CN110807150A - Information processing method and apparatus, electronic device and computer-readable storage medium - Google Patents

Abstract

Embodiments of the present invention provide an information processing method and apparatus, an electronic device, and a computer-readable storage medium, which belong to the technical field of computers and communications. The method includes: determining a first character of a target object; obtaining first object data of the target object according to the first character attribute information of the first character; obtaining item attribute information of an object to be recommended; The first object data and the item attribute information are processed, and a first target item recommended to the first character of the target object is determined from the items to be recommended. The technical solutions of the embodiments of the present invention provide an information processing method, which can improve the accuracy of personalized recommendation of items to be recommended.

Description

Information processing method and apparatus, electronic device and computer-readable storage medium

technical field

The present invention relates to the field of computer and communication technologies, and in particular, to an information processing method and apparatus, an electronic device, and a computer-readable storage medium.

Background technique

In recent years, web games have developed rapidly and have become an important entertainment activity. Games can not only allow players to participate, but also enhance game fun, enhance user experience, enhance user stickiness, and increase the revenue of game platforms by selling virtual goods (such as props).

There are often many kinds of virtual goods in games. At the same time, games have high real-time requirements, and users have the need to quickly find the target props they want. Therefore, whether the game platform can provide users with an efficient and accurate information screening system is the most important thing. important.

It should be noted that the information disclosed in the above Background section is only for enhancing understanding of the background of the invention, and therefore may contain information that does not form the prior art known to a person of ordinary skill in the art.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide an information processing method and apparatus, an electronic device, and a computer-readable storage medium, which can improve the accuracy of personalized recommendation of items to be recommended.

Other features and advantages of the present invention will become apparent from the following detailed description, or be learned in part by practice of the present invention.

An embodiment of the present invention provides an information processing method, the method includes: determining a first role of a target object; obtaining first object data of the target object according to the first role attribute information of the first role; obtaining The item attribute information of the item to be recommended; the first object data and the item attribute information are processed through a neural network model, and the first target recommended to the first character of the target object is determined from the item to be recommended thing.

An embodiment of the present invention provides an information processing device, the device includes: a first object role determination module configured to determine a first role of a target object; a first object data acquisition module configured to The first character attribute information is used to obtain the first object data of the target object; the item attribute information acquisition module is configured to obtain the item attribute information of the item to be recommended; the first target item determination module is configured to use a neural network model for the The first object data and the item attribute information are processed, and the first target item recommended to the first character of the target object is determined from the items to be recommended.

Embodiments of the present invention provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the information processing method described in the foregoing embodiments is implemented.

An embodiment of the present invention provides an electronic device, including: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors , causing the one or more processors to implement the information processing method described in the above embodiments.

In the technical solutions provided by some embodiments of the present invention, by determining the first role of the target object, and according to the first role attribute information of the first role, the first object data of the target object is obtained, and the Item attribute information of the item to be recommended, so that the first object data and the item attribute information can be processed through a neural network model, and the item to be recommended is determined from the item to be recommended to the first character of the target object. a target item. On the one hand, by comprehensively considering the rich role attribute information of the target object and the rich item attribute information of the item to be recommended, the target item to be recommended is determined, which can improve the accuracy of the personalized recommendation of the item; On the one hand, the nonlinear neural network model is used to describe the complex interaction between the target object and the object to be recommended, which can achieve the purpose of enhancing the interpretability of the model and improving the recommendation effect.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort. In the attached image:

FIG. 1 shows a schematic diagram of an exemplary system architecture of an information processing method or an information processing apparatus to which an embodiment of the present invention can be applied;

FIG. 2 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present invention;

FIG. 3 schematically shows a flowchart of an information processing method according to an embodiment of the present invention;

FIG. 4 schematically shows a flowchart of an information processing method according to another embodiment of the present invention;

5 schematically shows a flowchart of an information processing method according to yet another embodiment of the present invention;

FIG. 6 shows a schematic diagram of the processing procedure of step S320 shown in FIG. 3 in an embodiment;

FIG. 7 shows a schematic diagram of the processing procedure of step S340 shown in FIG. 3 in an embodiment;

FIG. 8 shows a schematic diagram of the processing procedure of step S341 shown in FIG. 7 in an embodiment;

FIG. 9 schematically shows a schematic diagram of a first embedded sub-model according to an embodiment of the present invention;

FIG. 10 shows a schematic diagram of the processing procedure of step S342 shown in FIG. 7 in an embodiment;

FIG. 11 schematically shows a schematic diagram of a second embedding sub-model according to an embodiment of the present invention;

FIG. 12 schematically shows a schematic structural diagram of a neural network model according to an embodiment of the present invention;

Fig. 13 shows a schematic diagram of the processing procedure of step S343 shown in Fig. 7 in an embodiment;

FIG. 14 schematically shows a schematic structural diagram of a first neural network sub-model according to an embodiment of the present invention;

Fig. 15 shows a schematic diagram of the processing procedure of step S344 shown in Fig. 7 in an embodiment;

FIG. 16 schematically shows a schematic structural diagram of a second neural network sub-model according to an embodiment of the present invention;

Fig. 17 shows a schematic diagram of the processing procedure of step S345 shown in Fig. 7 in an embodiment;

FIG. 18 schematically shows a schematic interface diagram of martial arts introduction according to an embodiment of the present invention;

19 and 20 schematically illustrate interface diagrams of character detail customization according to an embodiment of the present invention;

FIG. 21 schematically shows a schematic interface diagram of character creation completion according to an embodiment of the present invention;

FIG. 22 schematically shows a schematic diagram of a game interface according to an embodiment of the present invention;

FIG. 23 schematically shows a schematic interface diagram of a role attribute according to an embodiment of the present invention;

FIG. 24 schematically shows a schematic interface diagram of a game mall according to an embodiment of the present invention;

FIG. 25 schematically shows a block diagram of an information processing apparatus according to an embodiment of the present invention.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present invention. However, those skilled in the art will appreciate that the technical solutions of the present invention may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present invention.

The block diagrams shown in the figures are merely functional entities and do not necessarily necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices entity.

The flowcharts shown in the figures are only exemplary illustrations and do not necessarily include all contents and operations/steps, nor do they have to be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

FIG. 1 shows a schematic diagram of an exemplary system architecture 100 to which an information processing method or an information processing apparatus according to an embodiment of the present invention may be applied.

As shown in FIG. 1 , the system architecture 100 may include one or more of terminal devices 101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs. For example, the server 105 may be a server cluster composed of multiple servers, or the like.

The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, smart home devices, etc. .

The server 105 may be a server that provides various services. For example, the user uses the terminal device 103 (it may also be the terminal device 101 or 102 ) to open the game client, and determines his game role in the game on the game client, and sends a request to the server 105 . The server 105 can obtain the character attribute information of the corresponding game character based on the game character information carried in the request, thereby obtaining the object data of the user; at the same time, the server 105 can also obtain the item attribute information of the items to be recommended in the game mall. The neural network model processes the user's object data and the item attribute information of each item to be recommended, determines the target item from these items to be recommended, and returns the target item to the terminal device 103, so that the user can view it on the terminal device 103 A target item recommended for its currently selected game character.

For another example, the terminal device 103 (it may also be the terminal device 101 or 102 ) may be a smart TV, a VR (Virtual Reality, virtual reality)/AR (Augmented Reality, augmented reality) head-mounted display, or an instant messaging, navigation, video For mobile terminals such as applications (application, APP), such as smart phones, tablet computers, etc., the user can send various requests to the server 105 through the smart TV, VR/AR head-mounted display, or the instant messaging and video APP. The server 105 may, based on the request, obtain feedback information in response to the request and return it to the smart TV, VR/AR head-mounted display or the instant messaging, video APP, and then through the smart TV, VR/AR head-mounted display or the instant messaging , The video APP will display the feedback information returned.

FIG. 2 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present invention.

It should be noted that the computer system 200 of the electronic device shown in FIG. 2 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present invention.

As shown in FIG. 2 , the computer system 200 includes a central processing unit (CPU, Central Processing Unit) 201, which can be loaded into a random device according to a program stored in a read-only memory (ROM, Read-Only Memory) 202 or from a storage part 208 A program in a memory (RAM, Random Access Memory) 203 is accessed to execute various appropriate operations and processes. In the RAM 203, various programs and data necessary for system operation are also stored. The CPU 201 , the ROM 202 and the RAM 203 are connected to each other through a bus 204 . An input/output (I/O) interface 205 is also connected to the bus 204 .

The following components are connected to the I/O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. ; a storage part 208 including a hard disk and the like; and a communication part 209 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I/O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 210 as needed so that a computer program read therefrom is installed into the storage section 208 as needed.

In particular, the processes described below with reference to the flowcharts may be implemented as computer software programs according to embodiments of the present invention. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 209 and/or installed from the removable medium 211 . When the computer program is executed by the central processing unit (CPU) 201, various functions defined in the method and/or apparatus of the present application are performed.

It should be noted that the computer-readable storage medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The 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 a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM (Erasable Programmable Read Only Memory) or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or the above any suitable combination. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium that can be sent, propagated, or transmitted for use by or in connection with the instruction execution system, apparatus, or device program of. The program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF (Radio Frequency, radio frequency), etc., or any suitable combination of the above.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The modules and/or units and/or subunits described in the embodiments of the present invention may be implemented in software or in hardware. The described modules and/or units and/or subunits It can also be set in the processor. Wherein, the names of these modules and/or units and/or sub-units do not constitute limitations on the modules and/or units and/or sub-units themselves under certain circumstances.

As another aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium may be included in the electronic device described in the above-mentioned embodiments; in electronic equipment. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed by an electronic device, the electronic device enables the electronic device to implement the methods described in the following embodiments. For example, the electronic device can implement the various steps shown in FIG. 3 or FIG. 4 or FIG. 5 or FIG. 6 or FIG. 7 or FIG. 8 or FIG. 10 or FIG. 13 or FIG. 15 or FIG.

Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.

Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, including both hardware-level technology and software-level technology. The basic technologies of artificial intelligence generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.

Machine Learning (ML) is a multi-field interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in how computers simulate or realize human learning behaviors to acquire new knowledge or skills, and to reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications are in all fields of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, teaching learning and other technologies.

With the research and progress of artificial intelligence technology, artificial intelligence technology has been researched and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, autonomous driving, drones It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important value.

The solutions provided by the embodiments of the present invention involve technologies such as artificial intelligence machine learning, and are specifically described by the following embodiments:

First, some terms involved in the following embodiments are explained.

Deep learning: Deep learning is a learning process that is based on a deep neural network, and finally obtains a one-to-one mapping function between the input data and the target data through optimization methods such as gradient descent. For example, given a person's age, gender and other information, it is hoped that this information can be used to predict whether the person likes pets, then the input data is the person's age, gender and other information, and the target data is "whether this person likes pets". What is needed is to construct a proper mapping function that can map the input data to the target data. In this way, given information about another person, it is possible to know whether that person likes pets. Deep learning is the process of solving this mapping function based on a large amount of data, and using a deep neural network to simulate this function.

Collaborative Filtering (CF): Collaborative filtering is a type of model algorithm used in recommender systems. The core of its content is to infer which users (or products) are more similar through past data. Therefore, this type of Models can be simply divided into "user-based (user-based)" and "item-based (item-based)", the former looks for which users are more similar, and the latter looks for which items are more similar. For the former, after knowing the similar users, the products purchased by the user before can be recommended to other users who are similar to the user. The latter means that after knowing a similar product, a user can purchase the product, infer that the user likes other products similar to the product, and recommend other similar products to the user.

Metric: A custom mapping function that needs to meet the 4 requirements met by the metric and is used to measure the distance between any two points in the domain space. Simply put, defining a new metric is defining a new distance.

In the embodiments of the present invention, game scenarios are used as examples for illustration, but it can be understood that the technical solutions provided in the embodiments of the present invention are not limited to be applied to game scenarios, and can also be applied to other recommended scenarios.

Among them, the data in the game recommendation scene has the following characteristics:

First, the data is massive. The game platform provides services for users ranging from millions to tens of millions. During the process of playing the game, the attributes and behavior of users will change dynamically, and they will choose to purchase different game products with the update of time, resulting in the daily accumulation of large amount of game products on the game platform. User behavior data at scale.

Second, the data is high-dimensional. The data in the game has the characteristics of high dimensionality. In addition to the user's personal portrait (such as the user's real age, gender, geographic location, and other real attribute information of the user), the attributes associated with the user also include the user's selected attributes. Game character attributes (such as attribute information such as the game character's name, gender, occupation, etc.), etc. At the same time, there are many categories of game commodities, and they also have multi-dimensional attributes.

Third, complex structural associations. Compared with e-commerce, social networking and other platforms, there is not a simple one-to-one correspondence between users and the products they purchase in game platforms. For example, a user can use different game characters at different times, such as when a user is using a game character. A may frequently purchase game commodity a when using game character B, but may not purchase game commodity a when using game character B. That is, in the case of different game characters, the choices made by the same user may be different.

Based on the above, when designing the recommendation method in the game scenario, the data scale and data characteristics in this scenario need to be considered.

Collaborative filtering is a type of recommendation algorithm in related technologies. It uses collaborative information in a large amount of data to make recommendations based on the following two starting points: (1) users with similar interests may be interested in the same things; (2) users May prefer things that are similar to what they have already purchased.

However, traditional collaborative filtering-based recommendation methods often only model the ID (identification) and rating matrix of users and products when learning the vector representation of users and products, ignoring or underutilizing rich background information. , that is, in collaborative filtering, if a user in the rating matrix buys a certain product, the corresponding score value is 1, otherwise it is 0, but the attribute information of each dimension of the user and the product is not considered.

CTR (Click-through rate prediction, click-through rate prediction) is not only used in CTR prediction, but also in scenarios such as product ranking of recommendation systems. Compared with the CF model, CTR directly calculates the probability of the target product being clicked by the target user through the input data features. Its general formula can be expressed as:

y=f(X) (1)

Where X is the input data feature matrix, y is the probability value between [0, 1], indicating the probability of the input data being clicked. For example, logistic regression (LR, logistic regression) and factorization machine (FM, factorization machine) can be used in the related art. Among them, the LR model is calculated as follows:

where θ is a learnable parameter. The features of each dimension in the LR model are independent of each other, and the combination of features often helps to improve the prediction effect. Based on this, FM considers the intersection between features. In the case of considering the intersection of two features, the FM model formula is as follows:

Among them, n represents the dimension of the input data X, n is a positive integer greater than or equal to 1, x _i and x _j represent the value of the i-th bit and the j-th bit in X respectively, and their values can be 0 or 1, for example. θ and w _ij are learnable parameters obtained during model training.

Although feature intersection can improve the prediction performance, when calculating the user's purchase probability of a product, a simple vector inner product operation is still used. Such traditional machine learning methods can only model the linear relationship between features, and the model ability has There are certain limitations. The predicted score value is calculated directly based on the characteristics, and the collaborative information of users or products will not be used.

FIG. 3 schematically shows a flowchart of an information processing method according to an embodiment of the present invention. The methods provided in the embodiments of the present invention may be executed by any electronic device with computing processing capabilities, such as one or more of the terminal devices 101 , 102 , and 103 in FIG. 1 and/or the server 105 . In the following example description, the terminal device is used as the execution subject for example description.

As shown in FIG. 3 , the information processing method provided by the embodiment of the present invention may include the following steps.

In step S310, the first role of the target object is determined.

In this embodiment of the present invention, the target object may be a certain game player of a certain game of a certain game platform. After the game player logs in to the game platform with his game account, he can select one game character A from the multiple game characters in the game as his first character at the current time t1.

In step S320, first object data of the target object is obtained according to the first character attribute information of the first character.

In an exemplary embodiment, the first character attribute information of the first character may include any one or more of identity information of the first character, current level information, and/or current operation information, and the like.

Here is an example of an RPG (Role-playing game, role-playing game) game, assuming that it has seven pre-set identities: escort, fast hunter, hunter, killer, music player, ranger, and scribe, each of which has Corresponding to the unique Jianghu industry, the target object can choose to join one of them.

In this RPG game, each identity can be further divided into three levels as an advanced identity, and each advanced level can obtain more powerful manufacturing skills and identity skills. Players can obtain experience points by completing daily tasks, and then consume experience points to learn more related skills and status advancement. For example, the status of scribes can include three grades of scribes, literati, and state clerks in ascending order. It can be set that scribes are the lowest rank, and state clerks are the highest. Le Ling's identity can include three successively increasing levels: Le Ling, actor, and famous actor. Killer identities can include three levels of killer, assassin, and killing god. The status of catching fast can include three levels of catching fast, catching head and catching god in order. Escort status can include escort, dart head, god dart three successively increasing levels. Ranger status can include three levels of ranger, Ren Xia, and hero. The identity of the hunter can include three levels of the hunter, the hunter, and the hunter.

In this RPG game, game characters with different identities can perform different operations (eg, tasks and/or gameplay), and game characters with the same identity can also perform different operations at different levels.

It should be understood that the above-mentioned identity information, current level information, current operation information, etc. are only used for illustration. In different application scenarios, or other games of different types, or other games of the same type, the first character attribute Information can be adaptively adjusted.

In step S330, the item attribute information of the item to be recommended is obtained.

Still taking a game scene as an example, the item to be recommended may be a game mall, such as a prop, in the game mall of the target game selected by the target object. At this time, the item attribute information may include, for example, the category to which each item belongs, the functions that can be completed, the identity of the corresponding game character, the level of the corresponding game character, the operation of the corresponding game character, etc. Any one or variety. For example, the props used for the game characters to practice light work, or the props used for the game characters to improve their internal strength, and so on. Specifically, the item attribute information can be set according to actual needs.

In step S340, the first object data and the item attribute information are processed through a neural network model, and a first target item recommended to the first character of the target object is determined from the items to be recommended.

The information processing method provided by the embodiment of the present invention determines the first role of the target object, and obtains the first object data of the target object according to the first role attribute information of the first role, and also obtains the information of the object to be recommended. Item attribute information, so that the first object data and the item attribute information can be processed through a neural network model, and the first target item recommended to the first character of the target object can be determined from the items to be recommended. On the one hand, by comprehensively considering the rich role attribute information of the target object and the rich item attribute information of the item to be recommended, the target item to be recommended is determined, which can improve the accuracy of the personalized recommendation of the item; On the one hand, the nonlinear neural network model is used to describe the complex interaction between the target object and the object to be recommended, which can achieve the purpose of enhancing the interpretability of the model and improving the recommendation effect.

FIG. 4 schematically shows a flowchart of an information processing method according to another embodiment of the present invention. As shown in FIG. 4 , compared with the foregoing embodiment, the method provided by the embodiment of the present invention is different in that the following steps may be further included.

In step S410, the second role of the target object is determined.

For example, at another time t2, the game player may be replaced with another game character B as the second character.

In step S420, second object data of the target object is obtained according to the second character attribute information of the second character.

In an exemplary embodiment, the second character attribute information of the second character may include any one or more of the identity information of the second character, current level information, and/or current operation information, and the like.

In step S430, the second object data and the item attribute information are processed through the neural network model, and a second target item recommended to the second character of the target object is determined from the items to be recommended .

In this embodiment of the present invention, the same user (for example, a game player) can select different game characters in the same game at different times. It recommends the props required by the low-level escort; at t2, when the game character B is selected, which is a high-level killer, the system will recommend the props required by the high-level killer to it, that is, the user chooses different game characters, which may have They belong to different sects, different identities and other attributes, and they will perform corresponding operations. For example, one type of props is needed for spell training, and another type of props is needed for mind training. A prop pool can be preset, and there are various props in the prop pool, and each prop has corresponding item attribute information. When the game character selected by the user changes and/or the attribute value of the selected game character changes , the type of props recommended to it by the system can change, or the arrangement order of props recommended to it can change. In the embodiment of the present invention, the same user may make different choices for the same game item under different game characters. This is because the game item in the game scene is the prop of the game character, and the purchase behavior is associated with the character attribute. . In addition, under the same game character, the same user may make different choices for the same game item if his character attributes change. For example, the character may not need to buy a luxurious item at a low level. , as the level increases, there may be a purchase behavior for this item.

FIG. 5 schematically shows a flowchart of an information processing method according to yet another embodiment of the present invention. As shown in FIG. 5 , compared with the foregoing embodiments, the method provided by the embodiment of the present invention is different in that the following steps may be further included.

In step S510, the historical role of the target object is obtained.

In step S520, the historical object data of the target object is obtained according to the historical role attribute information of the historical role.

In step S530, a historical operation record of the target object on the item to be recommended is obtained.

In step S540, according to the historical operation records, the labels of the historical object data and the item attribute information are determined to generate a training data set.

In the embodiment of the present invention, the used neural network model may be trained in advance. A training dataset is first constructed when training a model. Here, the historical operation record of the target object to the recommendation is used. Still taking the above game scene as an example, the items to be recommended can be each item in the item pool, and the historical operation record can be the purchase record of each item in the history of the game player, but the present invention is not limited to this, it can also be The game player has a history of using each item, a preview record, and the like.

In the embodiment of the present invention, the construction of the training data set may be in the following form:

待推荐物及其物品属性信息组成的

用户相关数据包含的域有：[user_id,user_feature_1,user_feature_2,…]，商品相关的数据包含的域有：[item_id,item_feature_1,item_feature_2,…]，其中id和各feature域均用数值表示，[feature_1,feature_2,…]称为属性信息(context)。其中游戏中用户的feature不是固定不变的，而是随着时间变化，所以同样的id可以对应多个属性信息。The data can be divided into two parts: the first object data composed of the target object and its first role attribute information

It consists of the item to be recommended and its item attribute information

The domains included in the user-related data are: [user_id, user_feature_1, user_feature_2,…], and the domains included in the product-related data are: [item_id, item_feature_1, item_feature_2,…], where id and each feature field are represented by numerical values, [feature_1 ,feature_2,…] is called attribute information (context). Among them, the features of users in the game are not fixed, but change with time, so the same id can correspond to multiple attribute information.

是目标对象id和目标对象的第一角色的第一角色属性信息的拼接，因为同一个目标对象在不同时间可以处于不同游戏角色，所以一个目标对象可以对应多个

例如目标对象id＝1，在context＝[0.1,0.3,…,0.2]时对应的

在id＝1，context＝[0.5,0.1,…,0.1]时对应的

这种表示方式的含义为：在特定游戏角色下的目标对象。(1)

It is the splicing of the target object id and the first character attribute information of the first character of the target object. Because the same target object can be in different game characters at different times, one target object can correspond to multiple

For example, target object id=1, corresponding to when context=[0.1,0.3,...,0.2]

Corresponding when id=1, context=[0.5,0.1,...,0.1]

The meaning of this representation is: the target object under a specific game character.

可以是游戏商品id与其物品属性信息的拼接。(2)

It can be the splicing of the game item id and its item attribute information.

和

对应一个二值的label，0表示该目标对象在该角色属性信息下没有购买该道具，1表示该目标对象在该角色属性信息下购买了该道具，具体的标签数值可以进行自主设定。(3) Label: each pair

and

Corresponding to a binary label, 0 indicates that the target object did not purchase the item under the character attribute information, 1 indicates that the target object purchased the item under the character attribute information, and the specific label value can be set independently.

In step S550, the neural network model is trained by using the training data set.

和

输入至该神经网络模型，该神经网络模型输出预测值，根据预测值和真实标签计算损失函数，以最小化损失函数为目标计算参数梯度，梯度反向传播以更新模型参数。In this embodiment of the present invention, during the model training process, the training data set may be

and

Input to the neural network model, the neural network model outputs the predicted value, calculates the loss function according to the predicted value and the real label, calculates the parameter gradient with the goal of minimizing the loss function, and the gradient is back propagated to update the model parameters.

The above process is iterated, the model parameters are continuously updated, and the model is verified by the validation set data. The iteration can be stopped when the loss function on the validation set basically no longer decreases, and the fitting ability and generalization ability are better at this time. Model.

In the embodiment of the present invention, the loss function may adopt the binary cross entropy loss function loss, and the calculation method is as follows:

和

y_k是当模型输入第k对

和

时所对应的真实标签，取值为0或者1；

是当模型输入第k对

和

时模型所输出的预测值，取值为[0,1]之间的数值。优化的目标是最小化loss，当预测值接近真实值时，loss较小，当预测值偏离真实值时，loss较大。In the above formula, k is a positive integer greater than or equal to 1 and less than or equal to m, and m is a positive integer greater than or equal to 1, which means that there are a total of m pairs in the training data set.

and

y _k is when the model inputs the kth pair

and

The real label corresponding to the time, the value is 0 or 1;

is when the model inputs the kth pair

and

The predicted value output by the model is a value between [0, 1]. The goal of optimization is to minimize the loss. When the predicted value is close to the true value, the loss is small, and when the predicted value deviates from the true value, the loss is large.

In this embodiment of the present invention, a model testing process may also be included. Model testing refers to testing the predictive ability of the model with a test data set that does not overlap with the training data set on the trained model. In order to more intuitively evaluate the predictive ability of the model, the evaluation criteria used on the test data set are the precision rate of prediction, the recall rate, and the AUC (Area Under Curve, ROC (receiver operating characteristic curve)) curve. the area enclosed by the axis below). The precision rate can represent the accuracy of the model, the recall rate can represent the recall ability of the model, and the AUC is the combination of the two.

By comparing the precision, recall, and AUC values of different models on the test data set, the predictive ability of each model can be observed.

In the embodiment of the present invention, in the process of training the model, not only the historical operation records of the target object on the object to be recommended are considered, but also the historical role attribute information of the target object and the item attribute information of the object to be recommended are comprehensively considered, so that it is possible to Improve the prediction accuracy of the model.

FIG. 6 shows a schematic diagram of the processing procedure of step S320 shown in FIG. 3 in an embodiment. As shown in FIG. 6 , in this embodiment of the present invention, the foregoing step S320 may further include the following steps.

In step S321, the object attribute information of the target object is acquired.

For example, still taking a certain game player as an example, the object attribute information may be the game player's real name, age, gender, geographic location, historical online time and other personal portrait information.

In step S322, the first object data is obtained according to the first character attribute information and the object attribute information.

Specifically, the first character attribute information and the object attribute information can be vector spliced to form the first object data, that is, when recommending props to the target object, not only the virtual attributes of the currently selected game character are included information, and the real attribute information of the target object can also be comprehensively considered, thereby further improving the recommendation accuracy.

FIG. 7 shows a schematic diagram of the processing procedure of step S340 shown in FIG. 3 in an embodiment. In this embodiment of the present invention, the neural network model may include a first neural network sub-model, a second neural network sub-model, and a third neural network sub-model.

As shown in FIG. 7 , in this embodiment of the present invention, the foregoing step S340 may further include the following steps.

In step S341, an object vector is generated according to the first object data.

In step S342, the item vector of the item to be recommended is generated according to the item attribute information.

In step S343, the object vector and the item vector are processed by the first neural network sub-model to obtain the object preference vector of the first character of the target object and the item characteristic vector of the object to be recommended .

In step S344, the object vector and the item vector are processed by the second neural network sub-model to obtain the interaction relationship vector between the first character of the target object and the object to be recommended.

In step S345, the object preference vector, the item characteristic vector and the interaction relationship vector are processed through the third neural network sub-model to obtain the first role of the target object to operate the item to be recommended The predicted probability value of .

In step S346, according to the predicted probability value, a first target item recommended to the first character of the target object is determined.

In the embodiment of the present invention, according to the predicted probability value of each item in the item pool, it can be sorted from large to small, and the first predetermined number (for example, 10, the specific value is not limited) or a predetermined ratio (for example, 10%, the specific value is not limited) can be selected. The item whose value is not limited) is returned to the game client as the first target item for display, and the item with the largest predicted probability value is displayed in the first position, and the item with the smallest predicted probability value in the first target item is displayed in the last position. The invention is not limited to this. In other embodiments, if the number of all the props in the props pool is not large, all the props may be displayed on the game client, and the props are only sorted according to the magnitude of the predicted probability value.

In this embodiment of the present invention, the data input into the model may be preprocessed first. The features of each dimension of the data include discrete features (categorical features) and continuous features (dense features). For discrete features, embedding can be used to convert sparse vectors into dense representations. For continuous features, due to the data distribution of some continuous features It is often a long-tailed distribution, and values with large differences in this distribution will interfere with the model. Therefore, in the embodiment of the present invention, continuous features are firstly binned, and then data normalization is performed.

FIG. 8 shows a schematic diagram of the processing procedure of step S341 shown in FIG. 7 in an embodiment. In this embodiment of the present invention, the neural network model may further include a first embedded sub-model, and the first object data may include discrete features of objects and continuous features of objects.

As shown in FIG. 8 , in this embodiment of the present invention, the foregoing step S341 may further include the following steps.

In step S3411, the discrete feature of the object is processed by the first embedding sub-model to obtain an object embedding vector.

In step S3412, binning is performed on the continuous feature of the object to obtain a discrete representation of the object.

In the embodiment of the present invention, any one of equal-frequency binning, equidistant binning, and chi-square binning may be adopted, which is not limited.

In step S3413, normalization processing is performed on the discrete representation of the object.

In step S3414, the object embedding vector and the normalized discrete representation of the object are spliced to generate the object vector.

FIG. 9 schematically shows a schematic diagram of a first embedded sub-model according to an embodiment of the present invention.

假设为4、3、…、0.2、0.5、…。其中4和3为对象离散特征，其独热编码分别为00001和0001，分别将其输入至第一嵌入子模型的嵌入层，输出稠密的对象嵌入向量。0.2、0.5是归一化后的对象连续特征的对象离散表示，保持不变，与对象嵌入向量一起进行级联，输出对象向量

As shown in Figure 9, the first object data

Let's say 4, 3, ..., 0.2, 0.5, .... Among them, 4 and 3 are object discrete features, and their one-hot encodings are 00001 and 0001, respectively, which are input to the embedding layer of the first embedding sub-model, and output dense object embedding vectors. 0.2 and 0.5 are the object discrete representations of the normalized object continuous features, which remain unchanged, and are cascaded together with the object embedding vector to output the object vector

FIG. 10 shows a schematic diagram of the processing procedure of step S342 shown in FIG. 7 in an embodiment. In this embodiment of the present invention, the neural network model may further include a second embedded sub-model, and the item attribute information of the item to be recommended may include discrete features of items and continuous features of items.

As shown in FIG. 10 , in this embodiment of the present invention, the foregoing step S342 may further include the following steps.

In step S3421, the discrete features of the item are processed by the second embedding sub-model to obtain an item embedding vector.

In step S3422, binning is performed on the continuous feature of the item to obtain a discrete representation of the item.

In step S3423, normalization processing is performed on the discrete representation of the item.

In step S3424, the item embedding vector and the normalized discrete representation of the item are spliced to generate the item vector.

FIG. 11 schematically shows a schematic diagram of a second embedding sub-model according to an embodiment of the present invention.

假设为2、1、…、0.4、0.1、…。其中2和1为物品离散特征，其独热编码分别为00100和0100，分别将其输入至第二嵌入子模型的嵌入层，输出稠密的物品嵌入向量。0.4、0.1是归一化后的物品连续特征的物品离散表示，保持不变，与物品嵌入向量一起进行级联，输出物品向量

As shown in Figure 11, the item attribute information

Let's say 2, 1, ..., 0.4, 0.1, .... Among them, 2 and 1 are discrete features of items, and their one-hot encodings are 00100 and 0100, respectively, which are input to the embedding layer of the second embedding sub-model, and output dense item embedding vectors. 0.4 and 0.1 are the item discrete representation of the normalized item's continuous features, which remain unchanged, and are cascaded together with the item embedding vector to output the item vector.

FIG. 12 schematically shows a schematic structural diagram of a neural network model according to an embodiment of the present invention.

As shown in FIG. 12 , the first object data is input into the first embedding sub-model, and the object vector is output; the item attribute information is input into the second embedding sub-model, and the item vector is output. Then, the object vector is input into the first neural network sub-model, and the object preference vector and the item characteristic vector are output; the item vector is input into the second neural network sub-model, and the interaction relationship vector is output. The object preference vector, item feature vector and interaction relationship vector are input into the third neural network sub-model, and the predicted probability value is output.

FIG. 13 shows a schematic diagram of the processing procedure of step S343 shown in FIG. 7 in an embodiment. In this embodiment of the present invention, the first neural network sub-model may include a first neural network unit and a second neural network unit. The first neural network sub-model is a representation learning module, which can be further divided into two parts: one part is used to learn the vector representation of the target object, and the other part is used to learn the vector representation of the object to be recommended.

As shown in FIG. 13 , in this embodiment of the present invention, the foregoing step S343 may further include the following steps.

In step S3431, the object preference vector is obtained by processing the object vector by the first neural network unit.

In step S3432, the item vector is processed by the second neural network unit to obtain the item characteristic vector.

FIG. 14 schematically shows a schematic structural diagram of a first neural network sub-model according to an embodiment of the present invention.

输入至第一神经网络单元MLP_user，MLP_user包括依次连接的层1、层2至层n1，n1为大于或等于1的正整数，这里n1可以取3～5，但本发明并不对此进行限定。第一神经网络单元MLP_user输出对象偏好向量

将物品向量

输入至第二神经网络单元MLP_item，MLP_item包括依次连接的层1、层2至层n2，n2为大于或等于1的正整数，这里n2可以取3～5，n1可以与n2取值相同，也可以不同，本发明并不对此进行限定。第二神经网络单元MLP_item输出物品特性向量

As shown in Figure 14, the object vector

Input to the first neural network unit MLP _user , MLP _user includes layer 1, layer 2 to layer n1 connected in sequence, n1 is a positive integer greater than or equal to 1, where n1 can take 3 to 5, but the present invention does not carry out this limited. The first neural network unit MLP _user outputs the object preference vector

the item vector

Input to the second neural network unit MLP _item , MLP _item includes layer 1, layer 2 to layer n2 connected in sequence, n2 is a positive integer greater than or equal to 1, where n2 can take 3 to 5, n1 can be the same as n2. , may be different, and the present invention is not limited to this. The second neural network unit MLP _item outputs the item feature vector

和

分别输出对应的

和 In the embodiment of FIG. 14 , the first neural network unit and the second neural network unit both use a Multilayer Perceptron (MLP, Multilayer Perceptron) as an example for illustration, but in other embodiments, the first neural network unit And/or the second neural network unit can also use other deep learning networks, such as LSTM (Long Short-TermMemory, long short-term memory network), GRU (Gated Recurrent Unit, gated recurrent unit), etc., and the first neural network unit The same deep learning network as the second neural network unit may be used, or a different deep learning network may be used, which is not limited in the present invention. Among them, the multilayer perceptron is a neural network with a forward structure, which maps a set of input vectors to a set of output vectors. In the embodiment of Figure 14, the vector representation is learned using MLP, that is, the input

and

output the corresponding

and

FIG. 15 shows a schematic diagram of the processing procedure of step S344 shown in FIG. 7 in an embodiment. As shown in FIG. 15 , in this embodiment of the present invention, the foregoing step S344 may further include the following steps.

In step S3441, the object vector and the item vector are spliced to obtain a splicing vector.

In step S3442, the splicing vector is processed by the second neural network sub-model to obtain the interaction relationship vector.

FIG. 16 schematically shows a schematic structural diagram of a second neural network sub-model according to an embodiment of the present invention.

和物品向量

进行级联(拼接)，获得拼接向量；将拼接向量输入至第二神经网络子模型MLP_{user_item}，MLP_{user_item}包括依次连接的层1、层2至层n3，n3为大于或等于1的正整数，这里n3可以取3～5，n3可以与n1或者n2相等，也可以不等，本发明并不对此进行限定。第二神经网络子模型MLP_{user_item}输出交互关系向量 As shown in Figure 16, the object vector

and item vector

Concatenation (splicing) is performed to obtain a splicing vector; the splicing vector is input into the second neural network sub-model MLP _{user_item} , and the MLP _{user_item} includes layers 1, 2 and n3 connected in turn, and n3 is a positive integer greater than or equal to 1, Here, n3 may take 3 to 5, and n3 may be equal to or not equal to n1 or n2, which is not limited in the present invention. The second neural network sub-model MLP _{user_item} outputs the interaction relation vector

进行串接，然后将拼接向量送入MLP_{user_item}。相比于相关技术中用向量内积这种线性函数刻画目标对象和待推荐物之间的关系，MLP的非线性结构更有利于刻画从表征到结果的复杂过程。In the embodiment of the present invention, the second neural network sub-model MLP _{user_item} may also be referred to as a relation learning (relation learning) module. In the representation learning module, the representations of the target object and the object to be recommended are learned separately, while the relation learning module is designed to learn the complex interaction between the target object and the object to be recommended. In this part, the first and

Do concatenation, then feed the concatenated vector into the MLP _{user_item} . Compared with the linear function of vector inner product in the related art to describe the relationship between the target object and the object to be recommended, the nonlinear structure of MLP is more conducive to describing the complex process from representation to result.

In other embodiments, in addition to the MLP, the second neural network sub-model may also use other neural networks or deep learning networks, such as LSTM, GRU, and the like. The first neural network sub-model and the second neural network sub-model may both use MLP, or may both use other identical neural networks, or may use different neural networks respectively.

As a technology that is suitable for processing large-scale complex data and has strong expressive power, deep learning is applied to the recommendation system here. In the embodiment of the present invention, a deep learning-based collaborative filtering network structure is designed in a game scene, and a neural network is used to replace the traditional The vector inner product is used to calculate the interaction between the user and the item.

FIG. 17 shows a schematic diagram of the processing procedure of step S345 shown in FIG. 7 in an embodiment. As shown in FIG. 17 , in this embodiment of the present invention, the foregoing step S345 may further include the following steps.

In step S3451, the object preference vector is multiplied by the item characteristic vector to obtain a dot product vector.

In step S3452, the dot product vector and the interaction relationship vector are concatenated to obtain a concatenated vector.

In step S3453, the concatenated vector is processed by the third neural network sub-model to obtain the predicted probability value.

In the embodiment of the present invention, the third neural network sub-model may also be referred to as a joint prediction layer (prediction layer). After the representation learning module and the relationship learning module, it is necessary to predict the purchase probability of the target object for the game product, and the joint prediction layer combines the outputs of the representation learning module and the relationship learning module to calculate the final prediction result. For example, the joint prediction layer can be calculated as follows:

表示向量串接，所选函数f可以为单层全连接层加softmax函数，输出的

是一个二维向量，形如第一位表示用户不购买商品的概率值，第二位表示用户购买商品的概率值即上述的预测概率值，两个概率之和为1。In the above formula, ⊙ represents the multiplication of vector elements,

Represents vector concatenation, the selected function f can be a single-layer fully connected layer plus a softmax function, and the output

is a two-dimensional vector of the form The first digit represents the probability value that the user does not purchase the product, and the second digit represents the probability value that the user purchases the product, that is, the above-mentioned predicted probability value, and the sum of the two probabilities is 1.

The following is an example of applying the solution provided by the above embodiment to a prop recommendation scene of an RPG game. In this game, users can choose game characters, and game characters are associated with rich attributes, such as character cultivation, skill, etc. (the value will increase with the length of the online time); users can enter the game mall , buy the props required by the character, and the props are also associated with multiple types of attributes. The purpose of recommendation in this scenario is to recommend one or more props that are most likely to be of interest to the user based on the attribute information of the user (the user’s real gender and other attribute information can be comprehensively considered, not limited to the example user id), character, and props. .

This RPG game is a martial arts-themed MMORPG (Massive Multiplayer Online Role-Playing Game) game. The Five Poisons, Shaolin and other factions; it also includes all kinds of industries in the rivers and lakes. The guilds such as the hunter, the escort, the hunter, the ranger, the killer, the singer, the scribe, etc. are the largest, followed by the Xuanyan, the merchants, the market and other industries. Users can download and install the game client. After the game client is installed, click the game icon on the desktop to run the game landing device of the game. Click "Enter Game" on the right side of the lander to enter the game account login interface, enter the game account and password on this interface, click "Enter Game", view "More Servers" to open the server list, and select the one you want to log in to. The game area and server (you can also directly select the most recently logged in server on the right), click "Start Game", and you can start the journey of the rivers and lakes.

FIG. 18 schematically shows a schematic interface diagram of a martial art introduction according to an embodiment of the present invention.

As shown in FIG. 18, the user first creates a role. The first step is to choose a faction. If the user logs into the game for the first time, the game account does not have any role under the server, and you will see the game's martial arts selection interface. You can select any open martial arts in this interface to create the user's role. Click on any open sect to enter the sect introduction interface. In the middle of the interface, you can see the currently selected martial art and the appearance of the character. The right side of the interface lists the combat characteristics of the martial art. You can switch the gender of the character below, and click the right mouse button to rotate the character to view the image. On the left, you can quickly switch between character schools.

19 and 20 schematically illustrate interface diagrams of character detail customization according to an embodiment of the present invention.

As shown in Figure 19, click "Customize Details" to further customize the character details. Under this interface, you can see more details of the character and can make fine adjustments for each item. According to the natural distribution of human facial bones and muscles, there are currently more than 200 adjustable parameters on 48 bones. At the same time, as shown in FIG. 20 , previews of various (here, 4 types are taken as an example) facial expressions and multiple sets (here, 5 sets are taken as an example) to try on outerwear are also provided. After entering the role name at the bottom of the interface, click "Create" to create the user's role. After creating the character, select the created character, and click "Start Game" below the character shown in Figure 21 to enter the game scene shown in Figure 22.

As shown in Figure 22, the side shortcut bar, chat interface, character status, bottom shortcut bar, function buttons (character and mall), minimap, and mission play guide.

The function buttons on the game interface are the entrance to the main function modules of the game. Among them, the roles include: attributes, meridians, mental methods, equipment, etc. The identities include: Escort, Killer, Ranger, Orion, Leling, Scribe, Jukuai, Xuanyan, Merchant, and Market are yet to be opened. The mall includes: common use, appearance, pet riding pendants, treasures, member exclusive, Tianreward points, binding coupons, purchasing membership, coupon consignment, coupon recharge.

The character status is used to check the current character's blood, inner breath, concentration, killing intent and the unique move information of each sect.

The shortcut bar at the bottom corresponds to 15 keys of QERTG and 0-9, and the page up and down buttons on the right can be switched. Items and skills can be placed in the shortcut bar, which can be used quickly after pressing the corresponding button. The key positions on the shortcut bar can be changed in the system settings.

The shortcut bar on the side corresponds to a total of 25 keys of F1-F10, Ctrl0-Ctrl9 and HVCXZ. You can place props and skills, and press the corresponding keys to use them quickly. The key positions on the shortcut bar can be changed in the system settings.

The chat interface can be used to display current chat information and system messages with other players in the game. In the upper part of the chat window, you can select the channel to speak and enter the contents of the speech.

In the player information, you can view the current character's avatar, martial art, name, and level information.

The small map here shows the surrounding map information of the player's current environment. The button in the upper left corner is the rain calendar, which can display the current region, date, time and weather; the button in the upper right corner is the mailbox; the buttons in the lower right corner are: zoom in, zoom out, view the world map, and view the big map.

Mission Play Guide is used to track current story mission/play activity information. Click the link above to guide you to the target point, and click the plot/playing tab above to switch to view the information of plot tasks and gameplay activities.

In this game, experience is closely related to the promotion of character levels, that is, character experience. The experience value is displayed at the top of the game client, with a yellow progress bar showing the experience you currently have and the experience you need to level up next. To obtain experience, in addition to completing the main quest, there are also ways to meditate, guild daily, gangster and other supplementary gameplay. You can open the "Everyday Must Do" on the left side of the small map at the upper right of the game interface to view the daily details. Completion.

FIG. 23 schematically shows a schematic interface diagram of a role attribute according to an embodiment of the present invention.

As shown in FIG. 23 , character attributes may include: sect (for example, Tang Sect), title, merit value, killing, cultivation base, vitality, etc., where cultivation base can be used to cultivate the meridians and mental methods of the character. You can click to select to view all attributes, meridian attributes, mental attributes and equipment attributes. All attributes can include basic attributes and combat attributes. Basic attributes can also include qi and blood, inner breath, concentration, gong, strength, root, qi, insight, and movement. Combat attributes can include external power attack, internal power attack, fixed power attack, hit rate, knowing heart rate, knowing heart damage, external power defense, internal power defense, fixed power defense, block, and tenacity.

FIG. 24 schematically shows a schematic interface diagram of a game mall according to an embodiment of the present invention.

As shown in Figure 24, you can choose to view all the props, equipment props, Bianstone props, mind art props, and identity props in the game mall. All the props can include purple heart method annotation, Xuantian stone mother, Tibetan antelope leather material, phoenix dance map, pearl, Xiuwei Dan, casting god order, jade glaze, golden silk ear, dragon red sand. Here, the setting period for the display of product attributes is 7 days, and the order of items is updated every 7 days according to the changes of the user's character attributes.

FIG. 25 schematically shows a block diagram of an information processing apparatus according to an embodiment of the present invention.

As shown in FIG. 25 , the information processing apparatus 2500 provided by the embodiment of the present invention may include: a first object role determination module 2510 , a first object data acquisition module 2520 , an item attribute information acquisition module 2530 , and a first target item determination module 2540 .

The first object role determination module 2510 may be configured to determine the first role of the target object. The first object data obtaining module 2520 may be configured to obtain the first object data of the target object according to the first character attribute information of the first character. The item attribute information obtaining module 2530 may be configured to obtain item attribute information of the item to be recommended. The first target item determination module 2540 may be configured to process the first object data and the item attribute information through a neural network model, and determine the first item recommended for the first character of the target object from the items to be recommended. a target item.

In an exemplary embodiment, the information processing apparatus 2500 may further include: a second object role determination module, which can be configured to determine a second role of the target object; a second object data acquisition module, which can be configured to determine the second role according to the second object the second character attribute information of the character, to obtain the second object data of the target object; the second target item determination module can be configured to process the second object data and the item attribute information through the neural network model , determining a second target item to be recommended to the second character of the target object from the item to be recommended.

In an exemplary embodiment, the information processing apparatus 2500 may further include: a historical role acquisition module, which can be configured to acquire the historical role of the target object; a historical object data acquisition module, which can be configured to obtain historical role attributes according to the historical role of the historical role information to obtain the historical object data of the target object; the historical operation record obtaining module can be configured to obtain the historical operation record of the target object on the object to be recommended; the training set generation module can be configured to obtain the historical operation record according to the historical operation record, and determine the labels of the historical object data and the item attribute information to generate a training data set; the model training module may be configured to train the neural network model by using the training data set.

In an exemplary embodiment, the neural network model may include a first neural network sub-model, a second neural network sub-model, and a third neural network sub-model. The first target item determination module 2540 may include: an object vector generation unit, which may be configured to generate an object vector according to the first object data; an item vector generation unit, which may be configured to generate the to-be-recommended item according to the item attribute information The item vector of the object; the object item characteristic vector obtaining unit may be configured to process the object vector and the item vector through the first neural network sub-model to obtain the object preference vector of the first character of the target object and the item characteristic vector of the object to be recommended; the interaction relationship vector obtaining unit can be configured to process the object vector and the item vector through the second neural network sub-model to obtain the first The interaction relationship vector between the character and the object to be recommended; the predicted probability obtaining unit may be configured to perform a calculation on the object preference vector, the item characteristic vector and the interaction relationship vector through the third neural network sub-model. processing, to obtain the predicted probability value of the object to be recommended by the first character of the target object; the first target item determination unit may be configured to determine to recommend to the first character of the target object according to the predicted probability value the first target item.

In an exemplary embodiment, the first neural network sub-model may include a first neural network unit and a second neural network unit. Wherein, the object item characteristic vector obtaining unit may include: an object preference vector obtaining subunit, which may be configured to process the object vector through the first neural network unit to obtain the object preference vector; obtain the item characteristic vector The subunit may be configured to process the item vector through the second neural network unit to obtain the item characteristic vector.

In an exemplary embodiment, the interaction relationship vector obtaining unit may include: a splicing vector obtaining subunit, which may be configured to splicing the object vector and the item vector to obtain a splicing vector; an interaction relationship vector obtaining subunit, It may be configured to process the splicing vector through the second neural network sub-model to obtain the interaction relationship vector.

In an exemplary embodiment, the predicted probability obtaining unit may include: a dot product vector obtaining subunit, which may be configured to multiply the object preference vector and the item characteristic vector to obtain a dot product vector; concatenating vectors to obtain a subunit, which can be configured to concatenate the dot product vector and the interaction relationship vector to obtain a concatenated vector; a prediction probability obtaining subunit can be configured to use the third neural network sub-model to concatenate the concatenated vector Processing is performed to obtain the predicted probability value.

In an exemplary embodiment, the neural network model may further include a first embedding sub-model, and the first object data may include object discrete features and object continuous features. The object vector generating unit may include: an object embedding vector obtaining subunit, which may be configured to process the object discrete features through the first embedding submodel to obtain an object embedding vector; an object discrete representation obtaining subunit, It can be configured to perform binning processing on the continuous features of the object to obtain the discrete representation of the object; the object normalization processing subunit can be configured to normalize the discrete representation of the object; the object vector generation subunit can be configured The object vector is generated for splicing the object embedding vector and the normalized discrete representation of the object.

In an exemplary embodiment, the neural network model may further include a second embedding sub-model, and the item attribute information of the item to be recommended may include discrete features of items and continuous features of items. Wherein, the item vector generating unit may include: an item embedding vector obtaining subunit, which may be configured to process the discrete features of the item through the second embedding submodel to obtain an item embedding vector; the item discrete representation obtaining subunit, It can be configured to perform binning processing on the continuous features of the item to obtain the discrete representation of the item; the item normalization processing subunit can be configured to normalize the discrete representation of the item; the item vector generation subunit can be configured The item vector is generated for splicing the item embedding vector and the normalized discrete representation of the item.

In an exemplary embodiment, the first object data obtaining module 2520 may include: an object attribute information obtaining unit, which may be configured to obtain the object attribute information of the target object; a first object data obtaining unit, which may be configured to obtain the object attribute information according to the first The first object data is obtained by character attribute information and the object attribute information.

In an exemplary embodiment, the first character attribute information of the first character may include identity information, current level information and/or current operation information of the first character.

For the specific implementation of each module, unit, and subunit in the information processing apparatus provided in the embodiment of the present invention, reference may be made to the content in the above-mentioned information processing method, and details are not repeated here.

It should be noted that although several modules, units and sub-units of the apparatus for action performance are mentioned in the above detailed description, this division is not mandatory. Indeed, the features and functions of two or more modules, units and sub-units described above may be embodied in one module, unit and sub-unit according to embodiments of the present invention. Conversely, the features and functions of one module, unit and sub-unit described above may be further divided to be embodied by a plurality of modules, units and sub-units.

From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein may be implemented by software, or may be implemented by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of software products, and the software products can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.) or on the network , which includes several instructions to cause a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.

Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the invention which follow the general principles of the invention and which include common knowledge or conventional techniques in the art not disclosed by the invention . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

It should be understood that the present invention is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims (14)

1. An information processing method characterized by comprising:

determining a first role of a target object;

obtaining first object data of the target object according to the first role attribute information of the first role;

acquiring article attribute information of an object to be recommended;

and processing the first object data and the item attribute information through a neural network model, and determining a first target item recommended to a first role of the target object from the object to be recommended.

2. The method of claim 1, further comprising:

determining a second role for the target object;

obtaining second object data of the target object according to second role attribute information of the second role;

and processing the second object data and the item attribute information through the neural network model, and determining a second target item recommended to a second role of the target object from the object to be recommended.

3. The method of claim 1, further comprising:

obtaining a historical role of the target object;

obtaining historical object data of the target object according to historical role attribute information of the historical roles;

obtaining a historical operating record of the target object on the object to be recommended;

determining labels of the historical object data and the article attribute information according to the historical operation records to generate a training data set;

training the neural network model using the training data set.

4. The method of claim 1, wherein the neural network model comprises a first neural network submodel, a second neural network submodel, and a third neural network submodel; the method for determining the first target object recommended to the first role of the target object from the object to be recommended by processing the first object data and the object attribute information through a neural network model comprises the following steps:

generating an object vector from the first object data;

generating an article vector of the object to be recommended according to the article attribute information;

processing the object vector and the article vector through the first neural network submodel to obtain an object preference vector of a first character of the target object and an article characteristic vector of the object to be recommended;

processing the object vector and the item vector through the second neural network sub-model to obtain an interactive relation vector between a first role of the target object and the object to be recommended;

processing the object preference vector, the article characteristic vector and the interaction relation vector through the third neural network submodel to obtain a prediction probability value of the first character operation of the target object on the object to be recommended;

and determining a first target item recommended to a first role of the target object according to the predicted probability value.

5. The method of claim 4, wherein the first neural network submodel comprises a first neural network element and a second neural network element; wherein, processing the object vector and the item vector through the first neural network submodel to obtain an object preference vector of a first character of the target object and an item characteristic vector of the object to be recommended, comprises:

processing the object vector by the first neural network unit to obtain the object preference vector;

and processing the item vector through the second neural network unit to obtain the item characteristic vector.

6. The method of claim 4, wherein processing the object vector and the item vector through the second neural network submodel to obtain an interaction relationship vector between the first character of the target object and the object to be recommended comprises:

splicing the object vector and the object vector to obtain a spliced vector;

and processing the splicing vector through the second neural network submodel to obtain the interactive relation vector.

7. The method of claim 4, wherein processing the object preference vector, the item characteristic vector and the interaction relation vector through the third neural network submodel to obtain a predicted probability value of the first character operation of the target object on the object to be recommended comprises:

multiplying the object preference vector by the article characteristic vector to obtain a point product vector;

connecting the point multiplication vector and the interaction relation vector in series to obtain a connected vector;

and processing the concatenated vector through the third neural network submodel to obtain the prediction probability value.

8. The method of claim 4, wherein the neural network model further comprises a first embedded submodel, the first object data comprising object discrete features and object continuous features; wherein generating an object vector from the first object data comprises:

processing the object discrete features through the first embedding sub-model to obtain an object embedding vector;

performing box separation processing on the object continuous characteristics to obtain an object discrete representation;

performing normalization processing on the object discrete representation;

and splicing the object embedded vector and the normalized object discrete representation to generate the object vector.

9. The method according to claim 4, wherein the neural network model further comprises a second embedded submodel, and the item attribute information of the object to be recommended comprises an item discrete feature and an item continuous feature; generating an article vector of the object to be recommended according to the article attribute information, wherein the method comprises the following steps:

processing the discrete features of the article through the second embedding sub-model to obtain an article embedding vector;

performing box separation processing on the continuous features of the articles to obtain discrete representations of the articles;

performing normalization processing on the discrete representation of the article;

and splicing the article embedding vector and the normalized article discrete representation to generate the article vector.

10. The method of claim 1, wherein obtaining first object data of the target object according to the first character attribute information of the first character comprises:

acquiring object attribute information of the target object;

and obtaining the first object data according to the first character attribute information and the object attribute information.

11. The method of claim 1, wherein the first persona attribute information for the first persona includes identity information, current level information, and/or current operation information for the first persona.

12. An information processing apparatus characterized by comprising:

a first object role determination module configured to determine a first role of a target object;

a first object data obtaining module configured to obtain first object data of the target object according to first role attribute information of the first role;

the article attribute information acquisition module is configured to acquire article attribute information of an object to be recommended;

and the first target item determination module is configured to process the first object data and the item attribute information through a neural network model, and determine a first target item recommended to a first role of the target object from the object to be recommended.

13. An electronic device, comprising:

one or more processors;

a storage device configured to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the information processing method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the information processing method according to any one of claims 1 to 11.

Images