Game virtual props recommendation system, method and storage medium

Through the quantitative processing of scene and user parameters, combined with prop parameters, the best recommended virtual props are calculated, which solves the problem that virtual props recommendations are not personalized enough in the existing technology, and improves the accuracy and fit of recommendations.

CN117771682BActive Publication Date: 2024-11-15HANGZHOU JIAWA TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311800596.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-26
Publication Date
2024-11-15
Estimated Expiration
2043-12-26

AI Technical Summary

Technical Problem

The existing game virtual prop recommendation system cannot personalize recommendations based on the user's environment and scene parameters, resulting in poor recommendation capabilities.

Method used

Through the scene parameter picking, quantization and user parameter picking, quantization modules, combined with prop parameters, the best recommended virtual props are calculated.

Benefits of technology

It improves the accuracy and fit of virtual prop recommendations, avoids unsuitable choices caused by large deviations, and enhances recommendation capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117771682B_ABST
    Figure CN117771682B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of game software technology, and in particular to a game virtual prop recommendation system, method and storage medium. The game virtual prop recommendation system comprises: a scene parameter picking module for extracting scene parameters. A scene parameter quantization module for obtaining a scene parameter set. A user parameter picking module for obtaining user parameters. A user parameter quantization module for obtaining a user parameter set. A parameter merging module for obtaining a parameter extension set. A prop parameter picking module for obtaining prop parameters. A prop parameter quantization module for obtaining a prop parameter set. A parameter processing module for obtaining analysis and evaluation parameters by calculating a prop parameter set and a parameter extension set; and sorting each analysis and evaluation parameter from small to large, and recommending in the sorted order. Taking into account the deviation of virtual props to game users and scenes, the recommendation is more in line with the virtual prop selection conditions, the selection is more appropriate, and the recommendation ability is strong.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of game software technology, and in particular to a game virtual prop recommendation system, method and storage medium. Background Art

[0002] With the development of science and technology and the progress of society, mankind has entered the information age. With the popularization of smart phones, smart phones have become people's daily necessities. Smart phones are like personal computers, with independent operating systems and independent operating spaces. Users can install software, games, navigation and other programs provided by third-party service providers, and can access wireless networks through mobile communication networks. The current development trend of smart phones is to fully incorporate multiple patented technologies such as artificial intelligence and 5G, making smart phones the most widely used patented products.

[0003] Game software usually refers to software products that combine various programs and animation effects, which we call "game software". At present, the large-scale 3D online games and WEBGAME web games that we often see on the Internet are developed by combining "3DMAX, MAYA, FLASH and other animation software with Java, C++, VB, and other programming languages, so they are called game software. Based on the development and popularization of smart phones, mobile games have developed rapidly, bringing huge profits to game development, and thus giving huge development momentum to the development of mobile game software.

[0004] Virtual props are items or symbols used in computer games, online games or other digital entertainment fields to enhance the gaming experience. These virtual props are usually created by game developers to affect the player's gaming experience, such as giving players extra lives, money, items or special abilities. Virtual props can usually be divided into many types, such as game currency, upgrade points, special abilities, equipment, etc. Players can purchase these virtual props through levels, tasks or malls in the game. Virtual props play an important role in the field of digital entertainment. They can bring better gaming experience to players and more income to game developers.

[0005] The existing recommendation of virtual props for games can only take into account the situation of game users, but cannot be considered according to the actual scene parameters. The recommended virtual props cannot fully adapt to the current scene, resulting in poor recommendation ability. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a game virtual prop recommendation system for recommending props according to the user's environment and target characteristics. The game virtual prop recommendation system includes:

[0007] The scene parameter picking module is used to extract the scene parameters in the scene where the game user is currently located. In the process of making the game, each scene has corresponding parameters, which contain a variety of parameter information. These parameter information will contain parameters related to the game user and irrelevant parameters. The scene parameter picking module is used to extract these parameters related to the game user. In the process of making the game, these parameters related to the game user can be marked, and when the scene parameter picking module extracts, these marked parameters can be directly extracted. Of course, the scene parameters described in the game scene also include the parameters of the target, and the target is also part of the scene at that time.

[0008] The scene parameter quantization module is used to quantize the scene parameter to obtain the scene parameter quantization value q, and to index the scene parameter quantization value q to obtain the scene index value I, and to arrange these scene index values ​​in a preset order to obtain the scene parameter set A. The scene parameter set A is {a1, a2┈}.

