CN117057863A

CN117057863A - Method for recommending commodity and related electronic device thereof

Info

Publication number: CN117057863A
Application number: CN202210618323.1A
Authority: CN
Inventors: 廖逸平
Original assignee: Taiwan Gamma Mobile Digital Co ltd
Current assignee: Taiwan Gamma Mobile Digital Co ltd
Priority date: 2022-04-29
Filing date: 2022-06-01
Publication date: 2023-11-14
Also published as: TWM634368U

Abstract

The disclosure provides a method for recommending commodities and a related electronic device thereof. The present disclosure provides an electronic device for processing a merchandise recommendation list. The electronic device comprises a communication module, a memory module and a processing module. The communication module is configured to perform: receiving the current state of a user; receiving at least one previous order of the user; receiving at least one browsing record of the user; and transmitting a first signal in response to the matching score of the item being greater than or equal to a first predetermined proportion of the user attribute score, wherein the first signal indicates that the item is to be added to the item recommendation list for the user. The processing module is configured to perform: determining a first set of user attributes based on the current state of the user; determining a second set of user attributes based on the at least one previous order of the user; determining a third set of user attributes based on the at least one browsing record of the user; determining a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes; and determining the matching score for the commodity based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of commodity attributes for the commodity.

Description

Method for recommending commodity and related electronic device thereof

Technical Field

The present disclosure relates to a method for recommending goods and related electronic devices. More particularly, the present disclosure relates to a method of recommending goods based on a degree of matching between a user and the goods and related electronic devices.

Background

The web shopping and auction platform is vigorous to bring huge web shopping merchant opportunities. How to recommend related commodities which can attract the attention of consumers according to the demands or the favorites of consumers can effectively improve the possibility of purchasing the commodities by the consumers, thereby facilitating the transaction.

Disclosure of Invention

The commodity recommending method may be to find out the popular commodity by counting sales amount or click through rate and recommend the popular commodity to each consumer. Or may recommend special or minimum price goods to the consumer and thereby entice the consumer to purchase. These practices may result in relatively reduced exposure to other cooler goods and opportunities to be purchased, and result in constant hot sales of the hot goods, which are not known to be consumed.

In some other recommendation methods, personalized commodity recommendations are given by way of data mining and based on the user's consumption habits, satisfaction or score feedback mechanisms. However, such a recommendation method requires recourse to a large number of user consumption records.

However, most commodity recommendation methods do not consider the relevance of commodity attributes. For example, the similarity or association of design styles or specifications of merchandise may be one of the important considerations of consumers before purchase occurs.

The disclosure provides a novel commodity recommendation method and an electronic device thereof. The disclosure provides a commodity recommendation method taking commodity attributes and user attributes as guide (user oriented) and a related electronic device thereof.

In certain embodiments, the present disclosure includes an electronic device for processing a recommendation list of items. The electronic device includes: the device comprises a communication module, a memory module and a processing module. The communication module is configured to communicatively couple with a user device of a user and a database. The communication module is configured to: receiving a current state of the user; receiving at least one previous order of the user; receiving at least one browsing record of the user; and transmitting a first signal indicating that the item is to be added to the item recommendation list for the user in response to the matching score of the item being greater than or equal to a first predetermined proportion of the user attribute score. The memory module is configured to store a plurality of instructions and information. The processing module is configured to be coupled to the communication module and the memory module and to perform the following operations based on instructions and information stored in the memory module: determining a first set of user attributes based on the current state of the user; determining a second set of user attributes based on the at least one previous order of the user; determining a third set of user attributes based on the at least one browsing record of the user; determining the user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes; and determining the matching score for the commodity based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of commodity attributes for the commodity.

In certain embodiments, the present disclosure includes a method for recommending goods. The method comprises the following steps: receiving the current state of a user; determining a first set of user attributes based on the current state of the user;

receiving at least one previous order of the user; determining a second set of user attributes based on the at least one previous order of the user; receiving at least one browsing record of the user; determining a third set of user attributes based on the at least one browsing record of the user; determining a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes; determining a matching score for the commodity based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of commodity attributes for the commodity; and adding the item to the user's recommendation list in response to the matching score of the item being greater than or equal to a first predetermined proportion of the user attribute score.

Drawings

Fig. 1 illustrates systems and devices according to some embodiments of the present disclosure.

Fig. 2 depicts a flow chart of a method according to some embodiments of the present disclosure.

Fig. 3A and 3B are schematic diagrams illustrating a method for calculating a user attribute score and a matching score according to some embodiments of the disclosure.

Fig. 4A-4C are schematic diagrams illustrating a method for calculating a user attribute score and a matching score according to some embodiments of the present disclosure.

Fig. 5 is a schematic diagram illustrating a method of calculating a user attribute score and a matching score according to some embodiments of the present disclosure.

Fig. 6A and 6B are schematic diagrams illustrating a method for calculating a user attribute score and a matching score according to some embodiments of the disclosure.

For a better understanding of the foregoing aspects of the disclosure, as well as additional aspects and embodiments thereof, reference should be made to the following description taken in conjunction with the above drawings. Like reference symbols in the various drawings indicate like elements. It should be noted that the various features may not be drawn to scale. Indeed, the size of the various features may be arbitrarily increased or decreased for clarity of discussion.

Detailed Description

Methods, systems, and other aspects of the present disclosure are described. Reference will now be made to certain embodiments of the disclosure, examples of which are illustrated in the accompanying drawings. While the disclosure will be described in conjunction with embodiments, it will be understood that they are not intended to limit the disclosure to these particular embodiments. On the contrary, the present disclosure is intended to cover alternatives, modifications and equivalents, which may be included within the spirit and scope of the disclosure. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Furthermore, in the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, one of ordinary skill in the art will be able to practice the present disclosure without these specific details. In other instances, methods, procedures, operations, components, and networks that are well known to those of ordinary skill in the art have not been described in detail so as not to obscure aspects of the present disclosure.

Fig. 1 illustrates a system 100 and a user device 140 according to some embodiments of the present disclosure. The system 100 may include a server 110, a database 120. In some embodiments, the server 110 may be located at a company that provides online shopping, a company that provides merchandise management, or other company that provides related services. The database 120 may be located at a company that provides online shopping, a company that provides merchandise management, or other company that provides related services. The database 120 may be used to store user data and merchandise data.

The server 110 may include an input-output module 111, a memory module 112, a processing module 113, and a communication module 114. The database 120 may include an input-output module 121, a memory module 122, a processing module 123, and a communication module 124. The user device 130 may include an input-output module 131, a memory module 132, a processing module 133, and a communication module 134.

The server 110 may be a workstation or a computer. Database 120 may be a workstation or a computer. In some embodiments, database 120 may be integrated in server 110. The user device 140 may be a computer, personal digital assistant, smart phone, or tablet computer.

The server 110 and the database 120 may be communicatively coupled to each other via a communication module 114 of the server 110 and a communication module 124 of the database 120. The server 110 and database 120 may be communicatively coupled to each other by a wired method, such as via an ethernet line, coaxial cable, universal Serial Bus (USB), or other communication capable line. The server 110 and the database 120 may be communicatively coupled to each other by wireless means, such as by Bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols.

In some embodiments, the server 110 and the database 120 may be located in different geographic locations. The server 110 may be communicatively coupled to each other with the internet via a communication module 114 of the server 110. The server 110 may be communicatively coupled to the Internet by wired means, such as by Ethernet lines, coaxial cables, or other lines with communication capabilities, or by wireless means, such as by Bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols. The database 120 may be communicatively coupled to each other with the internet via a communication module 124 of the database 120. The database 120 may also be communicatively coupled to the Internet by wired means, such as by Ethernet lines, coaxial cables, or other lines with communication capabilities, or by wireless means, such as by Bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols. The server 110 and the database 120 may be communicatively coupled to each other via the internet.

Via the communication module 134 of the user device 130, the system 100 and the user device 130 may be communicatively coupled to each other by wireless means, such as by bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols. In some embodiments, via the communication module 134 of the user device 130, the system 100 and the user device 130 may be communicatively coupled to each other by a wired method, such as via an ethernet line, coaxial cable, USB, or other communication-enabled line. The system 100 may be communicatively coupled with a user device 130 through a communication module 114 of the server 110. In some embodiments, the system 100 may be communicatively coupled with the user device 130 through additional communication modules.

In some embodiments, system 100 may be communicatively coupled to Internet 140 by wired means (e.g., via Ethernet lines, coaxial cables, or other lines with communication capabilities), or by wireless means (e.g., via Bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols). The user device 130 may be communicatively coupled to each other with the internet via a communication module 134 of the user device 130. User device 130 may also be communicatively coupled to the internet by wired means, such as by ethernet, coaxial cable, or other lines with communication capabilities, or by wireless means, such as by bluetooth, IEEE 802.11, LTE, 5G, or other wireless communication protocols. The system 100 and the user device 130 may be communicatively coupled to each other through the internet.

The input-output module 111, the memory module 112, the processing module 113, and the communication module 114 of the server 110 may be configured to perform operations described below and in fig. 2-6B. The input-output module 121, the memory module 122, the processing module 123, and the communication module 124 of the database 120 may be configured to perform the operations described below and in fig. 2-6B. In some embodiments, the system 100 may perform the operations described below and in fig. 2-6B through additional output modules, memory modules, processing modules, and communication modules.

Fig. 2 illustrates a flow chart of a process 200 according to some embodiments of the present disclosure. Various operations of procedure 200 may be performed by system 100 as shown in fig. 1. The operations of procedure 200 may be performed by server 110 in system 100 as shown in fig. 1. The operations of procedure 200 may be coordinated with database 120 by server 110 in system 100 as shown in fig. 1. The operations of process 200 may be coordinated with user device 130 by system 100 as shown in fig. 1.

Program 200 may include an operation 201. Operation 201 comprises receiving a current state of a user. The user may input the current state of the user through the user device 130. The user may input the user's current activity, current emotion, current place, or other current state into the user device 130. The current status of the user may be received from the user device 130 or database 120 via the corresponding communication module. The current location of the user may be determined by the location of the user device 130. The current activity of the user may be determined based on the location of the user device 130 and nearby activities. The current activity or current emotion of the user may be determined based on the location of the user device 130 and the most recent social software textbook. The communication module 114 of the server 110 may be configured to perform operation 201. In some embodiments, operation 201 may be performed in response to user device 130 starting an associated program (e.g., a shopping platform program, or a program that may browse a shopping platform).

Program 200 may include an operation 202. Operation 202 comprises determining a first set of user attributes based on a current state of a user. A first set of user attributes is determined via the respective processing module based on a current activity, a current emotion, a current place, or other current state of the user. For example, the user's current location is "Apple commodity monopoly," then it may be determined that the first set of user attributes includes Apple's related attributes, such as "brand" or "Apple applicable" attributes. For example, if the user's current activity is "celebrating a birthday," then it may be determined that the first set of user attributes includes related attributes of the birthday, such as attributes of "birthday cake" or attributes of "birthday gift. For example, the current emotion of the user is "stress", and the first set of user attributes may be determined to include stress relieving related attributes, such as "stress relieving" attributes.

Program 200 may include operation 203. Operation 203 comprises receiving at least one previous order for the user. One or more previous orders for the user may be received from the database 120 via the respective communication modules. Operation 203 may further comprise viewing the merchandise in the previous order, as well as related merchandise attributes of the merchandise.

Program 200 may include an operation 204. Operation 204 comprises determining a second set of user attributes based on at least one previous order of the user. One or more previous orders received from the database 120 for the user may include one or more purchased merchandise. A second set of user attributes may be determined via the respective processing modules based on items purchased in the user's previous order. For example, if the merchandise purchased in the user's previous order includes Sony's cell phone, the second set of user attributes may include "brand Sony" or "Sony applicable" attributes. If the items purchased in the user's previous order include non-print good items, the second set of user attributes may include a "reduced style" attribute.

Program 200 may include an operation 205. Operation 205 comprises receiving at least one browsing record of a user. One or more browsing records of the user can be received according to the temporary record of the server side. One or more browsing records of the user may be received from the database 120 via the respective communication modules. Operation 206 may further include viewing the merchandise in the browse record and related merchandise attributes of the merchandise.

Program 200 may include an operation 206. Operation 206 comprises determining a third set of user attributes based on at least one browsing record of the user. The one or more browsing records may include one or more clicked or browsed merchandise. Based on the clicked or browsed merchandise in the user's browsing record, a third set of user attributes may be determined via the corresponding processing module. For example, if a user has clicked or browsed a shirt comprising flannel in a browsing record, a third set of user attributes may comprise the attribute of "flannel" or the attribute of "casual shirt". If the merchandise purchased in the user's previous order includes a knit vest, the second set of user attributes may include the attributes of "college style" or "woolen" attributes.

According to the present disclosure, the merchandise attribute of the merchandise may be determined based on the visual feature of the merchandise, the tactile feature of the merchandise, the design feature of the merchandise, the brand feature of the merchandise, the text feature of the merchandise, or the category of the merchandise. For example, the merchandise attributes may be determined to include "moldy color system" or "pink system" based on the visual characteristics of the merchandise. The commodity attributes may be determined based on design characteristics of the commodity including "reduced style", "Goldwind", or "Industrial wind". Commodity attributes including "HERMES", "LV" or "PRADA" may be determined based on brand characteristics of the commodity. Determining commodity attributes based on commodity word characteristics including 'i want to pay', 'retirement early' orThe merchandise attributes may be determined based on the category of the merchandise, including "top-quality," evening package, "or" necklace.

Program 200 may include an operation 207. Operation 207 comprises determining a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes. Operation 207 may determine a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes, and via the respective processing modules.

Program 200 may include an operation 208. Operation 208 includes determining a matching score for the good based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and the first set of good attributes for the good. Operation 207 may determine a matching score for the item via the respective processing module based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and the first set of item attributes for the item. Operation 208 may further include receiving merchandise data and/or respective merchandise attributes from database 120 via respective communication modules. A match score for the item for the user is determined based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a degree of match between the item and the first set of item attributes.

Program 200 may include an operation 209. Operation 209 comprises adding the item to the recommendation list of the user in response to the matching score of the item being greater than or equal to the predetermined proportion of the user attribute score. In some embodiments, in response to the matching score of the item being greater than or equal to a predetermined proportion of the user attribute score, a signal may be transmitted via the respective communication module to indicate that the item is to be added to the user's recommendation list.

