CN117312878A - Method, system and device for generating mall user mark - Google Patents
Method, system and device for generating mall user mark Download PDFInfo
- Publication number
- CN117312878A CN117312878A CN202311415424.XA CN202311415424A CN117312878A CN 117312878 A CN117312878 A CN 117312878A CN 202311415424 A CN202311415424 A CN 202311415424A CN 117312878 A CN117312878 A CN 117312878A
- Authority
- CN
- China
- Prior art keywords
- commodities
- matching
- commodity
- user mark
- matching degree
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 241000531116 Blitum bonus-henricus Species 0.000 description 1
- 235000008645 Chenopodium bonus henricus Nutrition 0.000 description 1
- 101100056289 Schizosaccharomyces pombe (strain 972 / ATCC 24843) ark1 gene Proteins 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a system and a device for generating a mall user mark, wherein the method comprises the following steps: acquiring a first commodity list purchased by a user; matching a plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities; generating an intermediate user mark through the matching degree of the first commodities; performing matching pushing according to the middle user mark to obtain feedback matching degree; the target user mark is obtained according to the feedback matching degree and the intermediate user mark, the intermediate user mark is obtained according to the obtained matching degree of the first commodity by matching the first commodity with the preset matching database, and the intermediate user mark is optimized by utilizing the feedback matching degree of the user, so that the finally obtained target user mark combines the feedback characteristics of the user, the target user mark is more attached to the user, and the accuracy and the practicability of the generated mark are improved.
Description
Technical Field
The present invention relates to the field of mall user mark generation technologies, and in particular, to a method, a system, a storage medium, and a device for generating a mall user mark.
Background
In the related art, in order to increase the sales/click rate, a mall pushes related commodities matching users to users in a mall home page, a user search page, and the like, but users cannot uniformly push the same commodities for all users due to different favorite preferences, personality characteristics, and the like, and the same user has different acceptability to different types of products, so that the mall can sign multiple marks for each user to push related commodities to users according to the user marks. The user mark is a problem that needs to be solved in a mall, and how to generate the user mark with the increased user click rate.
Disclosure of Invention
The embodiment of the invention provides a method, a system, a storage medium and a device for generating a mall user mark so as to generate a more pertinent user mark.
In order to solve the problems, the technical scheme provided by the invention is as follows:
in a first aspect, an embodiment of the present application provides a method for generating a mall user mark, including the following steps: acquiring a first commodity list purchased by a user; matching a plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities; generating an intermediate user mark through the matching degree of a plurality of first commodities; performing matching pushing according to the middle user mark to obtain feedback matching degree; and obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
In an embodiment, before the step of matching the plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities, the step of building the preset matching database further includes: acquiring a second commodity list in the mall, wherein the second commodity list comprises a plurality of second commodities; dividing the plurality of second commodities into a plurality of key commodities and a plurality of secondary commodities; acquiring the key matching degree corresponding to each key commodity and the secondary matching degree corresponding to each secondary commodity; and establishing the preset matching database according to the key commodity, the key matching degree, the secondary commodity and the secondary matching degree.
In an embodiment, the step of matching the plurality of first commodities in the first commodity list with the preset matching database to obtain matching degrees of the plurality of first commodities includes: and matching the plurality of first commodities with the plurality of second commodities so as to divide the plurality of first commodities into a plurality of key commodities and/or a plurality of secondary commodities, and acquiring a plurality of corresponding key matching degrees and/or a plurality of secondary matching degrees.
In one embodiment, the step of generating the intermediate user mark by matching the plurality of first commodities includes: obtaining the intermediate user mark according to the matching degree of the plurality of first commodities and an intermediate user mark generation formula, wherein the intermediate user mark generation formula is as follows:;
wherein, K1 is the intermediate user mark, Z1 is the sum of the key matching degrees of the first commodity divided into the key commodity, Z2 is the sum of the secondary matching degrees of the first commodity divided into the secondary commodity, and a and b are constants.
