CN112235636B - Calculation method and device for browsing value attribute of video with goods - Google Patents
Calculation method and device for browsing value attribute of video with goods Download PDFInfo
- Publication number
- CN112235636B CN112235636B CN202010928029.1A CN202010928029A CN112235636B CN 112235636 B CN112235636 B CN 112235636B CN 202010928029 A CN202010928029 A CN 202010928029A CN 112235636 B CN112235636 B CN 112235636B
- Authority
- CN
- China
- Prior art keywords
- video
- target
- goods
- time period
- historical
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Social Psychology (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a calculation method and a device of a video browsing value attribute, wherein the method comprises the following steps: acquiring historical interaction data corresponding to each of all the goods-carrying videos used for selling the target goods in the target time period and historical goods browsing data of the target goods in the historical time period corresponding to the historical interaction data; calculating a target relation coefficient corresponding to each cargo video according to the historical interaction data corresponding to each cargo video and the historical commodity browsing data of the target commodity in a historical time period; and calculating the browsing value attribute of each video with goods in the target time period according to the target relation coefficient corresponding to each video with goods and the current goods browsing data of the target goods in the target time period. Therefore, the invention can provide a determination mode of the browsing value attribute of the video with goods so as to accurately and quickly determine the browsing value attribute of each video with goods for selling goods with goods.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a calculation method and device of a video browsing value attribute with goods.
Background
With the rapid development of the internet, internet users are increasing. In order to expand the audience range and influence of commodities, the marketing mode of commodities introduces video marketing based on internet besides traditional advertising marketing, for example: an advertiser may choose a number of video bloggers to post videos for a certain item or items, which may also be referred to as a video on-demand.
In practical application, for the same commodity, a plurality of videos issued by a plurality of video bloggers usually exist, the styles of the videos issued by different video bloggers are various, the browsing amount of the videos issued by each video blogger for the commodity is also different, and the browsing amount of the videos for the commodity also affects the contribution of the videos to the commodity sales amount to a certain extent. In order to gradually increase the cost performance of commodity video marketing, a video with higher browsing contribution to commodities needs to be determined from a plurality of videos of a plurality of video bloggers. It can be seen that how to accurately determine the browsing value attribute of each video to the commodity is important.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a calculation method and a calculation device for the browsing value attribute of the video with goods, which can provide a determination mode of the browsing value attribute of the goods so as to accurately determine the browsing value attribute of each video with goods for selling the goods with goods.
In order to solve the technical problem, the first aspect of the present invention discloses a method for calculating a viewing value attribute of a video with goods, which comprises the following steps:
acquiring historical interaction data corresponding to each goods video in all the goods videos used for selling the target goods in the target time period and historical goods browsing data of the target goods in the historical time period corresponding to the historical interaction data;
calculating a target relation coefficient corresponding to each commodity video according to the historical interaction data corresponding to each commodity video and the historical commodity browsing data of the target commodity in the historical time period;
according to the target relation coefficient corresponding to each goods video and the current commodity browsing data of the target commodity in the target time period, calculating the browsing value attribute of each goods video to the target commodity in the target time period, wherein the browsing value attribute of the goods video to the target commodity in the target time period is used for representing the contribution condition of the goods video to the browsing amount of the target commodity in the target time period.
In an optional implementation manner, in a first aspect of the present invention, the calculating, according to historical interaction data corresponding to each of the video with goods and historical goods browsing data of the target goods in the historical time period, a target relationship coefficient corresponding to each of the video with goods includes:
According to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period, calculating a corresponding stability relation coefficient of each goods-carrying video in the historical time period;
and for any one of the video with goods, determining a stable relation coefficient corresponding to the video with goods in the historical time period as a target relation coefficient corresponding to the video with goods.
In an optional implementation manner, in a first aspect of the present invention, before determining, for any of the video-in-band, a stable relationship coefficient corresponding to the video-in-band in the historical time period as the target relationship coefficient corresponding to the video-in-band, the method further includes:
calculating a corresponding current relation coefficient of each cargo video in the target time according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period;
calculating a coefficient difference value of a current relation coefficient corresponding to each video-in-stock video in the target time period and a stable relation coefficient corresponding to the video-in-stock video in the historical time period;
For any one of the video with goods, judging whether the absolute value of the coefficient difference value corresponding to the video with goods is smaller than or equal to a predetermined difference value threshold, and when the judgment result is yes, triggering and executing the operation of determining the stable relation coefficient corresponding to the video with goods in the historical time period as the target relation coefficient corresponding to the video with goods; and when the judging result is negative, correcting the current relation coefficient corresponding to the video with goods according to the stable relation coefficient corresponding to the video with goods to obtain the target relation coefficient corresponding to the video with goods.
In an optional implementation manner, in a first aspect of the present invention, the calculating, according to historical interaction data corresponding to each of the video with goods and historical goods browsing data of the target goods in the historical time period, a target relationship coefficient corresponding to each of the video with goods includes:
according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period, calculating a corresponding stability relation coefficient of each goods-carrying video in the historical time period;
calculating a corresponding current relation coefficient of each cargo video in the target time according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period;
And for any one of the video with goods, correcting the current relation coefficient corresponding to the video with goods in the target time period according to the stable relation coefficient corresponding to the video with goods in the historical time period, and obtaining the target relation coefficient corresponding to each video with goods.
In an optional implementation manner, in a first aspect of the present invention, the calculating, according to historical interaction data corresponding to each of the video with goods and historical goods browsing data of the target goods in the historical time period, a stability relationship coefficient corresponding to each of the video with goods in the historical time period includes:
acquiring historical interaction data increment of each cargo video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
according to the historical interaction data increment of each goods-carrying video in each historical time period and the historical goods browsing data increment of the target goods in each historical time period, constructing an independent equation corresponding to each historical time period, wherein the independent equation corresponding to each historical time period takes a historical relation coefficient corresponding to each goods-carrying video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all the goods-carrying videos and the historical goods browsing data increment of the target goods in the historical time period;
And constructing an equation set by using independent equations corresponding to all the historical time periods, and calculating a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
In an optional implementation manner, in a first aspect of the present invention, the calculating, according to an iterative method, a solution of the equation set to obtain a stability relationship coefficient corresponding to each of the on-demand videos in the historical time period includes:
continuously calculating a solution of the equation set according to an iteration method;
judging whether the newly calculated solution of the equation set meets a preset precision condition or not;
when the newly calculated solution of the equation set meets the precision condition, respectively determining the newly calculated solution of the equation set as a corresponding stable relation coefficient of each cargo video in the historical time period;
and triggering and executing the operation of continuously calculating the solution of the equation set according to an iteration method when the newly calculated solution of the equation set is judged not to meet the precision condition.
As an optional implementation manner, in the first aspect of the present invention, before calculating the current relationship coefficient corresponding to each of the video-in-band in the target time according to the current interaction data of each of the video-in-band in the target time period and the current commodity browsing data of the target commodity in the target time period, the method further includes:
Judging whether all the carried videos have carried videos with incomplete interaction data according to the acquired current interaction data of each carried video in the target time period;
when judging that the video with incomplete interaction data does not exist in all the video with goods, triggering and executing the operation of calculating the corresponding current relation coefficient of each video with goods in the target time according to the current interaction data of each video with goods in the target time period and the current goods browsing data of the target goods in the target time period;
when judging that the all the cargo video has incomplete interaction data, executing data supplementing operation on the cargo video with incomplete interaction data in all the cargo video, triggering and executing the operation according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period, and calculating the corresponding current relation coefficient of each cargo video in the target time period;
the data supplementing operation is performed on all the carried videos with incomplete interactive data, and the data supplementing operation comprises the following steps:
Counting the quantity of the incomplete interactive data in all the cargo video, and obtaining an interactive data supplementing algorithm matched with the quantity;
and executing data supplementation operation on all the cargo video with incomplete interaction data in the cargo video according to the acquired interaction data supplementation algorithm.
The second aspect of the invention discloses a computing device for a viewing value attribute of a video in a cargo, the device comprising:
the acquisition module is used for acquiring historical interaction data corresponding to each cargo video in all cargo videos used for selling target commodities in a cargo period and historical commodity browsing data of the target commodities in a historical period corresponding to the historical interaction data;
the first calculation module is used for calculating a target relation coefficient corresponding to each cargo video according to the historical interaction data corresponding to each cargo video and the historical commodity browsing data of the target commodity in the historical time period;
the second calculation module is used for calculating the browsing value attribute of each video with goods in the target time period according to the corresponding target relation coefficient of each video with goods and the current goods browsing data of the target goods in the target time period, wherein the browsing value attribute of the video with goods in the target time period on the target goods is used for representing the contribution condition of the video with goods in the target time period on the browsing quantity of the target goods.
As an alternative embodiment, in a second aspect of the present invention, the first computing module includes:
the first calculation sub-module is used for calculating a stable relation coefficient corresponding to each goods-carrying video in the historical time period according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period;
and the determining submodule is used for determining the stable relation coefficient corresponding to any video with goods in the historical time period as the target relation coefficient corresponding to the video with goods.
In a second aspect of the present invention, the first calculating submodule is further configured to calculate, before the determining submodule determines, for any one of the live video, a stable relationship coefficient corresponding to the live video in the history period as a target relationship coefficient corresponding to the live video, a current relationship coefficient corresponding to each of the live video in the target period according to current interaction data of each of the live video in the target period and current commodity browsing data of the target commodity in the target period, and calculate a coefficient difference between the current relationship coefficient corresponding to each of the live video in the target period and the stable relationship coefficient corresponding to the live video in the history period;
The first computing module further includes:
the judging submodule is used for judging whether the absolute value of the coefficient difference value corresponding to any one of the goods video is smaller than or equal to a predetermined difference value threshold value, and triggering the determining submodule to execute the operation of determining the stable relation coefficient corresponding to the goods video in the historical time period as the target relation coefficient corresponding to the goods video when the judging result is yes;
and the first correction sub-module is used for correcting the current relation coefficient corresponding to the video with goods according to the stable relation coefficient corresponding to the video with goods when the judging result of any video with goods is negative, so as to obtain the target relation coefficient corresponding to the video with goods.
As an alternative embodiment, in a second aspect of the present invention, the first computing module includes:
the second calculation sub-module is used for calculating a stable relation coefficient corresponding to each goods-carrying video in the historical time period according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period;
The second calculation submodule is further used for calculating a corresponding current relation coefficient of each cargo video in the target time according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period;
and the second correction submodule is used for correcting the current relation coefficient corresponding to the video in the target time period according to the stable relation coefficient corresponding to the video in the history time period for any video in charge to obtain the target relation coefficient corresponding to the video in charge.
In a second aspect of the present invention, the specific manner of calculating the stability relationship coefficient corresponding to each of the video-in-band in the history period according to the history interaction data corresponding to each of the video-in-band and the history merchandise browsing data of the target merchandise in the history period is:
acquiring historical interaction data increment of each cargo video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
According to the historical interaction data increment of each goods-carrying video in each historical time period and the historical goods browsing data increment of the target goods in each historical time period, constructing an independent equation corresponding to each historical time period, wherein the independent equation corresponding to each historical time period takes a historical relation coefficient corresponding to each goods-carrying video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all the goods-carrying videos and the historical goods browsing data increment of the target goods in the historical time period;
and constructing an equation set by using independent equations corresponding to all the historical time periods, and calculating a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
In a second aspect of the present invention, the specific manner of calculating, by the first calculation submodule, the solution of the equation set according to the iterative method to obtain the stability relationship coefficient corresponding to each of the on-demand videos in the historical time period is as follows:
continuously calculating a solution of the equation set according to an iteration method;
Judging whether the newly calculated solution of the equation set meets a preset precision condition or not;
when the newly calculated solution of the equation set meets the precision condition, respectively determining the newly calculated solution of the equation set as a corresponding stable relation coefficient of each cargo video in the historical time period;
and triggering and executing the operation of continuously calculating the solution of the equation set according to an iteration method when the newly calculated solution of the equation set is judged not to meet the precision condition.
In a second aspect of the present invention, the determining submodule is further configured to determine whether there is a video with incomplete interaction data in all the video with cargo according to the obtained current interaction data of each video with cargo in the target time period; when the judging submodule judges that the all the belonged videos have no incomplete interaction data, triggering the first calculating submodule to execute the operation of calculating the current relation coefficient corresponding to each belonged video in the target time according to the current interaction data of each belonged video in the target time period and the current commodity browsing data of the target commodity in the target time period and calculating the coefficient difference value of the current relation coefficient corresponding to each belonged video in the target time period and the stable relation coefficient corresponding to each belonged video in the history time period;
The first correction submodule is further used for executing data supplementing operation on the goods video with incomplete interactive data in all the goods videos when the judging submodule judges that the goods video with incomplete interactive data exists in all the goods videos, triggering the first calculation submodule to execute the operation according to the current interactive data of each goods video in the target time period and the current commodity browsing data of the target commodity in the target time period, calculating the current relation coefficient corresponding to each goods video in the target time period, and calculating the coefficient difference value between the current relation coefficient corresponding to each goods video in the target time period and the stable relation coefficient corresponding to the goods video in the history time period;
the specific way for the first correction sub-module to perform the data supplementing operation on the video with incomplete interactive data in all the video with goods is as follows:
counting the quantity of the incomplete interactive data in all the cargo video, and obtaining an interactive data supplementing algorithm matched with the quantity;
and executing data supplementation operation on all the cargo video with incomplete interaction data in the cargo video according to the acquired interaction data supplementation algorithm.
In a third aspect, the present invention discloses another computing device for a value attribute of viewing a video in a cargo, the device comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform some or all of the steps in the method for calculating the attribute of the browsing value of the video with cargo disclosed in the first aspect of the embodiment of the present invention.
In a fourth aspect of the embodiment of the present invention, a computer storage medium is disclosed, where the computer storage medium stores computer instructions that, when invoked, are used to execute part or all of the steps in the method for calculating the attribute of browsing value of a video with goods disclosed in the first aspect of the embodiment of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, historical interaction data corresponding to each cargo video in all cargo videos used for selling target commodities in a target time period and historical commodity browsing data of the target commodities in a historical time period corresponding to the historical interaction data are obtained; calculating a target relation coefficient corresponding to each cargo video according to the historical interaction data corresponding to each cargo video and the historical commodity browsing data of the target commodity in a historical time period; according to the corresponding target relation coefficient of each goods video and the current commodity browsing data of the target commodity in the target time period, calculating the browsing value attribute of each goods video to the target commodity in the target time period, wherein the browsing value attribute of the goods video to the target commodity in the target time period is used for representing the contribution condition of the goods video to the browsing amount of the target commodity in the target time period. Therefore, the invention can provide a determination mode of commodity browsing value attribute so as to accurately and rapidly determine the browsing value attribute of each commodity-carrying video for selling commodities with goods, and further can provide objective and accurate reference for determining the sales contribution condition of each commodity-carrying video to the commodities and/or the commodity carrying capability of a video owner of each commodity-carrying video.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for calculating a value attribute of a video browsing with cargo according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for calculating a value attribute of a video browsing with cargo according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a computing device with video browsing value attributes according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another exemplary embodiment of a computing device with video browsing value attributes;
FIG. 5 is a schematic diagram of a computing device with video browsing value attributes according to another embodiment of the present invention;
FIG. 6 is a schematic diagram of a computing device with video browsing value attributes according to another embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, 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.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a calculation method and a calculation device for a commodity-carrying video browsing value attribute, which can provide a determination mode of the commodity browsing value attribute so as to accurately and rapidly determine the commodity browsing value attribute of each commodity-carrying video for selling commodities with the commodity, and further can provide objective and accurate reference for determining the commodity-carrying contribution condition of each commodity-carrying video and/or the commodity-carrying capability of a video blogger of each commodity-carrying video. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for calculating a viewing value attribute of a video with goods according to an embodiment of the present invention. The method described in fig. 1 may be applied to a computing device, which may be a computing terminal, a computing device, or a server, and the server may be a local server or a cloud server, which is not limited in the embodiments of the present invention. As shown in fig. 1, the calculation method of the attribute of the browsing value of the video with goods may include the following operations:
101. the computing device acquires historical interaction data corresponding to each of all the goods-carrying videos used for selling the target goods in the target time period and historical goods browsing data of the target goods in the historical time period corresponding to the historical interaction data.
In the embodiment of the invention, each of the video with goods is also used for selling the target commodity with goods in the historical time period. All the goods video used for selling the target goods with goods can comprise goods video with goods links corresponding to the target goods, can also comprise goods video with video content as promotion content of the target goods, and can also comprise goods video with goods links corresponding to the target goods and goods video with video content as promotion content of the target goods.
In the embodiment of the present invention, after the execution of step 101 is completed, the execution of step 102 may be directly triggered. In other optional embodiments, after the computing device obtains the historical interaction data corresponding to each of all the video-in-stock for the target commodity for the target time period, the method may further include the operations of:
the computing device judges whether the goods video with incomplete historical interaction data exists in all the goods video according to the historical interaction data corresponding to each goods video in all the goods video used for selling the target goods in the obtained target time period;
When the judgment result is negative, the computing device executes subsequent operations;
and when the judgment result is yes, the computing device performs data supplementing operation on the freighted videos with incomplete historical interaction data in all the freighted videos, and after the completion of supplementing the historical interaction data, which is lack of the freighted videos with incomplete historical interaction data, the computing device performs subsequent operation.
The subsequent operation may be the operation of step 102, or the operation of obtaining the historical merchandise browsing data in the historical time period, where the obtaining of the historical interactive data and the obtaining of the historical merchandise browsing data have no precedence relationship.
Further optionally, the computing device performs a data supplementing operation on the video with incomplete historical interaction data in all the video with goods, which may include:
the computing device counts the number of the incomplete video with the historical interaction data (also called as the first type of video with the goods) in all the video with the goods, and acquires an interaction data supplementing algorithm matched with the number;
and the computing device executes data supplementing operation on the first type of the cargo video with incomplete historical interaction data in all cargo videos according to the acquired interaction data supplementing algorithm.
When the number of the first type of the video with goods is small (such as the number is smaller than or equal to the determined number threshold), the interactive data supplementing algorithm matched with the number is a big data supplementing algorithm; when the number is large, the interactive data supplementing algorithm matched with the number is a crawler supplementing algorithm. It should be noted that, if the number of the first type of the video-in-band is large, or the total time period (such as total days) of incomplete historical interaction data of all the first type of the video-in-band in the historical time period is large, the computing device may also directly output a prompt to prompt that the browsing value attribute of the video-in-band to the target commodity is not calculated. Optionally, when the total time period (such as total days) of incomplete historical interaction data in the historical time period is more for all the first-type video, the computing device may further perform the following operations before outputting the prompt:
the computing device computes the increment duty ratio of the interactive data of the all-cargo video in each time period according to the existing historical interactive data of all the cargo video in the historical time period, wherein the existing historical interactive data is more or the complete cargo video in the existing historical interactive data, and if the increment duty ratio of the interactive data is smaller than or equal to a preset duty ratio threshold value, the output prompt is executed to prompt the operation of not computing the browsing value attribute of the cargo video to the target commodity;
If the incremental duty cycle of the interaction data is greater than the preset duty cycle threshold, the computing device may supplement the missing historical interaction data according to a crawler supplement algorithm.
Wherein, the total time period of incomplete historical interaction data in the historical time period is exemplified as follows:
assuming that the video with goods comprises a video with goods A, a video with goods B and a video with goods C, the historical time period is 5 days, the time period is 1 day, the video with incomplete historical interaction data is the video with goods A and the video with goods B, the video with goods A has incomplete historical interaction data of 3 days in the historical time period, the video with goods B has incomplete historical interaction data of 2 days in the historical time period, and the total time surrounding the incomplete historical interaction data in the historical time period is equal to 2 days plus 3 days. Namely: the total time period of incomplete historical interaction data of all the first-type cargo video in the historical time period is equal to the sum of the time periods of incomplete historical interaction data of all the first-type cargo video in the historical time period.
Still further optionally, when the number is less than or equal to a predetermined number threshold, the computing device performs a data supplementing operation on the video with incomplete interactive data in all the video with complete interactive data according to the obtained interactive data supplementing algorithm, and may include:
The computing device determines a video delivery platform of each first type of cargo video;
for each determined video delivery platform, collecting sample video with goods which are delivered by the video delivery platform and meet preset conditions and reach corresponding orders of magnitude (such as 1000), calculating the interactive data change amount of each sample video with goods in each time period (such as each day) in a predetermined time period, calculating the periodic interactive data increment ratio corresponding to the video delivery platform according to the interactive data change amount of each sample video with goods in each time period in the predetermined time period, and determining the average value or the median of the periodic interactive data increment ratios as the platform interactive data increment percentage corresponding to the video delivery platform in each time period;
and for each determined first-type video, the computing device supplements the historical interaction data of the video with the corresponding time period in the target time period according to the platform interaction data increment percentage of the video delivery platform of the first-type video corresponding to each time period and the existing historical interaction data of the first-type video. That is, when supplementing the historical interaction data of the first type of video-in-band in the nth time period, the computing device needs to use the platform interaction data increment percentage corresponding to the video delivery platform in the nth time period, wherein the starting time of the nth time period is the starting release time of the video-in-band.
The change amount of the interactive data of the sample video in a time period (such as each day) is specifically equal to the total amount of the interactive data of the sample video in the ending time of the time period minus the total amount of the interactive data of the sample video in the ending time of the time period in the adjacent time period before the time period.
Optionally, for any determined video delivery platform, the sample cargo video which has been delivered by the video delivery platform and meets the preset condition is specifically a cargo video with complete interactive data in each time period which has been delivered by the video delivery platform and is within the determined time period, and further optionally, the determined time period may be greater than or equal to the maximum release duration in release durations of all cargo videos of the first type at the ending time of the above-mentioned target time period. Still further optionally, for any video delivery platform determined, the commodities sold by the sample with-goods video belong to the same category as the target commodity, and/or the initial release time of all the sample with-goods video is the same.
For example, a certain first type of video D lacks historical interaction data for 3 days 1-3 from the release time, and the increment percentages of interaction data of 3 sample video on day 1 released by the video release platform where the first type of video D is located are 60%, 50% and 55%, respectively, then the increment percentage of periodic interaction data of the video release platform on day 1 is 55% (i.e. the average of the three); the interactive data increment percentages of 3 sample cargo videos issued by the video delivery platform where the first class cargo video D is located on the 2 nd day are 30%, 20% and 20% respectively, and then the periodic interactive data increment percentage of the video delivery platform on the 2 nd day is 23.33% (namely the average of the three); the interactive data increment percentages of 3 sample video with goods distributed on the video delivery platform where the first type video with goods D is located on the 2 nd day are 30%, 20% and 20% respectively, and then the periodic interactive data increment percentage of the video delivery platform on the 2 nd day is 23.33% (namely the average of the three), and similarly, the periodic interactive data increment percentage of the video delivery platform on the 3 rd day can also be calculated.
It should be noted that, since the total amount of interactive data of most of the video-in-stock is not changed basically after the release time reaches the preset time (for example, up to 7 days), the interactive data increment of each time period after the release time reaches the preset time can be determined to be 0.
Still further alternatively, when the number is greater than a predetermined number threshold, the computing device performs a data supplementing operation on the partial interactive data of all the cargo videos according to the acquired interactive data supplementing algorithm, and may include:
the computing device repeatedly grabs the historical interaction data corresponding to each first-type cargo video in the historical time period for one or more times according to a predetermined crawler algorithm, and supplements the obtained historical interaction data corresponding to each first-type cargo video in the historical time period according to the historical interaction data corresponding to each re-grabbed first-type cargo video in the historical time period.
It should be noted that, no matter how many the number of the video with incomplete historical interaction data is, the computing device may perform data supplementation on the video with incomplete historical interaction data through the same interaction data supplementation algorithm (such as a big data supplementation algorithm or a crawler algorithm).
It should be further noted that, when the total time period (such as total days) of incomplete historical interaction data of all the first type of video with goods is more, the computing device may supplement the historical interaction data lacking in part of the time period through the crawler algorithm, and after the total time period of incomplete historical interaction data is reduced to a certain amount, supplement the historical interaction data lacking in the remaining time period according to the big data supplementing algorithm.
Therefore, when the historical interaction data corresponding to the video with goods is lack, the alternative embodiment can supplement the lacking historical interaction data, ensure the integrity of the historical interaction data corresponding to the video with goods, and further improve the accuracy of the browsing value attribute of each video with goods calculated later to the target goods in the target time period. In addition, the optional embodiment can also adaptively select a proper interaction data supplementing algorithm according to the quantity of the video with the lacking historical interaction data, when the lacking historical interaction data is less, the supplementing is performed through a big data supplementing algorithm, the accuracy of the supplemented historical interaction data is improved, and the data supplementing efficiency is ensured to a certain extent; when the lack of historical interaction data is more, the crawler algorithm is used for crawling again, and compared with a big data supplementing algorithm, the data calculation amount is reduced.
102. The computing device computes target relation coefficients corresponding to each video with goods according to the historical interaction data corresponding to each video with goods and the historical goods browsing data of the target goods in the historical time period.
In the embodiment of the invention, the ending time of the historical time period is earlier than the starting time of the target time period.
103. The computing device computes the browsing value attribute of each video with goods in the target time period according to the corresponding target relation coefficient of each video with goods and the current goods browsing data of the target goods in the target time period.
In the embodiment of the present invention, the current commodity browsing data of the target commodity in the target time period may be specifically the visitor volume or browsing volume of the target commodity in the target time period, which is not limited in the embodiment of the present invention. The attribute of the browsing value of the video with goods to the target commodity in the target time period is used for representing the browsing amount contribution condition of the video with goods to the target commodity in the target time period, and the browsing amount contribution ratio, the specific browsing amount and the corresponding browsing amount contribution level can be adopted, and the embodiment of the invention is not limited.
In the embodiment of the invention, optionally, the browsing value attribute of each of the video with goods in the target time period for the target commodity can be determined by the product of the target relation coefficient corresponding to the video with goods and the current commodity browsing data of the target commodity in the target time period, the calculated product of the target relation coefficient and the current commodity browsing data of the target commodity in the target time period can be directly determined as the browsing value attribute of the video with goods in the target time period by the computing device, and the browsing value attribute of the video with goods in the target time period can be finally determined according to the product of the target relation coefficient and the current commodity browsing data of the target commodity in the target time period and the browsing contribution correction parameter which is determined in advance.
It should be noted that, if the required browsing value attribute is the browsing contribution ratio, the computing device may directly determine the browsing value attribute of the video with respect to the target commodity according to the target relationship coefficient corresponding to each video with respect to the target commodity.
In an alternative embodiment, the method may further comprise the following operations, before performing step 101:
the computing device determines the time length of the target time period;
the computing device judges whether the time length of the target time period meets the predetermined length condition;
when it is determined that the time length of the target time period satisfies the predetermined length condition, execution of step 101 is triggered.
Optionally, the calculating means determines whether the time length of the target time period satisfies a predetermined length condition, and may include:
the computing device judges whether the time length of the target time period is larger than or equal to the time length corresponding to the predetermined minimum time period and smaller than or equal to the predetermined maximum time length;
when the time length of the target time period is judged to be greater than or equal to the time length corresponding to the minimum time period and less than or equal to the maximum time length, the time length of the target time period is determined to meet the predetermined length condition.
Therefore, in this optional embodiment, after determining the time period corresponding to the attribute of the browsing value, whether the time length of the time period meets the predetermined length condition is determined first, and then, the subsequent operation is performed under the condition that the time length of the time period meets the predetermined length condition, which can reduce unnecessary operations of the computing device, and further is beneficial to the accuracy and reliability of the subsequent operations executed by the computing device.
In another alternative embodiment, after performing the finishing step 103, the method further comprises the operations of:
the computing device screens at least one target cargo video with the attribute of browsing value of the target commodity meeting the browsing contribution condition (such as the visitor volume is larger than or equal to a visitor volume threshold value or the visitor volume ratio is larger than or equal to a visitor volume ratio threshold value) from all the cargo videos;
the computing device determines relevant video parameters of each target cargo video according to the video identification uniquely corresponding to each target cargo video;
the computing device counts at least one video parameter with the occurrence frequency exceeding a preset frequency threshold according to the related video parameters of all the target video with goods.
The relevant video parameters of the target cargo video may include one or more combinations of a release platform of the target cargo video, a fan amount of a video blogger of the target cargo video, a video style of the target cargo video, a release duration of the target cargo video, and the like, which are not limited in the embodiment of the present invention.
In this alternative embodiment, all the video parameters counted by the computing device are used as an analysis model to analyze video parameters (such as a release platform, a video style, etc.) with a great influence degree of the video on the browsing value attribute of the target commodity, and may also be used to output to the advertiser of the target commodity, so that the advertiser of the target commodity knows relevant video parameters of the video with great contribution to the browsing of the target commodity, so that the advertiser of the target commodity can better make an effective decision on the video with good, for example, select a proper release platform, select a proper video style, etc.
Therefore, the optional embodiment can also intelligently count video parameters with larger influence degree of the video with goods on the browsing value attribute of the target commodity after the browsing value attribute of each video with goods is determined, so that the intelligent function of the computing device can be further enriched, and an effective reference basis can be provided for better decision making of advertisers on the video with goods.
In yet another alternative embodiment, after performing the finishing step 103, the method further comprises the operations of:
the computing device screens the target commodity video with highest browsing value attribute from all the commodity videos, and determines relevant video parameters of the target commodity video, wherein the relevant video parameters can comprise one or more of the release time of the target commodity video, the release platform of the target commodity video, the video style of the target commodity video, the number of vermicelli of video bloggers of the target commodity video and the like.
It can be seen that the optional embodiment can also automatically determine the relevant video parameters of the target cargo video with the highest browsing value attribute of the target commodity in the target time period, so as to provide an effective reference basis for formulating an advertisement delivery strategy (such as selecting a proper video blogger to release a cargo video of a certain video style on a proper release platform, etc.).
In yet another alternative embodiment, the calculating device calculates the target relationship coefficient corresponding to each of the video with goods according to the historical interaction data corresponding to each of the video with goods and the historical goods browsing data of the target goods in the historical time period, which may include:
the computing device computes a stable relation coefficient corresponding to each goods video in a historical time period according to the historical interaction data corresponding to each goods video and the historical commodity browsing data of the target commodity in the historical time period;
the computing device computes a corresponding current relation coefficient of each goods-carrying video in the target time according to the current interaction data of each goods-carrying video in the target time period and the current commodity browsing data of the target commodity in the target time period;
and for any video, the computing device corrects the current relation coefficient corresponding to the video in the target time period according to the stable relation coefficient corresponding to the video in the historical time period, so as to obtain the target relation coefficient corresponding to each video.
In this optional embodiment, further optionally, the calculating device calculates, according to the historical interaction data corresponding to each of the video with goods and the historical goods browsing data of the target goods in the historical time period, a stability relationship coefficient corresponding to each of the video with goods in the historical time period, which may include:
the computing device obtains historical interaction data increment of each goods-carrying video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
the calculation device constructs an independent equation corresponding to each historical time period according to the historical interaction data increment of each goods-carrying video in each historical time period and the historical goods browsing data increment of the target goods in each historical time period, and the independent equation corresponding to the historical time period takes the historical relation coefficient corresponding to each goods-carrying video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all the goods-carrying videos and the historical goods browsing data increment of the target goods in the historical time period;
the calculation device constructs an equation set by using independent equations corresponding to all the historical time periods, and calculates a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
Still further alternatively, the calculating means calculates a solution of the equation set according to an iterative method to obtain a stable relationship coefficient corresponding to each of the video-in-band in the historical time period, and may include:
the calculation device continuously calculates the solution of the equation set according to an iteration method;
the calculation device judges whether the solution of the latest calculated equation set meets the preset precision condition;
when the solution of the latest calculated equation set is judged to meet the precision condition, the calculation device respectively determines the solution of the latest calculated equation set as a stable relation coefficient corresponding to each cargo video in the historical time period;
when it is judged that the solution of the newly calculated equation set does not satisfy the accuracy condition, the calculation means triggers the execution of the above-described operation of continuously calculating the solution of the equation set according to the iterative method.
The solution of the latest calculated equation set includes a sub-solution corresponding to each of the video with goods, and when the solution of the latest calculated equation set is judged to meet the accuracy condition, the sub-solution corresponding to the video with goods is the stable relation coefficient corresponding to the video with goods in the historical time period.
Still further alternatively, the determining, by the computing device, whether the solution of the newly computed equation set satisfies a preset accuracy condition may include:
The computing means determines a preset number (e.g., 6) of solutions (also known as historical solutions) of the system of equations that are successively computed before the solution of the system of equations that was last computed (also known as the last solution);
the calculating device calculates the difference value between the latest solution and each historical solution;
if the absolute value of the difference between the latest solution and each historical solution is smaller than or equal to the difference threshold, or if the ratio of the number of the historical solutions with the absolute value of the difference between the latest solution and each historical solution is smaller than or equal to the difference threshold to the preset number is larger than or equal to the corresponding threshold, the calculation device determines that the solution of the latest calculated equation set meets the preset precision condition.
It should be noted that, the calculation means may also be understood as a process of determining whether the solution of the newly calculated equation set satisfies the preset accuracy condition or not. And because the solution of the equation set includes the corresponding sub solutions of each video with goods, when calculating the difference value of the two solutions of the equation set, the calculating device calculates the difference value of the sub solutions corresponding to the same video with goods in the two solutions respectively, so as to obtain the corresponding sub difference value of each video with goods, and if the sub difference value corresponding to all video with goods is less than or equal to the difference value threshold or the ratio of the number of video with goods with the corresponding sub difference value being less than or equal to the difference value threshold to the number of video with goods is greater than or equal to the ratio threshold, the calculating device determines that the difference value of the two solutions is less than or equal to the difference value threshold.
It should be noted that, if the historical interaction data increment of a certain video-in-stock in a certain historical time period is negative, the computing device may directly determine the sub-relationship coefficient (or the historical sub-relationship coefficient) corresponding to the video-in-stock in the historical time period as zero, or may directly correct the negative historical interaction data increment as zero.
For example, assuming that the historical time period is 2020.1.1-2020.1.5, all the determined video-in-stock includes video a, video b and video c, the historical time period is 1 day long, the merchandise browsing data for 2020.1.1-2020.1.5 days are 100, 250 (increment of 150), 450 (increment of 200), 600 (increment of 150), 700 (increment of 100), respectively, the praise amount for capturing only video b on 2020.1.1 days is 50, the praise amounts for the remaining video may be recorded as 0, i.e., the praise amounts for capturing video a, video b and video c on 2020.1.1 days are 0, 50 and 0, respectively, the praise amounts of the video a, the video b, and the video c captured on the day 2020.1.2 are 100 (increment of 100), 100 (increment of 50), and 0 (increment of 0), respectively, the praise amounts of the video a, the video b, and the video c captured on the day 2020.1.3 are 200 (increment of 100), 300 (increment of 200), and 100 (increment of 100), respectively, the praise amounts of the video a, the video b, and the video c captured on the day 2020.1.4 are 350 (increment of 150), 500 (increment of 200), and 200 (increment of 100), respectively, the praise amounts of the video a, the video b, and the video c captured on the day 2020.1.5 are 300 (increment of 0), 500 (increment of 0), and 300 (increment of 100), respectively, and the independent equations per day are:
2020.1.1 50*Tb=100;
2020.1.2 100*Ta+50*Tb=150;
2020.1.3 100*Ta+200*Tb+100*Tc=200;
2020.1.4 150*Ta+200*Tb+100*Tc=150;
2020.1.5 100*Tc=100;
In practical application, considering factors such as time attenuation, video heat attenuation, recommended mechanism change and the like, ta, tb and Tc each day may be different, and because it is difficult to quantify various influencing factors, ta, tb and Tc need to be calculated once each day, and the values of Ta, tb and Tc calculated currently are optimized in combination with Ta, tb and Tc calculated historically, after a plurality of times of calculation are accumulated, the values of Ta, tb and Tc tend to be stable, and the values of Ta, tb and Tc tending to be stable may be regarded as the values closest to the correct values. It should be noted that the specific values are not actual values, but are only used to illustrate the construction process of the independent equation, and the specific data do not have actual reference meaning and are subject to actual crawl data.
It should be noted that, assuming that the data of the first day or the first historical time period exceeds two coefficients, it may be assumed that each coefficient is equal first, and it is optimized based on the calculation of the subsequent historical time period.
Therefore, the alternative embodiment can determine the stable relation coefficient of each cargo video in the historical time period based on the historical interaction data increment and the historical commodity browsing data increment, and further determine the target relation coefficient according to the determined stable relation coefficient, namely the target relation coefficient is not fixed and unchanged, changes along with the change of some factors, and is beneficial to improving the accuracy and reliability of the determined target relation coefficient.
Example two
Referring to fig. 2, fig. 2 is a flowchart illustrating another calculation method of a value attribute of video browsing with goods according to an embodiment of the present invention. The method described in fig. 2 may be applied to a computing device, which may be a computing terminal, a computing device, or a server, and the server may be a local server or a cloud server, which is not limited in the embodiments of the present invention. As shown in fig. 2, the calculation method of the attribute of the browsing value of the video with goods may include the following operations:
201. the computing device acquires historical interaction data corresponding to each of all the goods-carrying videos used for selling the target goods in the target time period and historical goods browsing data of the target goods in the historical time period corresponding to the historical interaction data.
202. The computing device computes a stable relation coefficient corresponding to each video with goods in a historical time period according to the historical interaction data corresponding to each video with goods and the historical goods browsing data of the target goods in the historical time period.
In the embodiment of the present invention, after the execution of the finishing step 202, the execution step 203 is triggered, and it should be noted that, after the execution of the finishing step 202, the execution step 206 may also be directly triggered for any video.
203. The computing device computes a current relation coefficient corresponding to each video with goods in the target time according to the current interaction data of each video with goods in the target time period and the current goods browsing data of the target goods in the target time period.
204. The calculating device calculates a coefficient difference value between a current relation coefficient corresponding to each video in a target time period and a stable relation coefficient corresponding to the video in a historical time period.
205. For any video, the computing device judges whether the absolute value of the coefficient difference value corresponding to the video is smaller than or equal to a predetermined difference threshold value, and when the judging result of the steps and 205 is yes, the step 206 is triggered to be executed; when the result of the determination in step 205 is no, execution of step 207 is triggered.
206. The computing device determines the stable relation coefficient corresponding to the video in the historical time period as the target relation coefficient corresponding to the video in the video.
In the embodiment of the present invention, it should be noted that the video-in-band in step 206 is consistent with the video-in-band in step 205.
207. And the computing device corrects the current relation coefficient corresponding to the video with goods according to the stable relation coefficient corresponding to the video with goods to obtain the target relation coefficient corresponding to the video with goods.
In the embodiment of the present invention, it should be noted that the video on the tape in step 207 is consistent with the video on the tape in step 205.
208. The computing device computes the browsing value attribute of each video with goods in the target time period according to the corresponding target relation coefficient of each video with goods and the current goods browsing data of the target goods in the target time period.
In an optional embodiment, the calculating device calculates the stability relation coefficient corresponding to each of the belt video in the historical time period according to the historical interaction data corresponding to each of the belt video and the historical commodity browsing data of the target commodity in the historical time period, and the calculating device may include:
the computing device obtains historical interaction data increment of each goods-carrying video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
the calculation device constructs an independent equation corresponding to each historical time period according to the historical interaction data increment of each goods-carrying video in each historical time period and the historical goods browsing data increment of the target goods in each historical time period, and the independent equation corresponding to the historical time period takes the historical relation coefficient corresponding to each goods-carrying video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all the goods-carrying videos and the historical goods browsing data increment of the target goods in the historical time period;
The calculation device constructs an equation set by using independent equations corresponding to all the historical time periods, and calculates a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
In this optional embodiment, further optionally, the calculating means calculates a solution of the equation set according to an iterative method to obtain a stable relationship coefficient corresponding to each of the video-in-stock in the historical time period, and may include:
the calculation device continuously calculates the solution of the equation set according to an iteration method;
the calculation device judges whether the solution of the latest calculated equation set meets the preset precision condition;
when the solution of the latest calculated equation set is judged to meet the precision condition, the calculation device respectively determines the solution of the latest calculated equation set as a stable relation coefficient corresponding to each cargo video in the historical time period;
when it is judged that the solution of the newly calculated equation set does not satisfy the accuracy condition, the calculation means triggers the execution of the above-described operation of continuously calculating the solution of the equation set according to the iterative method.
In another alternative embodiment, the method may further comprise, prior to step 203, the following operations:
the computing device judges whether the video with incomplete interaction data exists in all the video with goods according to the acquired current interaction data of each video with goods in the target time period;
When judging that the incomplete video with interaction data does not exist in all the video with goods, the computing device executes the operation of computing the corresponding current relation coefficient of each video with goods in the target time according to the current interaction data of each video with goods in the target time and the current goods browsing data of the target goods in the target time;
when judging that the incomplete video with the interactive data exists in all the video with goods, the computing device executes the data supplementing operation on the video with incomplete interactive data in all the video with goods, and triggers the operation of executing the current relation coefficient corresponding to each video with goods in the target time according to the current interactive data of each video with goods in the target time period and the current commodity browsing data of the target commodity in the target time period;
optionally, the computing device performs a data supplementing operation on the video with incomplete interactive data in all the video with goods, including:
counting the quantity of the incomplete interactive data of all the cargo videos by the computing device, and acquiring an interactive data supplementing algorithm matched with the quantity;
and the computing device executes data supplementation operation on the video with incomplete interactive data in all the video with goods according to the acquired interactive data supplementation algorithm.
It should be noted that, in the alternative embodiment, the other detailed description of the supplement of the interactive data refers to the detailed description of the missing historical interactive data in the first embodiment, and the supplement principle is the same, which is not repeated in the embodiments of the present invention.
Therefore, when the current interaction data corresponding to the video with goods is not available, the alternative embodiment can supplement the missing current interaction data, ensure the integrity of the current interaction data corresponding to the video with goods, and further improve the accuracy of the current relationship coefficient corresponding to each video with goods calculated subsequently. In addition, the optional embodiment can also adaptively select a proper interaction data supplementing algorithm according to the quantity of the video with the current interaction data, when the current interaction data is less, the supplement is performed through a big data supplementing algorithm, the accuracy of the supplemented current interaction data is improved, and the data supplementing efficiency is ensured to a certain extent; when the current interaction data is lack more, the crawler algorithm is used for crawling again, and compared with a big data supplementing algorithm, the data calculation amount is reduced.
Therefore, the method described by implementing the embodiment of the invention can provide a determination mode of the commodity browsing value attribute based on the history related data and further combined with the current related data, so that the browsing value attribute of each video with goods for selling the commodity with goods can be accurately and rapidly determined, and objective and accurate reference basis can be provided for determining the sales contribution condition of each video with goods and/or the commodity carrying capability of the video blogger of each video with goods.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a computing device with video browsing value attribute according to another embodiment of the present invention. The apparatus described in fig. 3 may be applied to a computing terminal, a computing device, or a server, where the server may be a local server or a cloud server, and embodiments of the present invention are not limited. As shown in fig. 3, the apparatus may include:
the acquiring module 301 is configured to acquire historical interaction data corresponding to each of all the cargo videos used for selling the target commodity in the target time period and historical commodity browsing data of the target commodity in a historical time period corresponding to the historical interaction data.
The first calculating module 302 is configured to calculate a target relationship coefficient corresponding to each of the video with goods according to the historical interaction data corresponding to each of the video with goods and the historical goods browsing data of the target goods in the historical time period.
The second calculating module 303 is configured to calculate a browsing value attribute of each of the video with goods in the target time period according to the target relationship coefficient corresponding to each of the video with goods and the current goods browsing data of the target goods in the target time period.
In an alternative embodiment, as shown in fig. 4, the first computing module 302 may include:
the first calculating submodule 3021 is configured to calculate a stability relationship coefficient corresponding to each of the video with goods in the history time period according to the history interaction data corresponding to each of the video with goods and the history goods browsing data of the target goods in the history time period.
The determining submodule 3022 is configured to determine, for any of the video with a load, a stable relationship coefficient corresponding to the video with a load in a historical time period, as a target relationship coefficient corresponding to the video with a load.
Further optionally, the first calculating submodule 3021 is further configured to calculate, before determining that the stability relationship coefficient corresponding to the video in the history period is determined as the target relationship coefficient corresponding to the video in the history period by the determining submodule 3022 for any video in the target period, the current relationship coefficient corresponding to each video in the target period according to the current interaction data of each video in the target period and the current merchandise browsing data of the target merchandise in the target period, and calculate a coefficient difference value between the current relationship coefficient corresponding to each video in the target period and the stability relationship coefficient corresponding to the video in the history period.
Wherein, as shown in fig. 4, the first computing module 302 may further include:
the judging submodule 3023 is configured to judge whether an absolute value of a coefficient difference value corresponding to any one of the video with the video is smaller than or equal to a predetermined difference threshold, and when the judging result is yes, trigger the determining submodule 3022 to execute the above operation of determining the stable relationship coefficient corresponding to the video with the video in the historical time period as the target relationship coefficient corresponding to the video with the video.
The first correction submodule 3024 is configured to correct, for any of the video under load, the current relationship coefficient corresponding to the video under load according to the stable relationship coefficient corresponding to the video under load when the determination result of the determination submodule 3023 is negative, to obtain the target relationship coefficient corresponding to the video under load.
Still further optionally, the judging submodule 3023 is further configured to judge whether there is a cargo video with incomplete interaction data in all cargo videos according to the obtained current interaction data of each cargo video in the target time period; when the judging submodule 3023 judges that no video with incomplete interaction data exists in all the video with goods, the first calculating submodule 3021 is triggered to execute the operation of calculating the current relation coefficient corresponding to each video with goods in the target time according to the current interaction data of each video with goods in the target time and the current goods browsing data of the target goods in the target time, and calculating the coefficient difference value between the current relation coefficient corresponding to each video with goods in the target time and the stable relation coefficient corresponding to the video with goods in the history time.
The first correction submodule 3024 is further configured to, when the judging submodule 3023 judges that there are all the freighted videos with incomplete interaction data, perform a data supplementing operation on the freighted videos with incomplete interaction data in all the freighted videos, trigger the first calculating submodule 3021 to perform the above operation according to the current interaction data of each freighted video in the target time period and the current commodity browsing data of the target commodity in the target time period, calculate the current relationship coefficient corresponding to each freighted video in the target time period, and calculate the coefficient difference value between the current relationship coefficient corresponding to each freighted video in the target time period and the stable relationship coefficient corresponding to each freighted video in the history time period.
Further optionally, the specific way for the first correction submodule 3024 to perform the data supplementing operation on the live video with incomplete interactive data in all the live videos is as follows:
counting the quantity of the incomplete interactive data of all the cargo video, and obtaining an interactive data supplementing algorithm matched with the quantity;
and executing data supplementation operation on the video with incomplete interactive data in all the video with goods according to the acquired interactive data supplementation algorithm.
Still further optionally, the specific manner of calculating the stability relationship coefficient corresponding to each of the tape-cargo videos in the historical time period by the first calculation submodule 3021 according to the historical interaction data corresponding to each of the tape-cargo videos and the historical commodity browsing data of the target commodity in the historical time period may be:
acquiring historical interaction data increment of each cargo video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
according to the historical interaction data increment of each cargo video in each historical time period and the historical commodity browsing data increment of the target commodity in each historical time period, constructing an independent equation corresponding to each historical time period, wherein the independent equation corresponding to the historical time period takes the historical relation coefficient corresponding to each cargo video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all cargo videos and the historical commodity browsing data increment of the target commodity in the historical time period;
and constructing an equation set by using independent equations corresponding to all the historical time periods, and calculating a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to the video with goods in the historical time period.
Further optionally, the specific manner in which the first calculation submodule 3021 calculates the solution of the equation set according to the iterative method to obtain the stability relationship coefficient corresponding to each of the video with the video in the history period may be:
continuously calculating a solution of the equation set according to an iteration method;
judging whether the solution of the latest calculated equation set meets a preset precision condition or not;
when the solution of the latest calculated equation set meets the precision condition, respectively determining the solution of the latest calculated equation set as a stable relation coefficient corresponding to each cargo video in the historical time period;
and when the newly calculated solution of the equation set does not meet the precision condition, continuing triggering and executing the operation of continuously calculating the solution of the equation set according to the iteration method.
In another alternative embodiment, as shown in fig. 5, the first computing module 302 may include:
the second calculating submodule 3025 is configured to calculate a stability relationship coefficient corresponding to each of the video with goods in the history time period according to the history interaction data corresponding to each of the video with goods and the history goods browsing data of the target goods in the history time period.
The second calculating submodule 3025 is further configured to calculate a current relationship coefficient corresponding to each of the video with goods in the target time according to the current interaction data of each of the video with goods in the target time period and the current goods browsing data of the target goods in the target time period.
The second correction submodule 3026 is configured to correct, for any one of the video under load, a current relationship coefficient corresponding to the video under load in a target time period according to a stable relationship coefficient corresponding to the video under load in a historical time period, so as to obtain a target relationship coefficient corresponding to each video under load.
Further optionally, the specific manner of calculating the stability relationship coefficient corresponding to each of the tape-cargo videos in the history period according to the history interaction data corresponding to each of the tape-cargo videos and the history commodity browsing data of the target commodity in the history period by the second calculation submodule 3025 is as follows:
acquiring historical interaction data increment of each cargo video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
according to the historical interaction data increment of each cargo video in each historical time period and the historical commodity browsing data increment of the target commodity in each historical time period, constructing an independent equation corresponding to each historical time period, wherein the independent equation corresponding to the historical time period takes the historical relation coefficient corresponding to each cargo video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all cargo videos and the historical commodity browsing data increment of the target commodity in the historical time period;
And constructing an equation set by using independent equations corresponding to all the historical time periods, and calculating a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
Further optionally, the specific manner in which the second calculation submodule 3025 calculates the solution of the equation set according to the iterative method to obtain the stability relationship coefficient corresponding to each of the video with the video in the history period may be:
continuously calculating a solution of the equation set according to an iteration method;
judging whether the solution of the latest calculated equation set meets a preset precision condition or not;
when the solution of the latest calculated equation set meets the precision condition, respectively determining the solution of the latest calculated equation set as a stable relation coefficient corresponding to each cargo video in the historical time period;
and when the newly calculated solution of the equation set does not meet the precision condition, continuing triggering and executing the operation of continuously calculating the solution of the equation set according to the iteration method.
Therefore, the device described by implementing the embodiment of the invention can be based on the historical related data and can be further combined with the determination mode of the commodity browsing value attribute of the current related data so as to accurately and rapidly determine the browsing value attribute of each commodity-carrying video for selling commodities with the commodity, and further can provide objective and accurate reference basis for determining the sales contribution condition of each commodity-carrying video and/or the commodity carrying capability of the video blogger of each commodity-carrying video.
Example IV
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computing device with video browsing value attribute according to another embodiment of the present invention. As shown in fig. 6, the apparatus may include:
a memory 401 storing executable program codes;
a processor 402 coupled with the memory 401;
the processor 402 invokes executable program code stored in the memory 401 to perform some or all of the steps in the calculation method of the value attribute of the video browsing with cargo disclosed in the first or second embodiment of the present invention.
Example five
The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing part or all of the steps in the calculation method of the attribute of the browsing value of the video with goods disclosed in the first embodiment or the second embodiment of the invention when the computer instructions are called.
The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a calculation method and a calculation device for the browsing value attribute of a video with goods, which are disclosed by the embodiment of the invention only for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (9)
1. A method for calculating a viewing value attribute of a video in a ship, the method comprising:
acquiring historical interaction data corresponding to each goods video in all the goods videos used for selling the target goods in the target time period and historical goods browsing data of the target goods in the historical time period corresponding to the historical interaction data;
calculating a target relation coefficient corresponding to each commodity video according to the historical interaction data corresponding to each commodity video and the historical commodity browsing data of the target commodity in the historical time period;
When the required browsing value attribute is the browsing contribution ratio, determining the browsing value attribute of each cargo video to the target commodity in the target time period according to the target relation coefficient corresponding to each cargo video;
when the required browsing value attribute is not the browsing contribution ratio, calculating the browsing value attribute of each commodity-carrying video to the target commodity in the target time period according to the corresponding target relation coefficient of each commodity-carrying video and the current commodity browsing data of the target commodity in the target time period, wherein the browsing value attribute of the commodity-carrying video to the target commodity in the target time period is used for representing the browsing quantity contribution condition of the commodity-carrying video to the target commodity in the target time period;
the calculating, according to the historical interaction data corresponding to each of the video with goods and the historical goods browsing data of the target goods in the historical time period, a target relationship coefficient corresponding to each of the video with goods includes:
according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period, calculating a corresponding stability relation coefficient of each goods-carrying video in the historical time period;
And for any one of the video with goods, determining a stable relation coefficient corresponding to the video with goods in the historical time period as a target relation coefficient corresponding to the video with goods.
2. The method for calculating a viewing value attribute of a video in charge according to claim 1, wherein, for any one of the video in charge, before determining a stable relationship coefficient corresponding to the video in charge in the historical period as a target relationship coefficient corresponding to the video in charge, the method further comprises:
calculating a corresponding current relation coefficient of each cargo video in the target time according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period;
calculating a coefficient difference value of a current relation coefficient corresponding to each video-in-stock video in the target time period and a stable relation coefficient corresponding to the video-in-stock video in the historical time period;
for any one of the video with goods, judging whether the absolute value of the coefficient difference value corresponding to the video with goods is smaller than or equal to a predetermined difference value threshold, and when the judgment result is yes, triggering and executing the operation of determining the stable relation coefficient corresponding to the video with goods in the historical time period as the target relation coefficient corresponding to the video with goods; and when the judging result is negative, correcting the current relation coefficient corresponding to the video with goods according to the stable relation coefficient corresponding to the video with goods to obtain the target relation coefficient corresponding to the video with goods.
3. The method for calculating a viewing value attribute of a video in charge according to claim 1, wherein calculating a target relationship coefficient corresponding to each video in charge according to historical interaction data corresponding to each video in charge and historical merchandise viewing data of the target merchandise in the historical time period comprises:
according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period, calculating a corresponding stability relation coefficient of each goods-carrying video in the historical time period;
calculating a corresponding current relation coefficient of each cargo video in the target time according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period;
and for any one of the video with goods, correcting the current relation coefficient corresponding to the video with goods in the target time period according to the stable relation coefficient corresponding to the video with goods in the historical time period, and obtaining the target relation coefficient corresponding to the video with goods.
4. A method for calculating a viewing value attribute of a video in a commodity according to any one of claims 1 to 3, wherein said calculating a stability relationship coefficient corresponding to each of said video in a history period based on the history interaction data corresponding to each of said video in a commodity in a history period and the history commodity viewing data of said target commodity in said history period includes:
Acquiring historical interaction data increment of each cargo video in each historical time period of the historical time period and historical commodity browsing data increment of the target commodity in each historical time period of the historical time period;
according to the historical interaction data increment of each goods-carrying video in each historical time period and the historical goods browsing data increment of the target goods in each historical time period, constructing an independent equation corresponding to each historical time period, wherein the independent equation corresponding to each historical time period takes a historical relation coefficient corresponding to each goods-carrying video in the historical time period as an unknown number and is used for representing the relation between the historical interaction data increment of all the goods-carrying videos and the historical goods browsing data increment of the target goods in the historical time period;
and constructing an equation set by using independent equations corresponding to all the historical time periods, and calculating a solution of the equation set according to an iteration method to obtain a stable relation coefficient corresponding to each cargo video in the historical time period.
5. The method for calculating a browsing value attribute of a video in charge according to claim 4, wherein the calculating a solution of the equation set according to an iterative method to obtain a stability relationship coefficient corresponding to each video in charge in the historical time period includes:
Continuously calculating a solution of the equation set according to an iteration method;
judging whether the newly calculated solution of the equation set meets a preset precision condition or not;
when the newly calculated solution of the equation set meets the precision condition, respectively determining the newly calculated solution of the equation set as a corresponding stable relation coefficient of each cargo video in the historical time period;
and triggering and executing the operation of continuously calculating the solution of the equation set according to an iteration method when the newly calculated solution of the equation set is judged not to meet the precision condition.
6. The method for calculating a viewing value attribute of a video in charge according to claim 2, wherein before calculating a corresponding current relationship coefficient of each video in charge in the target time according to the current interaction data of each video in charge in the target time and the current merchandise viewing data of the target merchandise in the target time, the method further comprises:
judging whether all the carried videos have carried videos with incomplete interaction data according to the acquired current interaction data of each carried video in the target time period;
When judging that the video with incomplete interaction data does not exist in all the video with goods, triggering and executing the operation of calculating the corresponding current relation coefficient of each video with goods in the target time according to the current interaction data of each video with goods in the target time period and the current goods browsing data of the target goods in the target time period;
when judging that the all the cargo video has incomplete interaction data, executing data supplementing operation on the cargo video with incomplete interaction data in all the cargo video, triggering and executing the operation according to the current interaction data of each cargo video in the target time period and the current commodity browsing data of the target commodity in the target time period, and calculating the corresponding current relation coefficient of each cargo video in the target time period;
the data supplementing operation is performed on all the carried videos with incomplete interactive data, and the data supplementing operation comprises the following steps:
counting the quantity of the incomplete interactive data in all the cargo video, and obtaining an interactive data supplementing algorithm matched with the quantity;
And executing data supplementation operation on all the cargo video with incomplete interaction data in the cargo video according to the acquired interaction data supplementation algorithm.
7. A computing device for a value attribute of a video-in-stock, the device comprising:
the acquisition module is used for acquiring historical interaction data corresponding to each cargo video in all cargo videos used for selling target commodities in a cargo period and historical commodity browsing data of the target commodities in a historical period corresponding to the historical interaction data;
the first calculation module is used for calculating a target relation coefficient corresponding to each cargo video according to the historical interaction data corresponding to each cargo video and the historical commodity browsing data of the target commodity in the historical time period;
the second calculation module is used for determining the browsing value attribute of each cargo video to the target commodity in the target time period according to the target relation coefficient corresponding to each cargo video when the required browsing value attribute is the browsing contribution duty ratio; when the required browsing value attribute is not the browsing contribution ratio, calculating the browsing value attribute of each commodity-carrying video to the target commodity in the target time period according to the corresponding target relation coefficient of each commodity-carrying video and the current commodity browsing data of the target commodity in the target time period, wherein the browsing value attribute of the commodity-carrying video to the target commodity in the target time period is used for representing the browsing quantity contribution condition of the commodity-carrying video to the target commodity in the target time period;
And, the first computing module, comprising:
the first calculation sub-module is used for calculating a stable relation coefficient corresponding to each goods-carrying video in the historical time period according to the historical interaction data corresponding to each goods-carrying video and the historical commodity browsing data of the target commodity in the historical time period;
and the determining submodule is used for determining the stable relation coefficient corresponding to any video with goods in the historical time period as the target relation coefficient corresponding to the video with goods.
8. A computing device for a value attribute of a video-in-stock, the device comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the method of calculating the value attribute of video browsing in tape as claimed in any one of claims 1 to 6.
9. A computer storage medium storing computer instructions which, when invoked, are operable to perform a method of calculating a value attribute of a video browsing with cargo according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010928029.1A CN112235636B (en) | 2020-09-07 | 2020-09-07 | Calculation method and device for browsing value attribute of video with goods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010928029.1A CN112235636B (en) | 2020-09-07 | 2020-09-07 | Calculation method and device for browsing value attribute of video with goods |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112235636A CN112235636A (en) | 2021-01-15 |
CN112235636B true CN112235636B (en) | 2023-04-21 |
Family
ID=74116980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010928029.1A Active CN112235636B (en) | 2020-09-07 | 2020-09-07 | Calculation method and device for browsing value attribute of video with goods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112235636B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112965969B (en) * | 2021-03-08 | 2024-05-07 | 咪咕文化科技有限公司 | Method and device for complement of statistical data, electronic equipment and storage medium |
CN113034230A (en) * | 2021-03-17 | 2021-06-25 | 杭州遥望网络科技有限公司 | Live broadcast delivery time length determination method, device, equipment and medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160225023A1 (en) * | 2013-09-26 | 2016-08-04 | Technicolor (China) Technology Co., Ltd. | Method and apparatus for providing targeted videos to user |
CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
CN110929127A (en) * | 2019-12-05 | 2020-03-27 | 广州市原象信息科技有限公司 | Method for analyzing Taobao live broadcast putting effect and computer equipment |
-
2020
- 2020-09-07 CN CN202010928029.1A patent/CN112235636B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112235636A (en) | 2021-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112235636B (en) | Calculation method and device for browsing value attribute of video with goods | |
US20180322404A1 (en) | Time Series Based Data Prediction Method and Apparatus | |
US9665902B2 (en) | Personalized recommendation method and system, and computer-readable record medium | |
US9294577B2 (en) | Click through rate estimation in varying display situations | |
AU2010212400B2 (en) | Using estimated ad qualities for ad filtering, ranking and promotion | |
TWI587229B (en) | Push method and device for product information | |
US20020046128A1 (en) | Automatic pricing method and device | |
KR102111223B1 (en) | Push information roughly select sorting method, device and computer storage media | |
US20030229502A1 (en) | Markdown management | |
CN107093091B (en) | Data processing method and device | |
US20090177520A1 (en) | Techniques for casual demand forecasting | |
CN109543132A (en) | Content recommendation method, device, electronic equipment and storage medium | |
CN110415004A (en) | For determining the method and device of merchandise valuation | |
CN108428153A (en) | Strategy adjusting method, server and the Developing Tactics system of presell commodity | |
CN110310168A (en) | Method of adjustment, device, server and the storage medium of model | |
CN112150182B (en) | Multimedia file pushing method and device, storage medium and electronic device | |
CN112218169B (en) | Method and device for calculating browsing value attribute of video with goods to commodities | |
CN112330098B (en) | Intelligent calculation method and device for KOL (KOL) capacity attribute | |
KR101658714B1 (en) | Method and system for predicting online customer action based on online activity history | |
CN112243153B (en) | Method and device for determining browsing value attribute based on video interaction data | |
CN112261475B (en) | Method and device for evaluating commodity browsing value attribute of video with goods | |
CN113298550A (en) | Commodity price adjusting method and device and server | |
CN110689406A (en) | Product push system based on internet | |
CN105589950B (en) | Event attribute sentence is determining and is based on event attribute sentence method for early warning and device | |
US20200380583A1 (en) | Promptly adjust recommendations to increase performance in a web site |
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 |