repurchase goods within both the third time period and the fourth time period, the value of whether the goods are repurchased is 1.

[0033] In one example, after obtaining the most recent consumption date, consumption frequency, consumption amount, and repurchase index, the processor 4 converts the most recent consumption date, consumption frequency, and consumption amount from the original percentage format into a score range (1-5 points), as shown in Table 1.

[0034]

[0035] After the processor 4 receives all the member consumption data of the manufacturer 6, the processor 4 performs data pre-processing on all the member consumption data of the manufacturer 6 to obtain the most recent consumption date, consumption frequency, consumption amount, and repurchase index of each member, and converts the most recent consumption date, consumption frequency and consumption amount from a percentage format into a fractional interval, the processor 4 inputs the member consumption data of all members in the third time segment into the repurchase model to train, iterate and optimize the repurchase model parameters through a machine learning algorithm (such as XGBoost), the processor 4 inputs the consumption data list of multiple members in the third time segment and the fourth time segment into the repurchase model to correct the repurchase model parameters of the repurchase model, and the processor 4 determines and establishes the repurchase model based on the corrected repurchase model parameters. The machine learning algorithm is based on the consumption data generated by the consumer individually or as a whole, through the technology of data mining, to obtain the characteristics of the consumer's purchase of goods, and through the technical training of machine learning to generate the model required by the present invention to predict whether the consumer will repurchase. It is worth noting that the machine learning algorithm in the repurchase model can be selected according to the actual needs of the manufacturer 6, and the present invention is not limited to this.

[0036] In one example, the third time period is, for example, the fourth quarter of 2017 to the third quarter of 2018, and the fourth time period is, for example, the fourth quarter of 2018. The processor 4 obtains the consumption data of all members and performs data pre-processing to obtain the most recent consumption date, consumption frequency, consumption amount, and repurchase index of each member, and converts the most recent consumption date, consumption frequency and consumption amount from a percentage format into a fractional interval. The processor 4 inputs the member consumption data of all members from the fourth quarter of 2017 to the third quarter of 2018 into the repurchase model for training, iteration and optimization of the repurchase model parameters, and the processor 4 inputs the consumption data list of multiple members from the fourth quarter of 2017 to the third quarter of 2018 and the fourth quarter of 2018 into the repurchase model to correct the repurchase model parameters of the repurchase model, and the processor 4 determines and establishes the repurchase model based on the corrected repurchase model parameters. Among them, the consumption data list of multiple members in the fourth quarter of 2017 to the third quarter of 2018 and the fourth quarter of 2018 also includes a value indicating whether multiple members repurchased the goods in the fourth quarter of 2017 to the third quarter of 2018 and the fourth quarter of 2018 at the same time; when one of the multiple members repurchased the goods in the fourth quarter of 2017 to the third quarter of 2018 and the fourth quarter of 2018 at the same time, the value of whether this member repurchased the goods is 0, and when one of the multiple members did not repurchase the goods in the fourth quarter of 2017 to the third quarter of 2018 and the fourth quarter of 2018 at the same time, the value of whether this member repurchased the goods is 1. It is worth noting that the third time segment and the fourth time segment can be set according to the actual needs of the manufacturer 6, and the present invention is not limited thereto.

[0037] In one embodiment, the processor 4 obtains the latest consumption date, consumption frequency, consumption amount, and repurchase index in the first time period in the consumption data list of each member to input into the repurchase model to obtain the probability of whether each member will repurchase the product in a second time period. The second time period is shorter than the first time period, and the second time period follows the first time period.

[0038] In one example, the first time segment is, for example, the four seasons of 2018, and the second time segment is, for example, the first season of 2019. The processor 4 obtains the latest consumption date, consumption frequency, consumption amount, and repurchase index in the four seasons of 2018 in the consumption data list of each member to input into the repurchase model to obtain the probability of whether each member will repurchase the product in the first season of 2019. It is worth noting that the first time segment, the second time segment, the third time segment, and the fourth time segment can be set according to the actual needs of the manufacturer 6, for example, the time segment can be in units of year, month, day, hour, etc., and the present invention is not limited thereto.

[0039] The processor 4 of the information processing system 1 for member repurchase of goods stores the probability of whether each member will repurchase the goods in the consumption data list of each member.

[0040] The processor 4 of the information processing system 1 for member repurchase of goods outputs a repurchased goods list including a list of consumption data of each member for the manufacturer 6 to browse. The repurchased goods list includes the consumption data of all members provided by the manufacturer 6, and also includes the probability of whether each member will repurchase goods in the next time period, so that the manufacturer 6 can know the probability of whether the member will repurchase goods in the next time period according to the repurchased goods list, and enable the manufacturer 6 to calculate the proportion of members who repurchase and do not repurchase in the next time period, the proportion of members who actually repurchase goods and are predicted to repurchase goods, and the proportion of members who actually repurchase goods among the members who are predicted to repurchase goods.

