CN114037500A - Service commodity recommendation method and device, computer equipment and storage medium - Google Patents
Service commodity recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114037500A CN114037500A CN202111414043.0A CN202111414043A CN114037500A CN 114037500 A CN114037500 A CN 114037500A CN 202111414043 A CN202111414043 A CN 202111414043A CN 114037500 A CN114037500 A CN 114037500A
- Authority
- CN
- China
- Prior art keywords
- commodity
- service
- user
- data
- recommended
- 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
- 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]
- G06Q30/0641—Shopping interfaces
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a service commodity recommendation method, a service commodity recommendation device, computer equipment and a storage medium. The method comprises the following steps: acquiring user data corresponding to a service user, wherein the user data carries a commodity label; performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels; and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended. By adopting the method, the recommendation effect can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a service commodity recommendation method, apparatus, computer device, and storage medium.
Background
By analyzing the behavior data of the user purchasing the commodity on the mall website program website, the mall website program website can recommend the related commodity so as to improve the purchasing rate of the commodity. However, in the existing recommendation method, recommendation is performed according to user behavior data or a user purchase record, the same kind of goods as the user purchased the user may be recommended, for example, the user purchased or browsed an air conditioner, various types or brands of air conditioners may be recommended again to the user, but since the user purchased the air conditioner, the air conditioner may not be needed any more. In the field of household appliance recommendation application, therefore, the recommendation method cannot meet the actual requirements of users, and the recommendation effect is poor.
Disclosure of Invention
Therefore, it is necessary to provide a service commodity recommendation method, device, computer device, and storage medium for solving the above technical problems, so that in the field of home appliance recommendation, a service commodity matched with a commodity label can be accurately recommended according to the commodity label in user behavior data, and the service commodity is used for serving a commodity corresponding to the commodity label, so that the actual demand of a user can be met, and the recommendation effect is improved.
A service commodity recommendation method, the method comprising:
acquiring user data corresponding to a service user, wherein the user data carries a commodity label;
performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels;
and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
In one embodiment, the user data includes commodity order data, user behavior data, and user region data, the commodity order data carries a commodity tag, the user behavior data carries a user tag, the user region data carries a user region tag, the preset service policy includes a hot-sell commodity policy, a recommendation cycle policy, and a region policy, and the data calculation is performed on the user data based on the preset service policy to obtain a to-be-recommended service commodity set, including: determining a hot-sales service commodity recommendation set corresponding to a commodity label according to commodity order data and a hot-sales commodity strategy, determining a first service commodity recommendation set corresponding to a user label according to user behavior data and a recommendation cycle strategy, determining a second service commodity recommendation set corresponding to a region label according to user region data and a region strategy, and calculating the hot-sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to a preset weight distribution ratio to obtain a service commodity set to be recommended.
In one embodiment, determining a hot-sales service commodity recommendation set corresponding to a commodity label according to commodity order data and a hot-sales commodity strategy includes: and searching at least one matched candidate service commodity from the candidate service commodity set according to the commodity label, and screening hot sales service commodities according to the attention degree corresponding to each candidate service commodity to form a hot sales service commodity recommendation set.
In one embodiment, determining a first service commodity recommendation set corresponding to a user tag according to user behavior data and a recommendation cycle policy includes: and obtaining a recommendation cycle corresponding to the recommendation cycle strategy, obtaining the user use time in the user behavior data, and screening the candidate service commodity set according to the recommendation cycle and the user use time to obtain a related first service commodity recommendation set.
In one embodiment, determining the second service commodity recommendation set corresponding to the region label according to the user region data and the region policy includes: and obtaining service regions corresponding to the candidate service commodities in the candidate service commodity set, and screening according to the user region data and the service regions to obtain a second service commodity recommendation set.
In one embodiment, the step of calculating the hot-sell service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to the preset weight distribution to obtain a service commodity set to be recommended comprises the following steps: and determining a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio, and performing sequencing calculation according to the first weight ratio corresponding to the hot sales service commodity recommendation set, the second weight ratio corresponding to the first service commodity recommendation set and the third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
In one embodiment, acquiring user data corresponding to a service user includes: receiving operation corresponding to a service user, acquiring user behavior data corresponding to the service user according to operation acquisition, acquiring a commodity label according to the operation, acquiring matched commodity order data according to the commodity label, acquiring user region data corresponding to the service user through a positioning technology corresponding to the service user, and forming user data according to the user behavior data, the commodity order data and the user region data.
A service commodity recommendation apparatus, the apparatus comprising:
the acquisition module is used for acquiring user data corresponding to the service user, and the user data carries a commodity label;
the calculation module is used for performing data calculation on the user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels;
and the sending module is used for sending the service commodity set to be recommended to the user equipment corresponding to the service user so that the user equipment can display each service commodity to be recommended in the service commodity set to be recommended.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring user data corresponding to a service user, wherein the user data carries a commodity label;
performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels;
and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring user data corresponding to a service user, wherein the user data carries a commodity label;
performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels;
and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
According to the service commodity recommendation method, the service commodity recommendation device, the computer equipment and the storage medium, user data corresponding to a service user are obtained, the user data carry commodity labels, data calculation is carried out on the user data based on a preset business strategy, a service commodity set to be recommended is obtained, the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to the commodity labels; and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended. Therefore, the service commodity matched with the commodity label can be accurately recommended according to the commodity label in the user behavior data, the service commodity is used for serving the commodity corresponding to the commodity label instead of recommending the commodity similar to the commodity corresponding to the commodity label to the user at intervals, the actual requirement of the user can be met, and the recommendation effect is improved.
Drawings
FIG. 1 is a diagram of an exemplary implementation of a service commodity recommendation method;
FIG. 2 is a flowchart illustrating a service commodity recommendation method according to an embodiment;
FIG. 3 is a flowchart illustrating the user data calculation step in one embodiment;
FIG. 4 is a block diagram showing the construction of a service commodity recommending apparatus according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The service commodity recommendation method provided by the application can be applied to the application environment shown in fig. 1. Where user device 102 communicates with server 104 over a network. The user equipment 102 may be a terminal or a server, the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers.
Specifically, the server 104 obtains user data corresponding to a service user, the user data carries a commodity tag, performs data calculation on the user data based on a preset business strategy to obtain a service commodity set to be recommended, the service commodity set to be recommended includes at least one service commodity to be recommended, the service commodity to be recommended is used for serving a commodity corresponding to the commodity tag, sends the service commodity set to be recommended to the user equipment 102 corresponding to the service user, and finally, the user equipment 102 displays each service commodity to be recommended in the service commodity set to be recommended.
In one embodiment, as shown in fig. 2, a service commodity recommendation method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
The user data is all data related to a service user, the service user is a user who needs to perform service at present, and the user data may include, but is not limited to, user behavior data, commodity order data, and user region data, where the user behavior data is data related to a service user behavior, for example, a user browsing record, a user search record, a user payment record, and the like, and the commodity order data is data of a commodity related to the service user, and may be commodity data purchased by the service user or commodity data browsed by the service user, and the commodity data carries a commodity tag, the commodity tag is used to identify the commodity, and the commodity tag may be obtained by wholly circling a tag such as basic commodity information, a commodity identifier, and a commodity attribute, and is collectively referred to as a commodity tag. The user region data is data related to the location of the service user and can be obtained through a positioning service of the equipment where the service user is located.
Specifically, a user identifier corresponding to the service user is determined, and the commodity label can be determined from the user data by searching for related user data through the user identifier.
In one embodiment, obtaining user data corresponding to a service user includes: receiving operation corresponding to a service user, acquiring user behavior data corresponding to the service user according to operation acquisition, acquiring a commodity label according to the operation, acquiring matched commodity order data according to the commodity label, acquiring user region data corresponding to the service user through a positioning technology corresponding to the service user, and forming user data according to the user behavior data, the commodity order data and the user region data.
Specifically, the service user may perform an operation in a related application interface, where the operation may be a click operation, a voice operation, or a timing event trigger operation, and after receiving the operation, the server acquires user behavior data corresponding to the service user according to the operation, which may be browsing behavior data of the service user, search behavior data of the service user, and the like, and may also determine at least one product tag according to the operation of the service user, for example, determine what a searched product is from the search operation of the service user, and further search for corresponding product order data according to the product tag, where the product order data is order data corresponding to all product tags of the service user at present, and includes order data of the product tag purchased at present, order data of the product tag purchased in the past, and the like.
