CN111738785A - Product selection method, system and storage medium - Google Patents
Product selection method, system and storage medium Download PDFInfo
- Publication number
- CN111738785A CN111738785A CN201910243207.4A CN201910243207A CN111738785A CN 111738785 A CN111738785 A CN 111738785A CN 201910243207 A CN201910243207 A CN 201910243207A CN 111738785 A CN111738785 A CN 111738785A
- Authority
- CN
- China
- Prior art keywords
- commodity
- data
- user
- commodities
- option
- 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
- 238000010187 selection method Methods 0.000 title abstract description 12
- 238000012163 sequencing technique Methods 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims description 65
- 238000000034 method Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 11
- 238000013480 data collection Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 12
- 238000007726 management method Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a product selection method, a product selection system and a storage medium. The product selection method comprises the following steps: receiving a commodity acquisition request, and acquiring an identifier of a selection module from the commodity acquisition request; responding to the commodity acquisition request, and acquiring user portrait data; selecting the option module from an option library according to the identifier of the option module, wherein the option library is used for storing a plurality of option modules, and the selected module comprises: commodity portrait data and commodity ordering rules corresponding to a plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity portrait data and the weight of the user portrait data; based on the commodity portrait data and the user portrait data, sequencing the plurality of candidate commodities by utilizing the commodity sequencing rule to obtain a first sequencing result; and selecting the goods to be presented according to the first sequencing result.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method, a system, and a storage medium for selecting a product.
Background
With the development of electronic commerce, the user is more and more accustomed to the operation of browsing commodities and the like through an electronic commerce platform. The page presented by the e-commerce platform may be divided into a plurality of regions (each region may include one or more presentation locations). The e-commerce back office may determine the items to be presented for each region. Currently, e-commerce backgrounds provide the same merchandise information to different users.
Disclosure of Invention
According to one aspect of the application, a method for selecting products is provided, which comprises the following steps: receiving a commodity acquisition request, and acquiring an identifier of a selection module from the commodity acquisition request; responding to the commodity acquisition request, and acquiring user portrait data; selecting the option module from an option library according to the identifier of the option module, wherein the option library is used for storing a plurality of option modules, and the selected module comprises: commodity portrait data and commodity ordering rules corresponding to a plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity portrait data and the weight of the user portrait data; based on the commodity portrait data and the user portrait, sequencing the plurality of candidate commodities by utilizing the commodity sequencing rule to obtain a first sequencing result; and selecting the goods to be presented according to the first sequencing result. .
According to one aspect of the present application, there is provided an item selection system comprising: the data processing unit is used for receiving a commodity obtaining request and obtaining the identification of the option module from the commodity obtaining request; a loading unit, configured to, in response to the commodity acquisition request, acquire user portrait data and select the option module from an option library according to an identifier of the option module, where the option library is configured to store a plurality of option modules, and the selected module includes: commodity portrait data and commodity ordering rules corresponding to a plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity portrait data and the weight of the user portrait data; wherein the data processing unit is further configured to: and sorting the plurality of candidate commodities by using the commodity sorting rule based on the commodity portrait data and the user portrait to obtain a first sorting result, and selecting the commodities to be presented according to the first sorting result.
According to one aspect of the present application, there is provided an item selection system comprising:
a processor;
a memory; and
one or more programs stored in the memory and configured to be executed by the processor, the one or more programs including instructions for performing the method of selecting an item according to the present application.
According to one aspect of the present application, there is provided a storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an option system, cause the option system to perform an option method according to the present application.
In conclusion, the commodity selection scheme according to the application can comprehensively consider commodity portrait data and user portrait data, so that corresponding commodities to be presented can be selected according to the requirements of each user, and the matching performance of the presented commodities and the user characteristics is improved. In other words, the selection scheme of the application can precisely select the commodities to be presented from the selection module according to the user interests.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1A illustrates a schematic diagram of an application scenario 100 in accordance with some embodiments of the present application;
FIG. 1B illustrates a schematic diagram of a merchandise page according to some embodiments of the present application;
FIG. 2 illustrates a flow diagram of an election method 200 according to some embodiments of the present application;
FIG. 3 illustrates a flow diagram of an election method 300 according to some embodiments of the present application;
FIG. 4 illustrates a flow diagram of a method 400 of determining merchandise representation data and user representation data according to some embodiments of the present application;
FIG. 5 illustrates a flow chart of a method 500 of determining an alternative good corresponding to each option module according to some embodiments of the present application;
FIG. 6 illustrates a flow diagram of a method 600 of ordering items of choice according to some embodiments of the present application;
FIG. 7 illustrates a schematic diagram of an options system 130 according to some embodiments of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
FIG. 1A illustrates a schematic diagram of an application scenario 100 according to some embodiments of the present application. As shown in fig. 1A, the application scenario 100 may include a terminal device 110, a page service system 120, and an option system 130. Here, the terminal device 110, the page service system 120, and the item selection system 130 may communicate through the network 140. Network 140 may include, for example, a Local Area Network (LAN) and a Wide Area Network (WAN). Embodiments of the present application may implement network 140 using any well-known network protocol, including various wired or wireless protocols, such as Ethernet, FIREWIRE, Global System for Mobile communications (GSM), Enhanced Data GSM Environment (EDGE), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, WiFi, Voice over IP (VoIP), Wi-MAX, or any other suitable communication protocol.
