CN110163453B - Method, device and system for predicting replenishment resource allocation strategy and storage medium - Google Patents
Method, device and system for predicting replenishment resource allocation strategy and storage medium Download PDFInfo
- Publication number
- CN110163453B CN110163453B CN201910538612.9A CN201910538612A CN110163453B CN 110163453 B CN110163453 B CN 110163453B CN 201910538612 A CN201910538612 A CN 201910538612A CN 110163453 B CN110163453 B CN 110163453B
- Authority
- CN
- China
- Prior art keywords
- replenishment
- competition
- historical
- type
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method, a device, a system and a storage medium for predicting a supply resource allocation strategy, wherein the method comprises the following steps: acquiring all historical competition data of the athletes participating in the competition, weather data, track types, supply point information and at least one supply type during the competition; inputting all historical competition data, weather data during the current competition and track types as input parameters into a pre-established score prediction model, and predicting the athlete distribution rule of each supply point; inputting weather data, a track type, a first supplement type, supplement point information, a distribution rule of athletes and a competition result of each athlete into a first supplement prediction model, and predicting the per-capita supplement consumption amount corresponding to the first supplement type; and predicting a final replenishment resource allocation strategy according to the distribution rule of the athletes at each replenishment point and the per-capita replenishment consumption of each replenishment product type at each replenishment point.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a method, a device and a system for predicting a supply resource allocation strategy and a storage medium.
Background
With the increasing health consciousness of people, the international events such as marathon and the like are more popular. The increasing number of people involved in an event presents a significant challenge to the service of event staff. Different event replenishment points need to be set in the process of a game, and each event replenishment point needs to be provided with staff, corresponding equipment and supplies and set corresponding replenishment duration.
Due to different road sections and different numbers of the players in the competition, the same equipment, personnel and replenishment amount cannot be simply and evenly distributed in different competition sections in an average system, and the same replenishment duration is set. Although, in the prior art, there is also a method for setting replenishment configuration of a replenishment point, which is to estimate the flow rate passing condition of the point according to manual experience, determine the number of personnel and equipment according to the peak value of the flow, and determine the working time of the replenishment point according to the flow time.
But the resource allocation is unreasonable due to the large error based on the assumption of human experience. The shortage of many supply point personnel, supplies and the like is caused, and the surplus of resources exists in some places.
Therefore, how to ensure that the resources of different supply points can be predicted more accurately, all the supply resources are fully utilized, and resource waste is avoided, which becomes a technical problem to be solved urgently in the application.
Disclosure of Invention
Therefore, embodiments of the present invention provide a method, an apparatus, a system, and a storage medium for predicting a replenishment resource allocation policy, so as to solve the technical problem in the prior art that the prediction of the replenishment resource is not accurate enough, which causes unreasonable allocation of the replenishment point resource.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
according to a first aspect of the embodiments of the present invention, there is provided a replenishment resource allocation policy prediction method, including:
acquiring all historical competition data of the athletes participating in the competition, weather data, track types, supply point information and at least one supply type during the competition;
inputting all historical competition data of the athletes participating in the competition, weather data during the competition and track types into a pre-established performance prediction model as input parameters, and predicting the distribution rule of the athletes at each supply point of the competition;
inputting weather data, a track type, a first replenishment type, replenishment point information, a predicted athlete distribution rule of the competition and a predicted competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, predicting per replenishment point consumption of people corresponding to the first replenishment type, wherein the first replenishment type is any one of at least one replenishment type;
and predicting a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-capita replenishment consumption amount of each replenishment product type at each replenishment point.
Further, all historical competition data of the athletes participating in the competition at this time specifically include:
historical weather data, historical track types, historical replenishment point information, historical replenishment item types, consumption of each historical replenishment item, final historical scores of athletes, historical score data of each timing point and a competition completion rate which correspond to each competition in the historical competition.
Further, inputting all historical competition data of the athletes participating in the current competition, weather data during the current competition and track types into a pre-established performance prediction model to predict the athlete distribution rule of each supply point of the current competition, wherein the input parameters specifically comprise:
taking all historical competition data of the athletes participating in the competition, weather data during the competition and the track type as input parameters, and predicting the pedestrian flow distribution condition of the track by using a pre-established performance prediction model;
and (4) according to the pedestrian flow distribution condition of the track, statistically analyzing the distribution rule of the athletes at each supply point.
Further, the first replenishment prediction model includes a first replenishment surplus prediction model, a first replenishment consumption prediction model, and a first total replenishment consumption prediction model, and one total replenishment consumption prediction model, at least one surplus replenishment prediction model, and at least one total replenishment consumption prediction model correspond to each type of replenishment product.
Further, when the first replenishment surplus prediction model includes at least two, and the first replenishment consumption prediction model includes at least two, inputting the weather data, the track type, the first replenishment item type, the first replenishment point information, the predicted athlete distribution rule of the current competition and the game result of each athlete in the current competition into the first replenishment prediction model which is pre-constructed and corresponds to the first replenishment item type, and predicting the per-person replenishment consumption corresponding to the first replenishment item type in the first replenishment point, specifically including:
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each first supplement surplus prediction model during the competition to obtain at least two predicted supplement surplus;
calculating a first average of at least two predicted replenishment residuals;
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each supplement consumption amount prediction model during the competition to obtain at least two predicted supplement consumption amounts;
calculating a second average of the at least two predicted replenishment consumptions;
inputting weather data, track types, first supplement types, supplement point information, predicted athlete distribution rules of the competition and the competition results of each athlete into a first total supplement consumption prediction model, and predicting total supplement consumption of the first supplement points;
and predicting the actual replenishment consumption of the first replenishment point according to the first average value, the second average value and the total replenishment consumption of the first replenishment point, so as to determine the average human replenishment consumption corresponding to the first replenishment type according to the actual replenishment consumption, wherein the first replenishment point is any replenishment point in the game.
Further, the final replenishment resource allocation strategy at least comprises:
the number of staff members, the number of equipment, the per-person dispensing amount of each supply for each point of supply, the total dispensing amount of each supply for each point of supply, and the length of service.
According to a second aspect of the embodiments of the present invention, there is provided a replenishment resource allocation policy prediction apparatus including:
the acquisition unit is used for acquiring all historical competition data of the athletes participating in the competition, weather data during the competition, track types, supply point information and at least one supply type;
the prediction unit is used for inputting all historical competition data of the athletes participating in the competition, weather data during the competition and track types into a pre-established performance prediction model by taking the historical competition data, the weather data and the track types as input parameters, and predicting the athlete distribution rule of each supply point of the competition;
inputting weather data, a track type, a first replenishment type, replenishment point information, a predicted athlete distribution rule of the competition and a predicted competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, predicting per replenishment point consumption of people corresponding to the first replenishment type, wherein the first replenishment type is any one of at least one replenishment type;
and the processing unit is used for predicting a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-person replenishment consumption of each replenishment product type at each replenishment point.
Further, the final replenishment resource allocation strategy at least comprises:
the number of staff members, the number of equipment, the per-person dispensing amount of each supply for each point of supply, the total dispensing amount of each supply for each point of supply, and the length of service.
According to a third aspect of the embodiments of the present invention, there is provided a replenishment resource allocation policy prediction system including: a processor and a memory;
the memory is used for storing one or more program instructions;
a processor for executing one or more program instructions to perform any of the method steps of the above method for predicting a replenishment resource allocation strategy.
According to a fourth aspect of embodiments of the present invention, there is provided a computer storage medium having one or more program instructions embodied therein for use by a replenishment resource allocation strategy prediction system in performing any one of the method steps of the replenishment resource allocation strategy prediction method described above.
The embodiment of the invention has the following advantages: acquiring all historical competition data of the athletes participating in the competition; and then inputting historical competition data and parameters of the competition, such as weather data, track types and the like, into a performance prediction model constructed by utilizing the historical parameter data in advance to obtain the respective rules of the athletes at each supply point of the competition. In addition to the above parameters, the types of supplies, the information of the points of supply, the predicted distribution rules of the players during the current competition, and the competition results of each player are input into the first supply prediction models which are pre-constructed and respectively correspond to each type of supplies, and the consumption of all the supplies in each point of supply is predicted. By the method, the replenishment resource allocation strategies such as the number of workers, the number of equipment, the type of replenishment supplies, the number of replenishment supplies, the service duration of the workers and the like which are required to be equipped at different replenishment points in different time periods can be predicted more accurately. Therefore, the supply resources are reasonably utilized, and the requirements of all athletes participating in the competition can be met as far as possible while resource waste is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
Fig. 1 is a schematic flow chart of a replenishment resource allocation policy prediction method according to embodiment 1 of the present invention;
fig. 2 is a people flow distribution situation of a one-time game provided by the present invention at a timing point of 10 km;
fig. 3 is a people flow distribution situation of a one-time match provided by the present invention at a timing point of 15 km;
fig. 4 is a distribution of people flow at a timing point of 20 km in a single game according to the present invention;
FIG. 5 is a schematic diagram showing the comparison between the actual water supply and the predicted water supply at the timing point of 10 km, 15 km and 20 km for one game according to the present invention;
fig. 6 is a schematic structural diagram of a replenishment resource allocation policy prediction apparatus according to embodiment 2 of the present invention;
fig. 7 is a schematic structural diagram of a replenishment resource allocation policy prediction system according to embodiment 3 of the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Embodiment 1 of the present invention provides a method for predicting a replenishment resource allocation policy, specifically, as shown in fig. 1, the method includes the following steps:
and step 110, acquiring all historical competition data of the athletes participating in the competition, weather data during the competition, track types, supply point information and at least one supply type.
Specifically, the historical listing data may include, but is not limited to, the following parameters: historical weather data, historical track types, historical replenishment point information, historical replenishment item types, consumption of each historical replenishment item, final historical scores of athletes, historical score data of each timing point and a competition completion rate which correspond to each competition in the historical competition. The competition completion rate is mainly the ratio of the number of check-ins of the athletes after the competition is completed to the number of check-ins of the athletes before the competition. The historical replenishment point information mainly comprises the number of replenishment points, and the position of each replenishment point is, for example, a replenishment point is arranged every 5 kilometers, so that the position of the replenishment point is the roadside position which is 5 kilometers, 10 kilometers, 15 kilometers away from the starting point of the runway, and the like. The weather data may include weather data for temperature, humidity, wind speed, sunny, cloudy, or rainy days, etc. The track type may include, for example, several cases:
dividing according to the altitude:
a) and (3) descending: the altitude difference between the starting point and the ending point of the track exceeds 1 meter per kilometer, and the starting point is higher than the ending point.
b) Ascending: the altitude difference between the starting point and the ending point of the track exceeds 1 meter per kilometer, and the starting point is lower than the ending point.
c) Flat type: the altitude difference between the starting point and the ending point of the track is not more than 1 meter per kilometer, and the accumulated ascending height of all climbing sections or the accumulated descending height of all descending sections is not more than 80 meters per kilometer.
d) Undulation type: the difference of the elevation heights of the starting point and the ending point of the track does not exceed 1 meter per kilometer, and the accumulated ascending height of all climbing sections or the accumulated descending height of all descending sections exceeds 80 meters per kilometer.
Dividing according to the ground: but also includes types such as highways, mountains, and plastics.
According to player selection division: the method comprises the modes of random drawing and selecting, selecting according to historical scores or group registration and the like.
And step 120, inputting all historical competition data of the athletes participating in the competition, weather data during the competition and track types into a pre-established performance prediction model by taking the historical competition data, the weather data and the track types as input parameters, and predicting the distribution rule of the athletes at each supply point of the competition.
Specifically, the historical competition data may further include competition time, the number of the competition participants, historical competition participant identification information (e.g., information such as numbers, names, identification numbers, etc.), and competition-related data such as the ages of the participants who participated in the competition.
As shown in step 110, the track types may include a plurality of types, and then the principle of the pre-established performance prediction model for predicting the pedestrian flow distribution of the athlete on the track is as follows:
firstly, the average performance of all the historical contestants on each type of track needs to be counted according to the historical contestant data. Then, a first type of conversion factor is calculated based on the average performance of the historical contestants between the different types of tracks. And calculating a second type conversion coefficient according to the age of each historical contestant in the historical contest data and the historical achievement in the contest.
Because the setting modes of the game timing points are different in historical games, even if the same person participates in two games at the same age, the positions of the recording points of the game scores are not completely consistent. Therefore, it is necessary to adjust the timing point in the historical games other than the first-type game in the historical games by using the setting manner of the timing point of the first game in the historical games played by the first-type historical contestants as a reference, where the preset manner includes one or more of the following: newly increasing or deleting; and when the new timing point is added in other analog games except the first type games in the historical games, the scores of the new timing point are filled according to an interpolation algorithm.
That is, for example, if the first type track is timed every 5 km during the competition of the first type track in which the historical competitors on the first type track participate, and the second type track is timed every 10 km during the competition, if the first type track is used as the timing point setting mode as the reference, the second type track lacks the timing when the first historical competitors reach 5 km during the competition, and a new timing point needs to be added. Or, if the timing point setting mode in the match of the second type track is taken as a reference, the data measured by 5 kilometers in the match of the first type track is more, and the timing point needs to be deleted.
If the new timing point is added, the score of the new timing point can be filled according to an interpolation algorithm. Naturally, in the above process, it is necessary to correspondingly adjust each contestant in the other types of tracks except the first type of track according to the performance of the contestant. For example, a new timing point.
When calculating the second type conversion coefficient, the method may specifically include: dividing each historical contestant into an age group according to the age, and determining the average score of all the historical contestants in each age group according to the updated historical competition score of each historical contestant;
the second type of conversion factor is calculated based on the average performance of all historical contestants between the two different age groups.
Optionally, some pre-processing may be required before calculating the first type of conversion factor or the second type of conversion factor. For example, with a game timing point setting mode of a first type of track as a reference, in a historical game of other types of tracks except for the first type of track, a timing point is adjusted according to a preset mode, where the preset mode includes one or more of the following modes: newly increasing or deleting;
when the new timing points are added in the historical competitions in other types of competitions except the competition of the first type of competition, the scores of the new timing points are filled according to an interpolation algorithm, so that the average scores of all the historical contestants on each type of competition can be determined according to the updated scores;
and/or the timing point setting mode of the first-type match in the historical match in which the first-type historical contestant participates is taken as a reference, the timing point is adjusted according to a preset mode in other matches except the first-type match in the historical match, and the preset mode comprises one or more of the following modes: newly increasing or deleting;
and when the new timing point is added in other analog games except the first type games in the historical games, the scores of the new timing point are filled according to an interpolation algorithm.
That is, in step 110, when the athlete participates in all the games, the historical performance data of each of the timing points in the other games is obtained based on one game.
And extracting the ages of the historical contestants participating in the same type as the track of the current contest and the historical scores of each historical contestant from the historical contest data, and grouping the ages according to the ages to obtain h age groups.
In the ith age group, the historical scores of each historical contestant are divided into n levels, the probability value of the number of the historical contestants in the jth level to the number of the historical contestants in the ith age group is calculated, and the average score of the historical contestants in the jth level is calculated.
For example, all historical contestants of each age group may be ranked according to historical performance, such as three ranks of fast, normal, and slow running.
The historical score is in the first range, the running speed is fast, the historical score is in the second range, the running is general, and the historical score is in the third range, the running speed is slow. Then, the ratio of the number of running fast to the total number of people in the age group is counted as the probability of the running fast of the people in the age group, and the general probability of the running and the probability of the running slow are calculated by the same principle. Average performance in fast running people, average performance in general running people, and average performance in slow running people are also calculated.
Players who have never participated in the game are extracted from players participating in the game, and are grouped by age to obtain h age groups.
Randomly allocating the players in the ith age group participating in the historical competition according to the probability value corresponding to each level in the ith age group and the average score corresponding to each level, and acquiring the estimated score of each player never participating in the historical competition.
The players who participated in the historical competition are extracted from the players who participated in the competition, and the estimated result of the competition is determined according to the historical result of each player who participated in the competition, the first type conversion coefficient and/or the second type conversion coefficient.
That is, for those who have not participated in the race, there is no historical data on their performance as a basis for evaluation. Then, the performance of the historical contestants who are the same age as those who have not participated in the competition and are of the same type as the track of the current competition can be referred for prediction.
In the estimation, the purpose is not to predict how accurate the people can run, but to predict how many people can run faster, how many people can run generally, and how many people can run slowly. Then, the probability of running fast when the player selects the match according to the historical match of the same age group is multiplied by the total number of the players of the same age group who participate in the match, the total number of the possible running fast of the age group in the match is used as the total number of the possible running fast of the age group, the players of the possible running fast total number are randomly extracted from the people who do not participate in the match in the age group, and the average score of the running fast is set for the players. Similarly, the general total number of possible runs is calculated, then randomly distributed to corresponding people, and the general average score of the runs is set for the corresponding people, and after random extraction, the rest people are slow people to run, and the average score of the slow runs is set for the corresponding people.
Of course, the score set here is not the actual score of the player participating in the game, but is an estimated score, which is only used as a reference for the subsequent prediction of the race track's stream distribution. Therefore, as to who sets the running speed and who sets the running speed, the player is not affected at all.
Finally, according to the estimated scores of each player participating in the competition, simulating the traveling routes of all the players on the track of the competition, and predicting the track pedestrian flow distribution condition. Wherein h, i and n are all positive integers greater than or equal to 1, and i is a positive integer less than or equal to h.
Through the mode, the distribution condition of the race track pedestrian flow can be predicted, and the distribution rule of the athletes at each supply point participating in the race can be analyzed and counted according to the distribution condition of the race track pedestrian flow.
For example, the moment a certain tender will be met by the first player and the moment the last player is met. During which the time period in which the number of players is the highest is the time period, etc.
And step 130, inputting the weather data, the track type, the first replenishment type, the replenishment point information, the predicted athlete distribution rule of the competition and the competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, and predicting the per-person replenishment consumption corresponding to the first replenishment type in each replenishment point.
Optionally, the first replenishment prediction model includes a first replenishment surplus prediction model, a first replenishment consumption prediction model, and a first total replenishment consumption prediction model, and one total replenishment consumption prediction model, at least one surplus prediction model, and at least one total replenishment consumption prediction model correspond to each type of replenishment product.
That is, the replenishment prediction model may include a plurality of types, one being a prediction model that predicts the replenishment surplus, one being a prediction model that predicts the replenishment consumption amount, and the other being a total replenishment consumption amount prediction model. In order to more clearly explain the prediction of the replenishment resources at the first replenishment point, the first replenishment surplus prediction model, the first replenishment consumption prediction model, and the first total replenishment consumption prediction model are respectively specified in the application document. However, the first non-limiting example is that these prediction models can be used not only for the first supply point, but also for each supply point.
Since the prediction itself has a certain error, at least two first replenishment surplus prediction models and at least two first replenishment consumption prediction models may be set so that the final prediction can be more accurate. For example, the first replenishment remaining amount prediction model is set to 3, and the first replenishment consumption amount prediction model is set to 5.
The method comprises the steps of establishing a plurality of prediction models, predicting input parameters of the game by using each prediction model, and inputting weather data, track types, first supplies types, first supply point information, predicted athlete distribution rules of the game, predicted game scores of each athlete and the like of the game into the corresponding prediction models to obtain prediction results.
Namely, weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the current competition and a predicted competition result of each athlete are input into each first supplement surplus prediction model respectively to obtain at least two predicted supplement surplus;
calculating a first average of at least two predicted replenishment residuals;
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each supplement consumption amount prediction model during the competition to obtain at least two predicted supplement consumption amounts;
calculating a second average of the at least two predicted replenishment consumptions;
inputting weather data, track types, first supplement types, supplement point information, predicted athlete distribution rules of the competition and the competition results of each athlete into a first total supplement consumption prediction model, and predicting total supplement consumption of the first supplement points;
and predicting the actual replenishment consumption of the first replenishment point according to the first average value, the second average value and the total replenishment consumption of the first replenishment point.
And predicting the actual replenishment consumption of the first replenishment point according to the first average value, the second average value and the total replenishment consumption of the first replenishment point, so as to determine the average human replenishment consumption corresponding to the first replenishment product type according to the actual replenishment consumption, which can be embodied by adopting the following formula:
h ═ x- (z-x-y)/2 (formula 1)
Wherein H is the actual replenishment consumption, x is the second average value, y is the first average value, and z is the total replenishment consumption of the first replenishment point.
When the first replenishment surplus prediction model, the first replenishment consumption prediction model, and the first total replenishment consumption prediction model are trained, input parameters are slightly different.
For example, when the first remaining replenishment quantity prediction model is trained, the first remaining replenishment quantity prediction model is trained for each type of replenishment product, and the first remaining replenishment quantity prediction model corresponding to the type of replenishment product is acquired by mainly referring to the first remaining replenishment quantity prediction model based on the weather data, the runway type data, the historical performance data of the athlete, and the historical remaining quantity of the type of replenishment product for each replenishment point in the historical match data as input data.
In training the first replenishment consumption prediction model, the first replenishment consumption prediction model is also trained separately for each type of replenishment. The input parameters differ from the training of the first replenishment surplus prediction model in that the input parameters do not include the historical surplus for the type of replenishment item for each replenishment point, but rather include the historical consumption of the type of replenishment item for each replenishment point.
In training the first total replenishment consumption prediction model, consumption is primarily for all types of supplies, so the first total replenishment consumption prediction model includes only one. In the training, the input parameters are different from the training of the first replenishment surplus prediction model in that the input parameters do not include the historical surplus of the type of replenishment item for each replenishment point, but include the historical total consumption of all types of replenishment items for each replenishment point.
The specific training method is the prior art and is not described herein too much. The training model can adopt a regression prediction model such as a neural network training model or a decision tree model.
After the actual replenishment consumption is obtained, determining the per-person replenishment consumption corresponding to a first replenishment product type according to the actual replenishment consumption, wherein the first replenishment point is any replenishment point in the game, and the first replenishment product type is any one of at least one replenishment product type.
And step 140, predicting a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-capita replenishment consumption amount of each replenishment product type at each replenishment point.
Specifically, after determining the distribution of players at each point of supply and the per-person replenishment consumption at each point of supply for each type of replenishment, the number of workers to be equipped, the number of equipment, the per-person distribution of each replenishment at each point of supply, the total distribution of each replenishment at each point of supply, the length of service, and the like may be determined. I.e. to predict the final replenishment resource allocation strategy.
In a specific example, fig. 2 to 4 show the people flow distribution at different timing points respectively. Also, it can be seen in the figure that the peak of the people flow is 200 people at 10 km, so the staff configuration of the replenishment point should be satisfied to serve 200 people per minute for 78 minutes between 30 minutes and 108 minutes after the start of the race.
Similarly, 160 persons should be served every minute at 15 km, and the service time is 112 minutes between 44 minutes and 156 minutes after the start of the competition;
at 20 km it should be sufficient to serve 125 persons per minute, the service time being 140 minutes between 58 and 198 minutes after the start of the race.
In fig. 5, the amount of supplies actually released by everyone, the actual supply consumption by everyone and the prediction result of the supply consumption by everyone are given by the system at the positions of 10, 15 and 20 kilometers of the competition.
The replenishment resource allocation strategy prediction method provided by the embodiment of the invention is characterized in that all historical competition data of athletes participating in the competition at this time are obtained; and then inputting historical competition data and parameters of the competition, such as weather data, track types and the like, into a performance prediction model constructed by utilizing the historical parameter data in advance to obtain the respective rules of the athletes at each supply point of the competition. In addition to the above parameters, the types of supplies, the information of the points of supply, the predicted distribution rules of the players during the current competition, and the competition results of each player are input into the first supply prediction models which are pre-constructed and respectively correspond to each type of supplies, and the consumption of all the supplies in each point of supply is predicted. By the method, the replenishment resource allocation strategies such as the number of workers, the number of equipment, the type of replenishment supplies, the number of replenishment supplies, the service duration of the workers and the like which are required to be equipped at different replenishment points in different time periods can be predicted more accurately. Therefore, the supply resources are reasonably utilized, and the requirements of all athletes participating in the competition can be met as far as possible while resource waste is avoided.
Corresponding to the foregoing embodiment 1, embodiment 2 of the present invention further provides a replenishment resource allocation policy prediction apparatus, specifically as shown in fig. 6, the apparatus includes: an acquisition unit 601, a prediction unit 602, and a processing unit 603.
An acquisition unit 601, configured to acquire all historical competition data of athletes participating in the current competition, weather data during the current competition, a track type, supply point information, and at least one supply type;
the prediction unit 602 is configured to input all historical competition data of the athletes participating in the current competition, weather data during the current competition, and track types as input parameters into a pre-established performance prediction model, and predict an athlete distribution rule of each supply point of the current competition;
inputting weather data, a track type, a first replenishment type, replenishment point information, a predicted athlete distribution rule of the competition and a predicted competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, predicting per replenishment point consumption of people corresponding to the first replenishment type, wherein the first replenishment type is any one of at least one replenishment type;
the processing unit 603 is configured to predict a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-person replenishment consumption amount of each replenishment item type at each replenishment point.
Optionally, all historical competition data of the athletes participating in the competition at this time specifically include:
historical weather data, historical track types, historical replenishment point information, historical replenishment item types, consumption of each historical replenishment item, final historical scores of athletes, historical score data of each timing point and a competition completion rate which correspond to each competition in the historical competition.
Optionally, the predicting unit 602 is specifically configured to predict the race track pedestrian flow distribution condition by using a pre-established performance prediction model, with all historical race data of athletes participating in the current race, weather data during the current race, and a race track type as input parameters;
and (4) according to the pedestrian flow distribution condition of the track, statistically analyzing the distribution rule of the athletes at each supply point.
Optionally, the first replenishment prediction model includes a first replenishment surplus prediction model, a first replenishment consumption prediction model, and a first total replenishment consumption prediction model, and one total replenishment consumption prediction model, at least one surplus prediction model, and at least one total replenishment consumption prediction model correspond to each type of replenishment product.
Optionally, when the first replenishment remainder prediction models include at least two, and the first replenishment consumption prediction models include at least two, the prediction unit 602 is specifically configured to input the weather data, the track type, the first replenishment item type, the replenishment point information, the predicted athlete distribution rule of the current competition, and the competition result of each athlete in the current competition into each first replenishment remainder prediction model, and obtain at least two predicted replenishment remainders;
calculating a first average of at least two predicted replenishment residuals;
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each supplement consumption amount prediction model during the competition to obtain at least two predicted supplement consumption amounts;
calculating a second average of the at least two predicted replenishment consumptions;
inputting weather data, track types, first supplement types, supplement point information, predicted athlete distribution rules of the competition and the competition results of each athlete into a first total supplement consumption prediction model, and predicting total supplement consumption of the first supplement points;
and predicting the actual replenishment consumption of the first replenishment point according to the first average value, the second average value and the total replenishment consumption of the first replenishment point, so as to determine the average human replenishment consumption corresponding to the first replenishment type according to the actual replenishment consumption, wherein the first replenishment point is any replenishment point in the game.
Optionally, the final replenishment resource allocation policy at least includes:
the number of staff members, the number of equipment, the per-person dispensing amount of each supply for each point of supply, the total dispensing amount of each supply for each point of supply, and the length of service.
The functions executed by each component in the replenishment resource allocation policy prediction apparatus provided in the embodiment of the present invention are described in detail in the above embodiment 1, and therefore, redundant description is not repeated here.
The replenishment resource allocation strategy prediction device provided by the embodiment of the invention obtains all historical competition data of athletes participating in the competition; and then inputting historical competition data and parameters of the competition, such as weather data, track types and the like, into a performance prediction model constructed by utilizing the historical parameter data in advance to obtain the respective rules of the athletes at each supply point of the competition. In addition to the above parameters, the types of supplies, the information of the points of supply, the predicted distribution rules of the players during the current competition, and the competition results of each player are input into the first supply prediction models which are pre-constructed and respectively correspond to each type of supplies, and the consumption of all the supplies in each point of supply is predicted. By the method, the replenishment resource allocation strategies such as the number of workers, the number of equipment, the type of replenishment supplies, the number of replenishment supplies, the service duration of the workers and the like which are required to be equipped at different replenishment points in different time periods can be predicted more accurately. Therefore, the supply resources are reasonably utilized, and the requirements of all athletes participating in the competition can be met as far as possible while resource waste is avoided.
Corresponding to the above embodiment, embodiment 3 of the present invention further provides a replenishment resource allocation policy prediction system, specifically as shown in fig. 7, where the system includes: a processor 701 and a memory 702;
the memory 702 is used to store one or more program instructions;
the processor 701 is configured to execute one or more program instructions to perform any method steps of a replenishment resource allocation strategy prediction method as described in the above embodiments.
The replenishment resource allocation strategy prediction system provided by the embodiment of the invention obtains all historical competition data of athletes participating in the competition; and then inputting historical competition data and parameters of the competition, such as weather data, track types and the like, into a performance prediction model constructed by utilizing the historical parameter data in advance to obtain the respective rules of the athletes at each supply point of the competition. In addition to the above parameters, the types of supplies, the information of the points of supply, the predicted distribution rules of the players during the current competition, and the competition results of each player are input into the first supply prediction models which are pre-constructed and respectively correspond to each type of supplies, and the consumption of all the supplies in each point of supply is predicted. By the method, the replenishment resource allocation strategies such as the number of workers, the number of equipment, the type of replenishment supplies, the number of replenishment supplies, the service duration of the workers and the like which are required to be equipped at different replenishment points in different time periods can be predicted more accurately. Therefore, the supply resources are reasonably utilized, and the requirements of all athletes participating in the competition can be met as far as possible while resource waste is avoided.
In correspondence with the above embodiments, embodiments of the present invention also provide a computer storage medium containing one or more program instructions therein. Wherein the one or more program instructions are for executing, by a replenishment resource allocation policy prediction system, a replenishment resource allocation policy prediction method as described above.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (9)
1. A replenishment resource allocation strategy prediction method, the method comprising:
acquiring all historical competition data of the athletes participating in the competition, weather data, track types, supply point information and at least one supply type during the competition; all historical competition data of the athletes participating in the competition comprise historical weather data, historical track types, historical replenishment point information, historical replenishment item types, consumption of each historical replenishment item, final historical scores of the athletes, historical score data of each timing point and competition completion rate which correspond to each competition during the historical competition;
inputting all historical competition data of the athletes participating in the competition, weather data during the competition and track types into a pre-established performance prediction model as input parameters, and predicting the distribution rule of the athletes at each supply point of the competition; the pre-established performance prediction model comprises: the method comprises the steps that the average scores of all historical contestants on each type of track are counted according to historical contest data, a first type conversion coefficient is calculated according to the average scores of the historical contestants among different types of tracks, and a second type conversion coefficient is calculated according to the age of each historical contestant in the historical contest data and the historical scores during the contest;
inputting weather data, a track type, a first replenishment type, replenishment point information, a predicted athlete distribution rule of the competition and a predicted competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, and predicting per-person replenishment consumption corresponding to the first replenishment type in each replenishment point, wherein the first replenishment type is any one of the at least one replenishment type;
predicting a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-capita replenishment consumption amount of each replenishment product type at each replenishment point;
the calculating a second type of conversion coefficient according to the age of each historical contestant in the historical contest data and the historical achievement in the contest comprises: dividing each historical contestant into an age group according to the age, and determining the average score of all the historical contestants in each age group according to the updated historical competition score of each historical contestant; calculating a second transformation coefficient according to the average scores of all historical contestants between two different age groups;
the method for predicting the distribution rule of the athletes at each supply point of the competition comprises the following steps: extracting players who never participate in the game from the players who participate in the game, and grouping the players according to the ages to obtain h age groups; randomly distributing players in the ith age group participating in the current game according to the probability value corresponding to each level in the ith age group participating in the historical game and the average score corresponding to each level, and acquiring the estimated score of each player never participating in the game; the method comprises the steps of extracting players participating in a historical competition from players participating in the competition, determining estimated scores of the competition according to the historical scores of the players participating in the competition, the first conversion coefficient and/or the second conversion coefficient, simulating the traveling routes of all the players on the track of the competition according to the estimated scores of the players participating in the competition, predicting the track pedestrian flow distribution condition to analyze and count the player distribution rule of each replenishment point of the competition, wherein h and i are positive integers larger than 0, and i is smaller than or equal to h.
2. The method according to claim 1, wherein the step of inputting all historical competition data of the athletes participating in the current competition, weather data of the current competition and track types into a pre-established performance prediction model to predict the distribution rule of the athletes at each supply point of the current competition comprises the following specific steps:
taking all historical competition data of the athletes participating in the competition, weather data during the competition and the track type as input parameters, and predicting the pedestrian flow distribution condition of the track by using a pre-established performance prediction model;
and statistically analyzing the distribution rule of the athletes at each supply point according to the pedestrian flow distribution condition of the track.
3. The method of claim 1, wherein the first replenishment prediction model comprises a first replenishment surplus prediction model, a first replenishment consumption prediction model, and a first total replenishment consumption prediction model, and wherein one total replenishment consumption prediction model, at least one surplus prediction model, and at least one replenishment consumption prediction model correspond to each type of replenishment product.
4. The method according to claim 3, wherein when the first replenishment surplus prediction model includes at least two, and the first replenishment consumption prediction model includes at least two, the weather data, the track type, the first replenishment point information, the predicted player distribution rule of the current game, and the predicted game performance of each player at the current game are input into a first replenishment prediction model which is pre-constructed and corresponds to the first replenishment type, and the predicting of the per-capita replenishment consumption amount at the first replenishment point, which corresponds to the first replenishment type, specifically includes:
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each first supplement surplus prediction model during the competition to obtain at least two predicted supplement surplus;
calculating a first average of at least two predicted replenishment residuals;
respectively inputting weather data, a track type, a first supplement type, supplement point information, a predicted athlete distribution rule of the competition and a competition result of each athlete into each supplement consumption amount prediction model during the competition to obtain at least two predicted supplement consumption amounts;
calculating a second average of the at least two predicted replenishment consumptions;
inputting weather data, track types, first supplement types, supplement point information, predicted athlete distribution rules of the competition and the competition results of each athlete into the first total supplement consumption prediction model, and predicting the total supplement consumption of the first supplement points;
and predicting the actual replenishment consumption of the first replenishment point according to the first average value, the second average value and the total replenishment consumption of the first replenishment point, so as to determine the per-person replenishment consumption corresponding to the first replenishment type according to the actual replenishment consumption, wherein the first replenishment point is any replenishment point in the game.
5. The method according to any of claims 1-4, wherein the final replenishment resource allocation strategy comprises at least:
the number of staff members, the number of equipment, the per-person dispensing amount of each supply for each point of supply, the total dispensing amount of each supply for each point of supply, and the length of service.
6. A replenishment resource allocation policy prediction apparatus, characterized in that the apparatus comprises:
the acquisition unit is used for acquiring all historical competition data of the athletes participating in the competition, weather data during the competition, track types, supply point information and at least one supply type; all historical competition data of the athletes participating in the competition comprise historical weather data, historical track types, historical replenishment point information, historical replenishment item types, consumption of each historical replenishment item, final historical scores of the athletes, historical score data of each timing point and competition completion rate which correspond to each competition during the historical competition;
the prediction unit is used for inputting all historical competition data of the athletes participating in the competition, weather data during the competition and track types into a pre-established performance prediction model by taking the historical competition data, the weather data and the track types as input parameters, and predicting the athlete distribution rule of each supply point of the competition; the pre-established performance prediction model comprises: the method comprises the steps that the average scores of all historical contestants on each type of track are counted according to historical contest data, a first type conversion coefficient is calculated according to the average scores of the historical contestants among different types of tracks, and a second type conversion coefficient is calculated according to the age of each historical contestant in the historical contest data and the historical scores during the contest;
inputting weather data, a track type, a first replenishment type, replenishment point information, a predicted athlete distribution rule of the competition and a predicted competition result of each athlete into a pre-constructed first replenishment prediction model corresponding to the first replenishment type, and predicting per-person replenishment consumption corresponding to the first replenishment type in each replenishment point, wherein the first replenishment type is any one of the at least one replenishment type;
the processing unit is used for predicting a final replenishment resource allocation strategy according to the predicted athlete distribution rule of each replenishment point and the per-person replenishment consumption of each replenishment product type at each replenishment point;
the prediction unit is specifically configured to: the calculating a second type of conversion coefficient according to the age of each historical contestant in the historical contest data and the historical achievement in the contest comprises: dividing each historical contestant into an age group according to the age, and determining the average score of all the historical contestants in each age group according to the updated historical competition score of each historical contestant; calculating a second transformation coefficient according to the average scores of all historical contestants between two different age groups;
the method for predicting the distribution rule of the athletes at each supply point of the competition comprises the following steps: extracting players who never participate in the game from the players who participate in the game, and grouping the players according to the ages to obtain h age groups; randomly distributing players in the ith age group participating in the current game according to the probability value corresponding to each level in the ith age group participating in the historical game and the average score corresponding to each level, and acquiring the estimated score of each player never participating in the game; the method comprises the steps of extracting players participating in a historical competition from players participating in the competition, determining estimated scores of the competition according to the historical scores of the players participating in the competition, the first conversion coefficient and/or the second conversion coefficient, simulating the traveling routes of all the players on the track of the competition according to the estimated scores of the players participating in the competition, predicting the track pedestrian flow distribution condition to analyze and count the player distribution rule of each replenishment point of the competition, wherein h and i are positive integers larger than 0, and i is smaller than or equal to h.
7. The apparatus of claim 6, wherein the final replenishment resource allocation policy comprises at least:
the number of staff members, the number of equipment, the per-person dispensing amount of each supply for each point of supply, the total dispensing amount of each supply for each point of supply, and the length of service.
8. A replenishment resource allocation strategy prediction system, the system comprising: a processor and a memory;
the memory is to store one or more program instructions;
the processor, configured to execute one or more program instructions to perform the method of any of claims 1-5.
9. A computer storage medium comprising one or more program instructions for execution by a replenishment resource allocation strategy prediction system to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538612.9A CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538612.9A CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110163453A CN110163453A (en) | 2019-08-23 |
| CN110163453B true CN110163453B (en) | 2021-08-13 |
Family
ID=67626417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538612.9A Active CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110163453B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673800A (en) * | 2020-05-15 | 2021-11-19 | 阿里巴巴集团控股有限公司 | Data processing method and device and terminal equipment |
| CN113743337A (en) * | 2021-09-09 | 2021-12-03 | 江阴市浩华新型复合材料有限公司 | Image signal capturing platform using depth of field analysis |
| CN113947753B (en) * | 2021-10-15 | 2022-11-22 | 深圳市参数领航科技有限公司 | Cloud-operated on-site article delivery platform |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7516095B1 (en) * | 2007-10-12 | 2009-04-07 | Advisor Software, Inc. | Stochastic control system and method for multi-period consumption |
-
2019
- 2019-06-20 CN CN201910538612.9A patent/CN110163453B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
Non-Patent Citations (2)
| Title |
|---|
| 基于神经网络的时间序列组合预测模型研究及应用;秦大建等;《计算机应用》;20060828;第26卷(第S1期);第129-131页 * |
| 美国陆军旅战斗队的后勤预测和估算;姚红霞;《现代军事》;20170705(第7期);第101-106页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110163453A (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163453B (en) | Method, device and system for predicting replenishment resource allocation strategy and storage medium | |
| Constantinou et al. | pi-football: A Bayesian network model for forecasting Association Football match outcomes | |
| Forrest et al. | Forecasting sport: the behaviour and performance of football tipsters | |
| KR100864398B1 (en) | Online tournament game open system and method thereof, and ranking determine system and method thereof | |
| CN112950251A (en) | Reputation-based vehicle crowd sensing node reverse combination auction excitation optimization method | |
| GB2598686A (en) | Interactive system for enabling hybrid fantasy-style pari-mutuel wagering over network interfaces | |
| CN104667511A (en) | Competition ranking promoting system and method based on big data | |
| CN111035934A (en) | Game teaching method, device, electronic equipment and storage medium | |
| Scarf et al. | The importance of a match in a tournament | |
| Butler et al. | Expert performance and crowd wisdom: Evidence from English premier league predictions | |
| CN109993371B (en) | Method, device, system and storage medium for predicting race track people stream distribution situation | |
| Singh et al. | A unified theory for bivariate scores in possessive ball-sports: the case of handball | |
| CN104014122B (en) | Based on the sports and competitions back-up system of internet | |
| US20180280808A1 (en) | System and method for arranging equine competitions according to participant ability groupings | |
| Soto-Valero et al. | Assessing the causal impact of the 3-point per victory scoring system in the competitive balance of LaLiga | |
| CN106039712B (en) | Grouping method and device in golf game | |
| CN110263937A (en) | A kind of data processing method, equipment and storage medium | |
| Newell | Optimizing daily fantasy sports contests through stochastic integer programming | |
| Rogulj et al. | Evaluation models of some morphological characteristcs for talent scouting in sport | |
| CN105844497A (en) | User data prediction method and prediction device | |
| CN108939542A (en) | Sports score method of adjustment, device, server and storage medium | |
| CN109117462A (en) | A kind of prediction technique of game active player number | |
| Maher | Predicting the outcome of the Ryder cup | |
| CN106390460A (en) | Amateur electronic sports player and team information obtaining method and system and server | |
| US11872464B1 (en) | Golf play outcome simulation modeling 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 |