Data analysis method and device, storage medium and electronic equipment

Abstract

The invention discloses a data analysis method and device, a storage medium and electronic equipment, and the method comprises the steps: in response to to-be-analyzed game data input by a user, determining a target algorithm in each balance algorithm according to a data type contained in the to-be-analyzed game data and a parameter type required by the balance algorithm corresponding to each preset balance index; and inputting the to-be-analyzed game data, the target algorithm and the first task cue word into a pre-configured first large language model to generate a calling code. And obtaining a calculation value according to the operation of the calling code, and determining an analysis result of the to-be-analyzed game data. In the method, the process of outputting the calling code for analyzing the to-be-analyzed game data through the first language model and determining the analysis result is an automatic execution process by applying the inference analysis capability of the large language model, and by means of the method, a user only needs to input the game data to obtain the analysis result, and the user experience is improved. The workload of the user in the game data analysis process is reduced, and the data analysis efficiency is improved.

Description

Technical Field

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

[0002] As game content and plots become richer, the types of data included in game data are also becoming richer. In games, various types of game data, such as character attribute data, equipment attribute data, skill attribute data, etc., interact with each other and jointly affect the balance of the game.

[0003] Currently, when analyzing game data to be analyzed, it mainly depends on planners' understanding of the interaction between various types of game data and the analysis of the balance of the game based on experience, which leads to low efficiency of data analysis.

[0004] Therefore, the present specification provides a data analysis method. Summary of the invention

[0005] The present specification provides a data analysis method, device, storage medium and electronic device to at least partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a data analysis method, including:

[0008] In response to the game data to be analyzed input by the user, according to the data type contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance index, determine, from each balance algorithm, a balance algorithm for analyzing the game data to be analyzed as a target algorithm;

[0009] Input the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured first language model to generate a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed;

[0010] Running the calling code to obtain the calculated value of the target algorithm;

[0011] The analysis result of the game data to be analyzed is determined according to the calculated value of the target algorithm.

[0012] Optionally, according to the data type contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator, a balance algorithm for analyzing the game data to be analyzed is determined as a target algorithm in each balance algorithm, specifically including:

[0013] Determine the parameter types required by the balancing algorithm corresponding to each preset balancing indicator;

[0014] For each preset balance indicator, determine the parameter type required by the balance algorithm corresponding to the balance indicator, and whether there is a corresponding data type in the data to be analyzed;

[0015] If so, the balance algorithm corresponding to the balance indicator is used as the target algorithm;

[0016] If not, the balance algorithm corresponding to the balance indicator is not used as the target algorithm.

[0017] Optionally, the target indicator is used to evaluate the balance of each game character, and the calculation value of the target algorithm includes the calculation results corresponding to each game character;

[0018] Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including:

[0019] Determine an expected value of the calculated value of the target algorithm according to the calculation results corresponding to the game characters in the calculated value of the target algorithm;

[0020] For each game character in the game data to be analyzed, determining a calculation result corresponding to the game character in the calculation value of the target algorithm;

[0021] When the deviation between the calculation result corresponding to the game character and the expected value of the calculation value of the target algorithm is greater than a first preset value, the game character is determined to be an unbalanced character.

[0022] Optionally, the target indicator is used to evaluate the balance of each game character, the calculation value of the target algorithm includes the calculation results corresponding to each game character, and the number of the target algorithms is multiple;

[0023] Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including:

[0024] For each target algorithm, according to the calculation results corresponding to each game character in the calculation value of the target algorithm, determine the expected value of the calculation value of the target algorithm;

[0025] For each calculation result of the calculation value of the target algorithm, when the deviation between the calculation result and the expected value of the calculation value of the target algorithm is greater than a first preset value, determining that the game character corresponding to the calculation result is a pending unbalanced character;

[0026] According to the unbalanced characters to be determined by each target algorithm, the analysis results of the game data to be analyzed are determined.

[0027] Optionally, determining the analysis result of the game data to be analyzed according to the unbalanced roles to be determined by each target algorithm specifically includes:

[0028] For each pending unbalanced role determined by each target algorithm, the number of target algorithms that determine the pending unbalanced role is counted;

[0029] When it is determined that the number of the target algorithms of the undetermined unbalanced role is greater than the second preset value, the undetermined unbalanced role is used as the unbalanced role.

[0030] Optionally, determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm specifically includes:

[0031] The calculated value of the target algorithm and the second task prompt word are input into a pre-configured second largest language model to obtain unbalanced data screened by the second largest language model from the game data to be analyzed, wherein the second task prompt word is used to prompt the second largest language model to determine abnormal calculated values ​​according to the distribution of calculated values ​​in the target algorithm, and determine unbalanced data according to the abnormal calculated values.

[0032] Optionally, the second largest language model includes multiple sub-models, each sub-model has the same function but different model parameters;

[0033] Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including:

[0034] Inputting the calculated value of the target algorithm and the second task prompt word into each sub-model of the second largest language model, and obtaining each pending imbalanced data screened by each sub-model from the game data to be analyzed;

[0035] For each determined unbalanced data to be determined, when the number of sub-models screened out for the unbalanced data to be determined is greater than a third preset value, the unbalanced data to be determined is used as unbalanced data.

[0036] This specification provides a data analysis device, the device comprising:

[0037] An input module, in response to the game data to be analyzed input by the user, determines, from among the balance algorithms, a balance algorithm for analyzing the game data to be analyzed as a target algorithm according to the type of data contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator;

[0038] A code generation module, inputting the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured large language model, and generating a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed;

[0039] A calculation value determination module runs the calling code to obtain the calculation value of the target algorithm;

[0040] The result determination module determines the analysis result of the game data to be analyzed according to the calculation value of the target algorithm.

[0041] 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 data analysis method is implemented.

[0042] 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 data analysis method when executing the program.

[0043] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0044] In the data analysis method provided in this specification, in response to the game data to be analyzed input by the user, according to the data type contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance index, the balance algorithm used to analyze the game data to be analyzed is determined in each balance algorithm as the target algorithm. The game data to be analyzed, the target algorithm and the first task prompt word are input into a pre-configured first language model to generate a call code, which is used to call the target algorithm to analyze the game data to be analyzed. The call code is run to obtain the calculated value of the target algorithm. According to the calculated value of the target algorithm, the analysis result of the game data to be analyzed is determined.

[0045] In this method, the reasoning and analysis capabilities of the large language model are applied, and the calling code of the target algorithm for analyzing the game data to be analyzed is output through the first language model, and then the calling code is automatically run to obtain the calculated value of the target indicator and determine the analysis result. The process of determining the analysis result is an automatic execution process. Through this method, the user only needs to input the game data to obtain the analysis result, which reduces the workload of the user in the game data analysis process and improves the efficiency of data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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:

[0047] Figure 1 A schematic diagram of a data analysis method in this specification;

[0048] Figure 2 A schematic diagram of a data analysis device provided in this specification;

[0049] Figure 3 The corresponding Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0050] 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 the embodiments. 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 application.

[0051] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0052] Figure 1 The following is a flow chart of a data analysis method in this specification, which specifically includes the following steps:

[0053] S100: In response to game data to be analyzed input by a user, according to the type of data contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator, determine, among each balance algorithm, a balance algorithm for analyzing the game data to be analyzed as a target algorithm.

[0054] All steps in the data analysis method provided in this specification can be implemented by any electronic device with computing functions, such as a terminal, a server, etc. For ease of description, the data analysis method provided in this specification is described below with the server as the execution subject.

[0055] In the analysis of game data, various balance indicators are usually needed. Different balance indicators are used to evaluate the balance of the game from different dimensions. For example, the balance indicator used to evaluate growth balance is upgrade time, the balance indicator used to evaluate character balance is character ability, and the balance indicator used to evaluate weapon or equipment balance is damage ability, defense ability, etc.

[0056] For each balance indicator, a calculation formula for the balance indicator can be pre-set according to the game scene setting, and various types of game data used as variables in the calculation formula are game data related to the balance of the corresponding dimension of the balance indicator.

[0057] In data analysis, a balance algorithm for the balance index can be written based on the calculation formula of the balance index, so that the server can automatically call the required balance algorithm based on the game data to be analyzed input by the user, and calculate the calculated values ​​of each balance index used for data analysis. The parameters required for the balance algorithm to run are the various game data used as variables in the calculation formula.

[0058] The same balance indicator has different balance parameters required by the balance algorithm in different game scene settings, so the same balance indicator may correspond to different balance algorithms. Taking the case where the balance indicator is character ability as an example, in a scene setting of a competitive game, the character ability can be related to health value and damage output per second, so the parameter types of the balance algorithm corresponding to the character ability are health value and damage output per second. In a scene setting of a role-playing game, the character ability can be related to growth coefficient, equipment bonus skill bonus and level, so the parameter types of the balance algorithm corresponding to the character ability are growth coefficient, equipment bonus skill bonus and level.

[0059] The calculation relationship between the various parameter types required by the balance algorithm can be set according to the needs of the game scene. For example, when the parameter types of the balance algorithm corresponding to the character ability are health value and output damage value per second, the balance algorithm can be "character ability = health value / output damage value per second".

[0060] In the data analysis method provided in this specification, the balance algorithms corresponding to various balance indicators that may be used in the game data analysis scenario and the parameter types required by each balance algorithm are pre-set. Therefore, each time the game data analysis is performed, for the game data to be analyzed used in the data analysis, it is only necessary to select the balance algorithm applicable to the game data to be analyzed in the preset balance algorithms corresponding to each balance indicator, so as to achieve the balance analysis of the game data to be analyzed with different contents.

[0061] In response to the game data to be analyzed input by the user, the server determines, among the various balance algorithms, a balance algorithm for analyzing the game data to be analyzed as a target algorithm according to the type of data contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator. The user mentioned in this specification refers to a game planner or a professional game data analyst.

[0062] Specifically, for each preset balance indicator, the server determines the parameter type required by the balance algorithm corresponding to the balance indicator, and whether there is a corresponding data type in the data to be analyzed. If so, the balance algorithm corresponding to the balance indicator is used as the target algorithm. If not, the balance algorithm corresponding to the balance indicator is not used as the target algorithm.

[0063] The specific number of parameter types corresponding to the balance indicator needs to be determined according to the calculation formula of the balance indicator. When there are multiple parameter types corresponding to the balance indicator, it is necessary to ensure that all parameter types corresponding to the balance indicator have corresponding data types in the game data. That is, the server needs to determine whether each calculation parameter of the balance indicator has a corresponding data type in the data to be analyzed.

[0064] When analyzing game data, the more balance indicators used, the more accurate the analysis results will be. In this embodiment, the server determines the balance algorithms corresponding to all balance indicators applicable to the game data to be analyzed. As long as the parameter type required to calculate a balance indicator exists in the game data to be analyzed, the server will automatically calculate the balance indicator, thereby ensuring the accuracy of the analysis results.

[0065] S102: Input the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured first language model to generate a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed.

[0066] S104: Run the calling code to obtain the calculated value of the target algorithm.

[0067] The trained large language model has the ability to understand and reason about the context, and can give corresponding outputs based on the context of the input information.

[0068] The server inputs the game data to be analyzed, the target algorithm and the first task prompt word into the pre-configured first language model to generate a calling code, so as to call the target algorithm through the calling code to analyze the game data to be analyzed.

[0069] The first task prompt word is used to prompt the first language model, determine the input parameters of calling the target algorithm according to the data type corresponding to the parameter type required by the target algorithm of the game data to be analyzed, and generate the calling code of calling the target algorithm according to the input parameters.

[0070] The calling code generated by the server's first language model can obtain the calculated value of the target indicator, so as to perform data analysis on the game data to be analyzed based on the calculated values.

[0071] Because different balancing algorithms are applicable to the game data to be analyzed that contain different data types, different target algorithms need to be called when analyzing different game data to be analyzed. This results in that in the current data analysis, users are required to select different balancing algorithms to analyze the game data to be analyzed that contain different data types, which results in a high degree of reliance on manual labor and reduces data analysis efficiency.

[0072] The data analysis method in this specification is based on the reasoning ability of the large language model. According to the data type contained in the game data to be analyzed, the large language model is used to generate a balance algorithm for analyzing the game data to be analyzed, that is, the calling code of the target algorithm, so as to automatically execute the data analysis process according to the differences in the game data to be analyzed, thereby improving the data analysis efficiency.

[0073] S106: Determine the analysis result of the game data to be analyzed according to the calculation value of the target algorithm.

[0074] The data analysis method provided in this specification can be applied to the analysis of game balance in various dimensions according to the different target indicators determined. The server can determine the analysis results of the game data to be analyzed in the analysis dimension corresponding to the target indicator according to the calculated value of the target algorithm.

[0075] For example, if the target indicator is the upgrade time, the server can obtain the analysis result of whether the game data to be analyzed is balanced in the growth balance dimension. If the target indicator is the character ability, the server can obtain the analysis result of whether the game data to be analyzed is balanced in the character balance dimension.

[0076] In one or more embodiments of this specification, the target indicator is used to evaluate the balance of each game character, and the target indicator in this embodiment can be combat capability. Accordingly, the calculation value of the target algorithm determined by the server includes the calculation result corresponding to each game character.

[0077] The server may then determine the analysis result in the following manner.

[0078] First, the server determines the expected value of the calculated value of the target algorithm according to the calculation results corresponding to each game character in the calculated value of the target algorithm.

[0079] Then, the server determines the calculation result corresponding to each game character in the game data to be analyzed in the calculation value of the target algorithm.

[0080] When the deviation between the calculation result corresponding to the game character and the expected value of the calculation value of the target algorithm is greater than a first preset value, the game character is determined to be an unbalanced character.

[0081] In this embodiment, determining an unbalanced character based on an expected value is not the only way. In fact, the expected value in this embodiment can also be replaced by other statistical values ​​such as the median and standard deviation, and the unbalanced character can be determined based on the deviation between the statistical value and the calculation result corresponding to the game character.

[0082] Based on the above, when the balance algorithm corresponding to the character ability is "character ability = health value / damage output value per second", when the server determines that the game data to be analyzed contains the health value and damage output value per second of each game character, the balance algorithm corresponding to the character ability can be used as the target algorithm. Then, the server runs the calling code of the target algorithm output by the first language model to obtain the calculated value of the target algorithm. Each calculation result in the calculated value is used to characterize the size of the character ability of each game character.

[0083] The calculation result corresponding to the game character determined as an unbalanced character is higher or lower than the calculation results included in the calculation value of the target algorithm. In the game process, the winning probability of the player who chooses the unbalanced character is greatly different from the winning probability of the player who chooses other game characters, which will affect the fairness of the game.

[0084] After obtaining the analysis results determined by the server, the user can adjust the game data corresponding to the unbalanced character to maintain the fairness of the game.

[0085] For example, if the calculation result corresponding to the unbalanced character is too high among the calculation results included in the calculation value of the target algorithm, the user can adjust the game data to be analyzed by reducing the health value of the unbalanced character or increasing the damage output per second of the unbalanced character.

[0086] Based on the above Figure 1 The data analysis method uses the reasoning and analysis capabilities of the large language model to output the calling code of the target algorithm for analyzing the game data to be analyzed through the first language model, and then automatically runs the calling code to obtain the calculated value of the target indicator and determine the analysis result. The process of determining the analysis result is an automatic execution process. Through this method, the user only needs to input the game data to obtain the analysis result, which reduces the workload of the user during the game data analysis process and improves the efficiency of data analysis.

[0087] In one or more embodiments of the present specification, the number of target algorithms determined in the above step S100 may be multiple.

[0088] When the target indicator is used to evaluate the balance of each game character, in the above step S106, the server can also determine the analysis result according to the following method.

[0089] The server determines, for each target algorithm, an expected value of the calculated value of the target algorithm based on the calculation results corresponding to each game character in the calculated value of the target algorithm.

[0090] Then, for each calculation result of the calculation value of the target algorithm, when the deviation between the calculation result and the expected value of the calculation value of the target algorithm is greater than a first preset value, the server determines that the game character corresponding to the calculation result is a pending unbalanced character.

[0091] Similarly, the expected value in this embodiment can be replaced by other statistical values ​​such as median and standard deviation.

[0092] Finally, the server determines the analysis result of the game data to be analyzed according to the unbalanced characters to be determined by each target algorithm.

[0093] The server may directly use the determined unbalanced roles to be determined as the analysis result. Alternatively, in order to improve the accuracy of the analysis result, the server may further screen the unbalanced roles to be determined, and use the unbalanced roles left after the screening as the analysis result.

[0094] In another embodiment, the server further screens each pending unbalanced role to determine the analysis result.

[0095] Specifically, the server counts and determines the number of target algorithms for each pending unbalanced role determined by each target algorithm. When the number of target algorithms for the pending unbalanced role is greater than a second preset value, the pending unbalanced role is used as the unbalanced role.

[0096] In this embodiment, the specific value of the second preset value can be set according to actual needs. The larger the value of the second preset value is, the higher the credibility of the determined unbalanced role is, and the higher the accuracy of the final analysis result is.

[0097] In one or more embodiments of the present specification, the analysis result in the above step S106 may also be obtained through a large language model.

[0098] Specifically, the server inputs the calculated value of the target algorithm and the second task prompt word into the pre-configured second largest language model to obtain the unbalanced data screened by the second largest language model from the game data to be analyzed. The second task prompt word is used to prompt the second largest language model to determine the abnormal calculated value according to the distribution of the calculated value in the target algorithm, and determine the unbalanced data according to the abnormal calculated value.

[0099] In this embodiment, in order to make the second largest language model output more accurate anomaly values, the second task prompt word may also include interfaces of various anomaly detection algorithms, and prompt the second largest language model to call the anomaly detection algorithm through the anomaly detection algorithm interface to obtain the anomaly calculation value obtained by the anomaly detection algorithm.

[0100] The interfaces of the above-mentioned anomaly detection algorithms may include interfaces of anomaly detection algorithms based on statistics, such as the standard score method and the Grubbs test method, interfaces of anomaly detection algorithms based on clustering, such as the density-based spatial clustering of applications with noise (DBSCAN), algorithms based on machine learning, such as the random forest algorithm and the single-class support vector machine algorithm, and the like.

[0101] When the second largest language model obtains the calculated value of the input target algorithm and the second task prompt word, it selects the anomaly detection algorithm to be used from the anomaly detection algorithms corresponding to the interfaces of each anomaly detection algorithm, and calls the anomaly detection algorithm to be used through the interface of the anomaly detection algorithm to obtain the calculation result of the anomaly detection algorithm, and uses the calculation result as the unbalanced data.

[0102] This embodiment calls the second largest language model and uses the reasoning ability of the second largest language model to enable the second largest language model to directly output unbalanced data based on the game data to be analyzed.

[0103] In order to improve the accuracy of the analysis results, in another embodiment, the second largest language model can be set as an integration of multiple sub-models, each sub-model having the same function but different model parameters.

[0104] Each sub-model in this embodiment can be trained based on the same training task, using different training data, or trained according to different initialization parameters, or trained through different network structures.

[0105] Specifically, the server inputs the calculated value of the target algorithm and the second task prompt word into each sub-model of the second largest language model, and obtains each pending imbalanced data screened by each sub-model from the game data to be analyzed.

[0106] Then, for each determined unbalanced data to be determined, when the number of sub-models screened out for the unbalanced data to be determined is greater than a third preset value, the server regards the unbalanced data to be determined as unbalanced data.

[0107] The specific value of the third preset value can be set according to actual data analysis requirements. Similar to the second preset value, the higher the value of the third preset value, the more accurate the imbalance data finally obtained.

[0108] The analysis result determined based on this embodiment is the final unbalanced data. The server can display the analysis result to the user, so that the user can refer to the analysis result and adjust the unbalanced data to optimize the game data to be analyzed.

[0109] Considering the poor interpretability of the decision-making process of the large language model, since the pending imbalanced data is directly output by the second largest language model, users usually have a low degree of confidence in the imbalanced data determined based on the pending imbalanced data. Therefore, in one embodiment, in order to improve the user's confidence in the analysis results obtained by the second largest language model, the server can display the pending imbalanced data output by each sub-model and the finally determined imbalanced data to the user together, thereby improving the user's confidence in the finally determined imbalanced data.

[0110] In one or more embodiments of the present specification, the input of the second largest language model may also include background settings of game characters. In the above step S106, the server inputs the background settings of the game characters, the calculated value of the target algorithm and the second task prompt word into the pre-configured second largest language model to obtain unbalanced data filtered by the second largest language model from the game data to be analyzed.

[0111] The background setting includes the character type information of each game character, as well as the game data types that reflect the characteristics of each character type. These game data types that reflect the characteristics of the character type ensure the differences of the game characters and the playability of the game. These game data types that reflect the characteristics of the character type are generally set by the planners. When determining unbalanced data, these game data types that reflect the characteristics of the character type are usually not adjusted first.

[0112] Therefore, in this embodiment, the background information is input into the second language model, and the game data types reflecting the characteristics of the character type are marked in the unbalanced data output by the second language model through the second task prompt word. Therefore, when the user adjusts the data to be analyzed according to the analysis results, the game data types reflecting the characteristics of the character type can be noticed and the appropriate data adjustment method can be selected.

[0113] The above is the data analysis method provided in this specification. Based on the same idea, this specification also provides a corresponding data analysis device, such as Figure 2 shown.

[0114] Figure 2 A schematic diagram of a data analysis device provided in this specification specifically includes:

[0115] The input module 200 is used to respond to the game data to be analyzed input by the user, and determine, from among the balance algorithms, a balance algorithm for analyzing the game data to be analyzed as a target algorithm according to the type of data contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator;

[0116] A code generation module 202 is used to input the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured large language model to generate a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed;

[0117] A calculation value determination module 204 is used to run the calling code to obtain the calculation value of the target algorithm;

[0118] The result determination module 206 is used to determine the analysis result of the game data to be analyzed according to the calculation value of the target algorithm.

[0119] Optionally, the input module 200 is specifically used to determine the parameter type required by the balancing algorithm corresponding to each preset balance indicator, and for each preset balance indicator, judge the parameter type required by the balancing algorithm corresponding to the balance indicator, and whether there is a corresponding data type in the data to be analyzed. If so, the balancing algorithm corresponding to the balance indicator is used as the target algorithm; if not, the balancing algorithm corresponding to the balance indicator is not used as the target algorithm.

[0120] Optionally, the target indicator is used to evaluate the balance of each game character, and the calculation value of the target algorithm includes the calculation results corresponding to the each game character. The result determination module 206 is specifically used to determine the expected value of the calculation value of the target algorithm based on the calculation results corresponding to the each game character in the calculation value of the target algorithm. For each game character in the game data to be analyzed, the calculation result corresponding to the game character is determined in the calculation value of the target algorithm. When the deviation between the calculation result corresponding to the game character and the expected value of the calculation value of the target algorithm is greater than a first preset value, the game character is determined to be an unbalanced character.

[0121] Optionally, the target indicator is used to evaluate the balance of each game character, the calculation value of the target algorithm includes the calculation results corresponding to the each game character, the number of the target algorithms is multiple, and the result determination module 206 is specifically used to determine, for each target algorithm, the expected value of the calculation value of the target algorithm according to the calculation results corresponding to the each game character in the calculation value of the target algorithm; for each calculation result in the calculation value of the target algorithm, when the deviation between the calculation result and the expected value of the calculation value of the target algorithm is greater than a first preset value, the game character corresponding to the calculation result is determined to be a pending unbalanced character; based on the pending unbalanced characters determined by each target algorithm, the analysis result of the game data to be analyzed is determined.

[0122] Optionally, the result determination module 206 is specifically used to statistically determine the number of target algorithms for each pending unbalanced role determined by each target algorithm, and when the number of target algorithms for the pending unbalanced role is greater than a second preset value, the pending unbalanced role is used as the unbalanced role.

[0123] Optionally, the result determination module 206 is specifically used to input the calculated value of the target algorithm and the second task prompt word into a pre-configured second largest language model to obtain the unbalanced data screened by the second largest language model from the game data to be analyzed, wherein the second task prompt word is used to prompt the second largest language model to determine the abnormal calculated value according to the distribution of the calculated value in the target algorithm, and determine the unbalanced data according to the abnormal calculated value.

[0124] Optionally, the result determination module 206 is specifically used to input the calculated value of the target algorithm and the second task prompt word into each sub-model of the second largest language model, and obtain each pending unbalanced data screened by each sub-model from the game data to be analyzed. For each determined pending unbalanced data, when the number of sub-models that screen out the pending unbalanced data is greater than a third preset value, the pending unbalanced data is used as unbalanced data.

[0125] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provided data analysis methods.

[0126] This manual also provides Figure 3 The schematic structure diagram of the electronic device shown in FIG. Figure 3 As mentioned above, 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 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0127] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of 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 the improvement of a method flow cannot be implemented with 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 themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. 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.

[0128] 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.

[0129] 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.

[0130] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0132] The present application 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 the present application. 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 generate 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.

[0133] 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.

[0134] 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.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] The above description is only an embodiment of this specification and is not intended to limit this specification. For those skilled in the art, this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification should be included in the scope of the claims of this application.

Claims

1. A data analysis method, characterized in that: include: In response to the game data to be analyzed input by the user, according to the data type contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator, determine, from each balance algorithm, a balance algorithm for analyzing the game data to be analyzed as a target algorithm; Input the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured first language model to generate a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed; Running the calling code to obtain the calculated value of the target algorithm; The analysis result of the game data to be analyzed is determined according to the calculated value of the target algorithm.

2. The method according to claim 1, characterized in that According to the data type contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance index, a balance algorithm for analyzing the game data to be analyzed is determined as a target algorithm in each balance algorithm, which specifically includes: Determine the parameter types required by the balancing algorithm corresponding to each preset balancing indicator; For each preset balance indicator, determine the parameter type required by the balance algorithm corresponding to the balance indicator, and whether there is a corresponding data type in the data to be analyzed; If so, the balance algorithm corresponding to the balance indicator is used as the target algorithm; If not, the balance algorithm corresponding to the balance indicator is not used as the target algorithm.

3. The method according to claim 1, characterized in that The target indicator is used to evaluate the balance of each game character, and the calculation value of the target algorithm includes the calculation results corresponding to each game character; Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including: Determine an expected value of the calculated value of the target algorithm according to the calculation results corresponding to the game characters in the calculated value of the target algorithm; For each game character in the game data to be analyzed, determining a calculation result corresponding to the game character in the calculation value of the target algorithm; When the deviation between the calculation result corresponding to the game character and the expected value of the calculation value of the target algorithm is greater than a first preset value, the game character is determined to be an unbalanced character.

4. The method according to claim 1, characterized in that The target indicator is used to evaluate the balance of each game character, the calculation value of the target algorithm includes the calculation results corresponding to each game character, and the number of the target algorithms is multiple; Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including: For each target algorithm, according to the calculation results corresponding to each game character in the calculation value of the target algorithm, determine the expected value of the calculation value of the target algorithm; For each calculation result of the calculation value of the target algorithm, when the deviation between the calculation result and the expected value of the calculation value of the target algorithm is greater than a first preset value, determining the game character corresponding to the calculation result as a pending unbalanced character; According to the unbalanced characters to be determined by each target algorithm, the analysis results of the game data to be analyzed are determined.

5. The method according to claim 4, characterized in that According to the unbalanced roles to be determined by each target algorithm, the analysis results of the game data to be analyzed are determined, specifically including: For each pending unbalanced role determined by each target algorithm, the number of target algorithms that determine the pending unbalanced role is counted; When it is determined that the number of the target algorithms of the undetermined unbalanced role is greater than the second preset value, the undetermined unbalanced role is used as the unbalanced role.

6. The method according to claim 1, characterized in that Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including: The calculated value of the target algorithm and the second task prompt word are input into a pre-configured second largest language model to obtain the unbalanced data screened by the second largest language model from the game data to be analyzed, wherein the second task prompt word is used to prompt the second largest language model, determine the abnormal calculated value according to the distribution of the calculated value in the target algorithm, and determine the unbalanced data according to the abnormal calculated value.

7. The method according to claim 6, characterized in that The second largest language model includes multiple sub-models, each sub-model has the same function but different model parameters; Determining the analysis result of the game data to be analyzed according to the calculated value of the target algorithm, specifically including: Inputting the calculated value of the target algorithm and the second task prompt word into each sub-model of the second largest language model, and obtaining each pending imbalanced data screened by each sub-model from the game data to be analyzed; For each determined unbalanced data to be determined, when the number of sub-models screened out for the unbalanced data to be determined is greater than a third preset value, the unbalanced data to be determined is taken as unbalanced data.

8. A data analysis device, characterized in that: include: An input module, in response to the game data to be analyzed input by the user, determines, from among the balance algorithms, a balance algorithm for analyzing the game data to be analyzed as a target algorithm according to the type of data contained in the game data to be analyzed and the parameter type required by the balance algorithm corresponding to each preset balance indicator; A code generation module, inputting the game data to be analyzed, the target algorithm and the first task prompt word into a pre-configured large language model, and generating a calling code, wherein the calling code is used to call the target algorithm to analyze the game data to be analyzed; A calculation value determination module runs the calling code to obtain the calculation value of the target algorithm; The result determination module determines the analysis result of the game data to be analyzed according to the calculation value of the target algorithm.

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