CN110852436B - Data processing method, device and storage medium for electronic poker game - Google Patents
Data processing method, device and storage medium for electronic poker game Download PDFInfo
- Publication number
- CN110852436B CN110852436B CN201910994243.4A CN201910994243A CN110852436B CN 110852436 B CN110852436 B CN 110852436B CN 201910994243 A CN201910994243 A CN 201910994243A CN 110852436 B CN110852436 B CN 110852436B
- Authority
- CN
- China
- Prior art keywords
- card
- neural network
- output
- cnn neural
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a data processing method, a device and a storage medium of an electronic poker game, wherein the method comprises the following steps: acquiring historical hand data of a user as a sample data list; dividing the sample data list into a training set and a verification set; constructing a CNN neural network, taking a training set as input of the CNN neural network, and performing feature training on the CNN neural network to obtain a trained CNN neural network; and taking the verification set as the input of the trained CNN neural network, carrying out repeated iterative processing on the trained CNN neural network according to the number of the verification set, counting the card-out accuracy rate output by the CNN neural network subjected to the iterative processing, and stopping iteration if the card-out accuracy rate meets the preset accuracy rate to obtain the optimal CNN neural network. According to the invention, the real historical hand data is collected and input into the CNN neural network to perform neural network training, and the neural network training is optimized through repeated iterative processing, so that the network parameter quantity is greatly reduced, and the training speed and accuracy can be improved.
Description
Technical Field
The invention mainly relates to the technical field of electronic competitive game data processing, in particular to a data processing method, a device and a storage medium of an electronic poker game.
Background
Currently, in the online game industry, the implementation mode of the electronic poker game AI mainly comprises a decision tree method and a search algorithm of a solution space tree, such as a branch limit method, a alpha-beta pruning search and the like, and the methods have loopholes in the processing process, namely the situation of wrong card playing judgment is easy to appear, so that the card playing situation is not ideal, and the game experience of a player is influenced.
Disclosure of Invention
The invention aims to solve the technical problem of providing a multi-line Cheng Lianbiao processing method, a multi-line Cheng Lianbiao processing device and a computer readable storage medium aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows: a data processing method of an electronic poker game, comprising the steps of:
acquiring historical hand data of a user as a sample data list;
dividing the sample data list into a training set and a verification set;
constructing a CNN neural network, taking the training set as input of the CNN neural network, and performing feature training on the CNN neural network to obtain a trained CNN neural network;
and taking the verification set as the input of the trained CNN neural network, carrying out repeated iterative processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate output by the CNN neural network after iterative processing, and stopping iteration if the card-out accuracy rate meets the preset accuracy rate to obtain the optimal CNN neural network.
The beneficial effects of the invention are as follows: the real historical hand data are collected and input into the CNN neural network to carry out neural network training, and the neural network training is optimized through repeated iteration processing, so that the number of network parameters is greatly reduced, and the training speed and accuracy can be improved.
The other technical scheme for solving the technical problems is as follows: a data processing apparatus for an electronic poker game, comprising the steps of:
the acquisition module is used for acquiring historical hand data of the user as a sample data list;
the classification module is used for dividing the sample data list into a training set and a verification set;
the training module is used for constructing a CNN neural network, taking the training set as the input of the CNN neural network, and carrying out feature training on the CNN neural network to obtain a trained CNN neural network;
and the verification module is used for taking the verification set as the input of the trained CNN neural network, carrying out repeated iteration processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate output by the CNN neural network after the iteration processing, and stopping iteration if the card-out accuracy rate accords with the preset accuracy rate, so as to obtain the optimal CNN neural network.
The other technical scheme for solving the technical problems is as follows: a data processing apparatus for an electronic poker game comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the data processing method for an electronic poker game as described above being implemented when the computer program is executed by the processor.
The other technical scheme for solving the technical problems is as follows: a computer readable storage medium storing a computer program which, when executed by a processor, implements a data processing method of an electronic poker game as described above.
The beneficial effects of the invention are as follows: the real historical hand data are collected and input into the CNN neural network to carry out neural network training, and the neural network training is optimized through repeated iteration processing, so that the number of network parameters is greatly reduced, and the training speed and accuracy can be improved.