If the predetermined ratio of operation 209 is set to 100%, the matching score of the good must be equal to the attribute score of the user, and the good may be added to the user's recommendation list. In other words, if the predetermined proportion of operation 209 is set to 100%, the merchandise attributes of the merchandise must be equal to a specific combination of the first, second, and third sets of user attributes, and the merchandise may be added to the user's recommendation list. If the predetermined ratio of operation 209 is set to 100%, the range of recommended goods is limited. According to some embodiments of the present disclosure, if the predetermined proportion of operation 209 is set to between 60% and 90%, the range of recommended goods is less limited. Because the range of the recommended commodity is not limited, the fatigue of the user caused by browsing similar commodities in a large amount can be effectively reduced, and the probability of purchasing the recommended commodity can be improved. According to certain embodiments of the present disclosure, if the predetermined proportion of operation 209 is set to 80%, the probability that the recommended merchandise is purchased may be effectively increased.

Fig. 3A and 3B are diagrams illustrating calculation of user attribute scores and matching scores according to some embodiments of the present disclosure. The computing methods disclosed in fig. 3A and 3B may be performed by the system 100. The computing methods disclosed in fig. 3A and 3B may be performed by the processing module 113 of the server 110 or by the processing module 123 of the database 120.

The set of user attributes described in this disclosure may be a collection, the elements of which are attributes. For example, the first set of user attributes may be the set ua1= { cell phone, brand Sony, applicable to Sony, xperia, android }. The set of merchandise attributes described in this disclosure may be a collection, the elements of which are attributes. For example, the first set of merchandise attributes may be the set ca1= { cell phone, brand Apple, applicable to Apple, iPhone, iOS }.

Fig. 3A shows a first set of user attributes UA1, a second set of user attributes UA2, and a third set of user attributes UA3. The fourth set of user attributes UA4 is determined based on the first set of user attributes UA1, the second set of user attributes UA2 and the third set of user attributes UA3. The fourth set of user attributes UA4 may be a union of the first set of user attributes UA1, the second set of user attributes UA2, and the third set of user attributes UA3. A user attribute score for the user is determined based on the fourth set of user attributes UA4. The user attribute score of this user may be the number of attributes of the fourth set of user attributes UA4.

For example, assume a first set of user attributes ua1= { a, b, c }, a second set of user attributes ua2= { c, d, e }, a third set of user attributes ua3= { d, e, f, g }, where each of the elements a, b, c, d, e, f, g is an attribute. Based on the union of the first, second and third sets of user attributes UA1, UA2, UA3, a fourth set of user attributes ua4=ua1_u2uu3= { a, b, c, d, e, f, g }. The user attribute score of the corresponding user is then n (UA 4) = |ua4|=7.

Fig. 3B shows a fourth set of user attributes UA4 (e.g., gray shapes in fig. 3B) and a first set of merchandise attributes CA1 (e.g., circles drawn with dashed lines in fig. 3B) of the merchandise. A second set of product attributes CA2 for the product is determined based on the fourth set of user attributes UA4 and the first set of product attributes CA 1. The second set of merchandise attributes CA2 of the merchandise may be an intersection of the fourth set of user attributes UA4 with the first set of merchandise attributes CA 1. A degree of matching of a user with the commodity is determined based on a second set of commodity attributes CA2 for the commodity. A matching score of a user attribute score of a user with the commodity is determined based on a second set of commodity attributes CA2 of the commodity. The matching score of the user attribute score and the commodity may be the attribute number of the second set of commodity attributes CA2 of the commodity.

For example, when the fourth set of user attributes UA 4= { a, b, c, d, e, f, g } and the first set of merchandise attributes ca1= { c, d, e, h, i, j }, each of the elements c, d, e, h, i, j is an attribute. Based on the intersection of the fourth set of user attributes UA4 with the first set of merchandise attributes CA1, the second set of merchandise attributes ca2=ua4 ∈ca1= { c, d, e }. The matching score of the user attribute score of the corresponding user and the commodity is as follows: n (CA 2) = |ca2|=3.

Assume that the predetermined ratio described in operation 209 is 80%. The user attribute score is 7 and the matching score is 3,3 is less than 7 x 80%, so the corresponding commodity will not be added to the commodity recommendation list of the corresponding user.

Fig. 4A-4C are diagrams illustrating the calculation of user attribute scores and matching scores in some embodiments according to the present disclosure. The computing methods disclosed in fig. 4A-4C may be performed by the system 100. The computing methods disclosed in fig. 4A-4C may be performed by the processing module 113 of the server 110 or by the processing module 123 of the database 120.

In the calculation methods of the user attribute scores of fig. 4A to 4C, the user attribute score of the user is determined based on the attribute number of the first group of user attributes UA1, the attribute number of the second group of user attributes UA2, and the attribute number of the third group of user attributes UA 3. The user attribute score for this user may be the sum of the number of attributes of the first set of user attributes UA1, the number of attributes of the second set of user attributes UA2, and the number of attributes of the third set of user attributes UA 3.

For example, assume a first set of user attributes ua1= { a, b, c }, a second set of user attributes ua2= { c, d, e }, and a third set of user attributes ua3= { d, e, f, g }. The user attribute score of the corresponding user is: n (UA 1) +n (UA 2) +n (UA 3) = |ua1|+|ua2|+|ua3|=10.

In this embodiment, the repeated attributes (elements) will be repeatedly calculated as scores. Attribute c appears in the first set of user attributes UA1 and the second set of user attributes UA2 and is counted as 2 points. Attribute d appears in the second set of user attributes UA2 and the third set of user attributes UA3 and is counted as 2 points. Attribute e appears in the second set of user attributes UA2 and the third set of user attributes UA3 and is counted as 2 points.

Fig. 4A shows a first set of user attributes UA1 (as a circle drawn with a solid line in fig. 4A) and a first set of merchandise attributes CA1 (as an ellipse drawn with a broken line in fig. 4A) of merchandise. Fig. 4B shows a second set of user attributes UA2 (as a circle drawn with a solid line in fig. 4B) and a first set of merchandise attributes CA1 (as an ellipse drawn with a broken line in fig. 4B) of the merchandise. Fig. 4C shows a third set of user attributes UA3 (as a circle drawn with solid lines in fig. 4C) and a first set of merchandise attributes CA1 of the merchandise (as an ellipse drawn with broken lines in fig. 4C).

A third set of merchandise attributes CA3 for the merchandise is determined based on the first set of merchandise attributes CA1 and the first set of user attributes UA1. The third set of product attributes CA3 of the product may be the intersection of the first set of product attributes CA1 and the first set of user attributes UA1, i.e. ca3=ca1 n UA1. A fourth set of merchandise attributes CA4 for the merchandise is determined based on the first set of merchandise attributes CA1 and the second set of user attributes UA2. The fourth set of product attributes CA4 of the product may be the intersection of the first set of product attributes CA1 and the second set of user attributes UA2, i.e. ca4=ca1 n UA2. A fifth set of product attributes CA5 for the product is determined based on the first set of product attributes CA1 and the third set of user attributes UA3. The fifth set of product attributes CA5 of the product may be the intersection of the first set of product attributes CA1 and the third set of user attributes UA3, i.e. ca5=ca1 n UA3.

The matching degree of the user and the commodity is determined based on the attribute number of the third group commodity attribute CA3, the attribute number of the fourth group commodity attribute CA4 and the attribute number of the fifth group commodity attribute CA5. The matching score of the user attribute score of the user and the commodity is determined based on the attribute number of the third group commodity attribute CA3, the attribute number of the fourth group commodity attribute CA4 and the attribute number of the fifth group commodity attribute CA5. The matching score of the user attribute score and the commodity may be the sum of the attribute number of the third set of commodity attributes CA3, the attribute number of the fourth set of commodity attributes CA4, and the attribute number of the fifth set of commodity attributes CA5 of the commodity.

