Game item recommendation method, device, equipment and computer readable storage medium

Abstract

The present invention discloses a method, device, equipment and computer-readable storage medium for recommending game items, wherein the method for recommending game items includes: obtaining the game character selected by the user in the current game and the game ranking of the user, and filtering and generating historical victory battle data according to the game ranking and the game character; obtaining the game item purchase record corresponding to each game of the game character from the historical victory battle data, and generating a game item recommendation package according to the game item purchase record; obtaining the current game item data corresponding to the game character, and recommending game items based on the current game item data and the game item recommendation package. The method for recommending game items of the present invention is more objective and flexible, reducing the learning time cost of the user's game, thereby further improving the game experience of new users.

Description

Technical Field

[0001] The present invention relates to the field of game technology, and in particular to a game item recommendation method, device, equipment and computer-readable storage medium. Background Art

[0002] At present, games are increasingly accepted as a form of leisure. When users first come into contact with a game, they often need to learn before they can get the game experience in the game, especially in some competitive games, such as MOBA games (Multiplayer Online Battle Arena). When facing a large number of game items (game props or game equipment) in MOBA games, new players often do not know how to reasonably select game items. To solve the above problems, the current solution is usually that the system or experienced game players formulate the recommended game items in advance according to the characteristics of the game characters, and then the new players choose the recommendation plan by themselves. However, this recommendation plan is generally fixed, and the low flexibility has limited help in improving the player's gaming experience. Therefore, a flexible game item recommendation method is urgently needed.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a game item recommendation method, aiming to solve the technical problem that the current game item recommendation method has a fixed recommendation scheme and low flexibility.

[0005] To achieve the above object, the present invention provides a method for recommending game items, the method comprising the following steps:

[0006] Obtain the game character selected by the user in the current game and the game ranking of the user, and filter and generate historical victory battle data based on the game ranking and the game character;

[0007] Acquire a purchase record of game items corresponding to the game character in each game from the historical victory battle data, and generate a recommended set of game items according to the purchase record of game items;

[0008] Current game item data corresponding to the game character is obtained, and game items are recommended based on the current game item data and the game item recommendation package.

[0009] Furthermore, after the step of generating historical victory battle data according to the game ranking and the game character screening, the process further includes:

[0010] The game character data of the current game is obtained, and the historical victory battle data is filtered according to the game character data of the current game to generate new historical victory battle data.

[0011] Furthermore, after the step of generating new historical victory battle data, the method further includes:

[0012] Determine whether the number of samples in the historical victory battle data is less than a preset sample number threshold;

[0013] If the sample quantity is less than the preset sample quantity threshold, a game character is deleted from the current game character data to generate new current game character data, and the step of screening the historical victory battle data according to the current game character data to generate new historical victory battle data is performed;

[0014] If the sample quantity is greater than or equal to the preset sample quantity threshold, the step of obtaining the item purchase record of the game character from the historical victory battle data is executed.

[0015] Furthermore, the step of generating a recommended set of game items according to the game item purchase record includes:

[0016] Filtering the game items with different functional characteristics from the game item purchase records to generate a set of game items with different functional characteristics, wherein each of the game items is marked with a functional characteristic;

[0017] Determining a recommended single game item for each of the game item sets based on the number of purchases;

[0018] The recommended set of game items is generated based on the recommended single game items.

[0019] Furthermore, after the step of generating the recommended game item set according to the recommended game item single piece, the method further includes:

[0020] A recommendation order of each of the recommended game items in the recommended game item set is generated according to the purchase time of the recommended game item in the game item purchase record.

[0021] Further, the step of recommending game items based on the current game item data and the game item recommendation package includes:

[0022] Generate a first functional feature set according to the functional features of each game item in the current game item data;

[0023] generating a second functional feature set according to the functional features of each game item in the recommended game item set;

[0024] Deleting the same functional features in the second functional feature set as those in the first functional feature set to generate a new second functional feature set;

[0025] The game items corresponding to the second functional feature set in the game item recommendation package are recommended according to the recommendation order.

[0026] Further, the step of generating historical victory battle data based on the game ranking and the game character screening includes:

[0027] From the battle data of the players in the game ranking, the battle data in which the game character exists and the camp in which the game character is located wins is selected as the historical victory battle data.

[0028] In addition, to achieve the above-mentioned purpose, the present invention further provides a game item recommendation device, the game item recommendation device comprising:

[0029] A screening module, used to obtain the game character selected by the current game user and the game ranking of the user, and to screen the original battle data according to the game ranking and the game character to generate historical victory battle data;

[0030] A generation module, used to obtain the game item purchase record corresponding to the game character in each game from the historical victory battle data, and generate a recommended game item set according to the game item purchase record;

[0031] The recommendation module is used to obtain current game item data corresponding to the game character, and recommend game items based on the current game item data and the game item recommendation package.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a game item recommendation device, which includes: a memory, a processor, and a game item recommendation program stored in the memory and executable on the processor, and when the game item recommendation program is executed by the processor, the steps of the game item recommendation method as described above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a game item recommendation program is stored, and when the game item recommendation program is executed by a processor, the steps of the game item recommendation method as described above are implemented.

[0034] A method for recommending game items proposed in an embodiment of the present invention obtains the game character selected by the user in the current game and the game ranking of the user, and generates historical victory battle data based on the game ranking and the game character; obtains the game item purchase record corresponding to the game character in each game from the historical victory battle data, and generates a game item recommendation package based on the game item purchase record; obtains the current game item data corresponding to the game character, and recommends game items based on the current game item data and the game item recommendation package. On the one hand, the battle data considered for recommending game items is more in line with the user's current battle environment, and on the other hand, the game items to be promoted are obtained from a large amount of battle data that has achieved victory. Compared with the use of a fixed recommendation scheme, the game item recommendation method of the present invention is more objective and flexible. Reduce the learning cost of the user's game, thereby further improving the gaming experience of new users. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0036] Figure 2 This is a flowchart of the first embodiment of the game item recommendation method.

[0037] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0038] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0039] like Figure 1 As shown, Figure 1 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0040] The device in the embodiment of the present invention may be a server, or may be an electronic terminal device with data processing function, such as a PC, a smart phone, a tablet computer, an e-book reader, or a portable computer.

[0041] like Figure 1As shown, the device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or it may be a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0042] Optionally, the device may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among them, sensors include light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light, and the proximity sensor may turn off the display screen and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which will not be repeated here.

[0043] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0044] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a game item recommendation program.

[0045] exist Figure 1 In the device shown, the network interface 1004 is mainly used to connect to the backend server and perform data communication with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and perform data communication with the client; and the processor 1001 can be used to call the game item recommendation program stored in the memory 1005 and perform the following operations:

[0046] Obtain the game character selected by the user in the current game and the game ranking of the user, and filter and generate historical victory battle data based on the game ranking and the game character;

[0047] Acquire a purchase record of game items corresponding to the game character in each game from the historical victory battle data, and generate a recommended set of game items according to the purchase record of game items;

[0048] Current game item data corresponding to the game character is obtained, and game items are recommended based on the current game item data and the game item recommendation package.

[0049] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0050] After the step of generating historical victory battle data according to the game ranking and the game character screening, the method further includes:

[0051] The game character data of the current game is obtained, and the historical victory battle data is filtered according to the game character data of the current game to generate new historical victory battle data.

[0052] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0053] After the step of generating new historical victory battle data, the method further includes:

[0054] Determine whether the number of samples in the historical victory battle data is less than a preset sample number threshold;

[0055] If the sample quantity is less than the preset sample quantity threshold, a game character is deleted from the current game character data to generate new current game character data, and the step of screening the historical victory battle data according to the current game character data to generate new historical victory battle data is performed;

[0056] If the sample quantity is greater than or equal to the preset sample quantity threshold, the step of obtaining the item purchase record of the game character from the historical victory battle data is executed.

[0057] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0058] The step of generating a recommended set of game items according to the game item purchase record comprises:

[0059] Filtering the game items with different functional characteristics from the game item purchase records to generate a set of game items with different functional characteristics, wherein each of the game items is marked with a functional characteristic;

[0060] Determining a recommended single game item for each of the game item sets based on the number of purchases;

[0061] The recommended set of game items is generated based on the recommended single game items.

[0062] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0063] After the step of generating the recommended game item set according to the recommended game item single piece, the method further includes:

[0064] A recommendation order of each of the recommended game items in the recommended game item set is generated according to the purchase time of the recommended game item in the game item purchase record.

[0065] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0066] The step of recommending game items based on the current game item data and the game item recommendation package comprises:

[0067] Generate a first functional feature set according to the functional features of each game item in the current game item data;

[0068] generating a second functional feature set according to the functional features of each game item in the recommended game item set;

[0069] Deleting the same functional features in the second functional feature set as those in the first functional feature set to generate a new second functional feature set;

[0070] The game items corresponding to the second functional feature set in the game item recommendation package are recommended according to the recommendation order.

[0071] Furthermore, the processor 1001 may call the game item recommendation program stored in the memory 1005, and further perform the following operations:

[0072] The step of generating historical victory battle data based on the game ranking and the game character screening includes:

[0073] From the battle data of the players in the game ranking, the battle data in which the game character exists and the camp in which the game character is located wins is selected as the historical victory battle data.

[0074] Reference Figure 2 , the first embodiment of the game item recommendation method of the present invention, the game item recommendation method comprises:

[0075] Step S10, obtaining the game character selected by the user in the current game and the game ranking of the user, and filtering and generating historical victory battle data according to the game ranking and the game character;

[0076] In current MOBA games, there are different battle modes. For example, 1V1, 3V3, 5V5 or 10V10. In this embodiment, the most common 5V5 is selected as an example for illustration, that is, there are two camps for competition, each camp has 5 game players, and each player can choose a game character. After the user enters the game, he selects a game character, and the server obtains the game character selected by the user. The above-mentioned game rankings (for example, rank or ladder score, etc.) are used to measure the data of the user's game strength. At the same time, the game ranking is also used by the server to match teammates and hostile players with similar strength to the user, so the user's game ranking is usually stored on the server.

[0077] Furthermore, from the battle data of the players in the game ranking, battle data in which the game character exists and the camp in which the game character is located wins is selected as the historical victory battle data.

[0078] Specifically, the server selects battle data corresponding to the game ranking of the user from the battle data of all players. For example, if the current user's game ranking is at level 1, battle data of level 1 is selected from the battle data of all players to obtain battle data of the same level as the user for reference. Further, battle data of the same level in which the game character selected by the user exists and the camp in which the game character is located has won is selected from the battle data of the same level, and is used as the above-mentioned historical victory battle data. It can be understood that, compared with the use of a fixed game item recommendation method, the reference basis for the game items recommended to the user in this embodiment will change with the change of the user's game ranking, so the game item recommendation is more flexible.

[0079] Optionally, after the step of generating the historical victory battle data according to the game ranking and the game character screening, it also includes: obtaining the game character data of the current game, screening the historical victory battle data according to the current game character data, and generating new historical victory battle data.

[0080] Specifically, the game character data of the current game includes the game characters selected by the teammate players of the user and the game characters of the user's enemy players in the current game. The game data including all teammate game characters and enemy game characters are further screened out from the historical victory battle data to generate new historical victory battle data. It is understandable that in addition to recommending game items based on the game characters selected by the user himself, the game characters of the user's teammates and enemy game characters are also added as recommendation factors for game items on this basis. Therefore, the game items recommended by the system each time are more flexible and more in line with the current battle lineup.

[0081] Optionally, after the step of generating new historical victory battle data, the step includes: determining whether the number of samples in the historical victory battle data is less than a preset sample number threshold; if the sample number is less than the preset sample number threshold, deleting a game character from the current game character data to generate new current game character data, and executing the step of filtering the historical victory battle data according to the current game character data to generate new historical victory battle data; if the sample number is greater than or equal to the preset sample number threshold, executing the step of obtaining the game character's item purchase record from the historical victory battle data.

[0082] Specifically, in order to ensure that the historical victory battle data used as a reference is universal, the minimum sample size of the above historical victory battle data is limited. Take each game battle data as a sample, obtain the sample size in the current historical victory battle data, and judge the size between the sample size and the preset sample size threshold (the preset sample size threshold can be set by a technician according to the situation, such as 500). If it is less than the preset sample size threshold, that is, the current historical victory battle data does not meet the minimum sample size, then delete a game character from the current game character data. For example, based on the above 5V5 example, the current game character data actually includes 9 game characters, and arbitrarily delete one game character from the 9 game characters. Thereby reducing the screening conditions for the battle data to increase the sample size of the historical victory battle data. Under normal circumstances, the game character selected by the user teammate can be deleted first. After obtaining the new current game character data, perform the steps of screening the historical victory battle data according to the current game character data to generate new historical victory battle data. Similarly, obtain the sample size of the newly generated historical victory battle data, and judge whether the sample size at this time is less than the preset sample size threshold. If it is still less than the preset sample quantity threshold, the above steps of deleting game characters and judging the size of the preset sample quantity threshold are repeated until the sample quantity is greater than / equal to the preset sample quantity threshold, or all game characters in the current game character data are deleted. If it is determined that the sample quantity of the current historical victory battle data is greater than / equal to the preset sample quantity threshold, the subsequent step of obtaining the prop purchase record of the game character from the historical victory battle data is performed.

[0083] Step S20, obtaining a purchase record of game items corresponding to the game character in each game from the historical victory battle data, and generating a recommended set of game items according to the purchase record of game items;

[0084] Specifically, the above historical victory battle data includes a large amount of battle data with the same game level as the user, the same game character selected by the user, and a similar lineup to the current game. The battle data is used to record the game behavior of each game player in a battle game. The game behavior includes the purchase of game items, that is, the game item purchase record. The game item purchase record records the game items purchased by the game character in the battle game. It can be understood that in this example, the above-mentioned acquisition of game item purchase records can only obtain the game prop purchase record of the game character selected by the user in each game. The game prop purchase records obtained are counted and sorted from high to low according to the number of times each game item has been purchased. The game items are configured into the recommended game item set according to the sorting, and the number of game items in the recommended game item set can be obtained based on the number of game characters that can be equipped.

[0085] Furthermore, the game items with different functional characteristics are screened out from the game item purchase records to generate game item sets with different functional characteristics, wherein each of the game items is marked with a functional characteristic; a recommended single game item in each of the game item sets is determined based on the number of purchases; and the recommended game item set is generated based on the recommended single game items.

[0086] Specifically, each game item has its own functional attribute characteristics, such as speed, attack, defense, physics, magic, etc. The corresponding functional characteristics are marked according to the functional attribute characteristics of the game items. The game items and different functional characteristics in the game item purchase records are classified, such as prop 1 (speed), prop 2 (attack), prop 3 (attack), prop 4 (speed), prop 5 (physics), and the classification is speed: prop 1, prop 4; physics: prop 2, prop 4; attack: prop 3. Correspondingly, the game item set with the functional characteristic (speed) is prop 1 and prop 4. According to the game item purchase record, the number of times prop 1 and prop 4 are purchased is obtained. If prop 4 is purchased the most times, prop 4 is recommended as a single game item with the functional characteristic (speed). Similarly, the process of generating recommended single game items with other functional characteristics will not be repeated here. The above-mentioned game item recommendation set has game item requirement configurations with different functional characteristics. For example, if the number of game items that a game character can equip is 6, then the requirement configuration can be set to: speed, attack, attack, physics, defense, and magic. Among them, there is a requirement configuration for the speed functional characteristic, and the above-mentioned prop 4 is allocated to the game item recommendation set. In addition, there may be two requirement configurations for a functional characteristic. Similarly, based on the above example, there are two attacks. If the top two are props 2 and props 3 according to the number of times the game items are purchased from high to low, they will be used as functional characteristic (attack) game item recommendation single piece 1 and game item recommendation single piece 2 respectively, and props 2 and props 3 will be allocated to the game item recommendation set, and the game item recommendation set will reach six game items. It can be understood that in this embodiment, game items are recommended according to functional characteristics, so that the game item recommendation is more reasonable.

[0087] Furthermore, after the step of generating the recommended set of game items based on the recommended single game items, it also includes: generating a recommendation order of each of the recommended single game items in the recommended set of game items based on the purchase time of the recommended single game items in the game item purchase record.

[0088] Specifically, in addition to recording the game items purchased by the game character, the game item purchase record will also record the purchase time of each game item. From the game item purchase record, the time when each game item in the above-mentioned game item recommendation set was purchased in each game is obtained to obtain the average purchase time of each game item. The recommendation order is sorted according to the average purchase time. For example, the average purchase time (1min) of prop 4 with the functional feature of speed is earlier than the average purchase time (4min) of prop 2 with the functional feature of attack. In this case, the recommendation priority of prop 4 is higher than that of prop 2, and prop 4 will be ranked before prop 2 in the recommendation order. The recommendation order is generated according to the prop purchase time in the game item purchase record corresponding to the battle data, which further makes the recommended game items more reasonable.

[0089] Step S30, obtaining current game item data corresponding to the game character, and recommending game items based on the current game item data and the game item recommendation package.

[0090] Furthermore, a first functional feature set is generated based on the functional features of each game item in the current game item data; a second functional feature set is generated based on the functional features of each game item in the game item recommendation set; functional features in the second functional feature set that are identical to those in the first functional feature set are deleted to generate a new second functional feature set; and the game items corresponding to the second functional feature set in the game item recommendation set are recommended in the recommendation order.

[0091] Specifically, in the actual game process, the game items actually purchased by the user may not match the game item recommendation set generated above. For example, the user purchased prop 7 with the functional feature of speed, while the game item corresponding to speed in the game item recommendation set is prop 4. The current game item data purchased by the user is obtained. For example, if prop 7 is obtained, the first functional feature set generated is speed. The second functional feature set generated according to the game item recommendation set is: speed, attack, attack, physics, defense, magic. The speed in the second functional feature set is deleted, and the new second functional feature set is attack, attack, physics, defense, magic. Then the game items corresponding to the new second functional feature set in the game item recommendation set are recommended in the recommended order, that is, prop 4 will no longer be recommended to the user. It can be understood that recommending game items to users based on the game items that the user has already purchased makes the game item recommendation more flexible and intelligent.

[0092] In this embodiment, the game character selected by the user in the current game and the game ranking of the user are obtained, and historical victory battle data is generated based on the game ranking and the game character; the game item purchase record corresponding to each game of the game character is obtained from the historical victory battle data, and a game item recommendation set is generated based on the game item purchase record; the current game item data corresponding to the game character is obtained, and game items are recommended based on the current game item data and the game item recommendation set. On the one hand, the battle data considered as the recommended game item is more in line with the user's current battle environment. On the other hand, the game items to be promoted are obtained from a large amount of battle data that have achieved victory. Compared with the use of a fixed recommendation scheme, the game item recommendation method of the present invention is more objective and flexible. Reduce the learning cost of the game, thereby further improving the gaming experience of new users.

[0093] In addition, this embodiment also provides a game item recommendation device, the game item recommendation device comprising:

[0094] A screening module, used to obtain the game character selected by the current game user and the game ranking of the user, and to screen the original battle data according to the game ranking and the game character to generate historical victory battle data;

[0095] A generation module, used to obtain the game item purchase record corresponding to the game character in each game from the historical victory battle data, and generate a recommended game item set according to the game item purchase record;

[0096] The recommendation module is used to obtain current game item data corresponding to the game character, and recommend game items based on the current game item data and the game item recommendation package.

[0097] Optionally, the screening module is further used for:

[0098] The game character data of the current game is obtained, and the historical victory battle data is filtered according to the game character data of the current game to generate new historical victory battle data.

[0099] Optionally, the screening module is further used for:

[0100] Determine whether the number of samples in the historical victory battle data is less than a preset sample number threshold;

[0101] If the sample quantity is less than the preset sample quantity threshold, a game character is deleted from the current game character data to generate new current game character data, and the step of screening the historical victory battle data according to the current game character data to generate new historical victory battle data is performed;

[0102] If the sample quantity is greater than or equal to the preset sample quantity threshold, the step of obtaining the item purchase record of the game character from the historical victory battle data is executed.

[0103] Optionally, the generating module is further used for:

[0104] Filtering the game items with different functional characteristics from the game item purchase records to generate a set of game items with different functional characteristics, wherein each of the game items is marked with a functional characteristic;

[0105] Determining a recommended single game item for each of the game item sets based on the number of purchases;

[0106] The recommended set of game items is generated based on the recommended single game items.

[0107] Optionally, the generating module is further used for:

[0108] A recommendation order of each of the recommended game items in the recommended game item set is generated according to the purchase time of the recommended game item in the game item purchase record.

[0109] Optionally, the recommendation module is further used to:

[0110] Generate a first functional feature set according to the functional features of each game item in the current game item data;

[0111] generating a second functional feature set according to the functional features of each game item in the recommended game item set;

[0112] Deleting the same functional features in the second functional feature set as those in the first functional feature set to generate a new second functional feature set;

[0113] The game items corresponding to the second functional feature set in the game item recommendation package are recommended according to the recommendation order.

[0114] Optionally, the screening module is further used for:

[0115] From the battle data of the players in the game ranking, the battle data in which the game character exists and the camp in which the game character is located wins is selected as the historical victory battle data.

[0116] The game item recommendation device provided by the present invention adopts the new game item recommendation method in the above embodiment to solve the technical problem that the recommendation scheme of the current game item recommendation method is fixed and the flexibility is not high. Compared with the prior art, the beneficial effects of the new game item recommendation device provided by the embodiment of the present invention are the same as the beneficial effects of the new game item recommendation method provided by the above embodiment, and other technical features in the new game item recommendation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0117] In addition, this embodiment also provides a game item recommendation device, which includes: a memory, a processor, and a game item recommendation program stored in the memory and executable on the processor, and when the game item recommendation program is executed by the processor, the steps of the game item recommendation method as described above are implemented.

[0118] The specific implementation of the new device for recommending game items of the present invention is basically the same as the various embodiments of the new method for recommending game items described above, and will not be described in detail herein.

[0119] In addition, this embodiment further provides a computer-readable storage medium, on which a game item recommendation program is stored. When the game item recommendation program is executed by a processor, the steps of the game item recommendation method as described above are implemented.

[0120] The specific implementation methods of the medium of the present invention are basically the same as the various embodiments of the above-mentioned new method for recommending game items, and will not be repeated here.

[0121] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0122] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, game console, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0124] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for recommending game items, characterized in that: The game item recommendation method comprises the following steps: Obtain the game character selected by the user in the current game and the game ranking of the user, and filter and generate historical victory battle data based on the game ranking and the game character; Acquire current game character data, filter the historical victory battle data according to the current game character data, and generate new historical victory battle data; Acquire a purchase record of game items corresponding to the game character in each game from the new historical victory battle data, and generate a recommended set of game items according to the purchase record of game items; Acquire current game item data corresponding to the game character, and recommend game items based on the current game item data and the game item recommended set; After the step of generating new historical victory battle data, the method further includes: Determine whether the number of samples in the new historical victory battle data is less than a preset sample number threshold; If the sample quantity is less than the preset sample quantity threshold, a game character is deleted from the current game character data to generate new current game character data, and the step of screening the historical victory battle data according to the current game character data to generate new historical victory battle data is performed, wherein, in the process of deleting the game characters, if there is a friendly game character, a friendly game character is deleted; if there is no friendly game character, a pair of opponent game characters is deleted; If the sample quantity is greater than or equal to the preset sample quantity threshold, the step of obtaining the game item purchase record corresponding to each game of the game character from the new historical victory battle data is executed.

2. The game item recommendation method according to claim 1, characterized in that: The step of generating a recommended set of game items according to the game item purchase record comprises: Filtering the game items with different functional characteristics from the game item purchase records to generate a set of game items with different functional characteristics, wherein each of the game items is marked with a functional characteristic; Determining a recommended single game item for each of the game item sets based on the number of purchases; The recommended set of game items is generated based on the recommended single game items.

3. The game item recommendation method according to claim 2, characterized in that: After the step of generating the recommended game item set according to the recommended game item single piece, the method further includes: A recommendation order of each of the recommended game items in the recommended game item set is generated according to the purchase time of the recommended game item in the game item purchase record.

4. The game item recommendation method according to claim 3, characterized in that: The step of recommending game items based on the current game item data and the game item recommendation package comprises: Generate a first functional feature set according to the functional features of each game item in the current game item data; generating a second functional feature set according to the functional features of each game item in the recommended game item set; Deleting the same functional features in the second functional feature set as those in the first functional feature set to generate a new second functional feature set; The game items corresponding to the second functional feature set in the game item recommendation package are recommended according to the recommendation order.

5. The game item recommendation method according to claim 1, characterized in that: The step of generating historical victory battle data based on the game ranking and the game character screening includes: From the battle data of the players in the game ranking, the battle data in which the game character exists and the camp in which the game character is located wins is selected as the historical victory battle data.

6. A game item recommendation device, characterized in that: The game item recommendation device comprises: A screening module, used to obtain the game character selected by the current game user and the game ranking of the user, and to screen the original battle data according to the game ranking and the game character to generate historical victory battle data; Acquire current game character data, filter the historical victory battle data according to the current game character data, and generate new historical victory battle data; After the step of generating new historical victory battle data, the method further includes: Determine whether the number of samples in the new historical victory battle data is less than a preset sample number threshold; If the sample quantity is less than the preset sample quantity threshold, a game character is deleted from the current game character data to generate new current game character data, and the step of screening the historical victory battle data according to the current game character data to generate new historical victory battle data is performed, wherein, in the process of deleting the game characters, if there is a friendly game character, a friendly game character is deleted; if there is no friendly game character, a pair of opponent game characters is deleted; If the sample quantity is greater than or equal to the preset sample quantity threshold, the step of acquiring the game item purchase record corresponding to each game character from the new historical victory battle data is performed; A generation module, used to obtain the game item purchase record corresponding to the game character in each game from the new historical victory battle data, and generate a recommended game item set according to the game item purchase record; The recommendation module is used to obtain current game item data corresponding to the game character, and recommend game items based on the current game item data and the game item recommendation package.

7. A game item recommendation device, characterized in that: The game item recommendation device includes: a memory, a processor, and a game item recommendation program stored in the memory and executable on the processor. When the game item recommendation program is executed by the processor, the steps of the game item recommendation method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The readable storage medium stores a game item recommendation program, which, when executed by a processor, implements the steps of the game item recommendation method according to any one of claims 1 to 5.

Images