In an embodiment, the step of performing matching pushing according to the intermediate user mark to obtain feedback matching degree includes: pushing a reference group commodity and a marking group commodity to a user, wherein the marking group commodity is a commodity marked by the middle user; and obtaining the feedback matching degree according to the click rate of the commodity of the reference group and the click rate of the commodity of the mark group.
In one embodiment, the step of obtaining the target user mark according to the feedback matching degree and the intermediate user mark includes: based on the feedback matching degree and the intermediate user markThe target user mark is obtained based on a target user mark generation formula, and the target user mark generation formula is as follows:;
wherein, K1 is the intermediate user mark, K2 is the target user mark, Z3 is the feedback matching degree, and c is a constant.
In one embodiment, the step of dividing the plurality of second commodities in the second commodity list into a plurality of key commodities and a plurality of secondary commodities includes: dividing a plurality of the second commodities into a plurality of first classifications; dividing the goods in each first category into a plurality of second categories based on the mall user features; and dividing the first N second commodities under each second category into key commodities, and dividing the rest second commodities into secondary commodities.
In a second aspect, an embodiment of the present application provides a system for generating a mall user mark, including: the acquisition module is used for acquiring a first commodity list purchased by a mall user; the matching module is used for matching a plurality of first commodities in the first commodity list with a preset matching database so as to obtain matching degrees of the plurality of first commodities; the pushing module is used for carrying out matching pushing according to the middle user mark so as to obtain feedback matching degree; and the generation module is used for generating the intermediate user mark according to the matching degree of the plurality of first commodities and obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
In a third aspect, embodiments of the present application provide a computer-readable storage medium comprising computer instructions which, when run on a computer, cause the computer to perform the method of any of the above embodiments.
In a fourth aspect, embodiments of the present application provide an electronic device comprising a processor and a storage medium storing instructions that, when executed by the processor, cause the electronic device to perform the method of any one of the embodiments above.
According to the method, the first commodity is matched with the preset matching database, the middle user mark is obtained according to the obtained matching degree of the first commodity, and the middle user mark is adjusted by utilizing the feedback matching degree of the user, so that the finally obtained target user mark is combined with the feedback characteristic of the user, the target user mark is more attached to the user, and the accuracy and the practicability of the generated mark are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description 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 schematic diagram of a control signal generating circuit according to the present invention;
FIG. 2 is a flow chart of a method for generating a mall user mark according to another embodiment of the present application;
fig. 3 is a schematic flow chart of step S102 in another embodiment of the present application;
fig. 4 is a schematic flow chart of step S400 in another embodiment of the present application;
fig. 5 is a schematic flow chart of step S500 in another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Fig. 1 is a flowchart of a method for generating a mall user mark according to an embodiment of the present application.
Referring to fig. 1, the method for generating the mall user mark includes:
s100, acquiring a first commodity list purchased by a user.
In general, a mall provides a user with a functional page such as shopping record/order/browsing record/collection list, and correspondingly, in order to support the implementation of the above functions, the mall stores related information of the user in a storage device and classifies information for each user. Based on this, purchase information of the user at the mall, etc. can be acquired from the storage device. In this embodiment, the first commodity list is a list of purchased commodities of the user in the corresponding mall, and the first commodity list includes a plurality of first commodities, where the first commodities are purchased commodities of the user in the corresponding mall.
It will be appreciated that each store has its unique business categories, service styles, etc., and that the user has different product viscosities for each store. In this embodiment, the list of purchased commodities of the user in the corresponding mall is used as the first commodity list, so that the accuracy of the user mark generated by the user in the corresponding mall can be improved, and the generated user mark is more attached to the corresponding mall.
In some other embodiments, the first commodity list is a list of commodities purchased by the user at each platform, obtained from the data service provider. When the mall needing to generate the mark has no user related data or has less related data, in order to pursue data breadth, a purchased commodity list of the user on a plurality of platforms can be obtained from a data service provider and used as the first commodity list. It will be appreciated that this can enhance the breadth of the user data used to generate the tag, making the tag more generic.