For example, when the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first set of merchandise attributes CA 1= { a, c, d, e, f }. Based on the intersection of the first set of merchandise attributes CA1 and the first set of user attributes UA1, the third set of merchandise attributes ca3= { a, c }. Based on the intersection of the first set of merchandise attributes CA1 and the second set of user attributes UA2, the fourth set of merchandise attributes ca4= { c, d, e }. Based on the intersection of the first set of merchandise attributes CA1 and the third set of user attributes UA3, the fifth set of merchandise attributes ca5= { d, e, f }. The matching score of the user attribute score of the corresponding user and the commodity is as follows:

n(CA3)+n(CA4)+n(CA5)＝|CA3|+|CA4|+|CA5|＝8。

assume that the predetermined ratio described in operation 209 is but 80%. The user attribute score is 10, and the matching score is 8,8 equals 10 x 80%, so the corresponding commodity will be added to the commodity recommendation list of the corresponding user.

In another method of calculating the user attribute score of fig. 4A to 4C, the user attribute score of the user is determined based on the attribute number of the first set of user attributes UA1, the attribute number of the second set of user attributes UA2, the attribute number of the third set of user attributes UA3, and the corresponding weight values. A first user weighted score may be determined based on the product of the number of attributes of the first set of user attributes UA1 and the first weight value W1; a second user weighted score may be determined based on the product of the number of attributes of the second set of user attributes UA2 and the second weight value W2; and a third weighted score may be determined based on the product of the number of attributes of the third set of user attributes UA3 and the third weight value W3. The user attribute score for the user may be a sum of the first user weighted score, the second user weighted score, and the third user weighted score.

For example, let us assume that the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first weight W1 is 3, the second weight W2 is 2, the third weight W3 is 1, and the user attribute score of the corresponding user is:

n(UA1)*3+n(UA2)*2+n(UA3)*1＝|UA1|*3+|UA2|*2+|UA3|*1＝19。

in this embodiment, in addition to the repeated attributes (elements) being repeatedly scored, attributes that appear in different groups are weighted differently.

A third set of merchandise attributes CA3 for the merchandise is determined based on the first set of merchandise attributes CA1 and the first set of user attributes UA 1. The third set of merchandise attributes CA3 of the merchandise may be an intersection of the first set of merchandise attributes CA1 and the first set of user attributes UA 1. A fourth set of merchandise attributes CA4 for the merchandise is determined based on the first set of merchandise attributes CA1 and the second set of user attributes UA 2. The fourth set of merchandise attributes CA4 of the merchandise may be an intersection of the first set of merchandise attributes CA1 and the second set of user attributes UA 2. A fifth set of product attributes CA5 for the product is determined based on the first set of product attributes CA1 and the third set of user attributes UA 3. The fifth set of merchandise attributes CA5 of the merchandise may be an intersection of the first set of merchandise attributes CA1 and the third set of user attributes UA 3.

In another calculation method of the matching score of fig. 4A to 4C, the matching degree of the user with the commodity is determined based on the attribute number of the third group commodity attribute CA3, the attribute number of the fourth group commodity attribute CA4, the attribute number of the fifth group commodity attribute CA5, and the corresponding weight value. And determining the matching score of the user attribute score of the user and the commodity based on the attribute number of the third group of commodity attributes CA3, the attribute number of the fourth group of commodity attributes CA4, the attribute number of the fifth group of commodity attributes CA5 and the corresponding weight value. Determining a first commodity weighted score by multiplying the attribute number of the third group of commodity attributes CA3 of the commodity by a first weight value W1; determining a second commodity weighting score by multiplying the attribute number of the fourth group of commodity attributes CA4 by a second weight value W2; and determining a third commodity weighting score by multiplying the number of attributes of the fifth set of commodity attributes CA5 by the third weight value W3. The matching score of the user attribute score and the commodity may be a sum of the first commodity weighted score, the second commodity weighted score, and the third commodity weighted score.

For example, when the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first set of merchandise attributes CA 1= { a, c, d, e, f }. Based on the intersection of the first set of merchandise attributes CA1 and the first set of user attributes UA1, the third set of merchandise attributes ca3= { a, c }. Based on the intersection of the first set of merchandise attributes CA1 and the second set of user attributes UA2, the fourth set of merchandise attributes ca4= { c, d, e }. Based on the intersection of the first set of merchandise attributes CA1 and the third set of user attributes UA3, the fifth set of merchandise attributes ca5= { d, e, f }. The first weight value W1 is 3, the second weight value W2 is 2, the third weight value W3 is 1, and the matching score between the user attribute score of the corresponding user and the commodity is:

n(CA3)*3+n(CA4)*2+n(CA5)*1＝|CA3|*3+|CA4|*2+|CA5|*1＝15。

Assume that the predetermined ratio described in operation 209 is 80%. The user attribute score is 19, and the matching score is 15, 15 is less than 19 x 80%, so the corresponding commodity will not be added to the commodity recommendation list of the corresponding user.

In this embodiment, the repeated attributes (elements) will be repeatedly scored, with different weights occurring for different groups of attributes.

Fig. 5 is a schematic diagram illustrating the calculation of user attribute scores and matching scores in some embodiments according to the present disclosure. The computing method disclosed in fig. 5 may be performed by the system 100. The computing method disclosed in fig. 5 may be performed by the processing module 113 of the server 110 or by the processing module 123 of the database 120.

In the calculation method of the user attribute score of fig. 5, the attributes that are repeated different times are determined based on the number of attributes of the first group of user attributes UA1, the number of attributes of the second group of user attributes UA2, and the number of attributes of the third group of user attributes UA3.

In fig. 5, a first set of user properties UA1 (circles drawn in solid lines), a second set of user properties UA2 (circles drawn in solid lines) and a third set of user properties UA3 (circles drawn in solid lines) are depicted. The fifth set of user attributes UA5 is determined based on the intersection of the first set of user attributes UA1, the second set of user attributes UA2 and the third set of user attributes UA3. In other words, ua5=ua1 n ua2 n ua3. The sixth set of user attributes UA6 may be determined by subtracting the fifth set of user attributes UA5 from the intersection of the first set of user attributes UA1 and the second set of user attributes UA 2. In other words, ua6= (ua1.u.ua2) -ua5. The seventh set of user attributes may be determined by subtracting the fifth set of user attributes UA5 from the intersection of the first set of user attributes UA1 and the third set of user attributes UA3. In other words, ua7= (ua1.u.ua3) -ua5. The eighth set of user attributes UA8 may be determined by subtracting the fifth set of user attributes UA5 from the intersection of the second set of user attributes UA2 and the third set of user attributes UA3. In other words, ua8= (ua2.u.ua3) -UA5. The ninth set of user attributes may be determined by subtracting the union of the fifth set of user attributes UA5, the sixth set of user attributes UA6, and the seventh set of user attributes UA7 from the first set of user attributes UA 1. In other words, ua9=ua1- (ua5.u.ua6.u.ua7). The tenth set of user attributes UA10 may be determined by subtracting the union of the fifth set of user attributes UA5, the sixth set of user attributes UA6, and the eighth set of user attributes UA8 from the second set of user attributes UA 2. In other words, ua10=ua2- (ua5.u.ua6.u.ua8). The eleventh set of user attributes UA11 may be determined by subtracting the union of the fifth set of user attributes UA5, the seventh set of user attributes UA7, and the eighth set of user attributes UA8 from the third set of user attributes UA3. In other words, ua11=ua3- (ua5.u.ua7.u.ua8).

