CN114612179A

CN114612179A - Commodity recommending and displaying method and device, electronic equipment and storage medium

Info

Publication number: CN114612179A
Application number: CN202210192708.6A
Authority: CN
Inventors: 不公告发明人
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-06-10

Abstract

The embodiment of the invention provides a commodity recommending and displaying method and device, wherein the method comprises the following steps: receiving associated data corresponding to the commodity subsidy information and extracting characteristic data; generating modeling sample data and modeling target data according to the characteristic data; predicting to obtain order information based on a machine learning algorithm, modeling sample data and modeling target data; and taking the commodities with the order information larger than the order information threshold value as recommended commodities, and carrying out sequencing display on the recommended commodities according to the probability information. According to the embodiment of the invention, the order information of each commodity is obtained through prediction based on the machine learning algorithm, and then the commodity with the order information larger than the order information threshold value is taken as the recommended commodity, so that the problem of manually selecting and uploading the commodity corresponding to the commodity subsidy information is solved, and each user in the user list can be subjected to sequencing display according to the probability information of the recommended commodity, thereby avoiding disordered display of the commodity and improving the experience of selecting and purchasing the commodity for the user.

Description

Commodity recommending and displaying method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for recommending and displaying a commodity, an electronic device, and a computer-readable storage medium.

Background

The basic gross profit of goods sold by E-business enterprises in daily operation needs to be guaranteed to be positive, meanwhile, part of subsidies are required to be given to part of users in a form of coupons with different money amounts regularly, the activity of the users is improved, after the money amount of the coupons needing to be issued on the next day is determined in advance for operation of each area, the goods pool meeting the constraint is uploaded manually by operators according to the money amount of the coupons, and the working efficiency is low. Due to the fact that the commodity pool is uploaded manually, when the coupon is issued the next day, it is difficult to guarantee that commodities in the commodity pool at the moment of issuing are in accordance with constraint conditions, and commodities in the commodity pool are not sorted according to preference when a user uses the coupon, so that user experience is poor. Meanwhile, the number of commodities in the commodity pool is large, and a user clicks to enter the commodity pool which is arranged in an unordered mode after receiving the coupons, so that the efficiency of selecting the commodities of the mood meter by the user is low.

Disclosure of Invention

In view of the above problems, embodiments of the present invention are provided to provide a method, an apparatus, an electronic device, and a computer-readable storage medium for recommending and presenting a merchandise that overcome or at least partially solve the above problems.

In order to solve the above problem, according to a first aspect of an embodiment of the present invention, a method for recommending and displaying a commodity is disclosed, the method including: receiving associated data corresponding to commodity subsidy information according to a preset period, wherein the commodity subsidy information comprises the following components: the system comprises area information, virtual preferential object information and target user information, wherein the associated data comprises: a user list, a commodity pool, and user behavior data; extracting feature data from the associated data; generating modeling sample data and modeling target data according to the characteristic data; predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on a machine learning algorithm, the modeling sample data and the modeling target data; and taking the commodity with the order information larger than the corresponding order information threshold value as a recommended commodity, and sequencing and displaying the recommended commodity according to probability information of each user for the recommended commodity for each user in the user list.

Optionally, the extracting feature data from the associated data includes: and extracting user group characteristic data and user characteristic data from the associated data.

Optionally, the extracting user group feature data from the associated data includes: extracting user behavior information, commodity amount information and variation degree information of each user group aiming at each commodity in the user list from the associated data; the extracting of the user feature data from the associated data includes: and extracting user behavior information, commodity amount information and variation degree information of each user aiming at each commodity in the user list from the associated data.

Optionally, the user behavior information includes a time difference between the last user operation and the current time, a frequency of the user operation within a preset first time period, and a time difference between the first user operation and the current time; the commodity amount information is the total amount purchased in a preset second time period; and the variation degree information is the consumption amount variance of the commodity in a preset third time period.

Optionally, the generating modeling sample data and modeling target data according to the feature data includes: generating user group modeling sample data and user group modeling target data according to the user group characteristic data, and generating the user modeling sample data and the user modeling target data according to the user characteristic data.

Optionally, the predicting to obtain order information of the user list for each commodity in the commodity pool based on the machine learning algorithm, the modeling sample data, and the modeling target data includes: and predicting to obtain order information of each user group in the user list aiming at each commodity in the commodity pool based on a regression algorithm, the user group modeling sample data and the user group modeling target data.

