WO2016157138A1 - Système et procédé de recommandation de produits - Google Patents

Système et procédé de recommandation de produits Download PDF

Info

Publication number
WO2016157138A1
WO2016157138A1 PCT/IB2016/051867 IB2016051867W WO2016157138A1 WO 2016157138 A1 WO2016157138 A1 WO 2016157138A1 IB 2016051867 W IB2016051867 W IB 2016051867W WO 2016157138 A1 WO2016157138 A1 WO 2016157138A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
tags
users
product
percentage
Prior art date
Application number
PCT/IB2016/051867
Other languages
English (en)
Inventor
Santosh Prabhu
Palash PATIL
Muralidhar Rajan
Original Assignee
Santosh Prabhu
Patil Palash
Muralidhar Rajan
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Santosh Prabhu, Patil Palash, Muralidhar Rajan filed Critical Santosh Prabhu
Publication of WO2016157138A1 publication Critical patent/WO2016157138A1/fr

Links

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

Definitions

  • the present invention relates to a recommendation system and method. More particularly, the present invention relates to recommendation of a product based on tags. BACKGROUND
  • the recommendation systems are a type of information filtering systems that recommend products available in e-shops, entertainment items (books music, videos, Video on Demand, books, news, images, events etc.) or people (e.g. on dating sites) that are likely to be of interest to the user.
  • the recommendation systems have been used to help users by providing recommendations of items and products that might interest them.
  • the existing recommendation systems suffer from the following drawbacks like (i) lack of ease in short listing within the product category i.e., with a wide range of options available in each product category of interest, it is hard for an average user to narrow down to a smaller, relevant set of options, (ii) contradicting information from multiple available sources like Facebook, blogs, review sites, ecommerce sites when making research related to purchase of the product, (iii) do not provide a hint/tip about why a particular product is recommended to the user i.e., user does not get to know the relevancy behind the recommendation, thus possibly leaving some doubt in the user's mind about the recommendation, (iv) do not analyse various elements of a user's life like interests, profession, hobbies and the like and map them to relevant aspects/sub-aspects of a product before recommending a product, (v) do not take into account the usage of the existing product, and analyse the usage of aspects/sub-
  • the recommendation systems mostly (i) rely upon the previous product purchase history or previous product viewing history, (ii) rely upon the product specification and do not go in detail about understanding aspects/ sub aspects of a product and characterizing the product, (iii) extracts few attributes from a user profile (e.g. Facebook), finding the similarity in their user profile database and recommend the products which are purchased by similar user profiles.
  • a user profile e.g. Facebook
  • the present invention provides a method for recommendation of products based on tags.
  • the method includes receiving user profile information and product information , generating first tags in relation to user profile automatically or receiving the first tags from the each user manually, generating second tags automatically or receiving the second tags from the each user manually, determining a first similarity and a second similarity index with a plurality of other users, monitoring the actions of the each user in response to the recommendations, and providing the information for the each user to clearly know the criteria for the recommendations.
  • the present invention provides a server for recommendation of products based on tags.
  • the server includes a first tag generation module, a second tag generation module, a recommendation module, and recommendation-monitoring module.
  • the first tag generation module is configured to generate and associate a plurality of tags, such as text strings, uniquely for the each user.
  • the second tag generation module is configured to generate and associate a plurality of tags, for the each product owned by the each user.
  • the recommendation module is configured for recommending one or more products for the each user.
  • the recommendation-monitoring module is configured for ensuring that the recommendation module involves a closed loop mechanism.
  • Figure 1 illustrates a product recommendation method 100, in accordance with one or more embodiments of the present invention.
  • FIG. 2 illustrates a product recommendation system 200, in accordance with embodiment of the present invention.
  • Figure 3 illustrates the constructional details of a product/device 300 owned by the user such as smart phone, in accordance with the embodiment of the present invention.
  • Figure 4 illustrates a unit 400 implemented in the server, said unit interacting with the product owned by user(s) in accordance with the embodiment of the present invention.
  • FIG. 5 illustrates a typical hardware configuration of a server 500, which is representative of a hardware environment for implementing the present invention.
  • any terms used herein such as but not limited to “includes,” “comprises,” “has,” “consists,” and grammatical variants thereof do NOT specify an exact limitation or restriction and certainly do NOT exclude the possible addition of one or more features or elements, unless otherwise stated, and furthermore must NOT be taken to exclude the possible removal of one or more of the listed features and elements, unless otherwise stated with the limiting language “MUST comprise” or “NEEDS TO include.”
  • Figure 1 illustrates a product recommendation method 100, in accordance with an embodiment of the present invention.
  • the method comprises assigning pre-defined weights to one or more first parameters and assigning pre-defined weights to one or more second parameters.
  • the weights are pre-defined in the server and may be altered.
  • the method comprises generating and associating one or more first tags to each user, each first tag corresponding to a first parameter.
  • the one or more first tags may be inputted by the user also.
  • the method comprises generating and associating one or more second tags to the each user, each second tag corresponding to a second parameter. The one or more may be inputted by the user.
  • the first parameters include one or more: (i) Demographic information of a user, (ii) characterization of a user, (iii) common interests of a user associated with different products,
