CN115345718B - Exclusive-based commodity recommendation method and system - Google Patents
Exclusive-based commodity recommendation method and system Download PDFInfo
- Publication number
- CN115345718B CN115345718B CN202211276798.3A CN202211276798A CN115345718B CN 115345718 B CN115345718 B CN 115345718B CN 202211276798 A CN202211276798 A CN 202211276798A CN 115345718 B CN115345718 B CN 115345718B
- Authority
- CN
- China
- Prior art keywords
- commodity
- commodities
- user
- recommendation list
- same
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity recommendation method and system based on exclusivity, wherein the method comprises the following steps: counting the commodity re-purchasing period in the E-commerce platform according to the categories; determining exclusive commodities according to the commodity repurchase period and a preset adjusting coefficient; generating a commodity recommendation list based on a preset relevance recommendation algorithm; filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list; and recommending the commodities in the optimized commodity recommendation list. The commodity recommendation method and the commodity recommendation system provided by the invention can improve the commodity recommendation effectiveness, recommend commodities which are more interesting to the user in a short period, meet the real requirements of the user by realizing personalized recommendation, and improve the experience of the user.
Description
Technical Field
The invention relates to the technical field of recommendation, in particular to a commodity recommendation method and system based on exclusivity.
Background
Currently, in the process of using the relevance-based recommendation algorithm, the exclusivity that the user has purchased the commodity is not considered, that is, the user does not purchase the same type of commodity any more in a short period or a certain period after purchasing the commodity. However, the existing recommendation algorithm still recommends exclusive commodities for users, which not only brings redundant information to users and reduces algorithm effectiveness, but also cannot meet the real requirements of users and reduces the experience of users.
Disclosure of Invention
Therefore, the invention provides a commodity recommendation method and system based on exclusivity, which can improve the effectiveness of commodity recommendation, recommend commodities which are more interesting to a user in a short period, meet the real requirements of the user by realizing personalized recommendation, and improve the experience of the user so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
in a first aspect, an embodiment of the present invention provides an exclusive-based commodity recommendation method, including:
counting the commodity repurchase period in the e-commerce platform according to the categories;
determining exclusive commodities according to the commodity repurchase cycle and a preset adjusting coefficient;
generating a commodity recommendation list based on a preset relevance recommendation algorithm;
filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list;
and recommending the commodities in the optimized commodity recommendation list.
Optionally, the commodity re-purchasing period is an average purchasing interval of the full-electric commerce platform user purchasing the same commodity for multiple times, and statistics is performed based on an interval of the same user purchasing the same commodity twice.
Optionally, the process of counting the commodity repurchase period in the e-commerce platform according to the categories includes:
classifying commodity hierarchy categories based on the category subdivision categories of the commodities of the main-flow E-commerce platform;
screening users who purchase goods of the same level with times more than twice, recording the total number of the users as n, and recording the first purchase time of the ith user as U ifirst The last purchase time is recorded as U ilast And the number of times of user's purchase is recorded as U icount The same-level commodity repurchase cycle is
。
Optionally, the preset adjustment coefficient k is used for optimizing and adjusting the repurchase period of the same-level product type commodities, the preset adjustment coefficient k is set and adjusted based on the consumption periods of different product types of commodities and the purchase demands of users, and the adjusted repurchase period B of the same-level product type commodities Pk = k×B P 。
Optionally, the attributes of the exclusive good include: the method comprises the following steps of resetting a time factor t, the work reason and the preference of a user, a preferential threshold Th and a search keyword;
the time factor T is based on the current time T NOW Ordering time T BUY And the regulated same-level class commodity repurchase period B Pk Calculated to obtain the current time T NOW The time for the user to enter the e-commerce platform to browse the commodity recommendation list is T BUY The time of last purchase of the same-level commodity for the user is the time factor T = T NOW - T BUY - B Pk If the time factor t is greater than 0, the commodity recommendation list keeps the commodity of the category, otherwise, the commodity of the category is filtered, and the commodity of the category is removed from the commodity recommendation list to obtain an initial optimized commodity recommendation list;
eliminating user needs based on user's job reasons and preferencesThe possibility of purchasing the same-level goods with high frequency in a short time is determined according to the re-purchase period B of the goods purchased by each user in the history in the platform PU The optimized recommended commodity list is obtained through calculation and used for updating the initial optimized recommended commodity list to obtain an optimized recommended commodity list;
the preferential threshold Th is based on the regulated same-level commodity repurchase period B Pk Calculating the interval time T between the last time of purchase and the current time and the commodity discount P, and updating the initial optimized commodity recommendation list to obtain an optimized recommended commodity list;
and after the search keyword is reset to the condition that the user purchases exclusive commodities, when related commodities are searched again, the searched commodities are added to the initial optimized commodity recommendation list, the initial optimized commodity recommendation list is reset, and an optimized recommended commodity list is obtained, wherein the related commodities belong to the same hierarchical class of commodities.