Drawings
FIG. 1 is a flow chart of a method for processing data of an electronic poker game according to an embodiment of the present invention;
FIG. 2 is a block diagram of a data processing device for an electronic poker game according to an embodiment of the present invention;
fig. 3 is a diagram of a CNN neural network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a primary input layer data format according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an additional input layer data format according to an embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
As shown in fig. 1, a data processing method of an electronic poker game includes the following steps:
s1: acquiring historical hand data of a user as a sample data list;
s2: dividing the sample data list into a training set and a verification set;
s3: constructing a CNN neural network, taking the training set as input of the CNN neural network, and performing feature training on the CNN neural network to obtain a trained CNN neural network;
s4: and taking the verification set as the input of the trained CNN neural network, carrying out repeated iterative processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate output by the CNN neural network after iterative processing, and stopping iteration if the card-out accuracy rate meets the preset accuracy rate to obtain the optimal CNN neural network.
Specifically, if the number of the verification sets is n, sequentially inputting the verification sets into a CNN neural network, realizing repeated iterative processing, setting a preset accuracy, comparing the card-out accuracy with the preset accuracy, and stopping iteration if the card-out accuracy is greater than or equal to the preset accuracy.
Specifically, the number of training sets is greater than the number of validation sets.
In the embodiment, the real historical hand data is collected and input into the CNN neural network to perform neural network training, and the neural network training is optimized through repeated iterative processing, so that the number of network parameters is greatly reduced, and the training speed and accuracy can be improved.
Optionally, as an embodiment of the present invention, performing feature training on the CNN neural network includes:
and sequencing according to the node values of all the output nodes in the electronic playing card type, determining the output node corresponding to the maximum node value, and determining the output electronic playing card type and card surface according to the maximum node value.
Optionally, as an embodiment of the present invention, the CNN neural network includes a plurality of output nodes, the electronic playing card type includes a plurality of main card types, and each card surface in the main card type is respectively in one-to-one correspondence with the plurality of output nodes;
the process of determining the output card type and the card face according to the maximum node value comprises the following steps:
and sorting according to the node values of the output nodes corresponding to all the card faces of the main card type to obtain the maximum node value, wherein the main card type where the output node corresponding to the maximum node value is positioned is the output card type, and outputting the card face corresponding to the output card type.
Optionally, as an embodiment of the present invention, the electronic playing card type further includes a plurality of main card plus deck types, and the main card plus deck type deck includes a main card deck and a deck; each card surface in the main card and auxiliary card type is respectively in one-to-one correspondence with the plurality of output nodes;
the process of determining the output card type and the card face according to the maximum node value comprises the following steps:
sorting according to node values of output nodes corresponding to all the main card faces to obtain a main card node maximum node value, wherein the card type of the output node corresponding to the main card node maximum node value is a main card output card type;
sorting according to node values of output nodes corresponding to all the dealing faces to obtain a dealing node maximum node value, wherein the dealing type of the output node corresponding to the dealing node maximum node value is the dealing output type;
and outputting the card surface corresponding to the main card output card type and the card surface corresponding to the auxiliary card output card type.
Optionally, as an embodiment of the present invention, the main-card-plus-auxiliary-card-type deck further includes a main-card-surface and two auxiliary-card-surfaces, and each of the main-card-plus-auxiliary-card-type deck is respectively in one-to-one correspondence with the plurality of output nodes;
the process of determining the output card type and the card face according to the maximum node value comprises the following steps:
sorting according to node values of output nodes corresponding to all the main card faces to obtain a main card node maximum node value, wherein the card type of the output node corresponding to the main card node maximum node value is a main card output card type;
sorting according to node values of output nodes corresponding to all the dealing faces, and selecting a first dealing node maximum node value and a second dealing node maximum node value, wherein the card type where the output node corresponding to the first dealing node maximum node value is the first dealing output card type, and the card type where the output node corresponding to the second dealing node maximum node value is the second dealing output card type;
and outputting the card surface corresponding to the first main card output card type, the card surface corresponding to the first auxiliary card output card type and the card surface corresponding to the second auxiliary card output card type.
