[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2020124962A1 - Product recommendation method and apparatus based on data analysis and terminal device - Google Patents

Product recommendation method and apparatus based on data analysis and terminal device Download PDF

Info

Publication number
WO2020124962A1
WO2020124962A1 PCT/CN2019/090831 CN2019090831W WO2020124962A1 WO 2020124962 A1 WO2020124962 A1 WO 2020124962A1 CN 2019090831 W CN2019090831 W CN 2019090831W WO 2020124962 A1 WO2020124962 A1 WO 2020124962A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
user
preset
products
product list
Prior art date
Application number
PCT/CN2019/090831
Other languages
French (fr)
Chinese (zh)
Inventor
乐志能
Original Assignee
平安科技(深圳)有限公司
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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2020124962A1 publication Critical patent/WO2020124962A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions

Definitions

  • the present disclosure relates to the field of big data technology, and in particular, to a product recommendation method, device, and terminal device based on data analysis.
  • Most online shopping platforms have a product recommendation function, which can provide users with recommended products that meet the filtering conditions based on the filtering conditions entered by the user.
  • the inventor realized that due to the large number of products on the online shopping platform, the number of recommended products provided to users based on the screening conditions is also large, which results in users taking a long time to select their favorite products from the recommended products and affecting the user experience.
  • the present disclosure provides a product recommendation method, device and terminal device based on data analysis.
  • a product recommendation method based on data analysis includes:
  • the first product list is obtained according to the instruction of the product recommendation request
  • the second product list is determined from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended;
  • a product recommendation device based on data analysis including:
  • An obtaining unit configured to obtain a first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected;
  • a determining unit configured to determine a second product list from the general service scenario logic by analyzing historical data of the user; wherein, the general service scenario logic includes a product serial number and a preset service scenario logic corresponding to the product serial number, The preset service scenario logic is used to indicate that the product indicated by the corresponding product serial number is not recommended for processing;
  • a processing unit configured to exclude products belonging to the second product list from the first product list from the first product list to obtain a third product list
  • the recommendation unit is used for recommending the products in the third product list.
  • a computer non-volatile readable storage medium that stores a computer program that causes a computer to perform a product recommendation method based on data analysis as described above.
  • a terminal device, the terminal device includes:
  • a memory in which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, implement the product recommendation method based on data analysis as described above.
  • the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:
  • the recommended products products in the first product list
  • the general service scenario logic the first Products in the three-product list
  • the number of products in the third product list is usually less than the number of products in the first product list, so it also achieves a reduction in the number of recommended products the goal of.
  • Fig. 1 is a schematic diagram of a product recommendation device based on data analysis according to an exemplary embodiment
  • Fig. 2 is a flow chart showing a method for product recommendation based on data analysis according to an exemplary embodiment
  • Fig. 3 is a flow chart showing a method for product recommendation based on data analysis according to another exemplary embodiment
  • Fig. 4 is a block diagram of a product recommendation device based on data analysis according to an exemplary embodiment.
  • the implementation environment of the present invention may be a portable terminal device, such as a smart phone, a tablet computer, or a desktop computer.
  • Fig. 1 is a schematic diagram of a product recommendation device based on data analysis according to an exemplary embodiment.
  • the product recommendation device 100 based on data analysis may be the aforementioned portable terminal device.
  • the product recommendation device 100 based on data analysis may include one or more of the following components: a processing component 102, a memory 104, a power component 106, a multimedia component 108, an audio component 110, a sensor component 114 and a communication component 116.
  • the processing component 102 generally controls the overall operations of the product recommendation device 100 based on data analysis, such as operations associated with display, phone calls, data communication, camera operations, and recording operations.
  • the processing component 102 may include one or more processors 118 to execute instructions to complete all or part of the steps of the method described below.
  • the processing component 102 may include one or more modules for facilitating interaction between the processing component 102 and other components.
  • the processing component 102 may include a multimedia module to facilitate interaction between the multimedia component 108 and the processing component 102.
  • the memory 104 is configured to store various types of data to support the operation of the product recommendation device 100 based on data analysis. Examples of these data include instructions for any application program or method operating on the product recommendation device 100 based on data analysis.
  • the memory 104 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (Static Random Access Memory (SRAM for short), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • the memory 104 further stores one or more modules for the one or more modules to be configured to be executed by the one or more processors 118 to complete all or part of the steps in the method shown below.
  • the power supply component 106 supplies power to various components of the product recommendation device 100 based on data analysis.
  • the power component 106 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the product recommendation device 100 based on data analysis.
  • the multimedia component 108 includes a screen that provides an output interface between the product recommendation device 100 based on data analysis and the user.
  • the screen may include a liquid crystal display (Liquid Crystal Display, referred to as LCD) and touch panel. If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding action, but also detect the duration and pressure related to the touch or sliding operation.
  • the screen may also include an organic electroluminescence display (Organic Light Emitting Display, referred to as OLED).
  • the audio component 110 is configured to output and/or input audio signals.
  • the audio component 110 includes a microphone (Microphone, MIC for short).
  • the microphone is configured to receive an external audio signal.
  • the received audio signal may be further stored in the memory 104 or sent via the communication component 116.
  • the audio component 110 further includes a speaker for outputting audio signals.
  • the sensor assembly 114 includes one or more sensors for providing various aspects of status assessment for the product recommendation device 100 based on data analysis.
  • the sensor component 114 can detect the on/off state of the product recommendation device 100 based on data analysis, the relative positioning of the components, and the sensor component 114 can also detect the product recommendation device 100 based on data analysis or the product recommendation device 100 based on data analysis The position of one component changes and the temperature of the product recommendation device 100 based on data analysis.
  • the sensor assembly 114 may also include a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 116 is configured to facilitate wired or wireless communication between the product recommendation device 100 and other devices based on data analysis.
  • the product recommendation device 100 based on data analysis can access a wireless network based on a communication standard, such as WiFi (Wireless-Fidelity, wireless fidelity).
  • the communication component 116 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 116 further includes a Near Field Communication (NFC) module for facilitating short-range communication.
  • the NFC module can be based on radio frequency identification (Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth technology and other technologies.
  • RFID Radio Frequency Identification
  • IrDA Infrared Data Association
  • UWB Ultra Wideband
  • the product recommendation device 100 based on data analysis may be used by one or more application specific integrated circuits (Application Specific Integrated Circuit (ASIC for short), digital signal processor, digital signal processing equipment, programmable logic device, field programmable gate array, controller, microcontroller, microprocessor or other electronic components, used to perform the following method.
  • ASIC Application Specific Integrated Circuit
  • Fig. 2 is a flow chart showing a method for product recommendation based on data analysis according to an exemplary embodiment. As shown in Figure 2, this method includes the following steps.
  • Step 210 When a product recommendation request input by the user is detected, obtain a first product list according to the instruction of the product recommendation request.
  • the above product recommendation request may include information such as product type and product price range.
  • the data analysis-based product recommendation method is applicable to an online shopping platform.
  • the user can log in to the shopping platform through a user account. Before performing step 210, it can also detect whether the user successfully logs in to the online shopping platform, and When it is detected that the user has successfully logged in, the user information associated with the user account is obtained, and the user label is obtained by analyzing the user information.
  • acquiring the first product list according to the instruction of the product recommendation request may include: when detecting the product recommendation request input by the user, acquiring according to the instruction of the product recommendation request and the user tag The first product list.
  • the first product list is obtained according to the instruction of the product recommendation request and the user tag, and the matching degree between the products in the first product list and the user can be improved.
  • the method mentioned in step 210 for obtaining the above-mentioned first product list may also be that, when it is detected that the user successfully logs in to the online shopping platform, the user's last login to the online shopping platform is obtained. Record and obtain products associated with the browsing record to generate a first product list.
  • Step 220 Determine the second product list from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, and the preset service scenario logic Used to indicate that the product indicated by the corresponding product serial number is not recommended.
  • determining the second product list from the general service scenario logic by analyzing the user's historical data may include:
  • the second product list is determined from the historical recommended products according to the recommended times and clicks of the historical recommended products and the logic of the preset service scene corresponding to the historical recommended products.
  • Step 230 Remove the products belonging to the second product list from the first product list to obtain the third product list.
  • Step 240 Perform recommendation processing on the products in the third product list.
  • the products in the first product list include product a and product b.
  • the preset service scenario logic corresponding to product a is recommended three times and the user has not Click to no longer recommend to the user
  • the default service scenario logic corresponding to product b is to recommend 5 times and the user has not clicked, no longer recommend to the user, by analyzing the user's historical data, it is obtained that product a has been recommended to the user 3 times and the user has not clicked
  • Product b has also been recommended to the user 5 times and the user has not clicked it.
  • it is necessary to do not recommend product a and product b in the above first product list that is, to remove product a and product b from the above first product list .
  • the above general service scenario logic is obtained by counting the behavior data of a preset number of users on the product within the second preset duration.
  • the number of recommendations for each product is the preset number of recommendations
  • the behavior data for the product can specifically include data such as whether to click on the product, click on the number of recommendations, whether to buy, and purchase on the number of recommendations.
  • the user comprehensively evaluates the behavior data of the same product to obtain the logic of the preset service scenario corresponding to the product.
  • the recommended products can be further screened to achieve the purpose of reducing the number of recommended products on the basis of ensuring the selectivity of the recommended products, and improving the user's experience.
  • recommending the products in the third product list may include:
  • the product recommendation window may automatically pop up after detecting that the user successfully logs in to the online shopping platform, and execute the above Control the product recommendation window to output the products in the third product list in a polling manner according to the preset rules, and when the user's click operation on the product recommendation window is not detected within the third preset duration, the product recommendation window is terminated Output.
  • the third preset duration can be obtained by counting historical operation data of the user on the product recommendation window.
  • the user information associated with the user account can also be obtained.
  • the user information includes at least the user's age, gender, and occupation;
  • the target window skin matching the user information is determined from the preset window skins; the window skin of the product recommendation window is set as the target window skin.
  • controlling the product recommendation window to output the products in the third product list in a polling manner according to a preset rule may include:
  • the control product recommendation window polls the output polling page in accordance with the above polling cycle.
  • the polling period of the product recommendation window can be set according to the average page-changing time of the user for the product recommendation window to provide the user with an automatic polling method applicable.
  • Fig. 3 is a flow chart showing a method for product recommendation based on data analysis according to another exemplary embodiment. As shown in FIG. 3, in addition to steps 210 to 240 shown in FIG. 2, the product recommendation method based on data analysis in this embodiment also includes the following steps:
  • steps 310 to 340 please refer to the description of steps 210 to 240 in the product recommendation method based on data analysis shown in FIG. 2, which will not be repeated in this embodiment of the present invention.
  • Step 350 it is detected whether there is a click operation on the product in the third product list, and if so, step 360 to step 370 are performed; if not, the process ends.
  • Step 360 the product corresponding to the above click operation is regarded as the product to be introduced.
  • Step 370 Control the output of the acquired introduction information of the product to be introduced according to a preset output mode.
  • the introduction information of the product corresponding to the click operation may be output to the user.
  • a camera module is used to obtain a user image; by identifying the obtained user image, the preset introduction associated with the product to be introduced is introduced
  • the target introduction information is determined in the information.
  • the introduction of the introduction information of the product to be introduced obtained by the above control according to the preset output mode may include: determining the target output mode matching the target introduction information from the preset output mode; controlling the target introduction information to be output in the target output mode .
  • the user's age and gender can be obtained by identifying the user image
  • the preset introduction information associated with the product to be introduced can correspond to the user's age and gender
  • the specific corresponding rule can be the preset associated with the product to be introduced
  • Each preset introduction information in the introduction information may correspond to a preset age group and a gender
  • the target introduction information is preset introduction information corresponding to the user's age and gender.
  • the above-mentioned preset output mode may be text, animation or voice, which is not limited in the embodiment of the present invention, and each preset introduction information corresponds to one output mode.
  • the following is an embodiment of a product recommendation device based on data analysis disclosed in the present invention.
  • Fig. 4 is a block diagram of a product recommendation device based on data analysis according to an exemplary embodiment.
  • the product recommendation device based on data analysis may include:
  • the obtaining unit 401 is configured to obtain the first product list according to the instruction of the product recommendation request when the product recommendation request input by the user is detected.
  • the obtaining unit 401 can also be used to detect whether the user successfully logs in to the online shopping platform before obtaining the first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected, and when it is detected that the user successfully logs in To obtain user information associated with the user account, and obtain user tags by analyzing the user information. Based on this method, the obtaining unit 401 is used to obtain the first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected. The obtaining unit 401 may be used to detect when a user input is detected. When requesting a product recommendation, the first product list is obtained according to the instruction of the product recommendation request and the obtained user tag.
  • the first product list is obtained according to the instruction of the product recommendation request and the user tag, and the matching degree between the product and the user in the first product list can be improved.
  • the acquisition unit 401 may also acquire the first product list in a manner that when the acquisition unit 401 detects that the user has successfully logged in to the online shopping platform, the acquisition unit 401 obtains the browsing history of the user's last login to the online shopping platform And obtain the product associated with the browsing record to generate a first product list.
  • the determining unit 402 is configured to determine the second product list from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended.
  • the determining unit 402 is used to determine the second product list from the general service scenario logic by analyzing the user's historical data, which may specifically be:
  • the above determination unit 402 is used to obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data; and find the preset service scene logic corresponding to the historically recommended products from the general service scene logic; and the recommendations based on the historically recommended products The number of times and the number of clicks, and the logic of the preset service scene corresponding to the historical recommended product, determine the second product list from the historical recommended products.
  • determination unit 402 For a detailed explanation of the determination unit 402, please refer to the examples of steps 210 to 240 in the product recommendation method based on data analysis shown in FIG. 2, which will not be repeated in this embodiment of the present invention.
  • the processing unit 403 is configured to exclude products belonging to the second product list from the first product list from the first product list to obtain a third product list.
  • the recommendation unit 404 is used for recommending the products in the third product list.
  • the manner in which the recommendation unit 404 is used to recommend the products in the third product list may specifically be: the above recommendation unit 404 is used to control the product recommendation window in a polling manner according to preset rules The products in the third product list are output.
  • the above recommendation unit 404 may also be used to control the product recommendation window to obtain user information associated with a user account before outputting products in the third product list in a polling manner according to a preset rule, the user information being at least Including the user's age, gender and occupation; and determining the target window skin matching the user information from the preset window skin according to the user information; and setting the window skin of the product recommendation window as the target window skin.
  • the above recommendation unit 404 is used to control the product recommendation window to output the products in the third product list in a polling manner according to preset rules.
  • the recommendation unit 404 may be used to obtain the first preset duration The average page-changing time of the product recommendation window for internal users; and setting the above average page-changing time as the polling period of the product recommendation window; and setting the polling of the product recommendation window based on preset rules and products in the third product list The number of pages and the products included in each polling page; and the control product recommendation window polls the polling output page in accordance with the above polling cycle.
  • the determining unit 402 includes:
  • the first obtaining subunit 4021 is used to obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
  • the searching subunit 4022 is used to search for the preset service scenario logic corresponding to the historical recommended product from the general service scenario logic;
  • the first determining subunit 4023 is configured to determine a second product list from the historical recommended products according to the recommended times and clicks of the historical recommended products and the logic of the preset service scene corresponding to the historical recommended products.
  • the recommendation unit 404 includes:
  • the first output subunit 4044 is used to control the product recommendation window to output the products in the third product list in a polling manner according to a preset rule.
  • the device further includes:
  • the second obtaining subunit 4041 is configured to obtain user information associated with the user account, where the user information includes at least the user's age, gender, and occupation;
  • the second determining subunit 4042 is configured to determine a target window skin matching the user information from preset window skins according to the user information;
  • the setting subunit 4043 is used to set the window skin of the product recommendation window as the target window skin.
  • the first output subunit 4044 includes:
  • the obtaining module 4044-1 is used to obtain the average page-changing time of the user for the product recommendation window within the first preset time period;
  • the first setting module 4044-2 is configured to set the average page-changing duration as the polling period of the product recommendation window
  • the second setting module 4044-3 is configured to set the number of polling pages of the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
  • the output module 4044-4 is configured to control the product recommendation window to poll and output the polling page according to the polling cycle.
  • the device further includes:
  • the detection unit 407 is configured to detect whether there is a click operation on a product in the third product list
  • the confirmation unit 408 is configured to, when there is the click operation, use the product corresponding to the click operation as the product to be introduced;
  • the output unit 411 is configured to control the obtained introduction information of the product to be introduced to be output according to a preset output mode.
  • the device further includes:
  • the user image obtaining unit 409 is used to obtain a user image by using a camera module
  • the identification unit 410 is configured to determine target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
  • the output unit 411 includes:
  • the third determining subunit 4111 is configured to determine a target output mode matching the target introduction information from preset output modes;
  • the second output subunit 4112 is configured to control the target introduction information to be output in the target output mode.
  • the invention also provides a terminal device.
  • the terminal device includes:
  • a memory which stores computer readable instructions.
  • the product recommendation method based on data analysis as described above is implemented.
  • the terminal device may be the product recommendation device 100 based on data analysis shown in FIG. 1.
  • the present invention also provides a computer non-volatile readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the data analysis-based Product recommendation method.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present application relates to the technical field of big data, and disclosed are a product recommendation method and apparatus based on data analysis and a terminal device. The method comprises: when detecting a product recommendation request inputted by a user, obtaining a first product list according to the indication of the product recommendation request; determining a second product list from a general service scene logic by analyzing historical data of the user; removing products, belonging to the second product list, in the first product list from the first product list to obtain a third product list; and performing recommendation processing on the products in the third product list. By implementing the method, the number of recommended products can be reduced on the basis of ensuring the optionality of the recommended products, and the user experience is improved.