The fifth set of user attributes UA5 includes attributes that appear in all of the first set of user attributes UA1, the second set of user attributes UA2, and the third set of user attributes UA 3. The sixth set of user attributes UA6 includes attributes that appear only in the first set of user attributes UA1 and the second set of user attributes UA 2. The seventh set of user attributes UA7 includes attributes that occur only in the first set of user attributes UA1 and the third set of user attributes UA 3. The eighth set of user attributes UA8 includes attributes that occur only in the second set of user attributes UA2 and the third set of user attributes UA 3. The ninth set of user properties UA9 includes properties that only occur in the first set of user properties UA 1. The tenth set of user attributes UA10 includes attributes that occur only in the second set of user attributes UA 2. The eleventh set of user attributes UA11 includes attributes that occur only in the third set of user attributes UA 3.

A fourth user weighted score may be determined based on the product of the number of attributes of the fifth set of user attributes UA5 and the fourth weight value W4. In other words, the fourth user weighted score is n (UA 5) W4 or |ua5| W4. A fifth user weighted score may be determined based on the product of the number of attributes of the sixth set of user attributes UA5 and the fifth weight value W5. In other words, the fifth user weighted score is n (UA 6) W5 or |ua6| W5. A sixth user weighted score may be determined based on the product of the number of attributes of the seventh set of user attributes UA7 and the sixth weight value W6. In other words, the sixth user weighted score is n (UA 7) W6 or |ua7| W6. A seventh user weighted score may be determined based on the product of the number of attributes of the eighth set of user attributes UA8 and the seventh weight value. In other words, the seventh user weighted score is n (UA 8) W7 or |ua8| W7. An eighth user weighted score may be determined based on the product of the number of attributes of the ninth set of user attributes UA9 and the eighth weight value W8. In other words, the eighth user weight score is n (UA 9) W8 or |ua9| W8. A ninth user weighted score may be determined based on the product of the number of attributes of the tenth set of user attributes UA10 and the ninth weight value W9. In other words, the ninth user weighted score is n (UA 10) W9 or |ua10| W9. The tenth user weighted score may be determined based on the product of the number of attributes of the eleventh set of user attributes UA11 and the tenth weight value W10. In other words, the tenth user weight score is n (UA 11) W10 or |ua11| W10.

The fourth weight value W4, the fifth weight value W5, the sixth weight value W6, the seventh weight value W7, the eighth weight value W8, the ninth weight value W9, the tenth weight value W10 may be further adjusted based on the number of repetitions of the attributes and/or on what set of user attributes the attributes are present in (e.g., the first set of user attributes, the second set of user attributes, or the third set of user attributes). In some embodiments, if the weight value is adjusted based on the number of attribute repetitions, the fourth weight value W4 may be a first value, the fifth weight value W5, the sixth weight value W6, and the seventh weight value W7 may be a second value, and the eighth weight value W8, the ninth weight value W9, and the tenth weight value W10 may be a third value, wherein the first value, the second value, and the third value are different.

The user attribute score for this user may be the sum of the fourth user weighted score to the tenth user weighted score described above.

For example, assuming that the first set of user attributes ua1= { a, b, c, g }, the second set of user attributes ua2= { a, c, d, e }, the third set of user attributes ua3= { c, d, f, g }, the fifth set of user attributes ua5= { c }, the sixth set of user attributes ua6= { a }, the seventh set of user attributes ua7= { g }, the eighth set of user attributes ua8= { d }, the ninth set of user attributes ua9= { b }, the tenth set of user attributes ua10= { e }, the eleventh set of user attributes ua11= { f }. The user attribute score of the corresponding user is:

n(UA5)*W4+n(UA6)*W5+n(UA7)*W6+n(UA8)*W7+n(UA9)*W8+n(UA10)*W9+n(UA11)*W10＝|UA5|*W4+|UA6|*W5+|UA7|*W6+|UA8|*W7+|UA9|*W8+|UA10|*W9+|UA11|*W10＝W4+W5+W6+W7+W8+W9+W10。

The sixth set of merchandise attributes CA6 may be determined based on the intersection of the first set of merchandise attributes CA1 and the fifth set of user attributes UA5 for the merchandise. In other words, ca6=ca1 n UA5. The seventh set of merchandise attributes CA7 may be determined based on the intersection of the first set of merchandise attributes CA1 and the sixth set of user attributes UA6. In other words, ca7=ca1 n UA6. The eighth set of merchandise attributes CA8 may be determined based on the intersection of the first set of merchandise attributes CA1 and the seventh set of user attributes UA7. In other words, ca8=ca1 n UA7. The ninth set of merchandise attributes CA9 may be determined based on the intersection of the first set of merchandise attributes CA1 and the eighth set of user attributes UA8. In other words, ca9=ca1 n UA8. The tenth set of merchandise attributes CA10 may be determined based on the intersection of the first set of merchandise attributes CA1 and the ninth set of user attributes UA9. In other words, ca10=ca1 n UA9. The eleventh set of merchandise attributes CA11 may be determined based on the intersection of the first set of merchandise attributes CA1 and the tenth set of user attributes UA10. In other words, ca11=ca1 n UA10. The twelfth set of merchandise attributes CA12 may be determined based on the intersection of the first set of merchandise attributes CA1 and the eleventh set of user attributes UA11. In other words, ca12=ca1 n UA11.

A fourth merchandise weighting score may be determined based on the product of the number of attributes of the sixth set of merchandise attributes CA6 and the fourth weight value W4. In other words, the fourth commodity weight score is n (CA 6) W4 or |ca6| W4. A fifth merchandise weighting score may be determined based on the product of the number of attributes of the seventh set of merchandise attributes CA7 and the fifth weight value W5. In other words, the fifth commodity weight score is n (CA 7) W5 or |ca7| W5. A sixth merchandise weighting score may be determined based on the product of the number of attributes of the eighth group of merchandise attributes CA8 and the sixth weight value W6. In other words, the sixth commodity weight score is n (CA 8) W6 or |ca8| W6. A seventh commodity weighting score may be determined based on the product of the number of attributes of the ninth set of commodity attributes CA9 and the seventh weight value W7. In other words, the seventh commodity weight score is n (CA 9) W7 or |ca9| W7. An eighth commodity weight score may be determined based on the product of the number of attributes of the tenth set of commodity attributes CA10 and the eighth weight value W8. In other words, the eighth commodity weight score is n (CA 10) W8 or |ca10| W8. The ninth commodity weight score may be determined based on the product of the number of attributes of the eleventh commodity attribute CA11 and the ninth weight value W9. In other words, the ninth commodity weight score is n (CA 11) W9 or |ca11| W9. The tenth commodity weight score may be determined based on the product of the number of attributes of the twelfth set of commodity attributes CA12 and the tenth weight value W10. In other words, the tenth commodity weight score is n (CA 12) W10 or |ca12| W10.

The degree of match of the user with the item may be determined based on the aforementioned fourth item weighted score to tenth item weighted score. A matching score for the user attribute score of the user to the commodity may be determined based on the aforementioned fourth commodity weighted score to the tenth commodity weighted score. The matching score of the user attribute score and the commodity may be the sum of the fourth commodity weighted score to the tenth commodity weighted score. The matching score of the user attribute score of this user to the merchandise may be:

n(CA6)*W4+n(CA7)*W5+n(CA8)*W6+n(CA9)*W7+n(CA10)*W8+n(CA11)*W9+n(CA12)*W10＝|CA6|*W4+|CA7|*W5+|CA8|*W6+|CA9|*W7+|CA10|*W8+|CA11|*W9+|CA12|*W10。

fig. 6A and 6B are diagrams illustrating calculation of user attribute scores and matching scores in some embodiments according to the disclosure. The computing methods disclosed in fig. 6A and 6B may be performed by the system 100. The computing method disclosed in fig. 5 may be performed by the processing module 113 of the server 110 or by the processing module 123 of the database 120.

