CN112546632A - Game map parameter adjusting method, device, equipment and storage medium - Google Patents
Game map parameter adjusting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112546632A CN112546632A CN202011430314.7A CN202011430314A CN112546632A CN 112546632 A CN112546632 A CN 112546632A CN 202011430314 A CN202011430314 A CN 202011430314A CN 112546632 A CN112546632 A CN 112546632A
- Authority
- CN
- China
- Prior art keywords
- map
- value
- variable
- game
- influence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000001364 causal effect Effects 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims description 59
- 238000002474 experimental method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 abstract description 10
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 9
- 201000005202 lung cancer Diseases 0.000 description 9
- 208000020816 lung neoplasm Diseases 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000009194 climbing Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000391 smoking effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for adjusting game map parameters, wherein the method comprises the following steps: acquiring user characteristic information and a map adjusting variable of a game, wherein the map adjusting variable is determined based on map parameter information; establishing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable; calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values; and determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value. According to the scheme, the influence of the user after the parameters are adjusted can be accurately judged, so that the parameters of the game map can be reasonably adjusted, the design efficiency of the game map is improved, and the workload of developers is reduced.
Description
Technical Field
The embodiment of the application relates to the field of computers, in particular to a method, a device, equipment and a storage medium for adjusting game map parameters.
Background
Video games are an entertainment mode that has emerged with the advent of computing devices for users to enjoy leisure and entertainment. With the development of computing devices, electronic game content is richer, playability is higher, and user experience is better and better. In the game design process, a plurality of parameter designs exist, for example, a house climbing game is taken as an example. A house climbing game is an entertainment game for a single user. In this game, the user manipulates 2 characters simultaneously, starting from the grid No. 0. The user may throw the dice once per round and select one role to advance after seeing the result. The awards are divided into a small prize and a big prize, wherein the small prize is the award which can be obtained when the user walks to the grid at the specified position in the game process; the jackpot is the prize that the two characters of the user can receive after reaching the end at the same time. Some of the boxes on the map are provided with mechanisms for fast forward and fast reverse, which, when activated, move the character directly to the designated location.
For the house climbing game, the quality of the game quality is determined by the quality of the map design. Generally speaking, there will be some difference in gameplay for games with different map configurations. A well-designed game map is sufficiently challenging for a player and not too boring, so that the user's game participation is higher. Conversely, if the map difficulty setting is not reasonable (too difficult or too simple), or the gameplay is not sufficient, the user experience may be affected, and thus the user's participation may be reduced.
In the prior art, the influence of a change of a certain product or service on the user experience can be generally explored in an A/B experiment mode, and the change can be called 'intervention'. Specifically, the users were randomly assigned to the experimental group or the control group. The users in the experimental group intervene, for example, with the modified services or products. The users in the control group do not accept the intervention, say using the original service or product. The effect of the modification can be estimated by comparing the user satisfaction indicators (e.g., whether remaining, activity of participation, duration of participation, etc.) in the test and control groups.
But for a house-climbing game, the mode of A/B experiment is not feasible. The reason is that it is possible for the user to actively or passively select a different map, rather than a random selection. Thus, the users of the control and experimental groups may have differences in the feature distributions, and the effects of "intervention" on their own would be difficult to estimate if they themselves had an effect on the user satisfaction index. For example, suppose we want to explore the impact (which can be represented by intervention) of a map adjustment that increases the difficulty of the game such that some difficulty exceeds the necessary limit. Players playing such maps tend to be higher in level (i.e. the experimental group), themselves have a higher activity level, so it is assumed that this intervention has a negative effect on the activity level of the game, but this negative effect may be difficult to estimate from the data because of the high activity nature of the players in the experimental group. Therefore, there is a need for other feasible ways to evaluate the impact of game setting changes to make reasonable parameter settings.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for adjusting game map parameters, which can accurately judge the influence of a user after the parameters are adjusted so as to reasonably adjust the game map parameters, improve the design efficiency of a game map and reduce the workload of a developer.
In a first aspect, an embodiment of the present invention provides a method for adjusting game map parameters, where the method includes:
acquiring user characteristic information and a map adjusting variable of a game, wherein the map adjusting variable is determined based on map parameter information;
establishing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable;
calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value.
In a second aspect, an embodiment of the present invention further provides a game map parameter adjusting apparatus, including:
the system comprises a parameter acquisition module, a parameter processing module and a game processing module, wherein the parameter acquisition module is used for acquiring user characteristic information and a map adjustment variable of a game, and the map adjustment variable is determined based on map parameter information;
the data construction module is used for constructing comparison group data and experimental group data according to the user characteristic information and the map adjusting variable;
the influence degree determining module is used for calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and the map adjusting module is used for determining whether to adjust the game map according to the map parameter information according to the contrast group influence difference value and the experimental group influence difference value.
In a third aspect, an embodiment of the present invention further provides a game map parameter adjustment device, where the device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for adjusting game map parameters according to the embodiment of the present invention.
In a fourth aspect, the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the game map parameter adjustment method according to the present invention.
In the embodiment of the invention, by acquiring user characteristic information and a map adjustment variable of a game, contrast group data and experimental group data are constructed according to the user characteristic information and the map adjustment variable, the contrast group data and the experimental group data are calculated based on a causal inference algorithm to obtain corresponding contrast group influence difference values and experimental group influence difference values, and whether a game map is adjusted according to the map parameter information is determined according to the contrast group influence difference values and the experimental group influence difference values. According to the scheme, the influence of the user after the parameters are adjusted can be accurately judged, so that the parameters of the game map can be reasonably adjusted, the design efficiency of the game map is improved, and the workload of developers is reduced.
Drawings
Fig. 1 is a flowchart of a method for adjusting parameters of a game map according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for determining an influence difference value according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for determining map parameter information to adjust a game map according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method for determining impact effect values according to an embodiment of the present invention;
FIG. 5 is a flowchart of another method for determining whether to adjust a game map according to map parameter information according to the magnitude of an effect value according to an embodiment of the present invention;
FIG. 6 is a block diagram of a game map parameter adjustment apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad invention. It should be further noted that, for convenience of description, only some structures, not all structures, relating to the embodiments of the present invention are shown in the drawings.
Fig. 1 is a flowchart of a method for adjusting parameters of a game map according to an embodiment of the present invention, where the embodiment is applicable to game map design, the method may be executed by a computer device, and may be an exemplary game of the type of dice-tossing customs, and examples of elements mainly included in this type of game are described below.
The game role is an agent of a user in the game, and the main purpose of the user is to control the clearance of the game role and achieve a certain preset target in the process.
The game map is the environment in which the game character is located during the game. The game character needs to interact with the game map in the game process. The game maps are different, the decision of each behavior of the player also changes correspondingly, and some good players can adjust own behaviors according to different maps.
Dice, which is thrown once each time a user makes a decision. The behavior of the user is restricted by the number of dice roll out points. Since the number of points thrown by the dice is random, the user must randomly change according to the number of points thrown by the dice when making a decision, thereby improving the game challenge.
In the present application, an exemplary game map may be a house-climbing game map, and a scene thereof will now be described as follows.
Assume that the map is linear, with a length of N. Grid G ═ G on map0，g1，g2，…，gNMeans that the starting point of the character is at g0. Suppose giI, i.e. giDenoted by the lattice number i. In the game, a quick-moving mechanism can be arranged1，e1)，(s2，e2)，…]And (4) showing. siThe code of the grid when the power is off, eiThe grid code that arrives at the moment when the mechanism is triggered. The user rolls the dice once per round of the game at a cost of c. Each dice rolling has a probability of one sixth of the number of the points rolled out by 1-6. Assuming that the number of thrown points is p, the user currently advances p grids. I.e. if the position of the user of the wheel is giThen the position of the user in the lower wheel is gi+ p. If the distance N-i between the current wheel and the terminal point is less than p, the user can advance to N- (g) to ensure that the position of the user does not exceed the upper limit of the mapiPosition of + p-N). M gifts are randomly placed on the grid, and if a character operated by a user steps on a certain gift, a specific amount is obtained. The attribute of the gift is a (value, position) binary, and the attribute of the mth cell is represented by (v)m，gm) And (4) showing. When the user finishes a round of game, the value v is obtained at one timefThe prize of (1). Assuming that the sum of the prizes acquired by the users in one game is V, and the dice thrown by the users in one game round for t times, the sum spent by the users in the game is ct, and the net income of the users in one game can be calculated to be V-ct. If net profit results from a large number of repeated games of multiple users are collected, the expected net profit E V-ct of the map can be calculated]. By adjusting the gift in the mapAnd (4) adjusting the expected net benefit of the map according to the physical condition and the institution condition, such as increasing the sum and the number of gifts to a certain extent to improve the expected net benefit of the map, and otherwise, reducing the expected net benefit.
The method and the device aim to reasonably predict the influence of the adjustment of the map parameter information on the activity degree of the user so as to determine whether to make corresponding map adjustment. Illustratively, the simplified description may be made in the following manner: a series of user feature information is represented by a feature matrix X. Typically, the dimension of X is dimX ═ n, p. Where n is the number of users in the history and p is the number of features collected for a single user. In the present embodiment, each feature is a variable of 0 to 1 for simplicity of explanation. A series of user-final retention information is collected simultaneously, represented by vector y. Where the dimension of y is dimy ═ n, 1. Each value of y is between 0 and 1, i.e., y ∈ (0, 1). The value of y represents the liveness of the user in the game if yi1 means that user i has reached the highest activity, whereas if y is the oppositei0 represents the lowest activity of user i.
The scheme of one embodiment of the application specifically comprises the following steps:
step S101, obtaining user characteristic information and a map adjusting variable of the game, wherein the map adjusting variable is determined based on map parameter information.
In one embodiment, the user characteristic information may be multidimensional, such as: the user's language, country, age, gender, model used, network type, etc. In addition, user characteristics obtained from the game record may be included, such as the number of times the user completed the game, the average time of day the user played the game, the winning rate of the game, etc. In this embodiment, in order to estimate the influence of the adjustment of the map parameter information on the user activity, the user characteristic information is a fixed input value, which is exemplarily denoted as X.
The map adjustment variable may be denoted as T, which is determined based on the map parameter information. Illustratively, for simplicity of illustration, T takes the value 0 or 1. When the value of T is 0, the representation that the proportion of the user participating in the map changed by the map parameter information in the past period is less than a given threshold value; when the value of T is 1, the representation that the proportion of the user participating in the map changed by the map parameter information in the past period is larger than a given threshold value. The map parameter information may include one or more, for example, the number of departments taking the map parameter information as a map is taken as an example, when the number of departments in the map in which the user participates in a past period (for example, within one week) exceeds 8, the number is recorded as T being 1, and when the number of departments in the map in which the user participates does not exceed 8, the number is recorded as T being 0; taking the number of prizes on the map as an example, when the number of map winning prizes participated by the user in a past period (such as within a week) exceeds 8, the score T is 1, and when the number of map winning prizes participated by the user does not exceed 8, the score T is 0.
And S102, constructing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable.
Specifically, the control group data and the experimental group data both include a plurality of observation data, and each observation data includes user characteristic information, a map adjustment variable, and a potential result corresponding to the map adjustment variable under different values. The map adjusting variable comprises a first variable value and a second variable value, and the corresponding potential results are a first variable result and a second variable result respectively. Illustratively, the first variable value is noted as 0 and the second variable value is noted as 1.
As represented by (U) for each observationi(0)，Ui(1)，Xi，Ti) Wherein Ti represents a map adjustment variable, and T is a variable from 0 to 1 in the scenario of the present embodiment. The experimental group data in the scheme is a sample set when Ti is equal to 1, and the comparison group data in the scheme is a sample set when Ti is equal to 0; xi represents covariates, i.e. variables relevant to the study in addition to map adjustment variables and result variables, such as user characteristic information in this example; u (0) represents a potential result of a result variable concerned by the developer when T ═ 0, that is, a first potential result; u (1) represents a potential result when the result variable concerned by the developer is T ═ 1, i.e., the second potential result. Wherein the control group data and the experimental group data both contain multiple views of the above representation formsAnd (6) measuring data.
And S103, calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values.
In the embodiment, the causal inference algorithm based on the method is different from the traditional prediction algorithm, and is briefly described as follows.
The traditional statistical learning method aims to fit data so as to help us predict unknown target variables given input characteristic variables, and the core of the research is to find the correlation among the variables. However, the correlation is not causality in many cases, such as: the fact that a can provide assistance in predicting B does not mean that a is the cause of B. For example, variable A is whether a person carries a lighter, variable B is whether a person smokes, and variable C is whether a person has lung cancer. The a variable can be found to have a correlation with the C variable: people with lung cancer often carry lighters. It cannot be concluded that this behavior of carrying a lighter is responsible for lung cancer. The reason is that B, a variable (called confounding factor), causes a and C to appear pseudo-correlated: b causes A and B simultaneously causes C, so that the values of A and C have correlation.
The present embodiment solves the above problem by a causal inference algorithm. The scheme is based on the Rubin framework, and the thinking of causal inference and the 'counter-fact inference' are closely connected. Counter-fact reasoning refers to: for an individual who has received a particular intervention (denoted by the variable T ═ 1), the causal effect of that intervention on the target variable depends on the value of the target variable for the same individual who has not received the particular intervention (T ═ 0) in another parallel universe. Vice versa (T ═ 1 and T ═ 0 replace each other), so that interference of all other variables can be excluded.
For the foregoing lighter example, the causal effect of carrying a lighter by an individual on lung cancer is calculated. It can be assumed that the individual does not carry a lighter or smoke under the real condition, and in order to calculate the causal effect of the individual carrying the lighter on the lung cancer, the same individual carrying the lighter but not smoking needs to be found in the parallel universe, and whether the lung cancer is changed or not is observed. Assuming that smoking is the most significant factor affecting lung cancer, the individual will still not have lung cancer because he is not smoking. It can be concluded that carrying the lighter has no causal effect on lung cancer.
Therefore, the idea of causal inference can effectively distinguish causality from correlation. But in practice no other individual in the parallel universe can be found, i.e. so-called counterfactual reasoning is actually not possible exactly. Therefore, there is a need to establish counterfactual reasoning with machine learning models to assist in simulations. In the scheme, the idea of the method is to convert observation of counter-fact phenomena into prediction problems of machine learning: for an individual, the counterfactual outcome of not receiving intervention is predicted if it is actually receiving intervention. If the real situation does not accept the intervention, the counterfactual result of the intervention is predicted. By comparing the difference between the two cases, the causal effect of the intervention, i.e. the impact effect value described in the present scheme, can then be determined.
The causal model framework used in the present solution is exemplarily illustrated as follows.
Let U be f (X, T). Where U is a result variable that the developer is interested in, such as y in the previous example, i.e., a variable that refers to the user's activity level. X represents user characteristic information, i.e. covariates. T is some map adjustment variable representing the developer's attention, and the dimension of T may be (n,1), where n is the number of data points in the dataset. The core problems of developer concern are: how to quantify the effect of the change in T on the resulting variable U without considering the interference caused by the change in X. Generally, a special randomization experiment is designed to quantify the effect of the change in T on U. Since the influence of the change of X on U cannot be completely isolated, the causal effect of T on U cannot be directly obtained from the historical data, and in order to estimate the causal effect of T on U from the historical data, it is necessary to estimate the causal effect by using a causal inference method.
Based on the above design thought, as shown in fig. 2, fig. 2 is a flowchart of a method for determining an influence difference value according to an embodiment of the present invention, where the step of calculating the control group data and the experimental group data based on a causal inference algorithm to obtain a corresponding control group influence difference value and an experimental group influence difference value further includes:
and step S1031, constructing a first estimation model and a second estimation model.
And S1032, estimating a first variable result in the experimental group data through the first estimation model, and calculating to obtain an experimental group influence difference value by combining a second variable result in the experimental group data.
And step S1033, estimating a second variable result in the control group data through the second estimation model, and calculating to obtain a control group influence difference value by combining the first variable result in the control group data.
In steps S1031-S1033, for example, the first estimation model is denoted as M0The second estimation model is denoted as M1. First estimation model M0For estimating mu0(x) In which μ0(x)＝E[U(0)|X＝x]The second estimation model is denoted as M1For estimating mu1(x) In which μ1(x)＝E[U(1)|X＝x]. For each observed data point (U)i(0)，Ui(1)，Xi，Ti) In the control group data (T ═ 0), U (0) was observed, and in the experimental group data (T ═ 1), U (1) was observed. Predicting U (0) in the experimental group data by the first estimation model, and predicting U (1) in the control group data by the second estimation model, whereby each observation point (U) is observed regardless of the control group data or the experimental group datai(0)，Ui(1)，Xi，Ti) Both U (0) and U (1) were obtained.
Wherein, the experimental group influences the calculation formula of the difference value:
wherein,
is calculated by a first estimation model; formula for calculating influence difference value of control group：
Wherein,
calculated by the second estimation model. Wherein,
represents the difference in outcome variable between the two potential outcomes of intervention and non-intervention at a single observation point in the experimental and control cohorts, respectively.
In one embodiment, the first estimation model and the second estimation model are machine learning models obtained by supervised learning training, and the learning training methods are exemplified by linear regression, random forest, support vector machine, XGBOOST, and the like.
And step S104, determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value.
Because the determined control group influence difference value and the determined experimental group influence difference value are obtained aiming at a single observation point, the expectation is obtained respectively by the single observation point in the control group data and the experimental group data so as to obtain a control group average influence difference value and an experimental group average influence difference value, and the calculation formula is as follows:
in the calculation of
And
the average value of the influence effect value is obtained.
And after the influence effect value is determined, determining whether to adjust the game map according to the map parameter information according to the influence effect value.
Accordingly, as shown in fig. 3, fig. 3 is a flowchart of a method for determining map parameter information to adjust a game map according to an embodiment of the present invention, and S104 includes:
and step S1041, calculating to obtain a control expected value of the control group influence difference value and an experiment expected value of the experiment group influence difference value.
Step S1042, determining the average value of the comparison expected value and the experiment expected value as an influence effect value brought by the map adjusting variable.
And S1043, determining whether to adjust the game map according to the map parameter information according to the influence effect value.
In another embodiment, as shown in fig. 4, fig. 4 is a flowchart of a method for determining an impact effect value according to an embodiment of the present invention, which specifically includes:
and S10421, determining a trend value weight, and summing the comparison expected value and the experiment expected value after calculating the trend value weight.
And under the condition that the weight of the tendency value is given user characteristic information, when the value of the map adjusting variable is a second variable value, the probability of a second variable result is obtained. Exemplarily, it is denoted as e (X) P (T ═ 1| X ═ X). This value is the probability that, in the real case, the user will accept intervention given X ═ X.
Accordingly, influence the effect value
Thereby making the calculation more accurate.
And step S10422, determining the summation result as an influence effect value brought by the map adjusting variable.
Exemplary calculations are shown in the following table:
| map parameter information | Influence effect value |
| Whether the number of organs of the map exceeds 8 | -0.23 |
| Whether the number of prizes on the map exceeds 8 | 0.41 |
From the above table, it is known that "whether the number of divisions of the map exceeds 8" has an influence on the user of-0.23, i.e., has a negative influence, and accordingly, the map parameter information is not adjusted. The influence degree of the map on the user is 0.41, namely, the map parameter information is adjusted correspondingly, and the influence degree is positive, namely, whether the number of the prizes of the map exceeds 8.
According to the scheme, the game map parameters are reasonably adjusted by adopting a mode based on a cause and effect inference algorithm, so that the influence of the user after the parameters are adjusted can be accurately judged, the game map parameters are reasonably adjusted, the design efficiency of the game map is improved, and the workload of developers is reduced.
On the basis of the above technical solution, the map parameter information includes a plurality of map parameter information, and as shown in fig. 5, fig. 5 is a flow chart of another method for determining whether to adjust a game map according to the map parameter information according to the magnitude of the effect value, according to an embodiment of the present invention, specifically as follows:
step S201, respectively calculating an influence effect value corresponding to each map parameter information.
Step S202, an average influence effect value is obtained by taking expectation on the obtained plurality of influence effect values.
And step S203, determining whether to adjust the game map according to the map parameter information according to the average influence effect value.
Wherein, by the aforementioned calculation step, the influence effect value given to the feature x can be derived
Get the expectation on the data set
And taking the average influence value as an average influence value under a plurality of map parameter information, and correspondingly adjusting the game map corresponding to the map parameter information when the average influence value is positive, or not adjusting the game map corresponding to the map parameter information.
Therefore, the influence effect on the user can be obtained by simultaneously calculating the parameter information of a plurality of maps so as to reasonably design and develop the game map.
Fig. 6 is a block diagram of a game map parameter adjusting apparatus according to an embodiment of the present invention, which is used for executing the game map parameter adjusting method according to the data receiving end embodiment, and has corresponding functional modules and beneficial effects of the executing method. As shown in fig. 6, the apparatus specifically includes: a parameter acquisition module 101, a data construction module 102, an influence determination module 103, and a map adjustment module 104, wherein,
the parameter obtaining module 101 is configured to obtain user feature information and a map adjustment variable of a game, where the map adjustment variable is determined based on the map parameter information;
the data construction module 102 is configured to construct comparison group data and experimental group data according to the user feature information and the map adjustment variable;
the influence degree determining module 103 is configured to calculate the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and the map adjusting module 104 is configured to determine whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value.
According to the scheme, the map adjusting variables of the game and the user characteristic information are obtained, and the map adjusting variables are determined based on the map parameter information; establishing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable; calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values; and determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value. According to the scheme, the influence of the user after the parameters are adjusted can be accurately judged, so that the parameters of the game map can be reasonably adjusted, the design efficiency of the game map is improved, and the workload of developers is reduced.
In one possible embodiment, the control group data and the experimental group data respectively include the user characteristic information, the map adjustment variable, and the corresponding potential results of the map adjustment variable under different values.
In one possible embodiment, the map adjustment variable includes a first variable value and a second variable value, the corresponding potential results are a first variable result and a second variable result respectively, the map adjustment variable in the control group data takes the value of the first variable value, and the map adjustment variable in the experimental group data takes the value of the second variable value.
In one possible embodiment, the influence degree determination module 103 is specifically configured to:
constructing a first estimation model and a second estimation model;
estimating a first variable result in the experimental group data through the first estimation model, and calculating to obtain an experimental group influence difference value by combining a second variable result in the experimental group data;
and estimating a second variable result in the control group data through the second estimation model, and calculating to obtain a control group influence difference value by combining the first variable result in the control group data.
In a possible embodiment, the map adjusting module 104 is specifically configured to:
calculating to obtain a control expected value of the control group influence difference value and an experiment expected value of the experiment group influence difference value, and determining a mean value of the control expected value and the experiment expected value as an influence effect value brought by the map adjusting variable;
and determining whether to adjust the game map according to the map parameter information according to the influence effect value.
In one possible embodiment, the influence degree determination module 103 is specifically configured to:
determining a tendency value weight, wherein the tendency value weight is the probability of a second variable result obtained when the map adjustment variable takes the value of the second variable value under the condition of giving the user characteristic information;
and calculating the comparison expected value and the experiment expected value through the tendency value weight, summing the calculation results, and determining the summation result as an influence effect value brought by the map adjusting variable.
In a possible embodiment, when the map parameter information is multiple, the map adjusting module 104 is specifically configured to:
respectively calculating the influence effect value corresponding to each map parameter information;
obtaining an average influence effect value by expecting the obtained multiple influence effect values;
and determining whether to adjust the game map according to the map parameter information according to the average influence effect value.
In a possible embodiment, the map adjusting module 104 is specifically configured to:
and if the average influence effect value is larger than a preset threshold value, adjusting the game map according to the map parameter information, otherwise, not adjusting the game map.
Fig. 7 is a schematic structural diagram of a game map parameter adjustment apparatus according to an embodiment of the present invention, as shown in fig. 7, the apparatus includes a processor 201, a memory 202, an input device 203, and an output device 204; the number of the processors 201 in the device may be one or more, and one processor 201 is taken as an example in fig. 7; the processor 201, the memory 202, the input device 203 and the output device 204 in the apparatus may be connected by a bus or other means, and fig. 7 illustrates the example of connection by a bus. The memory 202 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the game map parameter adjustment method in the embodiment of the present invention. The processor 201 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 202, that is, the above-described game map parameter adjustment method is realized. The input device 203 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the apparatus. The output device 204 may include a display device such as a display screen.
Embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for adjusting game map parameters, the method including:
acquiring user characteristic information and a map adjusting variable of a game, wherein the map adjusting variable is determined based on map parameter information;
establishing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable;
calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value.
From the above description of the embodiments, it is obvious for those skilled in the art that the embodiments of the present invention can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better implementation in many cases. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to make a computer device (which may be a personal computer, a service, or a network device) perform the methods described in the embodiments of the present invention.
It should be noted that, in the embodiment of the game map parameter adjusting apparatus, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.
It should be noted that the foregoing is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will appreciate that the embodiments of the present invention are not limited to the specific embodiments described herein, and that various obvious changes, adaptations, and substitutions are possible, without departing from the scope of the embodiments of the present invention. Therefore, although the embodiments of the present invention have been described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and many other equivalent embodiments may be included without departing from the concept of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.
Claims (11)
1. The game map parameter adjusting method is characterized by comprising the following steps:
acquiring user characteristic information and a map adjusting variable of a game, wherein the map adjusting variable is determined based on map parameter information;
establishing contrast group data and experimental group data according to the user characteristic information and the map adjusting variable;
calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and determining whether to adjust the game map according to the map parameter information according to the control group influence difference value and the experimental group influence difference value.
2. The method of claim 1, wherein the control group data and the experimental group data respectively comprise potential results corresponding to the user characteristic information, the map adjustment variable, and the map adjustment variable at different values.
3. The method of claim 2, wherein the map adjustment variables include a first variable value and a second variable value, the corresponding potential results are a first variable result and a second variable result, respectively, the map adjustment variable in the control group data takes the value of the first variable value, and the map adjustment variable in the experimental group data takes the value of the second variable value.
4. The method of claim 3, wherein calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group effect difference values and experimental group effect difference values comprises:
constructing a first estimation model and a second estimation model;
estimating a first variable result in the experimental group data through the first estimation model, and calculating to obtain an experimental group influence difference value by combining a second variable result in the experimental group data;
and estimating a second variable result in the control group data through the second estimation model, and calculating to obtain a control group influence difference value by combining the first variable result in the control group data.
5. The method of any of claims 1-4, wherein determining whether to adjust a game map based on the map parameter information based on the control group effect difference values and the experimental group effect difference values comprises:
calculating to obtain a control expected value of the control group influence difference value and an experiment expected value of the experiment group influence difference value, and determining a mean value of the control expected value and the experiment expected value as an influence effect value brought by the map adjusting variable;
and determining whether to adjust the game map according to the map parameter information according to the influence effect value.
6. The method of claim 5, wherein determining the average of the expected control values and the expected experimental values as the effect values of the map adjusting variables comprises:
determining a tendency value weight, wherein the tendency value weight is the probability of a second variable result obtained when the map adjustment variable takes the value of the second variable value under the condition of giving the user characteristic information;
and calculating the comparison expected value and the experiment expected value through the tendency value weight, summing the calculation results, and determining the summation result as an influence effect value brought by the map adjusting variable.
7. The method according to claim 5, wherein when the map parameter information is plural, the determining whether to adjust the game map according to the map parameter information according to the magnitude of the influence effect value includes:
respectively calculating the influence effect value corresponding to each map parameter information;
obtaining an average influence effect value by expecting the obtained multiple influence effect values;
and determining whether to adjust the game map according to the map parameter information according to the average influence effect value.
8. The method of claim 7, wherein determining whether to adjust the game map according to the map parameter information according to the magnitude of the average impact effect value comprises:
and if the average influence effect value is larger than a preset threshold value, adjusting the game map according to the map parameter information, otherwise, not adjusting the game map.
9. The game map parameter adjustment device is characterized by comprising:
the system comprises a parameter acquisition module, a parameter processing module and a game processing module, wherein the parameter acquisition module is used for acquiring user characteristic information and a map adjustment variable of a game, and the map adjustment variable is determined based on map parameter information;
the data construction module is used for constructing comparison group data and experimental group data according to the user characteristic information and the map adjusting variable;
the influence degree determining module is used for calculating the control group data and the experimental group data based on a causal inference algorithm to obtain corresponding control group influence difference values and experimental group influence difference values;
and the map adjusting module is used for determining whether to adjust the game map according to the map parameter information according to the contrast group influence difference value and the experimental group influence difference value.
10. A game map parameter adjustment apparatus, the apparatus comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the game map parameter adjustment method according to any one of claims 1 to 8.
11. A storage medium containing computer-executable instructions for performing the game map parameter adjustment method of any one of claims 1-8 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430314.7A CN112546632B (en) | 2020-12-09 | 2020-12-09 | Game map parameter adjustment method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430314.7A CN112546632B (en) | 2020-12-09 | 2020-12-09 | Game map parameter adjustment method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112546632A true CN112546632A (en) | 2021-03-26 |
| CN112546632B CN112546632B (en) | 2024-10-01 |
Family
ID=75060795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011430314.7A Active CN112546632B (en) | 2020-12-09 | 2020-12-09 | Game map parameter adjustment method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112546632B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040117239A1 (en) * | 2002-12-17 | 2004-06-17 | Mittal Parul A. | Method and system for conducting online marketing research in a controlled manner |
| US20100144444A1 (en) * | 2008-12-04 | 2010-06-10 | Disney Enterprises, Inc. | Real-time, video game playtesting |
| US20110212784A1 (en) * | 2009-09-30 | 2011-09-01 | Matthew Ocko | Apparatuses, Methods and Systems for a Live Online Game Tester |
| CN102521832A (en) * | 2011-12-07 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Image analysis method and system |
| CN105243006A (en) * | 2015-09-30 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Flow layer setting method and apparatus based on flow experiment and flow experiment implementing method and apparatus |
| WO2016068625A1 (en) * | 2014-10-29 | 2016-05-06 | 에스케이텔레콤 주식회사 | Method for removing bias in target nucleotide sequence analysis using nmf |
| WO2016149347A1 (en) * | 2015-03-16 | 2016-09-22 | Interdigital Technology Corporation | Context aware actionable behavior pattern management for evolving user behaviors |
| CN107526750A (en) * | 2016-06-22 | 2017-12-29 | 阿里巴巴集团控股有限公司 | One species diversity sets the determination method and device of effect |
| US20180243656A1 (en) * | 2017-02-28 | 2018-08-30 | Electronic Arts Inc. | Realtime dynamic modification and optimization of gameplay parameters within a video game application |
| US20180357654A1 (en) * | 2017-06-08 | 2018-12-13 | Microsoft Technology Licensing, Llc | Testing and evaluating predictive systems |
| CN110033156A (en) * | 2018-12-14 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of determination method and device of business activity effect |
| CN110555659A (en) * | 2019-09-10 | 2019-12-10 | 电子科技大学 | method for analyzing value of fourth logistics platform to shipper |
| KR20190139008A (en) * | 2018-06-07 | 2019-12-17 | 주식회사 엔씨소프트 | A system for preventing user leaving based on expectation profit and controlling method thereof |
| CN110892436A (en) * | 2018-07-11 | 2020-03-17 | 谷歌有限责任公司 | Improving accuracy of experimental results through geographical selection |
| CN110956297A (en) * | 2018-09-26 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Prediction processing method and device for loss probability |
| CN111061624A (en) * | 2019-11-11 | 2020-04-24 | 北京三快在线科技有限公司 | Policy execution effect determination method and device, electronic equipment and storage medium |
| CN111311336A (en) * | 2020-03-17 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Test tracking method and system for strategy execution |
| CN111625720A (en) * | 2020-05-21 | 2020-09-04 | 广州虎牙科技有限公司 | Method, device, equipment and medium for determining data decision item execution strategy |
| CN111773732A (en) * | 2020-09-04 | 2020-10-16 | 完美世界(北京)软件科技发展有限公司 | Target game user detection method, device and equipment |
| CN111784173A (en) * | 2020-07-09 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | AB experiment data processing method, device, server and medium |
| WO2020228514A1 (en) * | 2019-05-13 | 2020-11-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and apparatus, and device and storage medium |
| CN111988634A (en) * | 2020-08-14 | 2020-11-24 | 广州市百果园信息技术有限公司 | Anchor selection method and device, computer readable storage medium and electronic equipment |
-
2020
- 2020-12-09 CN CN202011430314.7A patent/CN112546632B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040117239A1 (en) * | 2002-12-17 | 2004-06-17 | Mittal Parul A. | Method and system for conducting online marketing research in a controlled manner |
| US20100144444A1 (en) * | 2008-12-04 | 2010-06-10 | Disney Enterprises, Inc. | Real-time, video game playtesting |
| US20110212784A1 (en) * | 2009-09-30 | 2011-09-01 | Matthew Ocko | Apparatuses, Methods and Systems for a Live Online Game Tester |
| CN102521832A (en) * | 2011-12-07 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Image analysis method and system |
| WO2016068625A1 (en) * | 2014-10-29 | 2016-05-06 | 에스케이텔레콤 주식회사 | Method for removing bias in target nucleotide sequence analysis using nmf |
| WO2016149347A1 (en) * | 2015-03-16 | 2016-09-22 | Interdigital Technology Corporation | Context aware actionable behavior pattern management for evolving user behaviors |
| CN105243006A (en) * | 2015-09-30 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Flow layer setting method and apparatus based on flow experiment and flow experiment implementing method and apparatus |
| CN107526750A (en) * | 2016-06-22 | 2017-12-29 | 阿里巴巴集团控股有限公司 | One species diversity sets the determination method and device of effect |
| US20180243656A1 (en) * | 2017-02-28 | 2018-08-30 | Electronic Arts Inc. | Realtime dynamic modification and optimization of gameplay parameters within a video game application |
| US20180357654A1 (en) * | 2017-06-08 | 2018-12-13 | Microsoft Technology Licensing, Llc | Testing and evaluating predictive systems |
| KR20190139008A (en) * | 2018-06-07 | 2019-12-17 | 주식회사 엔씨소프트 | A system for preventing user leaving based on expectation profit and controlling method thereof |
| CN110892436A (en) * | 2018-07-11 | 2020-03-17 | 谷歌有限责任公司 | Improving accuracy of experimental results through geographical selection |
| CN110956297A (en) * | 2018-09-26 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Prediction processing method and device for loss probability |
| CN110033156A (en) * | 2018-12-14 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of determination method and device of business activity effect |
| WO2020228514A1 (en) * | 2019-05-13 | 2020-11-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and apparatus, and device and storage medium |
| CN110555659A (en) * | 2019-09-10 | 2019-12-10 | 电子科技大学 | method for analyzing value of fourth logistics platform to shipper |
| CN111061624A (en) * | 2019-11-11 | 2020-04-24 | 北京三快在线科技有限公司 | Policy execution effect determination method and device, electronic equipment and storage medium |
| CN111311336A (en) * | 2020-03-17 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Test tracking method and system for strategy execution |
| CN111625720A (en) * | 2020-05-21 | 2020-09-04 | 广州虎牙科技有限公司 | Method, device, equipment and medium for determining data decision item execution strategy |
| CN111784173A (en) * | 2020-07-09 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | AB experiment data processing method, device, server and medium |
| CN111988634A (en) * | 2020-08-14 | 2020-11-24 | 广州市百果园信息技术有限公司 | Anchor selection method and device, computer readable storage medium and electronic equipment |
| CN111773732A (en) * | 2020-09-04 | 2020-10-16 | 完美世界(北京)软件科技发展有限公司 | Target game user detection method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 王培刚: "《多元统计分析与SAS实现》", 30 November 2020, 武汉大学出版社, pages: 212 - 214 * |
| 田玲;池迎春;侯志明;: "聚焦解决模式在阿尔茨海默病合并脑血栓患者中的效果", 血栓与止血学, no. 03, 20 June 2018 (2018-06-20) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112546632B (en) | 2024-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109091868B (en) | Method, apparatus, computer equipment and the storage medium that battle behavior determines | |
| CN111738294B (en) | AI model training method, AI model using method, computer device, and storage medium | |
| Yuan et al. | A mixture-of-modelers approach to forecasting NCAA tournament outcomes | |
| Yaari et al. | “Hot hand” on strike: Bowling data indicates correlation to recent past results, not causality | |
| CN111265878B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN107749006A (en) | Game appraisal procedure, device and equipment | |
| CN111988634A (en) | Anchor selection method and device, computer readable storage medium and electronic equipment | |
| Maimone et al. | Football is becoming more predictable; network analysis of 88 thousand matches in 11 major leagues | |
| Humphreys et al. | Consumer behaviour in lottery: The double hurdle approach and zeros in gambling survey data | |
| Beliën et al. | Optimization modelling for analyzing fantasy sport games | |
| CN112546632B (en) | Game map parameter adjustment method, device, equipment and storage medium | |
| Zappalà et al. | On the role of chance in fencing tournaments: An agent-based approach | |
| Rager et al. | Groups, governance, and greed: the ACCESS world model | |
| Aycinena et al. | Entry in contests with incomplete information: Theory and experiments | |
| CN112600682B (en) | Block chain consensus method and device based on delegation interest certification algorithm | |
| St-Vincent | An experimental test of the pivotal voter model under plurality and PR elections | |
| Kaizeler et al. | Is the lottery product an inferior good in higher income countries | |
| CN113941157A (en) | Game matching method and device, electronic equipment and storage medium | |
| CN113240190A (en) | Athlete pre-race state evaluation method based on multi-period evolution entropy technology | |
| CN112001071A (en) | Method, device, equipment and medium for determining simulated guess data | |
| Mahoney et al. | Method and Validation for Optimal Lineup Creation for Daily Fantasy Football Using Machine Learning and Linear Programming | |
| O'Hanlon | Using Supervised Machine Learning to Predict the Final Rankings of the 2021 Formula One Championship | |
| Agrawal et al. | Targeted upskilling framework based on player mistake context in online skill gaming platforms | |
| CN115430154B (en) | Game AI training method and system for different players | |
| CN113144605B (en) | User behavior simulation method and device, electronic equipment and storage medium |
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 |