  • Demographic information of a user includes age, gender, location and the likes of the user.
  • the first tags in relation to demographic information may be #male, #bangalore.
  • the said information may be inputted by the user or may be fetched by a server in the system from one or more social media accounts of the user.
  • Characterization of a user-The characterization of the user includes information such as profession, interests and the likes of the user.
  • the first tags in relation to said parameter may be #reporter, #traveller, #audiophile and so on.
  • the said information may be inputted by the user or may be fetched by a server in the system from one or more social media accounts of the user.
  • Common interests of a user associated with different products could be derived from a combination of "Product" information based on specific key features/key aspects ⁇ the term features and aspects have been used interchangeably for the purposes of the invention) for and sub-features/sub-aspects ⁇ the term sub-features and sub-aspects have been used interchangeably for the purposes of the invention) of the product owned by the user, previous products purchase history, if available in the system, connected singular or plurality of products to the product owned by the user and the like.
  • the first tags in relation to said parameter may be in relation to features and sub-features of the product owned by the user. For example, in the case of a product i.e.
  • the client would identify that the camera consists of a Sony Exmor sensor, the handycam connected to the smartphone also consists of a Sony Exmor sensor and the previous smartphone also had a Sony Exmor sensor, the associated tags could be #sonyfan, #sonyexmorfan and so on.
  • Product usage information for specific key aspects and sub aspects of the product could be monitored by the system.
  • the system would monitor information such as number of games installed, frequency of usage of the games and associated tag could be #gamer.
  • the client could monitor the usage of camera, the number of images clicked in a day, the specific settings of the camera and information extracted from the image metadata.
  • the first tags in relation to said parameter could be #selfielover, #lowlightphotographer and so on. e.
  • Activities of the user in system The activities of the user with the system, which is recorded by a server, such as frequent rating and reviews for any products, response to queries in discussion forums associated with any product, combined with associated feedback from other users in the system by means of upvotes and the like.
  • a server such as frequent rating and reviews for any products, response to queries in discussion forums associated with any product, combined with associated feedback from other users in the system by means of upvotes and the like.
  • the first tags in relation to said parameter could be
  • the second parameters include one or more: (i) Product(s) owned by the user and key aspects and sub aspects of said product(s), and (ii) Product tags updated by the owner.
  • the said second parameters and examples of second tags, corresponding to said second parameter, generated for each user by the system are discussed below.
  • Product(s) owned by the user and key aspects and sub aspects of said products - Information in relation to product such as model of the product, brand of the product and the likes. Information in relation to key features and/or sub-features such as camera, performance of camera in low light, battery usage and other features/sub- features . The said information is automatically extracted by the system from the product.
  • the products would include the "Product”, as well as singular or plurality of products, connected to this "Product", which acts as the gateway.
  • the associated tags could be #nexus5, #dual speaker and so on.
  • the associated tags could be #gaming, #selfie, #performance and the like.
  • the method comprises comparing one or more first tags associated with a first user with one or more first tags associated with one or more further users.
  • first user means any registered user to whom the products are recommended.
  • further user(s) means all the registered users in the system except the said "first user”.
  • the method comprises determining a first similarity index, said first similarity index indicating a percentage of weighted matching first tags corresponding to each further user with that of said first user.
  • the percentage of weighted matching first tags is determined based on (i) number of matching first tags the each further user has with said first user, and (ii) weight assigned to the first parameter corresponding to each matching first tag.
  • other key parameters specific to the user may also be taken as inputs for arriving at the first similarity index. This could include information such as, if any user in the system is a friend of the "User", which could be known from contact list, social media such as Facebook and the like.
  • the method comprises selecting a first set of users from said one or more further user(s), said first set of users having a pre-determined percentage of weighted matching first tags.
  • the pre-determined percentage may be a single percentage or a range of percentage.
  • the one or more further users in the system who have the highest percentage of weighted matching tags with the first user have a higher user similarity index and are grouped together as the first set of users.
  • the said first set of users may be associated with a unique group identity.
  • the method comprises comparing one or more second tags associated with the first user with one or more second tags associated with said first set of users.
  • the method comprises determining a second similarity index, said second similarity index indicating a percentage of weighted matching second tags corresponding to each user of said first set of users with that of said first user.
  • the percentage of weighted matching second tags is determined based on (i) number of matching second tags each user of said first set of users has with said first user, and (ii) weight assigned to the second parameters corresponding to each matching second tag.
  • other key parameters specific to the product may also be taken as inputs for arriving at a product recommendation list. For example, in the case of smartphone recommendations could include, time since the smartphone was launched, whether the latest version of the software is available, if there is an upgraded version for the same smartphone available from the brand and the like.