Optionally, the repurchase period B of the item goods historically purchased by each user in the platform PU Comprises the following steps:
Optionally, the preference threshold Th is calculated by the following formula:
In a second aspect, an embodiment of the present invention provides an exclusivity-based commodity recommendation system, including:
the commodity repurchase cycle extraction module: the system is used for counting the commodity repurchase period in the E-commerce platform according to the categories;
exclusive commodity setting module: the system is used for determining exclusive commodities according to the commodity repurchase period and a preset adjusting coefficient;
an initial commodity recommendation list generation module: the system is used for generating a commodity recommendation list based on a preset relevance recommendation algorithm;
the commodity recommendation list optimizing module: the system is used for filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list;
a recommendation module: and the commodity recommendation system is used for recommending the commodities in the optimized commodity recommendation list.
In a third aspect, an embodiment of the present invention provides a computer device, including: the computer-readable medium includes at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executable by the at least one processor to cause the at least one processor to perform a method for recommending merchandise based on exclusivity according to the first aspect of the embodiments of the invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute an exclusivity-based commodity recommendation method according to the first aspect of the embodiment of the present invention.
The technical scheme of the invention has the following advantages:
according to the exclusive commodity recommendation method and system, the commodity repurchase period in the E-commerce platform is counted according to the categories; determining exclusive commodities according to the commodity repurchase period and a preset adjusting coefficient; generating a commodity recommendation list based on a preset relevance recommendation algorithm; filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list; and recommending the commodities in the optimized commodity recommendation list. The commodity recommendation method and the commodity recommendation system provided by the invention can improve the commodity recommendation effectiveness, recommend commodities which are more interesting to the user in a short period, meet the real requirements of the user by realizing personalized recommendation, and improve the experience of the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of an exclusivity-based merchandise recommendation method provided in an embodiment of the present invention;
FIG. 2 is a flowchart of a specific example of an exclusivity-based merchandise recommendation method provided in an embodiment of the present invention;
FIG. 3 is a block diagram of an exclusivity-based merchandise recommendation system provided in an embodiment of the present invention;
fig. 4 is a block diagram showing a specific example of a computer device provided in the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments, and are not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Furthermore, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment of the invention provides an exclusive commodity recommendation method, which comprises the following steps of:
step S1: and counting the commodity re-purchasing period in the E-commerce platform according to the categories.
In the embodiment of the invention, the commodity re-purchasing period is an average purchasing interval of a full-electric commerce platform user for purchasing the same commodity for multiple times, and statistics is carried out on the basis of an interval of purchasing the same commodity for the same user twice.
In this embodiment, the process of counting the commodity repurchase period in the e-commerce platform according to the categories includes:
step S11: and classifying commodity level categories based on the category subdivision categories of the commodities of the main-flow E-commerce platform.
In a specific embodiment, the commodity level grades are divided into three levels by integrating the existing main stream commercial platform grade division and generating after manual arrangement. For example, after sorting and analysis, the total number of the commodities including computer numbers, mother and infant toys and the like is 14 primary categories, and the commodities under each primary category are further classified into secondary and tertiary sub-categories. The first class is computer digital, and the following 12 second classes such as computer complete machine, digital camera and mobile phone are listed; the whole computer of the second category also comprises a notebook computer of the third category and the like; snack beverage of the first-class order, which is divided into 17 second-class orders such as food, frozen food, brewed beverage and the like; the second class beverage comprises third class low sugar beverage, milk yogurt, etc. The above description is by way of example only and is not intended as limiting.
Step S12: screening users who purchase goods of the same level with times more than twice, recording the total number of the users as n, and recording the first purchase time of the ith user as U ifirst The last time of purchase is recorded as U ilast And the number of times of user's purchase is recorded as U icount The same-level commodity repurchase cycle is
。
Step S2: and determining exclusive commodities according to the commodity repurchase period and a preset adjusting coefficient.
