CN113409106B - Commodity recommendation method, device, equipment and storage medium based on user value - Google Patents
Commodity recommendation method, device, equipment and storage medium based on user value Download PDFInfo
- Publication number
- CN113409106B CN113409106B CN202110628729.3A CN202110628729A CN113409106B CN 113409106 B CN113409106 B CN 113409106B CN 202110628729 A CN202110628729 A CN 202110628729A CN 113409106 B CN113409106 B CN 113409106B
- Authority
- CN
- China
- Prior art keywords
- user
- current user
- value
- data
- consumption
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007619 statistical method Methods 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims description 36
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a commodity recommendation method, device, equipment and storage medium based on user value, wherein the method comprises the following steps: acquiring the consumption attribute of the current user; acquiring consumption data of the current user, and acquiring consumption data of other users with the same consumption attribute as the current user; carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user; and recommending target commodities to the current user according to the user value type. According to the commodity recommendation method, device, equipment and storage medium based on the user value, the consumption data of other users with the same consumption attribute are obtained based on the consumption attribute of the user, the user value type is determined, the commodity recommendation accuracy can be improved under the condition that the consumption data of the user are less, and further user experience is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a commodity recommendation method, apparatus, device and storage medium based on user value.
Background
The prior art typically categorizes corresponding merchandise recommendations for a user based on the value of the user (e.g., corresponding virtual merchandise recommendations for the game user based on the game user's value categorization). However, when classifying the user value, if the consumption data of the user is small (i.e., if the user is a new user), it is difficult to perform a reasonable user value analysis on the user, and the obtained user value classification result is not accurate enough, resulting in low accuracy in recommending the commodity and poor user experience.
Disclosure of Invention
The technical problems to be solved by the embodiment of the invention are as follows: the commodity recommending method, device, equipment and storage medium based on the user value are provided, accuracy of commodity recommending is improved, and user experience is further improved.
In order to solve the above technical problems, in a first aspect, an embodiment of the present invention provides a commodity recommendation method based on a user value, where the commodity recommendation method includes:
acquiring the consumption attribute of the current user;
acquiring consumption data of the current user, and acquiring consumption data of other users with the same consumption attribute as the current user;
carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user;
recommending target commodities to the current user according to the user value type;
the statistical analysis is performed on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user, including:
based on an RFM model, performing value analysis on the consumption data of the current user to obtain the data value of each consumption data of the current user;
based on an RFM model, performing value analysis on consumption data of other users to obtain standard data value degree of each consumption data;
comparing the data value degree of each consumption data of the current user with the standard data value degree of each consumption data, and judging the data value degree of the consumption data with the comparison result smaller than the standard data value degree as a non-abnormal data value degree;
and carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
As a preferred solution, the obtaining the consumption attribute of the current user includes:
acquiring a user portrait of a current user;
and determining the consumption attribute of the user according to the user portrait and based on the mapping relation between the preset user portrait and the consumption attribute.
As a preferred solution, if the target commodity is a virtual commodity, the obtaining the consumption attribute of the current user includes:
acquiring the game duration data of the current user and browsing data of various virtual commodities in a mall;
and determining the consumption attribute of the current user according to the game duration data and the browsing data.
As a preferred solution, the performing statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user includes:
based on an RFM model, performing value analysis on the consumption data of the current user and the consumption data of the other users to obtain the data value degree of each consumption data;
and carrying out statistical analysis on the data value degree of each consumption data to obtain the user value type of the current user.
As a preferred solution, the recommending the target commodity to the current user according to the user value type includes:
acquiring corresponding commodities to be recommended according to the user value type and based on a mapping relation between the preset user value type and the recommended commodities;
selecting the first N commodities in all commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and recommending the target commodity to the current user.
In order to solve the above technical problem, in a second aspect, an embodiment of the present invention provides a commodity recommendation device based on a user value, where the commodity recommendation device includes:
the first acquisition module is used for acquiring the consumption attribute of the current user;
the second acquisition module is used for acquiring the consumption data of the current user and acquiring the consumption data of other users with the same consumption attribute as the current user;
the statistical analysis module is used for carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user;
the commodity recommending module is used for recommending target commodities to the current user according to the user value type;
the statistical analysis module specifically comprises:
the second data value degree acquisition unit is used for carrying out value analysis on the consumption data of the current user based on the RFM model to obtain the data value degree of each consumption data of the current user;
the standard data value degree acquisition unit is used for carrying out value analysis on the consumption data of the other users based on the RFM model to obtain the standard data value degree of each consumption data;
the data value comparison unit is used for comparing the data value of each consumption data of the current user with the standard data value of each consumption data and judging the data value of the consumption data with the comparison result smaller than the standard data value as a non-abnormal data value;
and the second user value type acquisition unit is used for carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
As a preferred solution, the commodity recommendation module specifically includes:
the commodity to be recommended acquisition unit is used for acquiring corresponding commodities to be recommended according to the user value type and based on a preset mapping relation between the user value type and the recommended commodities;
the target commodity selecting unit is used for selecting the first N commodities in all the commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and the target commodity recommending unit is used for recommending the target commodity to the current user.
In order to solve the above technical problem, in a third aspect, an embodiment of the present invention provides a commodity recommendation device based on a user value, where the commodity recommendation device includes:
a memory for storing a computer program;
a processor for executing the computer program;
wherein the processor, when executing the computer program, implements the user value based commodity recommendation method according to any one of the first aspects.
In order to solve the above technical problem, according to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, which when executed implements the commodity recommendation method based on user value according to any one of the first aspects.
Compared with the prior art, the commodity recommendation method, device, equipment and storage medium based on the user value provided by the embodiment of the invention have the beneficial effects that: based on the consumption attribute of the user, the consumption data of the user and the consumption data of other users with the same consumption attribute are obtained, and then the consumption data of the user and the consumption data of other users with the same consumption attribute are subjected to statistical analysis, so that the user value type of the user is determined, commodity recommendation is carried out according to the user value type of the user, the user value type classification is carried out on the consumption data of the user needing commodity recommendation and the consumption data of other users with the same consumption attribute, the accuracy of commodity recommendation can be improved under the condition that the consumption data of the user is less, and further user experience is improved.
Drawings
In order to more clearly illustrate the technical features of the embodiments of the present invention, the drawings that are required to be used in the embodiments of the present invention will be briefly described below, and it is apparent that the drawings described below are only some embodiments of the present invention and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a preferred embodiment of a commodity recommendation method based on user value provided by the present invention;
FIG. 2 is a schematic diagram of a preferred embodiment of a commodity recommendation device based on user value according to the present invention;
fig. 3 is a schematic structural view of a preferred embodiment of a commodity recommendation apparatus based on user value according to the present invention.
Detailed Description
In order to make the technical features, objects and effects of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention will be given with reference to the accompanying drawings and examples. The following examples are only for illustrating the present invention, but are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, other embodiments that can be obtained by a person skilled in the art without any inventive effort shall fall within the scope of the present invention.
In the description of the present invention, it should be understood that the numbers themselves, such as "first," "second," etc., herein are used merely to distinguish between the described objects, and do not have a sequential or technical meaning, and are not to be construed as defining or implying importance to the described objects.
Fig. 1 is a schematic flow chart of a preferred embodiment of a commodity recommendation method based on user value according to the present invention.
As shown in fig. 1, the commodity recommendation method includes the following steps:
s10: acquiring the consumption attribute of the current user;
s20: acquiring consumption data of the current user, and acquiring consumption data of other users with the same consumption attribute as the current user;
s30: carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user;
s40: and recommending target commodities to the current user according to the user value type.
Wherein the consumer attributes of the user are indicative of consumer characteristics of the user, and may include consumer level levels, such as a high consumer level, a medium consumer level, and a low consumer level; the consumer attributes of the user may also include consumer preferences, e.g., the user is a game user, and the consumer attributes of the user may be preference-to-skin consumer, preference-enhanced prop consumer, etc.
