Game gift package recommendation method and related device

Abstract

The application provides a game gift package recommendation method and related equipment, the method comprises the following steps: obtaining player portrait features, prop portrait features and prop co-occurrence features; the prop co-occurrence features represent the record information of the player using the prop in the target game; inputting the player portrait features, the prop portrait features and the prop co-occurrence features into a pre-constructed gift package recommendation model to determine a recommended gift package set; wherein the recommended gift package set comprises at least one alternative gift package; determining a target recommended gift package from all alternative gift packages in the recommended gift package set.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method for recommending game gift packs and related equipment. Background Technology

[0002] With the development of game development technology, the variety of items in games is also increasing. Players need to use different items in different game scenarios and game modes, and different player groups have different choices of game items. Therefore, by combining the relationships between items, game scenarios and items, and game modes and items, we can analyze players' item preferences and recommend items or gift packs to players more efficiently and accurately. This can improve the player's gaming experience and generate revenue for game operators. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a method for recommending game gift packs and related equipment to solve the problem of not being able to recommend items in combination with application scenarios.

[0004] To achieve the above objectives, this application provides a method for recommending game gift packs, the method comprising:

[0005] The system acquires player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the player's recorded item usage information in the target game. The player profile features, the item profile features, and the item co-occurrence features are input into a pre-built gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack; The target recommended gift pack is determined from all the alternative gift packs in the recommended gift pack set.

[0006] For the same inventive purpose, this application also provides a game gift pack recommendation device, the device comprising: The acquisition module is configured to acquire player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the player's record information on item usage in the target game; The gift pack generation module is configured to input the player profile features, the item profile features, and the item co-occurrence features into a pre-built gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack; The recommendation module is configured to determine the target recommended gift pack from all candidate gift packs in the recommended gift pack set.

[0007] For the purposes described above, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the game gift pack recommendation method as described in any of the above claims.

[0008] For the purposes described above, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the game gift pack recommendation method described in any one of the above-described methods.

[0009] Based on the same inventive concept, the exemplary embodiments of this disclosure also provide a computer program product, including computer program instructions, which, when run on a computer, cause the computer to execute the game gift pack recommendation method as described in any of the above.

[0010] As can be seen from the above, the game gift pack recommendation method and related equipment provided in this application obtain player profile features, item profile features, and item co-occurrence features; wherein, the item co-occurrence features represent the record information of players using items in the target game. Further, the player profile features, item profile features, and item co-occurrence features are input into a pre-constructed gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack. Finally, the target recommended gift pack is determined from all alternative gift packs in the set of recommended gift packs. This application, while recommending gift packs to target users, analyzes the purchase probability of items by considering the co-occurrence relationships between items used by players in the game, the co-occurrence relationships between game scenes and items, and the co-occurrence relationships between game modes and items. This generates a pool of recommended gift packs and selects the most suitable target game gift pack from these pools. This application can choose the optimal game gift pack to recommend to players based on the relationships between items used by players, the relationships between game scenes and items, and the relationships between game modes and items, thus meeting users' gaming needs and greatly improving their gaming experience. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram illustrating an application scenario of the game gift pack recommendation method provided in this application embodiment; Figure 2A schematic flowchart of a perspective adjustment method provided in an embodiment of this application; Figure 3 A schematic diagram of a game gift pack recommendation device provided in this application embodiment; Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0013] To make the objectives, technical solutions and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0014] It should be noted that, unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the term encompasses the elements or objects listed following the term and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0015] As described in the background section, in large-scale online games, manufacturers provide customized gift packs to game players based on their current status (such as game behavior, game time, events, etc.). These gift packs are usually time-sensitive and personalized, and can accurately target the current pain points of players to provide recommended items or gift packs.

[0016] In the process of developing this invention, the applicant discovered that game scenarios prioritize the player's gaming experience, and the generation and personalized recommendation of gift packs rely heavily on the experience of game designers. Gift pack combinations depend on the expert experience of game designers or the data analysis of the game team; these gift packs, to a certain extent, represent the game developers' understanding of the game. The number of gift packs generated based on expert experience and data analysis is ultimately limited. In the personalized recommendation of game gift packs, similar approaches are used: what items are needed in what scenarios? This expert experience forms specific recommendation strategies to personalize gift pack recommendations for players. Furthermore, with the introduction of various personalization algorithms, game gift pack recommendations have gradually become a recommendation scenario primarily based on conversion rate prediction. However, when the composition and recommendation of gift packs focus more or less on the expert experience of the game team, or simply on conversion rate modeling, few pay attention to the co-occurrence relationships between user usage of items, game scenes and items, and game modes and items in the gift pack generation and recommendation model. There may be brand new gameplay and new gift pack combinations that go beyond expert experience, or there may be important information that cannot be captured by simply using purchase behavior modeling conversion.

[0017] The principles and spirit of this application will be explained in detail below with reference to several representative embodiments.

[0018] refer to Figure 1 This is a schematic diagram illustrating an application scenario of the game gift pack recommendation method provided in this application embodiment.

[0019] This application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, server 102, and data storage system 103 can all be connected via wired or wireless communication networks.

[0020] Among them, the terminal device 101 includes, but is not limited to, desktop computers, mobile phones, mobile computers, tablet computers, media players, smart wearable devices, personal digital assistants (PDAs) or other electronic devices capable of performing the above functions.

[0021] Server 102 is used to provide data processing services for terminal devices.

[0022] Data storage system 103 is used to provide data storage services for terminal devices.

[0023] The data storage system and servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0024] The terminal device connects to a terminal unit via a wired or wireless communication network. The terminal unit can control the viewing direction within the screen. The terminal unit can be, but is not limited to, a flat mouse, touchpad, hover mouse, gamepad, trackball, or any other device capable of generating three-dimensional spatial signals. The terminal device possesses omnidirectional stereoscopic control capabilities. It has six movement directions: forward, backward, left, right, up, and down, and can combine these directions to create forward-right, left-down, and other movement directions.

[0025] The following is combined Figure 1 The above application scenarios are used to describe the game gift pack recommendation method according to exemplary embodiments of this application. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way in this regard. Rather, the embodiments of this application can be applied to any applicable scenario.

[0026] refer to Figure 2 This is a flowchart illustrating a perspective adjustment method provided in an embodiment of this application.

[0027] Step S201: Obtain player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the player's record information on using items in the target game.

[0028] In this embodiment, a game gift pack can be understood as a combination of one or more game items, and its display and purchase channels are generally the game's activity interface, game lobby, or game store. Game items can be understood as paid, free, or limited-time (sold only during specific periods) game items listed in the game's store. In practical applications, the game items can appear individually in the game store or as game items within a game gift pack. This application does not impose any restrictions on this.

[0029] Player profile features consist of one or more characteristics of a specific player group or individual player object; they can be understood as labels that define player attributes. For example, if player A is an instance of player profile features, then player A's labels might include "female," "18 years old," "proficient in support roles," and "game server 1," etc.

[0030] Similarly, the characteristics of an item profile are composed of one or more features of a game package consisting of several game items or a single item. For example, game package A includes item A and item B. The tags for item A may include "attack item", "attack power 10", and "bestselling item"; the tags for item B may include "recovery item", "recovery power 10", and "slow-selling item".

[0031] Item co-occurrence characteristics can be understood as Cartesian product co-occurrence relationships. The Cartesian product co-occurrence operation is an operation used in relational algebra to construct a combination relationship between two relations. The notation for the Cartesian product operation is "X". This application aims to model player interests by utilizing real-world item-to-item, game scene-to-item, and game mode-to-item interactions within the game world. These Cartesian product co-occurrence relationships originate from players' most authentic gameplay and experiences, and better reflect players' genuine interests compared to the expert experience of the design team and ordinary conversion rate prediction models.

[0032] The Cartesian product co-occurrence relationship between items primarily aims to capture the relationships between items collected during gift pack generation. This could be co-occurrence of items used by the user or co-occurrence of items purchased by the user. The Cartesian product co-occurrence relationship between game scenes and items primarily aims to capture the relationship between the user's current scene and items. This could be the user using or purchasing items in a particular scene. The Cartesian product co-occurrence relationship between game modes and items primarily aims to capture the relationship between a user's specific gameplay style and items. This could be the user using or purchasing items in a particular gameplay style.

[0033] As an optional implementation, the co-occurrence relationship of items can be obtained from the game logs. Upon receiving a recommendation instruction, the game server determines the player's game scene and game mode based on the recommendation instruction, obtains the player's item usage records in the game scene and game mode, and determines the item co-occurrence characteristics based on the records.

[0034] Specifically, when a player launches a target game, the game server sends a recommendation request to the recommendation service module. While returning the recommendation result, the recommendation service module also embeds corresponding logs. These game logs mainly include logs of the user's exposure, clicks, conversions, and other related behaviors associated with the gift pack in response to this request. The raw logs are parsed into structured data and stored in the HIVE database for data analysis and to build the training dataset for the corresponding recommendation model.

[0035] HIVE is a data warehouse tool based on Hadoop, used for data extraction, transformation, and loading. It is a mechanism for storing, querying, and analyzing large-scale data stored in Hadoop.

[0036] There are many types of raw logs. Logs about item co-occurrence features mainly record user usage of items in certain game scenarios and modes. These item usage records contain data on the three Cartesian products. The game developers record these logs containing the data, and algorithm engineers parse the co-occurrence relationships of the three Cartesian products from these item usage records. This relationship data is then structured and stored in the HIVE database.

[0037] As an optional embodiment, the item association information can be determined in the following ways; The co-occurrence relationship between items can be illustrated by the following example: when a player is fighting monsters, they need to use both healing and attack power items simultaneously. These two items will always be used by the player while fighting monsters. This is the co-occurrence relationship between items. There may be many such co-occurrence relationships because different players may have different habits of using items, which will result in a large number of Cartesian products of item co-occurrence.

[0038] In one scenario, if the game items include a first game item and a second game item, and the game server responds to a player simultaneously using both items within a preset time interval, the game server determines the first item identifier of the first game item and the second item identifier of the second game item. Further, it constructs a first co-occurrence relationship pair between the first and second game items using a Cartesian product operation based on the first and second item identifiers. For example, the co-occurrence relationship sequence of a player's historical items and items is as follows: t represents the length of the player's historical items and the sequence of co-occurrence relationships between items. This represents the player's i-th item and the co-occurrence relationships between items. Each co-occurrence relationship will have a unique ID to represent it.

[0039] As an optional embodiment, scene association information can be determined in the following ways; The co-occurrence relationship between game scenes and items. For example, users will always use escort items in the escort scene, which forms a co-occurrence relationship between the escort scene and the escort items.

[0040] In one scenario, if the game item includes a first game item and the game scene includes a first game scene, the game server responds to the player using the first game item in the first game scene by determining the first item identifier of the first game item and the first scene identifier of the first game scene. Further, a second co-occurrence relationship pair between the first game item and the first game scene is constructed based on the first item identifier and the first scene identifier through a Cartesian product operation.

[0041] As an optional embodiment, pattern association information can be determined in the following ways; The co-occurrence relationship between game modes and items, for example, if some users create a certain gameplay mode that requires specific items, this also forms a certain co-occurrence relationship.

[0042] In one scenario, if the game item includes a first game item and the game mode includes a first game mode, the game server responds to the player's use of the first game item in the first game mode by determining the first item identifier of the first game item and the first mode identifier of the first game mode. Furthermore, it constructs a third co-occurrence relationship pair between the first game item and the first game mode based on the first item identifier and the first mode identifier through a Cartesian product operation.

[0043] Step S202: Input the player profile features, the item profile features, and the item co-occurrence features into the pre-built gift pack recommendation model to determine the recommended gift pack set; wherein, the recommended gift pack set includes at least one alternative gift pack.

[0044] As an optional embodiment, the gift pack recommendation model may include an input layer, an intermediate layer, and an output layer; inputting item co-occurrence features into the pre-built gift pack recommendation model to determine the item co-occurrence sequence corresponding to the item co-occurrence features; embedding player profile features and item profile features into the item co-occurrence sequence to determine the item co-occurrence matrix; determining several associated items from a pre-stored item set based on the item co-occurrence matrix, and predicting the purchase probability corresponding to the several associated items; determining a recommended gift pack set based on the purchase probability; wherein the recommended gift pack set includes at least one alternative gift pack; the alternative gift pack includes at least one item.

[0045] In practice, the offline training process of the recommendation model generates corresponding gift packs, which are then added to the gift pack library. Simultaneously, a ranking model is generated to serve the ranking module within the recommendation service.

[0046] In practice, the input layer of the recommendation model receives a sample dataset constructed from the HIVE database. The sample dataset mainly includes the Cartesian features, User Cartesian Behaviors, and other types of player profile features and item profile features.

[0047] The intermediate layers of the model can consist of a self-attention network layer and a target-attention network layer. These intermediate layers can model the user's historical Cartesian product co-occurrence relationship behavior sequences. These two attention layers mainly receive the Cartesian product co-occurrence relationships generated in the user's history, which will have a certain time window, such as a Cartesian product relationship sequence generated during the user's 30-day gaming process.

[0048] Among them, the self-attention mechanism network layer is a type of attention mechanism, which is mainly used to model the importance of each behavior in a user behavior sequence. After generating each importance, the corresponding weights are used to fuse the behavior sequence to form a new user representation.

[0049] Target-Attention is a type of attention mechanism in deep networks. It is mainly used to model the corresponding weights between target behavior and user's historical behavior. Each historical behavior will form a correlation importance score with the target behavior, which is used to characterize the correlation between the target behavior and the user's historical behavior.

[0050] Furthermore, the intermediate layers of the model include a Cross Net, which can cross-reference Cartesian product co-occurrence relationships. The Cross Net receives IDs of several co-occurrence relationships, and these IDs are associated by the Cross Net. Common cross-references can be operations such as multiplying or adding two features. The Cross Net can be understood as a more complex cross-reference operation; it can express arbitrarily higher-order combinations while retaining lower-order combinations at each layer. The vectorization of parameters also controls the complexity of the model. Given multiple feature values, it automatically performs the cross-references. Finally, the player profile features and item profile features are embedded into the item co-occurrence sequence to determine the item co-occurrence matrix.

[0051] Cross Net is a commonly used concatenation operation in deep network models, which involves concatenating embedding matrices generated from features from multiple users.

[0052] The model output layer can accept input from intermediate layers. It adopts a fully connected MLP structure, determines several associated items from a pre-stored item set based on the item co-occurrence matrix, predicts the purchase probability of the associated items, and outputs the prediction results. The true label of the prediction results is whether the player will purchase the gift pack.

[0053] Finally, the recommended gift pack set is determined by the purchase probability. Game developers can pre-set a purchase probability threshold according to actual needs. When the predicted purchase probability is greater than the pre-set purchase probability threshold, the corresponding items can be packaged to generate a recommended gift pack set. The recommended gift pack set includes at least one alternative gift pack, and the alternative gift pack includes at least one item.

[0054] As an optional implementation, the gift package recommendation model can be trained using the following method: First, obtain the training dataset, which may include historical player profile features, historical item profile features, and historical item co-occurrence features.

[0055] The training dataset is input into a deep learning framework, and the self-attention mechanism layer and target attention mechanism layer of the deep learning framework determine the co-occurrence sequence of training props corresponding to the historical prop co-occurrence features. The deep learning framework can be selected according to actual needs, including but not limited to: Theano, Caffe / Caffe2, Tensorflow 1.x, Keras, MXNet, PaddlePaddle, CNTK, PyTorch, etc.

[0056] Furthermore, by embedding historical player profile features and historical item profile features into the training item co-occurrence sequence through a feature cross-layer of a deep learning framework, a training item co-occurrence matrix is ​​determined. Based on the training item co-occurrence matrix, several training-related items are identified from a pre-stored training item set, and the training purchase probabilities corresponding to these training-related items are predicted. To enable the model to generate and recommend gift packs based on players' real game data during application, it is preferable to determine the training dataset from players' historical game data.

[0057] Step S203: Determine the target recommended gift pack from all candidate gift packs in the recommended gift pack set.

[0058] As an optional embodiment, all candidate gift packs in the recommended gift pack set can be scored according to preset rules, and all candidate gift packs can be sorted from high to low according to the scores, and the candidate gift pack with the highest score can be determined as the target recommended gift pack.

[0059] As an optional implementation, selection criteria for the target recommended gift pack can also be set according to the actual situation, such as the price, type, or discount level of the recommended gift pack.

[0060] It's important to note that the gift pack generation library accepts gift packs generated by the recommendation model, and new gift packs are continuously generated as the recommendation model changes. Based on player profile characteristics, different gift packs will be recalled for different players. The recommendation model provides the ability to rank the gift packs and select the most suitable gift pack for each user.

[0061] It should be noted that, regarding the data and information obtained in this application, it is understood that before using the technical solutions disclosed in the various embodiments of this application, the user should be informed of the type, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and the user's authorization should be obtained.

[0062] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0063] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0064] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0065] As can be seen from the above, the game gift pack recommendation method and related equipment provided in this application obtain player profile features, item profile features, and item co-occurrence features; wherein, the item co-occurrence relationship represents the record information of players using items in the target game. Further, the player profile features, item profile features, and item co-occurrence features are input into a pre-constructed gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack. Finally, the target recommended gift pack is determined from all alternative gift packs in the set of recommended gift packs. This application, while recommending gift packs to target users, analyzes the purchase probability of items by considering the co-occurrence relationships between items used by players in the game, the co-occurrence relationships between game scenes and items, and the co-occurrence relationships between game modes and items. This generates a pool of recommended gift packs and selects the most suitable target game gift pack from these pools. This application can choose the optimal game gift pack to recommend to players based on the relationships between items used by players, the relationships between game scenes and items, and the relationships between game modes and items, thus meeting users' gaming needs and greatly improving their gaming experience.

[0066] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0067] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a game gift pack recommendation device.

[0069] refer to Figure 3 This is a schematic diagram of a game gift pack recommendation device provided in an embodiment of this application.

[0070] The device includes: The acquisition module 301 is configured to acquire player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the record information of the player's use of items in the target game; The gift pack generation module 302 is configured to input the player profile features, the item profile features, and the item co-occurrence features into a pre-built gift pack recommendation model to determine a recommended gift pack set; wherein, the recommended gift pack set includes at least one alternative gift pack; The recommendation module 303 is configured to determine a target recommended gift pack from all candidate gift packs in the recommended gift pack set.

[0071] Optionally, the acquisition module 301 is further configured to: In response to receiving a recommendation instruction, the game scene and game mode in which the player is located are determined based on the recommendation instruction; Obtain the record information of the player's use of items in the game scene and the game mode; The co-occurrence characteristics of the props are determined based on the recorded information.

[0072] Optionally, the co-occurrence feature of the props includes any one of the following: prop association information between at least two game props, scene association information between props and game scenes, and mode association information between props and game modes.

[0073] Optionally, the game props include: a first game prop and a second game prop; The gift pack generation module 302 is also configured to: In response to the player using the first game item and the second game item simultaneously within a preset time interval, the first item identifier of the first game item and the second item identifier of the second game item are determined. A first co-occurrence relationship pair between the first game item and the second game item is constructed using Cartesian product operations based on the first item identifier and the second item identifier.

[0074] Optionally, the game props include: a first game prop; the game scene includes: a first game scene; The gift pack generation module 302 is also configured to: In response to the player using the first game item in the first game scene, a first item identifier of the first game item and a first scene identifier of the first game scene are determined. A second co-occurrence relationship pair between the first game item and the first game scene is constructed using Cartesian product operations based on the first item identifier and the first scene identifier.

[0075] Optionally, the game props include: a first game prop; the game mode includes: a first game mode; The gift pack generation module 302 is also configured to: In response to the player using the first game item in the first game mode, a first item identifier of the first game item and a first mode identifier of the first game mode are determined. A third co-occurrence relationship between the first game item and the first game mode is constructed using Cartesian product operations based on the first item identifier and the first mode identifier.

[0076] Optionally, the gift pack generation module 302 is further configured to: The co-occurrence features of the items are input into a pre-built gift pack recommendation model to determine the co-occurrence sequence of items corresponding to the co-occurrence features; The player profile features and the item profile features are embedded into the item co-occurrence sequence to determine the item co-occurrence matrix; Based on the item co-occurrence matrix, several associated items are determined from a pre-stored item set, and the purchase probability corresponding to the several associated items is predicted. The recommended gift pack set is determined based on the purchase probability; wherein the recommended gift pack set includes at least one alternative gift pack; and the alternative gift pack includes at least one item.

[0077] Optionally, the recommendation module 303 is further configured to: All candidate gift packs in the recommended gift pack set are scored according to preset rules, and all candidate gift packs are sorted from high to low according to the scores; The candidate gift pack with the highest rating is determined as the target recommended gift pack.

[0078] Optionally, the gift package recommendation model is obtained through training, and the training method includes: Obtain a training dataset; wherein the training dataset includes historical player profile features, historical item profile features, and historical item co-occurrence features; The training dataset is input into a deep learning framework, and the self-attention mechanism layer and target attention mechanism layer of the deep learning framework are used to determine the training prop co-occurrence sequence corresponding to the historical prop co-occurrence features; The historical player profile features and the historical item profile features are embedded into the training item co-occurrence sequence through the feature cross layer of the deep learning framework to determine the training item co-occurrence matrix. Based on the co-occurrence matrix of the training props, a number of training-related props are determined from the pre-stored set of training props, and the training purchase probability corresponding to the number of training-related props is predicted.

[0079] The apparatus described above is used to implement the corresponding game gift pack recommendation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0080] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the game gift pack recommendation method described in any of the above embodiments.

[0081] Figure 4 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0082] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0083] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0084] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0085] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0086] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0087] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0088] The electronic devices described above are used to implement the corresponding game gift pack recommendation methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0089] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the game gift pack recommendation method as described in any of the above embodiments.

[0090] The aforementioned non-transitory computer-readable storage media can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0091] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the game gift pack recommendation method as described in any of the embodiments in the exemplary method section above, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0092] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, method, or computer program product. Therefore, this disclosure can be implemented as entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this disclosure can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0093] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (not exhaustive) of a computer-readable storage medium may include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0095] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0096] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] It should be understood that each block of a flowchart and / or block diagram, as well as combinations of blocks in a flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine that, when executed by a computer or other programmable data processing device, creates means for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0098] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce a product comprising an instruction apparatus that implements the functions / operations specified in the boxes of a flowchart and / or block diagram.

[0099] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus can provide a process for implementing the functions / operations specified in the boxes of a flowchart and / or block diagram.

[0100] Furthermore, although the operations of the methods of this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Rather, the steps depicted in the flowcharts may be executed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0101] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0102] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be interpreted in the broadest sense, thereby encompassing all such modifications and equivalent structures and functions.

Claims

1. A method for recommending game gift packs, characterized in that, The method includes: The system acquires player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the player's recorded item usage information in the target game; the item co-occurrence features include any one of the following: item association information between at least two game items, scene association information between an item and a game scene, and mode association information between an item and a game mode; the game items include: a first game item and a second game item; The player profile features, the item profile features, and the item co-occurrence features are input into a pre-built gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack; The target recommended gift pack is determined from all the alternative gift packs in the recommended gift pack set; The method further includes determining the item association information by: in response to the player using the first game item and the second game item simultaneously within a preset time interval, determining the first item identifier of the first game item and the second item identifier of the second game item; and constructing a first co-occurrence relationship pair between the first game item and the second game item based on the first item identifier and the second item identifier through a Cartesian product operation.

2. The method according to claim 1, characterized in that, Acquire item co-occurrence characteristics, including: In response to receiving a recommendation instruction, the game scene and game mode in which the player is located are determined based on the recommendation instruction; Obtain the record information of the player's use of items in the game scene and the game mode; The co-occurrence characteristics of the props are determined based on the recorded information.

3. The method according to claim 1, characterized in that, The game props include: a first game prop; the game scene includes: a first game scene; The method further includes determining the scene association information through the following means: In response to the player using the first game item in the first game scene, a first item identifier of the first game item and a first scene identifier of the first game scene are determined. A second co-occurrence relationship pair between the first game item and the first game scene is constructed using Cartesian product operations based on the first item identifier and the first scene identifier.

4. The method according to claim 1, characterized in that, The game items include: a first game item; the game modes include: a first game mode; The method further includes determining the pattern association information by the following means: In response to the player using the first game item in the first game mode, a first item identifier of the first game item and a first mode identifier of the first game mode are determined. A third co-occurrence relationship between the first game item and the first game mode is constructed using Cartesian product operations based on the first item identifier and the first mode identifier.

5. The method according to any one of claims 1, 3, and 4, characterized in that, The step of inputting the player profile features, the item profile features, and the item co-occurrence features into a pre-built gift pack recommendation model to determine the recommended gift pack set includes: The co-occurrence features of the items are input into a pre-built gift pack recommendation model to determine the co-occurrence sequence of items corresponding to the co-occurrence features; The player profile features and the item profile features are embedded into the item co-occurrence sequence to determine the item co-occurrence matrix; Based on the item co-occurrence matrix, several associated items are determined from a pre-stored item set, and the purchase probability corresponding to the several associated items is predicted. The recommended gift pack set is determined based on the purchase probability; wherein the recommended gift pack set includes at least one alternative gift pack; and the alternative gift pack includes at least one item.

6. The method according to claim 1, characterized in that, The method further includes: All candidate gift packs in the recommended gift pack set are scored according to preset rules, and all candidate gift packs are sorted from high to low according to the scores; The candidate gift pack with the highest rating is determined as the target recommended gift pack.

7. The method according to claim 1, characterized in that, The gift package recommendation model is obtained through training, and the training method includes: Obtain a training dataset; wherein the training dataset includes historical player profile features, historical item profile features, and historical item co-occurrence features; The training dataset is input into a deep learning framework, and the self-attention mechanism layer and target attention mechanism layer of the deep learning framework are used to determine the training prop co-occurrence sequence corresponding to the historical prop co-occurrence features; The historical player profile features and the historical item profile features are embedded into the training item co-occurrence sequence through the feature cross layer of the deep learning framework to determine the training item co-occurrence matrix. Based on the co-occurrence matrix of the training props, a number of training-related props are determined from the pre-stored set of training props, and the training purchase probability corresponding to the number of training-related props is predicted.

8. A game gift pack recommendation device, characterized in that, The device includes: The acquisition module is configured to acquire player profile features, item profile features, and item co-occurrence features; the item co-occurrence features represent the player's record information on using items in the target game; the item co-occurrence features include any one of the following: item association information between at least two game items, scene association information between an item and a game scene, and mode association information between an item and a game mode; the game items include: a first game item and a second game item; The gift pack generation module is configured to input the player profile features, the item profile features, and the item co-occurrence features into a pre-built gift pack recommendation model to determine a set of recommended gift packs; wherein, the set of recommended gift packs includes at least one alternative gift pack; The recommendation module is configured to determine the target recommended gift pack from all candidate gift packs in the recommended gift pack set; The device further includes: a determining module configured to determine a first item identifier of the first game item and a second item identifier of the second game item in response to the player simultaneously using the first game item and the second game item within a preset time interval; and a constructing module configured to construct a first co-occurrence relationship pair between the first game item and the second game item based on the first item identifier and the second item identifier through a Cartesian product operation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

11. A computer program product, characterized in that, Including computer program instructions, when the When computer program instructions are executed on a computer, the computer causes the computer to perform the method as described in any one of claims 1 to 7.

Images