Description

一种基于数据分析的产品推荐方法、装置及终端设备Product recommendation method, device and terminal equipment based on data analysis 技术领域Technical field
本申请要求2018年12月19日递交、发明名称为“一种基于数据分析的产品推荐方法、装置及终端设备”的中国专利申请CN 201811556324.8的优先权,在此通过引用将其全部内容合并于此。This application requires a Chinese patent application CN filed on December 19, 2018 with the invention titled "A product recommendation method, device and terminal equipment based on data analysis" The priority of 201811556324.8 is hereby incorporated by reference.
本公开涉及大数据技术领域,特别涉及一种基于数据分析的产品推荐方法、装置及终端设备。The present disclosure relates to the field of big data technology, and in particular, to a product recommendation method, device, and terminal device based on data analysis.
背景技术Background technique
网购平台大都具有产品推荐功能,其可以依据用户输入的筛选条件向用户提供满足筛选条件的推荐产品。Most online shopping platforms have a product recommendation function, which can provide users with recommended products that meet the filtering conditions based on the filtering conditions entered by the user.
但是,发明人意识到,由于网购平台的产品数量较大,其依据筛选条件提供给用户的推荐产品数量也较大,导致用户从推荐产品中挑选心仪产品需要耗费较长时间,影响用户体验。However, the inventor realized that due to the large number of products on the online shopping platform, the number of recommended products provided to users based on the screening conditions is also large, which results in users taking a long time to select their favorite products from the recommended products and affecting the user experience.
技术问题technical problem
为了解决相关技术中存在的问题,本公开提供了一种基于数据分析的产品推荐方法、装置及终端设备。In order to solve the problems in the related art, the present disclosure provides a product recommendation method, device and terminal device based on data analysis.
技术解决方案Technical solution
一种基于数据分析的产品推荐方法,所述方法包括:A product recommendation method based on data analysis, the method includes:
当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; When a product recommendation request input by the user is detected, the first product list is obtained according to the instruction of the product recommendation request;
通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;The second product list is determined from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended;
将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;Removing products belonging to the second product list from the first product list from the first product list to obtain a third product list;
对所述第三产品列表中的产品做推荐处理。Recommend the products in the third product list.
一种基于数据分析的产品推荐装置,包括:A product recommendation device based on data analysis, including:
获取单元,用于当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; An obtaining unit, configured to obtain a first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected;
确定单元,用于通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;A determining unit, configured to determine a second product list from the general service scenario logic by analyzing historical data of the user; wherein, the general service scenario logic includes a product serial number and a preset service scenario logic corresponding to the product serial number, The preset service scenario logic is used to indicate that the product indicated by the corresponding product serial number is not recommended for processing;
处理单元,用于将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;A processing unit, configured to exclude products belonging to the second product list from the first product list from the first product list to obtain a third product list;
推荐单元,用于对所述第三产品列表中的产品做推荐处理。The recommendation unit is used for recommending the products in the third product list.
一种计算机非易失性可读存储介质,其存储计算机程序,所述计算机程序使得计算机执行如上所述的基于数据分析的产品推荐方法。A computer non-volatile readable storage medium that stores a computer program that causes a computer to perform a product recommendation method based on data analysis as described above.
一种终端设备,所述终端设备包括:A terminal device, the terminal device includes:
处理器;processor;
存储器,所述存储器上存储有计算机可读指令,所述计算机可读指令被所述处理器执行时,实现如上所述的基于数据分析的产品推荐方法。A memory, in which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, implement the product recommendation method based on data analysis as described above.
有益效果Beneficial effect
本公开的实施例提供的技术方案可以包括以下有益效果:此方法下,结合用户的历史数据和通用服务场景逻辑对待推荐产品(第一产品列表中的产品)做进一步筛选得到的推荐产品(第三产品列表中的产品),可以保证推荐产品的可选性,同时,所得到的第三产品列表中的产品数量通常是小于第一产品列表中产品数量的,所以也达到了降低推荐产品数量的目的。The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: In this method, the recommended products (products in the first product list) are further filtered by combining the user's historical data and the general service scenario logic (the first Products in the three-product list), which can ensure the selectivity of recommended products, and at the same time, the number of products in the third product list is usually less than the number of products in the first product list, so it also achieves a reduction in the number of recommended products the goal of.
应当理解的是,以上的一般描述和后文的细节描述仅是示例性的,并不能限制本公开。It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present disclosure.
附图说明BRIEF DESCRIPTION
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本申请的实施例,并于说明书一起用于解释本申请的原理。The drawings herein are incorporated into the specification and constitute a part of the specification, show embodiments consistent with the application, and are used together with the specification to explain the principles of the application.
图1是根据一示例性实施例示出的一种基于数据分析的产品推荐装置的示意图;Fig. 1 is a schematic diagram of a product recommendation device based on data analysis according to an exemplary embodiment;
图2是根据一示例性实施例示出的一种基于数据分析的产品推荐方法的流程图;Fig. 2 is a flow chart showing a method for product recommendation based on data analysis according to an exemplary embodiment;
图3是根据另一示例性实施例示出的一种基于数据分析的产品推荐方法的流程图;Fig. 3 is a flow chart showing a method for product recommendation based on data analysis according to another exemplary embodiment;
图4是根据一示例性实施例示出的一种基于数据分析的产品推荐装置的框图。Fig. 4 is a block diagram of a product recommendation device based on data analysis according to an exemplary embodiment.
本发明的实施方式Embodiments of the invention
这里将详细地对示例性实施例执行说明,其示例表示在附图中。下面的描述涉及附图时,除非另有表示,不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反,它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。The exemplary embodiments will be explained in detail here, examples of which are shown in the drawings. When referring to the drawings below, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.
本发明的实施环境可以是便携式终端设备,例如智能手机、平板电脑、台式电脑。图1是根据一示例性实施例示出的一种基于数据分析的产品推荐装置的示意图。基于数据分析的产品推荐装置100可以是上述便携式终端设备。如图1所示,基于数据分析的产品推荐装置100可以包括以下一个或多个组件:处理组件102,存储器104,电源组件106,多媒体组件108,音频组件110,传感器组件114以及通信组件116。The implementation environment of the present invention may be a portable terminal device, such as a smart phone, a tablet computer, or a desktop computer. Fig. 1 is a schematic diagram of a product recommendation device based on data analysis according to an exemplary embodiment. The product recommendation device 100 based on data analysis may be the aforementioned portable terminal device. As shown in FIG. 1, the product recommendation device 100 based on data analysis may include one or more of the following components: a processing component 102, a memory 104, a power component 106, a multimedia component 108, an audio component 110, a sensor component 114 and a communication component 116.
处理组件102通常控制基于数据分析的产品推荐装置100的整体操作,诸如与显示,电话呼叫,数据通信,相机操作以及记录操作相关联的操作等。处理组件102可以包括一个或多个处理器118来执行指令,以完成下述的方法的全部或部分步骤。此外,处理组件102可以包括一个或多个模块,用于便于处理组件102和其他组件之间的交互。例如,处理组件102可以包括多媒体模块,用于以方便多媒体组件108和处理组件102之间的交互。The processing component 102 generally controls the overall operations of the product recommendation device 100 based on data analysis, such as operations associated with display, phone calls, data communication, camera operations, and recording operations. The processing component 102 may include one or more processors 118 to execute instructions to complete all or part of the steps of the method described below. In addition, the processing component 102 may include one or more modules for facilitating interaction between the processing component 102 and other components. For example, the processing component 102 may include a multimedia module to facilitate interaction between the multimedia component 108 and the processing component 102.
存储器104被配置为存储各种类型的数据以支持在基于数据分析的产品推荐装置100的操作。这些数据的示例包括用于在基于数据分析的产品推荐装置100上操作的任何应用程序或方法的指令。存储器104可以由任何类型的易失性或非易失性存储设备或者它们的组合实现,如静态随机存取存储器(Static Random Access Memory,简称SRAM),电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory,简称EEPROM),可擦除可编程只读存储器(Erasable Programmable Read Only Memory,简称EPROM),可编程只读存储器(Programmable Red-Only Memory,简称PROM),只读存储器(Read-Only Memory,简称ROM),磁存储器,快闪存储器,磁盘或光盘。存储器104中还存储有一个或多个模块,用于该一个或多个模块被配置成由该一个或多个处理器118执行,以完成如下所示方法中的全部或者部分步骤。The memory 104 is configured to store various types of data to support the operation of the product recommendation device 100 based on data analysis. Examples of these data include instructions for any application program or method operating on the product recommendation device 100 based on data analysis. The memory 104 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (Static Random Access Memory (SRAM for short), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The memory 104 further stores one or more modules for the one or more modules to be configured to be executed by the one or more processors 118 to complete all or part of the steps in the method shown below.
电源组件106为基于数据分析的产品推荐装置100的各种组件提供电力。电源组件106可以包括电源管理系统,一个或多个电源,及其他与为基于数据分析的产品推荐装置100生成、管理和分配电力相关联的组件。The power supply component 106 supplies power to various components of the product recommendation device 100 based on data analysis. The power component 106 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the product recommendation device 100 based on data analysis.
多媒体组件108包括在基于数据分析的产品推荐装置100和用户之间的提供一个输出接口的屏幕。在一些实施例中,屏幕可以包括液晶显示器(Liquid Crystal Display,简称LCD)和触摸面板。如果屏幕包括触摸面板,屏幕可以被实现为触摸屏,以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界,而且还检测与触摸或滑动操作相关的持续时间和压力。屏幕还可以包括有机电致发光显示器(Organic Light Emitting Display,简称OLED)。The multimedia component 108 includes a screen that provides an output interface between the product recommendation device 100 based on data analysis and the user. In some embodiments, the screen may include a liquid crystal display (Liquid Crystal Display, referred to as LCD) and touch panel. If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding action, but also detect the duration and pressure related to the touch or sliding operation. The screen may also include an organic electroluminescence display (Organic Light Emitting Display, referred to as OLED).
音频组件110被配置为输出和/或输入音频信号。例如,音频组件110包括一个麦克风(Microphone,简称MIC),当基于数据分析的产品推荐装置100处于操作模式,如呼叫模式、记录模式和语音识别模式时,麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器104或经由通信组件116发送。在一些实施例中,音频组件110还包括一个扬声器,用于输出音频信号。The audio component 110 is configured to output and/or input audio signals. For example, the audio component 110 includes a microphone (Microphone, MIC for short). When the product recommendation device 100 based on data analysis is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in the memory 104 or sent via the communication component 116. In some embodiments, the audio component 110 further includes a speaker for outputting audio signals.
传感器组件114包括一个或多个传感器,用于为基于数据分析的产品推荐装置100提供各个方面的状态评估。例如,传感器组件114可以检测到基于数据分析的产品推荐装置100的打开/关闭状态,组件的相对定位,传感器组件114还可以检测基于数据分析的产品推荐装置100或基于数据分析的产品推荐装置100一个组件的位置改变以及基于数据分析的产品推荐装置100的温度变化。在一些实施例中,该传感器组件114还可以包括磁传感器,压力传感器或温度传感器。The sensor assembly 114 includes one or more sensors for providing various aspects of status assessment for the product recommendation device 100 based on data analysis. For example, the sensor component 114 can detect the on/off state of the product recommendation device 100 based on data analysis, the relative positioning of the components, and the sensor component 114 can also detect the product recommendation device 100 based on data analysis or the product recommendation device 100 based on data analysis The position of one component changes and the temperature of the product recommendation device 100 based on data analysis. In some embodiments, the sensor assembly 114 may also include a magnetic sensor, a pressure sensor, or a temperature sensor.
通信组件116被配置为便于基于数据分析的产品推荐装置100和其他设备之间有线或无线方式的通信。基于数据分析的产品推荐装置100可以接入基于通信标准的无线网络,如WiFi(Wireless-Fidelity,无线保真)。在一个示例性实施例中,通信组件116经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中,通信组件116还包括近场通信(Near Field Communication,简称NFC)模块,用于以促进短程通信。例如,在NFC模块可基于射频识别(Radio Frequency Identification,简称RFID)技术,红外数据协会(Infrared Data Association,简称IrDA)技术,超宽带(Ultra Wideband,简称UWB)技术,蓝牙技术和其他技术来实现。The communication component 116 is configured to facilitate wired or wireless communication between the product recommendation device 100 and other devices based on data analysis. The product recommendation device 100 based on data analysis can access a wireless network based on a communication standard, such as WiFi (Wireless-Fidelity, wireless fidelity). In an exemplary embodiment, the communication component 116 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 116 further includes a Near Field Communication (NFC) module for facilitating short-range communication. For example, the NFC module can be based on radio frequency identification (Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth technology and other technologies.
在示例性实施例中,基于数据分析的产品推荐装置100可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit,简称ASIC)、数字信号处理器、数字信号处理设备、可编程逻辑器件、现场可编程门阵列、控制器、微控制器、微处理器或其他电子元件实现,用于执行下述方法。In an exemplary embodiment, the product recommendation device 100 based on data analysis may be used by one or more application specific integrated circuits (Application Specific Integrated Circuit (ASIC for short), digital signal processor, digital signal processing equipment, programmable logic device, field programmable gate array, controller, microcontroller, microprocessor or other electronic components, used to perform the following method.
图2是根据一示例性实施例示出的一种基于数据分析的产品推荐方法的流程图。如图2所示,此方法包括以下步骤。Fig. 2 is a flow chart showing a method for product recommendation based on data analysis according to an exemplary embodiment. As shown in Figure 2, this method includes the following steps.
步骤210,当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示获取第一产品列表。Step 210: When a product recommendation request input by the user is detected, obtain a first product list according to the instruction of the product recommendation request.
在本发明实施例中,上述产品推荐请求可以包括产品类型和产品价格范围等信息。在一示例性实施例中,该基于数据分析的产品推荐方法适用于网购平台,用户可以通过用户账号登录该购物平台,在执行步骤210之前,还可以检测用户是否成功登录该网购平台,以及在检测到用户成功登录时,获取与该用户账号关联的用户信息,通过分析该用户信息得到用户标签。上述当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示获取第一产品列表,可以包括:当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示和用户标签获取第一产品列表。通过实施该方法,在用户成功登录网购平台,且输入产品推荐请求时,依据产品推荐请求的指示和用户标签获取第一产品列表,可以提高第一产品列表中产品与用户的匹配度。In the embodiment of the present invention, the above product recommendation request may include information such as product type and product price range. In an exemplary embodiment, the data analysis-based product recommendation method is applicable to an online shopping platform. The user can log in to the shopping platform through a user account. Before performing step 210, it can also detect whether the user successfully logs in to the online shopping platform, and When it is detected that the user has successfully logged in, the user information associated with the user account is obtained, and the user label is obtained by analyzing the user information. When the product recommendation request input by the user is detected, acquiring the first product list according to the instruction of the product recommendation request may include: when detecting the product recommendation request input by the user, acquiring according to the instruction of the product recommendation request and the user tag The first product list. By implementing this method, when a user successfully logs in to the online shopping platform and enters a product recommendation request, the first product list is obtained according to the instruction of the product recommendation request and the user tag, and the matching degree between the products in the first product list and the user can be improved.
可选的,在本发明实施中,步骤210中所提及的获取上述第一产品列表的方式还可以是,当检测到用户成功登录网购平台时,获取该用户最近一次登录该网购平台的浏览记录,并获取与该浏览记录关联的产品以生成第一产品列表。Optionally, in the implementation of the present invention, the method mentioned in step 210 for obtaining the above-mentioned first product list may also be that, when it is detected that the user successfully logs in to the online shopping platform, the user's last login to the online shopping platform is obtained. Record and obtain products associated with the browsing record to generate a first product list.
步骤220,通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,通用服务场景逻辑中包含有产品序号以及产品序号对应的预设服务场景逻辑,该预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理。Step 220: Determine the second product list from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, and the preset service scenario logic Used to indicate that the product indicated by the corresponding product serial number is not recommended.
    在一示例性实施例中,通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表,可以包括: In an exemplary embodiment, determining the second product list from the general service scenario logic by analyzing the user's historical data may include:
通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;Obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
从通用服务场景逻辑中查找历史推荐产品对应的预设服务场景逻辑;Find the preset service scene logic corresponding to the historical recommended products from the general service scene logic;
依据历史推荐产品的推荐次数和点击次数,以及历史推荐产品对应的预设服务场景逻辑,从历史推荐产品中确定出第二产品列表。The second product list is determined from the historical recommended products according to the recommended times and clicks of the historical recommended products and the logic of the preset service scene corresponding to the historical recommended products.
步骤230,将第一产品列表中属于第二产品列表的产品从第一产品列表中剔除得到第三产品列表。Step 230: Remove the products belonging to the second product list from the first product list to obtain the third product list.
步骤240,对第三产品列表中的产品做推荐处理。Step 240: Perform recommendation processing on the products in the third product list.
下面针对步骤210~步骤240进行举例说明,假设上述第一产品列表中的产品包含产品a和产品b,在通用服务场景逻辑中,产品a对应的预设服务场景逻辑为推荐3次且用户未点击不再给用户推荐,产品b对应的预设服务场景逻辑为推荐5次且用户未点击不再给用户推荐,通过分析用户的历史数据得到产品a已推荐给用户3次且用户未点击,产品b也已经推荐给用户5次且用户未点击,此时,需要对上述第一产品列表中的产品a和产品b做不推荐处理,即将产品a和产品b从上述第一产品列表中剔除。The following is an example for steps 210 to 240. Suppose that the products in the first product list include product a and product b. In the general service scenario logic, the preset service scenario logic corresponding to product a is recommended three times and the user has not Click to no longer recommend to the user, the default service scenario logic corresponding to product b is to recommend 5 times and the user has not clicked, no longer recommend to the user, by analyzing the user's historical data, it is obtained that product a has been recommended to the user 3 times and the user has not clicked Product b has also been recommended to the user 5 times and the user has not clicked it. At this time, it is necessary to do not recommend product a and product b in the above first product list, that is, to remove product a and product b from the above first product list .
需要说明的是,上述通用服务场景逻辑是通过统计第二预设时长内预设数量用户针对产品的行为数据得到的。其中,每一产品的推荐次数为预设推荐次数,针对产品的行为数据具体可以包括是否点击产品,于第几次推荐时点击、是否购买以及于第几次推荐时购买等数据,通过分析不同用户针对同一产品的行为数据,综合评估得到产品对应的预设服务场景逻辑。It should be noted that the above general service scenario logic is obtained by counting the behavior data of a preset number of users on the product within the second preset duration. Among them, the number of recommendations for each product is the preset number of recommendations, and the behavior data for the product can specifically include data such as whether to click on the product, click on the number of recommendations, whether to buy, and purchase on the number of recommendations. The user comprehensively evaluates the behavior data of the same product to obtain the logic of the preset service scenario corresponding to the product.
通过执行步骤210~步骤230,可以对推荐产品进行进一步的筛选,达到在保证推荐产品可选性的基础上降低推荐产品的数量的目的,提高用户的使用体验感。By performing steps 210 to 230, the recommended products can be further screened to achieve the purpose of reducing the number of recommended products on the basis of ensuring the selectivity of the recommended products, and improving the user's experience.
在另一示例性实施例中,对第三产品列表中的产品做推荐处理,可以包括:In another exemplary embodiment, recommending the products in the third product list may include:
控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品。若上述第一产品列表是通过获取该用户在该网购平台最近一次登录的浏览记录获得的,进一步可选的,产品推荐窗口可以在检测到用户成功登录网购平台之后,自动弹出,并执行上述的控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品,以及当在第三预设时长内未检测到用户针对产品推荐窗口输出产品的点击操作时,则终止产品推荐窗口的输出。需要说明的是,该第三预设时长可以通过统计用户针对产品推荐窗口的历史操作数据得到。通过实施该方法,可以提供给用户智能化的产品推荐方法,此外,当在第三预设时长内未检测到用户针对产品推荐窗口输出产品的点击操作时,终止产品推荐窗口的输出,可以减少对用户的干扰。 Control the product recommendation window to output the products in the third product list in a polling manner according to preset rules. If the above first product list is obtained by obtaining the user's browsing history of the user's last login on the online shopping platform, further optional, the product recommendation window may automatically pop up after detecting that the user successfully logs in to the online shopping platform, and execute the above Control the product recommendation window to output the products in the third product list in a polling manner according to the preset rules, and when the user's click operation on the product recommendation window is not detected within the third preset duration, the product recommendation window is terminated Output. It should be noted that the third preset duration can be obtained by counting historical operation data of the user on the product recommendation window. By implementing this method, users can be provided with an intelligent product recommendation method. In addition, when the user’s click operation on the product recommendation window is not detected within the third preset time period, the output of the product recommendation window is terminated, which can be reduced Interference with users.
其中,控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品之前,还可以获取用户账号关联的用户信息,该用户信息至少包括用户年龄、性别以及职业;根据用户信息从预设的窗口皮肤中确定出与用户信息匹配的目标窗口皮肤;设置产品推荐窗口的窗口皮肤为目标窗口皮肤。通过实施该示例性实施例,若第三产品列表中的产品在产品推荐窗口按照预设规则以轮询方式输出,可以依据用户信息将产品推荐窗口的窗口皮肤设置为与该用户信息匹配的目标窗口皮肤,提高趣味性,进一步提高用户的使用体验感。Before controlling the product recommendation window to output the products in the third product list in a polling manner according to the preset rules, the user information associated with the user account can also be obtained. The user information includes at least the user's age, gender, and occupation; The target window skin matching the user information is determined from the preset window skins; the window skin of the product recommendation window is set as the target window skin. By implementing this exemplary embodiment, if the products in the third product list are output in a polling manner according to preset rules in the product recommendation window, the window skin of the product recommendation window can be set as the target matching the user information according to the user information Window skins improve fun and further enhance the user's experience.
可选的,在一示例性实施例中,控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品可以包括:Optionally, in an exemplary embodiment, controlling the product recommendation window to output the products in the third product list in a polling manner according to a preset rule may include:
获取第一预设时长内用户针对产品推荐窗口的平均换页时长;Obtain the average page-changing time of the user recommendation window for the product within the first preset time period;
将上述平均换页时长设置为产品推荐窗口的轮询周期;Set the above average page change duration to the polling period of the product recommendation window;
依据预设规则和第三产品列表中的产品,设置产品推荐窗口的轮询页的数量和每一轮询页所包括的产品;According to the preset rules and the products in the third product list, set the number of polling pages in the product recommendation window and the products included in each polling page;
控制产品推荐窗口按照上述轮询周期轮询输出轮询页。The control product recommendation window polls the output polling page in accordance with the above polling cycle.
通过实施该可选实施方法,可以依据用户针对产品推荐窗口的平均换页时长设置产品推荐窗口的轮询周期,提供给用户适用的自动轮询方式。By implementing this optional implementation method, the polling period of the product recommendation window can be set according to the average page-changing time of the user for the product recommendation window to provide the user with an automatic polling method applicable.
图3是根据另一示例性实施例示出的一种基于数据分析的产品推荐方法的流程图。如图3所示,除图2所示的步骤210~步骤240之外,此实施例中基于数据分析的产品推荐方法还包括以下步骤:Fig. 3 is a flow chart showing a method for product recommendation based on data analysis according to another exemplary embodiment. As shown in FIG. 3, in addition to steps 210 to 240 shown in FIG. 2, the product recommendation method based on data analysis in this embodiment also includes the following steps:
其中,针对步骤310~步骤340的详细描述,请参照图2所示的基于数据分析的产品推荐方法中针对步骤210~步骤240的描述,本发明实施例不再赘述。For the detailed description of steps 310 to 340, please refer to the description of steps 210 to 240 in the product recommendation method based on data analysis shown in FIG. 2, which will not be repeated in this embodiment of the present invention.
步骤350,检测是否存在对第三产品列表中产品的点击操作,如果是,执行步骤360~步骤370;如果否,结束本流程。Step 350, it is detected whether there is a click operation on the product in the third product list, and if so, step 360 to step 370 are performed; if not, the process ends.
步骤360,将上述点击操作对应的产品作为待介绍产品。Step 360, the product corresponding to the above click operation is regarded as the product to be introduced.
步骤370,控制获取到的待介绍产品的介绍信息按照预设输出方式进行输出。Step 370: Control the output of the acquired introduction information of the product to be introduced according to a preset output mode.
执行步骤350~步骤370,可以在存在对第三产品列表中产品的点击操作时,输出该点击操作对应的产品的介绍信息给用户。Performing steps 350 to 370, when there is a click operation on the product in the third product list, the introduction information of the product corresponding to the click operation may be output to the user.
可选的,在一示例性实施例中,步骤360执行完毕之后,以及在执行步骤370之前,还利用摄像模组获得用户图像;通过识别获得的用户图像,从待介绍产品关联的预设介绍信息中确定出目标介绍信息。那么,上述控制获取到的待介绍产品的介绍信息按照预设输出方式进行输出可以包括:从预设输出方式中确定出与目标介绍信息匹配的目标输出方式;控制目标介绍信息以目标输出方式输出。实施该示例性实施例,可以通过识别用户图像,将符合用户的目标介绍信息以目标输出方式输出,使得目标介绍信息的可读性更强,有利于提高推荐产品的产品转化率。 Optionally, in an exemplary embodiment, after step 360 is performed, and before step 370 is performed, a camera module is used to obtain a user image; by identifying the obtained user image, the preset introduction associated with the product to be introduced is introduced The target introduction information is determined in the information. Then, the introduction of the introduction information of the product to be introduced obtained by the above control according to the preset output mode may include: determining the target output mode matching the target introduction information from the preset output mode; controlling the target introduction information to be output in the target output mode . By implementing this exemplary embodiment, it is possible to output the target introduction information conforming to the user in a target output mode by identifying the user image, which makes the target introduction information more readable, which is beneficial to improve the product conversion rate of the recommended products.
需要说明的是,通过识别用户图像可以获取到用户的年龄和性别,待介绍产品关联的预设介绍信息可以与用户的年龄和性别对应,具体的对应规则可以是,待介绍产品关联的预设介绍信息中的每一预设介绍信息可以对应一个预设年龄段和一种性别,目标介绍信息即为与用户年龄和性别对应的预设介绍信息。It should be noted that the user's age and gender can be obtained by identifying the user image, and the preset introduction information associated with the product to be introduced can correspond to the user's age and gender, and the specific corresponding rule can be the preset associated with the product to be introduced Each preset introduction information in the introduction information may correspond to a preset age group and a gender, and the target introduction information is preset introduction information corresponding to the user's age and gender.
其中,上述预设输出方式可以是文本、动画或者语音,本发明实施例不做限定,且每一预设介绍信息对应一种输出方式。Wherein, the above-mentioned preset output mode may be text, animation or voice, which is not limited in the embodiment of the present invention, and each preset introduction information corresponds to one output mode.
以下是本发明公开的基于数据分析的产品推荐装置实施例。The following is an embodiment of a product recommendation device based on data analysis disclosed in the present invention.
图4是根据一示例性实施例示出的一种基于数据分析的产品推荐装置的框图。如图4所示,该基于数据分析的产品推荐装置可以包括:Fig. 4 is a block diagram of a product recommendation device based on data analysis according to an exemplary embodiment. As shown in FIG. 4, the product recommendation device based on data analysis may include:
获取单元401,用于当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示获取第一产品列表。 The obtaining unit 401 is configured to obtain the first product list according to the instruction of the product recommendation request when the product recommendation request input by the user is detected.
获取单元401,还可以用于当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示获取第一产品列表之前,检测用户是否成功登录该网购平台,以及在检测到用户成功登录时,获取与该用户账号关联的用户信息,通过分析该用户信息得到用户标签。基于该方法,获取单元401用于当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示获取第一产品列表的方式具体可以为:获取单元401,用于当检测到用户输入的产品推荐请求时,依据该产品推荐请求的指示和得到的用户标签获取第一产品列表。通过实施该方式,在用户成功登录网购平台,且输入产品推荐请求时,依据产品推荐请求的指示和用户标签获取第一产品列表,可以提高第一产品列表中产品与用户的匹配度。The obtaining unit 401 can also be used to detect whether the user successfully logs in to the online shopping platform before obtaining the first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected, and when it is detected that the user successfully logs in To obtain user information associated with the user account, and obtain user tags by analyzing the user information. Based on this method, the obtaining unit 401 is used to obtain the first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected. The obtaining unit 401 may be used to detect when a user input is detected. When requesting a product recommendation, the first product list is obtained according to the instruction of the product recommendation request and the obtained user tag. By implementing this method, when the user successfully logs in to the online shopping platform and enters a product recommendation request, the first product list is obtained according to the instruction of the product recommendation request and the user tag, and the matching degree between the product and the user in the first product list can be improved.
可选的,在本发明实施中,获取单元401获取第一产品列表的方式还可以是,获取单元401 当检测到用户成功登录网购平台时,获取该用户最近一次登录该网购平台的浏览记录,并获取与该浏览记录关联的产品以生成第一产品列表。Optionally, in the implementation of the present invention, the acquisition unit 401 may also acquire the first product list in a manner that when the acquisition unit 401 detects that the user has successfully logged in to the online shopping platform, the acquisition unit 401 obtains the browsing history of the user's last login to the online shopping platform And obtain the product associated with the browsing record to generate a first product list.
确定单元402,用于通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,通用服务场景逻辑中包含有产品序号以及产品序号对应的预设服务场景逻辑,预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理。The determining unit 402 is configured to determine the second product list from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended.
在一示例性实施例中,上述确定单元402用于通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表的方式具体可以为:In an exemplary embodiment, the determining unit 402 is used to determine the second product list from the general service scenario logic by analyzing the user's historical data, which may specifically be:
上述确定单元402,用于通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;以及从通用服务场景逻辑中查找历史推荐产品对应的预设服务场景逻辑;以及依据历史推荐产品的推荐次数和点击次数,以及历史推荐产品对应的预设服务场景逻辑,从历史推荐产品中确定出第二产品列表。The above determination unit 402 is used to obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data; and find the preset service scene logic corresponding to the historically recommended products from the general service scene logic; and the recommendations based on the historically recommended products The number of times and the number of clicks, and the logic of the preset service scene corresponding to the historical recommended product, determine the second product list from the historical recommended products.
其中,针对确定单元402的详细解释,请参照图2所示的基于数据分析的产品推荐方法中针对步骤210~步骤240的举例,本发明实施例不再赘述。For a detailed explanation of the determination unit 402, please refer to the examples of steps 210 to 240 in the product recommendation method based on data analysis shown in FIG. 2, which will not be repeated in this embodiment of the present invention.
处理单元403,用于将第一产品列表中属于第二产品列表的产品从第一产品列表中剔除得到第三产品列表。The processing unit 403 is configured to exclude products belonging to the second product list from the first product list from the first product list to obtain a third product list.
推荐单元404,用于对第三产品列表中的产品做推荐处理。The recommendation unit 404 is used for recommending the products in the third product list.
在另一示例性实施例中,推荐单元404用于对第三产品列表中的产品做推荐处理的方式具体可以为:上述推荐单元404,用于控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品。基于该示例性实施例,上述推荐单元404,还可以用于控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品之前,获取用户账号关联的用户信息,该用户信息至少包括用户年龄、性别以及职业;以及根据用户信息从预设的窗口皮肤中确定出与用户信息匹配的目标窗口皮肤;以及设置产品推荐窗口的窗口皮肤为目标窗口皮肤。In another exemplary embodiment, the manner in which the recommendation unit 404 is used to recommend the products in the third product list may specifically be: the above recommendation unit 404 is used to control the product recommendation window in a polling manner according to preset rules The products in the third product list are output. Based on this exemplary embodiment, the above recommendation unit 404 may also be used to control the product recommendation window to obtain user information associated with a user account before outputting products in the third product list in a polling manner according to a preset rule, the user information being at least Including the user's age, gender and occupation; and determining the target window skin matching the user information from the preset window skin according to the user information; and setting the window skin of the product recommendation window as the target window skin.
进一步可选的,上述推荐单元404用于控制产品推荐窗口按照预设规则以轮询方式输出第三产品列表中的产品的方式具体可以为:上述推荐单元404,用于获取第一预设时长内用户针对产品推荐窗口的平均换页时长;以及将上述平均换页时长设置为产品推荐窗口的轮询周期;以及依据预设规则和第三产品列表中的产品,设置产品推荐窗口的轮询页的数量和每一轮询页所包括的产品;以及控制产品推荐窗口按照上述轮询周期轮询输出轮询页。Further optionally, the above recommendation unit 404 is used to control the product recommendation window to output the products in the third product list in a polling manner according to preset rules. The recommendation unit 404 may be used to obtain the first preset duration The average page-changing time of the product recommendation window for internal users; and setting the above average page-changing time as the polling period of the product recommendation window; and setting the polling of the product recommendation window based on preset rules and products in the third product list The number of pages and the products included in each polling page; and the control product recommendation window polls the polling output page in accordance with the above polling cycle.
在一实施例中,所述确定单元402包括:In an embodiment, the determining unit 402 includes:
第一获取子单元4021,用于通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;The first obtaining subunit 4021 is used to obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
查找子单元4022,用于从通用服务场景逻辑中查找所述历史推荐产品对应的预设服务场景逻辑;The searching subunit 4022 is used to search for the preset service scenario logic corresponding to the historical recommended product from the general service scenario logic;
第一确定子单元4023,用于依据所述历史推荐产品的推荐次数和点击次数,以及所述历史推荐产品对应的预设服务场景逻辑,从所述历史推荐产品中确定出第二产品列表。The first determining subunit 4023 is configured to determine a second product list from the historical recommended products according to the recommended times and clicks of the historical recommended products and the logic of the preset service scene corresponding to the historical recommended products.
在一实施例中,所述推荐单元404包括:In an embodiment, the recommendation unit 404 includes:
第一输出子单元4044,用于控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品。The first output subunit 4044 is used to control the product recommendation window to output the products in the third product list in a polling manner according to a preset rule.
在一实施例中,所述装置还包括:In an embodiment, the device further includes:
第二获取子单元4041,用于获取用户账号关联的用户信息,所述用户信息至少包括用户年龄、性别以及职业;The second obtaining subunit 4041 is configured to obtain user information associated with the user account, where the user information includes at least the user's age, gender, and occupation;
第二确定子单元4042,用于根据所述用户信息从预设的窗口皮肤中确定出与所述用户信息匹配的目标窗口皮肤;The second determining subunit 4042 is configured to determine a target window skin matching the user information from preset window skins according to the user information;
设置子单元4043,用于设置产品推荐窗口的窗口皮肤为所述目标窗口皮肤。The setting subunit 4043 is used to set the window skin of the product recommendation window as the target window skin.
在一实施例中,所述第一输出子单元4044包括:In an embodiment, the first output subunit 4044 includes:
获取模块4044-1,用于获取第一预设时长内用户针对产品推荐窗口的平均换页时长;The obtaining module 4044-1 is used to obtain the average page-changing time of the user for the product recommendation window within the first preset time period;
第一设置模块4044-2,用于将所述平均换页时长设置为所述产品推荐窗口的轮询周期;The first setting module 4044-2 is configured to set the average page-changing duration as the polling period of the product recommendation window;
第二设置模块4044-3,用于依据预设规则和所述第三产品列表中的产品,设置所述产品推荐窗口的轮询页的数量和所述轮询页所包括的产品;The second setting module 4044-3 is configured to set the number of polling pages of the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
输出模块4044-4,用于控制所述产品推荐窗口按照所述轮询周期轮询输出所述轮询页。The output module 4044-4 is configured to control the product recommendation window to poll and output the polling page according to the polling cycle.
在一实施例中,所述装置还包括:In an embodiment, the device further includes:
检测单元407,用于检测是否存在对所述第三产品列表中产品的点击操作;The detection unit 407 is configured to detect whether there is a click operation on a product in the third product list;
确认单元408,用于当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品;The confirmation unit 408 is configured to, when there is the click operation, use the product corresponding to the click operation as the product to be introduced;
输出单元411,用于控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出。The output unit 411 is configured to control the obtained introduction information of the product to be introduced to be output according to a preset output mode.
在一实施例中,所述装置还包括:In an embodiment, the device further includes:
用户图像获取单元409,用于利用摄像模组获得用户图像;The user image obtaining unit 409 is used to obtain a user image by using a camera module;
识别单元410,用于通过识别所述用户图像,从所述待介绍产品关联的预设介绍信息中确定出目标介绍信息;The identification unit 410 is configured to determine target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
所述输出单元411包括:The output unit 411 includes:
第三确定子单元4111,用于从预设输出方式中确定出与所述目标介绍信息匹配的目标输出方式;The third determining subunit 4111 is configured to determine a target output mode matching the target introduction information from preset output modes;
第二输出子单元4112,用于控制所述目标介绍信息以所述目标输出方式输出。The second output subunit 4112 is configured to control the target introduction information to be output in the target output mode.
本发明还提供一种终端设备,该终端设备包括:The invention also provides a terminal device. The terminal device includes:
处理器;processor;
存储器,该存储器上存储有计算机可读指令,该计算机可读指令被处理器执行时,实现如前所示的基于数据分析的产品推荐方法。A memory, which stores computer readable instructions. When the computer readable instructions are executed by the processor, the product recommendation method based on data analysis as described above is implemented.
该终端设备可以是图1所示的基于数据分析的产品推荐装置100。The terminal device may be the product recommendation device 100 based on data analysis shown in FIG. 1.
在一示例性实施例中,本发明还提供一种计算机非易失性可读存储介质,其上存储有计算机程序,该计算机程序被处理器执行时,实现如前所示的基于数据分析的产品推荐方法。In an exemplary embodiment, the present invention also provides a computer non-volatile readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the data analysis-based Product recommendation method.
应当理解的是,本公开并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围执行各种修改和改变。本公开的范围仅由所附的权利要求来限制。It should be understood that the present disclosure is not limited to the precise structure that has been described above and shown in the drawings, and that various modifications and changes can be performed without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (28)

  1. 一种基于数据分析的产品推荐方法,其特征在于,所述方法包括:A product recommendation method based on data analysis, characterized in that the method includes:
    当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; When a product recommendation request input by the user is detected, the first product list is obtained according to the instruction of the product recommendation request;
    通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;The second product list is determined from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended;
    将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;Removing products belonging to the second product list from the first product list from the first product list to obtain a third product list;
    对所述第三产品列表中的产品做推荐处理。Recommend the products in the third product list.
  2. 根据权利要求1所述的方法,其特征在于,所述通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表,包括:The method according to claim 1, wherein determining the second product list from the general service scenario logic by analyzing the user's historical data includes:
    通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;Obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
    从通用服务场景逻辑中查找所述历史推荐产品对应的预设服务场景逻辑;Searching for the preset service scene logic corresponding to the historical recommended product from the general service scene logic;
    依据所述历史推荐产品的推荐次数和点击次数,以及所述历史推荐产品对应的预设服务场景逻辑,从所述历史推荐产品中确定出第二产品列表。The second product list is determined from the historical recommended products according to the recommended times and click times of the historical recommended products, and the preset service scene logic corresponding to the historical recommended products.
  3. 根据权利要求1或2所述的方法,其特征在于,所述对所述第三产品列表中的产品做推荐处理,包括:The method according to claim 1 or 2, wherein the recommendation processing for the products in the third product list includes:
    控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品。Control the product recommendation window to output the products in the third product list in a polling manner according to preset rules.
  4. 根据权利要求3所述的方法,其特征在于,所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品之前,所述方法还包括:The method according to claim 3, wherein before the control product recommendation window outputs the products in the third product list in a polling manner according to a preset rule, the method further comprises:
    获取用户账号关联的用户信息,所述用户信息至少包括用户年龄、性别以及职业;Obtain user information associated with a user account, where the user information includes at least the user's age, gender, and occupation;
    根据所述用户信息从预设的窗口皮肤中确定出与所述用户信息匹配的目标窗口皮肤;Determine a target window skin matching the user information from preset window skins according to the user information;
    设置产品推荐窗口的窗口皮肤为所述目标窗口皮肤。The window skin of the product recommendation window is set as the target window skin.
  5. 根据权利要求3所述的方法,其特征在于,所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品,包括:The method according to claim 3, wherein the control product recommendation window outputs the products in the third product list in a polling manner according to a preset rule, including:
    获取第一预设时长内用户针对产品推荐窗口的平均换页时长;Obtain the average page-changing time of the user recommendation window for the product within the first preset time period;
    将所述平均换页时长设置为所述产品推荐窗口的轮询周期;Setting the average page-changing duration to the polling period of the product recommendation window;
    依据预设规则和所述第三产品列表中的产品,设置所述产品推荐窗口的轮询页的数量和所述轮询页所包括的产品;Set the number of polling pages in the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
    控制所述产品推荐窗口按照所述轮询周期轮询输出所述轮询页。Controlling the product recommendation window to poll and output the polling page according to the polling cycle.
  6. 根据权利要求1所述的方法,其特征在于,所述对所述第三产品列表中的产品做推荐处理之后,所述方法还包括:The method according to claim 1, wherein after the recommendation processing is performed on the products in the third product list, the method further comprises:
    检测是否存在对所述第三产品列表中产品的点击操作;Detecting whether there is a click operation on the product in the third product list;
    当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品;When the click operation exists, the product corresponding to the click operation is taken as the product to be introduced;
    控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出。Control the obtained introduction information of the product to be introduced according to a preset output mode.
  7. 根据权利要求6所述的方法,其特征在于,所述当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品之后,以及所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出之前,所述方法还包括:The method according to claim 6, wherein when the click operation exists, the product corresponding to the click operation is taken as the product to be introduced, and the product of the product to be introduced obtained by the control Before the introduction information is output according to the preset output method, the method further includes:
    利用摄像模组获得用户图像;Use the camera module to obtain user images;
    通过识别所述用户图像,从所述待介绍产品关联的预设介绍信息中确定出目标介绍信息;Determine the target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
    所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出,包括:The introduction information of the product to be introduced obtained by the control is output according to a preset output mode, including:
    从预设输出方式中确定出与所述目标介绍信息匹配的目标输出方式;Determining a target output mode matching the target introduction information from the preset output modes;
    控制所述目标介绍信息以所述目标输出方式输出。The target introduction information is controlled to be output in the target output mode.
  8. 一种基于数据分析的产品推荐装置,其特征在于,包括:A product recommendation device based on data analysis is characterized by including:
    获取单元,用于当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; An obtaining unit, configured to obtain a first product list according to the instruction of the product recommendation request when a product recommendation request input by the user is detected;
    确定单元,用于通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;A determining unit, configured to determine a second product list from the general service scenario logic by analyzing historical data of the user; wherein, the general service scenario logic includes a product serial number and a preset service scenario logic corresponding to the product serial number, The preset service scenario logic is used to indicate that the product indicated by the corresponding product serial number is not recommended for processing;
    处理单元,用于将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;A processing unit, configured to exclude products belonging to the second product list from the first product list from the first product list to obtain a third product list;
    推荐单元,用于对所述第三产品列表中的产品做推荐处理。The recommendation unit is used for recommending the products in the third product list.
  9. 根据权利要求8所述的装置,其特征在于,所述确定单元包括:The apparatus according to claim 8, wherein the determining unit comprises:
    第一获取子单元,用于通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;The first obtaining subunit is used to obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
    查找子单元,用于从通用服务场景逻辑中查找所述历史推荐产品对应的预设服务场景逻辑;A search subunit, used to find the preset service scene logic corresponding to the historical recommended product from the general service scene logic;
    第一确定子单元,用于依据所述历史推荐产品的推荐次数和点击次数,以及所述历史推荐产品对应的预设服务场景逻辑,从所述历史推荐产品中确定出第二产品列表。The first determining subunit is configured to determine a second product list from the historical recommended products according to the recommended times and clicks of the historical recommended products and the logic of the preset service scene corresponding to the historical recommended products.
  10. 根据权利要求8或9所述的装置,其特征在于,所述推荐单元包括:The device according to claim 8 or 9, wherein the recommendation unit comprises:
    第一输出子单元,用于控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品。The first output subunit is used to control the product recommendation window to output the products in the third product list in a polling manner according to a preset rule.
  11. 根据权利要求10所述的装置,其特征在于,还包括:The device according to claim 10, further comprising:
    第二获取子单元,用于获取用户账号关联的用户信息,所述用户信息至少包括用户年龄、性别以及职业;The second obtaining subunit is used to obtain user information associated with the user account, where the user information includes at least the user's age, gender, and occupation;
    第二确定子单元,用于根据所述用户信息从预设的窗口皮肤中确定出与所述用户信息匹配的目标窗口皮肤;A second determining subunit, configured to determine a target window skin matching the user information from preset window skins according to the user information;
    设置子单元,用于设置产品推荐窗口的窗口皮肤为所述目标窗口皮肤。A setting subunit is used to set the window skin of the product recommendation window as the target window skin.
  12. 根据权利要求10所述的装置,其特征在于,所述第一输出子单元包括:The apparatus according to claim 10, wherein the first output subunit comprises:
    获取模块,用于获取第一预设时长内用户针对产品推荐窗口的平均换页时长;An obtaining module, configured to obtain the average page-changing time of the user's product recommendation window within the first preset time period;
    第一设置模块,用于将所述平均换页时长设置为所述产品推荐窗口的轮询周期;A first setting module, configured to set the average page-breaking time as the polling period of the product recommendation window;
    第二设置模块,用于依据预设规则和所述第三产品列表中的产品,设置所述产品推荐窗口的轮询页的数量和所述轮询页所包括的产品;A second setting module, configured to set the number of polling pages of the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
    输出模块,用于控制所述产品推荐窗口按照所述轮询周期轮询输出所述轮询页。The output module is configured to control the product recommendation window to poll and output the polling page according to the polling cycle.
  13. 根据权利要求8所述的装置,其特征在于,还包括:The device according to claim 8, further comprising:
    检测单元,用于检测是否存在对所述第三产品列表中产品的点击操作;A detection unit, configured to detect whether there is a click operation on a product in the third product list;
    确认单元,用于当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品;The confirmation unit is configured to use the product corresponding to the click operation as the product to be introduced when the click operation exists;
    输出单元,用于控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出。The output unit is used to control the obtained introduction information of the product to be introduced to be output according to a preset output mode.
  14. 根据权利要求13所述的装置,其特征在于,还包括:The device according to claim 13, further comprising:
    用户图像获取单元,用于利用摄像模组获得用户图像;User image acquisition unit, used to obtain user images using camera modules;
    识别单元,用于通过识别所述用户图像,从所述待介绍产品关联的预设介绍信息中确定出目标介绍信息;A recognition unit, configured to determine target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
    所述输出单元包括:The output unit includes:
    第三确定子单元,用于从预设输出方式中确定出与所述目标介绍信息匹配的目标输出方式;A third determining subunit, configured to determine a target output mode matching the target introduction information from preset output modes;
    第二输出子单元,用于控制所述目标介绍信息以所述目标输出方式输出。The second output subunit is used to control the target introduction information to be output in the target output mode.
  15. 一种计算机非易失性可读存储介质,其特征在于,其存储计算机程序,所述计算机程序在被处理器执行时使得处理器执行以下处理:A computer non-volatile readable storage medium, characterized in that it stores a computer program, which when executed by a processor causes the processor to perform the following processing:
    当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; When a product recommendation request input by the user is detected, the first product list is obtained according to the instruction of the product recommendation request;
    通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;The second product list is determined from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended;
    将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;Removing products belonging to the second product list from the first product list from the first product list to obtain a third product list;
    对所述第三产品列表中的产品做推荐处理。Recommend the products in the third product list.
  16. 根据权利要求15所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表时执行如下处理:The storage medium according to claim 15, wherein the computer program, when executed by the processor, causes the processor to execute when the second product list is determined from the general service scenario logic by analyzing the user's historical data Process as follows:
    通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;Obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
    从通用服务场景逻辑中查找所述历史推荐产品对应的预设服务场景逻辑;Searching for the preset service scene logic corresponding to the historical recommended product from the general service scene logic;
    依据所述历史推荐产品的推荐次数和点击次数,以及所述历史推荐产品对应的预设服务场景逻辑,从所述历史推荐产品中确定出第二产品列表。The second product list is determined from the historical recommended products according to the recommended times and click times of the historical recommended products, and the preset service scene logic corresponding to the historical recommended products.
  17. 根据权利要求15或16所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述对所述第三产品列表中的产品做推荐处理时执行如下处理:The storage medium according to claim 15 or 16, wherein the computer program, when executed by the processor, causes the processor to perform the following processing when the recommendation processing is performed on the products in the third product list:
    控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品。Control the product recommendation window to output the products in the third product list in a polling manner according to preset rules.
  18. 根据权利要求17所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品之前执行如下处理:The storage medium according to claim 17, wherein when the computer program is executed by the processor, the processor causes the processor to output the third product list in a polling manner according to a preset rule in the control product recommendation window Of products before the following processing:
    获取用户账号关联的用户信息,所述用户信息至少包括用户年龄、性别以及职业;Obtain user information associated with a user account, where the user information includes at least the user's age, gender, and occupation;
    根据所述用户信息从预设的窗口皮肤中确定出与所述用户信息匹配的目标窗口皮肤;Determine a target window skin matching the user information from preset window skins according to the user information;
    设置产品推荐窗口的窗口皮肤为所述目标窗口皮肤。The window skin of the product recommendation window is set as the target window skin.
  19. 根据权利要求17所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品时执行如下处理:The storage medium according to claim 17, wherein when the computer program is executed by the processor, the processor causes the processor to output the third product list in a polling manner according to a preset rule in the control product recommendation window The product is executed as follows:
    获取第一预设时长内用户针对产品推荐窗口的平均换页时长;Obtain the average page-changing time of the user recommendation window for the product within the first preset time period;
    将所述平均换页时长设置为所述产品推荐窗口的轮询周期;Setting the average page-changing duration to the polling period of the product recommendation window;
    依据预设规则和所述第三产品列表中的产品,设置所述产品推荐窗口的轮询页的数量和所述轮询页所包括的产品;Set the number of polling pages of the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
    控制所述产品推荐窗口按照所述轮询周期轮询输出所述轮询页。Controlling the product recommendation window to poll and output the polling page according to the polling cycle.
  20. 根据权利要求15所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述对所述第三产品列表中的产品做推荐处理之后执行如下处理:The storage medium according to claim 15, wherein the computer program, when executed by the processor, causes the processor to perform the following processing after the recommendation processing of the products in the third product list:
    检测是否存在对所述第三产品列表中产品的点击操作;Detecting whether there is a click operation on the product in the third product list;
    当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品;When the click operation exists, the product corresponding to the click operation is taken as the product to be introduced;
    控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出。Control the obtained introduction information of the product to be introduced according to a preset output mode.
  21. 根据权利要求20所述的存储介质,其特征在于,所述计算机程序在被处理器执行时使得处理器在所述当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品之后,以及所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出之前执行如下处理:The storage medium according to claim 20, wherein the computer program, when executed by the processor, causes the processor to use the product corresponding to the click operation as the product to be introduced when the click operation exists After that, and before the introduction information of the product to be introduced obtained by the control is output according to the preset output mode, the following processing is performed:
    利用摄像模组获得用户图像;Use the camera module to obtain user images;
    通过识别所述用户图像,从所述待介绍产品关联的预设介绍信息中确定出目标介绍信息;Determine the target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
    所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出,包括:The introduction information of the product to be introduced obtained by the control is output according to a preset output mode, including:
    从预设输出方式中确定出与所述目标介绍信息匹配的目标输出方式;Determining a target output mode matching the target introduction information from the preset output modes;
    控制所述目标介绍信息以所述目标输出方式输出。The target introduction information is controlled to be output in the target output mode.
  22. 一种终端设备,其特征在于,所述终端设备包括:A terminal device, characterized in that the terminal device includes:
    处理器;processor;
    存储器,所述存储器上存储有计算机可读指令,所述计算机可读指令被所述处理器执行时使得处理器执行以下处理:A memory, on which computer-readable instructions are stored, which when executed by the processor causes the processor to perform the following processing:
    当检测到用户输入的产品推荐请求时,依据所述产品推荐请求的指示获取第一产品列表; When a product recommendation request input by the user is detected, the first product list is obtained according to the instruction of the product recommendation request;
    通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表;其中,所述通用服务场景逻辑中包含有产品序号以及所述产品序号对应的预设服务场景逻辑,所述预设服务场景逻辑用于表示对其对应的产品序号所指示的产品做不推荐处理;The second product list is determined from the general service scenario logic by analyzing the user's historical data; wherein, the general service scenario logic includes the product serial number and the preset service scenario logic corresponding to the product serial number, the preset service The scene logic is used to indicate that the product indicated by the corresponding product serial number is not recommended;
    将所述第一产品列表中属于所述第二产品列表的产品从所述第一产品列表中剔除得到第三产品列表;Removing products belonging to the second product list from the first product list from the first product list to obtain a third product list;
    对所述第三产品列表中的产品做推荐处理。Recommend the products in the third product list.
  23. 根据权利要求22所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述通过分析用户的历史数据,从通用服务场景逻辑中确定第二产品列表时执行如下处理:The terminal device according to claim 22, wherein when the computer-readable instructions are executed by the processor, the processor determines the second product from the general service scenario logic by analyzing historical data of the user Perform the following processing when listing:
    通过分析用户的历史数据获得历史推荐产品的推荐次数和点击次数;Obtain the recommended times and clicks of historically recommended products by analyzing the user's historical data;
    从通用服务场景逻辑中查找所述历史推荐产品对应的预设服务场景逻辑;Searching for the preset service scene logic corresponding to the historical recommended product from the general service scene logic;
    依据所述历史推荐产品的推荐次数和点击次数,以及所述历史推荐产品对应的预设服务场景逻辑,从所述历史推荐产品中确定出第二产品列表。The second product list is determined from the historical recommended products according to the recommended times and click times of the historical recommended products, and the preset service scene logic corresponding to the historical recommended products.
  24. 根据权利要求22或23所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述对所述第三产品列表中的产品做推荐处理时执行如下处理:The terminal device according to claim 22 or 23, characterized in that, when the computer-readable instructions are executed by the processor, the processor is executed when the recommendation processing for the products in the third product list is performed Process as follows:
    控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品。Control the product recommendation window to output the products in the third product list in a polling manner according to preset rules.
  25. 根据权利要求24所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品之前执行如下处理:The terminal device according to claim 24, wherein when the computer-readable instructions are executed by the processor, the processor causes the processor to output the third in a polling manner according to a preset rule in the control product recommendation window The products in the product list perform the following processing before:
    获取用户账号关联的用户信息,所述用户信息至少包括用户年龄、性别以及职业;Obtain user information associated with a user account, where the user information includes at least the user's age, gender, and occupation;
    根据所述用户信息从预设的窗口皮肤中确定出与所述用户信息匹配的目标窗口皮肤;Determine a target window skin matching the user information from preset window skins according to the user information;
    设置产品推荐窗口的窗口皮肤为所述目标窗口皮肤。The window skin of the product recommendation window is set as the target window skin.
  26. 根据权利要求24所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述控制产品推荐窗口按照预设规则以轮询方式输出所述第三产品列表中的产品时执行如下处理:The terminal device according to claim 24, wherein when the computer-readable instructions are executed by the processor, the processor causes the processor to output the third in a polling manner according to a preset rule in the control product recommendation window The products in the product list are processed as follows:
    获取第一预设时长内用户针对产品推荐窗口的平均换页时长;Obtain the average page-changing time of the user recommendation window for the product within the first preset time period;
    将所述平均换页时长设置为所述产品推荐窗口的轮询周期;Setting the average page-changing duration to the polling period of the product recommendation window;
    依据预设规则和所述第三产品列表中的产品,设置所述产品推荐窗口的轮询页的数量和所述轮询页所包括的产品;Set the number of polling pages of the product recommendation window and the products included in the polling page according to preset rules and products in the third product list;
    控制所述产品推荐窗口按照所述轮询周期轮询输出所述轮询页。Controlling the product recommendation window to poll and output the polling page according to the polling cycle.
  27. 根据权利要求22所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述对所述第三产品列表中的产品做推荐处理之后执行如下处理:The terminal device according to claim 22, wherein when the computer-readable instructions are executed by the processor, the processor causes the processor to perform the following processing after the recommendation processing of the products in the third product list :
    检测是否存在对所述第三产品列表中产品的点击操作;Detecting whether there is a click operation on the product in the third product list;
    当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品;When the click operation exists, the product corresponding to the click operation is taken as the product to be introduced;
    控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出。Control the obtained introduction information of the product to be introduced according to a preset output mode.
  28. 根据权利要求27所述的终端设备,其特征在于,所述计算机可读指令被所述处理器执行时使得处理器在所述当存在所述点击操作时,将所述点击操作对应的产品作为待介绍产品之后,以及所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出之前执行如下处理:The terminal device according to claim 27, wherein when the computer-readable instructions are executed by the processor, the processor makes the product corresponding to the click operation as the product corresponding to the click operation when the click operation exists After the product to be introduced, and before the introduction information of the product to be introduced obtained by the control is output according to the preset output mode, the following processing is performed:
    利用摄像模组获得用户图像;Use the camera module to obtain user images;
    通过识别所述用户图像,从所述待介绍产品关联的预设介绍信息中确定出目标介绍信息;Determine the target introduction information from the preset introduction information associated with the product to be introduced by identifying the user image;
    所述控制获取到的所述待介绍产品的介绍信息按照预设输出方式进行输出,包括:The introduction information of the product to be introduced obtained by the control is output according to a preset output mode, including:
    从预设输出方式中确定出与所述目标介绍信息匹配的目标输出方式;Determining a target output mode matching the target introduction information from the preset output modes;
    控制所述目标介绍信息以所述目标输出方式输出。The target introduction information is controlled to be output in the target output mode.
PCT/CN2019/090831 2018-12-19 2019-06-12 Product recommendation method and apparatus based on data analysis and terminal device WO2020124962A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811556324.8A CN109785049A (en) 2018-12-19 2018-12-19 A kind of Products Show method, apparatus and terminal device based on data analysis
CN201811556324.8 2018-12-19

Publications (1)

Publication Number Publication Date
WO2020124962A1 true WO2020124962A1 (en) 2020-06-25

Family

ID=66497315

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/090831 WO2020124962A1 (en) 2018-12-19 2019-06-12 Product recommendation method and apparatus based on data analysis and terminal device

Country Status (2)

Country Link
CN (1) CN109785049A (en)
WO (1) WO2020124962A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112101980A (en) * 2020-08-04 2020-12-18 北京思特奇信息技术股份有限公司 Method and system for analyzing purchase preference of user

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109785049A (en) * 2018-12-19 2019-05-21 平安科技(深圳)有限公司 A kind of Products Show method, apparatus and terminal device based on data analysis
CN110415101A (en) * 2019-06-19 2019-11-05 深圳壹账通智能科技有限公司 Products Show test method, device, computer equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106462615A (en) * 2014-06-03 2017-02-22 索尼公司 Information processing device, information presentation method, program, and system
CN108921655A (en) * 2018-06-20 2018-11-30 深圳正品创想科技有限公司 Method of Commodity Recommendation and its device, server based on anti-fake information of tracing to the source
CN109785049A (en) * 2018-12-19 2019-05-21 平安科技(深圳)有限公司 A kind of Products Show method, apparatus and terminal device based on data analysis

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150227972A1 (en) * 2014-02-07 2015-08-13 Huang (Joy) Tang System and methods for identifying and promoting tagged commercial products
CN106600302A (en) * 2015-10-19 2017-04-26 玺阅信息科技(上海)有限公司 Hadoop-based commodity recommendation system
CN105512909A (en) * 2015-11-26 2016-04-20 小米科技有限责任公司 Commodity recommendation method apparatus
CN108230058B (en) * 2016-12-09 2022-05-13 阿里巴巴集团控股有限公司 Product recommendation method and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106462615A (en) * 2014-06-03 2017-02-22 索尼公司 Information processing device, information presentation method, program, and system
CN108921655A (en) * 2018-06-20 2018-11-30 深圳正品创想科技有限公司 Method of Commodity Recommendation and its device, server based on anti-fake information of tracing to the source
CN109785049A (en) * 2018-12-19 2019-05-21 平安科技(深圳)有限公司 A kind of Products Show method, apparatus and terminal device based on data analysis

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112101980A (en) * 2020-08-04 2020-12-18 北京思特奇信息技术股份有限公司 Method and system for analyzing purchase preference of user
CN112101980B (en) * 2020-08-04 2024-04-02 北京思特奇信息技术股份有限公司 Method and system for analyzing purchasing preference of user

Also Published As

Publication number Publication date
CN109785049A (en) 2019-05-21

Similar Documents

Publication Publication Date Title
US11132547B2 (en) Emotion recognition-based artwork recommendation method and device, medium, and electronic apparatus
US11264021B2 (en) Method for intent-based interactive response and electronic device thereof
CN104079962B (en) A kind of method and device for pushing recommendation information
EP3334127A1 (en) Message pushing method and apparatus thereof
US9852375B2 (en) Techniques for mobile prediction
US20160026272A1 (en) Method for displaying screen in electronic device, and electronic device thereof
US20170286058A1 (en) Multimedia data processing method of electronic device and electronic device thereof
US20200007948A1 (en) Video subtitle display method and apparatus
US11374925B2 (en) Method and system for authenticating customers on call
WO2020124962A1 (en) Product recommendation method and apparatus based on data analysis and terminal device
US20140324623A1 (en) Display apparatus for providing recommendation information and method thereof
US10034151B2 (en) Method for providing point of interest and electronic device thereof
US20240232949A1 (en) Method and system for gesture-based cross channel commerce and marketing
US20220277204A1 (en) Model training method and apparatus for information recommendation, electronic device and medium
CN108681871B (en) Information prompting method, terminal equipment and computer readable storage medium
CN108984628B (en) Loss value obtaining method and device of content description generation model
US20240171679A1 (en) Systems and methods for generating customized customer service menu
CN112287713A (en) Two-dimensional code identification method and device
US20230110006A1 (en) Electronic apparatus and controlling method thereof
US20220067213A1 (en) Subliminal Software Detection
US11233953B2 (en) Image editing method and electronic device supporting same
KR102255369B1 (en) Method for providing alternative service and electronic device thereof
CN110334177B (en) Semantic similarity model training and semantic similarity recognition methods and devices and electronic equipment
US10419555B2 (en) Computing system and methods for associating computing devices
CN113392238A (en) Media file processing method and device, computer readable medium and electronic equipment

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: 19899817

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: 19899817

Country of ref document: EP

Kind code of ref document: A1