Specifically, under the condition that the consumption data of the user is less, the invention firstly obtains the consumption attribute of the user needing commodity recommendation, wherein the consumption attribute can be determined by the user portrait of the current user or the browsing data of the current user on various commodities in the mall. After the consumption attribute of the current user is obtained, the consumption data of the user is obtained, and the consumption data of other users with the same consumption attribute as the user is obtained, wherein the number of the other users can be unlimited, the accuracy of the result can be improved when the number is more, and the calculation time can be shortened when the number is less. And then carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users through a pre-established user value analysis model, so as to determine the user value type of the current user. And finally, acquiring a corresponding target commodity according to the user value type of the current user, and recommending the target commodity to the user.
According to the commodity recommendation method based on the user value, based on the consumption attribute of the user, the consumption data of the user and the consumption data of other users with the same consumption attribute are obtained, and then the consumption data of the user and the consumption data of other users with the same consumption attribute are subjected to statistical analysis, so that the user value type of the user is determined, commodity recommendation is carried out according to the user value type of the user, the user value type classification is carried out on the user needing commodity recommendation and the consumption data of other users with the same consumption attribute, and the accuracy of commodity recommendation can be improved under the condition that the consumption data of the user is less, so that user experience is improved.
In a preferred embodiment, the obtaining the consumption attribute of the current user includes:
acquiring a user portrait of a current user;
and determining the consumption attribute of the current user according to the user portrait and based on the mapping relation between the preset user portrait and the consumption attribute.
Specifically, in this embodiment, a user portrait is first obtained, an analysis result is obtained according to analysis dimensions of the user portrait and values of the analysis dimensions, and then consumption attributes of the user are determined based on a preset mapping relationship according to the analysis result.
As one example, a user representation has eight analysis dimensions: p represents basic (Primary): refer to whether the user representation is based on contextual interviews with real users; e stands for irrational (empath): refers to the user portrait including descriptions related to names, photos and commodities, and whether the user portrait has concentricity or not; r represents authenticity (Realistic): refers to whether the user representation looks like a real character; s stands for uniqueness (singullar): whether each user is unique or not, has little similarity to each other; o stands for objective (objects): whether the user representation contains a high-level object associated with the commodity, whether the object is described by containing keywords; n represents the Number: whether the number of user portraits is sufficiently small so that the design team can remember the name of each user portrayal, and one of the primary user portraits; a represents applicability (Applicable): whether the design team can use the user portraits as a utility tool to make design decisions; l represents Long (Long): the permanence of the user tag. After the user portrait is obtained, acquiring the value of each analysis dimension, and then calculating an analysis result according to a preset analysis formula:wherein R is the analysis result, omega i The xi is the value of the ith analysis dimension as the weight of the ith analysis dimension. Finally, determining the consumption attribute of the user based on the mapping relation between the analysis result and the consumption attribute: t=f (R), where T is a consumption attribute, and f is a mapping relationship between an analysis result and a consumption attribute.
The method for acquiring the user portrait of the current user specifically comprises the following steps:
establishing a historical user portrait of the current user according to the historical feature tag of the current user;
establishing a temporary user portrait of the current user according to the inherent characteristic labels in the historical characteristic labels; wherein the inherent characteristic tag comprises at least one of an age tag and a gender tag;
acquiring other characteristic labels except the inherent characteristic label of the current user in preset time;
acquiring the matching degree of other characteristic labels except the inherent characteristic labels of the current user in preset time and other characteristic labels except the inherent characteristic labels in the historical characteristic labels;
if the matching degree is larger than a preset matching degree threshold, taking the historical user portrait as the user portrait of the current user;
if the matching degree is not greater than a preset matching degree threshold, establishing the latest user portrait of the current user according to other characteristic labels of the current user in preset time except the inherent characteristic label and the inherent characteristic label of the current user, and taking the latest user portrait as the user portrait of the current user.
When a user portrait is acquired, the present embodiment creates a user portrait including an inherent tag, a behavior tag, and the like in advance from the feature tag data accumulated previously. The inherent labels comprise inherent attributes of the user such as gender, age and the like of the user, and can be collected to the user in links such as user registration and the like; the behavior labels comprise the behaviors of the user for interactive operations such as attention adding, attention canceling, wish list adding, wish list taking, order forming, order canceling, payment, refund and the like, and are acquired after the user is authorized. When a user is newly online, a temporary user portrait is established for the user, and inherits inherent labels from the historical user portrait to reflect the inherent properties of the user such as gender, age and the like; and the feature tag reflecting the user behavior in the temporary user portrait is obtained by acquiring the behavior in the preset time, and judging the matching degree of the newly acquired feature tag data and the feature tag data accumulated in advance. When the matching degree is larger than a preset matching degree threshold, the latest behavior of the user is higher in consistency with the historical user portrait, so that the historical user portrait can be used as a user portrait; when the matching degree is not greater than the preset matching degree threshold, the latest behavior of the user is deviated from the historical user portrait, the latest user portrait is established again according to the inherent tag and the newly acquired characteristic tag, and the latest user portrait is adopted to replace the historical user portrait and is used as the user portrait.
According to the embodiment, the user portrait of the user can be effectively maintained and updated according to the latest behavior data of the user, particularly, under the condition that the user behavior is suddenly changed, the latest user portrait of the user can be quickly established by utilizing the temporary user portrait and the latest behavior preference of the user, and the latest user portrait can also reflect the latest preference of the user more accurately, so that the consumption attribute of the user is more accurately determined, and the accuracy of commodity recommendation is further improved.
In a preferred embodiment, if the target commodity is a virtual commodity, the obtaining the consumption attribute of the current user includes:
acquiring the game duration data of the current user and browsing data of various virtual commodities in a mall;
and determining the consumption attribute of the current user according to the game duration data and the browsing data.
In this embodiment, the consumption attribute of the user is directly determined by the game duration data and the browsing data of the user on various virtual commodities in the mall, so that the consumption attribute of the user can be quickly determined.
As an example, there is a new piece of fashion (or skin) in the mall, the user has a duration of 54 minutes on line after logging in the game again, in which 54 minutes it takes 22 minutes to browse the on-sale goods in the mall, and the browsing times for fashion a reach 6 times and the browsing time reaches 13 mm. At this time, the user has a purchasing desire for the commodity in the mall, and the purchasing desire for the fashion a is strong, so that the consumption attribute of the user can be obtained as follows: has strong consumption desire, and the consumption preference is fashion A.
In a preferred embodiment, the performing statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user includes:
based on an RFM model, performing value analysis on the consumption data of the current user and the consumption data of the other users to obtain the data value degree of each consumption data;
and carrying out statistical analysis on the data value degree of each consumption data to obtain the user value type of the current user.
It should be noted that the RFM model is an important tool and means for measuring user value and user profits, and is composed of three elements: the last consumption (precision), the Frequency of consumption (Frequency), and the amount of consumption (monetari).
In this embodiment, under the condition that the consumption data of the user is less, the consumption data of the user is obtained, the consumption data of other users belonging to the same consumption attribute as the user is obtained, the two consumption data are comprehensively analyzed to obtain the data value degree of each consumption data, and then the user value type of the user is determined, so that the defect that the consumption data of the user is less can be made up by using the consumption data of the other users with the same consumption attribute.
In a preferred embodiment, the performing statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user includes:
based on an RFM model, performing value analysis on the consumption data of the current user to obtain the data value of each consumption data of the current user;
based on an RFM model, performing value analysis on consumption data of other users to obtain standard data value degree of each consumption data;
comparing the data value degree of each consumption data of the current user with the standard data value degree of each consumption data, and judging the data value degree of the consumption data with the comparison result smaller than the standard data value degree as a non-abnormal data value degree;
and carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
As an example, after value analysis is performed on other users with the same consumption attribute, the standard data value degree of the consumption frequency is 4.5 times/day, and the data value degree of the consumption frequency of the current user is 16 times/day, and at the moment, the two are compared to obtain 16 & gt 4.5, which means that the data value degree of the current user under the consumption frequency is abnormal, and the data value degree needs to be discarded to avoid misjudgment.
In this embodiment, the value analysis is performed on the consumption data of the current user and the consumption data of other users belonging to the same consumption attribute as the current user through the RFM model, so as to obtain the standard data value of each consumption data and the data value of each consumption data of the current user, and then the data value determined as non-abnormal is obtained through comparison, so as to determine the user value type of the user, and the consumption data of the user with the same consumption attribute can be used as a reference, so that misjudgment caused by less consumption data of the user is avoided.
