CN116051154A - Media terminal data analysis management system - Google Patents
Media terminal data analysis management system Download PDFInfo
- Publication number
- CN116051154A CN116051154A CN202310200747.0A CN202310200747A CN116051154A CN 116051154 A CN116051154 A CN 116051154A CN 202310200747 A CN202310200747 A CN 202310200747A CN 116051154 A CN116051154 A CN 116051154A
- Authority
- CN
- China
- Prior art keywords
- user
- media terminal
- data
- target media
- loss
- 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.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 238000013075 data extraction Methods 0.000 claims abstract description 6
- 238000012544 monitoring process Methods 0.000 claims description 64
- 238000011156 evaluation Methods 0.000 claims description 39
- 238000000034 method Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 19
- 238000007726 management method Methods 0.000 claims description 14
- 238000012790 confirmation Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000002457 bidirectional effect Effects 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 3
- 238000004141 dimensional analysis Methods 0.000 abstract description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000007792 addition Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of data analysis management, and particularly discloses a media terminal data analysis management system, which comprises a media data extraction module, a media data analysis module, a reference media data setting module, a user loss analysis module and an information feedback terminal; according to the invention, through carrying out multiple links such as user loss analysis, setting reference media data, confirming main user loss elements and the like, the multi-dimensional analysis of the main user loss elements is realized, the problem that the current utilization rate of the media data is not high is effectively solved, the intuitiveness and timeliness of early warning of loss of a media terminal user are improved, reliable decision suggestion and optimization direction are provided for the improvement of a subsequent operation plan of the media terminal, the registration rate and conversion rate of a new user and the experience of an old user are further effectively improved, the bidirectional maintenance of the new user and the old user is realized, and the subsequent loss rate of the user is greatly reduced.
Description
Technical Field
The invention belongs to the technical field of data analysis and management, and relates to a media terminal data analysis and management system.
Background
With the continuous development of internet technology and full media process, various media forms and terminals are more specialized and subdivided, people can also receive information of the media forms in more scenes, and under the background, the competitive pressure of various media terminals is gradually increased, so that the necessity of media data analysis is highlighted.
The feasibility and risk of the subsequent operation of the media terminal are directly influenced by the user, and the current media data of the media terminal is also focused on the user analysis level, such as user preference and user loss.
According to the method and device for determining the lost user disclosed in the Chinese patent application with the application publication number of CN107358247A in the prior art, the behavior characteristic data of the user at the preset time and the access result of the user in the statistical time of the distance between the preset time are mainly used as sample data for PU learning, and a classifier capable of calculating the loss probability of the user at the statistical time is constructed, so that the loss probability of the user at the statistical time is accurately calculated, and the accuracy of identifying the lost user is improved.
Aiming at the scheme, the current technology focuses on the loss confirmation of a user at a certain moment, belongs to predictive loss client analysis, and has the following problems: 1. the loss probability of the user can only be obtained, so that whether the client is lost or not is judged, the method belongs to the individual view angle of the user, is focused on the subsequent maintenance of a single user, does not carry out integral client loss analysis according to the user change layer, cannot improve the intuitiveness and early warning timeliness of the loss early warning of the media terminal user, and cannot provide reliable decision-making advice for the improvement of the subsequent operation plan of the media terminal.
2. The current utilization rate of the media data is not high, the analysis of the customer loss reasons is not carried out by combining the media data of the same type of media terminals only according to the behavior data and the access data of the users, and a reliable optimization direction cannot be provided for the media terminals, so that the registration rate of new users and the experience of old users cannot be improved.
Disclosure of Invention
In view of this, in order to solve the problems set forth in the background art, a media terminal data analysis management system is now proposed.
The aim of the invention can be achieved by the following technical scheme: the invention provides a media terminal data analysis management system, which comprises: the media data extraction module is used for extracting media data corresponding to the target media terminal, wherein the media data comprises basic data, user data and media data.
And the media data analysis module is used for carrying out user loss assessment according to the user data corresponding to the target media terminal, if the user loss is larger than the set loss threshold value, the user loss analysis module is started, and otherwise, the information feedback terminal is started.
The reference media data setting module is used for extracting media data of each media terminal with the same attribute as the target media terminal and setting the media data corresponding to the reference of the target media terminal.
And the user loss analysis module is used for confirming the loss element of the main user of the target media terminal according to the media data corresponding to the target media terminal and the referenced media data.
And the information feedback terminal is used for feeding back the user loss assessment result or the main user loss element to an operation manager of the target media terminal.
In a preferred embodiment of the present invention, the basic data is creation date, integrated user quantity, user age interval and coverage area number.
The user data includes an accumulated user amount, an added user amount, a member registration user amount, an active user amount, a logged-off user amount, and an average viewing time period in each monitoring period.
The media data includes copyright data, advertisement data, play data, and resource data.
Wherein the copyright data includes the number of exclusive copyrights and the number of ordinary copyrights.
The advertisement data includes a member advertisement duration and a non-member advertisement duration.
The play data includes picture definition, average loading time length and analysis error rate.
The resource data includes the number of first-broadcast films, the number of single-broadcast films, the number of homemade films, the number of non-member viewable films, the number of film types and the number of films corresponding to each film type.
In a preferred embodiment of the present invention, the user loss assessment method includes: extracting average watching time length of target media terminal in each monitoring period
D represents the monitoring period number, < >>
。
Calculating a loss evaluation index of a target media terminal corresponding to a viewing time layer
，
。
wherein ,
representing the average viewing time length of the target media terminal in the t+1th monitoring period,/for the target media terminal>
For a set reference user average viewing duration difference, +.>
For the viewing layer loss evaluation correction factor, m represents the number of monitoring cycles.
Calculating loss evaluation index of target media terminal corresponding to user variation layer
。
Will be
、/>
The method comprises the steps of importing a formula to calculate a comprehensive loss evaluation index of a target media terminal>
，
。
wherein ,
the comprehensive loss duty ratio weight factors corresponding to the watching time length and the user variation are respectively +.>
To set constant +.>
，/>
The correction factor is evaluated for the user churn.
In a preferred embodiment of the present invention, the loss evaluation index of the target media terminal corresponding to the user variation layer is specifically calculated as follows: and counting the newly added user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio of the target media terminal in each monitoring period according to the user data of the target media terminal in each monitoring period.
And constructing a change curve of the newly added user ratio, the membership registration user ratio, the active user ratio and the cancellation user ratio.
And locating the position of each extreme point from the newly added user ratio change curve, and dividing the newly added user ratio change curve into curve segments.
Counting the number of falling curve segments
And analyzing to obtain the average slope of the falling curve segment +.>
Average interval monitoring period length->
And comprehensive coverage monitoring period length +.>
。/>
Calculating the change coincidence degree of newly added users
，/>
。
wherein ,
respectively corresponding to the set slope, the interval monitoring period length and the coverage monitoring period length and the estimated duty ratio weight factor, < ->
Evaluating correction factors for setting new user changes, < ->
Respectively setting the descending slope, descending interval monitoring period length and descending coverage monitoring period ratio of the reference, +.>
The number of the monitoring periods and the number of the newly added user ratio change curve segments are respectively.
The change coincidence degree of the member registration user is calculated in a same way according to the calculation mode of the change coincidence degree of the newly added user
Active user variation compliance->
Analyzing the variation coincidence degree of the logged-off user according to the variation ratio curve of the logged-off user>
；
Calculating loss evaluation index of target media terminal corresponding to user variation layer
，
；
wherein ,
respectively is newly addedUser, member registration user, active user and logged off user change compliance corresponding to user change level churn assessment duty factor, +.>
And evaluating correction factors for the set user variation level loss.
In a preferred embodiment of the present invention, the specific setting process of the media data correspondingly referred to by the target media terminal is: and recording each media terminal with the same attribute as the target media terminal as each associated media terminal.
And calculating the comprehensive loss evaluation index of each associated media terminal, and screening each reference media terminal.
Basic data of each reference media terminal is extracted, and the reference association degree of each reference media terminal is calculated
And taking the media data of the reference media terminal with the highest association degree as the media data of the corresponding reference of the target media terminal.
In a preferred embodiment of the present invention, the specific calculation process of the reference relevance of each reference media terminal is: positioning the comprehensive user quantity from the basic data of each reference media terminal
User age section->
And coverage area number->
，/>
Indicating reference to media terminal number->
。
Positioning the comprehensive user quantity from the basic data of the target media terminal
User age section->
And coverage area number->
。
Calculating the reference association degree of each reference media terminal
，
；
wherein ,
the corresponding association evaluation of the set user quantity, the user age interval and the coverage area number is respectively used for evaluating the duty ratio weight, +.>
The user difference, the user age difference, and the coverage area number difference of the set reference are respectively.
In a preferred embodiment of the present invention, the target media terminal main body user loss element specifically comprises: extracting referenced copyright data and resource data from media data correspondingly referenced by a target media terminal, and calculating a resource volume element difference index corresponding to the target media terminal
。
Extracting referenced advertisement data and playing data from media data correspondingly referenced by a target media terminal, and calculating a viewing experience element difference index corresponding to the target media terminal
；
Extracting the basic data of the reference from the media data corresponding to the reference of the target media terminal, and further extracting the creation date
And comprehensive user quantity->
Calculating market viscosity element difference index corresponding to target media terminal>
。
Respectively differencing the resource volume element difference index, the viewing experience element difference index and the market viscosity element difference index corresponding to the target media terminal with the set permission difference index, and sequentially marking the differences as
、/>
And
。
if it is
And taking other elements as loss elements of the main user of the target media terminal.
If it is
、/>
and />
If the difference index difference value of a certain element is larger than 0, the element is marked as a candidate element.
And counting the number of the elements to be selected, and taking the element to be selected with the largest difference index difference as a loss element of the main body user of the target media terminal.
In a preferred embodiment of the present invention, the specific calculation process of the target media terminal resource volume element difference index is: copyright number correspondingly referenced from target media terminalExtracting the number of exclusive copyrights from the data
And the number of general copyrights->
Setting a resource volume evaluation compensation factor +.>
。
Analyzing the resource data correspondingly referenced by the target media terminal to obtain the richness of the referenced film
And viewing dominance with reference to film>
And analyzing the same to obtain the corresponding film richness of the target media terminal>
And movie viewing dominance->
。
Calculating the difference index of the target media terminal resource volume element
，
。
wherein ,
the occupancy weights are evaluated for the corresponding resource volumes of the resource richness and the film playing dominance respectively,
the differences are the differences in film richness and film viewing preference of the set permissions.
In a preferred embodiment of the present invention, the target media terminal has poor viewing experience elementsThe specific calculation process of the differential index comprises the following steps: extracting member advertisement time length from advertisement data correspondingly referenced by target media terminal
And non-member advertisement duration->
。
Extracting picture definition from play data correspondingly referenced by target media terminal
Average load duration->
And resolution error Rate->
。
Calculating a target media terminal watching experience element difference index
，/>
。
Wherein e is a natural constant,
the corresponding watching experience difference of the advertisement layer and the playing layer are respectively evaluated to be the duty ratio weight and the +.>
Evaluating correction factors for viewing experience->
And the advertisement layer and the playing layer correspond to the difference indexes of the watching experience elements respectively. />
wherein ,
the weight of the ratio is evaluated for the set member advertisement time length and the advertisement layer corresponding to the non-member advertisement time length respectively, and the weight is +.>
The corresponding play layer evaluation of the set picture definition, loading time and analysis error rate is respectively used for evaluating the duty ratio weight, < >>
Respectively setting reference member advertisement time length difference, non-member advertisement time length difference, playing loading time length difference and analysis error rate difference,>
、/>
、/>
、/>
、/>
the method comprises the steps of respectively obtaining the member advertisement time length, the non-member advertisement time length, the picture definition, the average loading time length and the analysis error rate corresponding to the target media terminal.
In a preferred embodiment of the present invention, a specific calculation formula of the target media terminal market viscosity factor difference index is as follows:
wherein ,
respectively setting up date and comprehensive user quantity corresponding to target media terminal>
Separately evaluating the duty weight, the ++for the set creation year, the user quantity and the market viscosity factor difference>
Respectively set reference difference annual limit value, reference user quantity ratio, +.>
Representing the rounding-up symbol +_>
The correction factor is evaluated for the set market viscosity difference.
Compared with the prior art, the invention has the following beneficial effects: (1) According to the invention, the multi-dimensional analysis of the main user loss element is realized by setting and referencing the media data and confirming the main user loss element from three dimensions of resource volume, viewing experience and market viscosity, so that the problem of low utilization rate of the current media data is effectively solved, a reliable optimization direction is provided for the media terminal, the registration rate and conversion rate of a new user and the experience of an old user are effectively improved, and the bidirectional maintenance of the new and old users is realized, thereby reducing the user loss rate of the subsequent media terminal.
(2) According to the invention, the user loss evaluation is carried out from the view duration layer and the user variation layer, so that the integral analysis of the loss of the media terminal user is realized, the intuitiveness of the loss early warning of the media terminal user and the timeliness of the early warning are improved, and reliable decision-making advice is provided for the improvement of the subsequent operation plan of the media terminal.
(3) According to the invention, the contrast and reliability of analysis of the loss elements of the main body user of the media terminal are improved by setting the reference media data from the user information and the regional information, so that the confirmation result of the loss elements of the main body user of the media terminal is more accurate and reasonable, and the error rate of confirmation of the loss elements of the main body user of the media terminal is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the connection of the modules of the system of the present invention.
FIG. 2 is a diagram showing a variation curve of the user ratio according to the present invention.
Reference numerals: 1. and covering the monitoring period length, and monitoring the period length at intervals of 2.
Detailed Description
The foregoing is merely illustrative of the principles of the invention, and various modifications, additions and substitutions for those skilled in the art will be apparent to those having ordinary skill in the art without departing from the principles of the invention or beyond the scope of the invention as defined in the accompanying claims.
Referring to fig. 1, the invention provides a media terminal data analysis management system, which comprises a media data extraction module, a media data analysis module, a reference media data setting module, a user loss analysis module and an information feedback terminal;
the media data extraction module is respectively connected with the media data analysis module and the user loss analysis module, the media data analysis module is respectively connected with the reference media data setting module, the user loss analysis module and the information feedback terminal, and the user loss analysis module is respectively connected with the reference media data setting module and the information feedback terminal.
The media data extraction module is used for extracting media data corresponding to the target media terminal, and the media data comprises basic data, user data and media data.
Specifically, the basic data is creation date, integrated user quantity, user age interval, and coverage area number.
The user data includes an accumulated user amount, an added user amount, a member registration user amount, an active user amount, a logged-off user amount, and an average viewing time period in each monitoring period.
The media data includes copyright data, advertisement data, play data, and resource data.
Wherein the copyright data includes the number of exclusive copyrights and the number of ordinary copyrights.
The advertisement data includes a member advertisement duration and a non-member advertisement duration.
The play data includes picture definition, average loading time length and analysis error rate.
The resource data includes the number of first-broadcast films, the number of single-broadcast films, the number of homemade films, the number of non-member viewable films, the number of film types and the number of films corresponding to each film type.
In one particular embodiment the media terminals include, but are not limited to, video viewing software and video viewing websites.
And the media data analysis module is used for carrying out user loss assessment according to the user data corresponding to the target media terminal, if the user loss is larger than the set loss threshold value, the user loss analysis module is started, and otherwise, the information feedback terminal is started.
Illustratively, performing a user churn assessment includes: a1, extracting average watching time length of target media terminal in each monitoring period
D represents the monitoring period number, < >>
。
A2, calculating a loss evaluation index of the target media terminal corresponding to the viewing time layer
，
。
wherein ,
representing the average viewing time length of the target media terminal in the t+1th monitoring period,/for the target media terminal>
For a set reference user average viewing duration difference, +.>
For the viewing layer loss evaluation correction factor, m represents the number of monitoring cycles.
A3, calculating a loss evaluation index of the target media terminal corresponding to the user variation layer
The specific calculation comprises the following steps: />
And A3-1, counting the newly added user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio of the target media terminal in each monitoring period according to the user data of the target media terminal in each monitoring period.
It should be noted that, the specific statistical process of the new user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio in each monitoring period is as follows: and extracting the accumulated user quantity, the newly added user quantity, the member registration user quantity, the active user quantity and the cancellation user quantity of the target media terminal in each monitoring period, and comparing the newly added user quantity, the member registration user quantity, the active user quantity and the cancellation user quantity with the accumulated user quantity respectively to obtain the newly added user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio of the target media terminal in each monitoring period.
A3-2, constructing a new user ratio, a member registration user ratio, an active user ratio and a cancellation user ratio change curve.
It should be noted that, the specific construction basis of the change curves of the newly added user ratio, the member registration user ratio, the active user ratio and the logged-off user ratio is as follows: and marking a plurality of points in two-dimensional coordinates of the newly added user ratio, the member registered user ratio, the active user ratio and the logged off user ratio in the monitoring period by taking the monitoring period as an abscissa and taking the newly added user ratio, the member registered user ratio, the active user ratio and the logged off user ratio as an ordinate, so as to obtain a time change curve of the newly added user ratio, the renewal user ratio, the active user ratio and the newly added member user ratio, and respectively marking the time change curve as the newly added user ratio, the member registered user ratio, the active user ratio and the logged off user ratio.
A3-4, please refer to FIG. 2, the position of each extreme point is located from the newly added user ratio change curve, and the newly added user ratio change curve is divided into curve segments.
A3-5, counting the number of descending curve segments
And analyzing to obtain the average slope of the falling curve segment +.>
Average interval monitoring period length->
And comprehensive coverage monitoring period length +.>
。
The average slope of the falling curve segment
Average interval monitoring period length->
And comprehensive coverage monitoring period length +.>
The specific analysis process of (2) is as follows:
the slope of each falling curve segment, the coverage monitoring period length 1, and the interval monitoring period length 2 between each falling curve segment are extracted.
Respectively carrying out average value calculation on the slope of each descending curve segment and the interval monitoring period length between each descending curve segment to obtain the average slope and the average interval monitoring period length corresponding to the descending curve segments;
and accumulating the coverage monitoring period lengths of the descending curve segments to obtain the comprehensive coverage monitoring period length of the descending curve segments.
A3-6, calculating the change coincidence degree of the newly added user
，/>
。
wherein ,
respectively corresponding to the set slope, the interval monitoring period length and the coverage monitoring period length and the estimated duty ratio weight factor, < ->
Evaluating correction factors for setting new user changes, < ->
Respectively setting the descending slope, descending interval monitoring period length and descending coverage monitoring period ratio of the reference, +.>
The number of the monitoring periods and the number of the newly added user ratio change curve segments are respectively.
A3-7, calculating the change coincidence degree of the member registration user in a same way according to the calculation mode of the change coincidence degree of the newly added user
Active user variation compliance->
Analyzing the variation coincidence degree of the logged-off user according to the variation ratio curve of the logged-off user>
。/>
It should be noted that, the specific calculation process of the user change conformity cancellation is as follows: dividing the logged-off user ratio change curve into ascending change curve segments according to the dividing mode of the newly added user ratio change curve.
The average slope of the ascending curve segment is obtained by the same analysis according to the analysis modes of the average slope of the descending curve segment, the average interval monitoring period length and the comprehensive coverage monitoring period length in the new user ratio change curve
Average interval monitoring period length->
And comprehensive coverage monitoring period length +.>
。
Calculating the change coincidence degree of a logged-off user
，
。
wherein ,
the set slope, interval monitoring period length and coverage monitoring period length correspond to the logged off user duty ratio change to accord with the estimated duty ratio weight factor respectively, < >>
To set the duty ratio change of the logged-off user to be in accordance with the evaluation and correction factors +.>
Respectively set up reference log-off user rising slope, reference rising interval monitoring period length, reference rising coverage monitoring period ratio, +.>
To log off the user's specific change curve segment number.
A3-8, calculating the loss evaluation index of the target media terminal corresponding to the user variation layer
，
。
wherein ,
the weight factor of the duty ratio is evaluated for the loss of the user change level corresponding to the change coincidence degree of the newly added user, the member registration user, the active user and the cancellation user respectively>
And evaluating correction factors for the set user variation level loss.
A4, will
、/>
The method comprises the steps of importing a formula to calculate a comprehensive loss evaluation index of a target media terminal>
，
。
wherein ,
the comprehensive loss duty ratio weight factors corresponding to the watching time length and the user variation are respectively +.>
To set constant +.>
，/>
The correction factor is evaluated for the user churn.
According to the embodiment of the invention, the user loss evaluation is carried out from the view duration layer and the user variation layer, so that the integral analysis of the loss of the media terminal user is realized, the intuitiveness of the early warning of the loss of the media terminal user and the timeliness of the early warning are improved, and reliable decision-making advice is provided for the improvement of the subsequent operation plan of the media terminal.
The reference media data setting module is used for extracting media data of each media terminal with the same attribute as the target media terminal and setting the media data corresponding to the reference of the target media terminal, and the specific setting process is as follows: and 1, recording each media terminal with the same attribute as the target media terminal as each associated media terminal.
And step 2, carrying out the same-way calculation according to the calculation mode of the target media terminal comprehensive loss evaluation index to obtain the comprehensive loss evaluation index of each associated media terminal, comparing the comprehensive loss evaluation index with the target media terminal comprehensive loss evaluation index, and screening each associated media terminal which is larger than the target media terminal comprehensive loss evaluation index from the comprehensive loss evaluation index as each reference media terminal.
Step 3, extracting basic data of each reference media terminal, and calculating the reference association degree of each reference media terminal
And taking the media data of the reference media terminal with the highest association degree as the media data of the corresponding reference of the target media terminal.
The specific calculation process of the reference association degree of each reference media terminal comprises the following steps: positioning the comprehensive user quantity from the basic data of each reference media terminal
User age section->
And coverage area number->
，/>
Indicating reference to media terminal number->
。
Positioning the comprehensive user quantity from the basic data of the target media terminal
User age section->
And coverage area number->
。
Calculating the reference association degree of each reference media terminal
，
。
wherein ,
the corresponding association evaluation of the set user quantity, the user age interval and the coverage area number is respectively used for evaluating the duty ratio weight, +.>
The user difference, the user age difference, and the coverage area number difference of the set reference are respectively.
According to the embodiment of the invention, the contrast and reliability of analysis of the loss elements of the main body user of the media terminal are improved by setting the reference media data from the user information and the regional information, so that the confirmation result of the loss elements of the main body user of the media terminal is more accurate and reasonable, and the error rate of confirmation of the loss elements of the main body user of the media terminal is reduced.
And the user loss analysis module is used for confirming the loss element of the main user of the target media terminal according to the media data corresponding to the target media terminal and the referenced media data.
Illustratively, the target media terminal main body user loss element comprises the following specific confirmation processes: x1, extracting referenced copyright data and resource data from media data correspondingly referenced by a target media terminal, and calculating a resource volume element difference index corresponding to the target media terminal
。
Understandably, the specific calculation process of the target media terminal resource volume element difference index is as follows: x1-1, extracting the number of exclusive copyrights from the copyrights data correspondingly referenced by the target media terminal
And the number of general copyrights->
Setting a resource volume evaluation compensation factor +.>
。
It should be noted that, the resource volume estimation compensation factor
The specific calculation formula is as follows:
wherein ,
and />
The number of exclusive rights and the number of common rights corresponding to the target media terminal are respectively,
respectively, the difference of the total number of the set reference copyrights and the difference of the ratio of the reference exclusive copyrights>
And evaluating and compensating the duty ratio weight for the resource volume elements of the copyright layer corresponding to the set total number of the copyright and the exclusive copyright duty ratio respectively.
X1-2, analyzing the resource data correspondingly referenced by the target media terminal to obtain the richness of the referenced film
And viewing dominance with reference to film>
And analyzing the same to obtain the corresponding film richness of the target media terminal>
And movie viewing dominance->
。/>
It should be noted that, the specific evaluation basis of the film richness is as follows: record the number of film types as
And accumulating the numbers of the movies corresponding to each movie category to obtain the number of integrated movies, which is recorded as +.>
。
Calculating the richness of a reference film
，/>
。
wherein ,
respectively expressed as the number of the types of the set reference filmsThe number of reference films to be added,
the film richness evaluation duty ratio weight is respectively expressed as the film type and the film number.
It should be further noted that, the specific analysis process with reference to the film viewing dominance is as follows: extracting the number of first-broadcast films, the number of single-broadcast films, the number of homemade films and the number of non-member visible films from the resource data correspondingly referenced by the target media terminal, and comparing the number of first-broadcast films, the number of single-broadcast films, the number of homemade films and the number of non-member visible films with the number of comprehensive films to obtain the ratio of the first-broadcast films to be referenced
Reference to the duty of a single film
Reference home-made film duty ∈ ->
And a reference normal viewable duty cycle->
。
Calculating a viewing dominance of a reference film
，/>
。
wherein ,
evaluating the duty weight for setting the viewing dominance of the reference film,/->
The weight of the duty ratio is evaluated for the corresponding film playing dominance duty ratio of the set common viewable duty ratio, the first-play film duty ratio, the single-play film duty ratio and the self-made film duty ratio respectively, and the weight is->
、/>
、/>
、/>
The control common visible ratio, the control first-broadcast film ratio, the control single-broadcast film ratio and the control self-made film ratio are respectively set.
X1-3, calculating a target media terminal resource volume element difference index
，
。
wherein ,
the occupancy weights are evaluated for the corresponding resource volumes of the resource richness and the film playing dominance respectively,
the differences are the differences in film richness and film viewing preference of the set permissions.
X2, extracting referenced advertisement data and play data from media data correspondingly referenced by the target media terminal, and calculating a viewing experience element difference index corresponding to the target media terminal
。
Understandably, the specific calculation process of the target media terminal watching experience element difference index is as follows: x2-1, extracting member advertisement duration from advertisement data correspondingly referenced by a target media terminal
And non-member advertisement duration->
。
X2-2, extracting picture definition from playing data correspondingly referenced by the target media terminal
Average loading time
And resolution error Rate->
。
X2-3, calculating a target media terminal watching experience element difference index
，
。/>
Wherein e is a natural constant,
the corresponding watching experience difference of the advertisement layer and the playing layer are respectively evaluated to be the duty ratio weight and the +.>
Evaluating correction factors for viewing experience->
And the advertisement layer and the playing layer correspond to the difference indexes of the watching experience elements respectively.
wherein ,
respectively corresponds to the set member advertisement time and the non-member advertisement timeAdvertisement deck evaluation duty weight, +.>
The corresponding play layer evaluation of the set picture definition, loading time and analysis error rate is respectively used for evaluating the duty ratio weight, < >>
Respectively setting reference member advertisement time length difference, non-member advertisement time length difference, playing loading time length difference and analysis error rate difference,>
、/>
、/>
、/>
、/>
the method comprises the steps of respectively obtaining the member advertisement time length, the non-member advertisement time length, the picture definition, the average loading time length and the analysis error rate corresponding to the target media terminal.
X3, extracting the reference basic data from the media data correspondingly referenced by the target media terminal, and further extracting the creation date
And comprehensive user quantity->
Calculating market viscosity element difference index corresponding to target media terminal>
。
Understandably, the specific calculation formula of the target media terminal market viscosity factor difference index is as follows:
wherein ,
respectively setting up date and comprehensive user quantity corresponding to target media terminal>
Separately evaluating the duty weight, the ++for the set creation year, the user quantity and the market viscosity factor difference>
Respectively set reference difference annual limit value, reference user quantity ratio, +.>
Representing the rounding-up symbol +_>
The correction factor is evaluated for the set market viscosity difference.
X4, respectively differencing the resource volume element difference index, the viewing experience element difference index and the market viscosity element difference index corresponding to the target media terminal with the set permission difference index, and sequentially marking the differences as
、/>
and />
。
X5, if
And taking other elements as loss elements of the main user of the target media terminal.
X6, if
、/>
and />
If the difference index difference value of a certain element is larger than 0, the element is marked as a candidate element.
And X7, counting the number of the elements to be selected, and taking the element to be selected with the largest difference index difference as a loss element of the main body user of the target media terminal.
According to the embodiment of the invention, the main user loss element is confirmed from three dimensions of resource volume, viewing experience and market viscosity by setting and referencing the media data, so that the multi-dimensional analysis of the main user loss element is realized, the problem of low utilization rate of the current media data is effectively solved, a reliable optimization direction is provided for the media terminal, the registration rate and conversion rate of a new user and the experience of an old user are effectively improved, and the bidirectional maintenance of the new and old user is realized, so that the user loss rate of a subsequent media terminal is reduced.
And the information feedback terminal is used for feeding back the user loss assessment result or the main user loss element to an operation manager of the target media terminal.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of the invention or beyond the scope of the invention as defined in the claims.
Claims (10)
1. A media terminal data analysis management system is characterized in that: comprising the following steps:
the media data extraction module is used for extracting media data corresponding to the target media terminal, wherein the media data comprises basic data, user data and media data;
the media data analysis module is used for carrying out user loss assessment according to the user data corresponding to the target media terminal, if the user loss is larger than the set loss threshold value, the user loss analysis module is started, and otherwise, the information feedback terminal is started;
the reference media data setting module is used for extracting media data of each media terminal with the same attribute as the target media terminal and setting the media data corresponding to the reference of the target media terminal;
the user loss analysis module is used for confirming the loss element of the main user of the target media terminal according to the media data corresponding to the target media terminal and the referenced media data;
and the information feedback terminal is used for feeding back the user loss assessment result or the main user loss element to an operation manager of the target media terminal.
2. The media terminal data analysis management system according to claim 1, wherein: the basic data are creation date, comprehensive user quantity, user age interval and coverage area number;
the user data comprises accumulated user quantity, newly added user quantity, member registration user quantity, active user quantity, logged-off user quantity and average watching time length in each monitoring period;
the media data includes copyright data, advertisement data, play data and resource data; wherein,
the copyright data includes the number of exclusive copyright and the number of ordinary copyright;
the advertisement data includes a member advertisement duration and a non-member advertisement duration;
the play data comprises picture definition, average loading time length and analysis error rate;
the resource data includes the number of first-broadcast films, the number of single-broadcast films, the number of homemade films, the number of non-member viewable films, the number of film types and the number of films corresponding to each film type.
3. The media terminal data analysis management system according to claim 2, wherein: the user loss assessment method comprises the following steps of:
extracting target media terminals in each monitoring periodAverage viewing duration over a period
D represents the number of the monitoring period,
；
calculating a loss evaluation index of a target media terminal corresponding to a viewing time layer
，/>
；
wherein ,
representing the average viewing time length of the target media terminal in the t+1th monitoring period,/for the target media terminal>
For a set reference user average viewing duration difference, +.>
Evaluating a correction factor for the viewing layer loss, m representing the number of monitoring cycles;
calculating loss evaluation index of target media terminal corresponding to user variation layer
；
Will be
、/>
The method comprises the steps of importing a formula to calculate a comprehensive loss evaluation index of a target media terminal>
，
；
wherein ,
the comprehensive loss duty ratio weight factors corresponding to the watching time length and the user variation are respectively +.>
In order to set the constant value of the constant,
，/>
the correction factor is evaluated for the user churn.
4. A media terminal data analysis management system according to claim 3, wherein: the loss evaluation index of the target media terminal corresponding to the user variation layer comprises the following specific calculation processes:
according to the user data of the target media terminal in each monitoring period, counting the newly added user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio of the target media terminal in each monitoring period;
constructing a change curve of the newly added user ratio, the member registration user ratio, the active user ratio and the cancellation user ratio;
positioning the position of each extreme point from the newly added user ratio change curve, and dividing the newly added user ratio change curve into curve segments;
counting the number of falling curve segments
And analyzing to obtain the average slope of the falling curve segment +.>
Average interval monitoringCycle length->
And comprehensive coverage monitoring period length +.>
；
Calculating the change coincidence degree of newly added users
，/>
；
wherein ,
respectively corresponding to the set slope, the interval monitoring period length and the coverage monitoring period length and the estimated duty ratio weight factor, < ->
Evaluating correction factors for setting new user changes, < ->
Respectively setting the descending slope, descending interval monitoring period length and descending coverage monitoring period ratio of the reference, +.>
The number of the monitoring periods and the number of the newly added user ratio change curve segments are respectively;
the change coincidence degree of the member registration user is calculated in a same way according to the calculation mode of the change coincidence degree of the newly added user
Active user variation compliance->
Analyzing the log-off according to the log-off user change ratio curveUser variation compliance +.>
；
Calculating loss evaluation index of target media terminal corresponding to user variation layer
，
；
wherein ,
the weight factor of the duty ratio is evaluated for the loss of the user change level corresponding to the change coincidence degree of the newly added user, the member registration user, the active user and the cancellation user respectively>
And evaluating correction factors for the set user variation level loss.
5. A media terminal data analysis management system according to claim 3, wherein: the specific setting process of the media data correspondingly referenced by the target media terminal is as follows:
recording each media terminal with the same attribute as the target media terminal as each associated media terminal;
calculating the comprehensive loss evaluation index of each associated media terminal, and screening each reference media terminal;
basic data of each reference media terminal is extracted, and the reference association degree of each reference media terminal is calculated
And taking the media data of the reference media terminal with the highest association degree as the media data of the corresponding reference of the target media terminal.
6. The media terminal data analysis management system according to claim 5, wherein: the specific calculation process of the reference association degree of each reference media terminal comprises the following steps:
positioning the comprehensive user quantity from the basic data of each reference media terminal
User age section->
And coverage area number->
，/>
Indicating reference to media terminal number->
；/>
Positioning the comprehensive user quantity from the basic data of the target media terminal
User age section->
And coverage area number->
；
Calculating the reference association degree of each reference media terminal
，
；
wherein ,
respectively the set user quantity and the userAge interval, coverage area number corresponding to association evaluation duty weight, +.>
The user difference, the user age difference, and the coverage area number difference of the set reference are respectively.
7. The media terminal data analysis management system according to claim 2, wherein: the target media terminal main body user loss element comprises the following specific confirmation process:
extracting referenced copyright data and resource data from media data correspondingly referenced by a target media terminal, and calculating a resource volume element difference index corresponding to the target media terminal
；
Extracting referenced advertisement data and playing data from media data correspondingly referenced by a target media terminal, and calculating a viewing experience element difference index corresponding to the target media terminal
；
Extracting the basic data of the reference from the media data corresponding to the reference of the target media terminal, and further extracting the creation date
And comprehensive user quantity->
Calculating market viscosity element difference index corresponding to target media terminal>
；
Respectively differencing the resource volume element difference index, the viewing experience element difference index and the market viscosity element difference index corresponding to the target media terminal with the set permission difference index, and sequentially marking the differences as
、/>
and />
；
If it is
Taking other elements as loss elements of the main body user of the target media terminal;
if it is
、/>
and />
If the difference index difference value of a certain element is larger than 0, the element is marked as a candidate element;
and counting the number of the elements to be selected, and taking the element to be selected with the largest difference index difference as a loss element of the main body user of the target media terminal.
8. The media terminal data analysis management system according to claim 7, wherein: the specific calculation process of the target media terminal resource volume element difference index comprises the following steps:
extracting the number of exclusive copyrights from the copyrights data correspondingly referenced by the target media terminal
And the number of general copyrights->
Setting a resource volume evaluation compensation factor +.>
；
Analyzing the resource data correspondingly referenced by the target media terminal to obtain the richness of the referenced film
And viewing dominance with reference to film>
And analyzing the same to obtain the corresponding film richness of the target media terminal>
And movie viewing dominance->
；
Calculating the difference index of the target media terminal resource volume element
，
；
wherein ,
the occupancy weights are evaluated for the corresponding resource volumes of the resource richness and the film playing dominance respectively,
the differences are the differences in film richness and film viewing preference of the set permissions.
9. The media terminal data analysis management system according to claim 7, wherein: the specific calculation process of the target media terminal watching experience element difference index is as follows:
advertisement number corresponding to reference from target media terminalExtracting member advertisement time length from the data
And non-member advertisement duration->
；
Extracting picture definition from play data correspondingly referenced by target media terminal
Average load duration->
And resolution error Rate->
；
Calculating a target media terminal watching experience element difference index
，/>
；
Wherein e is a natural constant,
the corresponding watching experience difference of the advertisement layer and the playing layer are respectively evaluated to be the duty ratio weight and the +.>
Evaluating correction factors for viewing experience->
The advertisement layer and the playing layer correspond to the difference indexes of the watching experience elements respectively;
wherein ,
the weight of the ratio is evaluated for the set member advertisement time length and the advertisement layer corresponding to the non-member advertisement time length respectively, and the weight is +.>
The corresponding play layer evaluation of the set picture definition, loading time and analysis error rate is respectively used for evaluating the duty ratio weight, < >>
Respectively setting reference member advertisement time length difference, non-member advertisement time length difference, playing loading time length difference and analysis error rate difference,>
、/>
、/>
、/>
、/>
the method comprises the steps of respectively obtaining the member advertisement time length, the non-member advertisement time length, the picture definition, the average loading time length and the analysis error rate corresponding to the target media terminal.
10. The media terminal data analysis management system according to claim 7, wherein: the specific calculation formula of the target media terminal market viscosity element difference index is as follows:
wherein ,
respectively setting up date and comprehensive user quantity corresponding to target media terminal>
Separately evaluating the duty weight, the ++for the set creation year, the user quantity and the market viscosity factor difference>
Respectively set reference difference annual limit value, reference user quantity ratio, +.>
Representing the rounding-up symbol +_>
The correction factor is evaluated for the set market viscosity difference. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200747.0A CN116051154B (en) | 2023-03-06 | 2023-03-06 | Media terminal data analysis management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200747.0A CN116051154B (en) | 2023-03-06 | 2023-03-06 | Media terminal data analysis management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116051154A true CN116051154A (en) | 2023-05-02 |
| CN116051154B CN116051154B (en) | 2023-06-13 |
Family
ID=86129691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310200747.0A Active CN116051154B (en) | 2023-03-06 | 2023-03-06 | Media terminal data analysis management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051154B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250999A (en) * | 2015-06-03 | 2016-12-21 | 阿里巴巴集团控股有限公司 | The methods, devices and systems of prediction turnover rate |
| CN110222975A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium |
| CN111601168A (en) * | 2020-05-21 | 2020-08-28 | 广州欢网科技有限责任公司 | Television program market performance analysis method and system |
| CN112837099A (en) * | 2021-02-05 | 2021-05-25 | 深圳市欢太科技有限公司 | Potential loss user identification method and device, storage medium and electronic equipment |
| CN115496545A (en) * | 2022-11-17 | 2022-12-20 | 北京名洋数字科技股份有限公司 | Online exhibition data analysis method, system and storage medium |
| CN115511525A (en) * | 2022-09-27 | 2022-12-23 | 欧冶云商股份有限公司 | Member loss early warning method and system for B2B platform user |
-
2023
- 2023-03-06 CN CN202310200747.0A patent/CN116051154B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250999A (en) * | 2015-06-03 | 2016-12-21 | 阿里巴巴集团控股有限公司 | The methods, devices and systems of prediction turnover rate |
| CN110222975A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium |
| CN111601168A (en) * | 2020-05-21 | 2020-08-28 | 广州欢网科技有限责任公司 | Television program market performance analysis method and system |
| CN112837099A (en) * | 2021-02-05 | 2021-05-25 | 深圳市欢太科技有限公司 | Potential loss user identification method and device, storage medium and electronic equipment |
| CN115511525A (en) * | 2022-09-27 | 2022-12-23 | 欧冶云商股份有限公司 | Member loss early warning method and system for B2B platform user |
| CN115496545A (en) * | 2022-11-17 | 2022-12-20 | 北京名洋数字科技股份有限公司 | Online exhibition data analysis method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116051154B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11405690B2 (en) | Methods and apparatus to calibrate audience measurement ratings based on return path data | |
| CN107657500B (en) | Stock recommendation method and server | |
| US20130132423A1 (en) | Method and system for detecting an applicance based on users' feedback information | |
| CN104954822A (en) | Methods and apparatus for estimating local market audiences of media content | |
| CN101673286A (en) | Apparatus, method and computer program for content recommendation and recording medium | |
| JP2013036887A (en) | Observed value reliability assessing apparatus, observed value reliability assessing method, and observed value reliability assessing program | |
| US20090150198A1 (en) | Estimating tv ad impressions | |
| US20230171011A1 (en) | Estimating volume of switching among television programs for an audience measurement panel | |
| CN112966778B (en) | Data processing method and device for unbalanced sample data | |
| CN116051154B (en) | Media terminal data analysis management system | |
| JP7015927B2 (en) | Learning model application system, learning model application method, and program | |
| CN110070304B (en) | Big data asset quality assessment method | |
| EP3783543A1 (en) | Learning system, learning method, and program | |
| CN112788351A (en) | Target live broadcast room identification method, device, equipment and storage medium | |
| CN116485071A (en) | Power consumer demand response potential evaluation method based on probability baseline load | |
| JP5172826B2 (en) | Method and apparatus for performing real-time audience estimation and commercial selection suitable for targeted advertising | |
| CN116956171A (en) | Classification method, device, equipment and storage medium based on AI model | |
| CN113127696B (en) | Method for improving accuracy of influence measurement based on behaviors | |
| CN114445342A (en) | Haze degree evaluation method and device, electronic equipment and storage medium | |
| CN110209938B (en) | Potential user recommendation method based on service multi-granularity attribute | |
| JP6856084B2 (en) | Information processing device, content control device, information processing method, and program | |
| CN112632404A (en) | Multi-granularity self-attention-based next interest point recommendation method | |
| US20030237094A1 (en) | Method to compare various initial cluster sets to determine the best initial set for clustering a set of TV shows | |
| CN117892009B (en) | Recommendation method and device for vehicle battery pack, computer equipment and storage medium | |
| CN115525556B (en) | Test method and system of AI decision system |
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 |