In this embodiment, the preset adjustment coefficient k is used for optimally adjusting the repurchase period of the same-level product class, the preset adjustment coefficient k is adjusted based on the consumption periods of different product classes and the purchase demands of users, and the adjusted repurchase period B of the same-level product class is obtained Pk = k×B P 。
In a specific embodiment, the preset adjustment coefficient is set according to the consumption periods of different types of commodities and the purchase demands of users, so that the repurchase period of the commodities of the types is judged and adjusted. For example, the notebook computer is a product type commodity which is updated and updated by taking years as a unit, and a user can buy the product type commodity from a plurality of channels, so that the purchase frequency of the product type commodity on an e-commerce platform is too low, the consumption cycle and the purchase channel are comprehensively considered, and the optimized and adjusted product type commodity repurchase cycle is set to be 1 year; snack beverage goods are not classified as exclusive goods due to their high frequency of purchase and low customer price. The above examples are only illustrative and not intended to be limiting.
And step S3: and generating a commodity recommendation list based on a preset relevance recommendation algorithm.
In one embodiment, the preset relevance recommendation algorithm includes: the content-based recommendation algorithm and the collaborative filtering recommendation algorithm are both conventional and mature recommendation algorithms, which are only used as examples and are not limited thereto.
And step S4: and filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list.
In the present embodiment, the attributes of the exclusive article include: the time factor t, the work reason and the preference of the user, the preferential threshold Th and the reset of the search keyword.
In the present embodiment, the time factor T is based on the current time T NOW Ordering time T BUY And the regulated same-level class commodity repurchase period B Pk Calculated to obtain the current time T NOW The time for the user to enter the e-commerce platform to browse the commodity recommendation list is T BUY Last purchase of same level for userTime of class goods, time factor T = T NOW - T BUY - B Pk And if the time factor t is greater than 0, the commodity recommendation list keeps the class of commodities, otherwise, the class of commodities are filtered, and the class of commodities are removed from the commodity recommendation list to obtain an initial optimized commodity recommendation list.
In the present embodiment, the possibility that the user needs to purchase the same-level item-class commodities with high frequency in a short time is excluded based on the work reason and preference of the user, and the repurchase period B of the item-class commodities historically purchased by each user in the platform is determined according to each user PU And calculating to update the initial optimized commodity recommendation list to obtain an optimized recommended commodity list. The repurchase period B of the item commodities historically purchased by each user in the platform PU The calculation is as follows:
when B is present PU When the value is not zero and is smaller than the preset proportion of the regulated repeated purchase cycle of the commodities of the same level, the commodities of the same level are not filtered, and the commodities of the same level are reserved in the initial optimized commodity recommendation list. In one embodiment, B PU Not equal to 0 and B PU < 0.5B Pk (the preset ratio is adaptively set based on the application scenario).
In this embodiment, the preferential threshold Th is based on the adjusted same-level commodity repurchase cycle B Pk And calculating the interval time T between the last time of purchase and the current time and the commodity discount P, and updating the initial optimized commodity recommendation list to obtain an optimized recommended commodity list. The preference threshold Th is calculated by the following formula:
and when the preferential threshold Th is larger than a preset threshold, the initial optimized commodity recommendation list keeps the commodities, otherwise, the commodities of the category are filtered, and the commodities of the category are removed from the initial optimized commodity recommendation list. In a specific embodiment, the preset threshold is 1 (it should be noted that the preset threshold is adaptively set based on an application scenario).
In this embodiment, after the search keyword is reset to that the user purchases an exclusive commodity, when a related commodity is searched again, the searched commodity is added to the initial optimized commodity recommendation list, and the initial optimized commodity recommendation list is reset to obtain an optimized recommended commodity list, where the related commodity refers to a commodity belonging to a same hierarchical category. In one embodiment, when the user needs to search and purchase the same type of goods for multiple times in the exclusive period, the purchase period of the goods by the crowd is far shorter than the purchase period of the goods repurchase, and special treatment is needed for the special user. For example, a user has purchased a notebook computer within 1 month, and when he searches the notebook computer again, the user still focuses on the market situation of the related product, and at this time, after the recommendation list is optimized according to the logic of the exclusive commodity, when the user newly generates the search behavior of the exclusive commodity category, the commodity recommendation list is optimized based on the commodity attribute reset by the search keyword, and the commodity which should not appear in the recommendation list according to the conventional recommendation algorithm is added in the recommendation list again.