Optionally, when the data value degree is compared, the data value degree within the preset range of the standard data value degree can be used as a non-abnormal data value degree, and if the data value degree is outside the preset range, the data value degree is used as an abnormal data value degree.
As an example, the standard data value of the consumption frequency is 4.5 times/day after value analysis is performed on other users with the same consumption attribute, and the data value of the consumption frequency of the current user is 5 times/day after analysis, and then the two are compared to obtain 5E [4.5-0.6,4.5+0.6 ]]The data value degree of the current user under the consumption frequency is indicated to be abnormal; if analysis obtains the cancellation of the current userThe data value of the fee frequency is 6 times/day, and the fee frequency and the data value are compared to obtainIt indicates that the data value degree of the current user under the consumption frequency is abnormal, and the current user needs to be discarded.
Further, after the abnormal data value is obtained, the abnormal data value can be corrected by the standard data value.
The correction process may be to directly replace the standard data value with the abnormal data value.
In a preferred embodiment, said recommending target commodity to said current user according to said user value type comprises:
acquiring corresponding commodities to be recommended according to the user value type and based on a mapping relation between the preset user value type and the recommended commodities;
selecting the first N commodities in all commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and recommending the target commodity to the current user.
Specifically, in the preset mapping relationship, a specific user value type may have a plurality of corresponding commodities to be recommended, each commodity to be recommended may have a recommendation suitability, and the higher the recommendation suitability, the higher the probability of indicating the preference of the fitting user, and the lower the recommendation suitability, the lower the probability of indicating the preference of the fitting user. At this time, N products with highest recommendation suitability need to be selected from all the products to be recommended as target products to be recommended to the user, where the value of N may be preset, or may be modified by the user.
It should be understood that the implementation of all or part of the above-mentioned commodity recommendation method based on user value according to the present invention may also be implemented by a computer program for instructing relevant hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the commodity recommendation method based on user value. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
Fig. 2 is a schematic structural diagram of a preferred embodiment of a commodity recommendation device based on user value according to the present invention, where the commodity recommendation device can implement all the processes of the commodity recommendation method based on user value according to any of the foregoing embodiments and achieve the corresponding technical effects.
As shown in fig. 2, the commodity recommendation device includes:
a first obtaining module 21, configured to obtain a consumption attribute of a current user;
a second obtaining module 22, configured to obtain consumption data of the current user, and obtain consumption data of other users having the same consumption attribute as the current user;
the statistical analysis module 23 is configured to perform statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain a user value type of the current user;
and the commodity recommending module 24 is used for recommending target commodities to the current user according to the user value type.
Wherein the consumer attributes of the user may include consumer level levels, such as a high consumer level, a medium consumer level, a low consumer level, etc.; consumption preferences such as preference fashion consumption, preference enhanced prop consumption, preference good prop consumption, and the like may also be included.
In a preferred embodiment, the first obtaining module 21 specifically includes:
the user portrait acquisition unit is used for acquiring a user portrait of the current user;
and the first consumption attribute determining unit is used for determining the consumption attribute of the user according to the user portrait and based on the mapping relation between the preset user portrait and the consumption attribute.
In a preferred embodiment, the user portrait acquisition unit specifically includes:
a history user portrait creation subunit, configured to create a history user portrait of the current user according to the history feature tag of the current user;
a temporary user portrait creation subunit, configured to create a temporary user portrait of the current user according to an inherent feature tag in the history feature tag; wherein the inherent characteristic tag comprises at least one of an age tag and a gender tag;
the characteristic tag obtaining subunit is used for obtaining other characteristic tags except the inherent characteristic tag of the current user in preset time;
the characteristic tag matching subunit is used for acquiring the matching degree of other characteristic tags except the inherent characteristic tag in the preset time of the current user and other characteristic tags except the inherent characteristic tag in the historical characteristic tag;
a first user portrait determining subunit, configured to take the historical user portrait as the user portrait of the current user if the matching degree is greater than a preset matching degree threshold;
and the second user portrait determining subunit is used for establishing the latest user portrait of the current user according to the other characteristic labels except the inherent characteristic label of the current user and the inherent characteristic label of the current user in preset time if the matching degree is not more than a preset matching degree threshold value, and taking the latest user portrait as the user portrait of the current user.
In a preferred embodiment, if the target commodity is a virtual commodity, the first obtaining module 21 specifically includes:
the user data acquisition unit is used for acquiring the game duration data of the current user and browsing data of various virtual commodities in the mall;
and the second consumption attribute determining unit is used for determining the consumption attribute of the current user according to the game duration data and the browsing data.
In a preferred embodiment, the statistical analysis module 23 specifically includes:
the first data value degree acquisition unit is used for carrying out value analysis on the consumption data of the current user and the consumption data of the other users based on an RFM model to obtain the data value degree of each consumption data;
the first user value type acquisition unit is used for carrying out statistical analysis on the data value degree of each consumption data to obtain the user value type of the current user.
In a preferred embodiment, the statistical analysis module 23 specifically includes:
the second data value degree acquisition unit is used for carrying out value analysis on the consumption data of the current user based on the RFM model to obtain the data value degree of each consumption data of the current user;
the standard data value degree acquisition unit is used for carrying out value analysis on the consumption data of the other users based on the RFM model to obtain the standard data value degree of each consumption data;
the data value comparison unit is used for comparing the data value of each consumption data of the current user with the standard data value of each consumption data and judging the data value of the consumption data with the comparison result smaller than the standard data value as a non-abnormal data value;
and the second user value type acquisition unit is used for carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
Optionally, when the data value degree is compared, the data value degree within the preset range of the standard data value degree can be used as a non-abnormal data value degree, and if the data value degree is outside the preset range, the data value degree is used as an abnormal data value degree.
Further, after the abnormal data value is obtained, the abnormal data value can be corrected by the standard data value.
In a preferred embodiment, the merchandise recommendation module 24 specifically includes:
the commodity to be recommended acquisition unit is used for acquiring corresponding commodities to be recommended according to the user value type and based on a preset mapping relation between the user value type and the recommended commodities;
the target commodity selecting unit is used for selecting the first N commodities in all the commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and the target commodity recommending unit is used for recommending the target commodity to the current user.
The value of N may be preset and may be modified by the user.
Fig. 3 is a schematic structural diagram of a preferred embodiment of a commodity recommendation device based on user value according to the present invention, where the commodity recommendation device can implement all the processes of the commodity recommendation method based on user value according to any one of the foregoing embodiments and achieve the corresponding technical effects.
As shown in fig. 3, the commodity recommendation apparatus includes:
a memory 31 for storing a computer program;
a processor 32 for executing the computer program;
wherein the processor 32 when executing the computer program implements the commodity recommendation method based on user value according to any one of the embodiments described above.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the article recommendation device.
The processor 32 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 31 may be used to store the computer program and/or module, and the processor 32 may implement various functions of the merchandise recommendation device by executing or executing the computer program and/or module stored in the memory 31 and invoking data stored in the memory 31. The memory 31 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory 31 may include a high-speed random access memory, and may further include a nonvolatile memory such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid-state storage device.
It should be noted that the above-mentioned commodity recommendation device includes, but is not limited to, a processor and a memory, and those skilled in the art will understand that the schematic diagram of fig. 3 is merely an example of the commodity recommendation device, and does not constitute limitation of the commodity recommendation device, and may include more components than those illustrated, or some components may be combined, or different components may be combined.
While the invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A commodity recommendation method based on user value, comprising:
acquiring the consumption attribute of the current user;
acquiring consumption data of the current user, and acquiring consumption data of other users with the same consumption attribute as the current user;
carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user;
recommending target commodities to the current user according to the user value type;
wherein the target commodity is a virtual commodity, and the user is a game user;
the statistical analysis is performed on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user, including:
based on an RFM model, performing value analysis on the consumption data of the current user to obtain the data value of each consumption data of the current user;
based on an RFM model, performing value analysis on consumption data of other users to obtain standard data value degree of each consumption data;
comparing the data value degree of each consumption data of the current user with the standard data value degree of each consumption data, and judging the data value degree of the consumption data with the comparison result smaller than the standard data value degree as a non-abnormal data value degree;
and carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
2. The commodity recommendation method based on user value according to claim 1, wherein said obtaining the consumption attribute of the current user comprises: acquiring a user portrait of a current user;
and determining the consumption attribute of the user according to the user portrait and based on the mapping relation between the preset user portrait and the consumption attribute.
3. The commodity recommendation method based on user value according to claim 2, wherein the obtaining the user portraits of the current user specifically comprises:
establishing a historical user portrait of the current user according to the historical feature tag of the current user;
establishing a temporary user portrait of the current user according to the inherent characteristic labels in the historical characteristic labels; wherein the inherent characteristic tag comprises at least one of an age tag and a gender tag;
acquiring other characteristic labels except the inherent characteristic label of the current user in preset time;
acquiring the matching degree of other characteristic labels except the inherent characteristic labels of the current user in preset time and other characteristic labels except the inherent characteristic labels in the historical characteristic labels;
if the matching degree is larger than a preset matching degree threshold, taking the historical user portrait as the user portrait of the current user;
if the matching degree is not greater than a preset matching degree threshold, establishing the latest user portrait of the current user according to other characteristic labels of the current user in preset time except the inherent characteristic label and the inherent characteristic label of the current user, and taking the latest user portrait as the user portrait of the current user.
4. The commodity recommendation method based on user value according to claim 1, wherein said obtaining the consumption attribute of the current user comprises: acquiring the game duration data of the current user and browsing data of various virtual commodities in a mall;
and determining the consumption attribute of the current user according to the game duration data and the browsing data.
5. The commodity recommendation method based on user value according to claim 1, wherein said performing statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user includes: based on an RFM model, performing value analysis on the consumption data of the current user and the consumption data of the other users to obtain the data value degree of each consumption data;
and carrying out statistical analysis on the data value degree of each consumption data to obtain the user value type of the current user.
6. The commodity recommendation method based on user value according to claim 1, wherein said recommending a target commodity to the current user according to the user value type comprises: acquiring corresponding commodities to be recommended according to the user value type and based on a mapping relation between the preset user value type and the recommended commodities;
selecting the first N commodities in all commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and recommending the target commodity to the current user.
7. A commodity recommendation device based on user value, comprising: the first acquisition module is used for acquiring the consumption attribute of the current user;
the second acquisition module is used for acquiring the consumption data of the current user and acquiring the consumption data of other users with the same consumption attribute as the current user;
the statistical analysis module is used for carrying out statistical analysis on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user;
the commodity recommending module is used for recommending target commodities to the current user according to the user value type;
wherein the target commodity is a virtual commodity, and the user is a game user;
the statistical analysis is performed on the consumption data of the current user and the consumption data of the other users to obtain the user value type of the current user, including:
based on an RFM model, performing value analysis on the consumption data of the current user to obtain the data value of each consumption data of the current user;
based on an RFM model, performing value analysis on consumption data of other users to obtain standard data value degree of each consumption data;
comparing the data value degree of each consumption data of the current user with the standard data value degree of each consumption data, and judging the data value degree of the consumption data with the comparison result smaller than the standard data value degree as a non-abnormal data value degree;
and carrying out statistical analysis on the non-abnormal data value degree of each consumption data to obtain the user value type of the current user.
8. The user value-based commodity recommendation device according to claim 7, wherein the commodity recommendation module specifically comprises: the commodity to be recommended acquisition unit is used for acquiring corresponding commodities to be recommended according to the user value type and based on a preset mapping relation between the user value type and the recommended commodities;
the target commodity selecting unit is used for selecting the first N commodities in all the commodities to be recommended as target commodities; n is an integer and is greater than or equal to 1;
and the target commodity recommending unit is used for recommending the target commodity to the current user.
9. A commodity recommendation device based on user value, comprising: a memory for storing a computer program;
a processor for executing the computer program;
wherein the processor, when executing the computer program, implements the user value based commodity recommendation method according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed, implements the commodity recommendation method based on user value according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110628729.3A CN113409106B (en) | 2021-06-04 | 2021-06-04 | Commodity recommendation method, device, equipment and storage medium based on user value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110628729.3A CN113409106B (en) | 2021-06-04 | 2021-06-04 | Commodity recommendation method, device, equipment and storage medium based on user value |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409106A CN113409106A (en) | 2021-09-17 |
| CN113409106B true CN113409106B (en) | 2023-10-27 |
Family
ID=77676536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110628729.3A Active CN113409106B (en) | 2021-06-04 | 2021-06-04 | Commodity recommendation method, device, equipment and storage medium based on user value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409106B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997957A (en) * | 2022-06-14 | 2022-09-02 | 中国银行股份有限公司 | Consumption recommendation method, device and equipment based on user portrait and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
| CN108090800A (en) * | 2017-11-27 | 2018-05-29 | 珠海金山网络游戏科技有限公司 | A kind of game item method for pushing and device based on player's consumption potentiality |
| CN108765052A (en) * | 2018-04-20 | 2018-11-06 | 网易无尾熊（杭州）科技有限公司 | Electric business recommendation/method for pushing and device, storage medium and computing device |
| US10157411B1 (en) * | 2014-03-13 | 2018-12-18 | Amazon Technologies, Inc. | Recommendation system that relies on RFM segmentation |
| CN109962956A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | For recommending the method and system of communication service to user |
-
2021
- 2021-06-04 CN CN202110628729.3A patent/CN113409106B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
| US10157411B1 (en) * | 2014-03-13 | 2018-12-18 | Amazon Technologies, Inc. | Recommendation system that relies on RFM segmentation |
| CN108090800A (en) * | 2017-11-27 | 2018-05-29 | 珠海金山网络游戏科技有限公司 | A kind of game item method for pushing and device based on player's consumption potentiality |
| CN109962956A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | For recommending the method and system of communication service to user |
| CN108765052A (en) * | 2018-04-20 | 2018-11-06 | 网易无尾熊（杭州）科技有限公司 | Electric business recommendation/method for pushing and device, storage medium and computing device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409106A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107369075B (en) | Commodity display method and device and electronic equipment | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| CN102216925A (en) | Associating an entity with a category | |
| US20110218852A1 (en) | Matching of advertising sources and keyword sets in online commerce platforms | |
| CN111784449A (en) | Data pushing method, data pushing equipment, storage medium and device | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN112329954B (en) | Article recall method, device, terminal equipment and storage medium | |
| CN112559900A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN115271976A (en) | Advisory recommendation method and device and computer readable storage medium | |
| CN115204971B (en) | Product recommendation method, device, electronic equipment and computer readable storage medium | |
| CN113409106B (en) | Commodity recommendation method, device, equipment and storage medium based on user value | |
| CN110209944B (en) | Stock analyst recommendation method and device, computer equipment and storage medium | |
| CN112328881B (en) | Article recommendation method, device, terminal equipment and storage medium | |
| CN108255920A (en) | Display methods, device, equipment and the storage medium of organization names retrieval type | |
| CN112511632A (en) | Object pushing method, device and equipment based on multi-source data and storage medium | |
| CN116503092A (en) | User reservation intention recognition method and device, electronic equipment and storage medium | |
| CN111125185A (en) | Data processing method, device, medium and electronic equipment | |
| CN116451074A (en) | Image generation method and device for target object, computer equipment and storage medium | |
| CN116644102A (en) | Intelligent investment object selection method, system terminal and computer readable storage medium | |
| CN116186119A (en) | User behavior analysis method, device, equipment and storage medium | |
| CN111401395A (en) | Data processing method, terminal equipment and storage medium | |
| CN113536111B (en) | Recommendation method and device for insurance knowledge content and terminal equipment | |
| CN115757973A (en) | Sorting method, device and equipment of recommendation system and readable storage medium | |
| CN111538905B (en) | Object recommendation method and device | |
| CN113407827A (en) | Information recommendation method, device, equipment and medium based on user value classification |
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 |