Optionally, the step of calculating the order information threshold includes: calculating the mean value and the standard deviation of order information for each commodity aiming at each user group; and taking the normal distribution result of the mean value and the standard deviation as the order information threshold value.

According to a second aspect of the embodiments of the present invention, there is also disclosed a device for recommending and displaying a commodity, the device including: the data acquisition module is used for receiving associated data corresponding to the commodity subsidy information according to a preset period, wherein the commodity subsidy information comprises: the system comprises area information, virtual preferential object information and target user information, wherein the associated data comprises: a user list, a commodity pool, and user behavior data; the characteristic extraction module is used for extracting characteristic data from the associated data; the modeling data generation module is used for generating modeling sample data and modeling target data according to the characteristic data; the data prediction module is used for predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on a machine learning algorithm, the modeling sample data and the modeling target data; and the recommendation display module is used for taking the commodity of which the order information is greater than the corresponding order information threshold value as a recommended commodity and sequencing and displaying the recommended commodity according to the probability information of each user for the recommended commodity for each user in the user list.

Optionally, the feature extraction module is configured to extract user group feature data and user feature data from the associated data.

Optionally, the feature extraction module includes: the user group characteristic data extraction module is used for extracting user behavior information, commodity amount information and variation degree information of each user group aiming at each commodity in the user list from the associated data; the feature extraction module further comprises: and the user characteristic data extraction module is used for extracting user behavior information, commodity amount information and variation degree information of each user aiming at each commodity in the user list from the associated data.

Optionally, the user behavior information includes a time difference between the latest user operation and the current time, a frequency of the user operation within a preset first time period, and a time difference between the first user operation and the current time; the commodity amount information is the total amount purchased in a preset second time period; and the variation degree information is the consumption amount variance of the commodity in a preset third time period.

Optionally, the modeling data generating module is configured to generate user group modeling sample data and user group modeling target data according to the user group feature data, and generate user modeling sample data and user modeling target data according to the user feature data.

Optionally, the data prediction module is configured to predict, based on a regression algorithm, the user group modeling sample data, and the user group modeling target data, order information of each user group in the user list for each commodity in the commodity pool.

Optionally, the apparatus further comprises: the threshold value calculation module is used for calculating the order information threshold value, and the threshold value calculation module is used for calculating the mean value and the standard deviation of the order information of each commodity aiming at each user group; and taking the normal distribution result of the mean value and the standard deviation as the order information threshold value.

According to a third aspect of the embodiments of the present invention, an electronic device is further disclosed, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method for recommending and displaying a product according to the first aspect is implemented.

According to a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is also disclosed, on which a computer program is stored, which when executed by a processor, implements the method for recommending and presenting a product according to the first aspect.

Compared with the prior art, the technical scheme provided by the embodiment of the invention has the following advantages:

according to the recommendation and display scheme for the commodities provided by the embodiment of the invention, the associated data corresponding to the commodity subsidy information is received according to a preset period, wherein the commodity subsidy information can comprise: the system comprises area information, virtual preference object information and target user information. The association data may include: user lists, commodity pools, and user behavior data. And then extracting feature data from the associated data, and generating modeling sample data and modeling target data according to the feature data. And predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on a machine learning algorithm, modeling sample data and modeling target data. And finally, taking the commodities with the order information larger than the corresponding order information threshold value as recommended commodities, and sequencing and displaying the recommended commodities according to probability information of each user for the recommended commodities for each user in the user list.

According to the embodiment of the invention, modeling sample data and modeling target data are created, the order information of each commodity is obtained based on the prediction of a machine learning algorithm, then the order information is compared with the order information threshold value, and the commodity with the order information larger than the order information threshold value is taken as a recommended commodity, so that the commodity corresponding to the commodity subsidy information is prevented from being manually selected and uploaded. Moreover, for each user in the user list, the display can be performed in an ordered manner according to the probability information of the recommended commodities, so that the disordered display of the commodities is avoided, and the experience of selecting and purchasing the commodities by the user is improved.

Drawings

FIG. 1 is a flowchart illustrating steps of a method for recommending and displaying merchandise according to an embodiment of the present invention;

fig. 2 is a schematic diagram illustrating a working principle of a scheme of commodity pool mining and commodity personality display according to an embodiment of the present invention;

FIG. 3 is a block diagram of a device for recommending and displaying merchandise according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Referring to fig. 1, a flowchart illustrating steps of a method for recommending and displaying a commodity according to an embodiment of the present invention is shown. The commodity recommending and displaying method can be applied to a terminal or a server. The commodity recommending and displaying method specifically comprises the following steps:

step 101, receiving associated data corresponding to the commodity subsidy information according to a preset period.

In an embodiment of the present invention, the article subsidy information may include: the system comprises area information, virtual preference object information and target user information. And the area information, the virtual preferential object information and the target user information have a corresponding relation. In practical application, commodity subsidy information can be acquired from the coupon issuing system every day. The virtual coupon object information may be coupon information, and the target user information may be user information of a coupon to be received. For example, the commodity subsidy information may be as shown in table 1.

Region information	Coupon information	Target user information
			Region of Q1	Full of 10-2	pin001
Region of Q1	Full of 10-2	pin057
			Region of Q1	Full of 10-2	pin2145
Region of Q1	5-3 of	pin251
			Region of Q1	5-3 of	pin1254
Region of Q1	5-3 of Chinese medicinal materials	pin8457
			Region of Q1	2-1 of	pin421
Region Q1	2-1 of	pin96
			Region of Q1	2-1 of	pin946
Region of Q1	9.9-3 parts by weight	pin421
			Region of Q1	9.9-3 parts by weight	pin63
Region of Q1	9.9-3 parts by weight	pin894
			Region of Q1	All of 19.9-4	pin235
Region Q1	Full 19.9-4	pin63
			Region of Q1	Full 19.9-4	pin7324
Region of Q1	All of 3-0.9	pin845832
			Region of Q1	All of 3-0.9	pin235
Region of Q1	Full of 3-0.9	pin6367

TABLE 1

In the coupon information, "full 10-2" may indicate that when the amount of the product reaches 10 yuan, the coupon is decreased by 2 yuan. In the above-mentioned target user information, "pin 001" may indicate type information of a target user, and the target user information may indicate one user or a group of users. Moreover, the coupon information to be issued may or may not be the same for different regions.

In an embodiment of the invention, the association data may comprise: user lists, commodity pools, and user behavior data. In practical application, the associated data corresponding to the commodity subsidy information may be received from a preset database according to a preset period. The commodity pool can be understood as a commodity pool conforming to the gross constraints. The gross constraint is that the amount of the item is greater than the full decrement amount in the coupon. For example, if a certain coupon information is full 5-3, the product amount needs to be larger than full minus 3 in the coupon information. User behavior data may be understood as behavior data of a user in a pool of goods that comply with the gross profit constraints, including but not limited to: browse data, click data, search data, buy data, order data, return data, and the like. Furthermore, the user behavior data may be behavior data transmitted from the user terminal to the database on the premise that the user knows and agrees. For example, the association data may be as shown in table 2.

Region information

Coupon information

Target user information

Commodity information

Browsing data

Click data

Searching data

Order data

Region of Q1

Full of 10-2

pin001

sku1

……

Region Q1

All of which is 10-2

pin002

sku7

……

Region of Q1

5-1 of

pin001

sku9

……

Region of Q1

5-1 of

pin002

sku15

……

Region of Q1

20-5% of total

pin001

sku5

……

Region of Q1

20-5% of total

pin002

sku8

……

TABLE 2

In table 2, the commodity information may be number information of each commodity in the commodity pool. "… …" in the browse data, click data, search data, and order data represents a corresponding data field or packet that may include, but is not limited to: date, time, number, amount, number, identification, and the like. The data form, data structure, data content, and the like denoted by "… …" are not particularly limited by the embodiments of the present invention.

It should be noted that the received associated data can be updated in real time to ensure the validity and the dynamic property of the commodity pool.

Step 102, extracting feature data from the associated data.

In the embodiment of the invention, the user group feature data and the user feature data can be extracted from the associated data in an automatic feature integration mode.

And 103, generating modeling sample data and modeling target data according to the characteristic data.

In the embodiment of the present invention, since the extracted feature data may include user group feature data and user feature data, user group modeling sample data and user group modeling target data may be generated according to the user group feature data, and user modeling sample data and user modeling target data may be generated according to the user feature data.

And 104, predicting order information of the user list aiming at each commodity in the commodity pool based on the machine learning algorithm, the modeling sample data and the modeling target data.

In the embodiment of the invention, the order information of each user group in the user list for each commodity in the commodity pool can be obtained through prediction based on the regression algorithm, the user group modeling sample data and the user group modeling target data. For example, the order information may be the number of orders placed, the frequency of orders placed, the probability of orders placed, and the like.

And 105, taking the commodity with the order information larger than the corresponding order information threshold value as a recommended commodity, and sequencing and displaying the recommended commodity according to probability information of each user for the recommended commodity for each user in the user list.

In the embodiment of the invention, the order information threshold of the commodities in the commodity pool by the user group in the associated data corresponding to the commodity subsidy information is calculated in advance, then the order information of each commodity in the commodity pool by the user group is compared with the order information threshold, and finally the commodity of which the order information is greater than the corresponding order information threshold is taken as a recommended commodity, namely the commodity of which the order information is greater than the corresponding order information threshold is recommended to the user group. When the recommended commodities are displayed for each user in the user group, the recommended commodities are displayed in descending order according to the probability information of each user.

According to the recommendation and display scheme for the commodities provided by the embodiment of the invention, the associated data corresponding to the commodity subsidy information is received according to a preset period, wherein the commodity subsidy information can comprise: the system comprises area information, virtual preference object information and target user information. The association data may include: user lists, commodity pools, and user behavior data. And then extracting feature data from the associated data, and generating modeling sample data and modeling target data according to the feature data. And predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on the machine learning algorithm, the modeling sample data and the modeling target data. And finally, taking the commodities with the order information larger than the corresponding order information threshold value as recommended commodities, and sequencing and displaying the recommended commodities according to probability information of each user for the recommended commodities for each user in the user list.

According to the embodiment of the invention, the modeling sample data and the modeling target data are created, the order information of each commodity is obtained based on the prediction of the machine learning algorithm, then the order information is compared with the order information threshold value, and the commodity of which the order information is greater than the order information threshold value is taken as the recommended commodity, so that the commodities corresponding to the commodity subsidy information are prevented from being manually selected and uploaded, and the labor cost is reduced. Moreover, for each user in the user list, the display can be performed in an ordered manner according to the probability information of the recommended commodities, so that the disordered display of the commodities is avoided, and the experience of selecting and purchasing the commodities by the user is improved.

In a preferred embodiment of the present invention, the user group feature data is extracted from the related data in such a manner that user behavior information, commodity amount information, and degree of variation information for each commodity of each user group in the user list are extracted from the related data. One embodiment of extracting the user feature data from the related data is to extract user behavior information, commodity amount information, and variation degree information of each user for each commodity in the user list from the related data.

In practical applications, the user behavior information, the commodity amount information, and the variation degree information of each user group for each commodity may be the same as or different from the user behavior information, the commodity amount information, and the variation degree information of each user for each commodity. The user behavior information may include a time difference between the last user operation and the current time, a frequency of the user operation within a preset first time period, a time difference between the first user operation and the current time, and the like. The commodity amount information is the total amount purchased in a preset second time period. The variation degree information is the consumption amount variance of the commodity in the preset third time period.

The user behavior information, the commodity amount information, and the variation degree information may be represented by corresponding fields. For example, the time difference between the last user operation and the current time in the user behavior information may be represented as a field "Recency". For example, the time difference between the latest time when a certain group of users clicked item sku1 in the item pool and the current time, and the time difference between the latest time when a certain user clicked item sku1 in the item pool and the current time. The field type of this field "Recency" is time type. The Frequency of the user operation in the first time period preset in the user behavior information may be represented as a field "Frequency". For example, the number of times a user group purchased the item sku1 in the item pool in the last three months, and the number of times a user purchased the item sku1 in the item pool in the last three months. The field type of this field "Frequency" is count type. The time difference between the first user operation and the current time in the user behavior information may be represented as a field "Tenure". For example, the time difference between the time when a certain group of users first purchases product sku1 in the product pool and the current time and the time difference between the time when a certain group of users first purchases product sku1 in the product pool and the current time. The field type of this field "Tenure" is time type. The merchandise amount information may be represented as a field "money". For example, the total amount of the product sku1 purchased by a group of users in the last three months and the total amount of the product sku1 purchased by a group of users in the last three months. The field type of this field "Monetary" is a total type. The variability information may be represented as a field "Variety". For example, the degree of change (variance can be interpreted) of the product sku1 in the product pool purchased by a certain user group in the last 6 months, and the degree of change of the consumption amount of the product sku1 in the product pool purchased by a certain user group in the last 6 months. The field type of the field "Variety" is numeric.

After the user group feature data and the user feature data are extracted, two types of sample data and modeling targets required by modeling can be automatically combined and generated. The user group modeling sample data and the user group modeling target data are generated according to the user group characteristic data, and the user modeling sample data and the user modeling target data are generated according to the user characteristic data.

For example, the user group modeling sample data and the user group modeling target data are shown in table 3.

TABLE 3

The modeling target in table 3 is user group modeling target data indicating order information of the user group1 for different commodities. In practical applications, the order information may be the number of orders placed.

For example, user modeling sample data and user modeling target data are shown in table 4.

TABLE 4

The modeling target in table 4, i.e., user modeling target data, indicates whether the user places an order for a different commodity. When the modeling target is 1, the order placing behavior of the user for the commodity is represented; when the modeling target is 0, it indicates that the user has no ordering behavior for the commodity.

After the user group modeling sample data and the user modeling sample data are obtained, order information and probability information can be predicted by using a machine learning algorithm.

In practical application, a regression algorithm may be used to predict the target of the user group, that is, predict the order information of the user group for each commodity in the commodity pool. In practical applications, the order information may be the number of orders placed.

For example, the user group order placing frequency estimation table for each product in the product pool is shown in table 5.

Region information	Coupon information	User group	Commodity information	Estimated number of orders to be placed
					Region of Q1	Full of 10-2	group1	sku1	35
Region of Q1	Full of 10-2	group1	sku7	352
					Region of Q1	Full of 10-2	group1	sku9	62
Region of Q1	Full of 10-2	group1	sku111	0
					Region of Q1	Full of 10-2	group1	skui	47
Region of Q1	Full of 10-2	group1	sku3	37

TABLE 5

In practical application, the target of the user can be predicted by using a classification algorithm, namely, probability information of the user for each commodity in the commodity pool is predicted. In practical applications, the probability information may be a lower order probability.

For example, the table of probability estimates for orders placed by the user for each item in the pool of items is shown in table 6.

TABLE 6

After the order information prediction table of the user group for each commodity in the commodity pool is obtained through machine learning, the commodity pool needs to be further refined through threshold comparison, that is, part of commodities in the commodity pool are filtered. In a preferred embodiment of the present invention, the step of calculating the order information threshold value comprises: calculating the mean value and the standard deviation of order information of each commodity for each user group; and taking the normal distribution result of the mean value and the standard deviation as an order information threshold value. For example, the average value (5 orders) of the orders of each commodity in the commodity pool by the user group is automatically obtained, the standard deviation 0.35125 of the orders is automatically obtained, and the 1sigma distribution evaluation is used as the threshold value (average value + one time standard deviation) of the orders. And selecting the commodities with the predicted number of times of placing orders exceeding the mean value plus one time of standard deviation into a refined commodity pool, taking the commodities with the number less than or equal to the mean value plus one time of standard deviation as long-tail commodities, automatically filtering the long-tail commodities, and forming the refined commodity pool by the residual commodities.

For example, the determination table of the refinement product pool is shown in table 7.

TABLE 7

After the refined commodity pool is obtained, that is, after recommended commodities are obtained, when the refined commodity pool is displayed, commodities in the refined commodity pool can be arranged in a descending order according to probability information of different users on the commodities.

Based on the above description about the embodiments of the method for recommending and displaying a commodity, a scheme for mining a commodity pool and displaying a commodity personality is introduced below. According to the scheme, a dynamic commodity pool which meets the gross profit constraint and the user requirement is excavated based on basic subsidy elements (commodity subsidy information), so that a proper commodity pool can be used for bearing when the coupons are issued and used. The pool of items that the user sees when using the coupon can be personalized. Referring to fig. 2, fig. 2 is a schematic diagram illustrating an operation principle of a scheme of commodity pool mining and commodity personality display.

Step 201, extracting basic subsidy elements.

The base subsidy elements may be obtained from a daily coupon distribution system. The basic subsidy element includes area information, coupon information (virtual coupon object information), user information (target user information) of the coupon to be issued, and a correspondence relationship among the area information, the coupon information (virtual coupon object information), and the user information (target user information) of the coupon to be issued.

Step 202, obtaining the associated data according to the basic subsidy elements.

And receiving the associated data corresponding to the basic subsidy elements in a preset database. The association data comprises a user list, a commodity pool according with gross profit restriction and user behavior data of the user in the commodity pool according with gross profit restriction.

And 203, generating modeling sample data and modeling target data of the dynamic commodity pool and the sequencing model according to the associated data.

The method comprises the steps of extracting user group characteristic data and user characteristic data from associated data, and then generating user group modeling sample data and user group modeling target data, the user modeling sample data and the user modeling target data based on the user group characteristic data and the user characteristic data.

And 204, training a dynamic commodity pool and a sequencing model according to the modeling sample data and the modeling target data, and predicting by using the trained dynamic commodity pool and the trained sequencing model to obtain a refined commodity pool and a commodity sequencing result.

And predicting by using a regression algorithm to obtain a refined commodity pool, and predicting by using a classification algorithm to obtain a commodity sequencing result.

Step 205, dynamically updating the commodity pool in the coupon issuing stage, and dynamically updating the refined commodity pool in the coupon using stage.

And calculating the gross profit of the commodities in the commodity pool in the coupon issuing stage, calculating the gross profit of the commodities in the refined commodity pool in the coupon using stage, eliminating the commodities which do not accord with the gross profit constraint, and dynamically ensuring the effectiveness and the real-time performance of the commodities in the commodity pool and the refined commodity pool.

According to the embodiment of the invention, the refined commodity pool can be automatically generated and commodities in the refined commodity pool can be individually sequenced, so that a large amount of labor cost is saved.

The embodiment of the invention can dynamically update the commodity pool and the refined commodity pool, so that the commodity pool in the coupon issuing stage can be updated in time, and a dynamic filtering mechanism is added in the coupon using stage, thereby ensuring that the gross profit of the commodity in the coupon issuing stage and the coupon using stage is not broken down, and avoiding the loss of income.

The embodiment of the invention provides a personalized refined commodity pool for different users, and enlarges the application range of commodity recommendation.

It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those of skill in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the embodiments of the invention.

Referring to fig. 3, a block diagram of a device for recommending and displaying a commodity according to an embodiment of the present invention is shown, where the device for recommending and displaying a commodity can be applied to a terminal or a server. The commodity recommending and displaying device specifically comprises the following modules:

the data obtaining module 31 is configured to receive, according to a preset period, associated data corresponding to the commodity subsidy information, where the commodity subsidy information includes: the system comprises area information, virtual preferential object information and target user information, wherein the associated data comprises: a user list, a commodity pool and user behavior data;

a feature extraction module 32, configured to extract feature data from the associated data;

a modeling data generation module 33, configured to generate modeling sample data and modeling target data according to the feature data;

a data prediction module 34, configured to predict, based on a machine learning algorithm, the modeling sample data, and the modeling target data, order information of the user list for each commodity in the commodity pool;

and the recommendation display module 35 is configured to use the commodity of which the order information is greater than the corresponding order information threshold value as a recommended commodity, and rank and display the recommended commodity according to probability information of each user for the recommended commodity for each user in the user list.

In a preferred embodiment of the present invention, the feature extraction module 32 is configured to extract user group feature data and user feature data from the associated data.

In a preferred embodiment of the present invention, the feature extraction module 32 includes:

the user group characteristic data extraction module is used for extracting user behavior information, commodity amount information and variation degree information of each user group aiming at each commodity in the user list from the associated data;

the feature extraction module 32 further includes:

and the user characteristic data extraction module is used for extracting user behavior information, commodity amount information and variation degree information of each user aiming at each commodity in the user list from the associated data.

In a preferred embodiment of the present invention, the user behavior information includes a time difference between a latest user operation and a current time, a frequency of the user operation within a preset first time period, and a time difference between the first user operation and the current time; the commodity amount information is the total amount purchased in a preset second time period; and the variation degree information is the consumption amount variance of the commodity in a preset third time period.

In a preferred embodiment of the present invention, the modeling data generating module 33 is configured to generate user group modeling sample data and user group modeling target data according to the user group feature data, and generate user modeling sample data and user modeling target data according to the user feature data.

In a preferred embodiment of the present invention, the data prediction module 34 is configured to predict order information of each user group in the user list for each commodity in the commodity pool based on a regression algorithm, the user group modeling sample data, and the user group modeling target data.

In a preferred embodiment of the present invention, the apparatus further comprises: the threshold value calculation module is used for calculating the order information threshold value, and the threshold value calculation module is used for calculating the mean value and the standard deviation of the order information of each commodity aiming at each user group; and taking the normal distribution result of the mean value and the standard deviation as the order information threshold value.

An embodiment of the present invention further provides an electronic device, with reference to fig. 4, including: the system comprises a processor 401, a memory 402 and a computer program 4021 stored on the memory 402 and operable on the processor 401, wherein the processor 401 implements the commodity recommending and displaying method of the foregoing embodiment when executing the program 4021.

The embodiment of the invention also provides a readable storage medium, wherein a computer program is stored on the readable storage medium, and when the program is executed by a processor, the program realizes the commodity recommending and displaying method of the embodiment.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

It should be noted that all actions of acquiring signals, information or data in the embodiments of the present invention are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The above method and apparatus for recommending and displaying a commodity provided by the present invention are introduced in detail, and a specific example is applied in the present document to explain the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understand the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A method for recommending and displaying commodities is characterized by comprising the following steps:

receiving associated data corresponding to commodity subsidy information according to a preset period, wherein the commodity subsidy information comprises: the system comprises area information, virtual preferential object information and target user information, wherein the associated data comprises: a user list, a commodity pool, and user behavior data;

extracting feature data from the associated data;

generating modeling sample data and modeling target data according to the characteristic data;

predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on a machine learning algorithm, the modeling sample data and the modeling target data;

and taking the commodity with the order information larger than the corresponding order information threshold value as a recommended commodity, and sequencing and displaying the recommended commodity according to probability information of each user for the recommended commodity for each user in the user list.

2. The method of claim 1, wherein extracting feature data from the associated data comprises:

and extracting user group characteristic data and user characteristic data from the associated data.

3. The method of claim 2, wherein the extracting user group feature data from the associated data comprises:

extracting user behavior information, commodity amount information and variation degree information of each user group aiming at each commodity in the user list from the associated data;

the extracting of the user feature data from the associated data includes:

and extracting user behavior information, commodity amount information and variation degree information of each user aiming at each commodity in the user list from the associated data.

4. The method according to claim 3, wherein the user behavior information includes a time difference between a last user operation and a current time, a frequency of the user operation within a preset first time period, and a time difference between the first user operation and the current time; the commodity amount information is the total amount purchased in a preset second time period; and the variation degree information is the consumption amount variance of the commodity in a preset third time period.

5. The method of claim 2, wherein generating modeling sample data and modeling target data from the feature data comprises:

generating user group modeling sample data and user group modeling target data according to the user group characteristic data, and generating the user modeling sample data and the user modeling target data according to the user characteristic data.

6. The method of claim 5, wherein said predicting order information for each commodity in the commodity pool for the user list based on a machine learning algorithm, the modeling sample data, and the modeling target data comprises:

and predicting to obtain order information of each user group in the user list aiming at each commodity in the commodity pool based on a regression algorithm, the user group modeling sample data and the user group modeling target data.

7. The method of claim 1, wherein the step of calculating the order information threshold comprises:

calculating the mean value and the standard deviation of order information of each commodity for each user group;

and taking the normal distribution result of the mean value and the standard deviation as the order information threshold value.

8. A recommendation and display device for merchandise, the device comprising:

the data acquisition module is used for receiving associated data corresponding to the commodity subsidy information according to a preset period, wherein the commodity subsidy information comprises: the method comprises the following steps of area information, virtual preference object information and target user information, wherein the associated data comprises the following data: a user list, a commodity pool, and user behavior data;

the characteristic extraction module is used for extracting characteristic data from the associated data;

the modeling data generation module is used for generating modeling sample data and modeling target data according to the characteristic data;

the data prediction module is used for predicting to obtain order information of the user list aiming at each commodity in the commodity pool based on a machine learning algorithm, the modeling sample data and the modeling target data;

and the recommendation display module is used for taking the commodities of which the order information is greater than the corresponding order information threshold value as recommended commodities and displaying the recommended commodities in an ordering mode according to the probability information of each user for the recommended commodities for each user in the user list.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for recommending and presenting merchandise according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of recommending and presenting an item of merchandise according to any one of claims 1 to 7.