  • the method comprises selecting a second set of users, said second set of users having a pre-determined percentage of weighted matching second tags.
  • the pre- determined percentage may be a single percentage or a range of percentage.
  • the method comprises recommending one or more products associated with said second set of users to the first user.
  • the method further comprises transmitting one or more first tags and second tags associated with the said second set of users.
  • the first tags enables the first user to know that the recommendations are from other users with similar interests and the second tags enable the user to identify key aspects of the recommended products as well as the perception about each of these products from other similar users.
  • #selfielover, #audiophile and other tags of a user are referenced by the system to recommend a smartphone which is being used by other users, who also have these 2 tags in their profile. While recommending that phone, the #selfielover and #audiophile tags are also shown to the user. Due to this, the user understands that the recommended phone probably has a good front camera and probably provides good audio experience too. This feature of the present invention allows the user to proceed with the recommended product or reject it clearly knowing if the decision is correct.
  • the method further comprises monitoring one or more purchase activities of said first user, generating, based on identification of purchase of atleast one recommended product, one or more additional first tags for said first user, and generating, based on identification of purchase of the atleast one recommended product, one or more additional second tags for said first user.
  • the new first tags and second tags generated due to purchase of a recommended product will ensure that there exists a closed loop mechanism.
  • the said new tags will be considered by the system while calculating a first similarity index and a second similarity index during next recommendation cycle to the first user. Also, if multiple users within a group purchase a common product based on the recommendations, this information is recorded as a part of the first parameter and considered as an input for future calculation of the first similarity index. It is also important to note that the first similarity index is re-calculated and re-grouping done, if necessary, whenever a new user is added to the system, or the new tags are updated for a specific user.
  • FIG. 2 illustrates a product recommendation system 200, in accordance with the embodiment of the present invention.
  • the system 200 comprises a plurality of users 210.
  • the said plurality of users 210 owns one or more products 220 such as mobile devices, smart phones and the likes.
  • the said plurality of products 220 is connected to one or more servers 240 by means of a communication network 230.
  • Figure 3 illustrates the constructional details of a product/device 300 owned by the user such as smart phone, in accordance with the embodiment of the present invention.
  • the said product 300 includes one or more of: a processing unit 301, a memory unit
  • the processing unit 301 may include one or more processors, microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or the like.
  • the processing unit 301 may control the operation of the said mobile communication device 300 and its components.
  • the memory unit 302 may include a random access memory (RAM), a read only memory (ROM), and/or other type of memory to store data and instructions that may be used by the processing unit 301.
  • the memory unit 302 includes product recommendation platform/application/module 303 and related data involved therein. More specifically, the product recommendation platform/application/module 303 may be a pre-installed application or may be downloaded from the server hosting such an external application. In an alternative implementation, the functionality provided by the product recommendation platform/application/module 303 may be implemented inbuilt in the product 300. A dedicated product recommendation module 303 may be provided in the product/device 300 for that purpose.
  • the product recommendation platform/application/module 303 may include one or more of routines, programs, objects, components, data structures, etc., which perform particular tasks, functions or implement particular abstract data types.
  • the product data 304 serves as a repository for storing data processed, received, and generated by the product recommendation platform/application/module 303.
  • the product/device interface 305 may include mechanisms for inputting information to the product/device 300 and/or for outputting information from the device 300.
  • input and output mechanisms might include a speaker to receive electrical signals and output audio signals; a camera lens to receive image and/or video signals and output electrical signals; a microphone to receive audio signals and output electrical signals; buttons (e.g., control buttons and/or keys of a keypad) to permit data and control commands to be input into the product/device 300; a display to output visual information; a light emitting diode; a vibrator to cause the device 300 to vibrate etc.
  • the communication interface 306 may include any transceiver-like mechanism that enables the product/device 300 to communicate with other devices and/or systems.
  • the communication interface 306 may include a modem or an Ethernet interface to a LAN.
  • the communication interface 306 may also include mechanisms for communicating via a network, such as a wireless network.
  • the communication interface 306 may include a transmitter that may convert baseband signals from the processing unit 301 to radio frequency (RF) signals and/or a receiver that may convert RF signals to baseband signals.
  • RF radio frequency
  • the communication interface 306 may include a transceiver to perform functions of both a transmitter and a receiver.
  • the communication interface 306 may connect to the antenna assembly 307 for transmission and/or reception of the RF signals.
  • the antenna assembly 307 may include one or more antennas to transmit and/or receive RF signals over the air.
  • the antenna assembly 307 may, for example, receive RF signals from the communication interface 306 and transmit them over the air and receive RF signals over the air and provide them to the communication interface 306.
  • the communication interface 306 may communicate with new generation cellular network, older generation cellular network, and/or with one or more other cellular networks.
  • the product/device 300 may perform certain operations. The product/device 300 may perform these operations in response to the processing unit 301 executing software instructions contained in a computer-readable medium, such as the memory unit 302.
  • a computer-readable medium may be defined as a non-transitory memory device.
  • a memory device may include spaces within a single physical memory device or spread across multiple physical memory devices.
  • the software instructions may be read into the memory unit 302 from another computer-readable medium or from another device via the communication interface 306.
  • the software instructions contained in the memory unit 302 may cause the processing unit 301 to perform processes described herein.
  • hardwired circuitry may be used in place of or in combination with software instructions to implement processes described herein. Thus, implementations described herein are not limited to any specific combination of hardware circuitry and software.
  • Figure 3 shows a number of components of the product/device 300
  • the device 300 may include fewer components, different components, differently arranged components, or additional components than depicted in said Figure 3. Additionally or alternatively, one or more components of the device 300 may perform the tasks described as being performed by one or more other components of the device 300.
  • the product recommendation module/application/platform 303 of the product/device 300 is configured for extracting information in relation to the product/device and transmitting said first information to a server.
  • the said information includes one or more: brand name of the product, model number of the product and specification of the product.
  • the product recommendation module 303 is further configured for one or more: (i) receiving a request from a server to provide information in relation to user and/or features and/or or sub-features of said product, (ii) transmitting said information to the server, (ii) receiving a request from server recommending one or more products, and (ii) transmitting the information in relation to buying of one or more recommended product to the server.
  • Figure 4 illustrates a unit 400 implemented in the server, said unit interacting with the product owned by user(s) in accordance with the embodiment of the present invention.
  • the said unit 400 comprises: a first comparing module 401, a first determination module 402, a first selection module 403, a second comparing module 404, a second determination module 405, a second selection module 406, a recommendation module 407, a recommendation monitoring module 408, an assignment module 409, a first tag generation module 410, a second tag generation module 411, a receiving/fetching module 412 and a transmitting module 413.
  • the said first comparing module 401 is configured for comparing one or more first tags associated with a first user with one or more first tags associated with one or more further users.
  • the first determination module 402 is configured for determining a first similarity index, said first similarity index indicating a percentage of weighted matching first tags corresponding to each further user with that of said first user.
  • the first selection module 403 is configured for selecting a first set of users from said one or more further user(s), said first set of users having a pre-determined percentage of weighted matching first tags.
  • the second comparing module 404 is configured for comparing one or more second tags associated with the first user with one or more second tags associated with said first set of users.
  • the second determination module 405 is configured for determining a second similarity index, said second similarity index indicating a percentage of weighted matching second tags corresponding to each user of said first set of users with that of said first user.
  • the second selection module 406 is configured for selecting a second set of users, said second set of users having a pre-determined percentage of weighted matching second tags.
  • the recommendation module 407 configured for recommending one or more products associated with said second set of users to the first user.
  • the recommendation monitoring module 408 is configured for monitoring one or more purchase activities of said first user.
  • the recommendation monitoring module 408 is further configured for identification of purchase of atleast one recommended product by the first user.
  • the assignment module 409 is configured for assigning pre-defined weights to one or more first parameters and assigning pre-defined weights to one or more said second parameters.
  • the first tag generation module 410 is configured for generating and associating one or more first tags to each user, each first tag corresponding to a first parameter.
  • the said first tag generation module is further configured for generating and associating one or more new first tags to the first user.
  • the second tag generation module 411 is configured for generating and associating one or more second tags to the each user, each second tag corresponding to a second parameter.
  • the said second tag generation module is further configured for generating and associating one or more new second tags to the first user.
  • the receiving/fetching module 412 is configured for: (i) receiving demographic information of a user from the user via user device/product, (ii) fetching demographic information of a user from one or more social media sites, (iii) receiving information in relation to characterization of the user such as profession, interest, hobbies from the user via user device/product, (iv) fetching information in relation to characterization of the user such as profession, interest, hobbies from one or more social media sites, (v) receiving/fetching information in relation to features and/or sub-features of the product, product usage, further products connected to said product, activities of the user in the system such as frequent rating and reviews, response to queries in discussion forums associated with any product, combined with associated feedback from other users in the system by means of up votes and the like.
  • the transmitting module 413 is configured for recommending one or more products to the user device/product.
  • any of the above-modules can be implemented as a software/hardware/combination of hardware and software and said modules can interact with each other and other components of a server for implementing the embodiments of the present invention.
  • FIG. 5 illustrates a typical hardware configuration of a server 500, which is representative of a hardware environment for implementing the present invention.
  • the server as described above, includes the hardware configuration as described below.
  • the server 500 may operate as a client owner computer in a server-client owner network environment, or as a peer computer system in a peer-to- peer (or distributed) network environment.
  • the server can also be implemented as or incorporated into various devices, such as, a tablet, a personal digital assistant (PDA), a palmtop computer, a laptop, a smart phone, a notebook, a smart watch and a communication device.
  • PDA personal digital assistant
  • the server 500 may include a processor 501 e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both.
  • the processor 501 may be a component in a variety of systems.
  • the processor 501 may be part of a standard personal computer or a workstation.
  • the processor 501 may be one or more general processors, digital signal processors, application specific integrated circuits, field programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analysing and processing data.
  • the processor 501 may implement a software program, such as code generated manually (i.e., programmed).
  • the server 500 may include a memory 502 communicating with the processor 501 via a bus 503.
  • the memory 502 may be a main memory, a static memory, or a dynamic memory.
  • the memory 502 may include, but is not limited to computer readable storage media such as various types of volatile and non-volatile storage media, including but not limited to random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like.
  • the memory 502 may be an external storage device or database for storing data. Examples include a hard drive, compact disc (“CD”), digital video disc (“DVD”), memory card, memory stick, floppy disc, universal serial bus (“USB”) memory device, or any other device operative to store data.
  • CD compact disc
  • DVD digital video disc
  • USB universal serial bus
  • the memory 502 is operable to store instructions executable by the processor 501.
  • the functions, acts or tasks illustrated in the figures or described may be performed by the programmed processor 501 executing the instructions stored in the memory 502.
  • the functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and may be performed by software, hardware, integrated circuits, firm-ware, microcode and the like, operating alone or in combination.
  • processing strategies may include multiprocessing, multitasking, parallel processing and the like.
  • the server 500 may further include a display unit 504, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid state display, a cathode ray tube (CRT), or other now known or later developed display device for outputting determined information.
  • a display unit 504 such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid state display, a cathode ray tube (CRT), or other now known or later developed display device for outputting determined information.
  • the server 500 may include an input device 505 configured to allow a owner to interact with any of the components of server 500.
  • the input device 505 may be a number pad, a keyboard, a stylus, an electronic pen, or a cursor control device, such as a mouse, or a joystick, touch screen display, remote control or any other device operative to interact with the server 500.
  • the server 500 may also include a disk or optical drive unit 506.
  • the drive unit 506 may include a computer-readable medium 508 in which one or more sets of instructions 508, e.g. software, can be embedded.
  • the instructions 508 may be separately stored in the processor 501 and the memory 502.
  • the server 500 may further be in communication with other device over a network 509 to communicate voice, video, audio, images, or any other data over the network 509. Further, the data and/or the instructions 508 may be transmitted or received over the network 509 via a communication port or interface 510 or using the bus 503.
  • the communication port or interface 510 may be a part of the processor 501 or may be a separate component.
  • the communication port 510 may be created in software or may be a physical connection in hardware.
  • the communication port 510 may be configured to connect with the network 509, external media, the display 504, or any other components in server 500 or combinations thereof.
  • the connection with the network 509 may be a physical connection, such as a wired Ethernet connection or may be established wirelessly as discussed later.
  • the additional connections with other components of the server 500 may be physical connections or may be established wirelessly.
  • the network 509 may alternatively be directly connected to the bus 503.
  • the network 509 may include wired networks, wireless networks, Ethernet AVB networks, or combinations thereof.
  • the wireless network may be a cellular telephone network, an 802.9, 802.16, 802.20, 802.1Q or WiMax network.
  • the network 509 may be a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and may utilize a variety of networking protocols now available or later developed including, but not limited to TCP/IP based networking protocols.
  • dedicated hardware implementations such as application specific integrated circuits, programmable logic arrays and other hardware devices, can be constructed to implement various parts of the server 500. Applications that may include the systems can broadly include a variety of electronic and computer systems.
  • One or more examples described may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules, or as portions of an application- specific integrated circuit. Accordingly, the present system encompasses software, firmware, and hardware implementations .
  • the server 500 may be implemented by software programs executable by the processor 501. Further, in a non-limited example, implementations can include distributed processing, component/object distributed processing, and parallel processing. Alternatively, virtual computer system processing can be constructed to implement various parts of the system.
  • the server 500 is not limited to operation with any particular standards and protocols.
  • standards for Internet and other packet switched network transmission e.g., TCP/IP, UDP/IP, HTML, HTTP
  • Such standards are periodically superseded by faster or more efficient equivalents having essentially the same functions. Accordingly, replacement standards and protocols having the same or similar functions as those disclosed are considered equivalents thereof.
  • the drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

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)

Abstract

La présente invention concerne un système et un procédé de recommandation de produits. Dans un mode de réalisation, le procédé consiste à comparer une ou plusieurs premières étiquettes associées à un premier utilisateur à une ou plusieurs premières étiquettes associées à un ou plusieurs autres utilisateurs; déterminer un premier indice de similarité, ledit premier indice de similarité indiquant un pourcentage de premières étiquettes concordantes pondérées correspondant à chaque autre utilisateur avec celles dudit premier utilisateur; sélectionner un premier ensemble d'utilisateurs parmi ledit un ou lesdits plusieurs autres utilisateurs, ledit premier ensemble d'utilisateurs ayant un pourcentage prédéterminé de premières étiquettes concordantes pondérées; comparer une ou plusieurs secondes étiquettes associées au premier utilisateur à une ou plusieurs secondes étiquettes associées audit premier ensemble d'utilisateurs; déterminer un second indice de similarité, ledit second indice de similarité indiquant un pourcentage de secondes étiquettes concordantes pondérées correspondant à chaque utilisateur dudit premier ensemble d'utilisateurs avec celles dudit premier utilisateur; sélectionner un second ensemble d'utilisateurs, ledit second ensemble d'utilisateurs ayant un pourcentage prédéterminé de secondes étiquettes concordantes pondérées; recommander au premier utilisateur un ou plusieurs produits associés audit second ensemble d'utilisateurs.
PCT/IB2016/051867 2015-04-02 2016-04-01 Système et procédé de recommandation de produits WO2016157138A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN1775/CHE/2015 2015-04-02
IN1775CH2015 2015-04-02

Publications (1)

Publication Number Publication Date
WO2016157138A1 true WO2016157138A1 (fr) 2016-10-06

Family

ID=57004817

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2016/051867 WO2016157138A1 (fr) 2015-04-02 2016-04-01 Système et procédé de recommandation de produits

Country Status (1)

Country Link
WO (1) WO2016157138A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109992719A (zh) * 2019-04-02 2019-07-09 北京字节跳动网络技术有限公司 用于确定推送优先级信息的方法和装置
CN110162518A (zh) * 2019-04-16 2019-08-23 平安科技（深圳）有限公司 数据分组方法、装置、电子设备及存储介质
CN110473040A (zh) * 2018-05-10 2019-11-19 北京三快在线科技有限公司 一种产品推荐方法及装置，电子设备
CN110807691A (zh) * 2019-10-31 2020-02-18 深圳市云积分科技有限公司 一种跨商品品类的商品推荐方法和装置
CN112507218A (zh) * 2020-12-03 2021-03-16 广州华多网络科技有限公司 业务对象推荐方法、装置、电子设备及存储介质

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070028266A1 (en) * 2002-12-04 2007-02-01 Koninklijke Philips Electronics, N.V. Groenewoudseweg 1 Recommendation of video content based on the user profile of users with similar viewing habits

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070028266A1 (en) * 2002-12-04 2007-02-01 Koninklijke Philips Electronics, N.V. Groenewoudseweg 1 Recommendation of video content based on the user profile of users with similar viewing habits

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473040A (zh) * 2018-05-10 2019-11-19 北京三快在线科技有限公司 一种产品推荐方法及装置，电子设备
CN110473040B (zh) * 2018-05-10 2021-11-19 北京三快在线科技有限公司 一种产品推荐方法及装置，电子设备
CN109992719A (zh) * 2019-04-02 2019-07-09 北京字节跳动网络技术有限公司 用于确定推送优先级信息的方法和装置
CN109992719B (zh) * 2019-04-02 2021-06-25 北京字节跳动网络技术有限公司 用于确定推送优先级信息的方法和装置
CN110162518A (zh) * 2019-04-16 2019-08-23 平安科技（深圳）有限公司 数据分组方法、装置、电子设备及存储介质
CN110162518B (zh) * 2019-04-16 2023-10-31 平安科技（深圳）有限公司 数据分组方法、装置、电子设备及存储介质
CN110807691A (zh) * 2019-10-31 2020-02-18 深圳市云积分科技有限公司 一种跨商品品类的商品推荐方法和装置
CN110807691B (zh) * 2019-10-31 2022-03-04 深圳市云积分科技有限公司 一种跨商品品类的商品推荐方法和装置
CN112507218A (zh) * 2020-12-03 2021-03-16 广州华多网络科技有限公司 业务对象推荐方法、装置、电子设备及存储介质

Similar Documents

Publication Publication Date Title
US10972559B2 (en) Systems and methods for providing recommendations and explanations
US10332172B2 (en) Lead recommendations
US11012753B2 (en) Computerized system and method for determining media based on selected motion video inputs
US11341153B2 (en) Computerized system and method for determining applications on a device for serving media
US9679062B2 (en) Local recommendation engine
US20190026285A1 (en) Generating Cards in Response to User Actions on Online Social Networks
US20170250930A1 (en) Interactive content recommendation personalization assistant
US20180048690A1 (en) Method and terminal for sharing content
US10324987B2 (en) Application search using device capabilities
US20160188733A1 (en) Generating Recommendations Based on Clustered Application States
US20170344553A1 (en) Methods and Systems for Making Recommendations based on Relationships
US20090216639A1 (en) Advertising selection and display based on electronic profile information
WO2016157138A1 (fr) Système et procédé de recommandation de produits
CN107533729B (zh) 基于两个或更多可操作耦合计算机的相对距离分析构建接近社交网络数据库
US10671615B2 (en) Methods and systems for assigning affinity scores to contacts
US20160055537A1 (en) Techniques to target and communicate mobile offers
US9373140B2 (en) Generation of an interface with computer-executable options and visual elements based on collected social network data
US20150348090A1 (en) Engagement with device and ad serving
US20150287069A1 (en) Personal digital engine for user empowerment and method to operate the same
CN110020156B (zh) 信息推荐方法、前端实现方法、装置、设备和存储介质
US8886799B1 (en) Identifying a similar user identifier
US20170249325A1 (en) Proactive favorite leisure interest identification for personalized experiences
US10979528B2 (en) System for trend discovery and curation from content metadata and context
CN111625737A (zh) 一种标签展示方法、装置、设备和存储介质
US20190090197A1 (en) Saving battery life with inferred location

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16771515

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16771515

Country of ref document: EP

Kind code of ref document: A1