In the above embodiment, the node values are calculated in the CNN neural network, and the premise of selecting the node is "legal", that is, the selected card can be played by the current player on the premise of conforming to the game rule. If not, the nodes are sorted according to the node values, and the sorting is carried out until a legal card output is obtained. If not, it is not. The CNN neural network only needs to collect the real historical hand data to train the neural network, so that the training efficiency and speed are improved.
Optionally, as an embodiment of the present invention, when obtaining the trained CNN neural network, the method further includes the steps of:
and updating the parameters of the CNN neural network according to the gradient descent method.
The gradient descent method is one type of iterative method that can be used to solve the least squares problem (both linear and non-linear). Gradient descent (Grad i ent Descent) is one of the most commonly employed methods in solving model parameters of machine learning algorithms, i.e., unconstrained optimization problems, another common method is the least squares method. When the minimum value of the loss function is solved, the minimum loss function and the model parameter value can be obtained through one-step iterative solution by a gradient descent method.
Specifically, the function in the gradient descent method is Adam, I r =0.001, beta1=0.9, beta2=0.999, and the loss function=cross entropy. Thus, the parameters of the CNN neural network are updated, and the accuracy of the CNN neural network is improved.
Specifically, fig. 3 is a structure diagram of a CNN neural network, where functions of each layer in the CNN neural network structure are as follows:
the additional input layer and the main input layer are used for situation input, namely, input the received historical hand data of the user; the Conv2D layer is used for carrying out vector convolution operation on the historical hand data of the user; the BatchNorm layer is used for accelerating the convergence speed and stabilizing the network; the RELU layer is used for correcting linearity of the network; the F l atten layer is used for flattening multi-dimensional data with structures into one-dimensional data;
the Concate layer is used for combining the two paths of data; the DropOut layer is used for averaging the prediction probability and preventing the network from being over fitted; the Dense layer is used for making final logic prediction by using the fully-connected neural network; the SOFTMAX layer is used for mapping a plurality of neurons in the network into a (0, 1) interval; and finally, the output layer is used for outputting the card face corresponding to the output card type.
As shown in fig. 4-5, the situation input is specifically that in the main input layer, the historical hand data of the user is divided into 4 rows, 15 columns and 8 channels. The data of the training set are divided into 8 channels for input, and the data are respectively: the channel for inputting 'My hand data', the channel for inputting 'the collection of the hands of other two players', the channel for inputting 'the ground owner bottom card', the channel for inputting 'I' out 'cards, the channel for inputting' last out 'cards, the channel for inputting' next out 'cards and the channel for inputting' last home round out 'and next home round out' cards. The 4 rows are arranged in a way that the same card is not divided into colors and is arranged continuously.
In the additional input layer, each input node has only 0/1 two values.
In the embodiment, the playing card data in the main input layer is divided into 8 channels, and the characteristic that a large number of two, three and four identical cards in the main card type of the bucket land can share the f/l ter is utilized, so that the number of network parameters can be greatly reduced, and the training speed can be improved.
The CNN neural network structure operation output nodes are one-dimensional arrays, are ordered according to the node values in the main board, and take the largest legal node as actual operation output. The definition of the output nodes is arranged as follows:
table 1 is a definition of output nodes:
wherein the first deck is deck 1 and the second deck is deck 2.
In the above embodiment, the format of the output node is defined, and the main cards and the auxiliary cards are all dispersed into a plurality of 0/1 output node lists, so that the output is clear, and the continuous improvement of training precision is facilitated. The card type output with the main card and the auxiliary card is respectively defined in the two-section or three-section 0/1 output node list, so that the expansion of the number of output nodes can be avoided, the number of output nodes is reduced, and the training speed is improved.
Alternatively, as another embodiment of the present invention, a data processing apparatus for an electronic poker game includes the steps of:
the acquisition module is used for acquiring historical hand data of the user as a sample data list;
the classification module is used for dividing the sample data list into a training set and a verification set;
the training module is used for constructing a CNN neural network, taking the training set as the input of the CNN neural network, and carrying out feature training on the CNN neural network to obtain a trained CNN neural network;
and the verification module is used for taking the verification set as the input of the trained CNN neural network, carrying out repeated iteration processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate output by the CNN neural network after the iteration processing, and stopping iteration if the card-out accuracy rate accords with the preset accuracy rate, so as to obtain the optimal CNN neural network.
Optionally, as another embodiment of the present invention, the training module is specifically configured to:
and sequencing according to the node values of all the output nodes in the electronic playing card type, determining the output node corresponding to the maximum node value, and determining the output electronic playing card type and card surface according to the maximum node value.
Alternatively, as an embodiment of the present invention, a data processing apparatus for an electronic poker game includes a memory, a processor, and a computer program stored in the memory and executable on the processor, which when executed by the processor, implements the data processing method for an electronic poker game as described above.
Alternatively, as another embodiment of the present invention, a computer-readable storage medium storing a computer program which, when executed by a processor, implements the data processing method of an electronic poker game as described above.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and units described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-On-y Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (6)
1. A method for processing data of an electronic poker game, comprising the steps of:
acquiring historical hand data of a user as a sample data list;
dividing the sample data list into a training set and a verification set;
constructing a CNN neural network, taking the training set as input of the CNN neural network, and performing feature training on the CNN neural network to obtain a trained CNN neural network;
taking the verification set as the input of the trained CNN neural network, carrying out repeated iterative processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate of the trained CNN neural network after iterative processing, and stopping iteration if the card-out accuracy rate meets the preset accuracy rate to obtain the optimal CNN neural network;
feature training of the CNN neural network includes:
sorting according to node values of all output nodes in the electronic playing card type, determining an output node corresponding to a maximum node value, and determining the output electronic playing card type and card surface according to the maximum node value;
the CNN neural network comprises a plurality of output nodes, the electronic playing card type comprises a plurality of main card types, the card surfaces of the main card types are main card surfaces, and each card surface in the main card types is respectively in one-to-one correspondence with the plurality of output nodes;
the process of determining the output card type and the card face according to the maximum node value comprises the following steps:
sorting according to node values of output nodes corresponding to all the main card faces to obtain a maximum node value, wherein the card type where the output node corresponding to the maximum node value is located is an output card type, and outputting the card face corresponding to the output card type;
the electronic playing card type card also comprises a plurality of main card and auxiliary card types, wherein the main card and auxiliary card type card surfaces comprise main card surfaces and auxiliary card surfaces; each card surface in the main card and auxiliary card type is respectively in one-to-one correspondence with the plurality of output nodes;
sorting according to node values of output nodes corresponding to all the main card faces to obtain a main card node maximum node value, wherein the card type of the output node corresponding to the main card node maximum node value is a main card output card type;
sorting according to node values of output nodes corresponding to all the dealing faces to obtain a dealing node maximum node value, wherein the dealing type of the output node corresponding to the dealing node maximum node value is the dealing output type;
outputting the card surface corresponding to the main card output card type and the card surface corresponding to the auxiliary card output card type;
the main card and auxiliary card type card surface also comprises a main card surface and two auxiliary card surfaces, and each card surface in the main card and auxiliary card type is respectively in one-to-one correspondence with the plurality of output nodes;
sorting according to node values of output nodes corresponding to all the main card faces to obtain a main card node maximum node value, wherein the card type of the output node corresponding to the main card node maximum node value is a first main card output card type;
sorting according to node values of output nodes corresponding to all the dealing faces, and selecting a first dealing node maximum node value and a second dealing node maximum node value, wherein the card type where the output node corresponding to the first dealing node maximum node value is the first dealing output card type, and the card type where the output node corresponding to the second dealing node maximum node value is the second dealing output card type;
and outputting the card surface corresponding to the first main card output card type, the card surface corresponding to the first auxiliary card output card type and the card surface corresponding to the second auxiliary card output card type.
2. The method for processing data of an electronic poker game according to claim 1, wherein the step of obtaining the trained CNN neural network further comprises the steps of:
and updating the parameters of the CNN neural network according to a gradient descent method.
3. The method for processing data of an electronic poker game according to claim 1, wherein the training set is used as an input of the CNN neural network, specifically:
the data of the training set are divided into 8 channels for input, and the data are respectively:
the channel for inputting 'My hand data', the channel for inputting 'the collection of the hands of other two players', the channel for inputting 'the ground owner bottom card', the channel for inputting 'I' out 'cards, the channel for inputting' last out 'cards, the channel for inputting' next out 'cards and the channel for inputting' last home round out 'and next home round out' cards.
4. A data processing apparatus for an electronic poker game employing a data processing method according to any one of claims 1 to 3, comprising the steps of:
the acquisition module is used for acquiring historical hand data of the user as a sample data list;
the classification module is used for dividing the sample data list into a training set and a verification set;
the training module is used for constructing a CNN neural network, taking the training set as the input of the CNN neural network, and carrying out feature training on the CNN neural network to obtain a trained CNN neural network;
and the verification module is used for taking the verification set as the input of the trained CNN neural network, carrying out repeated iteration processing on the trained CNN neural network through the verification set, counting the card-out accuracy rate output by the trained CNN neural network after the iteration processing, and stopping iteration if the card-out accuracy rate meets the preset accuracy rate, so as to obtain the optimal CNN neural network.
5. A data processing device of an electronic poker game comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the data processing method of an electronic poker game according to any one of claims 1 to 3 is implemented when the computer program is executed by the processor.
6. A computer-readable storage medium storing a computer program, characterized in that the data processing method of an electronic poker game according to any one of claims 1 to 3 is implemented when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994243.4A CN110852436B (en) | 2019-10-18 | 2019-10-18 | Data processing method, device and storage medium for electronic poker game |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994243.4A CN110852436B (en) | 2019-10-18 | 2019-10-18 | Data processing method, device and storage medium for electronic poker game |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852436A CN110852436A (en) | 2020-02-28 |
| CN110852436B true CN110852436B (en) | 2023-08-01 |
Family
ID=69597597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910994243.4A Active CN110852436B (en) | 2019-10-18 | 2019-10-18 | Data processing method, device and storage medium for electronic poker game |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852436B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667043B (en) * | 2020-05-20 | 2023-09-19 | 季华实验室 | Chess game playing method, system, terminal and storage medium |
| CN112446424B (en) * | 2020-11-16 | 2024-02-27 | 桂林力港网络科技股份有限公司 | Word card game data processing method, system and storage medium |
| CN112819641A (en) * | 2020-12-28 | 2021-05-18 | 中国人寿保险股份有限公司上海数据中心 | Intelligent pricing system, method, equipment and storage medium for group insurance |
| CN113262496A (en) * | 2021-06-09 | 2021-08-17 | 浙江畅唐网络股份有限公司 | Card type data processing method of whipped egg game and related device |
| CN113952731B (en) * | 2021-12-21 | 2022-03-22 | 广州优刻谷科技有限公司 | Motion sensing game action recognition method and system based on multi-stage joint training |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447419B1 (en) * | 2012-05-02 | 2013-05-21 | Ether Dynamics Corporation | Pseudo-genetic meta-knowledge artificial intelligence systems and methods |
| CN106469317A (en) * | 2016-09-20 | 2017-03-01 | 哈尔滨工业大学深圳研究生院 | A kind of method based on carrying out Opponent Modeling in non-perfect information game |
| CN109165724A (en) * | 2018-08-06 | 2019-01-08 | 哈工大大数据（哈尔滨）智能科技有限公司 | A kind of gradient neural network based decline the number of iterations prediction technique and device |
| CN109598342A (en) * | 2018-11-23 | 2019-04-09 | 中国运载火箭技术研究院 | A kind of decision networks model is from game training method and system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69723899T2 (en) * | 1996-02-12 | 2004-06-17 | St. Jude Medical Ab | Heart rate sensitive pacemaker |
| US20060034508A1 (en) * | 2004-06-07 | 2006-02-16 | Zhou Xiang S | Computer system and method for medical assistance with imaging and genetics information fusion |
| US20100023465A1 (en) * | 2006-10-19 | 2010-01-28 | Yukiko Kuroiwa | Active learning system, method and program |
| JP5874292B2 (en) * | 2011-10-12 | 2016-03-02 | ソニー株式会社 | Information processing apparatus, information processing method, and program |
| CN103632380B (en) * | 2013-11-01 | 2017-04-12 | 华南理工大学 | On-line game playing card identification method based on key point decision trees |
| CN106055339A (en) * | 2016-06-08 | 2016-10-26 | 天津联众逸动科技发展有限公司 | Method for determining card playing strategy of computer player in two-against-one game |
| CN106778735B (en) * | 2016-11-25 | 2020-04-21 | 北京大学深圳研究生院 | License plate recognition method and device |
| CN106681968A (en) * | 2016-12-21 | 2017-05-17 | 桂林力港网络科技股份有限公司 | Transmitting method for batch numeric data, receiving terminal and sending terminal |
| CN107812377A (en) * | 2017-11-27 | 2018-03-20 | 华南理工大学 | A kind of convolutional neural networks structural model for big pineapple playing card first run arrangement |
| CN109621422B (en) * | 2018-11-26 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Electronic chess and card decision model training method and device and strategy generation method and device |
| CN110175619B (en) * | 2018-11-27 | 2023-02-03 | 深圳市腾讯信息技术有限公司 | Method, device and storage medium for determining card-playing set based on machine learning model |
| CN109871943A (en) * | 2019-02-20 | 2019-06-11 | 华南理工大学 | A kind of depth enhancing learning method for big two three-wheel arrangement of pineapple playing card |
-
2019
- 2019-10-18 CN CN201910994243.4A patent/CN110852436B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447419B1 (en) * | 2012-05-02 | 2013-05-21 | Ether Dynamics Corporation | Pseudo-genetic meta-knowledge artificial intelligence systems and methods |
| CN106469317A (en) * | 2016-09-20 | 2017-03-01 | 哈尔滨工业大学深圳研究生院 | A kind of method based on carrying out Opponent Modeling in non-perfect information game |
| CN109165724A (en) * | 2018-08-06 | 2019-01-08 | 哈工大大数据（哈尔滨）智能科技有限公司 | A kind of gradient neural network based decline the number of iterations prediction technique and device |
| CN109598342A (en) * | 2018-11-23 | 2019-04-09 | 中国运载火箭技术研究院 | A kind of decision networks model is from game training method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852436A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852436B (en) | Data processing method, device and storage medium for electronic poker game | |
| CN107506823A (en) | A kind of construction method for being used to talk with the hybrid production style of generation | |
| Fusco et al. | A new method for evaluating the shape of large phylogenies | |
| Bottazzi et al. | Measuring industry relatedness and corporate coherence | |
| CN107368540A (en) | The film that multi-model based on user's self-similarity is combined recommends method | |
| CN113521749B (en) | Abnormal account detection model training method and abnormal account detection method | |
| WO2019107396A1 (en) | Data analysis device and data analysis program | |
| CN114841374A (en) | Method for optimizing transverse federated gradient spanning tree based on stochastic greedy algorithm | |
| Elfrink | Predicting the outcomes of MLB games with a machine learning approach | |
| CN110458295B (en) | Chess and card level generation method, training method and device based on artificial intelligence | |
| Rogers | Central moments and probability distributions of three measures of phylogenetic tree imbalance | |
| CN112446424B (en) | Word card game data processing method, system and storage medium | |
| Purmonen | Predicting game level difficulty using deep neural networks | |
| CN114580345A (en) | Circuit simulation method and device, computer equipment and computer readable storage medium | |
| Aburas et al. | ICC World Cup Prediction Based Data Analytics and Business Intelligent (BI) Techniques | |
| Leung et al. | Data analytics on the board game Go for the discovery of interesting sequences of moves in joseki | |
| CN111861034A (en) | Method and device for optimizing marshalling capability of equipment architecture | |
| CN110478907A (en) | Mahjong intelligent algorithm based on big data driving | |
| CN111783976A (en) | Neural network training process intermediate value storage compression method and device based on window gradient updating | |
| Greenfield | On the co-evolution of evolving expressions | |
| Thaker et al. | Evolutionary computation in artificial board game playing through genetic weight evolution | |
| Li et al. | Study on the play strategy of dou dizhu poker based on convolution neural network | |
| CN104915532A (en) | Electronic card game data processing method and system | |
| CN110851661B (en) | User ID mapping relation determination method and device and electronic equipment | |
| TWI773619B (en) | Automatic race schedule system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |