CN115631014A - Intelligent commodity recommendation method and system - Google Patents
Intelligent commodity recommendation method and system Download PDFInfo
- Publication number
- CN115631014A CN115631014A CN202211364558.9A CN202211364558A CN115631014A CN 115631014 A CN115631014 A CN 115631014A CN 202211364558 A CN202211364558 A CN 202211364558A CN 115631014 A CN115631014 A CN 115631014A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- weight
- intelligent
- dimension information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000000875 corresponding effect Effects 0.000 claims description 32
- 230000006399 behavior Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 238000013136 deep learning model Methods 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 7
- 230000002596 correlated effect Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for intelligently recommending commodities, which comprises the following steps: acquiring personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database; acquiring user figures of corresponding users and purchase information of corresponding commodities based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information; according to the user image, scoring the user weight of each user to obtain a user weight score, scoring the commodity weight of each commodity according to purchase information to obtain a commodity weight score, and correspondingly associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model; and acquiring the current user portrait of the target user, and outputting a commodity recommendation result based on a commodity intelligent recommendation model according to the current user portrait of the target user. The method can solve the problems of single mode and weak pertinence of the commodity recommendation method in the prior art.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a commodity intelligent recommendation method, a commodity intelligent recommendation system, computer equipment and a non-volatile computer readable storage medium.
Background
At present, along with the continuous development of the Internet e-commerce platform, the commodity recommendation function of the e-commerce platform is more and more intelligent and richer, but along with the continuous improvement of the living standard of people, the shopping habit is continuously upgraded, and the commodity recommendation function of the e-commerce platform can not meet the requirements of people more and more. In the prior art, most commodity recommendation methods recommend commodities according to historical shopping preferences of users, and are single in mode and weak in pertinence.
Thus, there is a need for improvements and enhancements in the art.
Disclosure of Invention
In view of the above-mentioned shortcomings in the prior art, an object of the present invention is to provide an intelligent commodity recommendation method, system, computer device and non-volatile computer-readable storage medium, which can be used in financial technology or other related fields, and can solve the problems that most commodity recommendation methods in the prior art recommend commodities according to the historical shopping preferences of users, and have single mode and weak pertinence, based on the historical billing information in the database.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent commodity recommendation method comprises the following steps:
acquiring personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database;
acquiring user figures of users and purchase information of commodities corresponding to the user figures based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information;
according to the user portrait, scoring the user weight of each user to obtain a user weight score, scoring the commodity weight of each commodity according to the purchase information to obtain a commodity weight score, and correspondingly associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model;
and acquiring the current user portrait of the target user, and outputting a commodity recommendation result based on the intelligent commodity recommendation model according to the current user portrait of the target user.
In a further technical solution, the method for intelligently recommending commodities, wherein the scoring the user weight of each user according to the user figure to obtain a user weight score includes:
acquiring a user behavior tag of each user according to the user portrait;
and scoring the user weight of each user according to the user behavior label to obtain a user weight score.
In a further technical solution, the method for intelligently recommending commodities, wherein the scoring the commodity weight of each commodity according to the purchase information to obtain a commodity weight score includes:
acquiring a commodity attribute label of each commodity according to the purchase information;
and according to the commodity attribute labels, carrying out commodity weight scoring on the commodities to obtain a commodity weight score.
In a further technical solution, the method for intelligently recommending commodities, wherein the associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model includes:
correspondingly associating the user weight scores with the commodity weight scores;
and constructing a deep learning model, and training the deep learning model according to the corresponding correlated samples of the user weight scores and the commodity weight scores to generate an intelligent commodity recommendation model.
In a further technical solution, the method for intelligently recommending a commodity, wherein the obtaining of the current user representation of the target user and the outputting of a commodity recommendation result according to the current user representation of the target user based on the commodity intelligent recommendation model, comprises:
acquiring a current user portrait of the target user;
inputting the current user portrait of the target user into the intelligent commodity recommendation model;
and outputting a commodity recommendation result to the target user.
In a further technical solution, in the method for intelligently recommending commodities, the user portrait of each user and the purchase information of each commodity corresponding to the user portrait are acquired based on the personal dimension information, the same-frequency user dimension information, and the high-frequency user dimension information, and the user portrait includes: the system comprises a user static tag, a user dynamic tag, a user asset tag and a user behavior tag, wherein the purchase information comprises a commodity attribute tag.
In a further technical scheme, the intelligent commodity recommendation method includes that the user behavior tag includes consumption frequency, consumption amount interval and repayment capacity of the user, and the commodity attribute tag includes commodity category, price, brand and purchased frequency.
An intelligent commodity recommendation system, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring personal dimension information of a target user, and same-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database;
the second acquisition module is used for acquiring user figures of users and purchase information of commodities corresponding to the second acquisition module based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information;
the scoring module is used for scoring the user weight of each user according to the user portrait to obtain a user weight score, scoring the commodity weight of each commodity according to the purchase information to obtain a commodity weight score, and correspondingly associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model;
and the recommending module is used for acquiring the current user portrait of the target user and outputting a commodity recommending result based on the commodity intelligent recommending model according to the current user portrait of the target user.
In a further technical solution, the system for intelligently recommending commodities, wherein the scoring the user weight of each user according to the user figure to obtain a user weight score includes:
acquiring a user behavior tag of each user according to the user portrait;
and scoring the user weight of each user according to the user behavior label to obtain a user weight score.
In a further technical solution, the intelligent commodity recommendation system, wherein the scoring the commodity weight of each commodity according to the purchase information to obtain a commodity weight score includes:
acquiring a commodity attribute label of each commodity according to the purchase information;
and according to the commodity attribute labels, carrying out commodity weight scoring on the commodities to obtain a commodity weight score.
In a further technical solution, the intelligent commodity recommendation system, wherein the associating the user weight score with the commodity weight score to obtain an intelligent commodity recommendation model includes:
correspondingly associating the user weight scores with the commodity weight scores;
and constructing a deep learning model, and training the deep learning model according to the corresponding correlated samples of the user weight scores and the commodity weight scores to generate an intelligent commodity recommendation model.
In a further technical solution, the system for intelligently recommending commodities, wherein the obtaining of the current user representation of the target user and the outputting of a commodity recommendation result according to the current user representation of the target user based on the commodity intelligent recommendation model, comprises:
acquiring a current user portrait of the target user;
inputting the current user portrait of the target user into the intelligent commodity recommendation model;
and outputting a commodity recommendation result to the target user.
In a further technical solution, in the system for intelligently recommending commodities, the user portrait of each user and the purchase information of each commodity corresponding to the user portrait are acquired based on the personal dimension information, the same-frequency user dimension information, and the high-frequency user dimension information, and the user portrait includes: the system comprises a user static tag, a user dynamic tag, a user asset tag and a user behavior tag, wherein the purchase information comprises a commodity attribute tag.
In a further technical solution, the intelligent commodity recommendation system includes a user behavior tag including a consumption frequency, a consumption amount interval, and a repayment capability of a user, and the commodity attribute tag includes a commodity category, a commodity price, a commodity brand, and a purchased frequency.
A computer device, wherein the computer device comprises at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the intelligent commodity recommendation method can be implemented according to any one of the above items.
A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method for intelligently recommending articles according to any one of the above methods can be implemented.
Compared with the prior art, the invention provides an intelligent commodity recommendation method and system, wherein the method comprises the following steps: acquiring personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database; acquiring user figures of users and purchase information of commodities corresponding to the user figures based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information; according to the user portrait, carrying out user weight scoring on each user to obtain a user weight score, carrying out commodity weight scoring on each commodity according to the purchase information to obtain a commodity weight score, and carrying out corresponding association on the user weight score and the commodity weight score to obtain a commodity intelligent recommendation model; and acquiring the current user portrait of the target user, and outputting a commodity recommendation result based on the commodity intelligent recommendation model according to the current user portrait of the target user. The method can solve the problems that most commodity recommendation methods in the prior art recommend commodities according to historical shopping preferences of users, and are single in mode and weak in pertinence.
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, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an intelligent commodity recommendation method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of functional modules of an intelligent commodity recommendation system according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a hardware structure of the computer device according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the description of the present invention, the terms "comprising," "including," "having," "containing," and the like, as used herein, are open-ended terms that mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
Various non-limiting embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present invention provides an intelligent commodity recommendation method, including the steps of:
s100, acquiring personal dimension information of a target user, and same-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database;
in specific implementation, in this step, personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user are obtained based on historical bill information in a database, wherein the personal dimension information of the target user includes user figures of the target user at each stage period, the co-frequency user dimension information includes user figures of the co-frequency users at each stage period, and the high-frequency user dimension information includes user figures of the high-frequency users at each stage period; specifically, the same-frequency users in the present invention refer to similar people with the target user, for example, people with the same age, the same job title level, the same assets, and the like as the target user, and the high-frequency users in the present invention refer to advanced people belonging to the target user, for example, people with an age, a job title level, assets, and the like higher than the target user.
S200, acquiring user figures of corresponding users and purchase information of corresponding commodities based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information;
in specific implementation, in this step, the user portrait and the purchase information of each commodity of each stage period of the target user in the home are acquired based on the personal dimension information, the user portrait and the purchase information of each commodity of each stage period of each co-frequency user in the home are acquired based on the co-frequency user dimension information, and the user portrait and the purchase information of each commodity of each stage period of each high-frequency user in the home are acquired based on the high-frequency user dimension information.
S300, according to the user portrait, scoring the user weight of each user to obtain a user weight score, according to the purchase information, scoring the commodity weight of each commodity to obtain a commodity weight score, and correspondingly associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model;
s400, obtaining the current user portrait of the target user, and outputting a commodity recommendation result based on the commodity intelligent recommendation model according to the current user portrait of the target user.
Further, the intelligent commodity recommendation method, wherein the scoring the user weight of each user according to the user portrait to obtain a user weight score, includes:
acquiring a user behavior tag of each user according to the user portrait;
and scoring the user weight of each user according to the user behavior label to obtain a user weight score.
Further, the intelligent commodity recommendation method, wherein the commodity weight scoring is performed on each commodity according to the purchase information to obtain a commodity weight score, includes:
acquiring a commodity attribute label of each commodity according to the purchase information;
and according to the commodity attribute labels, carrying out commodity weight scoring on the commodities to obtain a commodity weight score.
Further, the intelligent commodity recommendation method, wherein the correspondingly associating the user weight scores with the commodity weight scores to obtain an intelligent commodity recommendation model, includes:
correspondingly associating the user weight scores with the commodity weight scores;
and constructing a deep learning model, and training the deep learning model according to the corresponding correlated samples of the user weight scores and the commodity weight scores to generate an intelligent commodity recommendation model.
Further, the method for intelligently recommending commodities, wherein the obtaining of the current user portrait of the target user and the outputting of a commodity recommendation result according to the current user portrait of the target user based on the intelligent commodity recommendation model, comprises:
acquiring a current user portrait of the target user;
inputting the current user portrait of the target user into the intelligent commodity recommendation model;
and outputting a commodity recommendation result to the target user.
Further, in the method for intelligently recommending commodities, the user portrait of each user and the purchase information of each commodity corresponding to the user portrait are acquired based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information, and the user portrait includes: the system comprises a user static tag, a user dynamic tag, a user asset tag and a user behavior tag, wherein the purchase information comprises a commodity attribute tag.
In specific implementation, the user static tag includes: name, sex, native place, height, occupation, etc.; the user dynamic tag includes: age, job title level, assets, etc.; the user asset tag includes: deposit, house property, vehicle property, financing amount, etc.
Further, the intelligent commodity recommendation method includes that the user behavior tag includes consumption frequency, consumption amount interval and repayment capacity of the user, and the commodity attribute tag includes category, price, brand and purchased frequency of the commodity.
According to the method embodiment, the commodity intelligent recommendation method provided by the invention is characterized in that the personal dimension information of a target user, the co-frequency user dimension information and the high-frequency user dimension information corresponding to the target user are obtained based on historical bill information in a database, the user portrait of each stage period of the target user and the purchase information of each commodity are obtained based on the personal dimension information, the user portrait of each stage period of each co-frequency user and the purchase information of each commodity are obtained based on the co-frequency user dimension information, the user portrait of each stage period of each high-frequency user and the purchase information of each commodity are obtained based on the high-frequency user dimension information, the user behavior label of each user is obtained according to the user portrait, the user weight score is performed on each user according to the user behavior label to obtain the user weight score, the commodity attribute label is obtained according to the purchase information, the commodity weight score is performed on each commodity according to the commodity attribute label to obtain the commodity weight score, then the user weight score and the commodity weight score are correspondingly associated with the commodity weight score, the commodity attribute label is obtained according to the user weight score, the user model, the commodity model is obtained, and the user recommendation model is generated, and the target user recommendation model is input to the target user learning target user portrait model. In the highly developed era of online shopping, the invention can provide a more appropriate and more applicable intelligent commodity recommendation method for a target user by means of massive historical bill information in bill flow generated by online shopping and based on multi-dimensional user information, can solve the problems that most commodity recommendation methods in the prior art are commodity recommendation according to historical shopping preferences of users, are single in mode and weak in pertinence, really solves the pain points of the users, promotes better experience service, prolongs the use viscosity of the users, and forms an intelligent commodity recommendation method for thousands of people.
It should be understood that although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-inventive labor, and the operation steps are not necessarily performed in the order of the embodiments or flowcharts. The order of steps recited in the embodiments or flowcharts is but one manner of executing many steps and is not intended to represent the only order of execution. Moreover, at least a portion of the steps in the embodiments or flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately, or synchronously with other steps or at least a portion of the sub-steps or stages of other steps.
Based on the above embodiment, referring to fig. 2, another embodiment of the present invention further provides an intelligent commodity recommendation system, including:
the first obtaining module 11 is configured to obtain, based on historical billing information in a database, personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user;
in the specific implementation, in the module, the personal dimension information of a target user, and the same-frequency user dimension information and high-frequency user dimension information corresponding to the target user are obtained based on historical bill information in a database, wherein the personal dimension information of the target user comprises user figures of the target user in each stage period, the same-frequency user dimension information comprises user figures of the same-frequency users in each stage period, and the high-frequency user dimension information comprises the user figures of the high-frequency users in each stage period; specifically, the same-frequency users in the present invention refer to similar people with the target user, for example, people with the same age, the same job title level, the same assets, and the like as the target user, and the high-frequency users in the present invention refer to advanced people belonging to the target user, for example, people with an age, a job title level, assets, and the like higher than the target user.
A second obtaining module 12, configured to obtain user figures of users and purchase information of commodities corresponding to the user figures based on the personal dimension information, the same-frequency user dimension information, and the high-frequency user dimension information;
in the module, during specific implementation, the user portrait of each stage period of the target user and the purchase information of each commodity in the module are acquired based on the personal dimension information, the user portrait of each stage period of each co-frequency user and the purchase information of each commodity in the module are acquired based on the co-frequency user dimension information, and the user portrait of each stage period of each high-frequency user and the purchase information of each commodity in the module are acquired based on the high-frequency user dimension information.
A scoring module 13, configured to score a user weight of each user according to the user representation to obtain a user weight score, score a commodity weight of each commodity according to the purchase information to obtain a commodity weight score, and associate the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model;
and the recommending module 14 is used for acquiring the current user portrait of the target user and outputting a commodity recommending result based on the commodity intelligent recommending model according to the current user portrait of the target user.
Further, the intelligent commodity recommendation system, wherein the scoring of the user weight of each user according to the user profile to obtain a user weight score includes:
acquiring a user behavior tag of each user according to the user portrait;
and scoring the user weight of each user according to the user behavior label to obtain a user weight score.
Further, the intelligent commodity recommendation system, wherein the commodity weight scoring is performed on each commodity according to the purchase information to obtain a commodity weight score, includes:
acquiring a commodity attribute label of each commodity according to the purchase information;
and according to the commodity attribute labels, carrying out commodity weight scoring on the commodities to obtain a commodity weight score.
Further, the intelligent commodity recommendation system associates the user weight scores with the commodity weight scores to obtain an intelligent commodity recommendation model, and includes:
correspondingly associating the user weight scores with the commodity weight scores;
and constructing a deep learning model, and training the deep learning model according to the corresponding correlated samples of the user weight scores and the commodity weight scores to generate an intelligent commodity recommendation model.
Further, the intelligent commodity recommendation system obtains the current user representation of the target user, and outputs a commodity recommendation result based on the intelligent commodity recommendation model according to the current user representation of the target user, and includes:
acquiring a current user portrait of the target user;
inputting the current user portrait of the target user into the intelligent commodity recommendation model;
and outputting a commodity recommendation result to the target user.
Further, in the system for intelligently recommending commodities, the user portrait of each user and the purchase information of each commodity corresponding to the user portrait are acquired based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information, and the user portrait includes: the system comprises a user static tag, a user dynamic tag, a user asset tag and a user behavior tag, wherein the purchase information comprises a commodity attribute tag.
In specific implementation, the user static tag includes: name, sex, native place, height, occupation, etc.; the user dynamic tag includes: age, job title level, assets, etc.; the user asset tag includes: deposit, house property, vehicle property, financing amount, etc.
Further, the intelligent commodity recommendation system includes that the user behavior tag includes consumption frequency, consumption amount interval and repayment capacity of the user, and the commodity attribute tag includes category, price, brand and purchased frequency of the commodity.
According to the system embodiment, the commodity intelligent recommendation system provided by the invention acquires personal dimension information of a target user, co-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database, acquires user portrait of each stage period of the target user and purchase information of each commodity based on the personal dimension information, acquires user portrait of each stage period of each co-frequency user and purchase information of each commodity based on the co-frequency user dimension information, acquires user portrait of each stage period of each high-frequency user and purchase information of each commodity based on the high-frequency user dimension information, acquires a user behavior tag of each user according to the user portrait, scores user weight of each user according to the user behavior tag to acquire user weight score, acquires commodity attribute tag of each commodity according to the purchase information, scores commodity weight of each commodity according to the commodity attribute tag to acquire commodity weight score, associates the user weight score with the commodity weight score, acquires an intelligent commodity weight score of each commodity according to the commodity attribute tag, acquires a target user model of the user to acquire a target commodity weight score, and generates a target commodity model for learning, and inputs the user behavior model of the target user to the target user. In an era of advanced online shopping, the invention can provide a more appropriate and more applicable intelligent commodity recommendation system for a target user by means of massive historical bill information in bill flow generated by online shopping and based on multi-dimensional user information, can solve the problems that most commodity recommendation methods in the prior art are commodity recommendation according to historical shopping preferences of users, have single mode and are not strong in pertinence, really solves the pain point of the users, promotes better experience service, prolongs the use viscosity of the users, and forms an intelligent commodity recommendation system for thousands of people.
Based on the foregoing embodiment, referring to fig. 3, another embodiment of the present invention further provides a computer device, where the computer device 10 includes:
the memory 120 and the one or more processors 110 are illustrated in fig. 3, where one processor 110 is taken as an example, the processor 110 and the memory 120 may be connected by a communication bus or other means, and fig. 3 is taken as an example of being connected by a communication bus.
The memory 120 is used as a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as computer programs corresponding to the intelligent merchandise recommendation method in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by executing the nonvolatile software programs, instructions and units stored in the memory 120, that is, implements the intelligent commodity recommendation method in the above method embodiments.
The memory 120 may include a storage program area and a storage data area, wherein the storage program area may store an application program required for operating the device, at least one function; the storage data area may store data created from use of the computer device 10, and the like. Further, the memory 120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 120 optionally includes memory located remotely from processor 110, which may be connected to computer device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more units are stored in the memory 120, and when being executed by the one or more processors 110, may implement the intelligent merchandise recommendation method in any one of the method embodiments described above, for example, the method steps S100 to S400 in fig. 1 described above may be implemented.
It will be understood by those skilled in the art that the hardware configuration diagram shown in fig. 3 is only a diagram of a part of the configuration related to the solution of the present invention, and does not constitute a limitation to the computer device to which the solution of the present invention is applied, and a specific computer device may include more components than those shown in the diagram, or combine some components, or have different arrangements of components.
Based on the foregoing embodiments, the present invention further provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method for intelligently recommending commodities in any method embodiment as described above may be implemented, for example, the method steps S100 to S400 in fig. 1 described above may be implemented.
By way of example, non-volatile storage media can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchl ink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The disclosed memory components or memory of the operating environment described herein are intended to comprise one or more of these and/or any other suitable types of memory.
Another embodiment of the present invention provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions, which when executed by a processor, can implement the intelligent merchandise recommendation method in any one of the above method embodiments, for example, can implement the above-described method steps S100 to S400 in fig. 1.
The above-described embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions essentially or contributing to the related art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Conditional language such as "can," "might," or "may" is generally intended to convey that a particular embodiment can include (yet other embodiments do not include) particular features, elements, and/or operations, unless specifically stated otherwise or otherwise understood within the context as used. Thus, such conditional language is also generally intended to imply that features, elements, and/or operations are in any way required for one or more embodiments or that one or more embodiments must include logic for deciding, with or without input or prompting, whether such features, elements, and/or operations are included or are to be performed in any particular embodiment.
What has been described herein in the specification and drawings includes examples of methods, systems, computer devices, and non-transitory computer-readable storage media capable of providing intelligent recommendation of merchandise. It will, of course, not be possible to describe every conceivable combination of components and/or methodologies for purposes of describing the various features of the disclosure, but it can be appreciated that many further combinations and permutations of the disclosed features are possible. It is therefore evident that various modifications may be made thereto without departing from the scope or spirit of the disclosure, and all such modifications are intended to be included within the scope of the following claims. In addition, or in the alternative, other embodiments of the disclosure may be apparent from consideration of the specification and drawings and from practice of the disclosure as presented herein. It is intended that the examples set forth in this specification and the drawings be considered in all respects as illustrative and not restrictive. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (10)
1. An intelligent commodity recommendation method is characterized by comprising the following steps:
acquiring personal dimension information of a target user, and co-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database;
acquiring user figures of users and purchase information of commodities corresponding to the user figures based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information;
according to the user portrait, carrying out user weight scoring on each user to obtain a user weight score, carrying out commodity weight scoring on each commodity according to the purchase information to obtain a commodity weight score, and carrying out corresponding association on the user weight score and the commodity weight score to obtain a commodity intelligent recommendation model;
and acquiring the current user portrait of the target user, and outputting a commodity recommendation result based on the intelligent commodity recommendation model according to the current user portrait of the target user.
2. The intelligent commodity recommendation method according to claim 1, wherein said scoring user weights for each of the users according to the user profile to obtain user weight scores comprises:
acquiring a user behavior tag of each user according to the user portrait;
and scoring the user weight of each user according to the user behavior label to obtain a user weight score.
3. The intelligent commodity recommendation method according to claim 2, wherein said scoring commodity weight of each of the commodities according to the purchase information to obtain a commodity weight score comprises:
acquiring a commodity attribute label of each commodity according to the purchase information;
and according to the commodity attribute labels, carrying out commodity weight scoring on the commodities to obtain a commodity weight score.
4. The intelligent commodity recommendation method according to claim 3, wherein the correspondingly associating the user weight scores with the commodity weight scores to obtain a commodity intelligent recommendation model comprises:
correspondingly associating the user weight scores with the commodity weight scores;
and constructing a deep learning model, and training the deep learning model according to the corresponding correlated samples of the user weight scores and the commodity weight scores to generate an intelligent commodity recommendation model.
5. The intelligent commodity recommendation method according to claim 4, wherein the obtaining of the current user profile of the target user and the outputting of the commodity recommendation result based on the intelligent commodity recommendation model according to the current user profile of the target user comprise:
acquiring a current user portrait of the target user;
inputting the current user portrait of the target user into the intelligent commodity recommendation model;
and outputting a commodity recommendation result to the target user.
6. The intelligent commodity recommendation method according to claim 1, wherein in the obtaining of the user portrait of each user and the purchase information of each commodity corresponding to the user portrait based on the personal dimension information, the same-frequency user dimension information, and the high-frequency user dimension information, the user portrait includes: the system comprises a user static tag, a user dynamic tag, a user asset tag and a user behavior tag, wherein the purchase information comprises a commodity attribute tag.
7. The intelligent commodity recommendation method according to claim 6, wherein the user behavior tags comprise consumption frequency, consumption amount interval and repayment capacity of the user, and the commodity attribute tags comprise category, price, brand and purchased frequency of the commodity.
8. An intelligent commodity recommendation system, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring personal dimension information of a target user, and same-frequency user dimension information and high-frequency user dimension information corresponding to the target user based on historical bill information in a database;
the second acquisition module is used for acquiring user figures of users and purchase information of commodities corresponding to the second acquisition module based on the personal dimension information, the same-frequency user dimension information and the high-frequency user dimension information;
the scoring module is used for scoring the user weight of each user according to the user portrait to obtain a user weight score, scoring the commodity weight of each commodity according to the purchase information to obtain a commodity weight score, and correspondingly associating the user weight score with the commodity weight score to obtain a commodity intelligent recommendation model;
and the recommending module is used for acquiring the current user portrait of the target user and outputting a commodity recommending result based on the commodity intelligent recommending model according to the current user portrait of the target user.
9. A computer device, characterized in that the computer device comprises at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the intelligent commodity recommendation method according to any one of claims 1 to 7 can be realized.
10. A non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by at least one processor, implements the intelligent merchandise recommendation method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211364558.9A CN115631014A (en) | 2022-11-02 | 2022-11-02 | Intelligent commodity recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211364558.9A CN115631014A (en) | 2022-11-02 | 2022-11-02 | Intelligent commodity recommendation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115631014A true CN115631014A (en) | 2023-01-20 |
Family
ID=84907814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211364558.9A Pending CN115631014A (en) | 2022-11-02 | 2022-11-02 | Intelligent commodity recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631014A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116402565A (en) * | 2023-02-01 | 2023-07-07 | 苏州极易科技股份有限公司 | Commodity recommendation method and system based on big data analysis |
| CN116579827A (en) * | 2023-07-11 | 2023-08-11 | 深圳千岸科技股份有限公司 | Commodity recommendation method and system based on user network behavior portrayal |
| CN118313906A (en) * | 2024-06-11 | 2024-07-09 | 杭州字节方舟科技有限公司 | Personalized product recommendation method |
-
2022
- 2022-11-02 CN CN202211364558.9A patent/CN115631014A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116402565A (en) * | 2023-02-01 | 2023-07-07 | 苏州极易科技股份有限公司 | Commodity recommendation method and system based on big data analysis |
| CN116402565B (en) * | 2023-02-01 | 2023-10-27 | 苏州极易科技股份有限公司 | Commodity recommendation method and system based on big data analysis |
| CN116579827A (en) * | 2023-07-11 | 2023-08-11 | 深圳千岸科技股份有限公司 | Commodity recommendation method and system based on user network behavior portrayal |
| CN116579827B (en) * | 2023-07-11 | 2024-01-05 | 深圳千岸科技股份有限公司 | Commodity recommendation method and system based on user network behavior portrayal |
| CN118313906A (en) * | 2024-06-11 | 2024-07-09 | 杭州字节方舟科技有限公司 | Personalized product recommendation method |
| CN118313906B (en) * | 2024-06-11 | 2024-08-20 | 杭州字节方舟科技有限公司 | Personalized product recommendation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784455B (en) | Article recommendation method and recommendation equipment | |
| KR102122373B1 (en) | Method and apparatus for obtaining user portrait | |
| Chen et al. | Recent developments in dynamic pricing research: multiple products, competition, and limited demand information | |
| CN115631014A (en) | Intelligent commodity recommendation method and system | |
| US10769702B2 (en) | Recommendations based upon explicit user similarity | |
| Guo | Inequity aversion and fair selling | |
| WO2019080662A1 (en) | Information recommendation method, device and apparatus | |
| CN107871276A (en) | Inquiry unit, method and the computer-readable recording medium of loan product | |
| CN110008397B (en) | Recommendation model training method and device | |
| Ke et al. | Dual-channel supply chain competition with channel preference and sales effort under uncertain environment | |
| CN112148973B (en) | Data processing method and device for information push | |
| Ramamurthy et al. | Inventory policy with parametric demand: Operational statistics, linear correction, and regression | |
| CN109816134A (en) | Shipping address prediction technique, device and storage medium | |
| CN111861605A (en) | Business object recommendation method | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| Omar et al. | A single-vendor multi-buyer integrated production-inventory system with stock-dependent demand | |
| CN113792134B (en) | User service method and system based on digital twin technology | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN111161009A (en) | Information pushing method and device, computer equipment and storage medium | |
| Polo et al. | Strengthening customer relationships: what factors influence customers to migrate to contracts? | |
| Li et al. | Dynamic pricing and production control in a two‐item make‐to‐stock system with flexible dual sourcing and lost sales | |
| Huang et al. | Service segment competition: size or value, which matters? | |
| Cai et al. | The bright and dark sides of customer switching | |
| CN108510302A (en) | A kind of marketing decision-making method and trading server |
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 |