Step S5: and recommending the commodities in the optimized commodity recommendation list.
In a specific embodiment, the process of performing the exclusive merchandise recommendation method using the above steps is as follows: suppose U A And U B Determining the product type commodity repurchase period as B for the E-commerce platform user according to the E-commerce platform commodity repurchase period and the preset adjustment coefficient Pk = 365 days, commodity A is exclusive commodity, discount P A = 0.5。
A recommendation algorithm based on relevance is used to generate a recommendation list for the goods as shown in table 1 below.
TABLE 1 Commodity recommendation List
For user U A Which never purchased category a on the platform, related item 1 and item 2 would appear in the item recommendation list.
When the user U A After browsing the goods, at time T BUY When shopping occurred and item class a item 1 was purchased, user U did not perform exclusive optimization A While browsing continues, the item recommendation list it sees is unchanged, and items 1 and 2 still exist.
According to the method provided by the embodiment of the invention, after the basic recommendation algorithm commodity list is obtained, the commodity recommendation list is filtered based on the attribute of the exclusive commodity to obtain the optimized commodity recommendation list, and the detailed flow is shown in fig. 2.
Firstly, calculating whether each commodity needs to be filtered, and the specific process is as follows:
when the commodities in the list are not matched with the exclusive commodities, the recommended commodities are kept in the recommended list;
when the commodities in the list are consistent with the exclusive commodity category, the calculation of the relative attribute of the exclusive commodity is carried out: time factor T = T NOW - T BUY - B Pk And a preference threshold
And when the time factor is greater than 0 or the preferential threshold value is greater than 1, the commodity is reserved in the recommendation list, otherwise, the commodity is removed from the recommendation list. Meanwhile, the recommendation list is also updated and optimized in consideration of the work reason and preference of the user of the exclusive goods and the attribute of the reset of the search keyword.
In one embodiment, user U A At time T BUY When item class A commodity 1 is purchased, user U A While browsing the goods, the user U A The ordering time is 5 days away from the current time, and the same type of commodities are not purchased in the user history record, the commodity recommendation method based on exclusivity has the following flows:
the commodity 1 is an exclusive commodity, and whether filtering is required to be calculated is as follows:
time factor t = 5-365 = -360 < 0;
offer threshold Th = 0.34 < 1;
considering the working reasons and preferences of the user, due to the user U A The number of purchases of item 1 is 1, so B PU1 = B Pk1 And user U A The related item of the item 1 is not searched again, and in sum, the item 1 is removed from the recommendation list.
In addition to user U B Before the recommendation method provided by the embodiment of the invention is used, the corresponding recommended commodity list is the same as U A And (5) the consistency is achieved. The difference is that the user U is found through calculation B The purchase period of the commodities of the same level class A is less than 0.1 time of the repurchase period of the commodities of the same level class, namely B PU2 < 0.1B Pk1 Then, consider user U B And for the special user of the category A, the working reason and the favorite commodity attribute of the user are met, exclusive commodity analysis is not performed on the commodities related to the category A in the recommendation list, and the commodity 1 is reserved in the recommendation list.
It should be noted that, the above is only used to illustrate the implementation flow of the recommendation method provided by the embodiment of the present invention, and is not limited thereto.
Example 2
An embodiment of the present invention provides an exclusive-based commodity recommendation system, as shown in fig. 3, including:
the commodity repurchase period extraction module is used for counting the repurchase period of the commodities in the E-commerce platform according to the categories; this module executes the method described in step S1 in embodiment 1, and details are not repeated here.
The exclusive commodity setting module is used for determining an exclusive commodity according to the commodity repurchase period and a preset adjusting coefficient; this module executes the method described in step S2 in embodiment 1, and is not described herein again.
The initial commodity recommendation list generating module is used for generating a commodity recommendation list based on a preset relevance recommendation algorithm; this module executes the method described in step S3 in embodiment 1, which is not described herein again.
The commodity recommendation list optimizing module is used for filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list; this module executes the method described in step S4 in embodiment 1, which is not described herein again.
And the recommending module is used for recommending the commodities in the optimized commodity recommending list. This module executes the method described in step S5 in embodiment 1, and is not described herein again.
