CN116894134B - Big data analysis method and system based on user behaviors - Google Patents
Big data analysis method and system based on user behaviors Download PDFInfo
- Publication number
- CN116894134B CN116894134B CN202311162052.4A CN202311162052A CN116894134B CN 116894134 B CN116894134 B CN 116894134B CN 202311162052 A CN202311162052 A CN 202311162052A CN 116894134 B CN116894134 B CN 116894134B
- Authority
- CN
- China
- Prior art keywords
- value
- analysis
- access
- coefficient
- analysis coefficient
- 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
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000006399 behavior Effects 0.000 title abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 105
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 235000019633 pungent taste Nutrition 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a big data analysis method and a big data analysis system based on user behaviors, wherein the big data analysis method comprises a behavior acquisition module, a user behavior analysis module and a user behavior analysis module, wherein the behavior acquisition module acquires an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of a user: the data analysis module is used for acquiring an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of the behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF; the data processing module acquires the analysis coefficient XF of the data analysis module and compares the analysis coefficient XF with the analysis coefficient threshold value.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a big data analysis method and system based on user behaviors.
Background
The Chinese patent application with publication number of CN113468432A discloses a mobile Internet-based user behavior big data analysis method and system, which comprises the steps of obtaining user operation behavior segments generated by a target user in a preset time period in a mobile Internet scene, sequentially taking each user operation behavior in the user operation behavior segments as a target user operation behavior needing user behavior intention analysis, then carrying out behavior intention analysis on the target user operation behavior according to a user operation behavior sequence library which is generated in advance and comprises a plurality of user operation behavior sequences, finally obtaining a current behavior portrait of the target user according to user behavior intention analysis respectively corresponding to each user operation behavior, and pushing corresponding mobile Internet information to the target user according to the current behavior portrait. Therefore, the user operation behavior intention of the target user based on the user operation behavior segmentation can be obtained through relatively accurate analysis, and a relatively good application effect can be obtained when the target user is used for the application such as the subsequent mobile internet information pushing;
in the prior art, in the browsing and reading process of the web page, collection and analysis cannot be effectively and comprehensively carried out according to user behaviors, and the popularity of the current web page cannot be compensated according to the current web page by adding and combining corresponding information materials, so that the browsing condition of the web page data is improved.
Disclosure of Invention
The invention aims to solve the problems of the background technology and provides a big data analysis method and a big data analysis system based on user behaviors.
The aim of the invention can be achieved by the following technical scheme:
a big data analysis system based on user behavior, comprising:
the behavior acquisition module acquires an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of a user:
the data analysis module is used for acquiring an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of the behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF;
the specific working process of the data analysis module is as follows:
step 1: substituting the obtained access effective value ZFY, the access interest value ZFX and the access heat value ZFR into a formulaCalculating to obtain an analysis coefficient XF; wherein b1, b2 and b3 are all proportionality coefficients;
step 2: the obtained analysis coefficient XF is sent to a data processing module;
the data processing module acquires an analysis coefficient XF of the data analysis module and compares the analysis coefficient XF with an analysis coefficient threshold.
As a further scheme of the invention: the visit effective value comprises visit residence time Tt, visit times Sf and visit frequency Pf;
by the formulaCalculating to obtain an access effective value ZFY; wherein a1, a2 and a3 are all proportionality coefficients.
As a further scheme of the invention: the method comprises the steps that the access interest value comprises the operation behaviors when a user accesses the webpage, wherein the operation behaviors comprise the collection times Ss and the collection time Ts of the webpage;
by the formulaCalculating to obtain access interestsA value ZFX; wherein a4 and a5 are proportionality coefficients.
As a further scheme of the invention: the access hotness value comprises the number of comments and the shared number of the user on the webpage, and is marked as Lp and Lf respectively;
by the formulaCalculating to obtain an access heat value ZFR; wherein a6 and a7 are proportionality coefficients.
As a further scheme of the invention: the specific working process of the data processing module is as follows:
comparing the obtained analysis coefficient XF with an analysis coefficient threshold value;
if the analysis coefficient XF is more than or equal to the analysis coefficient threshold value, generating an influence qualified signal;
if the analysis coefficient XF is smaller than the analysis coefficient threshold value, an influence failure signal is generated.
As a further scheme of the invention: further comprises:
the prediction module is used for setting an acquisition time node T, and an initial stage analysis coefficient XF1, a middle point stage analysis coefficient XF2 and an end stage analysis coefficient XF3 in the acquisition time node;
by the formulaCalculating to obtain a node analysis coefficient XFJ;
setting an analysis period D, and adding and summing all node analysis coefficients XFJ in the analysis period D to obtain an analysis coefficient influence value ZYx; the analysis period D is a plurality of connected acquisition time nodes T.
As a further scheme of the invention: comparing the analysis coefficient influence value ZYx with an analysis coefficient influence threshold;
if the analysis coefficient influence value ZYx is more than or equal to the analysis coefficient influence threshold value, generating an influence growth signal;
if the analysis coefficient influence value ZYx is smaller than the analysis coefficient influence threshold value, an influence down signal is generated.
As a further scheme of the invention: further comprises:
the guiding module acquires an attraction value ZXY of the information material; the information material attraction value ZXY is obtained by:
the browsing frequency of the obtained information material is marked as Zp, and the browsing time abnormal value is marked as Zy;
by the formulaAcquiring an attraction value ZXY of the information material;
wherein, c1 and c2 are proportionality coefficients;
obtaining analysis coefficient XF and information material suction value ZXY through formulaCalculating to obtain a compensation coefficient XB of the information material; wherein c3 is a scaling factor;
and selecting information materials with compensation coefficients XB larger than a preset compensation coefficient threshold value, and adding the information materials into the webpage.
A big data analysis method based on user behavior comprises the following steps:
step 1: acquiring an access effective value, an access interest value and an access heat value of a user; the method comprises the steps of obtaining an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of a behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF; acquiring an analysis coefficient XF of the data analysis module, and comparing the analysis coefficient XF with an analysis coefficient threshold;
step 2: acquiring an influence disqualification signal of the data processing module, and predicting the subsequent influence condition of the webpage; when the influence descending signal of the prediction module is obtained, information materials are added in the webpage.
The invention has the beneficial effects that:
according to the big data analysis system based on the user behavior, the user access effective value, the user access interest value and the user access heat value are analyzed and judged, so that the current webpage can more intuitively and effectively observe the popularity of the user;
when the current webpage has poor attraction effect, the popularity of the webpage is predicted in time, and when the webpage descends, the popularity of the current webpage can be effectively and accurately compensated and the webpage has descending trend by adding the information material which is matched with the analysis coefficient and contains the compensation coefficient; therefore, the invention analyzes according to the user behavior of the client to effectively solve the problem of poor popularity of the current webpage.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a system block diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the present invention is a big data analysis system based on user behavior, comprising:
the behavior acquisition module acquires an access effective value, an access interest value and an access heat value of a user:
the access effective value comprises access residence time, return visit times and return visit frequency;
wherein the access residence time is the time spent by the user in browsing and reading when accessing the web page, and is denoted as Tt;
the return visit times are the times of the user accessing the webpage and are marked as Sf;
the return visit frequency is the time interval between each time the user accesses the web page and the previous time the user accesses the web page, and is marked as Pf;
by the formulaCalculating to obtain an access effective value ZFY; wherein a1, a2 and a3 are all proportionality coefficients, the value of a1 is 0.32, the value of a2 is 0.35, and the value of a3 is 0.39;
the access interest value comprises an operation behavior when a user accesses the webpage, wherein the operation behavior comprises the collection times and collection time of the webpage, the collection times are total times for collecting the webpage and marked as Ss, and the collection time is a time value between clicking and not clicking the webpage and marked as Ts;
by the formulaCalculating to obtain an access interest value ZFX; wherein, a4 and a5 are proportionality coefficients, the value of a4 is 0.95, and the value of a5 is 0.97;
the access hotness value comprises the number of comments and the shared number of the user on the webpage, and is marked as Lp and Lf respectively;
by the formulaCalculating to obtain an access heat value ZFR; wherein, a6 and a7 are proportionality coefficients, the value of a6 is 0.51, and the value of a7 is 0.58;
the data analysis module is used for acquiring an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of the behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF;
the specific working process of the data analysis module is as follows:
step 1: substituting the obtained access effective value ZFY, the access interest value ZFX and the access heat value ZFR into a formulaCalculating to obtain an analysis coefficient XF; wherein b1, b2 and b3 are all proportionality coefficients, b1 takes on a value of 0.41, b2 takes on a value of 0.45 and b3 takes on a value of 0.44;
step 2: the obtained analysis coefficient XF is sent to a data processing module;
the data processing module is used for acquiring an analysis coefficient XF of the data analysis module and comparing the analysis coefficient XF with an analysis coefficient threshold value;
the specific working process of the data processing module is as follows:
comparing the obtained analysis coefficient XF with an analysis coefficient threshold value;
if the analysis coefficient XF is more than or equal to the analysis coefficient threshold value, generating an influence qualified signal;
if the analysis coefficient XF is smaller than the analysis coefficient threshold value, generating an influencing disqualified signal;
the information provided by the webpage is represented by the influence qualified signal, so that the information has stronger attraction to users; the bad signal indicates that the information provided by the web page is less attractive to the user;
the prediction module is used for obtaining the influencing disqualification signal of the data processing module and predicting the subsequent influencing condition of the webpage;
the specific working process of the prediction module is as follows:
step 1: setting an acquisition time node T, and setting an initial stage analysis coefficient XF1, a middle point stage analysis coefficient XF2 and an end stage analysis coefficient XF3 in the acquisition time node;
by the formulaCalculating to obtain a node analysis coefficient XFJ;
step 2: setting an analysis period D, and adding and summing all node analysis coefficients XFJ in the analysis period D to obtain an analysis coefficient influence value ZYx; wherein the analysis period D is a plurality of connected acquisition time nodes T, namelyI is a positive integer;
step 3: comparing the analysis coefficient influence value ZYx with an analysis coefficient influence threshold;
if the analysis coefficient influence value ZYx is more than or equal to the analysis coefficient influence threshold value, generating an influence growth signal;
generating an influence down signal if the analysis coefficient influence value ZYx < analysis coefficient influence threshold;
according to the invention, the influence increasing signal shows that the attractive force of the webpage is in an increasing trend, the number of people browsing the webpage increases along with the time extension, the influence decreasing signal shows that the attractive force of the webpage is in a decreasing trend, and the number of people browsing the webpage decreases along with the time extension;
the guiding module is used for adding information materials into the webpage when the influence descending signal of the predicting module is obtained; the information material can be words, pictures and videos;
the specific working process of the guide module is as follows:
step 1: acquiring an attraction value ZXY of the information material; the information material attraction value ZXY is obtained by:
the browsing frequency of the obtained information material is marked as Zp, and the browsing time abnormal value is marked as Zy;
the browsing frequency of the information material is the ratio of the number of times of browsing by the user to the time difference value in the time difference value between the first browsing time of the user and the last user time of the user;
the browsing time fluctuation value of the information material is the difference value of two adjacent consultation times of the user, and the variance value of all the difference values is calculated to obtain the browsing time fluctuation value;
by the formulaAcquiring an attraction value ZXY of the information material;
wherein, c1 and c2 are proportionality coefficients, the value of c1 is 0.56, and the value of c2 is 0.28;
step 2: obtaining analysis coefficient XF and information material suction value ZXY through formulaCalculating to obtain a compensation coefficient XB of the information material; wherein c3 is a proportionality coefficient, and the value of c3 is 1.36;
step 3: and selecting information materials with compensation coefficients XB larger than a preset compensation coefficient threshold value, and adding the information materials into the webpage.
Example 2
Based on the above embodiment 1, the present invention is a big data analysis method based on user behavior, comprising the following steps:
step 1: acquiring an access effective value, an access interest value and an access heat value of a user; the method comprises the steps of obtaining an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of a behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF; acquiring an analysis coefficient XF of the data analysis module, and comparing the analysis coefficient XF with an analysis coefficient threshold;
step 2: acquiring an influence disqualification signal of the data processing module, and predicting the subsequent influence condition of the webpage; when the influence descending signal of the prediction module is obtained, information materials are added in the webpage.
The working principle of the invention is as follows: according to the big data analysis system based on the user behavior, the user access effective value, the user access interest value and the user access heat value are analyzed and judged, so that the current webpage can more intuitively and effectively observe the popularity of the user;
when the current webpage has poor attraction effect, the popularity of the webpage is predicted in time, and when the webpage descends, the popularity of the current webpage can be effectively and accurately compensated and the webpage has descending trend by adding the information material which is matched with the analysis coefficient and contains the compensation coefficient; therefore, the invention analyzes according to the user behavior of the client to effectively solve the problem of poor popularity of the current webpage.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (4)
1. A big data analysis system based on user behavior, comprising:
the behavior acquisition module acquires an access effective value ZFY, an access interest value ZFX and an access heat value ZFR when a user browses a webpage:
the data analysis module is used for acquiring an access effective value ZFY, an access interest value ZFX and an access heat value ZFR of the behavior acquisition module, and calculating and analyzing the access effective value ZFY, the access interest value ZFX and the access heat value ZFR to obtain an analysis coefficient XF;
the specific working process of the data analysis module is as follows:
step 1: substituting the obtained access effective value ZFY, the access interest value ZFX and the access heat value ZFR into the formula xf= (b 1 zfy+b2 zfx+b3 ZFR) 2 /（b1+b2+b3） 2 Calculating to obtain an analysis coefficient XF; wherein b1, b2 and b3 are all proportionality coefficients;
step 2: the obtained analysis coefficient XF is sent to a data processing module;
the data processing module is used for acquiring an analysis coefficient XF of the data analysis module and comparing the analysis coefficient XF with an analysis coefficient threshold value;
the specific working process of the data processing module is as follows:
comparing the obtained analysis coefficient XF with an analysis coefficient threshold value;
if the analysis coefficient XF is more than or equal to the analysis coefficient threshold value, generating an influence qualified signal;
if the analysis coefficient XF is smaller than the analysis coefficient threshold value, generating an influencing disqualified signal;
the prediction module predicts the subsequent influence condition of the webpage when the influence disqualification signal of the data processing module is acquired, sets a collecting time node T, and collects an initial stage analysis coefficient XF1, a middle point stage analysis coefficient XF2 and an end stage analysis coefficient XF3 in the time node;
the node analysis coefficient XFJ is calculated by the formula XFJ = { (XF 1-XF 2) + (XF 2-XF 3) }/T;
setting an analysis period D, and adding and summing all node analysis coefficients XFJ in the analysis period D to obtain an analysis coefficient influence value ZYx; the analysis period D is a plurality of connected acquisition time nodes T;
comparing the analysis coefficient influence value ZYx with an analysis coefficient influence threshold;
if the analysis coefficient influence value ZYx is more than or equal to the analysis coefficient influence threshold value, generating an influence growth signal;
generating an influence down signal if the analysis coefficient influence value ZYx < analysis coefficient influence threshold;
the guiding module is used for adding information materials into the webpage when the influence descending signal of the predicting module is obtained, and acquiring an attraction value ZXY of the information materials; the information material attraction value ZXY is obtained by:
the browsing frequency of the obtained information material is marked as Zp, and the browsing time abnormal value is marked as Zy;
by the formula zxy= (c1+c2+zy) 1/3 Acquiring an attraction value ZXY of the information material;
wherein, c1 and c2 are proportionality coefficients;
obtaining an analysis coefficient XF and an attraction value ZXY of an information material, and calculating to obtain a compensation coefficient XB of the information material through a formula XB=c3; wherein c3 is a scaling factor;
and selecting information materials with compensation coefficients XB larger than a preset compensation coefficient threshold value, and adding the information materials into the webpage.
2. A big data analysis system based on user behaviour according to claim 1, wherein the access validity values comprise access residence time Tt, number of revisions Sf, frequency of revisions Pf;
the access effective value ZFY is calculated by the formula zfy=a1×tt+a2×sf+a3×pf; wherein a1, a2 and a3 are all proportionality coefficients.
3. The big data analysis system based on user behavior according to claim 1, wherein accessing the interest value includes acquiring an operation behavior when the user accesses the web page, wherein the operation behavior includes collecting the web page for the number Ss of times and the collection time Ts;
calculating to obtain an access interest value ZFX through a formula zfx=a4×ss+a5×ts; wherein a4 and a5 are proportionality coefficients.
4. The big data analysis system based on user behavior according to claim 1, wherein the access hotness value includes the number of comments and the number of shares made by the user on the web page, and is labeled Lp and Lf, respectively;
calculating to obtain an access heat value ZFR through a formula zfr=a6+a7; wherein a6 and a7 are proportionality coefficients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311162052.4A CN116894134B (en) | 2023-09-11 | 2023-09-11 | Big data analysis method and system based on user behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311162052.4A CN116894134B (en) | 2023-09-11 | 2023-09-11 | Big data analysis method and system based on user behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116894134A CN116894134A (en) | 2023-10-17 |
| CN116894134B true CN116894134B (en) | 2023-12-12 |
Family
ID=88312458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311162052.4A Active CN116894134B (en) | 2023-09-11 | 2023-09-11 | Big data analysis method and system based on user behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894134B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009064741A1 (en) * | 2007-11-12 | 2009-05-22 | Compete, Inc. | Systems and methods for normalizing clickstream data |
| CN102622445A (en) * | 2012-03-15 | 2012-08-01 | 华南理工大学 | User interest perception based webpage push system and webpage push method |
| CN106227883A (en) * | 2016-08-05 | 2016-12-14 | 北京聚爱聊网络科技有限公司 | The temperature of a kind of content of multimedia analyzes method and apparatus |
| CN107766484A (en) * | 2017-10-16 | 2018-03-06 | 南京师范大学 | The knowledge chain that a kind of learning objective is oriented to recommends method |
| WO2018231097A1 (en) * | 2017-06-14 | 2018-12-20 | Общество С Ограниченной Ответственностью "Центр Разработки И Внедрения Инновационных Технологий" | Interactive system and method for displaying advertising content |
| WO2022111095A1 (en) * | 2020-11-30 | 2022-06-02 | 中移(苏州)软件技术有限公司 | Product recommendation method and apparatus, computer storage medium, and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8494978B2 (en) * | 2007-11-02 | 2013-07-23 | Ebay Inc. | Inferring user preferences from an internet based social interactive construct |
| US8504488B2 (en) * | 2008-04-30 | 2013-08-06 | Cisco Technology, Inc. | Network data mining to determine user interest |
| US20200050527A1 (en) * | 2013-09-05 | 2020-02-13 | Colleen Pettit Jones | Content analysis and scoring system and method |
| US10558332B2 (en) * | 2018-03-30 | 2020-02-11 | Microsoft Technology Licensing, Llc | Computationally efficient human-computer interface for web browser tab user interface button |
-
2023
- 2023-09-11 CN CN202311162052.4A patent/CN116894134B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009064741A1 (en) * | 2007-11-12 | 2009-05-22 | Compete, Inc. | Systems and methods for normalizing clickstream data |
| CN102622445A (en) * | 2012-03-15 | 2012-08-01 | 华南理工大学 | User interest perception based webpage push system and webpage push method |
| CN106227883A (en) * | 2016-08-05 | 2016-12-14 | 北京聚爱聊网络科技有限公司 | The temperature of a kind of content of multimedia analyzes method and apparatus |
| WO2018231097A1 (en) * | 2017-06-14 | 2018-12-20 | Общество С Ограниченной Ответственностью "Центр Разработки И Внедрения Инновационных Технологий" | Interactive system and method for displaying advertising content |
| CN107766484A (en) * | 2017-10-16 | 2018-03-06 | 南京师范大学 | The knowledge chain that a kind of learning objective is oriented to recommends method |
| WO2022111095A1 (en) * | 2020-11-30 | 2022-06-02 | 中移(苏州)软件技术有限公司 | Product recommendation method and apparatus, computer storage medium, and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116894134A (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110941740B (en) | Video recommendation method and computer-readable storage medium | |
| US9348924B2 (en) | Almost online large scale collaborative filtering based recommendation system | |
| US9535938B2 (en) | Efficient and fault-tolerant distributed algorithm for learning latent factor models through matrix factorization | |
| CN110390033B (en) | Training method and device for image classification model, electronic equipment and storage medium | |
| US8930376B2 (en) | Search result abstract quality using community metadata | |
| CN108460082B (en) | Recommendation method and device and electronic equipment | |
| JP2001155169A (en) | Method and system for dividing, classifying and summarizing video image | |
| CN111683274B (en) | Bullet screen advertisement display method, device and equipment and computer readable storage medium | |
| US20060288272A1 (en) | Computer-implemented method, system, and program product for developing a content annotation lexicon | |
| CN112989209B (en) | Content recommendation method, device and storage medium | |
| CN112100504B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN111314732A (en) | Method for determining video label, server and storage medium | |
| CN112052387A (en) | Content recommendation method and device and computer readable storage medium | |
| CN113961823B (en) | News recommendation method, system, storage medium and equipment | |
| US20130108180A1 (en) | Information processing device, information processing method, and program | |
| CN116894134B (en) | Big data analysis method and system based on user behaviors | |
| CN112116159B (en) | Information interaction method and device, computer readable storage medium and electronic equipment | |
| CN113204699B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN110113410B (en) | Information push management method and device, electronic equipment and storage medium | |
| Janvier et al. | Information-theoretic temporal segmentation of video and applications: multiscale keyframes selection and shot boundaries detection | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN109933691A (en) | Method, apparatus, equipment and storage medium for content retrieval | |
| CN114245232B (en) | Video abstract generation method and device, storage medium and electronic equipment | |
| Ma et al. | Robust video summarization using collaborative representation of adjacent frames | |
| CN115618024A (en) | Multimedia recommendation 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 |