And S200, matching the plurality of first commodities in the first commodity list with a preset matching database to obtain the matching degree of the plurality of first commodities.
In the storage device of the mall, or in the storage device of the system for generating the tag, a preset matching database may be built in, which may contain classification information of all goods in the mall, each goods corresponding to the degree of matching of the classification. And the matching module can match the plurality of first commodities in the first commodity list with a preset matching database, so that the matching degree of the plurality of first commodities under the corresponding classification is obtained. The goods such as the mall can be classified into foods, clothing, footwear, daily necessities, furniture, home appliances, textiles, hardware appliances, kitchen tools, basic living, enjoyment, development, etc. And presetting corresponding matching degrees for the commodities under each category. The matching degree of the commodity under the corresponding classification can be based on the typical degree of the commodity for the corresponding classification, the value range of the matching degree can be 0 to 1, and when the commodity is matched in the forward direction, the higher the matching degree is, the higher the value can be. If the commodity is a baby diaper, the matching degree of the commodity under the classification of infants can be 1.
S300, generating an intermediate user mark through the matching degree of the plurality of first commodities.
The matching degree of each first commodity forms basic matching data of the user under the corresponding classification, and the intermediate user mark of the user corresponding to the classification can be obtained by evaluating the basic matching data. For example, the generation module performs simple sum calculation, integral calculation, weighted calculation and the like on the matching degree of each first commodity. It will be appreciated that the method of processing the data described above may be selected based on requirements.
And S400, carrying out matching pushing according to the middle user mark to obtain feedback matching degree.
Only by the matching degree of the first commodity in the first commodity list of the user, only the preliminary mark of the user under the corresponding classification can be obtained, and whether the mark of the user under the corresponding classification is close or not cannot be determined according to the preliminary mark. Therefore, after the intermediate user mark is obtained, push test can be performed according to the intermediate user mark, feedback matching degree is obtained through a test result, and the intermediate user mark is optimized accordingly, so that the target user mark is finally obtained. And if the commodities under the corresponding classification are pushed according to the middle user mark, acquiring the click rate of the user, and taking the rising or falling of the click rate as an evaluation index of the feedback matching degree.
S500, obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
The generation module can be used for generating a target user mark according to the obtained feedback matching degree as a tuning parameter of the intermediate user mark. It can be understood that the target user mark finally obtained by the method combines the feedback information of the user, so that the target user mark is more attached to the user, the accuracy and the practicability of the generated mark are improved, and the target user mark is obtained by corresponding model operation instead of simply counting by user data in the related art.
Fig. 2 is a schematic flow chart of a method for generating a mall user mark according to another embodiment of the present application, fig. 3 is a schematic flow chart of step S102 according to another embodiment of the present application, fig. 4 is a schematic flow chart of step S400 according to another embodiment of the present application, and fig. 5 is a schematic flow chart of step S500 according to another embodiment of the present application.
Referring to fig. 2, unlike the above embodiment, in the embodiment of the present application, before the step of matching the plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities, the method further includes a step S110 of establishing the preset matching database.
Specifically, the method comprises the following steps:
s100, acquiring a first commodity list purchased by a user.
And acquiring purchase information of the user in the mall from the storage device. In this embodiment, the first commodity list is a list of purchased commodities of the user in the corresponding mall, and the first commodity list includes a plurality of first commodities, where the first commodities are purchased commodities of the user in the corresponding mall. It will be appreciated that each store has its unique business categories, service styles, etc., and that the user has different product viscosities for each store. In this embodiment, the list of purchased commodities of the user in the corresponding mall is used as the first commodity list, so that the accuracy of the user mark generated by the user in the corresponding mall can be improved, and the generated user mark is more attached to the corresponding mall.
S110, establishing the preset matching database, which comprises the following steps:
s101, acquiring a second commodity list in the mall, wherein the second commodity list comprises a plurality of second commodities.
The commodity list sold in the mall is used as a second commodity list, so the second commodity list comprises a plurality of second commodities which are sold in the mall. It will be appreciated that the generated user indicia should fit the corresponding mall, so that the on-sale merchandise in the corresponding mall should be selected.
S102, dividing the plurality of second commodities into a plurality of key commodities and a plurality of secondary commodities. It will be appreciated that the plurality of second articles under different classifications may be characterized differently. Therefore, the second commodity which can better embody the characteristics of the corresponding classification is taken as the key commodity. The selection of the key commodity and the secondary commodity can be selected by establishing a scoring system.
In some embodiments, the step S102 may include the steps of:
s1021, dividing the plurality of second commodities into a plurality of first classifications. The second commodities are divided into a plurality of first classifications, and the plurality of first classifications may include foods M1, clothes M2, shoes and caps M3, daily necessities M4, furniture M5, household appliances M6, textiles M7, hardware appliances M8, kitchen ware M9, basic living class M10, enjoyment class M11 and development class M12. It will be appreciated that the first category may be divided by the products on sale within the mall.
And S1022, dividing the commodities in each first category into a plurality of second categories based on the characteristics of the mall user.
In the above steps, only the first classifications are classified by the commodity category, and the consideration factor is only the characteristic of the commodity, but in order to generate the mark accuracy, in this embodiment, the commodity in each first classification is classified into a plurality of second classifications based on the user characteristic. The user characteristics may include age, gender, work, family persona, etc. Thus, the corresponding second classification may be divided into age1-5, sex1, sex2, and so on. Further, each second classification user may be further subdivided into work, unwork, parents, etc. The final label may be denoted as M1-age 1-unlock (example).
S1023, dividing the first N second commodities under each second category into key commodities, and dividing the rest second commodities into secondary commodities.
And ranking the commodities under the second category, wherein N second commodities ranked at the top are used as key commodities, and the rest second commodities are used as secondary commodities. Ranking may be based on a scoring system, such as a scoring system scoring sales volume, with a top ranking of sales volume. Or a mall manager, which is a common practice for those skilled in the art and will not be described herein. Or the scoring system determines commodity ranking by the verified data, and ranks each commodity according to the matching proportion of the commodity according to the classification in the purchasers of the commodity obtained by telephone return visit, identity information verification, third-party data service providers and the like.
In one embodiment, the scoring system performs comprehensive ranking on the comprehensive sales volume and the matching proportion, such as a scoring formula:;
wherein,for the number of second commodities under the second category, X1 is the sales of a certain second commodity, X2 is the total sales of a plurality of second commodities under the category, < + >>The matching ratio is the matching ratio.
It will be appreciated that ranking the items under each category by combining the features described above can determine that the items under each category that are top ranked are typical items under the corresponding category.
S103, acquiring the key matching degree corresponding to each key commodity and the secondary matching degree corresponding to each secondary commodity.
And carrying out matching degree assignment on the second commodities in sequence according to the ranking order, wherein the value range of the matching degree can be 0 to 1, and the higher the matching degree is, the higher the value can be when the matching degree is matched in the forward direction.
And S104, establishing the preset matching database according to the key commodity, the key matching degree, the secondary commodity and the secondary matching degree.
And establishing corresponding mapping relations among the key commodity, the key matching degree, the secondary commodity, the secondary matching degree and other parameters, wherein the mapping relations are one-to-one mapping relations among a plurality of key commodities and a plurality of key matching degrees, the secondary commodities and the secondary matching degrees are one-to-one mapping relations, and the set of the mapping relations is the preset matching database. The database is stored in advance in a storage module of a mall or a storage module of a generating system in the following embodiment, and can be called when the first commodity is matched.
And S200, matching the plurality of first commodities in the first commodity list with a preset matching database to obtain the matching degree of the plurality of first commodities.
And matching the plurality of first commodities in the first commodity list with the preset matching database through a matching module, so that the matching degree of the plurality of first commodities under the corresponding classification is obtained.
