CN109165253A - A kind of method and apparatus of Basketball Tactical auxiliary - Google Patents
A kind of method and apparatus of Basketball Tactical auxiliary Download PDFInfo
- Publication number
- CN109165253A CN109165253A CN201810931480.1A CN201810931480A CN109165253A CN 109165253 A CN109165253 A CN 109165253A CN 201810931480 A CN201810931480 A CN 201810931480A CN 109165253 A CN109165253 A CN 109165253A
- Authority
- CN
- China
- Prior art keywords
- team
- sportsman
- data
- auxiliary
- analysis
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to sports tournament data mining technology fields, specifically include machine learning field, computer vision field and data visualization field, more particularly to a kind of method and apparatus of Basketball Tactical auxiliary, it can compete according to sportsman and practice process and assess and judge, it is convenient that pre-games planning and prediction are carried out to team, or the deployment of battle array and crucial moment is arranged in play, coach is facilitated to be managed, analyze and assess sportsman and team, and targetedly drill program is formulated, promote the success rate of match；The following steps are included: carrying out data mining to sportsman's information for the game, and carry out annual data analysis；It is analyzed and predicted according to team's competition data over the years and video；Maintenance data visualization technique indicates sportsman and team over the years and recent racing season data；The training program of sportsman and team's each period are counted and arranged.
Description
Technical field
The present invention relates to sports tournament data mining technology fields, specifically include machine learning field, computer vision neck
Domain and data visualization field, more particularly to a kind of method and apparatus of Basketball Tactical auxiliary.
Background technique
It is well known that stepping up with the athletics sports level of IT application, a large amount of event has accumulated magnanimity
Data and video need to watch a large amount of data and video, and a large amount of during training and tactics arrangement on the basketabll team
Screening meets the content of team's training in data and video, data content is converted to the actual combat content of team's training, therefore such as
Where team's analysis decision ability is improved on the basis of a large amount of data and video, improve the fast-changing decision reaction speed of team
Degree, magnanimity and video be converted to knowledge abundant, to assist coach and team to make reasonably decision, this problem at
For now by extensive concern the problem of.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of method and apparatus of Basketball Tactical auxiliary.It can be according to ball
Member's match and practice process are assessed and are judged, convenient to carry out pre-games planning and prediction to team, or arrange in play
The deployment of battle array and crucial moment facilitates coach to be managed, analyze and assess sportsman and team, and formulates and targetedly instruct
Practice plan, promotes the success rate of match.
A kind of method of Basketball Tactical auxiliary of the invention, comprising the following steps:
Data mining is carried out to sportsman's information for the game, and carries out annual data analysis；
It is analyzed and predicted according to team's competition data over the years and video；
Maintenance data visualization technique indicates sportsman and team over the years and recent racing season data, and is tied according to schedules
Fruit prediction；
And arrangement for statistical analysis to the training program of sportsman and team's each period.
A kind of method of Basketball Tactical auxiliary of the invention, it is described that data mining is carried out to sportsman's information for the game, and carry out
Annual data analysis, comprising the following steps:
It is caught every time according to sportsman data, battle array data, team's emolument and court location information, utilizes machine learning side
Method establishes analysis model, carries out project ranking assessment to sportsman's technology, and carry out visual analyzing to sportsman's motion profile.
A kind of method of Basketball Tactical auxiliary of the invention, it is described to be analyzed according to team's competition data over the years and video
And prediction, include the following steps；
Maintenance data excavates and machine learning method is analyzed and predicted, for the project sum number of reflection team's ability
According to, in conjunction with the information for the game at team scene, machine learning model is established, is analyzed and predicted to obtain score team hot-zone figure,
And the technical characterstic of the various formations of team, and battle array is predicted before can playing, and for life match information in match, is done
Decision out.
A kind of method of Basketball Tactical auxiliary of the invention, it is described to indicate sportsman and team over the years and recent racing season number
According to including the following steps；
For single sportsman or the game status and technical level of team, by its competition data with scatter plot, histogram, heat
Try hard to or rectilinear indicates, when carrying out ability comparison for multiple sportsmen or team, table is carried out with histogram, pie chart or radar map
Show.
A kind of method of Basketball Tactical auxiliary of the invention, the training program to sportsman and team's each period carry out
Statistics and arrangement, comprising the following steps:
Using machine learning model, in conjunction with such as attack state of sportsman's competitive state at this stage, defence state and physical fitness
To its association analysis, obtain influencing the related training program of sportsman's competitive state based on the analysis results.
A kind of device of Basketball Tactical auxiliary of the invention, described device include:
Sportsman's module for carrying out data mining to sportsman's information for the game, and carries out annual data analysis；
Team's module, for being analyzed and predicted according to team's competition data over the years and video；
Schedules module, the racing season data over the years and recent for maintenance data visualization technique expression sportsman and team, and
It is predicted according to schedules proceeding results；
Drill program module, for the training program to sportsman and team's each period it is for statistical analysis and arrange.
A kind of device of Basketball Tactical auxiliary of the invention, sportsman's module for data of being caught every time according to sportsman,
Battle array data, team's emolument and court location information, establish analysis model using machine learning method, carry out to sportsman's technology
Project ranking assessment, and visual analyzing is carried out to sportsman's motion profile.
A kind of device of Basketball Tactical auxiliary of the invention, team's module is excavated for maintenance data and machine learning
Method is analyzed and predicted, and establishes machine in conjunction with the information for the game at team scene for the project and data of reflection team's ability
Device learning model, is analyzed and predicted to obtain the technical characterstic of the various formations of score team hot-zone figure and team, and can be with
Battle array is predicted before playing, and for life match information in match, is made a policy.
A kind of device of Basketball Tactical auxiliary of the invention, the schedules module are used for the ratio for single sportsman or team
Match state and technical level are indicated its competition data with scatter plot, histogram, thermodynamic chart or rectilinear, for multiple sportsmen
Or it when team's progress ability comparison, is indicated with histogram, pie chart or radar map.
A kind of device of Basketball Tactical auxiliary of the invention, the drill program module are used to utilize machine learning model,
In conjunction with such as attack state of sportsman's competitive state at this stage, defence state and physical fitness to its association analysis, based on the analysis results
It obtains influencing the related training program of sportsman's competitive state.
Compared with prior art the invention has the benefit that using a kind of Basketball Tactical householder method provided by the invention
And device, it has the advantage that
1, scientific technical data can be obtained, is split according to information for the game, effective, accurate analysis knot is obtained
Fruit；
2, according to competition data and video data, sportsman's technical characterstic is analyzed, carries out sportsman's judge, supplemental training；
3, it according to team's schedules, is arranged forces in certain formation for different battle arrays, team assessment,
4, it is trained with the various combinations of team, auxiliary in Basketball Match progress crucial moment ball power point according to the characteristics of sportsman
Match, battle array arrangement, realize optimal effectiveness, improves team's entirety attack efficiency and winning probability.
Detailed description of the invention
Fig. 1 is Frame of Decision Support System structure chart；
Fig. 2 is analysis predicted portions frame diagram；
Fig. 3 is assisting workflows figure；
Fig. 4 is neural network prediction functional diagram；
Fig. 5 is clustering functional diagram；
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
The device of a kind of Basketball Tactical auxiliary of the invention, mainly by sportsman's module, team's module, schedules module, training
Four part of schedule module composition, wherein sportsman and team's module divide it using data mining technology and machine learning method
Analysis and prediction, are analyzed result and are presented with visualization technique.Schedules and drill program module are directed to games played over the years
According to sportsman's competitive state, carry out data comparison, prediction of result, auxiliary coach formulate special training.
Score that sportsman's module essential record is competed over the years such as backboard, grabs, defends at the basic datas, according to basis over the years
Data establish a kind of evaluation index of science, such as true hit rate, efficiency value, triumph contribution margin, utilize data mining and machine
Learning method analyzes sportsman's motion profile, hot-zone；Team's module carries out various changes using basic data in further detail
Team's high level data is got in return, as attack efficiency, defence efficiency, ball weigh utilization rate, efficiency value, effective field goalds, and benefit
With machine learning and data digging method, assessment and visual analyzing are carried out to team's technology, battle array feature, auxiliary coach carries out
Crucial moment carries out decision-making treatment；The recent schedules of schedules module real-time update and alliance's schedules, carry out more sportsmen, team's ability and
Battle array comparative analysis, and prediction of result analysis is carried out to corresponding schedules, auxiliary coach formulates strategy of game in advance；Drill program mould
Block includes attack training program and training program is defended to utilize machine learning according to the recent competition data of team and competitive state
Method, association analysis influence the training program of sportsman's competitive state, and optimal training program and frequency are formulated in auxiliary coach's analysis,
And its training program intensity is assessed.
In sportsman's module, by the technical data of sportsman, if score, backboard, rebound chance, speed and distance, receiving
It throws, the touching master datas such as ball and holding, pass, nut cap store to database, and are subject to area to these data with totality and field
Point.It clicks corresponding sportsman and carries out data call, and carry out statistics calculating using master data, such as sportsman score, the equal basket in field
The data such as plate, field are assisted, field is grabbed, field covers.And by items such as every game data such as score, backboard, fault, secondary attack
Purpose variation tendency is analyzed with Visual Chart and is shown.
In sportsman's module, according to sportsman's master data, such as shoots, assists, grabbing, backboard, penalty shot, receiving and pass several
According to establishing a kind of polytechnic evaluation index of reaction sportsman using mathematical analysis method, for example imitate at present using more attack
Rate, defence efficiency, ball power utilization rate, true hit rate, sportsman's contribution margin etc., click corresponding sportsman, respective formula are called to carry out
Calculation Estimation index value namely sportsman's high level data.And alliance's technical ability ranking, racing season are carried out to the high level data of corresponding sportsman
Ranking.High level data is such as indicated using pie chart in the form of data list, cake chart, sector diagram etc. visual analyzing is carried out
Every game sportsman's attack efficiency and defence efficiency shared by percentage.
In sportsman's module, using sportsman master data (shooting, backboard, penalty shot etc.) and high level data (defence efficiency, into
Attack efficiency etc.) data mining is carried out, with the Clustering Model in machine learning method, by screening different sportsmen and data items
As the input of the model, the technical characterstic of analysis output sportsman, auxiliary coach or general manager are to the evaluation of sportsman's wages, energy
Force estimation.
Machine learning clustering method in sportsman's module, selects several sportsmen to compare and analyze as needed, will be to be evaluated
The sportsman's data for estimating analysis are divided into the matrix of n*m, and n is the number for selecting sportsman, and m is the feature vector for representing sportsman, such as ball
The master data (score, backboard, penalty shot etc.) of member, the high-level data (attack efficiency, defence efficiency etc.) of sportsman, sportsman's emolument etc.
Data.Sample data is randomly divided into k cluster centre, Euclidean distance of the distance d between sample between any two sample, according to
Sample data is divided to each cluster centre by nearby principle, belongs to matrix w=n*k using a class, is somebody's turn to do when cluster centre meets
When class belongs to matrix error sum of squares minimum standard, do not continuing to classify.If not being inconsistent standardization reclassifies cluster centre k,
Until reaching the condition of satisfaction.The classification of each sportsman is exported using scatter plot, coach can check tool according to Clustering Effect
The technology strengths and weaknesses of body sportsman, suitable wages range etc..
In sportsman's module, using match video and sportsman's data, with neural network model.The neural network model is by ball
Field is divided into zone of dispersion, can identify the object of all movements in match video, distinguishes two teams' ball according to the color of football shirt
The basketball of member, court-referee and movement are divided the trace information for moving sportsman by identifying the uniform number of each sportsman
Layer establishes motion model by the tagged sportsman's number of input tape and sportsman's essential information, as data on the level
Collect recognition training, exports between the thermal map of sportsman and motion profile feature.
In team's module, according to first formation over the years of team and substitute battle array distinguish, by indicate team score,
The basic datas such as backboard, secondary attack, penalty shot, touching ball, pass, fault are stored to database, are clicked corresponding team, are called respective counts
According to.Calculating analysis in detail is carried out using data mining knowledge and to its master data simultaneously, such as the equal speed in field, field distance, field
Touch ball and field break through, three-point shot rate, free throw percentage etc..Can by screen different data project, as attack, defence,
Backboard etc. distinguishes the master data and detailed data of output team according to the equal form of totality and field, and by it according to from high to low
Sequence successively ranking.
In team's module, different teams are clicked, corresponding data is called, generates the master data list of corresponding team members,
Such as field goalds, three-point shot rate, free throw percentage, racing season ranking data, integrally carry out for sportsman's individual and team
Ranking indicates.When clicking corresponding sportsman's individual simultaneously, corresponding sportsman profile is called to analyze list, such as personal height, technology
The information such as feature, team position.Corresponding team is clicked, to data such as team's entirety hit rate, fault rate, backboard, attack efficiency
Data visualization analysis is carried out, such as attack efficiency of the team within certain a period of time is shown using line drawing analysis, uses column
Figure indicates difference of team's difference sportsman between a certain technological project.
In team's module, when different battle arrays or assessment sportsman will be selected to be suitble to those positions, using in machine learning
Each sportsman is carried out more classification by random forest tree method, including (offensive rebounds defend backboard, is total for the equal score in field, backboard
Backboard), secondary attack, nut cap, fault, the data such as triumph contribution (defence contribution, attack contribution).In random forest method training process
In, the determination decision tree number to be integrated is T, is followed successively by every one tree and randomly selects a sample set, generally complete or collected works
2/3.According to m feature is randomly selected on each node of tree as character subset, one is finally selected on each node
Optimal feature carries out best features branch.By selecting m feature of each node, calculates and export what the sportsman may be suitble to
Position, such as power forward, small forward, shooting guard, point guard and centre forward position, auxiliary coach carry out that sportsman is arranged to carry out one
The attack and defense in a little regions.
In team's module, for team's battle array, battle array prediction is carried out with neural network model, which divides court
At multiple zone of dispersion, and court different zones are assigned with certain position coordinates.Because the position of basketball determines the battle array of team
Type position, so one group of neural network of building, by the position of basketball under the match mode of court different zones and history other side's ball
The position of member carries out model training, the battle array position that output team is likely to occur as data set.According to selection input team at
Member, prediction export the battle array that these sportsmen are likely to occur, i.e., the battle array position in team facilitates coach to make corresponding tactics tune
It is whole.
Processing in team's module, when match, which falls into the deadlocked or time, to remain little, for some key balls
It is machine key of winning the game.By the battle array information of live team and player information as input, with neural network model,
Prediction output crucial moment passing position and ball power distribution Dynamic Graph, auxiliary coach's Analysis of Policy Making.
The neural network model used in team's module is classified first first with the master data of quarters player
Training, analysis obtain the fundamental type of sportsman, then use match video over the years, will compete video division according to time series approach
For multiple periods, facilitate the input for distinguishing crucial moment match video as neural network.The neural network model automatic identification
Mobile sportsman will distinguish the sportsman of different formations using the number in uniform number, by being trained autonomous learning
Sportsman, assessment calculate the movement position of output basketball, i.e. Athletess track.Help train crucial moment decision and deployment into
The best route attacked or defended and defence member, and according to every kind of strategy output deployment strategy Dynamic Graph and its successful probability.
If how defender should respond, attacker how combinational techniques opponent, passer how to select pass ball position, connect
How team person selects route to avoid blocking.
In schedules module, including recent our team's schedules and the following schedules, history schedules and alliance's schedules, click corresponding schedules
List carries out corresponding data and calls inquiry, such as to handball team, fixture, result of the match.Different teams can also be screened, are carried out
Team's detailed data comparison, such as both sides team racing season data, sportsman's competition data.Using data visualization technique by both sides team
The data such as the equal score in the field of racing season, field assist, the equal backboard in field, field is lost points, field is made mistakes carry out graphic analyses, such as according to double
Square team's score, backboard, secondary attack, penalty shot, the data items such as three points generate the comparison histogram of the ability in certain time.
In schedules module, in the following schedules list, using the logistic regression method in machine learning, count every in conventional competition
Branch team triumph number of fields and failure number of fields and every team master data and integrated data, as ranking, score, defence, into
Attack, penalty shot, three-point shot rate, fault rate, average age etc. as the feature vector of reflection team are trained calculating, according to
The following schedules list output prediction may triumphantly be promoted to team, and corresponding drill program is formulated in auxiliary coach defence planning in advance.
In schedules module, Logic Regression Models in machine learning method utilize team over the years, sportsman, schedules basic number
According to as feature vector, be converted into 4 overall targets: team's comprehensive strength, the strength of team lead man, chief coach are held
Row ability, team's home-away strengths and weaknesses.According to 4 overall targets as independent variable, output ratio is predicted with logistic regression method
The team's list for matching triumph, when dependent variable Y value 1, then it represents that team is promoted, and value -1 indicates that team is eliminated.
In drill program list, team and sportsman's training program are counted.For newest schedules plan arrangement, sportsman is tracked
Nearly trimestral every training target, such as score, assist, grab, backboard, penalty shot data, and to sportsman's items training target
The plan of progress arrangement, such as attack project (mobile, biography receives, dribbles, shooting), defence project (rob and interrupt, cover, robbing by movement
Backboard and body-defence etc.).
In drill program list, according to the difference of sportsman's individual, as body of sportsmen situation, injured situation, speciality, technology are excellent
The indexs such as disadvantage, using relation analysis model in machine learning, analysis obtains influencing the key factor of sportsman or team's achievement.Religion
Practice the influence factor obtained according to analysis, adjust the project of team or sportsman's training, such as paces pass and receive, lay up, dribbling, and throw
Projects such as basket, and carry out strength assessment to some projects, click and select corresponding sportsman, simultaneous display training program, period and strong
Degree.
The relation analysis model in machine learning in drill program, selection represent the project of sportsman's drill program as research
Object.The tables of data D of Basketball Match affairs is created, wherein D={ A, B, C, D, E, F, G... }, respectively represents height, weight, helps
It attacks, three-point shot, the data such as penalty shot, breaks through, grabs, using parameter support, confidence level, whether training of judgement item association rule
For strong rule.Assuming that minimum support be 40% and its more than, min confidence 50%, scanning sportsman compete all numbers of affairs
According to table, candidate 1 item collection and frequent 1 item collection are generated, determines the support of each.It is started the cycle over from 2 item collections, by frequent K-1 item collection
Frequent K item collection is generated, whether its subset, which is that frequency collects, is detected to each item collection in K item collection, deletes subset not in the item collection of frequency collection.It sweeps
Database table is retouched, the support of filtered K item collection is recalculated, discards the item collection that support is less than minimum support, it is raw
At frequent K item collection, if circulation terminates when only one item collection in current K item collection.Finally verify whether its frequent item set meets not
Less than min confidence.
Training program is directed in training program list, such as: paces, biography receive, lay up, dribbling, and shooting etc. can using data
Depending on change technology, team and sportsman's entirety training program are analyzed, the throwing of sportsman in certain time is such as indicated using line chart
The Long-term change trend of basket hit rate, according to the variation before histogram graph representation sportsman training with basketball technique project after training.Auxiliary religion
Practice progress, frequency, the intensity for observing every kind of project of training, so as to timely adjusting training status data.
This example is predicted and is analyzed data by using artificial intelligence model, and assessment, prediction and decision are trained in help,
The validity of whole system operation is improved, and the accuracy of these model predictions can be improved by the competition data of continuous renewal；
The present invention can under different scenes data and video effectively detected, the multiple teams of trace analysis and sportsman, by can
Depending on changing sportsman of the technology-mapped in court Anywhere, and it is tracked in the sportsman track of different zones, detailed hot-zone figure.Benefit
It analyzed with these data, assess the performance of sportsman, team in play, auxiliary coach formulates corresponding plan in play
Slightly.According to team's state, special training plan is formulated, improves training effect.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvements and modifications, these improvements and modifications can also be made
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of method of Basketball Tactical auxiliary, which comprises the following steps:
Data mining is carried out to sportsman's information for the game, and carries out annual data analysis；
It is analyzed and predicted according to team's competition data over the years and video；
Maintenance data visualization technique indicates sportsman and team over the years and recent racing season data, and it is pre- according to schedules to carry out result
It surveys；
And arrangement for statistical analysis to the training program of sportsman and team's each period.
2. a kind of method of Basketball Tactical auxiliary as described in claim 1, which is characterized in that it is described to sportsman's information for the game into
Row data mining, and carry out annual data analysis, comprising the following steps:
It is caught according to sportsman data, battle array data, team's emolument and court location information, is built using machine learning method every time
Vertical analysis model carries out project ranking assessment to sportsman's technology, and carries out visual analyzing to sportsman's motion profile.
3. a kind of method of Basketball Tactical auxiliary as described in claim 1, which is characterized in that described to be competed over the years according to team
Data and video are analyzed and predicted, and are included the following steps；
Maintenance data excavates and machine learning method is analyzed and predicted, for the project and data of reflection team's ability, knot
The information for the game for closing team scene, establishes machine learning model, is analyzed and predicted to obtain score team hot-zone figure, Yi Jiqiu
The technical characterstic of the various formations of team, and battle array is predicted before can playing, and for life match information in match, is made certainly
Plan.
4. a kind of method of Basketball Tactical auxiliary as described in claim 1, which is characterized in that the expression sportsman and team are gone through
Year and recent racing season data, include the following steps；
For single sportsman or the game status and technical level of team, by its competition data with scatter plot, histogram, hot-zone figure
Or rectilinear indicates, when carrying out ability comparison for multiple sportsmen or team, is indicated with histogram, pie chart or radar map.
5. a kind of method of Basketball Tactical auxiliary as described in claim 1, which is characterized in that described each to sportsman and team
The training program of period is counted and is arranged, comprising the following steps:
Using machine learning model, in conjunction with such as attack state of sportsman's competitive state at this stage, defence state and physical fitness to it
Association analysis obtains influencing the related training program of sportsman's competitive state based on the analysis results.
6. a kind of device of Basketball Tactical auxiliary, which is characterized in that described device includes:
Sportsman's module for carrying out data mining to sportsman's information for the game, and carries out annual data analysis；
Team's module, for being analyzed and predicted according to team's competition data over the years and video；
Schedules module, the racing season data over the years and recent for maintenance data visualization technique expression sportsman and team, and according to
Recent schedules carry out prediction of result；
Drill program module, for the training program to sportsman and team's each period it is for statistical analysis and arrange.
7. a kind of device of Basketball Tactical auxiliary as claimed in claim 6, which is characterized in that sportsman's module is used for basis
Sportsman catches data, battle array data, team's emolument and court location information every time, and machine learning method is utilized to establish analysis mould
Type carries out project ranking assessment to sportsman's technology, and carries out visual analyzing to sportsman's motion profile.
8. a kind of device of Basketball Tactical auxiliary as claimed in claim 6, which is characterized in that team's module is for using
Data mining and machine learning method are analyzed and predicted, existing in conjunction with team for the project and data of reflection team's ability
The information for the game of field, establishes machine learning model, is analyzed and predicted to obtain the various battle arrays of score team hot-zone figure and team
The technical characterstic of type, and battle array is predicted before can playing, and for life match information in match, is made a policy.
9. a kind of device of Basketball Tactical auxiliary as claimed in claim 6, which is characterized in that the schedules module is for being directed to
The game status and technical level of single sportsman or team, by its competition data with scatter plot, histogram, hot-zone figure or rectilinear
It indicates, when carrying out ability comparison for multiple sportsmen or team, is indicated with histogram, pie chart or radar map.
10. a kind of device of Basketball Tactical auxiliary as claimed in claim 6, which is characterized in that the drill program module is used
In utilizing machine learning model, it is closed in conjunction with sportsman's competitive state at this stage such as attack state, defence state and physical fitness
Connection analysis obtains influencing the related training program of sportsman's competitive state based on the analysis results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810931480.1A CN109165253A (en) | 2018-08-15 | 2018-08-15 | A kind of method and apparatus of Basketball Tactical auxiliary |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810931480.1A CN109165253A (en) | 2018-08-15 | 2018-08-15 | A kind of method and apparatus of Basketball Tactical auxiliary |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109165253A true CN109165253A (en) | 2019-01-08 |
Family
ID=64895828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810931480.1A Pending CN109165253A (en) | 2018-08-15 | 2018-08-15 | A kind of method and apparatus of Basketball Tactical auxiliary |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165253A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109758758A (en) * | 2019-03-12 | 2019-05-17 | 福建工程学院 | A kind of tactics based on sportsman's feature draft method |
| CN109948896A (en) * | 2019-01-31 | 2019-06-28 | 软通智慧科技有限公司 | Match formation determining method, device, server and storage medium |
| CN110222723A (en) * | 2019-05-14 | 2019-09-10 | 华南理工大学 | A kind of starting prediction technique of football match based on mixed model |
| CN110727826A (en) * | 2019-09-30 | 2020-01-24 | 浙江大学 | Visual analysis method for tactical excavation of table tennis |
| CN110796085A (en) * | 2019-10-29 | 2020-02-14 | 新华智云科技有限公司 | Method for automatically distinguishing basketball goal segment AB team based on deep learning object detection algorithm |
| CN110931106A (en) * | 2019-12-23 | 2020-03-27 | 国家体育总局体育科学研究所 | Motion monitoring and evaluating system |
| CN110960843A (en) * | 2019-12-23 | 2020-04-07 | 天水师范学院 | Basketball skill auxiliary training system |
| CN111724414A (en) * | 2020-06-23 | 2020-09-29 | 宁夏大学 | Basketball movement analysis method based on 3D attitude estimation |
| CN111797812A (en) * | 2020-07-20 | 2020-10-20 | 深圳市云数链科技有限公司 | Method, system, terminal and medium for automatically recording effective goal in football match |
| CN112138407A (en) * | 2020-08-31 | 2020-12-29 | 杭州威佩网络科技有限公司 | Information display method and device |
| CN112513995A (en) * | 2018-06-01 | 2021-03-16 | 弗劳恩霍夫应用研究促进协会 | System for determining game scenes in a sports game |
| CN112528785A (en) * | 2020-11-30 | 2021-03-19 | 联想(北京)有限公司 | Information processing method and device |
| CN112766546A (en) * | 2021-01-05 | 2021-05-07 | 上海大学 | Machine learning-based football match win and loss real-time prediction method |
| CN113111225A (en) * | 2021-03-28 | 2021-07-13 | 根尖体育科技（北京）有限公司 | Automatic matching team forming method for basketball game |
| CN113811898A (en) * | 2019-05-08 | 2021-12-17 | 斯塔特斯公司 | System and method for content and style prediction in sports |
| CN113939837A (en) * | 2020-05-08 | 2022-01-14 | 株式会社电通 | Win-loss prediction system |
| CN114580529A (en) * | 2022-03-03 | 2022-06-03 | 电子科技大学 | System for selecting and training football players |
| TWI779301B (en) * | 2020-06-16 | 2022-10-01 | 國立清華大學 | Method and apparatus for baseball strategy planning based on reinforcement learning |
| CN115630774A (en) * | 2022-09-06 | 2023-01-20 | 东北师范大学 | Football match data analysis system and method |
| CN115757551A (en) * | 2022-11-30 | 2023-03-07 | 肇庆市智云体育信息科技有限公司 | Method for mining and predicting key information of events |
| CN118365105A (en) * | 2024-06-20 | 2024-07-19 | 广州华夏汇海科技有限公司 | Intelligent team formation method based on volleyball training |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833232A (en) * | 2010-04-20 | 2010-09-15 | 浙江大学 | Visual support and match analysis system for ping-pong match and method for running same |
| CN102213957A (en) * | 2010-04-08 | 2011-10-12 | 上海薄荷信息科技有限公司 | Control method, and device and system for providing virtual private sport coach |
| CN104899413A (en) * | 2015-04-14 | 2015-09-09 | 湘潭大学 | Team competition result prediction method based on maximum entropy model |
| CN106663224A (en) * | 2014-06-30 | 2017-05-10 | 亚马逊科技公司 | Interactive interfaces for machine learning model evaluations |
| CN108066971A (en) * | 2017-12-08 | 2018-05-25 | 浙江大学 | The method for visualizing of single racing season basketball team competitive state |
-
2018
- 2018-08-15 CN CN201810931480.1A patent/CN109165253A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102213957A (en) * | 2010-04-08 | 2011-10-12 | 上海薄荷信息科技有限公司 | Control method, and device and system for providing virtual private sport coach |
| CN101833232A (en) * | 2010-04-20 | 2010-09-15 | 浙江大学 | Visual support and match analysis system for ping-pong match and method for running same |
| CN106663224A (en) * | 2014-06-30 | 2017-05-10 | 亚马逊科技公司 | Interactive interfaces for machine learning model evaluations |
| CN104899413A (en) * | 2015-04-14 | 2015-09-09 | 湘潭大学 | Team competition result prediction method based on maximum entropy model |
| CN108066971A (en) * | 2017-12-08 | 2018-05-25 | 浙江大学 | The method for visualizing of single racing season basketball team competitive state |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112513995A (en) * | 2018-06-01 | 2021-03-16 | 弗劳恩霍夫应用研究促进协会 | System for determining game scenes in a sports game |
| CN109948896A (en) * | 2019-01-31 | 2019-06-28 | 软通智慧科技有限公司 | Match formation determining method, device, server and storage medium |
| CN109758758A (en) * | 2019-03-12 | 2019-05-17 | 福建工程学院 | A kind of tactics based on sportsman's feature draft method |
| CN113811898A (en) * | 2019-05-08 | 2021-12-17 | 斯塔特斯公司 | System and method for content and style prediction in sports |
| CN110222723A (en) * | 2019-05-14 | 2019-09-10 | 华南理工大学 | A kind of starting prediction technique of football match based on mixed model |
| CN110222723B (en) * | 2019-05-14 | 2021-07-20 | 华南理工大学 | Hybrid model-based football match first-launch prediction method |
| CN110727826A (en) * | 2019-09-30 | 2020-01-24 | 浙江大学 | Visual analysis method for tactical excavation of table tennis |
| CN110727826B (en) * | 2019-09-30 | 2022-03-25 | 浙江大学 | Visual analysis method for tactical excavation of table tennis |
| CN110796085B (en) * | 2019-10-29 | 2022-04-22 | 新华智云科技有限公司 | Method for automatically distinguishing basketball goal segment AB team based on deep learning object detection algorithm |
| CN110796085A (en) * | 2019-10-29 | 2020-02-14 | 新华智云科技有限公司 | Method for automatically distinguishing basketball goal segment AB team based on deep learning object detection algorithm |
| CN110960843A (en) * | 2019-12-23 | 2020-04-07 | 天水师范学院 | Basketball skill auxiliary training system |
| CN110931106A (en) * | 2019-12-23 | 2020-03-27 | 国家体育总局体育科学研究所 | Motion monitoring and evaluating system |
| CN113939837B (en) * | 2020-05-08 | 2024-07-26 | 株式会社电通 | Victory-defeat prediction system |
| CN113939837A (en) * | 2020-05-08 | 2022-01-14 | 株式会社电通 | Win-loss prediction system |
| TWI779301B (en) * | 2020-06-16 | 2022-10-01 | 國立清華大學 | Method and apparatus for baseball strategy planning based on reinforcement learning |
| CN111724414A (en) * | 2020-06-23 | 2020-09-29 | 宁夏大学 | Basketball movement analysis method based on 3D attitude estimation |
| CN111724414B (en) * | 2020-06-23 | 2024-01-26 | 宁夏大学 | Basketball motion analysis method based on 3D gesture estimation |
| CN111797812A (en) * | 2020-07-20 | 2020-10-20 | 深圳市云数链科技有限公司 | Method, system, terminal and medium for automatically recording effective goal in football match |
| CN112138407A (en) * | 2020-08-31 | 2020-12-29 | 杭州威佩网络科技有限公司 | Information display method and device |
| CN112528785A (en) * | 2020-11-30 | 2021-03-19 | 联想(北京)有限公司 | Information processing method and device |
| CN112766546B (en) * | 2021-01-05 | 2022-04-26 | 上海大学 | Machine learning-based football match win and loss real-time prediction method |
| CN112766546A (en) * | 2021-01-05 | 2021-05-07 | 上海大学 | Machine learning-based football match win and loss real-time prediction method |
| CN113111225A (en) * | 2021-03-28 | 2021-07-13 | 根尖体育科技（北京）有限公司 | Automatic matching team forming method for basketball game |
| CN114580529A (en) * | 2022-03-03 | 2022-06-03 | 电子科技大学 | System for selecting and training football players |
| CN114580529B (en) * | 2022-03-03 | 2023-04-21 | 电子科技大学 | System for selecting and training football player |
| CN115630774A (en) * | 2022-09-06 | 2023-01-20 | 东北师范大学 | Football match data analysis system and method |
| CN115757551A (en) * | 2022-11-30 | 2023-03-07 | 肇庆市智云体育信息科技有限公司 | Method for mining and predicting key information of events |
| CN115757551B (en) * | 2022-11-30 | 2023-08-25 | 肇庆市智云体育信息科技有限公司 | Event key information mining and predicting method |
| CN118365105A (en) * | 2024-06-20 | 2024-07-19 | 广州华夏汇海科技有限公司 | Intelligent team formation method based on volleyball training |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165253A (en) | A kind of method and apparatus of Basketball Tactical auxiliary | |
| Lord et al. | Methods of performance analysis in team invasion sports: A systematic review | |
| Cintia et al. | The harsh rule of the goals: Data-driven performance indicators for football teams | |
| Cintia et al. | A network-based approach to evaluate the performance of football teams | |
| US11568713B2 (en) | Systems and methods for making use of telemetry tracking devices to enable event based analysis at a live game | |
| Miarka et al. | Time-motion analysis and decision making in female judo athletes during victory or defeat at olympic and non-olympic events: Are combat actions really unpredictable? | |
| CN110322380B (en) | Visual analysis system for tactical simulation of table tennis match | |
| Schumaker et al. | Sports knowledge management and data mining. | |
| Miarka et al. | Evaluation of sex-specific movement patterns in judo using probabilistic neural networks | |
| US20230085122A1 (en) | Systems and methods for making use of telemetry tracking devices to enable event based analysis at a live game | |
| Pugsee et al. | Football match result prediction using the random forest classifier | |
| Bhatnagar et al. | A systematic review of sports analytics | |
| Zeng et al. | A Machine Learning Model to Predict Player's Positions based on Performance. | |
| Lord et al. | Identifying and analysing game styles and factors influencing a team’s strategy in field hockey | |
| Prakash et al. | A new category based deep performance index using machine learning for ranking IPL cricketers | |
| Das et al. | Prediction Model of Success and Failure in Football Competitions | |
| Ratgeber et al. | Comparative review of statistical parameters for Men's and Women's basketball leagues in Serbia | |
| Van Haaren et al. | Analyzing Performance and Playing Style Using Ball Event Data | |
| Bouzarth et al. | Storytelling with sports analytics | |
| Méndez et al. | Improving the Expected Goal Value in Football Using Multilayer Perceptron Networks | |
| Tilp | Modelling in the analysis of tactical behavior in team handball | |
| Hipp et al. | Mining ice hockey: Continuous data flow analysis | |
| Alsaif et al. | Computer vision systems and deep learning for the recognition of athlete's movement: A review article | |
| Anton | In-game strategy recommendations in association football: A study based on network theory | |
| Singh et al. | Data-Driven Player Recruitment in Football |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |
|
| RJ01 | Rejection of invention patent application after publication |