The page service system 120 may include one or more servers. Page service system 120 may send a merchandise acquisition request to option system 130 in response to the access request from terminal device 110. The selection system 130 may select the item to be presented in the item page according to the item acquisition request. In an application scenario of electronic commerce, the page service system 120 and the option system 130 both belong to an e-commerce platform.
The access request of terminal device 110 may, for example, request one or more merchandise pages. An item page may include one or more item presentation areas. Each merchandise presentation area may include one or more presentation locations (also referred to as page pit locations). Each presentation location may present information for an item. Each presentation location may present, for example, a thumbnail of the item, a video related to the item, a textual description, and so forth. Embodiments of the present application may create an options module for an item presentation area in options system 130. Here, one option module may correspond to one or more article presentation areas. An item selection module may include merchandise representation data for a plurality of candidate items. Merchandise representation data for a merchandise item candidate is used to characterize the merchandise item candidate. The number of candidate commodities corresponding to the commodity image data in one commodity selection module is greater than the number of commodities to be presented in the commodity presentation area corresponding to the commodity selection module. In response to the merchandise acquisition request, the merchandise system 130 may select merchandise to be presented in the merchandise presentation area from the candidate merchandise corresponding to the merchandise representation data of the merchandise module. In some embodiments, the item selection system 130 may sort the candidate items corresponding to the item representation data in an item selection module according to the item representation data in the item selection module and the representation data (i.e., user characteristics) of the user requesting the item page, and then determine a list of items to be presented according to the sorting result and the number of presentation positions in the item presentation area. The user characteristics can reflect the interests and the requirements of the user.
In summary, the embodiment of the application can select the commodity to be presented from the alternative commodities according to the portrait data of the user and the portrait data of the commodity, and can greatly improve the matching between the presented commodity and the characteristics of the user. Therefore, the selection scheme of the embodiment of the application can fully consider the interest of the user, and further improve the transaction possibility of the commodity.
FIG. 1B illustrates a schematic diagram of a merchandise page according to some embodiments of the present application. As shown in FIG. 1B, the item page may include item presentation areas 101, 102, and 103. The article presentation area 103 may include, for example, 4 article presentation locations (i.e., 4 pit positions), i.e., 1031, 1032, 1033, and 1034. It should be noted that fig. 1B is only an example of the product presentation area, and the specific form of the product presentation area is not limited in the present application.
Fig. 2 illustrates a flow diagram of an election method 200 according to some embodiments of the present application. The selection method 200 may be performed by, for example, but not limited to, the selection system 130.
As shown in fig. 2, in step S201, a product acquisition request is received, and an identifier of an option module is acquired from the product acquisition request. In some embodiments, the item selection system 130 may receive an item acquisition request from the page server 120.
In step S202, user portrait data is acquired in response to a product acquisition request. The user representation data is used to describe characteristic information of the user.
In step S203, an option module is selected from the option library according to the identifier of the option module. The selection library is used for storing a plurality of selection modules. The selected modules may include: commodity portrait data and commodity sorting rules corresponding to a plurality of candidate commodities. The product sort rules are used to describe the weight of the product representation data and the weight of the user representation data. The product representation data of each candidate product is used to describe characteristic information of each candidate product.
In some embodiments, the product portrait data of each candidate product is a multidimensional feature obtained by performing feature extraction on business data of the candidate product. The business data includes business statistics information related to the commodity, such as the order quantity of the commodity, the user attention quantity of the commodity, the click quantity, the visit quantity and other business contents. The product representation data may include a plurality of product characteristic items, for example, at least some of product characteristic items including a product number, a product name, a product grade classification, a product brand, a time to put in a counter, whether new products are available, a sales mode (self-owned or third-party merchant), a product detail page access amount, a product attention amount, a product sharing amount, a product good evaluation amount, a product bad evaluation amount, a price band in which the product is located, a product sales amount of approximately 3 days, a product sales amount of approximately 7 days, a product sales amount of approximately 15 days, a product sales amount of approximately 30 days, a product order conversion rate, a return rate, and a business index value may be included. The service index value may be a weighted sum of a plurality of product feature items in the product portrait data. For example, the business index value may be a weighted sum of a plurality of behavior characteristics corresponding to the commodity (each behavior characteristic is a commodity characteristic item), and the business index value may reflect an activity condition of the commodity.
In some embodiments, the user representation data may be, for example, user characteristic information determined from user identity information and a user historical operating record. User profile data may include, for example, a user account number, a user location, a user gender, an age group, a membership grade, a user income, a marital status, a user registration time, a number of days since a last order was made to date, a category preference, a sales pattern preference (for a private or third party merchant), and so forth.
In step S204, the plurality of candidate products are sorted by the product sorting rule based on the product image data and the user image data, and a first sorting result is obtained. Here, the commodity ranking rule is a ranking rule in which commodity image data and user image data are comprehensively considered.
In step S205, the merchandise to be presented is selected according to the first sort result. In some embodiments, step S206 may select the top ranked item in the first ranking result based on the number of items to be presented.
In summary, the product selection method 200 according to the present application can comprehensively consider the merchandise image data and the user image data, so that the corresponding merchandise to be presented can be selected according to the requirement of each user, and the matching between the presented merchandise and the user characteristics is further improved. In other words, the method 200 may select items to be presented from the choice module based on the user's interests.
Fig. 3 illustrates a schematic diagram of an election method 300 according to some embodiments of the present application. The selection method 300 may be performed by the selection system 130, for example.
As shown in fig. 3, in step S301, business data of a plurality of commodities and data of a plurality of users are acquired. The business data of each commodity comprises business statistical information related to the commodity, and the data of each user comprises user identity information and user operation records.
In some embodiments, the business data of each commodity includes business statistics related to the commodity, such as the commodity content, such as the order quantity of the commodity, the user attention quantity of the commodity, the click quantity, the visit quantity, and the like. Here, the service data may be acquired from each service system of the e-commerce platform.
In some embodiments, the user identity information may be user gender, age group, member rating, user income, marital status, user registration time, and the like. The user operation record refers to historical operation records of browsing, paying attention, placing orders, commenting and the like of the user on the commodity. Step S301 may acquire a user operation record from a user operation log, for example.
In some embodiments, the e-commerce platform may generate an operation log data each time a user performs an operation on a web page (e.g., clicks on a product, visits a page, clicks on a button, etc.). The data content of the user operation log comprises the following steps: the method comprises the contents of a current page address, a last page address, a site number, a client IP, a user account, a clicked commodity number, a browser version, an app version, an operating system version, a mobile phone model, operating time and the like.
In step S302, product portrait data corresponding to each product and user portrait data corresponding to each user are determined based on the service data of the plurality of products and the data of the plurality of users. The commodity image data corresponding to each commodity comprises a plurality of commodity characteristic items corresponding to the commodity, and the user image data corresponding to each user comprises a plurality of user characteristic items corresponding to the user.
In some embodiments, the merchandise representation data may include, for example, at least a portion of merchandise characteristics items including merchandise number, merchandise name, merchandise class classification, merchandise brand, time to put on counter, whether new merchandise is available, sales pattern (self-owned or third party merchant), merchandise detail page visit, merchandise concern, merchandise share, merchandise goodness, merchandise badness, merchandise price band, merchandise sales amount of approximately 3 days, merchandise sales amount of approximately 7 days, merchandise sales amount of approximately 15 days, merchandise sales amount of approximately 30 days, merchandise order conversion rate, return rate, and business index value. The business index value is a weighted sum of a plurality of commodity feature items in the commodity portrait data. For example, the business index value may be a weighted sum of a plurality of behavior characteristics corresponding to the commodity, and the business index value may reflect the activity condition of the commodity. The business metric value may also be referred to as a commercial Business Intelligence (BI) score.
In some embodiments, the traffic indicator value may be calculated according to the following:
the business index value is commodity feature item 1, commodity feature item 2, commodity feature item 3, … and commodity feature item N, wherein the commodity feature item and the weight can be adjusted as required, and all weights are added to be 1. Such as: business index value is commodity click quantity, click weight, commodity order quantity, order weight, commodity access quantity, access weight, commodity attention quantity and attention weight
In some embodiments, user representation data may include, for example, a user account number, a user's locale, a user gender, an age group, a membership level, a user income, a marital status, a user registration time, a number of days since a last order was made to today, a category preference, a sales pattern preference (for a self-owned or third party merchant), and so forth.
In step S303, the product image data of the plurality of products is stored in the product pool. In some embodiments, the pool of items may include item information for each item in addition to item representation data for each item. Here, the commodity information is commodity contents for displaying on a commodity page.
In step S304, user image data of a plurality of users is stored in a user image library.
In some embodiments, the pool of items and the user imagery library may be stored in one or more storage nodes. Each storage node is a server node of the election system 130 for storing data. The server node may store the data in a storage manner such as a database.
In step S305, one or more option modules are created, and a product screening rule and a product sorting rule corresponding to each option module are determined. In some embodiments, the option system 130 may create the option module in response to a creation operation by a manager at the terminal device. The selection system 130 may determine the commodity screening rules and the commodity sorting rules according to configuration operations of the administrator. The commodity screening rule is used for selecting the alternative commodities corresponding to the commodity selection module from the commodity library. And the commodity sequencing rule is used for sequencing the alternative commodities corresponding to the commodity selection module according to the user portrait data and the commodity portrait data. The product sort rule may describe, for example, a weight of a product feature item in the product representation data and a weight of a user feature item in the user representation data. Thus, the commodity ranking rule may take into account the characteristics of the user representation data and the commodity representation data in combination.
In some embodiments, for any one option module, step S305 may also configure a white list and a black list of items for that option module. Here, the item blacklist refers to a list of items that are not suitable for presentation to the user. The item white list refers to a list of items that are preferentially presented to the user.
In step S306, a plurality of candidate commodities corresponding to each option module are screened out according to the commodity screening rule of each option module and the commodity image data in the commodity pool. In some embodiments, the options system 130 may store the data for each option module in an option library.
In some embodiments, the goods filtering rule may include one or more filtering conditions and the number of candidate goods. Here, one filtering condition may be a restriction condition for one product feature item in the product representation data. For example, one item feature item in the item image data is an order amount of an item, and a filtering condition corresponding to the order amount of the item is, for example, an order amount of 1000. For another example, one product feature item in the product image data is a product click rate, and the screening condition corresponding to the product click rate is, for example, that the click rate reaches 10000 times. The number of the alternative goods can determine the size of the alternative goods in the selection module.
In step S307, a product acquisition request is received, and an identifier of the option module is acquired from the product acquisition request. In some embodiments, the merchandise acquisition request may include an identification of the pick module. In some embodiments, the merchandise acquisition request may include an identification of the pick module and an identification of the user. Here, the user identification is, for example, identification information such as a user account.
In step S308, in response to the product acquisition request, user portrait data is acquired. In some embodiments, upon obtaining the user identifier from the merchandise acquisition request, step S308 may obtain user portrait data corresponding to the user identifier from a user portrait repository.
When the user identification is not acquired from the merchandise acquisition request, step S308 may acquire default user portrait data from the user portrait repository and use it as user portrait data. Here, the default user representation data is general representation data stored in a user representation library. Here, the general portrait data may describe a common preference of general users.
In step S309, an option module is selected from the option library according to the identifier of the option module.
In step S310, the plurality of candidate products are sorted by the product sorting rule based on the product image data and the user image data, and a first sorting result is obtained. Here, the commodity ranking rule is a ranking rule in which commodity image data and user image data are comprehensively considered. In some embodiments, the merchandise sort rules are used to describe weights of merchandise characteristic items in the merchandise representation and weights of user characteristic items in the user representation.
In step S311, the goods to be presented are selected according to the first sorting result. In some embodiments, step S206 may select the top ranked item in the first ranking result based on the number of items to be presented.
In some embodiments, step S302 may be implemented as method 400.
As shown in fig. 4, in step S401, the service data of the plurality of products and the data of the plurality of users are subjected to feature extraction by the user image model, and user image data corresponding to each user is obtained. Here, the user figure model may be any of various models that can be modeled based on user data and business data of a product, such as a linear regression model and a deep learning model. The user profile model may represent user demand attributes such as product preferences of the user.
In step S402, feature extraction is performed on the business data of the plurality of products and the data of the plurality of users by using a product representation model, thereby obtaining product representation data corresponding to each product. Here, the product image model may be any of various machine learning models suitable for extracting the product feature, and the present application is not limited thereto.
In summary, the product selection method 400 according to the present application can determine user representation data and commodity representation data (i.e., determine user characteristics and commodity characteristics) according to the user data and the commodity business data. On this basis, the commodity selection method 400 of the present application may determine the candidate commodities of each commodity selection module according to the configured commodity screening rule. Here, the candidate product of each selection module is selected based on the product image data, whereby the first product screening can be performed for the presentation area of the product page. Further, in response to the goods acquisition request, the selection method 400 may perform a second goods screening on the candidate goods in the selected selection module. Here, the product selection method 400 may perform the product screening (i.e., obtain the first sorting result) by comprehensively considering the product portrait data and the user portrait data through the second product screening, so that the matching between the presented product and the user characteristics may be improved through the two product screening, and the product may be accurately selected according to the user interests.
In some embodiments, step S306 may be implemented as method 500.
As shown in fig. 5, in step S501, for any one of the option modules, the commodities corresponding to the commodity image data in the commodity pool are screened according to the screening condition corresponding to the option module, and a first screening result is obtained.
In step S502, the commodities in the first screening result are sorted according to the service index value, so as to obtain a second sorting result.
In some embodiments, step S502 may include steps S5021 and S5022. In step S5021, the service index value corresponding to the commodity belonging to the commodity white list in the first screening result is set as a maximum value, and the commodity belonging to the commodity black list in the first screening result is removed, so as to obtain a second screening result. Here, the maximum value is an upper limit value of the traffic index value. In step S5022, the commodities in the second screening result are sorted according to the service index value, so as to obtain a second sorting result.
In step S503, the plurality of candidate products are selected from the second ranking result according to the number of candidate products of the selection module.
In summary, the method 500 may select an alternative commodity corresponding to an option module from the commodity pool according to the commodity screening rule of the option module. The selection module can store commodity portrait data corresponding to the alternative commodities. The selection library is used for storing a plurality of selection modules.
In some embodiments, step S310 may be implemented as method 600.
As shown in fig. 6, in step S601, a predicted value of the transaction rate of a candidate product corresponding to any one of the product image data is determined according to a product sort rule based on the product image data and the user image data. Here, the predicted value of the rate of interest of a candidate product may represent the possibility that the user finally purchases the candidate product. For example, the candidate product is B, and the user image data is image data of the user A.
The transaction rate predicted value of the candidate commodity B is the business index value of B, the weight of the business index value + the user A image dimension 1, the dimension 1 weight + the user A image dimension 2, the dimension 2 weight + … … + the user A image N, the dimension N weight, wherein the weight of each dimension of the commodity image data and the user image data can be maintained in the configuration process of the commodity sequencing rule.
In step S602, according to the predicted value of the transaction rate of the candidate product corresponding to each product portrait data in the option module, the candidate products corresponding to the product portrait data in the set are sorted to obtain a first sorting result. In summary, the method 600 may sort the candidate merchandise with the merchandise representation data and the user representation data, so that the first sorting result may accurately reflect the user's requirement. That is, the more top the ranking, the more likely the items of interest to the user.
FIG. 7 illustrates a schematic diagram of an options system 130 according to some embodiments of the present application.
As shown in FIG. 7, options system 130 may include a configuration management platform 710, a goods services platform 720, a data storage platform 730, and a data collection platform 740. Here, in the embodiment of the present application, the business functions of the configuration management platform 710, the commodity service platform 720, the data storage platform 730, and the data collection platform 740 may be deployed in one server, or each platform may be deployed in an independent server.
Data storage platform 730 may include a pool of items 731, a selection library 732, and a user representation library 733. The data collection platform 740 may include a data collection unit 741, a data analysis unit 742, and a push unit 743.
The data collection unit 741 is configured to acquire business data of a plurality of commodities and data of a plurality of users. The business data of each commodity comprises business statistical information related to the commodity, and the data of each user comprises user identity information and user operation records.
The data analysis unit 742 is configured to determine commodity portrait data corresponding to each commodity and user portrait data corresponding to each user according to the business data of the commodities and the data of the users. The commodity image data corresponding to each commodity comprises a plurality of commodity characteristic items corresponding to the commodity, and the user image data corresponding to each user comprises a plurality of user characteristic items corresponding to the user.
In some embodiments, the data analysis unit 742 may include a user portrait model 7421 and a merchandise portrait model 7422. The user portrait model 7421 is used to perform feature extraction on the business data of the plurality of commodities and the data of the plurality of users, and obtain user portrait data corresponding to each user. The product representation model 7422 is used to extract the characteristics of the business data of the plurality of products and the data of the plurality of users, and obtain product representation data corresponding to each product.
The push unit 743 stores product image data of each of a plurality of products in the product pool 731, and stores user image data of each of a plurality of users in the user image library 733.
In some embodiments, options management platform 710 may include an options management unit 711 and an options execution unit 712. The option management unit 711 is configured to create a plurality of option modules, and determine a commodity screening rule and a commodity sorting rule corresponding to each option module. The optional product execution unit 712 is configured to screen out a plurality of optional products corresponding to each optional product module according to the product screening rule of each optional product module and the product portrait data in the product pool 731.
In some embodiments, the merchandise representation data for each merchandise in the merchandise pool 731 includes a business index value, each business index value being a weighted sum of a plurality of merchandise feature items in the merchandise representation data. The commodity screening rule of each option module comprises the following steps: screening conditions and number of candidate commodities.
For any of the option modules, the option performing unit 712 may perform screening on the commodities corresponding to the commodity image data in the commodity pool according to the screening condition corresponding to the option module, so as to obtain a first screening result. On this basis, the selection execution unit 712 may rank the commodities in the first screening result according to the service index value, so as to obtain a second ranking result. The item selection execution unit 712 may select the plurality of candidate items from the second sorting result according to the number of candidate items of the item selection module.
In some embodiments, the option management platform 710 may further include a black and white list management unit configured to configure a white list and a black list of the goods in each option module. Accordingly, each option module may further include: a white list of goods and a black list of goods. The selection executing unit 712 may set a service index value corresponding to the commodity belonging to the commodity white list in the first screening result as a maximum value, and reject the commodity belonging to the commodity black list in the first screening result to obtain a second screening result. And sorting the commodities in the second screening result according to the service index value, and obtaining a second sorting result by the selection executing unit 712.
In some embodiments, the data collection platform 740 may continuously collect business data for the goods and data for the user. The data collection platform updates the product representation data in product pool 731 and the user representation data in user representation library 733. Configuration management platform 710 may also include a timed task unit 714. The timed task unit 714 may periodically invoke the choice execution unit 712 to update the merchandise representation data for each choice module in the choice repository 732.
The goods services platform 720 may include a loading unit 721 and a data processing unit 722.
In some embodiments, the data processing unit 722 may receive the item acquisition request and obtain the identification of the option module from the item acquisition request.
The loading unit 721 is configured to obtain user portrait data and select an option module from the option library 732 according to an identifier of the option module in response to the merchandise acquisition request. The selected modules include: and commodity representation data and commodity ordering rules corresponding to the plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity representation data and the weight of the user representation data, the commodity representation data of each candidate commodity is used for describing the feature information of each candidate commodity, and the user representation data is used for describing the feature information of the user.
The data processing unit 733 may sort the plurality of candidate commodities based on the commodity drawing data and the user drawing data, obtain a first sorting result, and select a commodity to be presented based on the first sorting result.
In some embodiments, load unit 721 may include a merchandise load module 7211 and a representation load module 7212. The commodity loading module 7211 is configured to obtain commodity portrait data from the option module corresponding to the identifier in the option library 732 according to the identifier of the option module. Representation loading module 7212 may retrieve user representation data from user representation library 733 based on the user identification when data processing unit 722 retrieves the user identification from the merchandise retrieval request. Representation loading module 7212 may retrieve default user representation data from user representation library 733 as user representation data when user identification is not retrieved by data processing unit 722 from the merchandise retrieval request.
In some embodiments, the choice module further comprises an item ordering rule. The commodity ordering rule is used for describing the weight of the commodity feature items in the commodity portrait data and the weight of the user feature items in the user portrait data. Load unit 721 may also include rule load module 7213. The rule loading module 7213 is configured to obtain a commodity sorting rule from a corresponding option module in the option library 732 according to the identifier of the option module.
For a candidate product corresponding to any one of the product image data, the data processing unit 722 may determine a predicted value of the transaction rate of the candidate product according to the product sort rule based on the any one of the product image data and the user image data. According to the predicted value of the transaction rate of the candidate merchandise corresponding to each merchandise image data, the data processing unit 722 may sort the candidate merchandise corresponding to the merchandise image data in the item selection module to obtain a first sorting result. It should be noted that a more specific embodiment of the selection system 130 in fig. 7 is consistent with the selection method 300, and is not described herein again.
In summary, the selection system 130 according to the present application can determine user representation data and commodity representation data (i.e., determine user characteristics and commodity characteristics) according to the user data and the commodity business data. On this basis, the option system 130 of the present application may determine the candidate goods of each option module according to the configured goods screening rule. Here, the candidate product of each selection module is selected based on the product image data, whereby the first product screening can be performed for the presentation area of the product page. Further, in response to the goods acquisition request, the item selection system 130 may perform a second goods screening on the candidate goods in the selected item selection module. Here, the item selection system 130 may perform item selection (i.e., obtain a first sorting result) by comprehensively considering the item portrait data and the user portrait data through the second item selection, so that the matching between the presented items and the user characteristics may be improved through the two item selections, and further, the items may be accurately selected according to the user interests.
In addition, the method steps described in this application may be implemented by hardware, for example, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers, embedded microcontrollers, and the like, in addition to data processing programs. Such hardware capable of implementing the methods described herein may also constitute the present application.
The above description is only exemplary of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the present application should be included in the scope of the present application.
Claims (20)
1. A method of selecting an item, comprising:
receiving a commodity acquisition request, and acquiring an identifier of a selection module from the commodity acquisition request;
responding to the commodity acquisition request, and acquiring user portrait data;
selecting the option module from an option library according to the identifier of the option module, wherein the option library is used for storing a plurality of option modules, and the selected module comprises: commodity portrait data and commodity ordering rules corresponding to a plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity portrait data and the weight of the user portrait data;
based on the commodity portrait data and the user portrait data, sequencing the plurality of candidate commodities by utilizing the commodity sequencing rule to obtain a first sequencing result; and
and selecting the commodities to be presented according to the first sequencing result.
2. The method of claim 1, wherein said obtaining user representation data in response to said merchandise acquisition request comprises:
when a user identifier is acquired from the commodity acquisition request, acquiring the user portrait data corresponding to the user identifier from a user portrait library, wherein the user portrait library is used for storing the user portrait data corresponding to a plurality of user identifiers;
and when the user identification is not acquired from the commodity acquisition request, acquiring default user portrait data from the user portrait library and using the default user portrait data as the user portrait data.
3. The method of claim 2, further comprising:
the method comprises the steps of obtaining business data of a plurality of commodities and data of a plurality of users, wherein the business data of each commodity comprises business statistical information related to the commodity, and the data of each user comprises user identity information and user operation records;
determining commodity portrait data corresponding to each commodity and user portrait data corresponding to each user according to the business data of the commodities and the data of the users, wherein the commodity portrait data corresponding to each commodity comprises a plurality of commodity characteristic items corresponding to the commodity, and the user portrait data corresponding to each user comprises a plurality of user characteristic items corresponding to the user;
storing commodity image data of a plurality of commodities into a commodity pool;
and storing user image data of a plurality of users into the user image library.
4. The method of claim 3, wherein determining merchandise representation data corresponding to each merchandise and user representation data corresponding to each user based on the business data for the plurality of merchandise and the data for the plurality of users comprises:
performing feature extraction on the service data of the plurality of commodities and the data of the plurality of users through a user portrait model to obtain user portrait data corresponding to each user;
and performing feature extraction on the service data of the plurality of commodities and the data of the plurality of users through a commodity portrait model to obtain commodity portrait data corresponding to each commodity.
5. The method of claim 3, wherein the commodity ordering rules are used to describe weights of commodity feature items in the commodity representation and weights of user feature items in the user representation; the ranking the plurality of candidate commodities based on the commodity portrait data and the user portrait by using the commodity ranking rule to obtain a first ranking result, comprising:
for a candidate commodity corresponding to any commodity portrait data, determining a predicted value of a trading rate of the candidate commodity according to the commodity sorting rule based on the commodity portrait data and the user portrait data;
and sorting the alternative commodities corresponding to the commodity portrait data in the commodity selection module according to the transaction rate predicted value of the alternative commodity corresponding to each commodity portrait data to obtain the first sorting result.
6. The method of claim 5, further comprising:
creating one or more option modules, and determining a commodity screening rule and a commodity sequencing rule corresponding to each option module;
and screening a plurality of alternative commodities corresponding to each option module according to the commodity screening rule of each option module and the commodity image data in the commodity pool.
7. The method of claim 6, wherein the merchandise representation data for each merchandise in the pool of merchandise includes a business index value, the business index value being a weighted sum of a plurality of merchandise feature items in the merchandise representation data; the commodity portrait screening rule of each option module comprises the following steps: screening conditions and the number of alternative commodities;
the screening of a plurality of alternative commodities corresponding to each option module according to the commodity screening rule of each option module and the commodity image data in the commodity pool comprises the following steps:
for any option module, screening commodities corresponding to the commodity image data in the commodity pool according to screening conditions corresponding to the option module to obtain a first screening result;
sorting the commodities in the first screening result according to the service index value to obtain a second sorting result;
and selecting the plurality of candidate commodities from the second sequencing result according to the number of the candidate commodities of the commodity selection module.
8. The method of claim 6, wherein each of the option modules further comprises: a white list and a black list of commodities; the sorting the commodities in the first screening result according to the service index value to obtain a second sorting result includes:
setting the service index value corresponding to the commodities belonging to the commodity white list in the first screening result as a maximum value, and eliminating the commodities belonging to the commodity black list in the first screening result to obtain a second screening result;
and sorting the commodities in the second screening result according to the service index value to obtain a second sorting result.
9. An item selection system, comprising:
the data processing unit is used for receiving a commodity obtaining request and obtaining the identification of the option module from the commodity obtaining request;
a loading unit, configured to, in response to the commodity acquisition request, acquire user portrait data and select the option module from an option library according to an identifier of the option module, where the option library is configured to store a plurality of option modules, and the selected module includes: commodity portrait data and commodity ordering rules corresponding to a plurality of candidate commodities, wherein the commodity ordering rules are used for describing the weight of the commodity portrait data and the weight of the user portrait data;
wherein the data processing unit is further configured to: and sorting the plurality of candidate commodities by using the commodity sorting rule based on the commodity portrait data and the user portrait data to obtain a first sorting result, and selecting the commodities to be presented according to the first sorting result.
10. The selection system of claim 9, wherein the loading unit comprises:
the commodity loading module is used for acquiring commodity portrait data from a commodity module corresponding to the identification in a commodity library according to the identification of the commodity module, wherein the commodity library is used for storing a plurality of commodity modules corresponding to the identifications;
an image loading module for: when a user identifier is acquired from the commodity acquisition request, acquiring the user portrait data from a user portrait library according to the user identifier, wherein the user portrait library is used for storing user portrait data corresponding to a plurality of user identifiers; and when the user identification is not acquired from the commodity acquisition request, acquiring default user portrait data from the user portrait library and using the default user portrait data as the user portrait data.
11. The selection system of claim 10, further comprising:
the data collection unit is used for acquiring the business data of a plurality of commodities and the data of a plurality of users, wherein the business data of each commodity comprises business statistical information related to the commodity, and the data of each user comprises user identity information and user operation records;
the data analysis unit is used for determining commodity portrait data corresponding to each commodity and user portrait data corresponding to each user according to the service data of the commodities and the data of the users, wherein the commodity portrait data corresponding to each commodity comprises a plurality of commodity characteristic items corresponding to the commodity, and the user portrait data corresponding to each user comprises a plurality of user characteristic items corresponding to the user;
and the pushing unit is used for storing the commodity image data of each of the commodities into a commodity pool and storing the user image data of each of the users into the user image library.
12. The selection system of claim 11, wherein the data analysis unit comprises:
the user portrait model is used for carrying out feature extraction on the service data of the commodities and the data of the users to obtain user portrait data corresponding to each user;
and the commodity portrait model is used for performing feature extraction on the business data of the commodities and the data of the users to obtain commodity portrait data corresponding to each commodity.
13. The system of claim 11, wherein the merchandise ranking rules are used to describe weights of merchandise characteristic items in the merchandise representation data and weights of user characteristic items in the user representation data;
the loading unit further comprises a rule loading module used for acquiring commodity sequencing rules from corresponding option modules in the option library according to the identification of the option modules;
the data processing unit sorts the plurality of candidate commodities by using the commodity sorting rule based on the commodity portrait data and the user portrait in the following way to obtain a first sorting result:
for a candidate commodity corresponding to any commodity portrait data, determining a trading rate predicted value of the candidate commodity according to a commodity sorting rule based on the commodity portrait data and the user portrait data;
and sorting the alternative commodities corresponding to the commodity portrait data in the alternative commodities according to the transaction rate predicted value of the alternative commodity corresponding to each commodity portrait data in the alternative commodities to obtain a first sorting result.
14. The selection system of claim 13, further comprising:
the system comprises an option management unit, a commodity sorting unit and a commodity sorting unit, wherein the option management unit is used for creating a plurality of option modules and determining a commodity screening rule and a commodity sorting rule corresponding to each option module;
and the selection execution unit is used for screening a plurality of alternative commodities corresponding to each selection module according to the commodity screening rule of each selection module and the commodity image data in the commodity pool.
15. The system of claim 14, wherein the merchandise representation data for each merchandise in the pool of merchandise includes a business index value, each business index value being a weighted sum of a plurality of merchandise feature items in the merchandise representation data; the commodity screening rule of each option module comprises the following steps: screening conditions and the number of alternative commodities;
the commodity selection execution unit screens out a plurality of alternative commodities corresponding to each commodity selection module according to the commodity screening rule of each commodity selection module and the commodity image data in the commodity pool in the following mode:
for any option module, screening commodities corresponding to the commodity image data in the commodity pool according to screening conditions corresponding to the option module to obtain a first screening result;
sorting the commodities in the first screening result according to the service index value to obtain a second sorting result;
and selecting the plurality of candidate commodities from the second sequencing result according to the number of the candidate commodities of the commodity selection module.
16. The option system of claim 15, wherein each option module further comprises: a white list and a black list of commodities; the selected product execution unit sorts the commodities in the first screening result according to the service index values in the following mode to obtain a second sorting result:
setting the service index value corresponding to the commodities belonging to the commodity white list in the first screening result as a maximum value, and eliminating the commodities belonging to the commodity black list in the first screening result to obtain a second screening result;
and sorting the commodities in the second screening result according to the service index value to obtain a second sorting result.
17. The system of claim 16, further comprising a blacklist and whitelist management unit to configure a whitelist and a blacklist of items in each option module.
18. The system of claim 14, further comprising a timed task unit to periodically invoke the pick execution unit to update the merchandise representation data for each pick module in the pick library.
19. An item selection system, comprising:
a processor;
a memory; and
one or more programs stored in the memory and configured to be executed by the processor, the one or more programs including instructions for performing the method of any of claims 1-8.
20. A storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910243207.4A CN111738785A (en) | 2019-03-28 | 2019-03-28 | Product selection method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910243207.4A CN111738785A (en) | 2019-03-28 | 2019-03-28 | Product selection method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738785A true CN111738785A (en) | 2020-10-02 |
Family
ID=72645872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910243207.4A Pending CN111738785A (en) | 2019-03-28 | 2019-03-28 | Product selection method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738785A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561642A (en) * | 2020-12-16 | 2021-03-26 | 中国平安人寿保险股份有限公司 | Multidimensional product comparison analysis method and device, computer equipment and storage medium |
| CN112613953A (en) * | 2020-12-29 | 2021-04-06 | 北京环球国广媒体科技有限公司 | Commodity selection method, system and computer readable storage medium |
| CN113077305A (en) * | 2021-03-23 | 2021-07-06 | 上海尊溢商务信息咨询有限公司 | Page processing method, system, electronic equipment and storage medium |
| CN113434770A (en) * | 2021-07-08 | 2021-09-24 | 广州康乾信息科技有限公司 | Business portrait analysis method and system combining electronic commerce and big data |
| CN113763111A (en) * | 2021-02-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article collocation method, device and storage medium |
| CN113822737A (en) * | 2021-03-30 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information pushing method and device, computer system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201220231A (en) * | 2010-11-15 | 2012-05-16 | Alibaba Group Holding Ltd | capable of more precisely recommending product information which a user possibly needs |
| CN106709741A (en) * | 2015-07-22 | 2017-05-24 | 中兴通讯股份有限公司 | Commodity recommendation method and system |
| CN109118283A (en) * | 2018-08-10 | 2019-01-01 | 云南数金科技有限公司 | Precision marketing service system based on big data |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
| CN109493177A (en) * | 2018-11-12 | 2019-03-19 | 深圳云行智能科技有限公司 | A kind of intelligent Matching SKU selection method and its system and storage medium |
-
2019
- 2019-03-28 CN CN201910243207.4A patent/CN111738785A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201220231A (en) * | 2010-11-15 | 2012-05-16 | Alibaba Group Holding Ltd | capable of more precisely recommending product information which a user possibly needs |
| CN106709741A (en) * | 2015-07-22 | 2017-05-24 | 中兴通讯股份有限公司 | Commodity recommendation method and system |
| CN109118283A (en) * | 2018-08-10 | 2019-01-01 | 云南数金科技有限公司 | Precision marketing service system based on big data |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
| CN109493177A (en) * | 2018-11-12 | 2019-03-19 | 深圳云行智能科技有限公司 | A kind of intelligent Matching SKU selection method and its system and storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561642A (en) * | 2020-12-16 | 2021-03-26 | 中国平安人寿保险股份有限公司 | Multidimensional product comparison analysis method and device, computer equipment and storage medium |
| CN112561642B (en) * | 2020-12-16 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Multi-dimensional product comparison analysis method and device, computer equipment and storage medium |
| CN112613953A (en) * | 2020-12-29 | 2021-04-06 | 北京环球国广媒体科技有限公司 | Commodity selection method, system and computer readable storage medium |
| CN113763111A (en) * | 2021-02-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article collocation method, device and storage medium |
| CN113077305A (en) * | 2021-03-23 | 2021-07-06 | 上海尊溢商务信息咨询有限公司 | Page processing method, system, electronic equipment and storage medium |
| CN113077305B (en) * | 2021-03-23 | 2024-03-29 | 上海尊溢商务信息咨询有限公司 | Page processing method, system, electronic device and storage medium |
| CN113822737A (en) * | 2021-03-30 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information pushing method and device, computer system and storage medium |
| CN113434770A (en) * | 2021-07-08 | 2021-09-24 | 广州康乾信息科技有限公司 | Business portrait analysis method and system combining electronic commerce and big data |
| CN113434770B (en) * | 2021-07-08 | 2022-09-09 | 上海识致信息科技有限责任公司 | Business portrait analysis method and system combining electronic commerce and big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738785A (en) | Product selection method, system and storage medium | |
| US11995112B2 (en) | System and method for information recommendation | |
| WO2019149145A1 (en) | Compliant report class sorting method and apparatus | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| US9578135B2 (en) | Method of identifying remote users of websites | |
| JP6911603B2 (en) | How to generate predictive models for the categories of facilities visited by users, programs, server equipment, and processing equipment | |
| US11558324B2 (en) | Method and system for dynamically generating a card | |
| US11232522B2 (en) | Methods, systems and techniques for blending online content from multiple disparate content sources including a personal content source or a semi-personal content source | |
| CN105975537A (en) | Sorting method and device of application program | |
| US10078706B2 (en) | Information processing apparatus, information processing method, information processing program, and recording medium storing thereon information processing program which classifies and displays a plurality of elements constituting a list on a plurality of pages | |
| JP7166116B2 (en) | Information processing device, information processing method, and program | |
| US20180204168A1 (en) | Shipping preferences population systems and related methods | |
| CN113032668A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN117235586B (en) | Hotel customer portrait construction method, system, electronic equipment and storage medium | |
| WO2017062256A1 (en) | Method and system for generating a card based on intent | |
| US10929905B2 (en) | Method, system and machine-readable medium for online task exchange | |
| CN109727056B (en) | Financial institution recommendation method, device, storage medium and device | |
| CN111078998A (en) | Information retrieval method, information retrieval device, storage medium and server | |
| CN108073609B (en) | Page display method and device | |
| CN112487277B (en) | Data distribution method and device, readable storage medium and electronic equipment | |
| KR102049507B1 (en) | System for providing consulting service for communication products and method thereof | |
| CN112488854A (en) | Service manager personalized recommendation method and related equipment | |
| KR101932814B1 (en) | System and method for providing word-information | |
| CN111553749A (en) | Activity push strategy configuration method and device | |
| JP7330726B2 (en) | MODEL GENERATING DEVICE, MODEL GENERATING METHOD, AND PROGRAM |
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 |