And S201, matching the plurality of first commodities with the plurality of second commodities to divide the plurality of first commodities into a plurality of key commodities and/or a plurality of secondary commodities, and obtaining a plurality of corresponding key matching degrees and/or a plurality of secondary matching degrees.
It can be appreciated that, in the plurality of first commodities, if there is a key commodity and/or a secondary commodity, there will be a corresponding key matching degree or secondary matching degree. If a certain first commodity is the same as the second commodity in the preset database, dividing the first commodity into a key commodity or a secondary commodity according to the type (the key commodity or the secondary commodity) of the second commodity, and giving the corresponding key matching degree or secondary matching degree to the first commodity, so that the key matching degree or secondary matching degree of the first commodity is obtained.
S300, generating an intermediate user mark through the matching degree of the plurality of first commodities.
And carrying out simple sum value calculation, integral calculation, weighting calculation and the like on the matching degree of each first commodity through a generating module. It will be appreciated that the method of processing the data described above may be selected based on requirements.
In an embodiment, the intermediate user mark is obtained according to the matching degree of the plurality of first commodities and an intermediate user mark generation formula, and the intermediate user mark generation formula is as follows:;
wherein, K1 is the intermediate user mark, Z1 is the sum of the key matching degrees of the first commodity divided into the key commodity, Z2 is the sum of the secondary matching degrees of the first commodity divided into the secondary commodity, and a and b are constants.
And S400, carrying out matching pushing according to the middle user mark to obtain feedback matching degree.
Only by the matching degree of the first commodity in the first commodity list of the user, only the preliminary mark of the user under the corresponding classification can be obtained, and whether the mark of the user under the corresponding classification is close or not cannot be determined according to the preliminary mark. Therefore, after the intermediate user mark is obtained, push test can be performed according to the intermediate user mark, feedback matching degree is obtained through a test result, and the intermediate user mark is optimized accordingly, so that the target user mark is finally obtained. And if the commodities under the corresponding classification are pushed according to the middle user mark, acquiring the click rate of the user, and taking the rising or falling of the click rate as an evaluation index of the feedback matching degree.
In one embodiment, S400 includes:
s401, pushing a reference group commodity and a marking group commodity to a user, wherein the marking group commodity is a commodity in the middle user mark.
S402, obtaining the feedback matching degree according to the click rate of the commodity of the reference group and the click rate of the commodity of the mark group.
Specifically, the feedback matching degree is obtained based on a feedback matching degree formula according to the click rate of the commodity of the reference group and the click rate of the commodity of the mark group, and the feedback matching degree formula is as follows:;
wherein Z3 is the feedback matching, D1 is the click rate of the marker group, D2 is the click rate of the reference group, L is a constant, and L is less than 1.
S500, obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
The generation module can be used for generating a target user mark according to the obtained feedback matching degree as a tuning parameter of the intermediate user mark. It can be understood that the target user mark finally obtained by the method combines the feedback information of the user, so that the target user mark is more attached to the user, the accuracy and the practicability of the generated mark are improved, and the target user mark is obtained by corresponding model operation instead of simply counting by user data in the related art.
In one embodiment, S500 includes:
s501, obtaining the target user mark based on a target user mark generation formula according to the feedback matching degree and the intermediate user mark, wherein the target user mark generation formula is as follows:;
wherein, K1 is the intermediate user mark, K2 is the target user mark, Z3 is the feedback matching degree, and c is a constant.
In an embodiment, the first commodity list of the user is { S1, S2, S3, S4}, the second commodity list of the mall is { S1 to Sn }, where a certain second category is labeled M1-age 1-unworks, the corresponding key commodities under the category include S1, S4, and the secondary commodities include S2, S3. The key matching degree corresponding to S1 and S4 is 0.8 and 0.7, and the secondary matching degree corresponding to S2 and S3 is 0.1 and 0.05.
The intermediate user mark generation formula is:;
the value of the intermediate user mark M1-age 1-unworks-K1 corresponding to the second category= (0.8+0.7) +0.5 x (0.1+0.05) =1.575.
Pushing based on the second classification corresponding to the middle user mark M1-age 1-unworks to obtain the click rate D2 of the reference group as 10% and the click rate D1 of the mark group as 80%.
The feedback matching degree formula is:;
the feedback matching degree z3=7.
The target user mark generation formula is as follows:;
the value corresponding to the target user mark M1-age 1-unworks-K1 under the second category=1.575+0.25×7= 5.575.
In some embodiments, in the first merchandise list of the user, the matching degree of the first merchandise classified as the secondary merchandise may be determined according to the matching degree of the first merchandise classified as the key merchandise in the first list.
If the first commodity list of the user is { S1, S2, S3, S4}, the second commodity list of the mall is { S1 to Sn }, where the label corresponding to a certain second category is M1-age 1-unworks, the corresponding key commodities under the category include S1, S4, and the secondary commodities include S2, S3. The key matching degree corresponding to S1 and S4 is 0.8 and 0.7, and the secondary matching degree of the secondary commodities S2 and S3 can be the minimum value of the key matching degree in the key commodities divided by the number of the key commodities, for example, min { S1 and S4 }/2=0.35.
The embodiment of the application also provides an online advertisement basic audience label construction system, which comprises: the acquisition module is used for acquiring the first commodity list purchased by the mall user; the matching module is used for matching a plurality of first commodities in the first commodity list with a preset matching database so as to obtain matching degrees of the plurality of first commodities; the pushing module is used for carrying out matching pushing according to the middle user mark so as to obtain feedback matching degree; and the generation module is used for generating the intermediate user mark according to the matching degree of the plurality of first commodities and obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation. The functional modules in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
Embodiments also provide a computer readable storage medium comprising computer instructions which, when run on a computer, cause the computer to perform the method according to any of the embodiments above.
Embodiments of the present application also provide an electronic device comprising a processor and a storage medium storing instructions that, when executed by the processor, cause the electronic device to perform a method according to any one of the embodiments above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable resource recommendation device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable resource recommendation device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable resource recommendation device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable resource recommendation device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer implemented process such that the instructions which execute on the computer or other programmable device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In summary, although the present invention has been described in terms of the preferred embodiments, the preferred embodiments are not limited to the above embodiments, and various modifications and changes can be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention is defined by the appended claims.
Claims (10)
1. A method for generating a mall user mark, comprising:
acquiring a first commodity list purchased by a user;
matching a plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities;
generating an intermediate user mark through the matching degree of a plurality of first commodities;
performing matching pushing according to the middle user mark to obtain feedback matching degree;
and obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
2. The method of claim 1, further comprising creating a preset matching database before the step of matching the plurality of first commodities in the first commodity list with a preset matching database to obtain matching degrees of the plurality of first commodities, wherein the step of creating the preset matching database comprises:
acquiring a second commodity list in the mall, wherein the second commodity list comprises a plurality of second commodities;
dividing the plurality of second commodities into a plurality of key commodities and a plurality of secondary commodities;
acquiring the key matching degree corresponding to each key commodity and the secondary matching degree corresponding to each secondary commodity;
and establishing the preset matching database according to the key commodity, the key matching degree, the secondary commodity and the secondary matching degree.
3. The method for generating a mall user mark according to claim 2, wherein the step of matching the plurality of first commodities in the first commodity list with the preset matching database to obtain matching degrees of the plurality of first commodities comprises:
and matching the plurality of first commodities with the plurality of second commodities so as to divide the plurality of first commodities into a plurality of key commodities and/or a plurality of secondary commodities, and acquiring a plurality of corresponding key matching degrees and/or a plurality of secondary matching degrees.
4. The method of claim 3, wherein the step of generating the intermediate user mark by matching the plurality of first commodities comprises:
obtaining the intermediate user mark according to the matching degree of the plurality of first commodities and an intermediate user mark generation formula, wherein the intermediate user mark generation formula is as follows:wherein, K1 is the intermediate user mark, Z1 is the sum of the key matching degrees of the first commodity divided into the key commodity, Z2 is the sum of the secondary matching degrees of the first commodity divided into the secondary commodity, and a and b are constants.
5. The method for generating a mall user mark according to claim 3 or 4, wherein the step of performing matching pushing according to the intermediate user mark to obtain feedback matching degree comprises:
pushing a reference group commodity and a marking group commodity to a user, wherein the marking group commodity is a commodity marked by the middle user;
and obtaining the feedback matching degree according to the click rate of the commodity of the reference group and the click rate of the commodity of the mark group.
6. The method of generating a mall user tag of claim 5, wherein the step of obtaining a target user tag based on the feedback matching degree and the intermediate user tag comprises:
and obtaining the target user mark based on a target user mark generation formula according to the feedback matching degree and the intermediate user mark, wherein the target user mark generation formula is as follows:wherein, K1 is the intermediate user mark, K2 is the target user mark, Z3 is the feedback matching degree, and c is a constant.
7. The method of claim 2, wherein the step of dividing the plurality of second merchandise in the second merchandise list into a plurality of key merchandise and a plurality of secondary merchandise comprises:
dividing a plurality of the second commodities into a plurality of first classifications;
dividing the goods in each first category into a plurality of second categories based on the mall user features;
and dividing the first N second commodities under each second category into key commodities, and dividing the rest second commodities into secondary commodities.
8. A system for generating a mall user mark, comprising:
the acquisition module is used for acquiring a first commodity list purchased by a mall user;
the matching module is used for matching a plurality of first commodities in the first commodity list with a preset matching database so as to obtain matching degrees of the plurality of first commodities;
the pushing module is used for carrying out matching pushing according to the middle user mark so as to obtain feedback matching degree;
and the generation module is used for generating the intermediate user mark according to the matching degree of the plurality of first commodities and obtaining a target user mark according to the feedback matching degree and the intermediate user mark.
9. A computer readable storage medium comprising computer instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-7.
10. An electronic device comprising a processor and a storage medium storing instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311415424.XA CN117312878B (en) | 2023-10-30 | 2023-10-30 | Method, system and device for generating mall user mark |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311415424.XA CN117312878B (en) | 2023-10-30 | 2023-10-30 | Method, system and device for generating mall user mark |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312878A true CN117312878A (en) | 2023-12-29 |
| CN117312878B CN117312878B (en) | 2024-05-14 |
Family
ID=89288383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311415424.XA Active CN117312878B (en) | 2023-10-30 | 2023-10-30 | Method, system and device for generating mall user mark |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312878B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609860A (en) * | 2012-01-20 | 2012-07-25 | 彭立发 | Method and system suitable for categorizing and recommending e-commerce commodities and information |
| CN109064285A (en) * | 2018-08-02 | 2018-12-21 | 西北大学 | A kind of acquisition commercial product recommending sequence and Method of Commodity Recommendation |
| CN109299993A (en) * | 2018-07-20 | 2019-02-01 | 平安科技（深圳）有限公司 | Product function recommended method, terminal device and computer readable storage medium |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| US20210406942A1 (en) * | 2020-06-26 | 2021-12-30 | Steven Eric Lilley | System and method for optimizing online privacy recommendations for entity users |
| CN114140193A (en) * | 2021-11-23 | 2022-03-04 | 苏州中仑网络科技有限公司 | Commodity recommendation method and device |
| CN114169965A (en) * | 2021-12-06 | 2022-03-11 | 广州歌神信息科技有限公司 | Commodity similarity matching method and device, equipment, medium and product thereof |
| CN114626909A (en) * | 2022-02-15 | 2022-06-14 | 广州伊智信息科技有限公司 | Commodity recommendation method, system, equipment and medium |
| CN116342226A (en) * | 2023-04-12 | 2023-06-27 | 郝荣恺 | Commodity recommendation method and system based on big data |
| CN116777550A (en) * | 2023-05-26 | 2023-09-19 | 上海固瑞捷工业科技有限公司 | Commodity recommendation method and device based on commodity relevance |
-
2023
- 2023-10-30 CN CN202311415424.XA patent/CN117312878B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609860A (en) * | 2012-01-20 | 2012-07-25 | 彭立发 | Method and system suitable for categorizing and recommending e-commerce commodities and information |
| CN109299993A (en) * | 2018-07-20 | 2019-02-01 | 平安科技（深圳）有限公司 | Product function recommended method, terminal device and computer readable storage medium |
| CN109064285A (en) * | 2018-08-02 | 2018-12-21 | 西北大学 | A kind of acquisition commercial product recommending sequence and Method of Commodity Recommendation |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| US20210406942A1 (en) * | 2020-06-26 | 2021-12-30 | Steven Eric Lilley | System and method for optimizing online privacy recommendations for entity users |
| CN114140193A (en) * | 2021-11-23 | 2022-03-04 | 苏州中仑网络科技有限公司 | Commodity recommendation method and device |
| CN114169965A (en) * | 2021-12-06 | 2022-03-11 | 广州歌神信息科技有限公司 | Commodity similarity matching method and device, equipment, medium and product thereof |
| CN114626909A (en) * | 2022-02-15 | 2022-06-14 | 广州伊智信息科技有限公司 | Commodity recommendation method, system, equipment and medium |
| CN116342226A (en) * | 2023-04-12 | 2023-06-27 | 郝荣恺 | Commodity recommendation method and system based on big data |
| CN116777550A (en) * | 2023-05-26 | 2023-09-19 | 上海固瑞捷工业科技有限公司 | Commodity recommendation method and device based on commodity relevance |
Non-Patent Citations (2)
| Title |
|---|
| FEIRAN WANG 等: "Personalized Commodity Recommendations of Retail Business using User Feature based Collaborative Filtering", 《IEEE COMPUTER SOCIETY》, 31 December 2018 (2018-12-31), pages 273 - 278, XP033531096, DOI: 10.1109/BDCloud.2018.00051 * |
| 穆晓霞 等: "融合LDA主题模型和支持向量机的商品个性化推荐方法", 《郑州大学学报(理学版)》, vol. 54, no. 3, 31 May 2022 (2022-05-31), pages 34 - 39 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312878B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11823218B2 (en) | Customer clustering using integer programming | |
| US8407104B2 (en) | Catalog based price search | |
| US11605111B2 (en) | Heuristic clustering | |
| US11816721B2 (en) | Recommendation apparatus and method | |
| CN103593392A (en) | Method and system for generating recommendations | |
| CN109636494A (en) | Drug recommended method and system | |
| CN104239338A (en) | Information recommendation method and information recommendation device | |
| CN108596705A (en) | A kind of commodity suitable for e-commerce recommend method and system with information classification | |
| CN111429203A (en) | Commodity recommendation method and device based on user behavior data | |
| CN109919737B (en) | Recommendation method and system for producing and selling commodities | |
| CN110727859B (en) | Recommendation information pushing method and device | |
| CN101625698A (en) | Information processing device, information processing method, and program | |
| CN111861605A (en) | Business object recommendation method | |
| CN107093122B (en) | Object classification method and device | |
| Gholamian et al. | Improving electronic customers' profile in recommender systems using data mining techniques | |
| JP2020107269A (en) | Information processing device, information processing method, and information processing program | |
| JP5056803B2 (en) | Information providing server and information providing method | |
| CN117312878B (en) | Method, system and device for generating mall user mark | |
| JP7249375B2 (en) | Information processing device, information processing method, and information processing program | |
| CN110610402A (en) | Commodity pushing method and computer storage medium | |
| Schwartz et al. | Style similarity as feedback for product design | |
| JP2019074816A (en) | Information processing device, information processing method, and information processing program | |
| CN114756758B (en) | Hybrid recommendation method and system | |
| TW201423639A (en) | System and method for providing target information | |
| JP7471602B2 (en) | Information processing device and information processing method |
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 |