In the method of calculating the user attribute score of fig. 6A and 6B, the user attribute score of the user may further include a first user attribute score, a second user attribute score, and a third user attribute score. A first user attribute score may be determined based on the first set of user attributes UA 1. A second user attribute score may be determined based on the second set of user attributes UA 2. A third user attribute score may be determined based on the third set of user attributes UA 3.

For example, the first, second, and third user attribute scores for the user may be determined based on the number of attributes of the first, second, and third sets of user attributes UA1, UA2, UA3, respectively. A first user attribute score may be determined based on the number of attributes of the first set of user attributes UA 1; a second user attribute score may be determined based on the number of attributes of the second set of user attributes UA 2; and a third user attribute score may be determined based on the number of attributes of the third set of user attributes UA 3.

In some embodiments, the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, and the third set of user attributes ua3= { d, e, f, g }. As in the embodiment shown in fig. 6A, the first user attribute score us1=n (UA 1) = |ua1|=3; second user attribute score us2=n (UA 2) = |ua2|=3; the third user attribute score us3=n (UA 3) = |ua3|=4.

In some embodiments, the first, second, and third user attribute scores for the user may be determined based on the number of attributes of the first set of user attributes UA1, the number of attributes of the second set of user attributes UA2, the number of attributes of the third set of user attributes UA3, and the corresponding weight values, respectively. A first user attribute score may be determined based on a product of the number of attributes of the first set of user attributes UA1 and the first weight value W1; a second user attribute score may be determined based on a product of the number of attributes of the second set of user attributes UA2 and a second weight value W2; and a third user attribute score may be determined based on the product of the number of attributes of the third set of user attributes UA3 and the third weight value W3.

In some embodiments, the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first weight value W1 is 3, the second weight value W2 is 2, and the third weight value W3 is 1. As in the embodiment shown in fig. 6B, the first user attribute score us1=n (UA 1) 3= |ua1|3=9; a second user attribute score us2=n (UA 2) 2= |ua2|x2=6; the third user attribute score us3=n (UA 3) ×1= |ua3|×1=4.

In the method for calculating the matching score of fig. 6A and 6B, the matching score may further include a first matching score, a second matching score, and a third matching score. The first matching score may be determined based on the first set of user attributes UA1 and the first set of merchandise attributes CA1 of the merchandise. A second match score may be determined based on the second set of user attributes UA2 and the first set of merchandise attributes CA 1. A third match score may be determined based on the third set of user attributes UA3 and the first set of merchandise attributes CA 1.

For example, a third set of merchandise attributes CA3 for the merchandise may be determined based on the intersection of the first set of merchandise attributes CA1 and the first set of user attributes UA1. In other words, ca3=ca1 n UA1. A fourth set of merchandise attributes CA4 for the merchandise may be determined based on the intersection of the first set of merchandise attributes CA1 and the second set of user attributes UA2. In other words, ca4=ca1 n UA2. The fifth set of merchandise attributes CA5 for the merchandise may be determined based on the intersection of the first set of merchandise attributes CA1 and the third set of user attributes UA3. In other words, ca5=ca1 n UA3.

In some embodiments, the first, second, and third match scores for the user may be determined based on the number of attributes of the third, fourth, and fifth sets of merchandise attributes CA3, CA4, and CA5, respectively. The first matching score may be determined based on the number of attributes of the third set of merchandise attributes CA 3; a second matching score may be determined based on the number of attributes of the fourth set of merchandise attributes CA 4; and a third matching score may be determined based on the number of attributes of the fifth set of merchandise attributes CA 5.

In some embodiments, the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first set of merchandise attributes CA 1= { a, c, d, e, f }. Based on the intersection of the first set of merchandise attributes CA1 and the first set of user attributes UA1, the third set of merchandise attributes ca3=ca1 n_ua1= { a, c }. Based on the intersection of the first set of merchandise attributes CA1 and the second set of user attributes UA2, the fourth set of merchandise attributes ca4=ca1 n_ua2= { c, d, e }. Based on the intersection of the first set of merchandise attributes CA1 and the third set of user attributes UA3, the fifth set of merchandise attributes ca5=ca1 n_ua3= { d, e, f }. As in the embodiment shown in fig. 6A, the first matching score ms1=n (CA 3) = |ca3|=2; second matching score MSs 2=n (CA 4) = |ca4|=3; third matching score MSs 3=n (CA 5) = |ca5|=3.

In some embodiments, the first, second, and third match scores for the user may be determined based on the number of attributes of the third, fourth, and fifth sets of commodity attributes CA3, CA4, CA5, and the corresponding weight values, respectively. The first user attribute score may be determined based on a product of the number of attributes of the third set of merchandise attributes CA3 and the first weight value W1; a second user attribute score may be determined based on the product of the number of attributes of the fourth set of merchandise attributes CA4 and the second weight value W2; and a third user attribute score may be determined based on the product of the number of attributes of the fifth set of merchandise attributes CA5 and the third weight value W3.

In some embodiments, the first set of user attributes ua1= { a, b, c }, the second set of user attributes ua2= { c, d, e }, the third set of user attributes ua3= { d, e, f, g }, the first set of merchandise attributes CA 1= { a, c, d, e, f }, the first weight value W1 is 3, the second weight value W2 is 2, and the third weight value W3 is 1. The third set of commodity attributes ca3=ca1 n ua1= { a, c }. The fourth set of commodity attributes ca4=ca1 n ua2= { c, d, e }. The fifth set of commodity attributes ca5=ca1 n ua3= { d, e, f }. As in the embodiment shown in fig. 6B, the first matching score may be MS1 = n (CA 3) 3= |ca 3|3 = 6; the second matching score may be MS2 = n (CA 4) 2= |ca 4|x2 = 6; the third matching score may be MS3 = n (CA 5) 1= |ca 5|1 = 3.

Whether to add the respective item to the item recommendation list of the respective user may be determined based on events such as whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and whether the third match score is greater than or equal to a third predetermined proportion of the third user attribute score.

For example, the respective item may be added to the item recommendation list of the respective user in response to at least one of (1) whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) whether the third match score is greater than or equal to a third predetermined proportion of the third user attribute score being true. The respective item may be added to the item recommendation list of the respective user in response to at least two of (1) whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) whether the third match score is greater than or equal to a third predetermined proportion of the third user attribute score being true. The respective item may be added to the item recommendation list of the respective user in response to three events being true of (1) whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) whether the third match score is greater than or equal to a third predetermined proportion of the third user attribute score.

Each of the first predetermined ratio, the second predetermined ratio, and the third predetermined ratio may be set to between 60% and 90%, and the range of the recommended commodity is not limited. Because the range of the recommended commodity is not limited, the fatigue of the user caused by browsing similar commodities in a large amount can be effectively reduced, and the probability of purchasing the recommended commodity can be improved. The first, second and third predetermined proportions may be adjusted to different values based on the importance of different sets of user attributes. For example, if the first set of user attributes is important for recommending the merchandise, the first predetermined ratio may be set to be less than the second predetermined ratio and the third predetermined ratio. In some embodiments, the first predetermined ratio, the second predetermined ratio, and the third predetermined ratio may be the same value.

