阅读说明：本技术 一种操牌信息确定方法、装置、服务器及存储介质 (Card handling information determining method and device, server and storage medium ) 是由 钟涛 于 2019-09-12 设计创作，主要内容包括：本发明提供了一种操牌信息确定方法、装置、服务器及存储介质,通过获取棋牌对决过程中目标玩家的当前手牌信息；获取棋牌对决过程中所有玩家的历史操牌信息；将当前手牌信息以及历史操牌信息输入到预先训练的玩家棋牌预测模型中；利用预先训练的玩家棋牌预测模型预测目标玩家对应的对决玩家的预测手牌信息；利用当前手牌信息、历史操牌信息、预测手牌信息以及预先设置的棋牌规则,确定目标玩家的操牌信息。在预测的过程中参考了棋牌对决过程中所有玩家的历史操牌信息,考虑到了历史操牌信息对对决玩家的预测手牌信息的影响,能够提高预测对决玩家的预测手牌信息的准确性,进而能够提高向目标玩家提示的操牌信息的准确性。(The invention provides a card operating information determining method, a device, a server and a storage medium, which are used for obtaining the current card hand information of a target player in a chess and card checking process; acquiring historical card handling information of all players in the chess and card checking process; inputting current card hand information and historical card handling information into a pre-trained player chess and card prediction model; predicting the predicted hand information of the player in the game corresponding to the target player by utilizing a pre-trained player chess and card prediction model; and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule. In the prediction process, the historical card handling information of all players in the chess and card dealing process is referred, the influence of the historical card handling information on the predicted card information of the players in the chess and card dealing process is considered, the accuracy of the predicted card information of the players in the chess and card dealing process can be improved, and the accuracy of the card handling information prompted to the target player can be improved.)

1. A card handling information determining method, characterized by comprising:

acquiring current hand information of a target player in a chess and card dealing process;

acquiring historical card handling information of all players in the chess and card checking process;

inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model;

predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model;

and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

2. The method of claim 1, wherein obtaining current hand information for the target player during the playing session comprises:

acquiring the type information and the number information of the current hand of a target player in the chess and card dealing process;

mapping the type information and the number information of the current hand to a preset chess tag matrix to obtain a current hand tag matrix;

and establishing a corresponding relation between the current hand label matrix and the target player identification, and taking the corresponding relation between the current hand label matrix and the target player identification as current hand information.

3. The method of claim 1, wherein obtaining historical playing information for all players in the playing session comprises:

determining the type information and the number information of all players who operate the chess and cards historically in the chess and card checking process;

mapping the type information and the number information of the historical playing cards of each player to a preset playing card tag matrix to obtain the historical playing card tag matrix corresponding to each player;

and establishing a corresponding relation between a historical card-handling tag matrix and a player identification, and taking the corresponding relation between the historical card-handling tag matrix and the player identification as historical card-handling information.

4. The method of claim 1, wherein predicting predicted hand information for a player in a block corresponding to a target player using the pre-trained player board prediction model comprises:

predicting the hand type information probability and the hand number information probability of the player in the game by using the pre-trained player chess and card prediction model to obtain the predicted hand type information probability and the predicted hand number information probability which correspond to the player in the game respectively;

mapping the predicted hand type information probability and the predicted hand number information probability corresponding to the player in the block to a preset chess tag matrix to obtain the predicted hand tag matrix corresponding to the player in the block;

and establishing a corresponding relation between a predicted hand tag matrix and the identifier of the player in the block, and taking the corresponding relation between the predicted hand tag matrix and the identifier of the player in the block as predicted hand information.

5. The method of claim 1, wherein determining the card handling information of the target player using the current card handling information, the historical card handling information, the predicted card handling information, and the preset card rules comprises:

sequentially taking each chess and card in the current hand of the target player as a pre-playing chess and card;

calculating the winning card probability corresponding to each pre-drawn chess and card by using the current hand information, the historical card handling information, the predicted hand information and the preset chess and card rules;

and calculating the card-winning information of the target player by using the respective corresponding card-winning probability of each pre-drawn chess card.

6. The method of claim 1, wherein the training process for the player board prediction model comprises:

obtaining training samples in a sample set, the training samples comprising at least: sample hand information of sample players, sample historical card handling information of all players in the chess and card dealing process and reference hand information of the dealing players corresponding to the sample players;

inputting the training samples in the sample set into a player chess and card prediction model for training to obtain predicted hand information of the player in the game corresponding to the sample player;

obtaining an objective function of the player chess and card prediction model by using the reference hand information and the predicted hand information;

and taking the model parameter when the objective function is maximized as the model parameter of the player chess and card prediction model, returning to the step of inputting the training samples in the sample set into the player chess and card prediction model for training to obtain the predicted hand information of the player in the game corresponding to the sample player, and continuing training until the training stopping condition is met.

7. The method of any one of claims 1-6, further comprising: and storing the player chess and card prediction model into a server, wherein the server is one node in the block chain.

8. An operation card information determination apparatus characterized by comprising:

the current hand information acquisition unit is used for acquiring current hand information of a target player in the chess and card dealing process;

the historical card handling information acquisition unit is used for acquiring the historical card handling information of all players in the chess and card checking process;

the input unit is used for inputting the current card hand information and the historical card handling information into a pre-trained player chess prediction model;

the predicting unit is used for predicting predicted hand information of the player in the game corresponding to the target player by utilizing the pre-trained player chess prediction model;

and the card handling information determining unit is used for determining the card handling information of the target player by utilizing the current card handling information, the historical card handling information, the predicted card handling information and a preset chess and card rule.