[0009] The user parameter picking module is used to obtain user parameters by collecting statistics on the current status of the game user. During the game process, each scene in which the game user is located has corresponding parameters, which include self-learning user selection preferences, such as color, price, etc. These parameters also include parameters related to or unrelated to the scene parameters. The user parameter picking module is used to extract these parameters related to the scene parameters, and the specific extraction method is basically similar to that of the scene parameter picking module.

[0010] The user parameter quantization module is used to quantize the user parameters to obtain the user parameter quantization values, and then obtain the user index values ​​through indexation, and arrange these user index values ​​in a preset order to obtain the user parameter set B. The user parameter set B is {b1, b2┈}. The processing method of each value of the user parameter set B is basically the same as that of the scene parameter set A, and the data processing method is similar to the above.

[0011] The parameter merging module is used to merge the scene parameter set A with the user parameter set B to obtain the parameter expansion set C. The parameter expansion set C is the combination of the two sets of numbers. The parameter expansion set C is {a1, a2┈b1, b2┈}. The parameter expansion set C is defined as {c1, c2┈c n}.

[0012] The prop parameter acquisition module is used to collect statistics on each virtual prop in the game to obtain prop parameters. In the process of making a game, each prop will have its applicable scene, and the parameters required by these adapted scenes are defined as prop parameters.

[0013] The prop parameter quantization module is used to quantize the prop parameters to obtain the prop parameter quantization value, and then obtain the negative number of the prop parameter quantization value, and then obtain the prop index value I' through indexation, and arrange these prop index values ​​in a preset order to obtain the prop parameter set D. And the prop parameter set D is defined as {d1,d2┈d n The prop parameter set is consistent with the parameter extension set, and the number of values ​​in the set is consistent with n, and the meaning of each value in the prop parameter set is consistent with that in the parameter extension set. In general, each value in the parameter extension set C corresponds to each value in the prop parameter set, but sometimes they are not exactly the same. If the prop parameter set does not have a number in the parameter extension set C, it can be replaced by 1, and the details will not be repeated here. For the number that is not in the parameter extension set C and is replaced by 1, the details will not be repeated here one by one.

[0014] The parameter processing module is used to calculate the analysis and evaluation parameters E through the prop parameter set D and the parameter expansion set C. The analysis and evaluation parameters E are sorted from small to large, and recommended in the sorted order. The first one is min{E}, which is the best recommended virtual prop.

[0015] Preferably: the scene parameter set acquisition method may include: the scene parameter picking module obtains the identification code of each scene parameter and the position of the keyword relative code through a preset parameter-identification code and position information table, then scans the current game code, obtains each scene parameter required in each parameter-identification code and position information table by identifying the identification code in the game and the position of the keyword relative code, and then obtains the scene parameter according to the number position in the parameter-identification code and position information table. The parameter-identification code and position information table can be prepared in advance according to the requirements.

[0016] Preferably: the scene parameter quantization process may specifically include: scanning the scene parameters and determining whether the scene parameters are quantized parameters, if so, normalizing them, if not, quantizing and normalizing the scene parameters. The quantized parameters are defined as Arabic numerals, and determining whether they are quantized parameters is to determine whether the scene parameters are Arabic numerals, which will not be described in detail here. Normalization may be to correct the non-normalized scene parameters to a specific numerical range, and the specific numerical range setting may be determined according to the actual situation, and the general value range may be 0-10 or 0-1.

[0017] Preferably, the quantization process of the scene parameter of the non-quantized parameter may include: dividing it into m levels, then annotating keywords corresponding to each level, and then constructing a keyword-level information table, and obtaining a similarity S by comparing the current scene parameter with the keyword. i, where i is the keyword level number, and then extract Max{S i} The corresponding level i is used as the parameter level, and then the quantized value of the scene parameter is calculated. At this time, q is a quantitative value greater than 0 and less than 1. The m can be determined according to the actual situation, and is generally 4 to 10. In general, the scene parameter content is relatively uniform.

[0018] Preferably, the similarity obtaining method may specifically include: obtaining the relevance w of each phrase in the scene parameter relative to the keyword by scanning the current scene parameter content. j , the relevance of the relative keywords w j It can be obtained by formulating rules. Calculate the similarity Where j is the number of each phrase in the scene parameter, w j is the relevance of the phrase numbered j in the current scene parameter to the keyword, M is the total number of phrases in the current scene parameter, and s is the number of phrases in the current scene parameter whose relevance is negative.

[0019] Preferably, when the scene parameter is a numerical value, the numerical value may be divided by a preset standard value as a quantized value of the scene parameter. The standard value may be greater than a numerical value of the same type under normal circumstances, and the details are not repeated here.

[0020] Preferably: when the scene parameter is a separated value, the quantized value of the scene parameter Where k is the number of each partition, X k is the value of the partition numbered k, X is the standard value of each partition, and the standard value may be greater than the value of this type under normal circumstances, and N is the total number of partitions.

[0021] Preferred: The analysis and evaluation parameters Among them, t is the order of the items in the prop parameter set D and the parameter expansion set C. Since the data corresponding to each item in the prop parameter set D and the parameter expansion set C have the same meaning and the total number is the same, the meaning expressed by t at this time is the same in the two sets.

[0022] The present invention also proposes a method for recommending virtual game props, which includes:

[0023] S1. Extracting scene parameters in the scene where the game user is currently located;

[0024] S2, quantizing the scene parameter to obtain a scene parameter quantization value q, and exponentially performing an exponential operation on the scene parameter quantization value q to obtain a scene index value I;

[0025] S3, arranging the scene index values ​​I in a preset order to obtain a scene parameter set A;

[0026] S4, collecting statistics on the current status of the game user to obtain user parameters;

[0027] S5, quantizing the user parameters to obtain user parameter quantization values, then indexing to obtain user index values, and arranging the user index values ​​in a preset order to obtain a user parameter set B;

[0028] S6. Obtain parameter expansion set C by merging scene parameter set A and user parameter set B;

[0029] S7, collecting statistics on each virtual game prop to obtain prop parameters;

[0030] S8, quantizing the prop parameter to obtain a prop parameter quantization value, and negating the prop parameter quantization value, and then exponentially obtaining a prop index value I';

[0031] S9, arranging these prop index values ​​in a preset order to obtain a prop parameter set D;

[0032] S10, obtaining analysis and evaluation parameters E by calculating the prop parameter set D and the parameter expansion set C;

[0033] S11, sorting the various analysis and evaluation parameters E from small to large, and recommending them in the sorted order.

[0034] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for recommending game virtual props are implemented. When the method for recommending game virtual props is applied, it can be applied in the form of software, such as a program designed to be independently run by a computer-readable storage medium. The computer-readable storage medium can be a USB flash drive, designed as a USB shield, and the USB flash drive is designed to start the program of the entire method through an external trigger.

[0035] The technical effects and advantages of the present invention: Taking into account the deviation of virtual props to game users and scenes, the evaluation is more in line with the selection conditions of virtual props, the selection is more appropriate, and the recommendation ability is strong. By calculating the relative fluctuation degree of each item, the deviation between props and scenes and game users can be better characterized, and the characterization ability is strong. In the selection process of virtual props, if a parameter has a large deviation, it is not suitable for selection. By setting the index calculation, the larger the deviation, the larger the corresponding fluctuation degree, which can be well separated from the items with small deviations, avoiding the occurrence of the wooden barrel phenomenon. By setting the prop parameter set and the parameter expansion set for comparison, multiple items can be evaluated, with strong evaluation ability, and can better meet the needs of game customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a structural block diagram of the game virtual props recommendation system proposed by the present invention.

[0037] Figure 2 The present invention is a flowchart of the method for recommending virtual game props. DETAILED DESCRIPTION

[0038] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0039] Example 1

[0040] refer to Figure 1 In this embodiment, a game virtual prop recommendation system is proposed, which is used to recommend props according to the user's environment, user status and prop characteristics. The game virtual prop recommendation system includes:

[0041] The scene parameter picking module is used to extract the scene parameters in the scene where the game user is currently located. In the process of making the game, each scene has corresponding parameters, which contain multiple parameter information. These parameter information will contain parameters related to the game user and irrelevant parameters. The scene parameter picking module is used to extract these parameters related to the game user. In the process of making the game, these parameters related to the game user can be bound and marked, and when the scene parameter picking module extracts, these marked parameters can be directly extracted. Of course, the scene parameters in the game scene also include the parameters of the target, and the target is also part of the scene at that time. The scene parameter set acquisition method may include: the scene parameter picking module obtains the identification code of each scene parameter and the position of the keyword relative code through a preset parameter-identification code and position information table, and then scans the current game code, and obtains each parameter-identification code, each scene parameter required in the position information table by identifying the identification code in the game and the position of the keyword relative code, and then obtains the scene parameter according to the number position in the parameter-identification code and position information table. The parameter-identification code and position information table can be prepared in advance according to the requirements. For example, in a game, we obtain the distance of the target, the color of the enemy's clothing, the number of enemies, the enemy's protection level, etc. Here we take a small game code as an example, the parameter-identification code, location information table can be as follows:

[0042] colour coordinate ┈┈ Color / color Positionin ┈┈ Datein() Datein() ┈┈

[0043] Then scan the game code:

[0044] gameOver(playSurface,score):

[0045] gameOverFont=pygame.font.SysFont('arial.ttf',54)

[0046] gameOverSurf=gameOverFont.render.'Gameover! ',True,color(150,150,150)gameOverRect=gameOverSurf.get_rect()

[0047] gameOverRect.midtop=(300,10)

[0048] playSurface.blit(gameOverSurfgameOverRect)

[0049] scoreFont=pygame.font.SysFont('arial.ttf',54)

[0050] scoreSurf=scoreFont.render'Score:'+str(score),True,color(150,150,150)scoreRect=scoreSurf.get_rect()

[0051] scoreRect.midtop=(300,50)

[0052] ┈┈

[0053] The color (150, 150, 150) obtained by scanning is greycolor, which will not be described in detail here. This is just a simple example and is not universal, so other details will not be described here.

[0054] The scene parameter quantization module is used to quantize the scene parameter to obtain the scene parameter quantization value q, and to obtain the scene index value I by exponentiating the scene parameter quantization value q, and to arrange these scene index values ​​in a preset order to obtain the scene parameter set A. The scene parameter set A is {a1, a2┈}. The scene parameter quantization process can be specifically as follows: scanning the scene parameter and determining whether the scene parameter is a quantization parameter. If so, normalizing it; if not, quantizing and normalizing the scene parameter. The quantization parameter is defined as an Arabic numeral. Determining whether it is a quantization parameter is to determine whether the scene parameter is an Arabic numeral. The specific details are not described here. The method of determining whether a byte is an Arabic numeral is a prior art, and the specific details are not described here. Our normalization can be to correct the non-normalized scene parameter to a specific numerical range. The specific numerical range setting can be determined according to the actual situation. Our general value range can be 0-10 or 0-1. Below we take 0-1 as an example. The quantization process of the scene parameters of non-quantized parameters can be: divide them into m levels, then annotate keywords corresponding to each level, and then build a keyword-level information table, and obtain the similarity S by comparing the current scene parameters with the keywords. i , where i is the keyword level number, and then extract Max{S i} The corresponding level i is used as the parameter level, and finally the quantized value of the scene parameter is calculated. At this time, q is a quantitative value greater than 0 and less than 1. The m can be determined according to the actual situation, generally 4-10. For example, we evaluate the skills of a target. In the skill catalog, there are 6 levels such as close attack, long-range attack, meat shield protection, shield protection, healing system, and auxiliary system. Then our m can be 6 at this time, and then the keywords we construct can be close attack-1, long-range attack-2, meat shield protection-3, shield protection-4, healing system-5, and auxiliary system-6. The scene parameter we extracted is meat shield protection. By searching the keyword-level information table, we get that the similarity between the current scene parameter meat shield protection and the keyword meat shield protection is 100% and the highest, so the corresponding 3 is the selected level, and the scene parameter quantization value q=3 / 6=0.5 is calculated. In general, the content of the scene parameters is relatively uniform, just like the current scene parameter meat shield protection and the keyword meat shield protection in the above example, the similarity is either 0 or 100%. It is relatively simple in the keyword search process, but it does not exclude other scenes with more content forms. For example, a piece of code does not include all keywords. In this case, we need to calculate the similarity. This method is suitable for the case where the scene parameter content changes greatly and can realize intelligent recognition. The similarity acquisition method can be specifically: by scanning the current scene parameter content, obtain the relevance w of each phrase in the scene parameter relative to the keyword j , the relevance of the relative keywords w j It can be obtained by formulating rules. For example, the relevance of the same keyword is 1, synonyms are set in the interval (0,1) according to the attribute, and antonyms are set in the interval (-1,0) according to the attribute. For example, the relevance of meat shield and shield can be 0.8, and some words such as non and no have negative relevance. The specific values ​​are not repeated here. Calculate the similarity where w j is the relevance of the phrase numbered j in the current scene parameter to the keyword, M is the total number of phrases in the current scene parameter, and s is the number of phrases in the current scene parameter whose phrase relevance is negative. By calculating the similarity, the influence of similarity can be taken into account while also taking into account the influence of oppositeness, and the evaluation ability is strong. Of course, this is just a simple example, and other specific situations are not described here. When the scene parameter is a numerical value, the numerical value can be divided by a preset standard value as a scene parameter quantization value. The standard value can be greater than the numerical value of this type under normal circumstances, and the details are not described here. When the scene parameter is a separated numerical value, such as the three primary colors display and coordinates of colors. The scene parameter quantization value Where k is the number of each partition, X kis the value of the segment numbered k, X is the standard value of each segment, which can be greater than the value of this type in general, and N is the total number of segments. Let's take the calculation of the three primary colors of gray as an example. Gray is (150, 150, 150). We can get N = 3, X1 = 150, X2 = 150, X3 = 150, X = 225, then calculate the parameter quantization value q = 150 3 / 225 3 =0.30. By converting the separated numerical value into a numerical value in a fixed format, the calculation method is convenient for unified calculation. Other situations will not be described one by one here. The exponential value I=exp(q). Of course, the base number can also be other numerical values, which will not be described in detail here. For example, in a game, the representation of the scene parameters of the target are the number of enemies, distance, skills, sensitivity, etc. After quantization, the quantized values ​​of the scene parameters are {0.2, 0.5, 0.4, 0.5}, and the exponential values ​​obtained after indexation are {1.22, 1.65, 1.49, 1.65}. These exponential values ​​are arranged in a preset order to obtain a scene parameter set of {1.22, 1.65, 1.49, 1.65}. The processing process here is just a simple example and is not universal, so it will not be described in detail here.

[0055] The user parameter picking module is used to obtain user parameters by counting the current status of the game user. During the game process, each scene in which the game user is located has corresponding parameters, which include self-learning user selection preferences, such as color, price, etc. These parameters also include parameters related to or unrelated to the scene parameters. The user parameter picking module is used to extract these parameters related to the scene parameters. The specific extraction method is basically similar to that of the scene parameter picking module, and will not be described in detail here.

[0056] The user parameter quantization module is used to quantize the user parameters to obtain the user parameter quantization values, and then obtain the user index values ​​through indexation, and arrange these index values ​​in a preset order to obtain the user parameter set B. The user parameter set B is {b1, b2┈}. The processing method of each value of the user parameter set B is basically the same as that of the scene parameter set A, and the data processing method is similar to the above, and the specific details are not repeated here.

[0057] The parameter merging module is used to merge the scene parameter set A with the user parameter set B to obtain the parameter expansion set C. The parameter expansion set C is the combination of the two sets of numbers. The parameter expansion set C is {a1, a2┈b1, b2┈}. The parameter expansion set C is defined as {c1, c2┈c n}. The specific method is a mathematical method, which is a prior art and will not be described in detail here.

[0058] The prop parameter picking module is used to obtain prop parameters by counting each virtual prop in the game. In the process of making the game, each prop will have its applicable scene, and the parameters required by these adapted scenes are defined as prop parameters. For example, a shield is for close-range defense, with a defense power of 1000 points, suitable for blocking attack points in the range of 500-1000. At this time, the prop parameter is 500-1000 points of attack, and the optimal value is 1000. This is just a simple example, which is not universal, so I will not elaborate on it here.

[0059] The prop parameter quantization module is used to quantize the prop parameters to obtain the prop parameter quantization value, and then obtain the negative number of the prop parameter quantization value, and then obtain the prop index value I' through indexation, and arrange these prop index values ​​in a preset order to obtain the prop parameter set D. And the prop parameter set D is defined as {d1,d2┈d n}. The prop parameter set is consistent with the parameter extension set, and the number of values ​​in the set is consistent, and the meaning of each value in the prop parameter set is consistent with that in the parameter extension set. Under normal circumstances, each value in the parameter extension set C corresponds to each value in the prop parameter set, but sometimes they are not exactly the same. The number items in the parameter extension set C that are not in the prop parameter set can be replaced by 1, and the number items that are not in the parameter extension set C are replaced with 1, and the details are not repeated here. In this way, the data corresponding to each item in the prop parameter set D and the parameter extension set C are the same, and the method of processing each data is also the same. The data processing method is similar to that described above, and the details are not repeated here.

[0060] The parameter processing module is used to calculate the analysis and evaluation parameter E through the prop parameter set D and the parameter expansion set C. And sort the various analysis and evaluation parameters E from small to large, and recommend them in the sorted order. The first one is min{E}, which is the best recommended virtual prop. The analysis and evaluation parameter E calculation method can be specifically Wherein t is the order of the items in the prop parameter set D and the parameter expansion set C. Since the data meanings corresponding to the items in the prop parameter set D and the parameter expansion set C are the same, and the total number is consistent, the meaning of t at this time is the same in the two sets. The present invention comprehensively considers the deviation of virtual props to game users and scenes, considers more suitable virtual prop selection conditions, and selects more appropriately. By calculating the relative fluctuation degree of each item, the deviation between props and scenes and game users can be better characterized, and the characterization ability is strong. In the selection process of virtual props, if a parameter deviation is large, it is not suitable for selection. By setting the index calculation, the larger the deviation, the larger the corresponding fluctuation degree, which can be well separated from the items with small deviations, avoiding the occurrence of the wooden barrel phenomenon. By setting the prop parameter set D to be compared with the parameter expansion set C, each item can be evaluated, the evaluation ability is strong, and it can be more suitable for the needs of game customers.

[0061] Example 2

[0062] refer to Figure 2 In this embodiment, a method for recommending game virtual props is proposed, and the method for recommending game virtual props includes:

[0063] S1. Extracting scene parameters in the scene where the game user is currently located;

[0064] S2, quantizing the scene parameter to obtain a scene parameter quantization value q, and exponentially performing an exponential operation on the scene parameter quantization value q to obtain a scene index value I;

[0065] S3, arranging the scene index values ​​I in a preset order to obtain a scene parameter set A;

[0066] S4, collecting statistics on the current status of the game user to obtain user parameters;

[0067] S5, quantizing the user parameters to obtain user parameter quantization values, then indexing to obtain user index values, and arranging the user index values ​​in a preset order to obtain a user parameter set B;

[0068] S6. Obtain parameter expansion set C by merging scene parameter set A and user parameter set B;

[0069] S7, collecting statistics on each virtual game prop to obtain prop parameters;

[0070] S8, quantizing the prop parameter to obtain a prop parameter quantization value, and negating the prop parameter quantization value, and then exponentially obtaining a prop index value I';

[0071] S9, arranging these prop index values ​​in a preset order to obtain a prop parameter set D;

[0072] S10, obtaining analysis and evaluation parameters E by calculating the prop parameter set D and the parameter expansion set C;

[0073] S11, sorting the various analysis and evaluation parameters E from small to large, and recommending them in the sorted order.

[0074] Example 3

[0075] As a preferred embodiment of the present invention, a computer readable storage medium stores a computer program. When the program is executed by a processor, the steps of the method for recommending virtual game props are implemented. When the method for recommending virtual game props is applied, it can be applied in the form of software, such as a program designed to be independently run on a computer readable storage medium. The computer readable storage medium can be a USB flash drive, designed as a USB shield, and the USB flash drive is designed to start the program of the entire method through an external trigger.

[0076] Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

[0077] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article 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 article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0078] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention invented herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not invented by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0079] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A game virtual props recommendation system, characterized in that: The game virtual props recommendation system includes: A scene parameter picking module, which is used to extract the scene parameters of the scene currently located by the game user; A scene parameter quantization module, which is used to quantize the scene parameter to obtain a scene parameter quantization value q, and to index the scene parameter quantization value q to obtain a scene index value I, and to arrange these scene index values ​​in a preset order to obtain a scene parameter set A; User parameter acquisition module, which is used to obtain user parameters by collecting statistics on the current status of game users; A user parameter quantization module, which is used to quantize the user parameters to obtain user parameter quantization values, and then obtain user index values ​​through indexation, and arrange these index values ​​in a preset order to obtain a user parameter set B; A parameter merging module, which is used to obtain a parameter expansion set C by merging a scene parameter set A with a user parameter set B; The prop parameter picking module is used to collect statistics on each virtual prop in the game to obtain prop parameters; A prop parameter quantization module, which is used to quantize the prop parameters to obtain prop parameter quantization values, and to find the negative of the prop parameter quantization values, and then to obtain prop index values ​​I' through exponentialization, and to arrange these prop index values ​​in a preset order to obtain a prop parameter set D; The parameter processing module is used to calculate the analysis and evaluation parameters E through the prop parameter set D and the parameter expansion set C; and sort the analysis and evaluation parameters E from small to large, and recommend them in the sorted order; The scene parameter quantization process includes: scanning the scene parameters to determine whether the scene parameters are quantized parameters, and if so, normalizing them; if not, quantizing and normalizing the scene parameters; the quantization process of the scene parameters of non-quantized parameters includes: dividing them into m levels, and then annotating keywords corresponding to each level, and then constructing a keyword-level information table, and obtaining a similarity S by comparing the current scene parameters with the keywords. i , where i is the keyword level number, and then extract Max{S i } The corresponding level i is used as the parameter level, and then the quantized value of the scene parameter is calculated.

2. The game virtual prop recommendation system according to claim 1, characterized in that: The scene parameter set acquisition method includes: scanning the current game code, obtaining each scene parameter required in each parameter-identification code, position information table by identifying the identification code in the game and the position of the keyword relative to the code, and then obtaining the scene parameter according to the number position in the parameter-identification code, position information table.

3. The game virtual prop recommendation system according to claim 1, characterized in that: The similarity obtaining method includes: obtaining the relevance w of each phrase in the scene parameter relative to the keyword by scanning the current scene parameter content. j , calculate the similarity Where j is the number of each phrase in the scene parameter, w j is the relevance of the phrase numbered j in the current scene parameter to the keyword, M is the total number of phrases in the current scene parameter, j=1, 2, ..., M; s is the number of phrases in the current scene parameter whose phrase relevance is negative.

4. The game virtual prop recommendation system according to claim 1, characterized in that: When the scene parameter is a numerical value, the numerical value is divided by a preset standard value as the scene parameter quantization value.

5. The game virtual prop recommendation system according to claim 1, characterized in that: When the scene parameter is a separated value, the scene parameter quantization value Where k is the number of each partition, X k is the value of the partition numbered k, X is the standard value of each partition, and N is the total number of partitions; k=1, 2, …, N.

6. The game virtual prop recommendation system according to claim 1, characterized in that: The scene parameter set A is {a1, a2┈}, the user parameter set B is {b1, b2┈}, the parameter expansion set C is the combination of the two sets of numbers, the parameter expansion set C is {a1, a2┈b1, b2┈}, and the parameter expansion set C is defined as {c1, c2┈c n }, and define the prop parameter set D as {d1, d2┈d n }, the analysis and evaluation parameters Where t is the order of items in the prop parameter set D and the parameter expansion set C; t = 1, 2, ..., n.

7. A method for recommending virtual game props, using the system for recommending virtual game props as claimed in any one of claims 1 to 6, characterized in that: The method for recommending game virtual props includes: S1. Extracting scene parameters in the scene where the game user is currently located; S2, quantizing the scene parameter to obtain a scene parameter quantization value q, and exponentially performing an exponential operation on the scene parameter quantization value q to obtain a scene index value I; S3, arranging the scene index values ​​I in a preset order to obtain a scene parameter set A; S4, collecting statistics on the current status of the game user to obtain user parameters; S5, quantizing the user parameters to obtain user parameter quantization values, then indexing to obtain user index values, and arranging these index values ​​in a preset order to obtain a user parameter set B; S6. Obtain parameter expansion set C by merging scene parameter set A and user parameter set B; S7, collecting statistics on each virtual game prop to obtain prop parameters; S8, quantizing the prop parameter to obtain a prop parameter quantization value, and negating the prop parameter quantization value, and then exponentially obtaining a prop index value I'; S9, arranging these prop index values ​​in a preset order to obtain a prop parameter set D; S10, obtaining analysis and evaluation parameters E by calculating the prop parameter set D and the parameter expansion set C; S11, sorting the various analysis and evaluation parameters E from small to large, and recommending them in the sorted order.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for recommending game virtual props as claimed in claim 7 are implemented.