In some embodiments, each of the first predetermined proportion, the second predetermined proportion, and the third predetermined proportion is 80%, and the respective item is added to the item recommendation list of the respective user in response to at least one of (1) whether the first match score is greater than or equal to the first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to the second predetermined proportion of the second user attribute score, and (3) whether the third match score is greater than or equal to the third predetermined proportion of the third user attribute score being true. In the embodiment shown in fig. 6A, MS2 = 3 ≡us2 x 80% = 2.4, so the corresponding commodity will be added to the commodity recommendation list of the corresponding user. In the embodiment shown in fig. 6B, MS2 = 6 ≡us2 x 80% = 4.8, so the corresponding commodity will be added to the commodity recommendation list of the corresponding user.

In some embodiments, the processing module 113 of the server 110 or the processing module 123 of the database 120 may determine the number of item recommendation lists that include an item. When the number of item recommendation lists including a certain item is greater than or equal to the first threshold, the current inventory number of the item may be requested from the server 110 or database 120. In some embodiments, it may be determined that the item recommendation list includes a number of users for a certain item. When the item recommendation list includes that the number of users for a certain item is greater than or equal to the first threshold, the current inventory number for the item may be requested from the server 110 or database 120.

Based on the received inventory number of the commodity, the processing module 113 of the server 110 or the processing module 123 of the database 120 may further determine whether the inventory number of the commodity is less than or equal to a second threshold. If the inventory number of the item is less than or equal to a second threshold, a signal may be transmitted indicating that the inventory of the item is to be increased. When the manager receives a signal indicating to increase the inventory of the commodity, replenishment can be performed first to avoid selling the commodity. In some embodiments, if the restocking process is complicated (e.g., the restocking process is performed by a replacement purchase), a smaller first threshold and a larger second threshold may be set to avoid selling the merchandise.

While the application has been described and illustrated with reference to specific embodiments thereof, the description and illustration is not intended to limit the application. It will be understood by those skilled in the art that various changes may be made and equivalents substituted without departing from the true spirit and scope of the application as defined by the appended claims. The description may not be drawn to scale. Due to manufacturing processes and tolerances, there may be a distinction between artistic reproductions in the present application and artistic reproductions in the actual application. Other embodiments of the application not specifically illustrated may exist. The specification and drawings are to be regarded in an illustrative rather than a restrictive sense. Modifications may be made to adapt a particular situation, material, composition of matter, method or process to the objective, spirit and scope of the present application. All such modifications are intended to be within the scope of the claims appended hereto. While the methods disclosed herein have been described with reference to particular operations being performed in a particular order, it will be understood that these operations may be combined, sub-divided, or reordered to form an equivalent method without departing from the teachings of the present disclosure. Thus, unless specifically indicated otherwise herein, the order and grouping of operations is not a limitation of the present application. Further, the effects detailed in the above-described embodiments and the like are merely examples. Thus, the present application may further have other effects.

Additionally, the logic flows depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In addition, other steps may be provided, or steps may be eliminated, from the described flows, and other components may be added to, or removed from, the described systems. Accordingly, other embodiments are within the scope of the following claims.

DESCRIPTION OF SYMBOLS IN THE DRAWINGS

100: system and method for controlling a system

110: server device

111: input/output module

112: memory module

113: processing module

114: communication module

120: database for storing data

121: input/output module

122: memory module

123: processing module

124: communication module

130: user device

131: input/output module

132: memory module

133: processing module

134: communication module

200: program

201: operation of

202: operation of

203: operation of

204: operation of

205: operation of

206: operation of

207: operation of

208: operation of

209: operation of

CA1: first set of merchandise attributes

MS1: first matching score

MS2: second matching score

MS3: third matching score

UA1: a first set of user attributes

UA2: second set of user attributes

UA3: third set of user attributes

UA4: fourth set of user attributes

UA5: a fifth set of user attributes

UA6: a sixth set of user attributes

UA7: seventh set of user attributes

UA8: eighth set of user attributes

UA9: ninth set of user attributes

UA10: tenth set of user attributes

UA11: eleventh set of user attributes

US1: first user attribute score

US2: second user attribute score

US3: third user attribute score

Drawing translation

FIG. 2

201. Receiving the current state of the user

202. Determining a first set of user attributes based on a current state of a user

203. Receiving at least one previous order of a user

204. Determining a second set of user attributes based on at least one previous order of the user

205. Receiving at least one browsing record of a user

206. Determining a third set of user attributes based on at least one browsing record of the user

207. Determining a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes

208. Determining a matching score for the good based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and the first set of good attributes for the good

209. Adding the item to the user's recommendation list in response to the matching score of the item being greater than or equal to the predetermined proportion of the user attribute score

Claims

1. An electronic device for processing a recommendation list of items, comprising:

A communication module configured to communicatively couple with a user device of a user and a database, and the communication module is configured to:

receiving a current state of the user;

receiving at least one previous order of the user;

receiving at least one browsing record of the user; and

transmitting a first signal indicating that the item is to be added to the item recommendation list of the user in response to the matching score of the item being greater than or equal to a first predetermined proportion of the attribute score of the user;

a memory module configured to store a plurality of instructions and information; and

a processing module configured to be coupled to the communication module and the memory module and to perform the following operations based on instructions and information stored in the memory module:

determining a first set of user attributes based on the current state of the user;

determining a second set of user attributes based on the at least one previous order of the user;

determining a third set of user attributes based on the at least one browsing record of the user;

determining the user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes; and

The matching score for the commodity is determined based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of commodity attributes for the commodity.

2. The electronic device of claim 1, wherein the processing module is further configured to:

determining a fourth set of user attributes based on the first set of user attributes, the second set of user attributes, and the union of the third set of user attributes;

determining the user attribute score based on the number of attributes of the fourth set of user attributes;

determining a second set of merchandise attributes based on an intersection of the first set of merchandise attributes and the fourth set of user attributes; and

the matching score is determined based on the number of attributes of the second set of merchandise attributes.

3. The electronic device of claim 2, wherein the processing module is further configured to:

determining the user attribute score based on a sum of the number of attributes of the first set of user attributes, the number of attributes of the second set of user attributes, and the number of attributes of the third set of user attributes;

determining a third set of merchandise attributes based on an intersection of the first set of merchandise attributes and the first set of user attributes;

Determining a fourth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the second set of user attributes;

determining a fifth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the third set of user attributes; and

the matching score is determined based on a sum of the number of attributes of the third set of merchandise attributes, the number of attributes of the fourth set of merchandise attributes, and the number of attributes of the fifth set of merchandise attributes.

4. The electronic device of claim 2, wherein the processing module is further configured to:

determining a first user weighted score based on a product of a number of attributes of the first set of user attributes and a first weight value;

determining a second user weighted score based on a product of a number of attributes of the second set of user attributes and a second weight value;

determining a third user weighted score based on a product of the number of attributes of the third set of user attributes and a third weight value;

determining the user attribute score based on a sum of the first user weighted score, the second user weighted score, and the third user weighted score;

determining a fifth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the third set of user attributes;

determining a first commodity weighting score based on a product of the number of attributes of the third set of commodity attributes and the first weight value;

determining a second commodity weighting score based on a product of the number of attributes of the fourth set of commodity attributes and the second weight value;

determining a third merchandise weighting score based on a product of the number of attributes of the fifth set of merchandise attributes and the third weight value; and

the matching score is determined based on a sum of the first commodity weighted score, the second commodity weighted score, and the third commodity weighted score.

5. The electronic device of claim 1, wherein the processing module is further configured to:

determining a fifth set of user attributes based on an intersection of the first set of user attributes, the second set of user attributes, and the third set of user attributes;

determining a sixth set of user attributes by subtracting the fifth set of user attributes from an intersection of the first set of user attributes and the second set of user attributes;

Determining a seventh set of user attributes by subtracting the fifth set of user attributes from the intersection of the first set of user attributes and the third set of user attributes;

determining an eighth set of user attributes by subtracting the fifth set of user attributes from the intersection of the second set of user attributes and the third set of user attributes;

determining a ninth set of user attributes by subtracting the union of the fifth set of user attributes, the sixth set of user attributes, and the seventh set of user attributes from the first set of user attributes;

determining a tenth set of user attributes by subtracting the second set of user attributes from the union of the fifth set of user attributes, the sixth set of user attributes, and the eighth set of user attributes;

determining an eleventh set of user attributes by subtracting the third set of user attributes from the union of the fifth set of user attributes, the seventh set of user attributes, and the eighth set of user attributes;

determining a fourth user weighted score based on a product of the number of attributes of the fifth set of user attributes and a fourth weight value;

determining a fifth user weighted score based on a product of the number of attributes of the sixth set of user attributes and a fifth weight value;

Determining a sixth user weighted score based on a product of the number of attributes of the seventh set of user attributes and a sixth weight value;

determining a seventh user weighted score based on a product of the number of attributes of the eighth set of user attributes and a seventh weight value;

determining an eighth user weighted score based on a product of the number of attributes of the ninth set of user attributes and an eighth weight value;

determining a ninth user weighted score based on a product of a number of attributes of the tenth set of user attributes and a ninth weight value;

determining a tenth user weighted score based on a product of the number of attributes of the eleventh set of user attributes and a tenth weight value;

determining the user attribute score based on a sum of the fourth user weighted score to the tenth user weighted score;

determining a sixth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the fifth set of user attributes;

determining a seventh set of merchandise attributes based on an intersection of the first set of merchandise attributes and the sixth set of user attributes;

determining an eighth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the seventh set of user attributes;

determining a ninth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the eighth set of user attributes;

Determining a tenth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the ninth set of user attributes;

determining an eleventh set of merchandise attributes based on an intersection of the first set of merchandise attributes and the tenth set of user attributes;

determining a twelfth set of merchandise attributes based on an intersection of the first set of merchandise attributes and the eleventh set of user attributes;

determining a fourth merchandise weighting score based on a product of the number of attributes of the sixth set of merchandise attributes and the fourth weight value;

determining a fifth merchandise weighting score based on a product of the number of attributes of the seventh set of merchandise attributes and the fifth weight value;

determining a sixth commodity weighting score based on a product of the number of attributes of the eighth set of commodity attributes and the sixth weight value;

determining a seventh commodity weighting score based on a product of the number of attributes of the ninth set of commodity attributes and the seventh weight value;

determining an eighth commodity weighting score based on a product of the number of attributes of the tenth set of commodity attributes and the eighth weight value;

determining a ninth merchandise weighting score based on a product of the number of attributes of the eleventh set of merchandise attributes and the ninth weight value;

Determining a tenth commodity weighting score based on a product of the number of attributes of the twelfth set of commodity attributes and the tenth weight value; and

the matching score is determined based on a sum of the fourth commodity weighted score to the tenth commodity weighted score.

6. The electronic device of claim 1, wherein the fifth weight value, the sixth weight value, and the seventh weight value are first values, and the eighth weight value, the ninth weight value, and the tenth weight value are second values, the first values being different from the second values.

7. The electronic device of claim 1, wherein the user attribute scores further comprise a first user attribute score, a second user attribute score, and a third user attribute score, the match scores further comprise a first match score, a second match score, and a third match score, and

wherein the processing module is further configured to:

determining the first user attribute score based on the first set of user attributes;

determining the second user attribute score based on the second set of user attributes;

determining the third user attribute score based on the third set of user attributes;

Determining the first matching score based on the first set of user attributes and the first set of merchandise attributes of the merchandise;

determining the second matching score based on the second set of user attributes and the first set of merchandise attributes of the merchandise;

determining the third matching score based on the third set of user attributes and the third set of merchandise attributes of the merchandise;

setting the flag to 0;

setting the flag to 1 in response to the first match score of the good being greater than or equal to a second predetermined proportion of the first user attribute score;

setting the flag to 1 in response to the second match score of the good being greater than or equal to a third predetermined proportion of the second user attribute score;

setting the flag to 1 in response to the third match score of the good being greater than or equal to a fourth predetermined proportion of the third user attribute score;

in response to the flag being 1, the item is added to the item recommendation list for the user.

8. The electronic device of claim 1, wherein the current state of the user includes at least one of:

Current activity, current emotion, or current location.

9. The electronic device of claim 1, wherein the processing module is further configured to:

determining the first set of merchandise attributes for the merchandise based on at least one of:

visual features of the merchandise, tactile features of the merchandise, design features of the merchandise, brand features of the merchandise, text features of the merchandise, or categories of the merchandise;

determining the second set of user attributes based on a first set of merchandise attributes of at least one merchandise in the at least one previous order; and

the third set of user attributes is determined based on a first set of merchandise attributes of at least one merchandise in the at least one browsing record.

10. The electronic device of claim 1, wherein the communication module is further configured to:

transmitting a second signal requesting a stock number of the commodity in response to the number of the commodity recommendation list including the commodity being greater than a first threshold; and

receiving a third signal indicative of the inventory count of the commodity; and

a fourth signal is transmitted to increase the inventory of the commodity in response to the inventory number of the commodity being less than a second threshold.

11. A method for recommending goods, comprising:

receiving the current state of a user;

receiving at least one previous order of the user;

receiving at least one browsing record of the user;

determining a user attribute score based on the first set of user attributes, the second set of user attributes, and the third set of user attributes;

determining a matching score for the commodity based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of commodity attributes for the commodity; and

and adding the commodity to a recommendation list of the user in response to the matching score of the commodity being greater than or equal to a first predetermined proportion of the user attribute score.

12. The method as in claim 11, further comprising:

13. The method as in claim 11, further comprising:

14. The method as in claim 11, further comprising:

15. The method as in claim 11, further comprising:

16. The method of claim 15, wherein the fifth, sixth, and seventh weight values are first values and the eighth, ninth, and tenth weight values are second values, the first and second values being different.

17. The method of claim 11, wherein the user attribute scores further comprise a first user attribute score, a second user attribute score, and a third user attribute score, the match scores further comprise a first match score, a second match score, and a third match score, and

wherein the method further comprises:

adding a commodity to the recommendation list of the user when at least one of the three events that the first matching score of the commodity is greater than or equal to a second predetermined proportion of the first user attribute score, the second matching score of the commodity is greater than or equal to a third predetermined proportion of the second user attribute score, and the third matching score of the commodity is greater than or equal to a fourth predetermined proportion of the third user attribute score is true.

18. The method of claim 11, wherein the current state of the user includes at least one of:

current activity, current emotion, or current location.

19. The method as in claim 11, further comprising:

20. The method as in claim 11, further comprising:

determining an inventory number of the item requested in response to the number of recommended listings including the item being greater than a first threshold; and

in response to the inventory count of the commodity being less than a second threshold, requesting an increase in the commodity inventory.