CN106909629B - Method and system for individually recommending pit bit labels - Google Patents

Method and system for individually recommending pit bit labels Download PDF

Info

Publication number
CN106909629B
CN106909629B CN201710057487.0A CN201710057487A CN106909629B CN 106909629 B CN106909629 B CN 106909629B CN 201710057487 A CN201710057487 A CN 201710057487A CN 106909629 B CN106909629 B CN 106909629B
Authority
CN
China
Prior art keywords
user
label
pit
unit
score
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710057487.0A
Other languages
Chinese (zh)
Other versions
CN106909629A (en
Inventor
谢晋
柴楹
黄承松
夏里峰
宋书俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Qimi Network Technology Co ltd
Original Assignee
Wuhan Qimi Network Technology Co ltd
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 Wuhan Qimi Network Technology Co ltd filed Critical Wuhan Qimi Network Technology Co ltd
Priority to CN201710057487.0A priority Critical patent/CN106909629B/en
Publication of CN106909629A publication Critical patent/CN106909629A/en
Application granted granted Critical
Publication of CN106909629B publication Critical patent/CN106909629B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • 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
    • G06Q30/0601Electronic shopping [e-shopping]

Landscapes

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

Abstract

The invention discloses a method for individually recommending pit bit labels, which is characterized by comprising the following steps: collecting user browsing information and client browsing behaviors; calculating the weight value of the user preference label according to the browsing information of the user and the browsing behavior of the client; judging whether a condition for displaying a recommended pit position label is met before loading the next screen commodity flow each time; and if the condition of displaying the pit bit label is met, displaying the pit bit label. According to the method and the system for recommending the pit bit label in the personalized manner, the pit bit label is recommended to the user in the personalized manner by collecting, calculating and judging the browsing information of the user, so that the interest point of the user can be captured in real time in the process that the user views the commodity stream, the current interest point of the user is displayed in a gathering manner by selecting a proper position in the process that the user turns over the screen, the information of the commodity which the user is interested in can be focused timely in the browsing process of the user, the fun of shopping in the commodity stream cannot be lost, and the consumption experience of the user is improved.

Description

Method and system for individually recommending pit bit labels
Technical Field
The present invention relates to a method and a system for recommending pit bit labels, and more particularly, to a method and a system for recommending pit bit labels individually.
Background
Currently, an electronic commerce platform App end usually displays a commodity set in a commodity flow form, which is determined by the characteristics of a mobile phone, and the main modes of the current commodity flow display include (but are not limited to):
(1) aggregating all category brands of the total station, arranging all category brands in a certain matching mode, for example, each category continuously occupies three pit positions, the categories are sequentially arranged in a certain sequencing mode, and the like;
(2) focusing on a certain top class, such as home appliances for men and women, the types of commodity subdivision under the class are various, so that a commodity queue of a single class is displayed in a commodity flow, and the collocation mode is similar to that of the commodity queue (1);
(3) guessing you like a commodity queue, and recommending a similar commodity queue according to the interested category, brand or commodity of the user.
Due to the characteristics of commodity flow, users can easily turn down the commodities, and the commodities displayed on one screen are limited, so that the commodity queue is displayed in a category mixed arrangement mode, and the users can find different commodities in a small space as much as possible.
But the disadvantage is also obvious, when users meet the categories, brands and commodities which are interested by the users, the users want to compare transversely, which is very troublesome, the users have to jump out the current commodity flow to search or subdivide the categories to find more similar categories, and the operation is very inconvenient.
Disclosure of Invention
The invention aims to overcome the defects of the background technology, and provides a method and a system for recommending pit position labels in a personalized manner, so that the method and the system can capture the interest points of a user in real time in the process of checking commodity streams by the user, select proper positions to display the current interest points of the user in a gathering manner in the process of turning over a screen of the user, are convenient for the user to timely focus interested commodity information in the browsing process, and can not lose the fun of shopping in the commodity streams.
The invention provides a method for individually recommending pit bit labels, which comprises the following steps:
s1: collecting user browsing information and client browsing behaviors;
s2: calculating the weight value of the user preference label according to the browsing information of the user and the browsing behavior of the client;
s3: judging whether a condition for displaying a recommended pit position label is met before loading the next screen commodity flow each time;
s4: the pit bit flag is presented if the condition for presenting the pit bit flag is reached, otherwise, it returns to S1.
The invention provides a system for individually recommending pit bit labels, which comprises:
the user information collecting unit is used for collecting user browsing information and client browsing behaviors;
the weighted value calculating unit of the user preference label is used for calculating the weighted value of the user preference label according to the browsing information of the user and the browsing behavior of the client;
judging whether a display recommended pit position label unit is reached or not, wherein the display recommended pit position label unit is used for judging whether a condition for displaying a recommended pit position label is reached or not before loading the next screen commodity flow each time;
and the display pit label unit is used for displaying the pit label for the user meeting the condition of displaying the pit label.
Has the advantages that: according to the method and the system for recommending the pit bit label in the personalized manner, the pit bit label is recommended to the user in the personalized manner by collecting, calculating and judging the browsing information of the user, so that the interest point of the user can be captured in real time in the process that the user views the commodity stream, the current interest point of the user is displayed in a gathering manner by selecting a proper position in the process that the user turns over the screen, the information of the commodity which the user is interested in can be focused timely in the browsing process of the user, the fun of shopping in the commodity stream cannot be lost, and the consumption experience of the user is improved.
Drawings
Fig. 1 is a flowchart of a method for personalized recommendation of pit bit tags according to an embodiment of the present invention;
fig. 2 is a block diagram of a system for personalized recommendation of pit site tags according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating an overall implementation of a method and a system for recommending pit bit labels in a personalized manner according to an embodiment of the present invention.
Detailed Description
The invention is described in detail below with reference to the drawings and examples, and the description in this section is only exemplary and explanatory and should not be construed as limiting the scope of the invention in any way.
As shown in fig. 1, an embodiment of the present invention provides a flowchart of a method for individually recommending pit bit tags, including the following steps:
as shown in FIG. 1, at 110, the system collects user browsing information and client browsing behavior, specifically, the client browsing information includes categories, brands, commodities and attributes of commodities preferred by the user; the user browsing behaviors comprise collecting and adding a car;
as shown in fig. 1, in 120, the system calculates a weight value of a user preference tag according to browsing information of a user and browsing behavior of a client, where the method for calculating the weight value of the user preference tag includes: calculating according to Score (user historical browsing behavior) HW + Score (user current browsing behavior) CW;
wherein HW is historical score weight, CW is current score weight, obtain the category score change brought by browsing the goods at present; the behaviors of other non-current commodities of the user are correspondingly attenuated according to Score (user historical browsing behavior) × AW (AW is a forgetting factor), wherein the forgetting factor aims to attenuate to zero the categories which are not browsed for more than 10 times, namely, the categories are eliminated from a preference queue of the user; the collection and vehicle-adding operation modes are similar, except that the CW is different, the browsed CW preset value is 0.1, the collection is 0.5, and the vehicle-adding is 0.6, which respectively represent the contribution degrees of different behaviors to preference scores; after the label is displayed in the position of the commodity stream pit, the displayed category, brand and attribute Score are attenuated by 50% according to a Score (user history browsing behavior) × 0.5 mode.
As shown in fig. 1, in 130, the system determines whether a condition for displaying a recommended pit position tag is met before loading the next screen of commodity stream, where the condition for displaying the recommended pit position tag includes:
(1) whether the weight score of the user preference label exceeds a threshold value of 0.5 or not is judged, when the user collects or adds the vehicle, the condition can be directly met due to the fact that the default weight > is 0.5, but the browsing behavior can be met only by continuously accumulating more than 5 times, and other logics are analogized;
(2) whether the mark belongs to the fatigue period or not, and when the mark recommends pit display, the subsequent two continuous screens are used as the fatigue period, and the mark cannot be displayed even if the condition (1) is met in the period;
(3) the user preference category, the brand, the commodity and the commodity attribute quantity are judged, 10 tags need to be displayed according to the display strategy of the tags, the preference category or the mixed brand and attribute tags are at least contained, and if the number of the tags preferred by the current user is less than 10, the tags cannot be displayed even if the conditions (1) and (2) are met.
As shown in fig. 1, in 130, if the system reaches the condition of displaying the pit bit label, the system displays the pit bit label, otherwise, the system returns to 110, and the method for displaying the pit bit label includes:
(1) preferably selecting 5 Top commodities for each category, and then randomly extracting 3-4 commodities from the Top commodities of each category in sequence to be loaded into a commodity queue;
(2) extracting the Top1 brand preferred under each category and sequentially loading the Top1 brand into a commodity queue;
(3) and extracting the Top1 attribute preferred under each category and loading the Top1 attribute into a commodity queue in turn.
As shown in fig. 2, a system for personalized recommendation of pit bit labels includes a user information collecting unit 210, a weight value calculating unit 220 of user preference labels, a unit 230 for judging whether a displayed recommended pit bit label is reached, and a displayed pit bit label unit 240.
The user information collecting unit 210 is configured to collect user browsing information and a client browsing behavior, specifically, as shown in fig. 3, the user information collecting unit 210 includes a collecting unit 211 of categories, brands, commodities, and attributes of commodities preferred by a user, and a user browsing behavior collecting unit 212, where the user browsing behavior collecting unit 212 includes a user collecting behavior unit 2121 and a user boarding behavior unit 2122;
the weighted value calculating unit 220 of the user preference tag is configured to calculate a weighted value of the user preference tag according to the browsing information of the user and the browsing behavior of the client, specifically, as shown in fig. 3, the weighted value calculating unit 220 of the user preference tag includes a history score weight calculating unit 221 and a current score weight score calculating unit 222, the history score weight calculating unit 221 performs score weight calculation on the history browsing information of the user, and the current score weight score calculating unit 222 performs score weight calculation on the current browsing information of the user.
The judging unit 230 is configured to judge whether a condition for displaying a recommended pit position label is met before loading a next screen commodity flow, and specifically, as shown in fig. 3, the judging unit 230 includes a weight value judging unit 231 for a user preference label, a user fatigue period judging unit 232, and a user preference number judging unit 233, browsing information sequentially passes through the weight value judging unit 231 for the user preference label, the user fatigue period judging unit 232, and the user preference number judging unit 233, and all three units pass through the three units to meet the requirement of the pit position label, the weight value judging unit 231 for the user preference label is configured to judge whether a weight score of the user preference label has a threshold value exceeding 0.5, and when a user has a collection or adds a vehicle, the default weight > is 0.5, so that the condition can be directly met, but the browsing behavior needs to be continuously accumulated for more than 5 times to be satisfied, and the rest logic is analogized; the user fatigue period judging unit 232 is configured to judge whether the user belongs to a fatigue period, and when the tag recommends pit position display, two subsequent continuous screens are used as the fatigue period, and the subsequent continuous screens cannot be displayed even if the judging condition of the weight value judging unit of the user preference tag is met; the user preference number judging unit 233 is configured to judge the number of user preference categories, brands, commodities, and commodity attributes, and according to a display policy of the tags, 10 tags need to be displayed, and at least includes the preference categories or mixed brands and attribute tags, and if the number of tags preferred by the current user is less than 10, the tags cannot be displayed even if the conditions of the weight value judging unit of the user preference tags and the user fatigue period judging unit are satisfied.
The display pit position label unit 240 is configured to display a pit position label for a user meeting a condition of displaying the pit position label, and specifically, as shown in fig. 3, the display pit position label unit 240 includes a category label unit 241, a brand label unit 242, and an attribute label unit 243; the category labeling unit 241 is configured to optimally select 5 Top commodities for each category, and then randomly extract 3 to 4 commodities from the Top commodities of each category in sequence to load the commodities into a commodity queue; the brand label unit 242 is configured to extract Top1 brands preferred under each category and load the Top1 brands into a commodity queue in sequence; the attribute labeling unit 243 is used for extracting Top1 attributes preferred under each category and loading the Top1 attributes into the commodity queue in turn.
According to the method and the system for recommending the pit bit label in the personalized manner, the pit bit label is recommended to the user in the personalized manner by collecting, calculating and judging the browsing information of the user, so that the interest point of the user can be captured in real time in the process that the user views the commodity stream, the current interest point of the user is displayed in a gathering manner by selecting a proper position in the process that the user turns over the screen, the information of the commodity which the user is interested in can be focused timely in the browsing process of the user, the fun of shopping in the commodity stream cannot be lost, and the consumption experience of the user is improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (9)

1. A method for individually recommending pit bit labels is characterized by comprising the following steps:
s1: collecting user browsing information and client browsing behaviors;
s2: calculating the weight value of the user preference label according to the browsing information of the user and the browsing behavior of the client;
s3: judging whether a condition for displaying a recommended pit position label is met before loading the next screen commodity flow each time;
s4: displaying the pit bit label if the condition of displaying the pit bit label is met, or returning to S1;
the method for calculating the weight value of the user preference label comprises the following steps: calculating according to Score (user historical browsing behavior) HW + Score (user current browsing behavior) CW;
wherein HW is historical score weight, CW is current score weight, obtain the category score change brought by browsing the goods at present; the behaviors of other non-current commodities of the user are correspondingly attenuated according to Score (user historical browsing behavior) × AW (AW is a forgetting factor), wherein the forgetting factor aims to attenuate to zero the categories which are not browsed for more than 10 times, namely, the categories are eliminated from a preference queue of the user; the collection and vehicle-adding operation modes are similar, except that the CW is different, the browsed CW preset value is 0.1, the collection is 0.5, and the vehicle-adding is 0.6, which respectively represent the contribution degrees of different behaviors to preference scores; after the label is displayed in the position of the commodity stream pit, the displayed category, brand and attribute Score are attenuated by 50% according to a Score (user history browsing behavior) × 0.5 mode.
2. The method for personalized recommendation of pit bit labels as claimed in claim 1, wherein: the client browsing information comprises categories, brands, commodities and attributes of the commodities preferred by the user; the user browsing behaviors comprise collecting and adding the car.
3. The method for personalized recommendation of pit bit labels as claimed in claim 1, wherein: the conditions for displaying the recommended pit bit label comprise:
(1) whether the weight score of the user preference label exceeds a threshold value of 0.5 or not is judged, when the user collects or adds the vehicle, the condition can be directly met due to the fact that the default weight > is 0.5, but the browsing behavior can be met only by continuously accumulating more than 5 times, and other logics are analogized;
(2) whether the mark belongs to the fatigue period or not, and when the mark recommends pit display, the subsequent two continuous screens are used as the fatigue period, and the mark cannot be displayed even if the condition (1) is met in the period;
(3) the user preference category, the brand, the commodity and the commodity attribute quantity are judged, 10 tags need to be displayed according to the display strategy of the tags, the preference category or the mixed brand and attribute tags are at least contained, and if the number of the tags preferred by the current user is less than 10, the tags cannot be displayed even if the conditions (1) and (2) are met.
4. The method for personalized recommendation of pit bit labels as claimed in claim 1, wherein: the display method of the pit bit label comprises the following steps:
(1) preferably selecting 5 Top commodities for each category, and then randomly extracting 3-4 commodities from the Top commodities of each category in sequence to be loaded into a commodity queue;
(2) extracting the Top1 brand preferred under each category and sequentially loading the Top1 brand into a commodity queue;
(3) and extracting the Top1 attribute preferred under each category and loading the Top1 attribute into a commodity queue in turn.
5. A system for personalizing a recommended pit site tag, comprising:
the user information collecting unit is used for collecting user browsing information and client browsing behaviors;
the weighted value calculating unit of the user preference label is used for calculating the weighted value of the user preference label according to the browsing information of the user and the browsing behavior of the client;
judging whether a display recommended pit position label unit is reached or not, wherein the display recommended pit position label unit is used for judging whether a condition for displaying a recommended pit position label is reached or not before loading the next screen commodity flow each time;
the exhibition pit label unit is used for exhibiting the pit label for the user meeting the condition of exhibiting the pit label;
the method for calculating the weight value of the user preference label comprises the following steps: calculating according to Score (user historical browsing behavior) HW + Score (user current browsing behavior) CW;
wherein HW is historical score weight, CW is current score weight, obtain the category score change brought by browsing the goods at present; the behaviors of other non-current commodities of the user are correspondingly attenuated according to Score (user historical browsing behavior) × AW (AW is a forgetting factor), wherein the forgetting factor aims to attenuate to zero the categories which are not browsed for more than 10 times, namely, the categories are eliminated from a preference queue of the user; the collection and vehicle-adding operation modes are similar, except that the CW is different, the browsed CW preset value is 0.1, the collection is 0.5, and the vehicle-adding is 0.6, which respectively represent the contribution degrees of different behaviors to preference scores; after the label is displayed in the position of the commodity stream pit, the displayed category, brand and attribute Score are attenuated by 50% according to a Score (user history browsing behavior) × 0.5 mode.
6. The system for personalized recommendation of pit site tags according to claim 5, wherein: the user information collecting unit comprises a collecting unit for categories, brands, commodities and attributes of the commodities preferred by the user; the user browsing behavior collection unit comprises a user collection behavior unit and a user car-adding behavior unit.
7. The system for personalized recommendation of pit site tags according to claim 5, wherein: the weight value calculation unit of the user preference label comprises a history score weight calculation unit and a current score weight score calculation unit, the history score weight calculation unit carries out score weight calculation on the history browsing information of the user, and the current score weight score calculation unit carries out score weight calculation on the current browsing information of the user.
8. The system for personalized recommendation of pit site tags according to claim 5, wherein: the unit for judging whether the displayed recommended pit position label is reached comprises a weight value judging unit of a user preference label, a user fatigue period judging unit and a user preference quantity judging unit, browsing information sequentially passes through the weight value judging unit of the user preference label, the user fatigue period judging unit and the user preference quantity judging unit, the three units meet the requirement of the pit position label when passing through, the weight value judging unit of the user preference label is used for judging whether the weight score of the user preference label has a threshold value exceeding 0.5, when a user collects or adds a vehicle, the condition can be directly met, but the browsing behavior can be met only by continuously accumulating more than 5 times, and other logics are analogized accordingly; the user fatigue period judging unit is used for judging whether the user belongs to a fatigue period, when the tag recommends pit position display, the subsequent two continuous screens are used as the fatigue period, and the subsequent two continuous screens cannot be displayed even if the judging condition of the weight value judging unit of the user preference tag is met; the user preference quantity judging unit is used for judging the quantity of user preference categories, brands, commodities and commodity attributes, 10 tags need to be displayed according to the display strategy of the tags, and the tags at least contain the preference categories or mixed brands and attribute tags, and if the quantity of the tags preferred by the current user is less than 10, the tags cannot be displayed even if the conditions of the weight value judging unit of the user preference tags and the user fatigue period judging unit are met.
9. The system for personalized recommendation of pit site tags according to claim 5, wherein: the display pit position label unit comprises a category label unit, a brand label unit and an attribute label unit; the category label unit is used for preferably selecting 5 Top commodities for each category, and then randomly extracting 3-4 commodities from the Top commodities of each category in sequence and loading the commodities into a commodity queue; the brand label unit is used for extracting the Top1 brands preferred under each category and sequentially loading the Top1 brands into a commodity queue; the attribute tag unit is used for extracting the Top1 attribute preferred under each category and loading the Top1 attribute into the commodity queue in turn.
CN201710057487.0A 2017-01-26 2017-01-26 Method and system for individually recommending pit bit labels Active CN106909629B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710057487.0A CN106909629B (en) 2017-01-26 2017-01-26 Method and system for individually recommending pit bit labels

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710057487.0A CN106909629B (en) 2017-01-26 2017-01-26 Method and system for individually recommending pit bit labels

Publications (2)

Publication Number Publication Date
CN106909629A CN106909629A (en) 2017-06-30
CN106909629B true CN106909629B (en) 2020-05-19

Family

ID=59207535

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710057487.0A Active CN106909629B (en) 2017-01-26 2017-01-26 Method and system for individually recommending pit bit labels

Country Status (1)

Country Link
CN (1) CN106909629B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109389440B (en) * 2017-08-02 2022-05-24 阿里巴巴集团控股有限公司 Method and device for providing data object information and electronic equipment
CN108460631B (en) * 2018-02-13 2021-03-09 口口相传(北京)网络技术有限公司 Hybrid pushing method and device for diversified information
CN108416003B (en) * 2018-02-27 2021-12-21 百度在线网络技术(北京)有限公司 Picture classification method and device, terminal and storage medium
CN108804491A (en) * 2018-03-27 2018-11-13 优视科技新加坡有限公司 item recommendation method, device, computing device and storage medium
CN109582857A (en) * 2018-10-15 2019-04-05 深圳壹账通智能科技有限公司 Based on big data information-pushing method, device, computer equipment and storage medium
CN110188297B (en) * 2019-05-21 2021-08-13 掌阅科技股份有限公司 Resource information display method, computing device and computer storage medium
CN113298594A (en) * 2020-07-16 2021-08-24 阿里巴巴集团控股有限公司 Data pushing method and device, electronic equipment and storage medium
CN112035735A (en) * 2020-07-28 2020-12-04 康艾艺 Short video-based commodity recommendation method, device and system
CN111882400A (en) * 2020-07-31 2020-11-03 平安国际融资租赁有限公司 Behavior recognition analysis method and device, computer equipment and readable storage medium
CN113129093A (en) * 2021-03-15 2021-07-16 特斯联科技集团有限公司 Recommendation method and device for recommending commodities based on user data of smart community

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105279224A (en) * 2015-09-09 2016-01-27 百度在线网络技术(北京)有限公司 Information push method and device
CN105574216A (en) * 2016-03-07 2016-05-11 达而观信息科技(上海)有限公司 Personalized recommendation method and system based on probability model and user behavior analysis
CN105787055A (en) * 2016-02-26 2016-07-20 合网络技术(北京)有限公司 Information recommendation method and device
CN105989004A (en) * 2015-01-27 2016-10-05 阿里巴巴集团控股有限公司 Information releasing pretreatment method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989004A (en) * 2015-01-27 2016-10-05 阿里巴巴集团控股有限公司 Information releasing pretreatment method and device
CN105279224A (en) * 2015-09-09 2016-01-27 百度在线网络技术(北京)有限公司 Information push method and device
CN105787055A (en) * 2016-02-26 2016-07-20 合网络技术(北京)有限公司 Information recommendation method and device
CN105574216A (en) * 2016-03-07 2016-05-11 达而观信息科技(上海)有限公司 Personalized recommendation method and system based on probability model and user behavior analysis

Also Published As

Publication number Publication date
CN106909629A (en) 2017-06-30

Similar Documents

Publication Publication Date Title
CN106909629B (en) Method and system for individually recommending pit bit labels
CN105283896B (en) Marketing system and marketing method
US11205195B2 (en) Information processing device, information processing method, and information processing program
CN110569432B (en) Commodity sequence calculating method, commodity sequence calculating device, computer equipment and storage medium
CN108776907A (en) Advertisement intelligent recommends method, server and storage medium
CN105135782B (en) A kind of Intelligent refrigerator management system based on Internet of Things
US20130031506A1 (en) Hotel results interface
CN108446410A (en) Information recommendation method, device, system, equipment and readable storage medium storing program for executing
CN106934498A (en) The recommendation method and system of hotel's house type in OTA websites
JP5002441B2 (en) Marketing data analysis method, marketing data analysis system, data analysis server device, and program
KR101646312B1 (en) Personal Action-Based Interest and Preference Analysis Method and System
JP5462983B1 (en) Information processing apparatus, information processing method, and information processing program
CN102184224A (en) System and method for screening search results
CN106611366A (en) Method and device for automatically selecting article
CN109983495A (en) Demand forecast system, needing forecasting method and program
CN110706014A (en) Shopping mall store recommendation method, device and system
CN113505301A (en) Information query method and related equipment thereof
WO2015151176A1 (en) Information processing device, information processing method, and information processing program
CN109048888B (en) Intelligent service method of robot
CN110881134A (en) Data processing method and device, electronic equipment and storage medium
CN107885856A (en) A kind of page display method and device
CN107016006A (en) A kind of page display method and system
CN110490683A (en) A kind of method and system of the offline upper collaboration multi-model mixed recommendation of line
CN105809275A (en) Item scoring prediction method and apparatus
CN110766504A (en) Display interface construction method, interface display method and device and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant