Zone clothing ecological detection method and device, storage medium and electronic equipment

Abstract

The invention discloses a district suit ecological detection method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining game data of a plurality of district suits in history, determining each index set for different game behaviors in advance, and determining each statistical value corresponding to each index according to each game data; dividing each game data according to each statistical value corresponding to each index to construct a district service ecological decision tree, determining a first information entropy corresponding to each statistical value, and determining an evaluation standard value corresponding to each index according to the first information entropy corresponding to each statistical value. And according to the evaluation standard value corresponding to each index, determining a district clothing ecological detection result. According to the method, the ecological decision-making tree of the district clothes is constructed based on the statistical values corresponding to the indexes, so that the influence degree of the indexes on the ecology of the district clothes can be better determined, the evaluation standard values of the indexes can be quickly determined, and the ecological balance of the district clothes can be better maintained.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, storage medium and electronic device for detecting the ecology of a server. Background Art

[0002] With the continuous development of technology, games are developing faster and faster, and there are more and more game players.

[0003] At present, players are usually assigned to different servers to play games in order to disperse the number of players and reduce the load on the server. The server may be a server for the game, and different servers may correspond to different servers. However, the ecology of the server may be unbalanced. For example, the game is divided into camp A and camp B. There are more players belonging to camp A in the server than to camp B. As a result, when both camps perform game tasks to obtain game resources, the players in camp A in the game obtain more game resources than the players in camp B, resulting in a decrease in the game experience of the players in camp B. An unbalanced server ecology will lead to a decrease in the game experience of the players in the server and affect the sustainable development of the game. Therefore, how to detect the ecology of the server to ensure the balance of the server ecology is a very important issue.

[0004] Based on this, this manual provides a method for detecting the ecological environment of a server. Summary of the invention

[0005] This specification provides a zone and service ecology detection method, device, storage medium and electronic device to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This manual provides a method for detecting the ecological environment of a server, including:

[0008] Get historical game data of several servers;

[0009] Determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data;

[0010] According to the statistical values ​​corresponding to the indicators, the game data are divided to construct a regional server ecological decision tree, and the first information entropy corresponding to the statistical values ​​is determined;

[0011] Determine the evaluation standard values ​​corresponding to the indicators respectively according to the first information entropies corresponding to the statistical values ​​respectively;

[0012] The ecological detection results of the area and service are determined according to the evaluation standard values ​​corresponding to each of the indicators.

[0013] Optionally, the game data are divided according to the statistical values ​​corresponding to the indicators to construct a regional server ecological decision tree, specifically including:

[0014] Using the game data as training samples and as root nodes;

[0015] Determine the zone and server states corresponding to each of the game data, and use them as the first annotations corresponding to each of the training samples;

[0016] Determine the information gain entropy corresponding to each indicator according to each first annotation and each statistical value corresponding to each indicator;

[0017] Dividing each training sample included in the root node according to each information gain entropy to obtain each child node of the root node;

[0018] For each child node, the child node is re-determined as the root node to continue dividing the re-determined root node until the training samples included in each divided child node meet the preset conditions, and the regional service ecological decision tree is obtained.

[0019] Optionally, determining the information gain entropy corresponding to each indicator respectively according to each first annotation and each statistical value corresponding to each indicator respectively includes:

[0020] According to each first annotation, for each indicator, determine a second annotation corresponding to the indicator;

[0021] Determine a second information entropy corresponding to the indicator according to the second annotation and each statistical value corresponding to the indicator;

[0022] The original information entropy corresponding to the root node is determined, and the information gain entropy corresponding to the indicator is determined according to the original information entropy and the second information entropy.

[0023] Optionally, determining a second information entropy corresponding to the indicator according to the second annotation and each statistical value corresponding to the indicator specifically includes:

[0024] According to the second annotation, for each statistical value corresponding to the indicator, determine a third annotation corresponding to the statistical value;

[0025] Determining, according to the third annotation, a first information entropy corresponding to the statistical value;

[0026] According to the first information entropy corresponding to each statistical value of the indicator, the second information entropy corresponding to the indicator is determined.

[0027] Optionally, dividing each training sample included in the root node according to each information gain entropy to obtain each child node of the root node specifically includes:

[0028] According to each information gain entropy, determine the index corresponding to the maximum information gain entropy and use it as the segmentation index;

[0029] Determine the statistical values ​​corresponding to the segmentation index and use them as the candidate values;

[0030] Determine the first information entropy corresponding to each of the candidate values;

[0031] According to the first information entropies corresponding to the candidate values, respectively, determining the candidate value corresponding to the minimum first information entropy and using it as the segmentation value;

[0032] The training samples included in the root node are divided according to the segmentation index and the segmentation value to obtain child nodes of the root node.

[0033] Optionally, determining the evaluation standard values ​​corresponding to the indicators respectively according to the first information entropies respectively corresponding to the statistical values ​​specifically includes:

[0034] For each indicator, determine the statistical values ​​corresponding to the indicator;

[0035] According to the first information entropy corresponding to each statistical value of the indicator, the statistical value corresponding to the minimum first information entropy is determined and used as the evaluation standard value corresponding to the indicator.

[0036] Optionally, the method further comprises:

[0037] Get the game data of the server to be tested;

[0038] Inputting the game data of the server to be detected into the server ecological decision tree to determine the server status corresponding to the server to be detected;

[0039] The zone and server status is displayed to the operator.

[0040] This specification provides a zone and server ecological detection device, including:

[0041] The acquisition module is used to obtain historical game data of several servers;

[0042] A first determination module is used to determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data;

[0043] A construction module, for dividing the game data according to the statistical values ​​corresponding to the indicators, so as to construct a zone and server ecological decision tree, and determine the first information entropy corresponding to the statistical values;

[0044] A second determination module is used to determine the evaluation standard value corresponding to each of the indicators according to the first information entropy corresponding to each of the statistical values;

[0045] The third determination module is used to determine the ecological detection result of the area server according to the evaluation standard values ​​corresponding to the respective indicators.

[0046] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned area and service ecology detection method is implemented.

[0047] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned area service ecology detection method when executing the program.

[0048] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0049] The regional service ecology detection method provided in this specification obtains the historical game data of several regional services, determines the various indicators pre-set for different game behaviors, and determines the statistical values ​​corresponding to the various indicators based on the various game data. According to the statistical values ​​corresponding to the various indicators, the various game data are divided to construct a regional service ecology decision tree, and the first information entropy corresponding to the various statistical values ​​is determined. According to the first information entropy corresponding to the various statistical values, the evaluation standard values ​​corresponding to the various indicators are determined. According to the evaluation standard values ​​corresponding to the various indicators, the regional service ecology detection results are determined.

[0050] It can be seen from the above method that when the application detects the area and service ecology, it obtains the historical game data of several areas and services, determines the various indicators pre-set for different game behaviors, and determines the statistical values ​​corresponding to each indicator based on each game data. According to the statistical values ​​corresponding to each indicator, each game data is divided to construct an area and service ecology decision tree, and the first information entropy corresponding to each statistical value is determined, and the evaluation standard value corresponding to each indicator is determined according to the first information entropy corresponding to each statistical value. According to the evaluation standard value corresponding to each indicator, the area and service ecology detection results are determined. By constructing an area and service ecology decision tree based on the statistical values ​​corresponding to each indicator, the degree of influence of each indicator on the area and service ecology can be better determined, and the evaluation standard value of each indicator can also be quickly determined, so as to better maintain the ecological balance of the area and service. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0052] Figure 1 This is a flow chart of a regional service ecological detection method provided in this manual;

[0053] Figure 2 This is a schematic diagram of a regional service ecological decision tree provided in this specification;

[0054] Figure 3 This is a schematic diagram of the structure of a regional service ecological detection device provided in this manual;

[0055] Figure 4 A method corresponding to the Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0057] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0058] Figure 1 The following is a flow chart of a regional service ecological detection method provided in this specification, which includes the following steps:

[0059] S100: Obtain historical game data of several regions and servers.

[0060] In this specification, the device used to detect the ecology of the regional service can obtain the historical game data of several regional services. Among them, the device used to detect the ecology of the regional service can be a server, or it can be an electronic device such as a desktop computer, a laptop computer, etc. For the convenience of description, the regional service ecology detection method provided in this specification is described below with the server as the execution subject. The above-mentioned regional service can be a server for the game, and each game can have multiple regional services, and each regional service is an independent game world. The regional service can be divided according to region, language or version. Players can choose different servers to play the same game, that is, players can choose any one or more regional services to play the game. There are several players in each regional service. The number of regional services corresponding to a specific game is not specifically limited in this specification, and the number of regional services can be set by the game developer. The above-mentioned game can be any type of game, and the specific type of game is not specifically limited in this specification.

[0061] The game data may be historical data for each zone and server, and each zone and server may correspond to at least one game data. In addition, the game data may also be data for different historical time periods for each zone and server, which is not specifically limited in this specification. The game data may be data generated by all players in the zone and server during the game process, and the game data may include player activity data, player payment data, player behavior data, and activity data. The player activity data may include login time, cumulative login time, cumulative login days, and login times. The player payment data may include the number of recharges, the amount of recharges, and the time of recharge. The player behavior data may include the player's game level, task completion time, task execution results, the number of tasks, and game operation data. The game operation data includes the strength of the player pressing the device during the execution of the game task, the position and perspective of the virtual character in the game, etc. The virtual character is a character in the game, and each player in the game has a corresponding game character, that is, a virtual character. The virtual character may be pre-selected by the player. The position or perspective of the virtual character is the position of the virtual character in the game scene or the perspective corresponding to the virtual character. The activity data may include the number of activities, the type of activity, the number of participants, the time of the activity, etc.

[0062] Of course, the game data may also include other game data such as device information, account information and player information, which are not specifically limited in this specification. The device information is the information corresponding to the device used by the player each time he logs into the game in history. The device information includes device identification, kernel, memory and central processing unit (CPU) information. Every time a player logs into the game, the information of the device used by the player to log into the game, i.e., device information, will be recorded. The account information is the information corresponding to the game account of the player each time he logs into the game. The account information may include account name and account identification. The above player information may include game level, game experience value and winning rate, etc.

[0063] S102: Determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data.

[0064] In this specification, the server may determine the various indicators pre-set for different game behaviors, and determine the statistical values ​​corresponding to each indicator according to each game data. Among them, the above-mentioned game behaviors may include login behaviors, payment behaviors, and of course, social behaviors, which are not specifically limited in this specification. The indicators set for login behavior may include at least one of player activity and player retention time. Of course, when the game is a multi-camp and multi-professional game, that is, each player has a corresponding game profession and also has a camp to which he belongs, the indicators set for login behavior may also include the number of people in each camp and the number of people in each game profession. The indicators set for payment behavior may include at least one of the payment rate and the number of paying people, wherein the number of paying people may include the number of people at different payment levels, and the payment level may be pre-set, and different amounts correspond to different payment levels. The more the amount recharged by the player, the higher the payment level to which the player belongs. Conversely, the less the amount recharged by the player, the smaller the payment level to which the player belongs. The indicators set for social behavior may include the number of social times. It should be noted that the above-mentioned indicators are pre-set for different game behaviors, and this specification does not specifically limit what indicators the indicators are.

[0065] In this specification, each indicator has at least one statistical value, which can be the value of the indicator, that is, each indicator can have at least one value. Each statistical value can be determined by the server directly based on the game data, that is, the above-mentioned game data can also include each indicator data, that is, the value corresponding to each indicator. Based on this, when determining the statistical values ​​corresponding to each indicator according to each game data, the server can determine the first values ​​corresponding to each indicator in the game data for each game data. Afterwards, for each indicator, the statistical values ​​corresponding to the indicator are determined according to the first values ​​corresponding to the indicator. Among them, each game data includes the first value corresponding to each indicator, and the number of the first value of each indicator is equal to the number of game data.

[0066] In addition, each statistical value can be obtained by the server performing statistical calculations on the game data, that is, the server cannot directly obtain the first values ​​corresponding to each indicator from the game data. Therefore, when determining the statistical values ​​corresponding to each indicator according to each game data, the server can determine the first values ​​corresponding to the indicator according to each game data, and determine the statistical values ​​corresponding to the indicator according to the first values ​​corresponding to the indicator. Among them, the server can determine a value of the indicator based on each game data, that is, the first value. That is, the first value of the indicator can be determined based on any game data. Therefore, when determining the first values ​​corresponding to the indicator according to each game data, the server can perform statistical calculations on the game data for each game data to determine the first value corresponding to the indicator. For example, assuming that there are game data 1 to 4 and indicators A to C, assuming that for indicator A, the server can perform statistical calculations on game data 1 for each game data, assuming that for game data 1, determine the first value corresponding to indicator A, that is, the first value A. Therefore, the server can obtain the first values ​​corresponding to indicator A, namely, the first values ​​A~D. The first value B is obtained based on game data 2, the first value C is obtained based on game data 3, and the first value D is obtained based on game data 4.

[0067] Specifically, taking the payment rate as an example, the server can determine the number of players in the area and service corresponding to each game data, and determine the number of players who have performed payment behavior, and use it as the number of paid people, determine the ratio between the number of players and the number of paid people, and use it as the first value corresponding to the payment rate indicator. Taking the retention time as an example, the server can determine the retention time of each player in the area and service corresponding to the game data for each game data, determine the average of each retention time, and use it as the first value corresponding to the retention time indicator. Among them, the retention time of each player can be the time difference between the player's registration time and the logout time. The logout time can be the time when the player last logged into the game. The specific determination process of each first value of other indicators is also similar to the determination process of each first value of the above-mentioned payment rate or retention time, and will not be described one by one here. Of course, the server can also use any existing means to determine the first values ​​corresponding to each indicator, and this specification does not make specific restrictions.

[0068] The above-mentioned indicator may correspond to multiple first values, and each statistical value of the indicator is obtained based on each first value, and each statistical value of the indicator is different. When determining each statistical value corresponding to the indicator according to each first value corresponding to the indicator, the server may divide each first value corresponding to the indicator to obtain each first combination. The first values ​​in each first combination are the same. For each first combination, a first value is randomly selected from the first combination and used as the statistical value corresponding to the indicator. For example, assuming that the indicator is indicator O, indicator O corresponds to first values ​​1 to 5, namely A, B, A, C, B. Therefore, the server can divide the 5 first values ​​of indicator O, that is, divide the first value 1 (ie A) and the first value 3 (ie A) into one group, divide the first value 2 (ie B) and the first value 5 (ie B) into one group, and divide the first value 4 (ie C) into one group, thereby obtaining first combinations 1 to 3, and the first values ​​in each divided first combination are the same. Afterwards, for each first combination, assuming that for the first combination 1, a first value is randomly selected from the first group 1 and used as the statistical value corresponding to the indicator, that is, A. According to the above method, the statistical values ​​selected from the first combination 2 and the first combination 3 are B and C, so the statistical values ​​corresponding to the indicator A are A, B and C.

[0069] In addition, the server may also randomly select a first value from the first values ​​corresponding to the indicator as the second value, and then continue to randomly select a first value from the other first values ​​except the first value that is the same as the second value as the second value, until the other first values ​​except the first value that is the same as the second value are the same, continue to randomly select a first value from the other first values ​​at this time as the second value. All second values ​​are used as statistical values ​​of the indicator. Continuing with the above example, the server can randomly select a first value from the first values ​​1 to 5 corresponding to indicator A as the second value, assuming that the first value 1 (i.e. A) is selected. Afterwards, a first value is randomly selected from the first values ​​other than the first value that is the same as the second value, that is, from the first value 2 (i.e., B), the first value 4 (i.e., C), and the first value 5 (i.e., B), and used as the second value. Assuming that the first value 4 is selected, the first values ​​other than the first value that is the same as the second value are only the first value 2 (i.e., B) and the first value 2 (i.e., B), and the two are the same, so the server can directly randomly select a first value from the first value 2 (i.e., B) and the first value 2 (i.e., B), and use it as the second value. All the second values ​​are then used as the statistical values ​​of the indicator, i.e., A, B, and C.

[0070] S104: Divide the game data according to the statistical values ​​corresponding to the indicators to construct a zone and server ecological decision tree, and determine the first information entropy corresponding to the statistical values.

[0071] In this specification, the server may divide each game data according to each statistical value corresponding to each indicator to construct a zone service ecological decision tree, and determine the first information entropy corresponding to each statistical value. Among them, the above-mentioned zone service ecological decision tree may include several nodes, and the zone service ecological decision tree is a decision tree with each game data as the root node. Specifically, the server may determine the zone service status corresponding to each game data. According to the statistical values ​​corresponding to each indicator and each zone service status, each game data is divided to construct a zone service ecological decision tree. The above-mentioned zone service status may be one of balanced and unbalanced. Each game data corresponds to a zone service status. The zone service status may be pre-marked by the operator, or it may be determined by any existing means, and this specification does not make specific restrictions.

[0072] In this specification, when the game data are divided according to the statistical values ​​corresponding to the indicators to construct the zone service ecological decision tree, first, the server can use the game data as training samples and as the root node. Afterwards, the zone service status corresponding to each game data is determined, and used as the first annotation corresponding to each training sample. Then, the server can determine the information gain entropy corresponding to each indicator according to each first annotation and each statistical value corresponding to each indicator. According to each information gain entropy, the training samples included in the root node are divided to obtain each child node of the root node. Afterwards, for each child node, the child node is re-used as the root node to continue to divide the re-determined root node until the training samples included in each divided child node meet the preset conditions, and the zone service ecological decision tree is obtained.

[0073] Among them, the above-mentioned preset conditions may be pre-set by the server, and the preset condition may be that the first annotations of the training samples included in the subnodes are the same. Of course, the preset condition may also be that the number of training samples included in the subnodes reaches a preset threshold, which is not specifically limited in this specification. For the sake of convenience, the following explanation is given by taking the preset condition that the first annotations of the training samples included in the subnodes are the same as an example. Therefore, when the first annotations of the training samples included in each divided subnode are the same, that is, for any divided subnode, the first annotations of the training samples included in the subnode are the same, at this time, it means that the construction of the district service ecological decision tree is completed, and the server can obtain the district service ecological decision tree. The root node of the district service ecological decision tree includes various game data, and each subnode includes a number of training samples. The first annotations of the training samples included in the leaf nodes are the same.

[0074] In this specification, when the information gain entropy corresponding to each indicator is determined according to each first annotation and each statistical value corresponding to each indicator, the server can determine the second annotation corresponding to the indicator for each indicator according to each first annotation. Determine the second information entropy corresponding to the indicator according to the second annotation and each statistical value corresponding to the indicator. Determine the original information entropy corresponding to the root node, and determine the information gain entropy corresponding to the indicator according to the original information entropy and the second information entropy. Among them, the above second annotation is the annotation corresponding to each indicator, that is, in each first annotation, each indicator can correspond to several second annotations. Since the number of first annotations is the same as the number of training samples, and the values ​​corresponding to each indicator can be determined based on each training sample, the number of second annotations is the same as the number of first annotations. In addition, the first annotation is the same as the second annotation. For example, assuming that there are indicators A~C and first annotations 1~10, for each indicator, assuming that for indicator A, the second annotation corresponding to indicator A is the first annotation 1~10.

[0075] In this specification, when the second information entropy corresponding to the indicator is determined according to the second annotation and each statistical value corresponding to the indicator, the server may determine the third annotation corresponding to the statistical value according to the second annotation for each statistical value corresponding to the indicator. According to the third annotation, the first information entropy corresponding to the statistical value is determined. According to the first information entropy corresponding to each statistical value of the indicator, the second information entropy corresponding to the indicator is determined. Among them, the third annotation is the annotation corresponding to each statistical value, and the sum of the number of third annotations corresponding to each statistical value is the number of the second annotation (i.e., the first annotation). When the third annotation corresponding to each statistical value corresponding to the indicator is determined according to the second annotation, the server may determine the second annotation corresponding to the game data as the third annotation of the statistical value for each statistical value corresponding to the indicator and for each game data corresponding to the second annotation, when the first value of the indicator of the game data is the statistical value. For example, assuming that the second annotation corresponding to indicator A can be second annotations 1 to 10, the game data corresponding to the second annotation can be game data 1 to 10, and the statistical value of the indicator A can be statistical values ​​1 to 3, then the server can, based on the second annotations 1 to 10, for each statistical value corresponding to indicator A, assume that for statistical value 1, and for each game data corresponding to the second annotations 1 to 10, assume that for game data 1, and then assume that the first value of indicator A of game data 1 is statistical value 1, when the first value of indicator A of game data 1 is statistical value 1, determine that the second annotation 1 corresponding to game data 1 is the third annotation of the statistical value 1. Other statistical values ​​can also determine their corresponding third annotations in the above manner, and the specific process will not be repeated here.

[0076] When determining the first information entropy corresponding to the statistical value according to the third annotation, the number of the third annotation is determined and used as the first number. The third annotations are grouped to obtain second combinations, and the third annotations included in each second combination are the same. For each second combination, the second number of third annotations included in the second combination is determined. The ratio of the second number to the first number is determined and used as the probability of the second combination. According to the probabilities corresponding to each second combination, the first information entropy corresponding to the statistical value is determined. Among them, when determining the first information entropy of the statistical value according to the probabilities corresponding to each second combination, the server can use the following formula for calculation:

[0077]

[0078] Where H represents the first information entropy, n represents the number of second combinations, and p i represents the probability of the i-th second combination, b is the base of the logarithm, which is usually 2. Of course, the natural logarithm can also be used, and this manual does not make any specific limitation. p represents n second combinations i log b p i The sum of the values ​​of .

[0079] When determining the second information entropy corresponding to the indicator according to the first information entropy corresponding to each statistical value of the indicator, the server can determine the sum of the first information entropies corresponding to each statistical value of the indicator, and use it as the second information entropy corresponding to the indicator. In addition, the server can also determine the ratio of the number of third annotations corresponding to the statistical value to the number of second annotations corresponding to the indicator, and use it as the first weight corresponding to the statistical value. According to the first weight, the first information entropy corresponding to the statistical value is weighted. Determine the sum of the weighted first information entropies corresponding to each statistical value of the indicator, and use it as the second information entropy corresponding to the indicator. Specifically, the following formula can be used for calculation:

[0080]

[0081] Among them, H 总 represents the second information entropy, s represents the number of statistical values, and w j represents the first weight corresponding to the jth statistical value, H j represents the first information entropy corresponding to the jth statistical value. j H j represents the weighted first information entropy of the j-th statistical value, The sum of the weighted first information entropy of s statistical values ​​is the second information entropy.

[0082] In this specification, when determining the original information entropy corresponding to the root node, the number of first annotations of the training samples included in the root node is determined, and as the original number, the first annotations of the training samples included in the root node are divided to obtain each third combination, and the first annotations included in each third combination are the same. For each third combination, the third number of first annotations included in the third combination is determined, and the ratio of the third number to the original number is determined and used as the probability of the third combination. According to the probabilities corresponding to each third combination, the original information entropy corresponding to the root node is determined. The specific process is similar to the process of determining the first information entropy, and will not be repeated here.

[0083] Based on this, when determining the information gain entropy corresponding to the indicator based on the original information entropy and the second information entropy, the server can determine the difference between the original information entropy and the second information entropy, and use it as the information gain entropy corresponding to the indicator.

[0084] In this specification, when the training samples included in the root node are divided according to the information gain entropies to obtain the child nodes of the root node, the server can determine the index corresponding to the maximum information gain entropy according to the information gain entropies, and use it as the segmentation index. Determine the statistical values ​​corresponding to the segmentation index and use them as the candidate values. Determine the first information entropy corresponding to each candidate value. According to the first information entropy corresponding to each candidate value, determine the candidate value corresponding to the minimum first information entropy and use it as the segmentation value. According to the segmentation index and the segmentation value, the training samples included in the root node are divided to obtain the child nodes of the root node. Among them, the segmentation index is the index corresponding to the maximum information gain entropy. The larger the information gain entropy of a certain indicator, the greater the impact of the indicator on the area service ecology. Conversely, the smaller the information gain entropy of the indicator, the smaller the impact of the indicator on the area service ecology. The segmentation value is the candidate value corresponding to the smallest first information entropy. The smaller the first information entropy of a candidate value, the higher the similarity of the first annotations of the training samples contained in the child nodes obtained after the candidate value is segmented, and the higher the purity of the child node. Conversely, the larger the first information entropy of the candidate value, the lower the similarity of the first annotations of the training samples contained in the child nodes obtained after the candidate value is segmented, and the lower the purity of the child node.

[0085] When the training samples included in the root node are divided according to the segmentation index and the segmentation value to obtain the child nodes of the root node, the server can use each training sample included in the root node as a segmentation sample when the first value corresponding to the segmentation index of the training sample is the segmentation value. Each segmentation sample is divided into a child node of the root node, and other training samples except the segmentation samples in the training samples included in the root node are divided into another child node of the root node.

[0086] In this specification, for each child node, the child node is re-used as the root node to continue to divide the re-determined root node until the training samples included in each divided child node meet the preset conditions, and when the district service ecological decision tree is obtained, the server can re-use the child node as the root node for each child node, and then re-determine the information gain entropy corresponding to each indicator according to the first annotation of the training sample included in the re-determined root node and the statistical values ​​corresponding to each indicator. According to the information gain entropy corresponding to each re-determined indicator, the training samples included in the re-determined root node are divided until the training samples included in each divided child node meet the preset conditions, and the district service ecological decision tree is obtained.

[0087] For example, Figure 2 As shown, Figure 2 This is a schematic diagram of a regional service ecological decision tree provided in this specification. Figure 2 The decision tree shown includes nodes 1 to 5. Assuming that there are game data 1 to 10 and zone and server ecosystems 1 to 10, and assuming that node 1 is the root node, the server can use game data 1 to 10 as training samples 1 to 10 and as the root node, that is, node 1. Afterwards, the zone and server ecosystems 1 to 10 are used as the first annotations 1 to 10. Afterwards, the server can determine the information gain entropy corresponding to each indicator according to the first annotations 1 to 10 and the statistical values ​​corresponding to each indicator. According to each information gain entropy, the training samples 1 to 10 included in node 1 are divided to obtain the child nodes of the root node, assuming that they are nodes 2 and 3, and node 2 includes training samples 1 to 3, and the first annotations of training samples 1 to 3 are the same, so node 2 is a leaf node. Afterwards, for each child node, since the first annotations of training samples 1 to 3 in node 2 are the same, for node 3, node 3 is re-used as the root node, and then the information gain entropy corresponding to each indicator is re-determined according to the first annotations of the training samples (i.e., training samples 4 to 10) included in node 3 and the statistical values ​​corresponding to each indicator. According to the re-determined information gain entropy corresponding to each indicator, the training samples 4 to 10 included in node 3 are divided to obtain the child nodes of node 3, assuming that they are nodes 4 and 5, and the first annotations of training samples 4 to 7 included in node 4 are the same, and the first annotations of training samples 8 to 10 included in node 5 are the same, so nodes 4 and 5 are leaf nodes. At this time, the training samples included in each divided child node meet the preset conditions, so the server can obtain a regional service ecological decision tree with node 1 as the root node and nodes 2, 4 and 5 as leaf nodes.

[0088] S106: Determine the evaluation standard values ​​corresponding to the indicators respectively according to the first information entropies corresponding to the statistical values ​​respectively.

[0089] In this specification, the server may determine the evaluation standard value corresponding to each indicator according to the first information entropy corresponding to each statistical value. Specifically, the server may determine the statistical values ​​corresponding to each indicator for each indicator. According to the first information entropy corresponding to each statistical value of the indicator, the statistical value corresponding to the minimum first information entropy is determined and used as the evaluation standard value corresponding to the indicator. Among them, the evaluation standard value is the candidate value corresponding to the minimum first information. The smaller the first information entropy of a certain statistical value, the more stable the detection result obtained after evaluating the game data using the statistical value, the higher the purity, and the higher the accuracy. Conversely, the larger the first information entropy of a certain statistical value, the more unstable the detection result obtained after evaluating the game data using the statistical value, the lower the purity, and the lower the accuracy. The above-mentioned evaluation standard value is the threshold value corresponding to the indicator. When the value of the indicator of the game data reaches the evaluation standard value, the detection result of the game data may be the first result, and when the value of the indicator of the game data does not reach the evaluation standard value, the detection result of the game data may be the second result. The first result or the second result may be a balanced or unbalanced zone.

[0090] S108: Determine the ecological detection result of the area and service based on the evaluation standard values ​​corresponding to the indicators.

[0091] In this specification, the server can determine the zone service ecology detection result according to the evaluation standard values ​​corresponding to each indicator. Specifically, the server can directly use the evaluation standard values ​​corresponding to each indicator as the zone service ecology detection result, and then display the zone service ecology detection result to the operator, so that the operator can analyze the zone service ecology according to the evaluation standard values ​​corresponding to each indicator, and generate an operation strategy to better maintain the zone service ecology balance.

[0092] It can be seen from the above method that when the application detects the zone and service ecology, the server can obtain the historical game data of several zones and services, determine the various indicators pre-set for different game behaviors, and determine the statistical values ​​corresponding to each indicator based on each game data. According to the statistical values ​​corresponding to each indicator, each game data is divided to construct a zone and service ecology decision tree, and the first information entropy corresponding to each statistical value is determined, and the evaluation standard value corresponding to each indicator is determined according to the first information entropy corresponding to each statistical value. According to the evaluation standard value corresponding to each indicator, the zone and service ecology detection results are determined. By constructing a zone and service ecology decision tree based on the statistical values ​​corresponding to each indicator, the degree of influence of each indicator on the zone and service ecology can be better determined, and the evaluation standard value of each indicator can also be quickly determined, so as to better maintain the balance of the zone and service ecology.

[0093] In this specification, the server can also obtain game data of the area and server to be detected, and display the game data to the operator, so that the operator can determine the area and server status corresponding to the area and server to be detected based on the evaluation standard values ​​of each indicator and the game data.

[0094] In this specification, after obtaining the zone and server ecological decision tree, the server can also obtain the game data of the zone and server to be detected. The game data of the zone and server to be detected is input into the zone and server ecological decision tree to determine the zone and server status corresponding to the zone and server to be detected. The zone and server status is displayed to the operator. Among them, the zone and server to be detected can be any zone and server in the game, and the game data of the zone and server to be detected can be the data generated when the players play the game in any time period of the zone and server to be detected. If the game data of the zone and server to be detected includes the values ​​corresponding to each indicator, the server can directly input the game data of the zone and server to be detected into the zone and server ecological decision tree to determine the zone and server status corresponding to the zone and server to be detected. If the game data of the zone and server to be detected does not include the values ​​corresponding to each indicator, the server can determine the value corresponding to the indicator for each indicator based on the game data of the zone and server to be detected, and input the values ​​corresponding to each indicator and the game data of the zone and server to be detected into the zone and server ecological decision tree together to determine the zone and server status corresponding to the zone and server to be detected. The process of determining the value corresponding to the indicator based on the game data of the area to be detected is similar to the process of determining the statistical values ​​corresponding to each indicator in the above step S102, and will not be repeated here.

[0095] When the game data of the server to be detected is input into the server ecological decision tree to determine the server status corresponding to the server to be detected, starting from the root node of the server ecological decision tree, for each child node of the root node, it is determined whether the value of the segmentation index of the child node in the game data of the server to be detected is a segmentation value. If so, when the child node is a leaf node, the first annotation of the training sample included in the child node is used as the server status of the server to be detected. When the child node is not a leaf node, the child node is used as the root node again, and each child node of the new root node is continuously determined to determine whether the value of the segmentation index of the child node in the game data of the server to be detected is a segmentation value, until the child node is a leaf node, and the first annotation of the training sample included in the child node is used as the server status of the server to be detected.

[0096] If not, continue to determine whether the value of the segmentation index of the subnode in the game data of the server to be detected is a segmentation value for the subnodes of the root node except the subnode, until the subnode is a leaf node, and use the first annotation of the training sample included in the subnode as the server status of the server to be detected. The specific process is as above and will not be repeated here.

[0097] For example, Figure 2Taking the server ecological decision tree shown as an example, assuming that the game data of the server to be detected is data K, starting from node 1 of the server ecological decision tree, for each child node of node 1 (i.e., node 2 and node 3) in turn, assuming that for node 2, it is determined whether the value of the segmentation index of node 2 in data K is the segmentation value. Assuming that the value of the segmentation index of node 2 in data K is the segmentation value, when node 2 is a leaf node, it is obviously yes, so the server can directly use the first annotation of the training sample included in node 2 as the server status of the server to be detected.

[0098] Assume again that the value of the segmentation index of node 2 in data K is not the segmentation value, so the server can continue to target the child nodes of node 1 except node 2, that is, node 3, to determine whether the value of the segmentation index of node 3 in data K is the segmentation value. Assume that the value of the segmentation index of node 3 in data K is the segmentation value. Therefore, when node 3 is a leaf node, the first annotation of the training sample included in node 3 is used as the service status of the service to be detected. Obviously, node 3 is not a leaf node. Therefore, when node 3 is not a leaf node, node 3 is re-used as the root node, and each child node of node 3 (that is, node 4 and node 5) is continued to be targeted. Assume that node 4 is continued to be targeted, and whether the value of the segmentation index of node 4 in data K is the segmentation value is continued to be determined. Assume that the value of the segmentation index of node 4 in data K is the segmentation value. Node 4 is a leaf node, so the server can use the first annotation of the training sample included in node 4 as the service status of the service to be detected.

[0099] In this specification, the above-mentioned zone server status may be one of zone server balance and zone server imbalance. The server may display the zone server status of the above-mentioned zone server to be detected to the operator, so that the operator can generate an operation strategy and execute the operation strategy when the zone server status is zone server imbalance to ensure the zone server balance of the zone server to be detected.

[0100] In addition, when the zone and server status is zone and server imbalance, the server can determine the imbalance cause of the zone and server to be detected, and according to the imbalance cause, determine the target strategy from the pre-set strategy library, and execute the target strategy in the zone and server to be detected. Among them, the above-mentioned imbalance cause can be at least one of the indicators. Since the above-mentioned zone and server status can be obtained based on the zone and server ecological decision tree, that is, when the game data of the zone and server to be detected hits a leaf node in the zone and server ecological decision tree, the first annotation of the training sample included in the hit leaf node is used as the zone and server status of the zone and server to be detected. Therefore, the server can generate a target path from the root node to the hit leaf node based on the zone and server ecological decision tree, and use the segmentation index and segmentation value of each node in each target path as the imbalance cause. In addition, the above-mentioned imbalance cause can also be determined by the operator based on the game data of the zone and server to be detected and the evaluation standard values ​​of each indicator, and uploaded to the server. The above-mentioned strategy library may be pre-set by the server, and the strategy library includes several strategies, which may be pre-uploaded by the operator, and the strategy may be to increase the activities of obtaining game resources for free, increase the rewards for completing game tasks, etc. There is a corresponding relationship between each strategy and the imbalance reason, and the server can determine the target strategy corresponding to the imbalance reason from the strategy library according to each corresponding relationship.

[0101] In this specification, the above statistical value can be a range of values ​​in addition to a single value. Therefore, when determining the statistical values ​​corresponding to the indicator according to the first values ​​corresponding to the indicator in the above step S102, the server can randomly generate several entry ranges according to the first values ​​corresponding to the indicator, and use them as the statistical values ​​corresponding to the indicator. Of course, the server can display the first values ​​corresponding to the indicator to the operator so that the operator can determine the several value ranges corresponding to the indicator and upload them to the server. In response to the upload operation of the operator, the server can determine the several value ranges corresponding to the indicator and use them as the statistical values ​​of the indicator.

[0102] In this specification, if there are more than two statistical values ​​for the segmentation index of the above-mentioned node, and the third annotations of its statistical values ​​other than the segmentation value of the node are different, the segmentation index may continue to serve as the segmentation index of other nodes in the future, so the above-mentioned index may have at least one first information entropy, and the index may have at least one evaluation standard value. Based on this, in the above-mentioned step S108, the server can determine the evaluation standard values ​​corresponding to each indicator for each indicator. According to each evaluation standard value, the first interval and the second interval corresponding to the indicator are determined, the first interval represents the balance of the server, and the second interval represents the imbalance of the server. That is, when the value of the indicator of the game data of a server is within the first interval, it means that the server status of the server is balanced, and when the value of the indicator of the game data of the server is within the second interval, it means that the server status of the server is unbalanced.

[0103] In this specification, the server may also determine the importance of each indicator according to the zone service ecological decision tree. Specifically, the server may determine the importance of each indicator according to the information gain entropy of each indicator. The greater the information gain entropy of the indicator, the greater the importance of the indicator. Conversely, the smaller the information gain entropy of the indicator, the smaller the importance of the indicator.

[0104] In this specification, in the above step S100, the server can obtain the original data of several regions and servers in history, and process the original data to obtain processed data as game data. The above processing includes data cleaning, missing value supplementation, etc.

[0105] The above are one or more implementation methods of this specification. Based on the same idea, this specification also provides a corresponding area service ecological detection device, such as Figure 3 shown.

[0106] Figure 3 A schematic diagram of a zone and server ecological detection device provided for this specification includes:

[0107] An acquisition module 200 is used to acquire historical game data of several servers;

[0108] The first determination module 202 is used to determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data;

[0109] A construction module 204 is used to divide the game data according to the statistical values ​​corresponding to the indicators to construct a zone and server ecological decision tree and determine the first information entropy corresponding to the statistical values;

[0110] A second determination module 206 is used to determine the evaluation standard value corresponding to each of the indicators according to the first information entropy corresponding to each of the statistical values;

[0111] The third determination module 208 is used to determine the area server ecological detection result according to the evaluation standard values ​​corresponding to the indicators.

[0112] Optionally, the construction module 204 is specifically used to use the game data as training samples and as root nodes; determine the zone and server states corresponding to the game data and use them as the first labels corresponding to the training samples; determine the information gain entropy corresponding to the indicators according to the first labels and the statistical values ​​corresponding to the indicators; divide the training samples included in the root node according to the information gain entropy to obtain child nodes of the root node; for each child node, re-use the child node as the root node to continue dividing the re-determined root node, until the training samples included in each divided child node meet the preset conditions, and obtain the zone and server ecological decision tree.

[0113] Optionally, the construction module 204 is specifically used to determine, for each indicator, a second annotation corresponding to the indicator based on each first annotation; determine a second information entropy corresponding to the indicator based on the second annotation and each statistical value corresponding to the indicator; determine the original information entropy corresponding to the root node, and determine the information gain entropy corresponding to the indicator based on the original information entropy and the second information entropy.

[0114] Optionally, the construction module 204 is specifically used to determine, according to the second annotation, for each statistical value corresponding to the indicator, a third annotation corresponding to the statistical value; according to the third annotation, determine the first information entropy corresponding to the statistical value; according to the first information entropy corresponding to each statistical value of the indicator, determine the second information entropy corresponding to the indicator.

[0115] Optionally, the construction module 204 is specifically used to determine, based on each information gain entropy, an indicator corresponding to the maximum information gain entropy, and use it as a segmentation indicator; determine each statistical value corresponding to the segmentation indicator, and use it as each candidate value; determine the first information entropy corresponding to each candidate value; based on the first information entropy corresponding to each candidate value, determine the candidate value corresponding to the minimum first information entropy, and use it as a segmentation value; based on the segmentation indicator and the segmentation value, divide each training sample included in the root node to obtain each child node of the root node.

[0116] Optionally, the second determination module 206 is specifically used to determine, for each indicator, the statistical values ​​corresponding to the indicator; determine the statistical value corresponding to the minimum first information entropy according to the first information entropy corresponding to the statistical values ​​of the indicator, and use it as the evaluation standard value corresponding to the indicator.

[0117] Optionally, the device further comprises:

[0118] The application module 210 is used to obtain the game data of the area and server to be detected; input the game data of the area and server to be detected into the area and server ecological decision tree to determine the area and server status corresponding to the area and server to be detected; and display the area and server status to the operator.

[0119] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A regional service ecology detection method is provided.

[0120] This manual also provides Figure 4 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 4 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The described area service ecological detection method.

[0121] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0122] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0123] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0124] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0125] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0126] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0127] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0131] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0132] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0134] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0136] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0137] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for detecting the ecological status of a service area, characterized in that: include: Get historical game data of several servers; Determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data; According to the statistical values ​​corresponding to the indicators, the game data are divided to construct a regional server ecological decision tree, and the first information entropy corresponding to the statistical values ​​is determined; Determine the evaluation standard values ​​corresponding to the indicators respectively according to the first information entropies corresponding to the statistical values ​​respectively; The ecological detection results of the area and service are determined according to the evaluation standard values ​​corresponding to each of the indicators.

2. The method according to claim 1, characterized in that According to the statistical values ​​corresponding to the indicators, the game data are divided to construct a regional server ecological decision tree, which specifically includes: Using the game data as training samples and as root nodes; Determine the zone and server states corresponding to each of the game data, and use them as the first annotations corresponding to each of the training samples; Determine the information gain entropy corresponding to each indicator according to each first annotation and each statistical value corresponding to each indicator; Dividing each training sample included in the root node according to each information gain entropy to obtain each child node of the root node; For each child node, the child node is re-determined as the root node to continue dividing the re-determined root node until the training samples included in each divided child node meet the preset conditions, and the regional service ecological decision tree is obtained.

3. The method according to claim 2, characterized in that Determining the information gain entropy corresponding to each indicator according to each first annotation and each statistical value corresponding to each indicator, specifically includes: According to each first annotation, for each indicator, determine a second annotation corresponding to the indicator; Determine a second information entropy corresponding to the indicator according to the second annotation and each statistical value corresponding to the indicator; The original information entropy corresponding to the root node is determined, and the information gain entropy corresponding to the indicator is determined according to the original information entropy and the second information entropy.

4. The method according to claim 3, characterized in that Determining, according to the second annotation and each statistical value corresponding to the indicator, a second information entropy corresponding to the indicator, specifically includes: According to the second annotation, for each statistical value corresponding to the indicator, determine a third annotation corresponding to the statistical value; Determining, according to the third annotation, a first information entropy corresponding to the statistical value; According to the first information entropy corresponding to each statistical value of the indicator, the second information entropy corresponding to the indicator is determined.

5. The method according to claim 2, characterized in that According to each information gain entropy, each training sample included in the root node is divided to obtain each child node of the root node, specifically including: According to each information gain entropy, determine the index corresponding to the maximum information gain entropy and use it as the segmentation index; Determine the statistical values ​​corresponding to the segmentation index and use them as the candidate values; Determine the first information entropy corresponding to each of the candidate values; According to the first information entropies corresponding to the candidate values, respectively, determining the candidate value corresponding to the minimum first information entropy and using it as the segmentation value; The training samples included in the root node are divided according to the segmentation index and the segmentation value to obtain child nodes of the root node.

6. The method according to claim 1, characterized in that Determining the evaluation standard values ​​corresponding to the indicators respectively according to the first information entropies respectively corresponding to the statistical values ​​specifically includes: For each indicator, determine the statistical values ​​corresponding to the indicator; According to the first information entropy corresponding to each statistical value of the indicator, the statistical value corresponding to the minimum first information entropy is determined and used as the evaluation standard value corresponding to the indicator.

7. The method according to claim 1, characterized in that The method further comprises: Get the game data of the server to be tested; Inputting the game data of the server to be detected into the server ecological decision tree to determine the server status corresponding to the server to be detected; The zone and server status is displayed to the operator.

8. A zone service ecological detection device, characterized in that: include: The acquisition module is used to obtain historical game data of several servers; A first determination module is used to determine various indicators pre-set for different game behaviors, and determine various statistical values ​​corresponding to the various indicators according to various game data; A construction module, for dividing the game data according to the statistical values ​​corresponding to the indicators, so as to construct a zone and server ecological decision tree, and determine the first information entropy corresponding to the statistical values; A second determination module is used to determine the evaluation standard value corresponding to each of the indicators according to the first information entropy corresponding to each of the statistical values; The third determination module is used to determine the ecological detection result of the area server according to the evaluation standard values ​​corresponding to the respective indicators.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

Images