CN114943579A - Commodity network sale recommendation method - Google Patents
Commodity network sale recommendation method Download PDFInfo
- Publication number
- CN114943579A CN114943579A CN202210447440.6A CN202210447440A CN114943579A CN 114943579 A CN114943579 A CN 114943579A CN 202210447440 A CN202210447440 A CN 202210447440A CN 114943579 A CN114943579 A CN 114943579A
- Authority
- CN
- China
- Prior art keywords
- commodity
- target
- label
- user
- commodities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a commodity network sales recommendation method, which relates to the technical field of network sales recommendation, and comprises the following steps: acquiring a commodity label submitted by a merchant for a commodity; matching the target label submitted by the user with the commodity label, and if the matching is successful, marking the commodity as the target commodity, wherein the target commodity forms a recommended commodity set; acquiring user data of a target commodity in a recommended commodity set, and acquiring a preference value of the target commodity according to the user data; determining a recommendation sequence of the target commodities in the recommended commodity set according to the preference value of the target commodity; the recommendation sequence of the target commodities in the recommended commodity set is determined according to the preference value, so that the target commodities similar to the preferences of the user can be accurately recommended to the user, the user experience is effectively improved, and the sales volume of the commodities in the website is increased.
Description
Technical Field
The invention relates to the technical field of network sales recommendation, in particular to a commodity network sales recommendation method.
Background
With the popularization of the internet and the development of website technologies, more and more users choose to browse, select or purchase commodities required by themselves on the internet. However, with the rapid increase of the number and types of the commodities, whether the ideal products in the mind of the user can be accurately searched is a key for improving the shopping conversion rate, but in actual research, the fact that the user cannot accurately master the keywords results in a long search process, and the recommended commodities are more, so that the user cannot quickly find the commodities in the mind, and the satisfaction degree of the user on the search results is difficult to improve.
Disclosure of Invention
The invention aims to: the invention provides a commodity network sale recommendation method, aiming at solving the technical problems that a search process is long, recommended commodities are more, a user cannot quickly find out a mental commodity, and the satisfaction degree of the user on a search result is difficult to improve due to the fact that the user cannot accurately master keywords.
The invention specifically adopts the following technical scheme for realizing the purpose:
a method for recommending goods network sales, the recommendation comprising the steps of:
acquiring a commodity label submitted by a merchant for a commodity;
matching the target label submitted by the user with the commodity label, and if the matching is successful, marking the commodity as the target commodity, wherein the target commodity forms a recommended commodity set;
acquiring user data of a target commodity in a recommended commodity set, and acquiring a preference value of the target commodity according to the user data;
and determining the recommendation sequence of the target commodities in the recommended commodity set according to the preference values of the target commodities.
Further, a commodity label library is configured in advance, and the commodity label library is set into a plurality of sub-commodity label libraries according to the categories of commodities; and the merchant selects the corresponding commodity label in the sub-commodity label library according to the category of the commodity and submits the commodity label.
Further, the merchant self-defines a commodity label of the commodity; carrying out similarity calculation on the commodity label of the user-defined commodity and the commodity label in the commodity label library; and if the similarity is greater than the preset threshold value, submitting the corresponding commodity label in the commodity label library as the commodity label of the commodity.
Further, a target label library is configured in advance, and the target label library is set into a plurality of sub target label libraries according to the categories of the commodities; and the user selects the target label in the corresponding sub-target label library according to the category of the commodity and submits the target label. .
Further, the user customizes the target tag; calculating the similarity between the user-defined target label and a target label in a target label library; and if the similarity is greater than the preset threshold value, submitting the corresponding target label in the target label library as the target label of the commodity.
Further, the user data includes transaction data, the actual purchase quantity of the target commodity is obtained according to the purchase quantity and the return quantity in the transaction data, and the actual purchase quantity is used as a preference value of the target commodity.
Further, the user data further comprises evaluation data, a good evaluation rate is obtained according to the good evaluation quantity and the total evaluation quantity in the evaluation data, a corresponding weight coefficient is obtained according to the good evaluation rate, and the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target commodity.
Further, if the evaluation data of the target commodity is not obtained, the shelf-loading time of the target commodity is obtained, a corresponding weight coefficient is obtained according to the shelf-loading time, and the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target commodity.