The user region data related to the location of the service user, including country, province, city, district, street, guideboard and the like, can be acquired through the positioning service of the equipment where the service user is located, and the user data can be composed of at least one of user behavior data, commodity order data and user region data.
And 204, performing data calculation on the user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to the commodity label.
The preset business strategy is used for calculating the service commodity to be recommended according to the user data, the service commodity is a commodity with service property and is not an entity commodity, the commodity corresponding to the commodity label can be an entity commodity, the corresponding service commodity can be deduced according to the entity commodity relevant to the service user, and the service commodity is recommended to the service user. The preset business strategy can be obtained by setting in advance according to actual business requirements, actual product requirements or actual application scenarios, for example, the preset business strategy can consider user behavior habits and requirements, north-south climates, seasons and other factors of the service commodities in different regions, different areas and different communities, wherein the preset business strategy can include recommendation rules corresponding to different commodities, and data calculation can be performed on user data through the recommendation rules described in the preset business strategy to obtain a to-be-recommended commodity set consisting of at least one to-be-recommended commodity.
The data calculation is carried out on the user data through the recommendation rules described in the preset service strategy, specifically, the user data comprises multiple types of data, the recommendation rules corresponding to the various types of data in the preset service data are obtained, the data are recommended according to the recommendation rules, and the service commodity set to be recommended is determined from the candidate service commodity set.
And step 206, sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment can display each service commodity to be recommended in the service commodity set to be recommended.
Specifically, the server sends the service commodity set to be recommended to user equipment corresponding to the service user, the user equipment may be a user terminal or the like, and further, after receiving the service commodity set to be recommended, the user equipment displays each service user to be recommended in the service commodity set to be recommended through a display interface of a related application until the user watches the service commodity set, so that a recommendation effect of the service commodity is achieved.
The service commodity recommendation method comprises the steps of obtaining user data corresponding to a service user, wherein the user data carries a commodity label, carrying out data calculation on the user data based on a preset service strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to the commodity label; and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended. Therefore, the service commodity matched with the commodity label can be accurately recommended according to the commodity label in the user behavior data, the service commodity is used for serving the commodity corresponding to the commodity label instead of recommending the commodity similar to the commodity corresponding to the commodity label to the user at intervals, the actual requirement of the user can be met, and the recommendation effect is improved.
In one embodiment, as shown in fig. 3, the user data includes commodity order data, user behavior data and user region data, the commodity order data carries a commodity tag, the user behavior data carries a user tag, the user region data carries a user region tag, the preset service policy includes a hot-sell commodity policy, a recommendation cycle policy and a region policy,
the method comprises the following steps of carrying out data calculation on user data based on a preset service strategy to obtain a service commodity set to be recommended, wherein the method comprises the following steps:
The hot-selling commodity strategy is one of preset business strategies, and is mainly used for screening out hot-selling service commodities corresponding to commodity labels from candidate service commodities, wherein the hot-selling service commodities are service commodities with high user attention in the service commodities. Specifically, commodity order data in the user data and a hot-sell commodity strategy in the preset business strategy are obtained, and a hot-sell service commodity recommendation set corresponding to the commodity label can be found out through the hot-sell commodity strategy and the commodity order data. Specifically, a corresponding commodity label in the commodity order data is obtained, and a hot-selling service commodity with the user attention is searched according to the commodity label to form a hot-selling service commodity recommendation set.
In one embodiment, determining a hot-sales service commodity recommendation set corresponding to a commodity label according to commodity order data and a hot-sales commodity strategy comprises: and searching at least one matched candidate service commodity from the candidate service commodity set according to the commodity label, and screening hot sales service commodities according to the attention degree corresponding to each candidate service commodity to form a hot sales service commodity recommendation set.
Specifically, the commodity label is determined according to the commodity order data, the commodity order data includes all data related to the commodity order, so that the commodity label can be extracted from the commodity order data, the commodity label can be a general name of a commodity name, commodity basic information, a commodity identification and the like, at least one matched candidate service commodity is searched from a candidate service commodity set according to the commodity label, and a mapping relation between the candidate service commodity and the commodity label can be established in advance. The attention degree corresponding to each candidate service commodity is obtained by calculating the attention degree of the candidate service commodity relative to the user, and the attention degree can be behaviors such as searching, browsing and purchasing.
For example, in the field of home appliances, the product order data is order data related to an air conditioner, the product tag is extracted from the product order data to be the air conditioner a, and the matching candidate service product is found according to the air conditioner a, such as a cleaning service of the air conditioner a, a maintenance service of the air conditioner a, a replacement service of the air conditioner a, and the like, and then the hot-selling service product is determined as follows according to the attention degree corresponding to each candidate service product: and the cleaning service of the air conditioner A and the maintenance service of the air conditioner A form a hot sales service commodity recommendation set.
And step 304, determining a first service commodity recommendation set corresponding to the user tag according to the user behavior data and the recommendation cycle strategy.
The recommendation cycle strategy is one of preset business strategies, and is mainly used for screening out a first service commodity which accords with a recommendation cycle and corresponds to a user tag from candidate service commodities, namely the recommendation cycle strategy is that a user purchases a certain entity commodity and recommends related service commodities after a long time. The user label may be a general term of a user image, user basic information, a user identifier, and the like, and specifically, the commodity identifier and the user label are determined according to the user behavior data, the recommendation period in the recommendation period policy is obtained, and at least one first service commodity which meets the recommendation period and corresponds to the user label is obtained from the candidate service commodity set according to the user behavior data and the recommendation period to form a first service commodity recommendation set.
In one embodiment, determining a first service commodity recommendation set corresponding to a user tag according to user behavior data and a recommendation cycle policy includes: and obtaining a recommendation cycle corresponding to the recommendation cycle strategy, obtaining the user use time in the user behavior data, and screening the candidate service commodity set according to the recommendation cycle and the user use time to obtain a related first service commodity recommendation set.
Specifically, a preset recommendation cycle in the recommendation cycle strategy is obtained, user use time, namely time for a user to use purchased commodities, such as commodity sign-in time and commodity installation time, is extracted from user behavior data, and then a related first service commodity recommendation set is obtained by screening from a candidate service commodity set through the recommendation cycle and the user use time.
For example, in the field of home appliances, the user behavior data is behavior data related to the service user a, the service user a has browsed product data related to the air conditioner a for multiple times, and the service user a has purchased product data related to the air conditioner a once a half year ago, and the recommendation cycle in the recommendation cycle policy is half a year, so that the first service product that needs to be recommended to the service user a after screening the half year is related to the air conditioner a, and may be a product for serving the air conditioner a, for example, a maintenance service for the air conditioner a once a half year.
And step 306, determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region strategy.
The region policy is also one of the preset business policies, and is mainly used for screening out a second service commodity which accords with the region label and corresponds to the commodity identifier from the candidate service commodities, namely the region policy is to screen out the service commodity which accords with the geographic factor of the location of the user in consideration of the geographic factor, for example, service commodity recommendations in north and south regions may be different. Specifically, the user region data is obtained, and the second service goods meeting the region label are screened out according to the user region data and the rules in the region policy. The region label can be a region factor, a climate factor, a season factor, etc., and the rule in the region strategy can be preset according to the business requirement, the actual product requirement or the actual application product.
In one embodiment, determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region policy includes: and obtaining service regions corresponding to the candidate service commodities in the candidate service commodity set, and screening according to the user region data and the service regions to obtain a second service commodity recommendation set.
Specifically, a service region corresponding to each candidate service commodity in the candidate service commodity set is obtained, a mapping relationship between the candidate service commodity and the service region may be established in advance according to an actual service requirement, an actual product requirement, or an actual application scenario, and then a second service commodity matched with the user region data may be obtained according to the mapping relationship, so as to obtain a second service commodity set.
For example, since the service region corresponding to the candidate service article a is guangzhou, the service region corresponding to the candidate service article B is beijing, and the user region data is all data of the guangzhou, the second service article that can be screened is the candidate service article a.
And 308, calculating the hot sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to preset weight distribution to obtain a service commodity set to be recommended.
The preset weight distribution ratio can be set in advance according to actual business requirements, actual product requirements or actual application scenes, and can include a first weight ratio corresponding to the hot-sell service commodity recommendation set, a second weight ratio corresponding to the first service commodity recommendation set and a weight ratio corresponding to the second service commodity recommendation set, and the service commodity set to be recommended is obtained through calculation according to the weight ratios corresponding to the hot-sell service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set.
In one embodiment, the calculating the service commodity set to be recommended according to the preset weight distribution ratio and the hot-sell service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set includes: and determining a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio, and performing sequencing calculation according to the first weight ratio corresponding to the hot sales service commodity recommendation set, the second weight ratio corresponding to the first service commodity recommendation set and the third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
For example, the regional policy recommends a 50% duty: optimizing recommendation sequencing according to the region area where the recommendation user is located, and performing sequencing influence according to the background configuration of the service; the recommended period accounts for 30%: a user-based behavioral track, comprising: searching, collecting, browsing, paying and the like, sequencing the recommended commodities, increasing the weight of the same commodity, and sequencing and grading different commodities according to the weight; hot-market strategy accounts for 20%: and calculating labels based on browsed, collected, purchased and purchased commodities, recommending users who do not generate purchasing behaviors on the same label, increasing the weight of the same commodity, and sorting and grading different commodities according to the weight to obtain a service commodity set to be recommended.
In a specific application scenario, service commodities are recommended to non-cleaning commodities, user behavior track data are calculated according to statistics, data calculation is carried out according to browsing, purchase adding, searching and collection behaviors of a user in a Suningyi purchase APP/applet and a Suningpaike APP/applet within a certain period (three months, half years and one year), and collaborative filtering processing based on the user is carried out according to the behavior data of the user to obtain a commodity sequencing set recommended to the user. The collaborative filtering processing is based on users and commodities, corresponding recommendation weighting processing can be carried out according to user labels during filtering processing, commodity labels can be used for recommending aiming at cold starting of users, consideration recommendation can be carried out according to commodities which are sold more hot or in a positioning area, the recommendation result is summarized, and commodities with low filtering recommendation conversion rate are summarized. The summarizing process is divided into manual and automatic processes, data can be exported manually, data can be independently summarized by a service party or an information party (data analysis can be carried out by using software such as a spread, and the like), and the automatic summarizing process is used for labeling commodities with low cold-start recommendation conversion rate and sequentially carrying out the commodity sequencing operation under cold start.
The cold start refers to calculation and recommendation through transaction records which are easily bought by a user in the prior art or data stored in an external platform in an imported form when the user does not generate behavior track data, and recommendation of service goods (based on user positioning operation) is performed according to hot-sold goods or regional strategies maintained in business strategies when the user does not generate transaction records and does not have import operation of external order information. If the user has no service address or positioning address, the commodity label is used for carrying out cold-start commodity sorting operation, commodity recommendation is carried out, the recommendation result is summarized, and sorting descending processing is carried out on commodities with low cold-start recommendation conversion rate.
For another example, the service commodity is recommended to be a cleaning commodity, the user behavior track data is calculated according to statistics, data calculation is carried out according to browsing, purchasing, searching and collecting behaviors of the user in a Suningyi purchase APP/applet and a Suningpaike APP/applet within a certain period (three months, half years and one year), wherein the commodities such as physical household appliances and decoration tools are subjected to private domain processing, if the confidence interval reaches the required level, collaborative filtering processing based on the user is carried out according to the behavior data of the user to obtain a commodity sequencing set recommended to the user, and the cleaning and formaldehyde removal service commodity is recommended according to the recommendation. The collaborative filtering processing is based on users and commodities, corresponding recommendation weighting processing can be carried out according to user labels during filtering processing, commodity labels can be used for recommending aiming at cold starting of users, consideration recommendation can be carried out according to commodities which are sold more hot or in a positioning area, the recommendation result is summarized, and commodities with low filtering recommendation conversion rate are summarized. The summarizing process is divided into manual and automatic processes, data can be exported manually, data can be independently summarized by a service party or an information party (data analysis can be carried out by using software such as a spread, and the like), and the automatic summarizing process is used for labeling commodities with low cold-start recommendation conversion rate and sequentially carrying out the commodity sequencing operation under cold start. It is noted that recommendations for cleaning type commodity operations are all based on cleaning commodity pools (maintenance of cleaning commodity pools by businesses).
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in the above-described flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided a service goods recommending apparatus 400 including: an obtaining module 402, a calculating module 404, and a sending module 406, wherein:
an obtaining module 402, configured to obtain user data corresponding to a service user, where the user data carries a commodity label.
The calculation module 404 is configured to perform data calculation on the user data based on a preset service policy to obtain a service commodity set to be recommended, where the service commodity set to be recommended includes at least one service commodity to be recommended, and the service commodity to be recommended is used to serve a commodity corresponding to a commodity label.
The sending module 406 is configured to send the service commodity set to be recommended to the user equipment corresponding to the service user, so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
In one embodiment, the user data includes commodity order data, user behavior data and user region data, the commodity order data carries a commodity tag, the user behavior data carries a user tag, the user region data carries a user region tag, the preset business strategy includes a hot-sell commodity strategy, a recommendation cycle strategy and a region strategy, the calculation module 404 determines a hot-sell service commodity recommendation set corresponding to the commodity tag according to the commodity order data and the hot-sell commodity strategy, determining a first service commodity recommendation set corresponding to the user label according to the user behavior data and the recommendation cycle strategy, determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region strategy, and comparing the hot sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to preset weight distribution to obtain a service commodity set to be recommended.
In an embodiment, the calculation module 404 searches at least one matched candidate service commodity from the candidate service commodity set according to the commodity label, and obtains a hot-selling service commodity according to the attention degree corresponding to each candidate service commodity to form a hot-selling service commodity recommendation set.
In one embodiment, the calculation module 404 obtains a recommendation period corresponding to the recommendation period policy, obtains the user usage time in the user behavior data, and obtains a related first service commodity recommendation set by screening from the candidate service commodity set according to the recommendation period and the user usage time.
In an embodiment, the calculation module 404 obtains a service region corresponding to each candidate service commodity in the candidate service commodity set, and obtains a second service commodity recommendation set according to the user region data and each service region.
In one embodiment, the calculating module 404 determines a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio, and performs ranking calculation according to the first weight ratio corresponding to the hot-sell service commodity recommendation set, the second weight ratio corresponding to the first service commodity recommendation set and the third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
In an embodiment, the obtaining module 402 receives an operation corresponding to a service user, obtains user behavior data corresponding to the service user according to operation acquisition, obtains a product tag according to the operation, obtains matched product order data according to the product tag, obtains user region data corresponding to the service user through a positioning technology corresponding to the service user, and forms user data according to the user behavior data, the product order data, and the user region data.
For specific limitations of the service commodity recommendation device, reference may be made to the above limitations of the service commodity recommendation method, which are not described herein again. The modules in the service commodity recommending device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing preset business strategies. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a service commodity recommendation method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring user data corresponding to a service user, wherein the user data carries a commodity label; performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels; and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
In one embodiment, the user data includes commodity order data, user behavior data, and user region data, the commodity order data carries a commodity tag, the user behavior data carries a user tag, the user region data carries a user region tag, the preset service policy includes a hot-sell commodity policy, a recommendation cycle policy, and a region policy, and the processor implements the following steps when executing the computer program: determining a hot-sales service commodity recommendation set corresponding to a commodity label according to commodity order data and a hot-sales commodity strategy, determining a first service commodity recommendation set corresponding to a user label according to user behavior data and a recommendation cycle strategy, determining a second service commodity recommendation set corresponding to a region label according to user region data and a region strategy, and calculating the hot-sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to a preset weight distribution ratio to obtain a service commodity set to be recommended.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and searching at least one matched candidate service commodity from the candidate service commodity set according to the commodity label, and screening hot sales service commodities according to the attention degree corresponding to each candidate service commodity to form a hot sales service commodity recommendation set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and obtaining a recommendation cycle corresponding to the recommendation cycle strategy, obtaining the user use time in the user behavior data, and screening the candidate service commodity set according to the recommendation cycle and the user use time to obtain a related first service commodity recommendation set.
In one embodiment, determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region policy includes: and obtaining service regions corresponding to the candidate service commodities in the candidate service commodity set, and screening according to the user region data and the service regions to obtain a second service commodity recommendation set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and determining a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio, and performing sequencing calculation according to the first weight ratio corresponding to the hot sales service commodity recommendation set, the second weight ratio corresponding to the first service commodity recommendation set and the third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving operation corresponding to a service user, acquiring user behavior data corresponding to the service user according to operation acquisition, acquiring a commodity label according to the operation, acquiring matched commodity order data according to the commodity label, acquiring user region data corresponding to the service user through a positioning technology corresponding to the service user, and forming user data according to the user behavior data, the commodity order data and the user region data.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring user data corresponding to a service user, wherein the user data carries a commodity label; performing data calculation on user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to commodity labels; and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
In one embodiment, the user data includes commodity order data, user behavior data, and user region data, the commodity order data carries a commodity tag, the user behavior data carries a user tag, the user region data carries a user region tag, the preset service policy includes a hot-sell commodity policy, a recommendation cycle policy, and a region policy, and the processor implements the following steps when executing the computer program: determining a hot-sales service commodity recommendation set corresponding to a commodity label according to commodity order data and a hot-sales commodity strategy, determining a first service commodity recommendation set corresponding to a user label according to user behavior data and a recommendation cycle strategy, determining a second service commodity recommendation set corresponding to a region label according to user region data and a region strategy, and calculating the hot-sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to a preset weight distribution ratio to obtain a service commodity set to be recommended.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and searching at least one matched candidate service commodity from the candidate service commodity set according to the commodity label, and screening hot sales service commodities according to the attention degree corresponding to each candidate service commodity to form a hot sales service commodity recommendation set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and obtaining a recommendation cycle corresponding to the recommendation cycle strategy, obtaining the user use time in the user behavior data, and screening the candidate service commodity set according to the recommendation cycle and the user use time to obtain a related first service commodity recommendation set.
In one embodiment, determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region policy includes: and obtaining service regions corresponding to the candidate service commodities in the candidate service commodity set, and screening according to the user region data and the service regions to obtain a second service commodity recommendation set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and determining a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio, and performing sequencing calculation according to the first weight ratio corresponding to the hot sales service commodity recommendation set, the second weight ratio corresponding to the first service commodity recommendation set and the third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving operation corresponding to a service user, acquiring user behavior data corresponding to the service user according to operation acquisition, acquiring a commodity label according to the operation, acquiring matched commodity order data according to the commodity label, acquiring user region data corresponding to the service user through a positioning technology corresponding to the service user, and forming user data according to the user behavior data, the commodity order data and the user region data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A service commodity recommendation method, the method comprising:
acquiring user data corresponding to a service user, wherein the user data carries a commodity label;
performing data calculation on the user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to the commodity label;
and sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
2. The method of claim 1, wherein the user data comprises commodity order data, user behavior data, and user geographic data, the commodity order data carries a commodity label, the user behavior data carries a user label, the user geographic data carries a user geographic label, the predetermined business policies comprise a hot-sell commodity policy, a recommendation cycle policy, and a geographic policy,
the data calculation of the user data based on the preset business strategy to obtain a service commodity set to be recommended comprises the following steps:
determining a hot-sales service commodity recommendation set corresponding to the commodity label according to the commodity order data and the hot-sales commodity strategy;
determining a first service commodity recommendation set corresponding to the user tag according to the user behavior data and the recommendation cycle strategy;
determining a second service commodity recommendation set corresponding to the region label according to the user region data and the region strategy;
and calculating the hot sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to a preset weight distribution ratio to obtain a service commodity set to be recommended.
3. The method of claim 2, wherein the determining a recommendation set of hot-sell service goods corresponding to the goods label according to the goods order data and the hot-sell goods policy comprises:
searching at least one matched candidate service commodity from a candidate service commodity set according to the commodity label;
and screening and obtaining the hot sales service commodities according to the attention degree corresponding to each candidate service commodity to form a hot sales service commodity recommendation set.
4. The method of claim 2, wherein the determining the first service item recommendation set corresponding to the user tag according to the user behavior data and the recommendation cycle policy comprises:
acquiring a recommendation cycle corresponding to the recommendation cycle strategy;
acquiring user use time in the user behavior data;
and screening the candidate service commodity set according to the recommendation period and the user service time to obtain a related first service commodity recommendation set.
5. The method of claim 2, wherein the determining the second recommended set of service goods corresponding to the geographic label according to the geographic data of the user and the geographic policy comprises:
acquiring a service region corresponding to each candidate service commodity in the candidate service commodity set;
and screening according to the user region data and each service region to obtain a second service commodity recommendation set.
6. The method of claim 2, wherein the calculating the hot sales service commodity recommendation set, the first service commodity recommendation set and the second service commodity recommendation set according to a preset weight distribution ratio to obtain a service commodity set to be recommended comprises:
determining a first weight ratio, a second weight ratio and a third weight ratio according to a preset weight distribution ratio;
and performing sequencing calculation according to a first weight ratio corresponding to the hot sales service commodity recommendation set, a second weight ratio corresponding to the first service commodity recommendation set and a third weight ratio corresponding to the second service commodity recommendation set to obtain a service commodity set to be recommended.
7. The method of claim 1, wherein the obtaining user data corresponding to the service user comprises:
receiving operation corresponding to the service user, and acquiring user behavior data corresponding to the service user according to the operation;
acquiring a commodity label according to the operation, and acquiring matched commodity order data according to the commodity label;
and obtaining user region data corresponding to the service user through a positioning technology corresponding to the service user, and forming user data according to the user behavior data, the commodity order data and the user region data.
8. A service commodity recommendation apparatus, characterized in that the apparatus comprises:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring user data corresponding to a service user, and the user data carries a commodity label;
the calculation module is used for performing data calculation on the user data based on a preset business strategy to obtain a service commodity set to be recommended, wherein the service commodity set to be recommended comprises at least one service commodity to be recommended, and the service commodity to be recommended is used for serving commodities corresponding to the commodity label;
and the sending module is used for sending the service commodity set to be recommended to user equipment corresponding to the service user so that the user equipment displays each service commodity to be recommended in the service commodity set to be recommended.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111414043.0A CN114037500A (en) | 2021-11-25 | 2021-11-25 | Service commodity recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111414043.0A CN114037500A (en) | 2021-11-25 | 2021-11-25 | Service commodity recommendation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114037500A true CN114037500A (en) | 2022-02-11 |
Family
ID=80145544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111414043.0A Pending CN114037500A (en) | 2021-11-25 | 2021-11-25 | Service commodity recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114037500A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429371A (en) * | 2022-04-06 | 2022-05-03 | 新石器慧通（北京）科技有限公司 | Unmanned vehicle-based commodity marketing method and device, electronic equipment and storage medium |
-
2021
- 2021-11-25 CN CN202111414043.0A patent/CN114037500A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429371A (en) * | 2022-04-06 | 2022-05-03 | 新石器慧通（北京）科技有限公司 | Unmanned vehicle-based commodity marketing method and device, electronic equipment and storage medium |
| CN114429371B (en) * | 2022-04-06 | 2022-06-28 | 新石器慧通（北京）科技有限公司 | Unmanned vehicle-based commodity marketing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108733706B (en) | Method and device for generating heat information | |
| CN109741146B (en) | Product recommendation method, device, equipment and storage medium based on user behaviors | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| CN107730389A (en) | Electronic installation, insurance products recommend method and computer-readable recording medium | |
| CN109300003B (en) | Enterprise recommendation method, enterprise recommendation device, computer equipment and storage medium | |
| US20100030648A1 (en) | Social media driven advertisement targeting | |
| CN109712001A (en) | Information recommendation method, device, computer equipment and storage medium | |
| CN111178069B (en) | Data processing method, device, computer equipment and storage medium | |
| US20140129596A1 (en) | Methods for geotemporal fingerprinting | |
| CN111008869A (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| WO2021088434A1 (en) | Data analysis method and system based on regionalized membership marketing scene, and computer device | |
| CN108563681B (en) | Content recommendation method and device, electronic equipment and system | |
| JP2010097612A (en) | Dynamic geo-location parameter for determining impact of online behavior on offline sales | |
| CN108334625B (en) | User information processing method and device, computer equipment and storage medium | |
| CN112288464A (en) | Commodity recommendation method and device, computer equipment and storage medium | |
| KR102084719B1 (en) | Sales forecast information providing system | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| CN113220657B (en) | Data processing method and device and computer equipment | |
| CN109801101A (en) | Label determines method, apparatus, computer equipment and storage medium | |
| CN112241489A (en) | Information pushing method and device, readable storage medium and computer equipment | |
| CN101140582A (en) | User preferences generation system and method thereof | |
| CN111882399A (en) | Service information recommendation method, device, computer system and readable storage medium | |
| CN113032668A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN112102002A (en) | Commodity recommendation method and device based on knowledge graph, computer and storage medium | |
| CN113763035A (en) | Advertisement delivery effect prediction method and device, computer equipment and 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 |