[0041] Please also see Figure 1 and Figure 2 , Figure 2: is a flowchart of the information processing method for member repurchase of goods according to an embodiment of the present invention. The information processing method for member repurchase of goods according to the present invention comprises the following steps: S1: obtaining all member consumption data provided by a manufacturer 6; S2: storing all member consumption data of the manufacturer 6 in a member database 3; S3: transmitting all member consumption data of the manufacturer 6 to a processor 4, wherein the processor 4 establishes a consumption data list for each member according to all member consumption data of the manufacturer 6, wherein the consumption data list includes the most recent consumption date (recency), consumption frequency (frequency), consumption amount (monerary), and repurchase index (repurchase index); S4: using the processor 4 to input each member's consumption data list into a repurchase model to obtain a probability of whether each member will repurchase goods; S5: using the processor 4 to store the probability of whether each member will repurchase goods in each member's consumption data list; and S6: using the processor 4 to output a repurchased goods list including each member's consumption data list for the manufacturer 6 to browse. In addition, the example of the member repurchase method according to the embodiment of the present invention is the same as the above, so it is not repeated here.

[0042] In step S3, please also refer to Figure 1 , Figure 2 and Figure 3 , Figure 3 It is a flow chart of generating a repurchase index in an embodiment of the present invention. The process of generating a repurchase index by the processor 4 of the information processing system 1 for member repurchase of goods includes: S21: using the processor 4 to obtain the total number of consumptions and the total amount of consumption in a first time segment in the consumption data list of each member to find the maximum total number of consumptions and the maximum total amount of consumption in the first time segment in all member consumption data of the manufacturer 6; S22: using the processor 4 to calculate a first ratio of the total number of consumptions of each member in the first time segment to the maximum total number of consumptions in the first time segment in all member consumption data of the manufacturer, and calculating a second ratio of the total amount of consumption of each member in the first time segment to the maximum total amount of consumption in the first time segment in all member consumption data of the manufacturer 6; S23: using the processor 4 to obtain a first weighted index and a second weighted index according to the characteristics of the goods or the characteristics of the industry; and S24: using the processor 4 to calculate the first weighted index weighted first ratio and the second weighted index weighted second ratio to generate a repurchase index. In addition, the example of generating a repurchase index in an embodiment of the present invention is the same as the above, so it is not repeated here.

[0043] In step S4, please also refer to Figure 1 , Figure 2 and Figure 4 , Figure 4It is a flow chart of establishing a repurchase model in an embodiment of the present invention. The process of establishing a repurchase model by the processor 4 of the information processing system 1 for member repurchase of goods includes: S41: using the processor 4 to input all member consumption data of the manufacturer 6 within a third time period into the repurchase model to train and optimize the repurchase model parameters of the repurchase model; S42: the processor 4 inputs the consumption data list of at least one member within the third time period and a fourth time period into the repurchase model to correct the repurchase model parameters of the repurchase model; and S43: using the processor 4 to establish a repurchase model based on the corrected repurchase model parameters. In addition, the example of establishing a repurchase model in an embodiment of the present invention is the same as the above, so it will not be repeated here.

[0044] In step S4, please also refer to Figure 1 , Figure 2 and Figure 5 , Figure 5 4 is a flow chart of generating a numerical value of whether each member will repurchase a product in an embodiment of the present invention. The process of the processor 4 of the information processing system 1 for member repurchase of products generating a probability of whether each member will repurchase a product includes: S51: using the processor 4 to obtain the latest consumption date, consumption frequency, consumption amount, and repurchase index in the first time period of each member's consumption data list to input into the repurchase model to obtain a probability of whether each member will repurchase a product in a second time period. In addition, the example of generating a numerical value of whether each member will repurchase a product in an embodiment of the present invention is the same as the above, so it will not be repeated here.

[0045] The information processing system and method for member repurchase of goods provided by the present invention can compile a list of consumption data of all members based on the past consumption records of all members provided by the manufacturer, and obtain key indicators such as the most recent consumption date, consumption frequency, consumption amount, and repurchase index in the consumption data of all members, so as to predict whether each member will repurchase goods.

[0046] The contents provided above are only preferred feasible embodiments of the present invention, and are not intended to limit the scope of the claims of the present invention. Therefore, all equivalent technical changes made using the contents of the specification and drawings of the present invention are included in the scope of the claims of the present invention.