9. A server, characterized in that the server comprises:

a processor and a memory;

the processor is used for calling and executing the program stored in the memory;

the memory is configured to store the program, the program at least to:

acquiring current hand information of a target player in a chess and card dealing process;

acquiring historical card handling information of all players in the chess and card checking process;

inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model;

predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model;

and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

10. A storage medium having stored thereon computer-executable instructions which, when loaded and executed by a processor, carry out a card handling information determination method according to any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of data processing, in particular to a card handling information determining method, a card handling information determining device, a card handling information determining server and a storage medium.

Background

Along with the development of network technology, people's amusement life is more and more abundant various, can no longer require the restriction in space to the player of chess and card class game, and the people that are located different geographical positions can cut and negotiate through chess and card class application.

During the process of mutual negotiation of the chess and card game players through the application program, before a certain player plays cards, the system prompts the player with proper card playing information according to the rules of the chess and card game, such as: the player is suitable for playing which card, or whether the player grabs the last card, or whether the player is suitable for touching the card, and the like.

Disclosure of Invention

In view of this, the invention provides a card handling information determining method, device, server and storage medium, so as to improve the accuracy of prompting card handling information in the prior art.

In order to achieve the purpose, the invention provides the following technical scheme:

in one aspect, the present application provides a card handling information determining method, including:

acquiring current hand information of a target player in a chess and card dealing process;

acquiring historical card handling information of all players in the chess and card checking process;

inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model;

predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model;

and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

In yet another aspect, the present application further provides a card handling information determining apparatus, including:

the current hand information acquisition unit is used for acquiring current hand information of a target player in the chess and card dealing process;

the historical card handling information acquisition unit is used for acquiring the historical card handling information of all players in the chess and card checking process;

the input unit is used for inputting the current card hand information and the historical card handling information into a pre-trained player chess prediction model;

the predicting unit is used for predicting predicted hand information of the player in the game corresponding to the target player by utilizing the pre-trained player chess prediction model;

and the card handling information determining unit is used for determining the card handling information of the target player by utilizing the current card handling information, the historical card handling information, the predicted card handling information and a preset chess and card rule.

In yet another aspect, the present application further provides a server, including:

a processor and a memory;

the processor is used for calling and executing the program stored in the memory;

the memory is configured to store the program, the program at least to:

acquiring current hand information of a target player in a chess and card dealing process;

acquiring historical card handling information of all players in the chess and card checking process;

inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model;

predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model;

and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

In yet another aspect, the present application further provides a storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the card handling information determination method as described above is implemented.

According to the technical scheme, compared with the prior art, the invention provides the card operating information determining method, the device, the server and the storage medium, and the current card hand information of the target player in the chess and card dealing process is acquired; acquiring historical card handling information of all players in the chess and card checking process; inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model; predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model; and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule. According to the method and the device, the predicted hand information of the player in the game in the opposite game corresponding to the target player is predicted by using the pre-trained player chess and card prediction model, the current hand information of the target player is referred to in the prediction process, and the historical card handling information of all players in the chess and card opposite game process is referred to, so that the influence of the historical card handling information on the predicted hand information of the opposite game is considered, the accuracy of the predicted hand information of the opposite game can be improved, and the accuracy of the card handling information prompted to the target player can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a server according to an embodiment of the present invention;

FIG. 2 is a functional diagram of each node in the blockchain system according to an embodiment of the present invention;

FIG. 3 is an alternative block structure (BlockStructure) diagram according to an embodiment of the present invention;

fig. 4 is a flowchart of a card handling information determining method according to an embodiment of the present invention;

FIG. 5 is a flow chart of another card handling information determination method according to an embodiment of the present invention;

FIG. 6 is a flow chart of a process for training a player board prediction model according to an embodiment of the present invention;

fig. 7 is a structural diagram of a card handling information determination device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The player chess and card prediction model training method provided by the embodiment of the application relates to the technologies such as machine learning technology in artificial intelligence, and the artificial intelligence technology and the machine learning technology are explained firstly below.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the 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 intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.

The scheme provided by the embodiment of the application relates to the technologies such as machine learning of artificial intelligence and the like, and is specifically explained by the following embodiment:

at present, in the process of mutual negotiation of players through a chess application program, before a certain player plays cards, a system prompts the player with appropriate card playing information according to the rules of a chess game, such as: the player is suitable for playing which card, or whether the player grabs the last card, or whether the player is suitable for touching the card, and the like.

In order to prompt the accuracy of card handling information, the embodiment of the application provides a card handling information determining method, which comprises the steps of obtaining current card handling information of a target player in a chess and card dealing process; acquiring historical card handling information of all players in the chess and card checking process; inputting the current hand information and the historical playing information into a pre-trained player chess and card prediction model; predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model; and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule. According to the method and the device, the predicted hand information of the player in the game in the opposite game corresponding to the target player is predicted by using the pre-trained player chess and card prediction model, the current hand information of the target player is referred to in the prediction process, and the historical card handling information of all players in the chess and card opposite game process is referred to, so that the influence of the historical card handling information on the predicted hand information of the opposite game is considered, the accuracy of the predicted hand information of the opposite game can be improved, and the accuracy of the card handling information prompted to the target player can be improved.

For convenience of understanding, a server to which the card handling information determination method according to the embodiment of the present application is applied is described, and as shown in fig. 1, a schematic structural diagram of a server to which the scheme of the present application is applied is shown. In fig. 1, the server may include: a processor 101 and a memory 102.

The server 100 may further include: a communication interface 103, an input unit 104, and a display 105 and a communication bus 106.

The processor 101, the memory 102, the communication interface 103, the input unit 104, and the display 105 all communicate with each other via the communication bus 106.

In the embodiment of the present application, the processor 101 may be a Central Processing Unit (CPU), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices.

The processor may call a program stored in the memory 102, and in particular, the processor may perform operations performed at the terminal side in the following method embodiments.

The memory 102 is used for storing one or more programs, which may include program codes including computer operation instructions, and in this embodiment, the memory stores at least the programs for implementing the following functions:

acquiring current hand information of a target player in a chess and card dealing process;

acquiring historical card handling information of all players in the chess and card checking process;

inputting the current hand information and the historical playing information into a pre-trained player chess and card prediction model;

predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model;

and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

The player chess and card prediction model is stored in the server, and the server is a node in the block chain.

Taking the distributed system 100 as an example of a blockchain system, referring to fig. 2, fig. 2 is an optional structural schematic diagram of a server applied to the blockchain system provided by the embodiment of the present invention, and is formed by a plurality of nodes 200 (computing devices in any form in an access network, such as servers and user terminals) and a client 300, a Peer-to-Peer (P2P, Peer to Peer) network is formed between the nodes, and the P2P protocol is an application layer protocol operating on top of a Transmission Control Protocol (TCP). In a distributed system, any machine, such as a server or a terminal, can join to become a node, and the node comprises a hardware layer, a middle layer, an operating system layer and an application layer.

Referring to the functions of each node in the blockchain system shown in fig. 2, the functions involved include:

1) routing, a basic function that a node has, is used to support communication between nodes.

Besides the routing function, the node may also have the following functions:

2) the application is used for being deployed in a block chain, realizing specific services according to actual service requirements, recording data related to the realization functions to form recording data, carrying a digital signature in the recording data to represent a source of task data, and sending the recording data to other nodes in the block chain system, so that the other nodes add the recording data to a temporary block when the source and integrity of the recording data are verified successfully.

For example, the services implemented by the application include:

2.1) wallet, for providing the function of transaction of electronic money, including initiating transaction (i.e. sending the transaction record of current transaction to other nodes in the blockchain system, after the other nodes are successfully verified, storing the record data of transaction in the temporary blocks of the blockchain as the response of confirming the transaction is valid; of course, the wallet also supports the querying of the remaining electronic money in the electronic money address;

and 2.2) sharing the account book, wherein the shared account book is used for providing functions of operations such as storage, query and modification of account data, record data of the operations on the account data are sent to other nodes in the block chain system, and after the other nodes verify the validity, the record data are stored in a temporary block as a response for acknowledging that the account data are valid, and confirmation can be sent to the node initiating the operations.

2.3) Intelligent contracts, computerized agreements, which can enforce the terms of a contract, implemented by codes deployed on a shared ledger for execution when certain conditions are met, for completing automated transactions according to actual business requirement codes, such as querying the logistics status of goods purchased by a buyer, transferring the buyer's electronic money to the merchant's address after the buyer signs for the goods; of course, smart contracts are not limited to executing contracts for trading, but may also execute contracts that process received information.

3) And the Block chain comprises a series of blocks (blocks) which are mutually connected according to the generated chronological order, new blocks cannot be removed once being added into the Block chain, and recorded data submitted by nodes in the Block chain system are recorded in the blocks.

Referring to fig. 3, fig. 3 is an optional schematic diagram of a Block Structure (Block Structure) according to an embodiment of the present invention, where each Block includes a hash value of a transaction record stored in the Block (hash value of the Block) and a hash value of a previous Block, and the blocks are connected by the hash values to form a Block chain. The block may include information such as a time stamp at the time of block generation. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using cryptography, and each data block contains related information for verifying the validity (anti-counterfeiting) of the information and generating a next block.

As shown in fig. 4, which shows a schematic flow chart of an embodiment of a card handling information determining method according to the present application, the embodiment is mainly illustrated by applying the method to a server, and referring to fig. 4, the card handling information determining method specifically includes the following steps:

s100, obtaining current hand information of a target player in a chess and card dealing process;

the target player is a player who needs to present card operation information at present, and the current hand information of the target player is related information of the chess and cards which are placed in front of the target player and can be seen by the target player, and the information at least comprises the following information: the target player currently has the type and number of cards that he or she can see in front of him or her. The type and the number of the current hand are not specifically limited in the application, and the hand can be determined according to the chess rules corresponding to different types of chess.

S110, obtaining historical card handling information of all players in the chess and card checking process;

it should be noted that all players in the chess and card competition process include both the target player and the competition player corresponding to the target player.

The playing and game piece checking process in the embodiment of the application refers to a historical playing and game piece checking process from playing to the current time point.

The historical card operating information of all players refers to the related information of the chess and cards operated by all players in the historical time period in the chess and card dealing process, and the related information includes the operation objects and the operation modes.

The historical card handling information of all players includes historical card playing information of all players, historical card catching information of all players, and the like, and the application is not particularly limited, and may specifically refer to: the type and number of historical plays of all players, and the type and number of historical grabs of all players, etc.

S120, inputting the current card hand information and the historical card handling information into a pre-trained player chess prediction model;

in the embodiment of the application, the current hand information and the historical card operating information are used as the input quantity of the player chess prediction model and are input into the player chess prediction model trained in advance.

S130, predicting the predicted hand information of the player in the block corresponding to the target player by using the pre-trained player chess prediction model;

the method and the device mainly use a pre-trained player chess and card prediction model to predict the hand information of the game deciding player, wherein the game deciding player refers to a player who is in a decision-deciding state with a target player in a certain game in the chess and card games.

The predicted hand information is the type and number of the game cards that the player can see, when the player currently owns the game piece corresponding to the target player predicted by the pre-trained player game prediction model is ahead of the player for the game piece. The type and the number of the predicted hands are not specifically limited in the application, and the predicted hands can be determined according to the chess rules corresponding to different types of chess.

It should be noted that, in the process of predicting the predicted hand information of a player in the block corresponding to the target player by using the pre-trained player chess prediction model, the embodiment of the present invention may also predict the hand information of a player adjacent to the player in the block, so that the predicted hand information of the player in the block is adjusted by using the predicted result of the hand information of the player adjacent to the player in the block, thereby improving the accuracy of the predicted hand information of the player in the block.

The player chess and card prediction model in the embodiment of the application adopts an ISMTS algorithm to predict the predicted hand information of the player in the game in the opposite game corresponding to the target player, and can also adopt other algorithms to predict the predicted hand information of the player in the opposite game corresponding to the target player, and the embodiment of the application is not limited specifically. The server side predicts hand information through Python, and the ISMCTS algorithm is realized by C + +.

And S140, determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

According to the method and the device, the card handling information of the target player can be determined by utilizing the hand information of the current target player, the historical card handling information of all players in the chess and card dealing process, the predicted hand information of the dealing player corresponding to the target player, which is predicted by utilizing the pre-trained player chess and card prediction model, and the preset chess and card rules.

The preset chess and card rules are the game playing methods of chess and cards, and can comprise the following steps: the number of the players, the playing rules, the card catching rules, the winning rules, the losing rules, etc. are not limited in this embodiment.

The card-handling information of the target player is specifically an operation mode of the target player for next card-handling and an operation object of the card-handling, for example: specifically, the next deal information of the target player or the next card-grabbing information of the target player, for example: the type and number of the target player playing the next card, or the type and number of the target player catching the next card, etc., and the embodiment of the present application is not particularly limited.

Obtaining current hand information of a target player in a chess and card dealing process; acquiring historical card handling information of all players in the chess and card checking process; inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model; predicting the predicted hand information of the player in the block corresponding to the target player by utilizing the pre-trained player chess and card prediction model; and determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule. The method and the device predict the predicted hand information of the player in the game corresponding to the target player by utilizing a pre-trained player chess and card prediction model, and not only refer to the current hand information of the target player in the prediction process, but also refer to the historical card handling information of all players in the chess and card game process, thereby considering the influence of the historical card handling information on the predicted hand information of the player in the game, such as: the type or the number of cards played by a certain player in the historical chess and card dealing process, the type or the number of the cards caught and the like all influence the distribution of the predicted hand information of the dealing player, so that the historical card handling information is taken into account, the accuracy of the predicted hand information of the game player can be improved, and the accuracy of the card handling information prompted to the target player can be improved.

In order to further improve the accuracy of the card handling information presented to the target player, the present application further provides a flow diagram of an embodiment of a card handling information determining method as follows, and with reference to fig. 5, the embodiment includes:

s200, acquiring current hand information of a target player in a chess and card dealing process;

it should be noted that, the embodiment of the present application discloses a manner of obtaining current hand information of a target player in a chess and card dealing process:

acquiring the type information and the number information of the current hand of a target player in the chess and card dealing process; mapping the type information and the number information of the current hand to a preset chess tag matrix to obtain a current hand tag matrix; and establishing a corresponding relation between the current hand label matrix and the target player identification, and taking the corresponding relation between the current hand label matrix and the target player identification as current hand information.

According to the embodiment of the application, a chess and card label matrix is arranged according to the type of chess and cards, information of each dimension in the chess and card label matrix represents information of each chess and card in the chess and card, the dimension of the chess and card label matrix is the same with the number of the chess and cards in the chess and card, unique chess and card identification information is respectively established for each chess and card in the chess and card in advance, and each dimension in the chess and card label matrix corresponds to each chess and card identification information one to one respectively. For example, the number of mahjong pieces in one type of chess and card game mahjong is 144, the dimension of the chess and card label matrix established in the embodiment of the application can be 144 dimensions, and each dimension corresponds to each mahjong piece one by one.

Certainly, for convenience of encoding, in this embodiment of the present application, the dimension of the chess and card label matrix may be set to be more than the number of chess and cards, where a dimension that carries content and is empty is set between the dimensions that carry chess and card information in the chess and card label matrix, for example, a dimension that carries content and is empty is inserted between the dimensions that represent different types of chess and cards, and the dimensions that represent different types of chess and cards are separated by using the dimension that carries content and is empty, thereby avoiding errors occurring in the encoding process.

According to the type information and the number information of the current hand, the current hand is mapped to the preset chess label matrix, namely, the chess of the current hand is mapped to the chess label matrix according to the corresponding relation between each dimensionality and the chess identification information in the chess label matrix. Since there may be more than one chess and cards of the same type in some chess and card games, for example, there are four chess and cards of the same type in mahjong chess and card games, in order to avoid confusion, the plurality of chess and cards of the same type in the present application have different chess and card identification information respectively.

Specifically, the information on the corresponding dimension of the chess in the current hand is set to 1, the information on the corresponding dimension of the chess not in the current hand is set to 0, and the information on the dimension with empty bearing content is also set to 0, so that a current hand tag matrix is obtained, the current hand tag matrix is a matrix with 0 and 1 in content, and the distribution condition of the current hand owned by the target player can be represented by using the current hand tag matrix.

It should be noted that, the current hand label matrix and the target player identification are in a one-to-one correspondence relationship.

S210, obtaining historical card handling information of all players in the chess and card checking process;

the embodiment of the present application discloses a process for acquiring historical card handling information of all players in a chess and card dealing process, which includes: determining the type information and the number information of all players who operate the chess and cards historically in the chess and card checking process; mapping the type information and the number information of the historical playing cards of each player to a preset playing card tag matrix to obtain the historical playing card tag matrix corresponding to each player; and establishing a corresponding relation between a historical card-handling tag matrix and a player identification, and taking the corresponding relation between the historical card-handling tag matrix and the player identification as historical card-handling information.

The player can adopt different operation modes to the chess and cards in the chess and card checking process, and the embodiment of the application can divide the operation modes into different historical card operation sets according to the different operation modes of the player to the chess and cards. Each type of historical card handling set corresponds to a different manner of action taken by the player on the playing cards.

For the future, the operation mode that the player can adopt to the mahjong is for example to eat or hit the cards, the cards that are put up by the last player can form a sequence with two cards in the current player hand, at this moment, the current player can eat the cards that are put up by the last player, and the two cards of the current player form a sequence and then need to be lighted in front of the player, and then one card is put up. The hit cards are the cards played by other players just the same as a pair of cards in the current player's hand, the current player can form a hit card after the hit, the current player takes out the two cards to combine with the cards played by other players to form a hit card to be placed in front of the current player, and then the current player plays a card. The method and the device can establish a historical card handling set aiming at the card-eating, the cards in the historical card handling set corresponding to the card-eating are the cards related to the card-eating of the player, the method and the device can also establish a historical card handling set aiming at the card-hitting, and the cards in the historical card handling set corresponding to the card-hitting are the cards related to the card-hitting of the player.

Each historical card handling set corresponding to each player comprises the type information and the number information of the operated chess, so that a historical card handling label matrix can be established for each historical card handling set corresponding to each player, and each player corresponds to at least one type of historical card handling label matrix.

In the embodiment of the application, the operated chess and cards are mapped to the preset chess and card label matrix according to the type information and the number information of the operated chess and cards contained in each historical card operating set, namely, the operated chess and cards are mapped to the chess and card label matrix according to the corresponding relation between each dimensionality and the chess and card identification information in the chess and card label matrix. Since there may be more than one chess and cards of the same type in some chess and card games, for example, there are four chess and cards of the same type in mahjong chess and card games, in order to avoid confusion, the plurality of chess and cards of the same type in the present application have different chess and card identification information respectively.

Specifically, the dimension information corresponding to the chess and cards in the operated chess and cards is set to be 1, the dimension information corresponding to the chess and cards not in the operated chess and cards is set to be 0, and the dimension information with empty bearing content is also set to be 0, so that the historical playing tag matrix corresponding to each historical playing set is a matrix with 0 and 1 in content, and the distribution condition of all the historical playing cards of the players can be represented by using the historical playing tag matrix.

S220, inputting the current card hand information and the historical card handling information into a pre-trained player chess and card prediction model;

s230, predicting the hand type information probability and the hand number information probability of the player in the game by using the pre-trained player chess prediction model to obtain the predicted hand type information probability and the predicted hand number information probability corresponding to the player in the game;

it should be noted that, in the embodiment of the present application, the pre-trained player game prediction model may be used to predict the hand types and the number of hands of the players in the game, for example, which types of cards are in the hands of the players in the game, and how many cards of each type are.

The prediction result can obtain the information probability of the predicted hand type and the information probability of the predicted hand number.

S240, mapping the predicted hand type information probability and the predicted hand number information probability corresponding to the player in the block to a preset chess tag matrix to obtain the predicted hand tag matrix corresponding to the player in the block;

according to the method and the device, the probability distribution of each kind of hand owned by the hands of the player in the block can be obtained according to the predicted hand type information probability and the predicted hand number information probability corresponding to the player in the block, and then the probability distribution of each kind of hand owned by the hands of the player in the block is mapped to the preset chess tag matrix to obtain the predicted hand tag matrix corresponding to the player in the block.

Because this application embodiment has set up chess and card label matrix according to the type of chess and card, the information of each dimension in the chess and card label matrix has represented the information of each chess and card in the chess and card, this application can be according to predicting hand kind information, on corresponding dimension that the hand that will predict corresponds to chess and card label matrix to information on corresponding dimension sets up the probability value of a certain hand, and the probability value is the numerical value between 0-1, including 0 and 1.

In the embodiment of the application, the probability distribution of each hand owned by the hand of the player can be represented by using the label matrix of the predicted hand.

S250, establishing a corresponding relation between a predicted hand tag matrix and a player identifier of a player in a block, and taking the corresponding relation between the predicted hand tag matrix and the player identifier of the block as predicted hand information;

the predicted hand information includes the correspondence between each player in the game and the predicted hand label matrix.

And S260, determining the card operating information of the target player by using the current card operating information, the historical card operating information, the predicted card operating information and a preset chess and card rule.

According to the method and the device, the card handling information of the target player can be determined by utilizing the hand information of the current target player, the historical card handling information of all players in the chess and card dealing process, the predicted hand information of the dealing player corresponding to the target player, which is predicted by utilizing the pre-trained player chess and card prediction model, and the preset chess and card rules.

Specifically, in the embodiment of the present invention, each of the current hands of the target player may be sequentially used as a pre-run chess; calculating the winning card probability corresponding to each pre-drawn chess and card by using the current hand information, the historical card handling information, the predicted hand information and the preset chess and card rules; and calculating the card-winning information of the target player by using the respective corresponding card-winning probability of each pre-drawn chess card.

When one of the current hands of the target player is used as a pre-out chess, the respective card operating modes of each player in the game are calculated by using the current hand information, the historical card operating information, the predicted hand information and preset chess rules, after the target player and the player in the game are in the game with the preset number, the result of the game of the target player is obtained according to each card operating mode of each player in the game, and the result of the game corresponding to each card operating mode of each player in the game is analyzed to obtain the winning probability corresponding to one pre-out chess of the target player. The number of preset authorities is not specifically limited in this application.

The winning probability corresponding to each of the pre-drawn chess and cards is utilized to calculate the drawing information of the target player, for example, the chess with the highest winning probability can be selected as the final drawing of the target player, and the final drawing of the target player can be selected in other manners.

On the other hand, in the embodiment of the application, each chess and card in the current hand of the player for the game can be used as a pre-grabbing chess and card in turn; calculating the winning card probability corresponding to each pre-grabbed chess and card by using the current hand information, the historical card handling information, the predicted hand information and the preset chess and card rules; and calculating the card-grabbing information of the target player by using the winning probability corresponding to each pre-grabbed chess and card.

When one of the current hands of the game players is used as a pre-grabbing game, the current hand information, the historical card handling information, the predicted hand information and the preset game rules are utilized to calculate the respective card handling mode of each game player, after the target player and the game players match the preset number, the match result of the target player is obtained for each card handling mode of each game player, and the match result of the target player corresponding to each card handling mode of each game player is analyzed to obtain the winning probability corresponding to one pre-grabbing game of the target player. The number of preset authorities is not specifically limited in this application.

The method includes the steps that the winning probability corresponding to each pre-grabbed chess and cards is utilized, the card grabbing information of the target player is calculated, for example, the chess and cards with the highest winning probability can be selected as the final card grabbing of the target player, and the final card grabbing of the target player can be selected in other modes.

In the embodiment of the application, the probability distribution condition of each hand owned by a player in a battle is represented by using the predicted hand tag matrix, the current hand information of a target player is represented by using the current hand tag matrix, and the historical card handling information of all players is also represented by using the historical card handling tag matrix, so that in the process of determining the card handling information of the target player by using the current hand information, the historical card handling information, the predicted hand information and the preset card rule, the predicted hand tag matrix, the historical card handling tag matrix and the complex card relation are determined by analyzing the predicted hand tag matrix, the current hand tag matrix and the historical card handling tag matrix, the complex card relation is digitized, and an accurate card handling information prompt result can be obtained by processing the numeric value, so that the accuracy of the card handling information prompted to the target player is improved.

Next, the present application further provides a schematic flow chart of a training process of a player chess and card prediction model, and referring to fig. 6, the present embodiment includes:

s300, obtaining training samples in a sample set, wherein the training samples at least comprise: sample hand information of sample players, sample historical card handling information of all players in the chess and card dealing process and reference hand information of the dealing players corresponding to the sample players;

s310, inputting the training samples in the sample set into a player chess and card prediction model for training to obtain predicted hand information of the player in the game in the battle corresponding to the sample player;

and inputting the training samples in the sample set into a player chess and card prediction model, and predicting the hand information of the player in the block corresponding to the sample player by using the player chess and card prediction model to obtain the predicted hand information of the player in the block corresponding to the sample player.

S320, obtaining an objective function of the player chess and card prediction model by using the reference hand information and the predicted hand information;

specifically, the model parameters may be continuously adjusted during the training process in a direction that reduces the difference between the reference hand information and the predicted hand information. Therefore, the predicted hand information is obtained by continuously inputting the sample set, and the model parameters are adjusted according to the difference between the reference hand information and the predicted hand information so as to train the player chess and card prediction model.

S330, taking the model parameters when the objective function is maximized as the model parameters of the player chess prediction model, returning to the step S310 to continue training until the training stopping condition is met, and stopping training.

The training stopping condition is a condition for ending the model training, and the training stopping condition may be that a preset number of iterations is reached, or that a performance index of the player chess and card prediction model after the model parameters are adjusted reaches a preset index, and the like, and the method is not particularly limited in the present application. Specifically, for the target function corresponding to each training sample, the model parameter when the target function is maximized is taken as the model parameter of the machine translation model, and then the next sample set is predicted on the basis of the model parameter, so that the model parameter is continuously trained until the training stopping condition is met, and the training is stopped.

The embodiment of the application adopts a network architecture of resnet, and the adopted training mode is a multilabel training mode. And is not particularly limited herein.

Optionally, the training stop condition in this embodiment of the application may be that the loss function of the player chess prediction model is minimum, and the degree of reducing the loss function of the player chess prediction model to the minimum is the training stop condition. The loss function used in the embodiment of the present application may be sigmoid cross entry, and the embodiment itself is not particularly limited. When the training curve begins to have the over-fitting phenomenon, the loss function of the player chess and card prediction model is reduced to the minimum, and the training is stopped. The training framework adopted in the embodiment of the application is google tenserflow training framework.

By utilizing the model training method disclosed by the embodiment of the application, an accurate player chess and card prediction model can be obtained, and the model obtained by training can obtain accurate predicted hand information of the player in the game.

The following describes the card handling information determination method disclosed in the embodiment of the present application in detail by using a specific chess and card example:

taking a mahjong example as an example, the target player in the mahjong competition process is A, and the competition player is B, C, D; suppose that the player id of the target player a is 0, the player id of the previous player B is 3, the player id of the previous player C is 2, and the player id of the previous player D is 1. The dimension of the chess and card label matrix of each player is 152 dimensions, wherein the codes (1-9) in the mahjong are corresponding to the 1 st dimension to the 9 th dimension in the chess and card label matrix; the codes of (one to nine) are (11 to 19) corresponding to the 11 th dimension to the 19 th dimension in the chess and card label matrix; the codes of the first to ninth chess cylinders are (21-29) and correspond to the 21 st to 29 th dimensions in the chess label matrix; the code (whitening in the south, east, west and north) is (31-37) and corresponds to the 31 st dimension to the 37 th dimension in the chess and card label matrix; the 10 th dimension, the 20 th dimension, the 30 th dimension and the 38 th dimension in the chess and card label matrix are filled with 0. By analogy, a 152-dimensional matrix results, such that 38 x 4 is 152, where 4 represents 4 cards of each type. The first 38 dimensions bear the first piece information of each piece in the mahjong, the 39 th to 76 th dimensions bear the second piece information of each piece in the mahjong, the 77 th to 114 th dimensions bear the third piece information of each piece in the mahjong, the 115 th to 152 th dimensions bear the fourth piece information of each piece in the mahjong, and the sequence of the four pieces of each piece is not specifically limited in the application.

Firstly, acquiring current hand information of a target player A in a chess and card dealing process; assume that the current hand of target player a is (1 ten thousand, ninety thousand, one, nine barrels, east, white) and the corresponding current hand label matrix is d. Then d [4 × 1] ═ 1 (first ten thousand), d [4 × 1+1] ═ 1 (second ten thousand), d [4 × 9] ═ 1 (nine thousand), d [4 × 11] ═ 1 (one), d [4 × 29] ═ 1 (first nine tubes), d [4 × 29+1] ═ 1 (second nine tubes), d [31 × 4] ═ 1 (east), d [37 × 4] ═ 1 (white), and the other bits are all 0. d [ ] represents the value in the phase dimension in the current hand label matrix, and the content in [ ] represents the corresponding dimension.

Taking the corresponding relation between the current hand tag matrix and the target player identifier player _ id which is 0 as the current hand information;

acquiring respective historical card handling information of all players A, B, C, D in the chess and card dealing process;

inputting the current hand information of player A and the historical card handling information of all players A, B, C, D into a pre-trained player game prediction model;

in addition to inputting the current hand information of player a and the historical card handling information of all players A, B, C, D into the pre-trained player card prediction model, the present application also inputs the distance from the previous card handling action player to the current player, the action category of the previous card handling action player, the card of the previous card handling action player, whether the current target player listens to the cards, the cards listened by the current target player, all the cards exposed on the table, and the cards exposed from the table 30 steps ahead from the current step into the pre-trained player card prediction model.

Predicting predicted hand information of the player B, C, D corresponding to the target player A by using the pre-trained player chess and card prediction model, wherein the loss function adopted by the scheme is sigmoid _ cross _ entry, namely training is carried out by using multilabel;

in order to completely express the chess and card information required by the double-chess type calculation as far as possible, the scheme uses a plurality of planes to comprehensively express the hand information and the non-hand information. The non-hand information is represented by different plane sets, and two expression modes are given here: a plane-combination representation (plane-combination representation) and a plane-difference representation (plane-difference representation).

Plane combination representation:

the plane combination means that four planes are used, 1 plane representing hand information of a certain player and 4 planes representing eat, hit, light bar and dark bar in non-hand information. When judging the player card type, the four planes need to be subjected to the superposed combination operation, so that the player card type combination has higher certainty. In particular, the method comprises the following steps of,

plane 0: the information indicating the kind and number of hands of a player.

Plane 1: the information of the cards eaten is shown, the cards eaten are noticed to be fixed into a group, the number of the cards eaten can be uniquely determined according to the type and the number of the cards eaten, and the plane shows the information of the type and the number of the cards eaten.

Plane 2: indicating hit card information, a hit 3 cards, is treated as an inscription in the calculation. The number of hit cards per hit is 3.

Plane 3: the number of the corresponding face cards is 4 for each face bar (including the extra bar) like the face bar.

Plane 4: the number of corresponding bar cards for each dark bar (including the extra bar) is 4.

Plane difference representation:

the plane difference representation also uses four planes. Unlike the plane combination representation, each plane in the plane difference representation is an integration of some information, and in particular, hand information and non-hand information (referring to card information that all people have played) need to be represented by differences between planes.

Plane 0: indicating the type and number of all cards in the hand (hand information and non-hand information).

Plane 1: the information indicating card eating is the same as the plane 1 in the plane combination notation.

Plane 2: the hit (medal) bar information in the non-hand information is shown, the number of hit cards is 3, the number of bar cards is 4, and the combination of the planes 2, 3, and 4 in the plane combination representation is shown.

Plane 3: the number of the face cards (including the open bar and the dark bar) is 4.

Plane 4: the number of dark bars is 4.

The plane difference representation method is more visual and easier to learn than the plane combination representation method.

The plane combination representation method must completely combine the information of a plurality of (4) planes to obtain the comprehensive information of the hand information and the non-hand information, and the plane difference representation method is a macroscopic to local difference representation method.

According to the above two plane set representation methods, A, B, C, D may be extracted from the contents represented by the two plane sets, where the respective chess tag matrices corresponding to A, B, C, D are: d0 (Player A), D1 (Player B), D2 (Player C), D3 (Player D). D0 contains (card information tag matrix played by the owner + hand information tag matrix played by player a), D1 contains (card information tag matrix played by the owner + hand tag matrix played by player B + hand information tag matrix played by player a), D2 contains (card information tag matrix played by the owner + hand information tag matrix played by player C + hand information tag matrix played by player B + hand information tag matrix played by player a), and D3 contains (card information tag matrix played by the owner + hand information tag matrix played by player D + hand information tag matrix played by player C + hand information tag matrix played by player a);

the data in the corresponding dimension of player B's own hand tag matrix in chess tag matrix d1 (player B) may be, for example: mask1[0:4] ═ 1, mask1[10 × 4:10 × 4+4] ═ 1, mask1[20 × 4:20 × 4+4] ═ 1; mask1[ ] represents the value in the phase dimension in player B's own hand label matrix, and the contents in [ ] represent the corresponding dimension.

The data in the corresponding dimension of player C's own hand tag matrix in chess tag matrix d2 (player C) may be, for example: mask2[0:4] ═ 1, mask2[10 × 4:10 × 4+4] ═ 1, mask2[20 × 4:20 × 4+4] ═ 1; mask2[ ] represents the value in the phase dimension in player C's own hand label matrix, and the contents in [ ] represent the corresponding dimension.

The data in the corresponding dimension of player D's own hand tag matrix in chess tag matrix D3 (player D) may be, for example: mask3[0:4] ═ 1, mask3[10 × 4:10 × 4+4] ═ 1, and mask3[20 × 4:20 × 4+4] ═ 1. mask3[ ] represents the value in the phase dimension in player D's own hand label matrix, and the contents in [ ] represent the corresponding dimension.

Finally, the card-playing information of the target player A is determined by using the card label matrixes D0 (player A), D1 (player B), D2 (player C) and D3 (player D) corresponding to the A, B, C, D respectively and the preset card rules. The accuracy of the predicted hand information of the predicted match-up player B, C, D can be obviously improved by using the method in the invention, and the accuracy of the card operating information presented to the target player A can be further improved.

The application also provides a card handling information determining device. As shown in fig. 7, it shows a schematic diagram of a component structure of a card handling information determining device of the present application, and the device may include:

a current hand information acquiring unit 100, configured to acquire current hand information of a target player in a chess and card dealing process;

a historical card handling information obtaining unit 110, configured to obtain historical card handling information of all players in a chess and card dealing process;

an input unit 120 for inputting the current hand information and the historical card handling information into a pre-trained player chess prediction model;

a predicting unit 130, configured to predict predicted hand information of a player in a block corresponding to the target player by using the pre-trained player chess prediction model;

and a card handling information determining unit 140, configured to determine card handling information of the target player by using the current card handling information, the historical card handling information, the predicted card handling information, and a preset card rule.

The current hand information acquiring unit includes:

the current hand obtaining unit is used for obtaining the type information and the number information of the current hand of the target player in the chess and card dealing process;

the first mapping unit is used for mapping the type information and the number information of the current hand to a preset chess label matrix to obtain a current hand label matrix;

and the first corresponding relation establishing unit is used for establishing the corresponding relation between the current hand label matrix and the target player identification, and taking the corresponding relation between the current hand label matrix and the target player identification as the current hand information.

The history card handling information acquisition unit includes:

the historical operation chess and card determining unit is used for determining the type information and the number information of all players in the historical operation chess and card in the chess and card checking process;

the second mapping unit is used for mapping the type information and the number information of the historical playing cards of each player to a preset chess tag matrix to obtain the historical playing card tag matrix corresponding to each player;

and the second corresponding relation establishing unit is used for establishing the corresponding relation between the historical card-handling tag matrix and the player identification, and taking the corresponding relation between the historical card-handling tag matrix and the player identification as the historical card-handling information.

The prediction unit includes:

the game player card type information probability prediction unit is used for predicting the game player card type information probability and the game player card number information probability of the game player by utilizing the pre-trained game prediction model to obtain the predicted game player card type information probability and the predicted game player card number information probability which correspond to the game player;

a third mapping unit, configured to map the predicted hand type information probability and the predicted hand number information probability corresponding to each player in the block to a preset chess tag matrix, so as to obtain the predicted hand tag matrices corresponding to the players in the block;

and the third corresponding relation establishing unit is used for establishing the corresponding relation between the predicted hand tag matrix and the identifier of the player in the opposite direction, and taking the corresponding relation between the predicted hand tag matrix and the identifier of the player in the opposite direction as the predicted hand information.

The card handling information determination unit includes:

the pre-chess-playing determining unit is used for sequentially taking each chess and card in the current hand of the target player as pre-chess and cards;

the winning card probability calculating unit is used for calculating the winning card probability corresponding to each pre-drawn chess and card by using the current hand information, the historical card handling information, the predicted hand information and the preset chess and card rules;

and the card-playing information calculation unit is used for calculating the card-playing information of the target player by utilizing the winning probability corresponding to each pre-played chess and card.

Further comprising: a player board prediction model training unit to:

obtaining training samples in a sample set, the training samples comprising at least: sample hand information of sample players, sample historical card handling information of all players in the chess and card dealing process and reference hand information of the dealing players corresponding to the sample players;

inputting the training samples in the sample set into a player chess and card prediction model for training to obtain predicted hand information of the player in the game corresponding to the sample player;

obtaining an objective function of the player chess and card prediction model by using the reference hand information and the predicted hand information;

and taking the model parameter when the objective function is maximized as the model parameter of the player chess and card prediction model, returning to the step of inputting the training samples in the sample set into the player chess and card prediction model for training to obtain the predicted hand information of the player in the game corresponding to the sample player, and continuing training until the training stopping condition is met.

Further comprising: and storing the player chess and card prediction model into a server, wherein the server is one node in the block chain.

On the other hand, the application also provides a storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the card handling information determination method is implemented.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.