Further, before the obtaining of the user data of the target commodity and the obtaining of the preference value of the target commodity according to the user data, the method further includes the following steps:
and submitting the price interval of the commodity to be purchased by the user, and rejecting the target commodity outside the price interval in the recommended commodity set.
Further, before the obtaining of the user data of the target commodity and the obtaining of the preference value of the target commodity according to the user data, the method further includes the following steps:
and the user submits the age interval of the commodity to be purchased and rejects the target commodity outside the age interval in the recommended commodity set.
The invention has the following beneficial effects:
1. according to the commodity network sale recommendation method, when commodities are put on shelves, merchants submit corresponding commodity labels, a user determines the type of the needed commodities, then the target labels are input to be matched with the commodity labels corresponding to the commodities, if the matching is successful, the commodity labels are marked as the target commodities, all the target commodities form a recommended commodity set, user data corresponding to the target commodities are obtained, preference values of the target commodities are calculated respectively, the recommendation sequence of the target commodities in the recommended commodity set is determined according to the preference values, the target commodities which are similar to the preference of the user can be recommended to the user accurately, the user experience is effectively improved, and the sales volume of the commodities in a website is increased.
2. According to the commodity network sale recommendation method, the commodity label library is set into the plurality of sub-commodity label libraries according to the categories of commodities, a merchant configures commodity labels through the commodity label library, and the commodity labels of the self-defined commodities of the merchant and the commodity labels in the commodity label library are subjected to similarity calculation to configure the commodity labels, so that the merchant can configure the commodity labels quickly when putting on the commodities.
3. According to the commodity network sale recommendation method, the target label library is set into a plurality of sub-target label libraries according to the categories of commodities, a user configures target labels through the target label library, the user defines the target labels of the commodities and carries out similarity calculation with the target labels in the target label library to configure the target labels, and the user can conveniently and quickly configure the target labels when searching the commodities.
4. According to the commodity network sale recommendation method, the actual purchase quantity of the target commodity is obtained according to the purchase quantity and the return quantity in the transaction data, and the actual purchase quantity is used as the preference value of the target commodity, so that the commodities similar to the preference of the user can be accurately recommended.
5. According to the commodity network sale recommendation method, the goodness rate is obtained according to the goodness quantity and the total evaluation number in the evaluation data, the corresponding weight coefficient is obtained according to the goodness rate, and the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target commodity, so that the recommendation accuracy is further improved.
6. According to the commodity network sale recommendation method, the shelf-loading time of the target commodity is obtained if the evaluation data of the target commodity is not obtained, the corresponding weight coefficient is obtained according to the shelf-loading time, the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target commodity, the weight coefficient is endowed according to the shelf-loading time of the commodity when the evaluation data does not exist, and the recommendation accuracy is further improved.
7. The invention relates to a commodity network sale recommendation method, which is characterized in that a user submits a price interval and an age interval of a commodity to be purchased, target commodities which do not meet requirements in a recommended commodity set are removed, and the target commodities in the recommended commodity set are further ensured to meet the selection of the user.
Drawings
FIG. 1 is a method work flow diagram of the present invention;
FIG. 2 is a flow chart of a method for a merchant to submit a merchandise label according to the present invention;
FIG. 3 is a flow chart of a method for a merchant to submit a merchandise label of the present invention;
FIG. 4 is a flowchart of a first method for a user to submit a target tag according to the present invention;
FIG. 5 is a flowchart of a second method for a user to submit a target tag according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the present embodiment provides a method for recommending goods online sales, where the recommendation includes the following steps:
acquiring a commodity label submitted by a merchant for a commodity;
specifically, as shown in fig. 2, a commodity label library is configured in advance, and the commodity label library is set into a plurality of sub-commodity label libraries according to categories of commodities; and the merchant selects the corresponding commodity label in the sub-commodity label library according to the category of the commodity and submits the commodity label. When the commodity label library is implemented, the commodity label library is set into a plurality of sub commodity label libraries according to the categories of commodities, when the commodities are put on shelves, the corresponding sub commodity label libraries are found according to the categories of the commodities, according to the characteristics of the commodities, the commodities labels corresponding to the characteristics of the commodities are selected in the sub commodity label libraries by the merchant, the number of the commodity labels is at least one, and the merchant can conveniently configure the commodity labels through the commodity label libraries.
As shown in fig. 3, the merchant customizes the merchandise tag of the merchandise; carrying out similarity calculation on the commodity label of the user-defined commodity and the commodity label in the commodity label library; and if the similarity is greater than the preset threshold value, submitting the corresponding commodity label in the commodity label library as the commodity label of the commodity. During implementation, the category of the commodity is determined, the commodity label of the commodity is input by a merchant in a self-defined mode according to the category of the commodity, whether the commodity label with the similarity exceeding a preset threshold value exists in the corresponding sub-commodity label library or not is calculated, if yes, the corresponding commodity label in the sub-commodity label library is used as the commodity label of the commodity, and the commodity label is conveniently and quickly configured when the merchant shelves the commodity. And if a plurality of commodity labels with the similarity exceeding a preset threshold exist, selecting the commodity label with the highest similarity as the commodity label. And calculating whether the corresponding sub-commodity label library has a commodity label with the similarity exceeding a preset threshold value, and if not, ending the task. It should be noted that the similarity calculation is performed in the prior art, and a person skilled in the art may select a corresponding similarity calculation method according to actual needs to perform the calculation, which is not described herein again.
Matching the target label submitted by the user with the commodity label, and if the matching is successful, marking the commodity as a target commodity, wherein the target commodity forms a recommended commodity set; during implementation, the premise that the target label submitted by the user is matched with the commodity label is that the user determines the category of the commodity, the commodity can be directly matched in the corresponding sub-commodity label library according to the category of the commodity, matching efficiency is improved, and meanwhile, the condition that different commodity categories have at least one same commodity label to cause that the commodities which are not in the same category are matched is avoided.
Specifically, as shown in fig. 4, a target tag library is configured in advance, and the target tag library is set as a plurality of sub-target tag libraries according to categories of goods; and the user selects the target label in the corresponding sub-target label library according to the category of the commodity and submits the target label. When the method is implemented, the target label library is set into a plurality of sub target label libraries according to the categories of the commodities, the target labels corresponding to the characteristics of the commodities are selected in the sub target label libraries by a user, the number of the target labels is at least one, and the user can conveniently configure the target labels through the target label library.
Wherein, as shown in fig. 5, the user customizes the target tag; similarity calculation is carried out on the user-defined target label and the target label in the target label library; and if the similarity is greater than the preset threshold value, submitting the corresponding target label in the target label library as the target label of the commodity. When the method is implemented, the category of the commodity is determined, the target label of the commodity is input by a user according to the category of the commodity, whether the target label with the similarity exceeding a preset threshold exists in the corresponding sub-target label library or not is calculated, if yes, the corresponding target label in the sub-target label library is used as the target label of the commodity, and therefore the user can configure the target label quickly. And if a plurality of target labels with similarity exceeding a preset threshold exist, selecting the label with highest similarity as the target label. And calculating whether a target label with the similarity exceeding a preset threshold exists in the corresponding sub-target label library, and if not, ending the task. It should be noted that the similarity calculation is performed in the prior art, and a person skilled in the art may select a corresponding similarity calculation method according to actual needs to perform the calculation, which is not described herein again.
Acquiring user data of a target commodity in a recommended commodity set, and acquiring a preference value of the target commodity according to the user data;
specifically, the user data includes transaction data, the actual purchase quantity of the target commodity is obtained according to the purchase quantity and the return quantity in the transaction data, and the actual purchase quantity is used as a preference value of the target commodity. In practice, the user data includes transaction data that facilitates measuring a preference value of the target item by an actual purchase quantity of the item, wherein the greater the actual purchase quantity, the greater the preference value, the smaller the actual purchase quantity, and the smaller the preference value. The method and the device are convenient for recommending commodities similar to the user preference to the user through the preference value, and improve the recommendation accuracy.
And determining the recommendation sequence of the target commodities in the recommended commodity set according to the preference values of the target commodities. In implementation, the target commodities in the recommended commodity set are recommended and sorted according to the preference values, the greater the preference value is, the more the recommendation sequence is, the greater the preference value is, and the more the recommendation sequence is. In order to avoid that a great number of target commodities exist in the recommended commodity set, target commodities with preference values topN can be recommended, wherein N is a natural number greater than zero.
Example 2
The present embodiment is different from embodiment 1 in that the user data further includes evaluation data, a favorable rating is obtained according to the favorable rating number and the total number of evaluations in the evaluation data, a corresponding weight coefficient is obtained according to the favorable rating, and the product of the weight coefficient and the actual purchase number is used as the preference value of the target product.
In this embodiment, the preference value is further optimized through the evaluation data, a good evaluation rate is obtained according to the number of good evaluations and the total number of evaluations in the evaluation data, and corresponding weights are obtained according to the good evaluation rate, for example, the weight of the good evaluation rate is 1 when the good evaluation rate is more than 90%, the weight of the good evaluation rate is 80% -90%, the weight of the good evaluation rate is 0.8, the weight of the good evaluation rate is 60% -80%, the weight of the good evaluation rate is 0.7, the weight of the good evaluation rate is less than 60%, and the weight of the good evaluation rate is 0.6. The weight may be set according to specific situations, and is not particularly limited herein. And the product of the weight coefficient and the actual purchase quantity is used as a preference value, so that the recommendation accuracy is further improved.
Example 3
On the basis of embodiment 2, if the evaluation data of the target product is not obtained, the shelf life of the target product is obtained, a corresponding weight coefficient is obtained according to the shelf life, and the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target product.
In this embodiment, when the evaluation data is not obtained, the length of the shelving time of the target product may be determined by the shelving time of the target product, and the corresponding weight coefficient may be obtained according to the length of time, where the shorter the shelving time, the larger the weight coefficient corresponding to the shorter the shelving time, the smaller the weight coefficient corresponding to the longer the shelving time, for example, a weighting coefficient of 0.7 is given when the shelving time is 3 months or longer, a weighting coefficient of 0.8 is given when the shelving time is 2-3 months, a weighting coefficient of 0.9 is given when the shelving time is less than 2 months, and the weight may be set according to specific situations, which is not specifically limited herein. And the product of the weight coefficient and the actual purchase quantity is used as a preference value, so that the recommendation accuracy is further improved.
Example 4
On the basis of the embodiment 1, before the obtaining of the user data of the target product and the obtaining of the preference value of the target product according to the user data, the method further includes the following steps:
the method comprises the steps that a user submits a price interval of a commodity to be purchased and rejects a target commodity outside the price interval in a recommended commodity set;
before the user data of the target commodity is acquired and the preference value of the target commodity is acquired according to the user data, the method further comprises the following steps:
and the user submits the age interval of the commodity to be purchased and rejects the target commodity outside the age interval in the recommended commodity set.
In this embodiment, the user submits the price interval and the age interval of the goods to be purchased, and removes the target goods that do not meet the requirements in the recommended goods set, thereby further ensuring that the target goods in the recommended goods set meet the selection of the user.
Claims (10)
1. A commodity network sale recommendation method is characterized in that the recommendation comprises the following steps:
acquiring a commodity label submitted by a merchant for a commodity;
matching the target label submitted by the user with the commodity label, and if the matching is successful, marking the commodity as the target commodity, wherein the target commodity forms a recommended commodity set;
acquiring user data of a target commodity in a recommended commodity set, and acquiring a preference value of the target commodity according to the user data;
and determining the recommendation sequence of the target commodities in the recommended commodity set according to the preference values of the target commodities.
2. The commodity network selling recommendation method according to claim 1, characterized in that a commodity label library is configured in advance, and the commodity label library is set into a plurality of sub commodity label libraries according to categories of commodities; and the merchant selects the corresponding commodity label in the sub-commodity label library according to the category of the commodity and submits the commodity label.
3. The method according to claim 2, wherein the merchant defines a merchandise tag of the merchandise; carrying out similarity calculation on the commodity label of the user-defined commodity and the commodity label in the commodity label library; and if the similarity is greater than the preset threshold value, submitting the corresponding commodity label in the commodity label library as the commodity label of the commodity.
4. The commodity network selling recommendation method according to claim 1, characterized in that a target tag library is configured in advance, and the target tag library is set into a plurality of sub target tag libraries according to the categories of commodities; and the user selects the target label in the corresponding sub-target label library according to the category of the commodity and submits the target label.
5. The merchandise network selling recommending method according to claim 4, characterized in that said user-defined target tag; similarity calculation is carried out on the user-defined target label and the target label in the target label library; and if the similarity is greater than the preset threshold value, submitting the corresponding target label in the target label library as the target label of the commodity.
6. The method as claimed in claim 1, wherein the user data includes transaction data, the actual purchase quantity of the target product is obtained according to the purchase quantity and the return quantity in the transaction data, and the actual purchase quantity is used as the preference value of the target product.
7. The method as claimed in claim 6, wherein the user data further includes evaluation data, the evaluation data is used to obtain a good evaluation rate according to the number of good evaluations and the total number of evaluations in the evaluation data, a corresponding weight coefficient is obtained according to the good evaluation rate, and the product of the weight coefficient and the actual number of purchases is used as the preference value of the target product.
8. The method according to claim 7, wherein if the evaluation data of the target commodity is not obtained, the shelf life of the target commodity is obtained, a corresponding weight coefficient is obtained according to the shelf life, and the product of the weight coefficient and the actual purchase quantity is used as the preference value of the target commodity.
9. The method as claimed in claim 1, wherein before obtaining the user data of the target product and obtaining the preference value of the target product according to the user data, the method further comprises the following steps:
and submitting the price interval of the commodity to be purchased by the user, and removing the target commodity outside the price interval in the recommended commodity set.
10. The method as claimed in claim 1, wherein before obtaining the user data of the target product and obtaining the preference value of the target product according to the user data, the method further comprises the following steps:
and the user submits the age interval of the commodity to be purchased and rejects the target commodity outside the age interval in the recommended commodity set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210447440.6A CN114943579A (en) | 2022-04-26 | 2022-04-26 | Commodity network sale recommendation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210447440.6A CN114943579A (en) | 2022-04-26 | 2022-04-26 | Commodity network sale recommendation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114943579A true CN114943579A (en) | 2022-08-26 |
Family
ID=82906509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210447440.6A Pending CN114943579A (en) | 2022-04-26 | 2022-04-26 | Commodity network sale recommendation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114943579A (en) |
-
2022
- 2022-04-26 CN CN202210447440.6A patent/CN114943579A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8407104B2 (en) | Catalog based price search | |
US8762226B2 (en) | Item discovery tools and methods for shopping in an electronic commerce environment | |
CN107590675B (en) | User shopping behavior identification method based on big data, storage device and mobile terminal | |
CN112837118B (en) | Commodity recommendation method and device for enterprise users | |
US20060259358A1 (en) | Grocery scoring | |
KR20200108058A (en) | Recommended device and method | |
CN111325609A (en) | Commodity recommendation list determining method and device, electronic equipment and storage medium | |
CN105630836A (en) | Searching result sorting method and apparatus | |
CN106651418A (en) | Method of recommending add-on item for special offer when spending enough by e-business | |
CN105138690B (en) | The method and apparatus for determining keyword | |
WO2017119952A1 (en) | Consumer decision tree generation system | |
WO2017148272A1 (en) | Method and apparatus for identifying target user | |
CN103903148A (en) | C2C system, B2C system, and application methods thereof | |
JP2023052120A (en) | Customer personalization control unit, system, and method | |
Prasetyo | Searching cheapest product on three different e-commerce using k-means algorithm | |
CN115713377A (en) | Packaging material intermediary platform and method | |
KR101637986B1 (en) | System for providing the optimal products and method thereof | |
KR101963711B1 (en) | Method for trading used goods | |
CN116611796A (en) | Exception detection method and device for store transaction data | |
US20070276720A1 (en) | Indexing of a focused data set through a comparison technique method and apparatus | |
CN111192115A (en) | Community group purchase commodity selection method and device, readable storage medium and terminal | |
CN102789615A (en) | Book information correlation recommendation method, server and system | |
CN116362831A (en) | Commodity recommendation method and related equipment | |
CN114943579A (en) | Commodity network sale recommendation method | |
CN111639989B (en) | Commodity recommendation method and readable storage medium |
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 |