Claims

1. A method for processing information of member repurchase of goods, characterized in that: include: Obtain all member consumption data provided by a manufacturer; Store all member consumption data of the manufacturer in a member database; Transmitting all member consumption data of the manufacturer to a processor, the processor establishing a consumption data list for each member based on all member consumption data of the manufacturer, wherein the consumption data list includes the most recent consumption date, consumption frequency, consumption amount and repurchase index; Using the processor to input the consumption data list of each member into a repurchase model to obtain a probability of whether each member will repurchase the product; Using the processor to store the probability of whether each member will repurchase the product in the consumption data list of each member; as well as Outputting a repurchased product list including the consumption data list of each member by the processor for the manufacturer to browse; wherein the processor is used to obtain a first weighted index and a second weighted index according to product characteristics or industry characteristics, and the processor is used to calculate the first weighted index weighted by a first ratio and the second weighted index weighted by a second ratio to generate the repurchase index, the first weighted index is the product preference index of each member, the second weighted index is the consumption amount index of each member, and the sum of the first weighted index and the second weighted index is 1; The repurchase model parameters of the repurchase model are calculated using time segments of different time interval lengths; The information processing method of the member's repurchased goods also includes: Using the processor to input all member consumption data of the manufacturer in a third time period into the repurchase model to train and optimize the repurchase model parameters of the repurchase model; Using the processor to input the consumption data list of at least one member in the third time period and a fourth time period into the repurchase model to modify the repurchase model parameters of the repurchase model; and Using the processor to establish the repurchase model according to the revised repurchase model parameters; The fourth time segment is smaller than the third time segment, and the fourth time segment follows the third time segment; Among them, the consumption data list of the at least one member within the third time period and the fourth time period also includes a value indicating whether the member repurchases goods within both the third time period and the fourth time period; when the at least one member repurchases goods within both the third time period and the fourth time period, the value is 0, and when the at least one member does not repurchase goods within both the third time period and the fourth time period, the value is 1.

2. The information processing method for member repurchase of goods according to claim 1, characterized in that: Also includes: Using the processor to obtain the latest consumption date, the consumption frequency, the consumption amount and the repurchase index in the consumption data list of each member within a first time period to input into the repurchase model to obtain the probability of whether each member will repurchase the product within a second time period; The second time segment is smaller than the first time segment, and the second time segment follows the first time segment.

3. The information processing method for member repurchase of goods according to claim 1, characterized in that: Also includes: Using the processor to obtain the total number of consumptions and the total amount of consumption in the first time period in the consumption data list of each member to find the maximum total number of consumptions and the maximum total amount of consumption in the first time period among all members' consumption data of the manufacturer; The processor is used to calculate the first ratio of the total number of consumptions of each member in the first time period to the maximum value of the total number of consumptions in the first time period among all members' consumption data of the manufacturer, and the second ratio of the total amount of consumption of each member in the first time period to the maximum value of the total amount of consumption in the first time period among all members' consumption data of the manufacturer.

4. A member repurchase commodity information processing system, characterized in that: include: A transmitter and receiver to obtain all member consumption data provided by a manufacturer; A member database, storing all member consumption data of the manufacturer; as well as 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 into a repurchase model to obtain a probability of whether each member will repurchase a product, storing the probability of whether each member will repurchase a product in the consumption data list of each member, and outputting a repurchase product list including the consumption data list of each member for the manufacturer to browse; The consumption data list includes the most recent consumption date, consumption frequency, consumption amount and repurchase index; wherein the processor is used to obtain a first weighted index and a second weighted index according to product characteristics or industry characteristics, and the processor is used to calculate the first weighted index weighted by a first ratio and the second weighted index weighted by a second ratio to generate the repurchase index, the first weighted index is the product preference index of each member, the second weighted index is the consumption amount index of each member, and the sum of the first weighted index and the second weighted index is 1; The repurchase model parameters of the repurchase model are calculated using time segments of different time interval lengths; The processor inputs all member consumption data of the manufacturer in a third time period into the repurchase model to train and optimize the repurchase model parameters of the repurchase model; The processor inputs the consumption data list of at least one member in the third time period and a fourth time period into the repurchase model to modify the repurchase model parameter of the repurchase model; and The processor establishes the repurchase model according to the revised repurchase model parameters; The fourth time segment is smaller than the third time segment, and the fourth time segment follows the third time segment; Among them, the consumption data list of the at least one member within the third time period and the fourth time period also includes a value indicating whether the member repurchases goods within both the third time period and the fourth time period; when the at least one member repurchases goods within both the third time period and the fourth time period, the value is 0, and when the at least one member does not repurchase goods within both the third time period and the fourth time period, the value is 1.

5. The information processing system for member repurchase of goods according to claim 4, characterized in that: The processor obtains the latest consumption date, the consumption frequency, the consumption amount, and the repurchase index in the consumption data list of each member within a first time period and inputs them into the repurchase model to obtain the probability of whether each member will repurchase the product within a second time period; The second time segment is smaller than the first time segment, and the second time segment follows the first time segment.

6. The information processing system for member repurchase of goods according to claim 4, characterized in that: The processor 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 out the maximum total number of consumptions and the maximum total amount of consumption in the first time period among all members' consumption data of the manufacturer.

Images