The exclusive commodity recommendation system provided by the invention can improve the effectiveness of commodity recommendation, recommend commodities which are more interesting to a user in a short period, meet the real requirements of the user by realizing personalized recommendation, and improve the experience of the user.
Example 3
An embodiment of the present invention provides a computer device, as shown in fig. 4, including: at least one processor 401, at least one communication interface 403, memory 404, and at least one communication bus 402. Wherein, the communication bus 402 is used to realize the connection and communication among these components, the communication interface 403 may include a display screen and a keyboard, and the optional communication interface 403 may also include a standard wired interface and a wireless interface. The memory 404 may be a high speed volatile random access memory, a non-volatile memory, or at least one memory device located remotely from the processor 401. Wherein the processor 401 may execute the exclusivity-based goods recommendation method of embodiment 1. A set of program codes is stored in the memory 404, and the processor 401 calls the program codes stored in the memory 404 for executing the exclusivity-based merchandise recommendation method of embodiment 1.
The communication bus 402 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 402 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one line is shown in FIG. 4, but it is not intended that there be only one bus or one type of bus.
The Memory 404 may include a Volatile Memory (Volatile Memory), such as a Random Access Memory (RAM); the Memory may also include a Non-volatile Memory (Non-volatile Memory), such as a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD) or a Solid-state Drive (SSD); the memory 404 may also comprise a combination of memories of the kind described above.
The Processor 401 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of the CPU and the NP.
The processor 401 may further include a hardware chip. The hardware chip may be an Application-Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a Field Programmable Gate Array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 404 is also used to store program instructions. The processor 401 may call a program instruction to implement the exclusivity-based item recommendation method according to embodiment 1 of the present invention.
An embodiment of the present invention further provides a computer-readable storage medium, where computer-executable instructions are stored on the computer-readable storage medium, and the computer-executable instructions may execute the exclusive commodity recommendation method according to embodiment 1. The storage medium may be a magnetic Disk, an optical Disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of the invention may be made without departing from the spirit or scope of the invention.
Claims (6)
1. An exclusivity-based commodity recommendation method, comprising:
classifying commodity hierarchy categories based on the category subdivision categories of the commodities of the main-flow E-commerce platform;
counting a commodity re-purchasing period in the E-commerce platform according to the commodity class, wherein the commodity re-purchasing period is an average purchasing interval of a full E-commerce platform user for purchasing the same commodity class for multiple times, and counting is carried out on the basis of an interval of purchasing the same commodity class by the same user twice;
screening users who purchase goods of the same level with times more than twice, recording the total number of the users as n, and recording the first purchase time of the ith user as U ifirst The last time of purchase is recorded as U ilast And the number of times of purchase of the user is recorded as U icount If the same-level class of commodities is repurchased in the same period, the repurchase period is
；
Determining exclusive commodities according to the commodity repurchase period and a preset adjustment coefficient, wherein the preset adjustment coefficient k is used for optimizing and adjusting the repurchase period of commodities of the same level class, the preset adjustment coefficient k is set and adjusted based on the consumption periods of different classes of commodities and the purchase demands of users, and the adjusted repurchase period B of commodities of the same level class Pk = k×B P ；
Generating a commodity recommendation list based on a preset relevance recommendation algorithm;
filtering the commodity recommendation list based on the attributes of the exclusive commodity to obtain an optimized commodity recommendation list, wherein the attributes of the exclusive commodity comprise: resetting time factors, work reasons and preferences of users, preferential thresholds and search keywords;
the time factor T is based on the current time T NOW Ordering time T BUY And the regulated same-level commodity repurchase period B Pk Calculated to obtain the current time T NOW The time for the user to enter the e-commerce platform to browse the commodity recommendation list is T BUY The time of last purchase of the same-level commodity for the user is the time factor T = T NOW - T BUY - B Pk If the time factor t is greater than 0, the commodity recommendation list keeps the commodity of the category, otherwise, the commodity of the category is filtered, and the commodity of the category is removed from the commodity recommendation list to obtain an initial optimized commodity recommendation list;
based on the working reason and preference of the user, the possibility that the user needs to purchase the commodities of the same grade at high frequency in a short time is eliminated, and the repurchase period B of the commodities of the same grade purchased by each user in the history in the platform is determined PU The optimized recommended commodity list is obtained through calculation and used for updating the initial optimized recommended commodity list to obtain an optimized recommended commodity list;
the preferential threshold Th is based on the regulated same-level commodity repurchase period B Pk Calculating the interval time T between the last time of purchase and the current time and the commodity discount P, and updating the initial optimized commodity recommendation list to obtain an optimized recommended commodity list;
after the search keyword is reset to the condition that a user purchases exclusive commodities, when related commodities are searched again, the commodities are added to the initial optimized commodity recommendation list, the initial optimized commodity recommendation list is reset, an optimized recommended commodity list is obtained, and the related commodities belong to the same hierarchical class of commodities;
and recommending the commodities in the optimized commodity recommendation list.
2. The exclusivity-based commodity recommendation method as claimed in claim 1, whichCharacterized in that the repurchase period B of the item commodities historically purchased by each user in the platform PU Comprises the following steps:
3. The exclusive-based commodity recommendation method according to claim 1, wherein the preferential threshold Th is calculated by the following formula:
4. An exclusivity-based item recommendation system, comprising:
the commodity repurchase cycle extraction module: the commodity classification method comprises the steps of classifying commodity grades based on grade subdivision categories of commodities of a main-stream electronic commerce platform; counting a commodity re-purchasing period in the E-commerce platform according to the commodity class, wherein the commodity re-purchasing period is an average purchasing interval of a full E-commerce platform user for purchasing the same commodity class for multiple times, and counting is carried out on the basis of an interval of purchasing the same commodity class by the same user twice; screening users who purchase goods of the same level with times more than twice, recording the total number of the users as n, and recording the first purchase time of the ith user as U ifirst The last time of purchase is recorded as U ilast And the number of times of user's purchase is recorded as U icount The same-level commodity repurchase cycle is
；
Exclusive commodity setting module: the system is used for determining exclusive commodities according to the commodity repurchase cycle and a preset adjustment coefficient, the preset adjustment coefficient k is used for optimizing and adjusting the repurchase cycle of commodities of the same level class, the preset adjustment coefficient k is adjusted based on the consumption cycles of different classes of commodities and the purchase demands of users, and the adjusted repurchase cycle B of commodities of the same level class Pk = k×B P ；
An initial commodity recommendation list generation module: the system is used for generating a commodity recommendation list based on a preset relevance recommendation algorithm;
the commodity recommendation list optimizing module: the method is used for filtering the commodity recommendation list based on the attribute of the exclusive commodity to obtain an optimized commodity recommendation list, wherein the attribute of the exclusive commodity comprises: resetting time factors, work reasons and preferences of users, preferential thresholds and search keywords;
the time factor T is based on the current time T NOW Time to order T BUY And the regulated same-level commodity repurchase period B Pk Calculated to obtain the current time T NOW The time for the user to enter the e-commerce platform to browse the commodity recommendation list is T BUY The time of last purchase of the same-level commodity for the user is the time factor T = T NOW - T BUY - B Pk If the time factor t is greater than 0, the commodity recommendation list keeps the commodity of the category, otherwise, the commodity of the category is filtered, and the commodity of the category is removed from the commodity recommendation list to obtain an initial optimized commodity recommendation list;
based on the work reason and preference of the user, the possibility that the user needs to purchase the same-level commodity with high frequency in a short time is eliminated, and the repurchase period B of the commodity purchased by each user in the history in the platform PU The optimized recommended commodity list is obtained through calculation and used for updating the initial optimized recommended commodity list to obtain an optimized recommended commodity list;
the preference threshold Th is based on the adjusted same-level productLike commodity repurchase period B Pk Calculating the interval time T between the last time of purchase and the current time and the commodity discount P, and updating the initial optimized commodity recommendation list to obtain an optimized recommended commodity list;
after the search keyword is reset to the condition that a user purchases exclusive commodities, when related commodities are searched again, the commodities are added to the initial optimized commodity recommendation list, the initial optimized commodity recommendation list is reset, an optimized recommended commodity list is obtained, and the related commodities belong to the same hierarchical class of commodities;
a recommendation module: and recommending the commodities in the optimized commodity recommendation list.
5. A computer device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the exclusivity-based item recommendation method of any one of claims 1-3.
6. A computer-readable storage medium storing computer instructions for causing a computer to perform the exclusivity-based item recommendation method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276798.3A CN115345718B (en) | 2022-10-19 | 2022-10-19 | Exclusive-based commodity recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276798.3A CN115345718B (en) | 2022-10-19 | 2022-10-19 | Exclusive-based commodity recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115345718A CN115345718A (en) | 2022-11-15 |
| CN115345718B true CN115345718B (en) | 2023-01-06 |
Family
ID=83957686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211276798.3A Active CN115345718B (en) | 2022-10-19 | 2022-10-19 | Exclusive-based commodity recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345718B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829965A (en) * | 2024-03-01 | 2024-04-05 | 深圳欧税通技术有限公司 | Product recommendation system and method for cross-border e-commerce platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114282100A (en) * | 2021-12-17 | 2022-04-05 | 南京阿尔文科贸有限责任公司 | E-commerce platform-oriented personalized recommendation method and device based on cloud computing technology |
| WO2022156529A1 (en) * | 2021-01-21 | 2022-07-28 | 北京电解智科技有限公司 | Commodity recommendation method and apparatus for enterprise user |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350832A1 (en) * | 2015-05-29 | 2016-12-01 | Ahold Licensing Sàrl | Method and system for automatically generating recommendations for a client shopping list |
| CN107437203A (en) * | 2017-08-07 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Information-pushing method, device, electronic installation and computer-readable medium |
| CN111738787A (en) * | 2019-06-13 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| JP2021099718A (en) * | 2019-12-23 | 2021-07-01 | 富士フイルムビジネスイノベーション株式会社 | Information processing device and program |
| CN111325609A (en) * | 2020-02-28 | 2020-06-23 | 京东数字科技控股有限公司 | Commodity recommendation list determining method and device, electronic equipment and storage medium |
| CN111369324B (en) * | 2020-03-12 | 2024-01-23 | 苏州大学 | Target information determining method, device, equipment and readable storage medium |
| CN113379511A (en) * | 2021-07-02 | 2021-09-10 | 北京沃东天骏信息技术有限公司 | Method and apparatus for outputting information |
-
2022
- 2022-10-19 CN CN202211276798.3A patent/CN115345718B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022156529A1 (en) * | 2021-01-21 | 2022-07-28 | 北京电解智科技有限公司 | Commodity recommendation method and apparatus for enterprise user |
| CN114282100A (en) * | 2021-12-17 | 2022-04-05 | 南京阿尔文科贸有限责任公司 | E-commerce platform-oriented personalized recommendation method and device based on cloud computing technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115345718A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087177B (en) | Method, device and computer-readable storage medium for recommending commodities to target user | |
| KR101735602B1 (en) | Personalized recommendation method, system and computer-readable record medium | |
| US9959563B1 (en) | Recommendation generation for infrequently accessed items | |
| US10176508B2 (en) | System, method, and non-transitory computer-readable storage media for evaluating search results for online grocery personalization | |
| TWI512653B (en) | Information providing method and apparatus, method and apparatus for determining the degree of comprehensive relevance | |
| US10430854B2 (en) | System, method, and non-transitory computer-readable storage media for evaluating search results for personalized product substitutions | |
| WO2016150354A1 (en) | Method and system for classifying users of e-commerce platform | |
| JP2020503596A (en) | High-precision search method on website | |
| US11748799B2 (en) | Method, medium, and system for information recommendation | |
| JP2014508333A (en) | Method and system for displaying cross-website information | |
| CN111738805B (en) | Behavior log-based search recommendation model generation method, device and storage medium | |
| CN115345718B (en) | Exclusive-based commodity recommendation method and system | |
| CN110930214A (en) | Commodity sorting method for full-subtractive activities | |
| CN111899047A (en) | Resource recommendation method and device, computer equipment and computer-readable storage medium | |
| CN108595668A (en) | A kind of auto ordering method of commodity, device and computer readable storage medium | |
| US20220309562A1 (en) | Intelligent listing creation for a for sale object | |
| CN113744016A (en) | Object recommendation method and device, equipment and storage medium | |
| CN106776697A (en) | Content recommendation method and device | |
| US20170193587A1 (en) | System, method, and non-transitory computer-readable storage media for evaluating search results for matching ingredients to products | |
| CN106156351A (en) | Multimedia resource recommendation information generates method and device | |
| CN115659055A (en) | Commodity recommendation method, system, equipment and storage medium based on event sequence | |
| JP7140588B2 (en) | Decision device, decision method and decision program | |
| CN106204163B (en) | Method and device for determining user attribute characteristics | |
| CN112711706A (en) | Information interaction method and device, readable storage medium and electronic equipment | |
| CN110020135B (en) | Demand determination method, resource recommendation method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |