CN113509713A

CN113509713A - Man-machine chess playing method, device, equipment and storage medium

Info

Publication number: CN113509713A
Application number: CN202110713569.2A
Authority: CN
Inventors: 蒲雪; 李凯; 卢乐炜; 蔺颖; 李文哲
Original assignee: Chengdu Sensetime Technology Co Ltd
Current assignee: Chengdu Sensetime Technology Co Ltd
Priority date: 2021-06-25
Filing date: 2021-06-25
Publication date: 2021-10-19
Also published as: WO2022267276A1; KR20240023178A

Abstract

The embodiment of the disclosure discloses a man-machine chess-playing method, a device, equipment and a storage medium, wherein the method comprises the following steps: recording the falling positions of the first party and the second party in the playing process to obtain historical falling records; responding to a falling event of the first party in the current round, and generating a second falling strategy corresponding to the second party based on a current falling position corresponding to the falling event and the historical falling record; the second drop strategy comprises a plurality of second candidate positions and a second winning rate corresponding to each second candidate position; determining a board force quantification value for the first party in the current round based on the historical drop record and the current drop location; the board force quantification value is used to characterize a board force level of the first party; determining a target falling position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

Description

Man-machine chess playing method, device, equipment and storage medium

Technical Field

The disclosed embodiments relate to the field of data processing, and in particular, to a man-machine chess playing method, device, equipment, and storage medium.

Background

With the development of artificial intelligence, the use of the man-machine chess is more and more extensive. However, in the current relevant products for man-machine chess playing, AI (artificial intelligence) chess force models with different levels are usually preset, and are manually set by a user before each game starts according to the personal judgment and selection of the user, and the mode depends on the subjective judgment capability of the user, so that level selection errors are usually caused by the reason that the self capability is difficult to judge, and the like, and the user cannot quickly feel the feeling of a chess seam opponent in the process of playing chess, thereby influencing the interest of the user in playing chess.

Disclosure of Invention

The disclosed embodiment provides a man-machine chess-playing method, device, equipment and storage medium.

In a first aspect, a man-machine playing method is provided, including:

recording the falling positions of the first party and the second party in the playing process to obtain historical falling records;

responding to a falling event of the first party in the current round, and generating a second falling strategy corresponding to the second party based on a current falling position corresponding to the falling event and the historical falling record; the second drop strategy comprises a plurality of second candidate positions and a second winning rate corresponding to each second candidate position;

determining a board force quantification value for the first party in the current round based on the historical drop record and the current drop location; the board force quantification value is used to characterize a board force level of the first party;

determining a target falling position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

In some embodiments, said determining a chess force quantification value for said first party based on said historical drop record and said current drop location comprises:

inputting the historical falling record and the current falling position into a preset chess force evaluation model to obtain a chess force score of the first party; the chess power score is used for representing the whole chess power level of the first party from the beginning of playing to the current turn;

determining a board force quantification value for the first party based on the board force score for the first party.

In some embodiments, the determining a target falling position in the second candidate positions includes:

sorting the plurality of second positions to be selected based on a second winning rate corresponding to each second position to be selected, and determining a sorting position of each second position to be selected;

acquiring a target sequencing position corresponding to the chess power score of the first party according to a preset first mapping table; the first mapping table comprises a mapping relation between the chess strength scores and the sequencing positions;

and determining a second candidate position corresponding to the target sorting position as the target falling position.

acquiring a target winning rate interval corresponding to the chess power score of the first party according to a preset second mapping table;

and determining a second candidate position in the target winning rate interval as the target falling position based on the target winning rate interval.

In the embodiment of the disclosure, since the real-time chess power score of the first party in the current round is determined based on the current falling position of the first party in the current round, and the target falling position having the mapping relation with the real-time winning rate of the first party is obtained in the second falling strategy based on the real-time chess power score, the effect of a 'chess seam opponent' can be realized between the first party and the second party in the current playing process.

In some embodiments, before the generating, in response to a fall event of the first party in a current round, a second fall strategy corresponding to the second party based on a first current fall corresponding to the fall event and the historical fall record, the method further comprises: predicting a first falling strategy corresponding to the first party based on the historical falling records; the first drop strategy comprises a plurality of first positions to be selected and a first party rate corresponding to each first position to be selected;

said determining a chess force quantification value for said first party based on said historical drop record and said current drop location, comprising: determining a first party winning rate corresponding to the current falling position based on a first party winning rate corresponding to each first position to be selected; and determining a first party winning rate corresponding to the current falling position as the chess force quantification value.

determining a target falling position in the second candidate positions based on the first party rate corresponding to the current falling position; and a mapping relation exists between the second party rate of the target landing position and the first party rate.

In the embodiment of the disclosure, since the falling strategy of the first party in the current round is predicted after the second party falls, the first falling strategy corresponding to the first party and including the plurality of first candidate locations and the first party winning rate corresponding to each first candidate location is obtained. And then in the current round, the chess force quantification value of the first party can be quickly determined after the first party falls, and the falling speed of the second party in the current round is further improved. Meanwhile, the real-time winning rate of the first party in the current round is determined based on the current falling position of the first party in the current round, and the target falling position which has a mapping relation with the real-time winning rate of the first party is obtained in the second falling strategy based on the real-time winning rate, so that the effect of a chess seam opponent can be realized between the first party and the second party in the current playing process.

In some embodiments, the historical fall record includes a fall time; the method further comprises the following steps:

acquiring the average falling time length of the first party based on the historical falling record; the average falling time length of the first party is used for representing the falling speed of the first party after falling in the second party;

predicting a third falling strategy of the first party in the current round based on the historical falling record under the condition that the average falling duration of the first party meets a preset condition; the third drop strategy comprises a plurality of third candidate positions; the third candidate position is related to a chess force quantification value of the first party in a historical turn;

generating a fourth drop strategy corresponding to the second party based on the third candidate positions and the historical drop records for each third candidate position; the fourth falling strategy comprises a plurality of fourth candidate positions and a second winning rate corresponding to each fourth candidate position;

and responding to a falling event of the first party in the current round, and acquiring the second falling strategy in a fourth falling strategy corresponding to each third candidate position based on the current falling position corresponding to the falling event.

Through the embodiment disclosed above, since the average falling time length of the first party is determined based on the history falling records, and when the average falling time length meets the preset condition, after the second party completes the falling in the previous round, the time considered by the first party is utilized, not only is the third falling strategy of the first party in the current round predicted, but also a plurality of fourth falling strategies of a plurality of second parties are generated based on the third falling strategy. Therefore, when the first party finishes the falling event of the current round, the second falling strategy corresponding to the current falling position of the first party can be directly determined from the plurality of fourth falling strategies, the response speed of the second party to the falling event of the first party in the current round is improved, and the use experience of a real user is further improved.

In some embodiments, the obtaining an average fall duration of the first party based on the historical fall records includes:

determining at least one first time interval based on at least one fall time of the first party and at least one fall time of the second party in the historical fall records; the first time interval is the falling time of the second falling and the time interval between the falling time of the adjacent first falling;

generating an average drop duration for the first party based on the at least one first time interval.

In some embodiments, the method further comprises:

obtaining a chess force quantification value of the first party in a historical turn;

generating prompt information based on the chess force quantified value of the first party in the historical round and the chess force quantified value of the first party in the current round; the prompt message is used for representing the chess force change condition of the first party in different rounds.

Through the disclosed embodiment, the game force quantized values of the first party in the historical round and the current round are compared to generate the prompt information for representing the game force variation conditions of the first party in different rounds. The real user can receive the real-time feedback corresponding to the current falling event after each falling, and the user can sense that the falling corresponding to the current turn is relatively better through the first prompt information under the condition that the chess force quantitative value is increased; under the condition that the chess force quantification value is reduced, the user can sense that the falling of the current turn is relatively poor through the second prompt message; therefore, the feedback timeliness of the human-computer chess playing method for the user can be improved, the user can sense the real-time effect of each step, and the learning efficiency of the real user is improved.

In a second aspect, there is provided a human-computer playing device comprising:

the recording module is used for recording the falling positions of the first party and the second party in the playing process to obtain a historical falling record;

a generating module, configured to generate, in response to a fall event of the first party in a current round, a second fall policy corresponding to the second party based on a current fall position corresponding to the fall event and the historical fall record; the second drop strategy comprises a plurality of second candidate positions and a second winning rate corresponding to each second candidate position;

a determination module for determining a board force quantification value for the first party in the current round based on the historical drop record and the current drop location; the board force quantification value is used to characterize a board force level of the first party;

the falling module is used for determining a target falling position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

In a third aspect, there is provided a human-computer playing device comprising: a memory storing a computer program operable on the processor and a processor implementing the steps of the method when executing the computer program.

In a fourth aspect, a computer storage medium is provided that stores one or more programs executable by one or more processors to implement the steps in the above-described method.

In the embodiment of the disclosure, in the process of playing a game by a human-computer, based on the current falling position of the first party in the current round, the chess force quantification value of the first party in the current round is obtained, and based on the chess force quantification value of the first party in the current round, the second candidate position with the second party winning rate matched with the chess force quantification value is selected as the target falling position of the second party, so that in the whole human-computer game playing process, based on the play condition of the real user in different rounds, the falling strategy of the virtual user is dynamically adjusted, the chess force level of the virtual user is dynamically matched with the chess force level of the real user, the real user can feel a 'rival' in the game playing process, and the interest of the user is promoted.

Drawings

Fig. 1 is a schematic structural diagram of a man-machine playing system provided in an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart of a man-machine playing method provided in the embodiments of the present disclosure;

FIG. 3 is a schematic flow chart of a man-machine playing method provided by the embodiment of the present disclosure;

FIG. 4 is a schematic flow chart of a man-machine playing method provided by the embodiment of the present disclosure;

FIG. 5 is a schematic flow chart of a man-machine playing method according to an embodiment of the present disclosure;

FIG. 6 is a schematic flow chart of a man-machine playing method according to an embodiment of the present disclosure;

FIG. 7 is a schematic flow chart of a man-machine playing method according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a human-computer playing device provided in the embodiment of the present disclosure;

fig. 9 is a hardware entity schematic diagram of a human-computer playing device provided in an embodiment of the present disclosure.

Detailed Description

The technical solution of the present disclosure will be specifically described below by way of examples with reference to the accompanying drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.

It should be noted that: in the examples of the present disclosure, "first", "second", and the like are used for distinguishing similar objects, and are not necessarily used for describing a sequential or chronological order of the objects. In addition, the technical solutions described in the embodiments of the present disclosure can be arbitrarily combined without conflict.

Fig. 1 is a schematic flow chart of a man-machine playing method provided in an embodiment of the present disclosure, and as shown in fig. 1, the method is applied to a message broker system, and the method includes:

and S101, recording the falling positions of the first party and the second party in the playing process to obtain a historical falling record.

In some embodiments, the human-machine playing method provided by the embodiments of the present disclosure may be used for various chess games, which may include at least one of weiqi, chinese chess, military chess, gobang, checkers, and flight chess.

In some embodiments, the first party is a real user party and the second party is a machine party, i.e., a virtual user party. During a game, at least one first party and at least one second party are included, and the number of the first party and the second party can be changed based on different chess types. For example, for chess such as go, Chinese chess, chess and gobang, only a first party and a second party can be included in a playing process, namely a real user party and a virtual user party are allowed to participate in playing; for chess such as military flags, Chinese checkers and flight chess, the chess playing process can only comprise a first party and a second party, can also comprise a first party and a plurality of second parties, can also comprise a plurality of first parties and a plurality of second parties, and can also comprise a plurality of first parties and a second party. The embodiments of the present disclosure are not limited thereto.

In some embodiments, the historical fall record may include all fall information prior to the first and second parties. Each drop information may include at least one of: a landing user, a landing time, a landing location, etc. In case the chess category includes pieces of different categories, i.e., one of the chinese chess, the international chess and the military chess, the falling information further includes the falling type.

In the case where the man-machine game playing method is applied to go, the corresponding fall information may include only the fall user and the fall time, and the fall position and other information may be set to a null value, because of the presence of "one hand is used", that is, "one hand is stopped". Wherein. Go allows one party to choose not to fall pieces and let the other party continue to fall pieces, which is "pass one hand".

S102, responding to a falling event of the first party in the current round, and generating a second falling strategy corresponding to the second party based on the current falling position corresponding to the falling event and the historical falling record; the second drop strategy comprises a plurality of second candidate positions and a second winning rate corresponding to each second candidate position.

In some embodiments, the current round is a round that includes a take-off of the first party followed by a take-off of the second party. In the current round, a falling event of the first party in the current round is generated by receiving a falling action of the first party, and meanwhile, the falling event can carry falling information. Then, according to the playing rules, the second party is required to fall, in order to aim at the fall event of the first party of the current round, at least the current fall position is considered in the process of generating a second fall strategy corresponding to the second party, so that the pertinence of the second party fall in the current round is improved; meanwhile, besides the current falling position, the historical falling record needs to be considered, so that the pertinence of the second-party falling in the global playing process is improved.

In some embodiments, in the process of generating the falling strategy corresponding to the second party based on the current falling position and the historical falling record corresponding to the falling event, the falling strategy corresponding to the second party may be generated based on all falling information and the current falling position in the historical falling record; and generating a falling strategy corresponding to the second party based on partial falling information and current falling positions in the historical falling record.

In some embodiments, the second drop policy corresponding to the second party may include a plurality of second candidate locations and a second party winning rate corresponding to each of the second candidate locations. The generated plurality of second candidate positions may include position information of all the second parties that can fall in the current round, for example, for the game of go, all the empty falling points in the chessboard may be the falling points of the second parties, and therefore, the plurality of second candidate positions may be all the empty falling points; the generated plurality of second candidate locations may include a touchdown point where the second winning rate exceeds the minimum winning rate threshold.

S103, determining a chess force quantification value of the first party in the current round based on the historical falling record and the current falling position; the board force quantification value is used to characterize a board force level of the first party;

in some embodiments, since the board force quantification value of the first party in the current round is determined based on the current drop position, the board force quantification value may be used to characterize the board force level corresponding to the first party in the current round. That is, in different rounds, step S103 may determine the playing force level of the first party in the different rounds based on different historical drop records and different current drop positions.

The chess strength evaluation model comprises a plurality of pieces of falling information, a plurality of pieces of falling information and a plurality of pieces of evaluation information, wherein the chess strength level of the playing party can be determined through a preset chess strength evaluation model, and in the process of determining the chess strength level of the first party by using the chess strength evaluation model, the falling information arranged according to time sequence can be input into the chess strength evaluation model according to actual needs, so that the chess strength level of each playing party in the plurality of pieces of falling information in the latest turn can be obtained. For example, in the case of go, the obtained pieces of falling information include a1, B1, a2, B2, …, AN, BN, and AN + 1. After the plurality of pieces of fall information are input to the chess force evaluation model, the chess force quantized value of the part A in the (N + 1) th round and the chess force quantized value of the part B in the Nth round can be obtained.

S104, determining a target falling position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

In some embodiments, a second candidate position where the second party winning rate is in a mapping relation with the chess force quantized value can be determined in each second candidate position directly according to the chess force quantized value of the first party in the current round and is taken as a target falling position based on the mapping relation between the preset second party winning rate and the chess force quantized value of the first party. After determining the target drop position, a drop event for the second party of the current round may be completed based on the target drop position. At this time, the man-machine playing process of the current round is finished, and the man-machine playing process of the next round is entered. During the man-machine game of the next round, the historical fall record of the next round comprises the fall positions of the first party and the second party of the current round.

Referring to fig. 2, fig. 2 is an optional schematic flow chart of the man-machine playing method provided in the embodiment of the present disclosure, based on fig. 1, S103 in fig. 1 may be updated to S201 to S202, and S104 may be updated to step S203, which will be described with reference to the steps shown in fig. 2.

S201, inputting the historical falling record and the current falling position into a preset chess force evaluation model to obtain a chess force score of the first party; the board power score is used for representing the overall board power level of the first party from the beginning of playing to the current turn.

S202, determining a chess force quantification value of the first party based on the chess force score of the first party.

S203, determining a target falling position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

In some embodiments, the determining of the target falling position in the second candidate positions may be implemented by step S2031:

s2031, sorting the plurality of second candidate positions based on a second square winning rate corresponding to each second candidate position, and determining a sorting position of each second candidate position; acquiring a target sequencing position corresponding to the chess power score of the first party according to a preset first mapping table; the first mapping table comprises a mapping relation between the chess strength scores and the sequencing positions; and determining a second candidate position corresponding to the target sorting position as the target falling position.

In some embodiments, the first mapping table may include a plurality of chess power scoring intervals and a corresponding ranking position for each chess power scoring interval. For example, the first mapping table may include a chess power score interval F1: [0, 20), chess power score interval F2: [20, 40), chess power score interval F3: [40, 60), chess power score interval F4: [60, 80), chess power score interval F5: [80, 100]. The sorting position corresponding to the chess force scoring interval F1 is the 5 th position, the sorting position corresponding to the chess force scoring interval F2 is the 4 th position, the sorting position corresponding to the chess force scoring interval F3 is the 3 rd position, the sorting position corresponding to the chess force scoring interval F4 is the 2 nd position, and the sorting position corresponding to the chess force scoring interval F5 is the 1 st position.

Wherein, if the obtained second fall strategy comprises: the second winning rate corresponding to the second candidate position a1 is 50%, the second winning rate corresponding to the second candidate position a2 is 80%, the second winning rate corresponding to the second candidate position A3 is 70%, the second winning rate corresponding to the second candidate position a4 is 60%, the second winning rate corresponding to the second candidate position a5 is 90%, the second winning rate corresponding to the second candidate position a6 is 95%, and 6 second candidate positions are provided. Then, it is necessary to sort the 6 second candidate positions based on the second winning rate corresponding to each second candidate position to obtain a second candidate position a1, where the corresponding sorting position is 6, the sorting position corresponding to the second candidate position a2 is 3, the sorting position corresponding to the second candidate position A3 is 4, the sorting position corresponding to the second candidate position a4 is 5, the sorting position corresponding to the second candidate position a5 is 2, and the sorting position corresponding to the second candidate position a6 is 1, and based on the above example of the first mapping table, in the case that the chess power score of the first party is 65, the corresponding scoring interval may be determined to be F4, and further based on the first mapping table, the corresponding target sorting position may be obtained to be the 2 nd position, that is, the second candidate position a5 with the ranking position of 2 is taken as the target dropping position.

In some embodiments, the determining of the target falling position in the second candidate positions may be implemented by step S2032:

s2032, obtaining a target winning rate interval corresponding to the chess power score of the first party according to a preset second mapping table; and determining a second candidate position in the target winning rate interval as the target falling position based on the target winning rate interval.

In some embodiments, the second mapping table may include a plurality of chess power scoring intervals and a winning rate interval corresponding to each chess power scoring interval. For example, the first mapping table may include a chess power score interval F1: the winning rate interval corresponding to [0, 20) is also [0, 20), and the chess power scoring interval F2: the winning rate interval corresponding to [20, 40 ] is also [20, 40), and the chess power scoring interval F3: the winning rate interval corresponding to [40, 60 ] is also [40, 60), and the chess power scoring interval F4: the winning rate interval corresponding to [60, 80) is also [40, 60), and the chess power scoring interval F5: the win ratio interval corresponding to [80, 100] is also [40, 60 ].

Wherein, if the obtained second fall strategy comprises: the second winning rate corresponding to the second candidate position a1 is 50%, the second winning rate corresponding to the second candidate position a2 is 80%, the second winning rate corresponding to the second candidate position A3 is 70%, the second winning rate corresponding to the second candidate position a4 is 60%, the second winning rate corresponding to the second candidate position a5 is 90%, the second winning rate corresponding to the second candidate position a6 is 95%, and 6 second candidate positions are provided. Based on the above example of the second mapping table, in the case that the game force score of the first party is 65, it may be determined that the corresponding target winning rate interval is also [40, 60), and the second candidate position a1 is taken as the target falling position.

Referring to fig. 3, fig. 3 is an optional schematic flow chart of the man-machine playing method provided in the embodiment of the present disclosure, and based on fig. 1, the method in fig. 1 further includes S301, S103 may be updated to S302, and S104 may be updated to S303, which will be described with reference to the steps shown in fig. 3.

S301, predicting a first falling strategy corresponding to the first party based on the historical falling record; the first drop strategy comprises a plurality of first candidate positions and a first party rate corresponding to each first candidate position.

In some embodiments, the location of the first party's fall in the current round may be predicted based on the historical fall log before the first party's fall in the current round, i.e., after the second party's fall in the previous round. Namely responding to the falling event of the second party in the last round, and predicting a first falling strategy corresponding to the first party based on the historical falling record.

It should be noted that, in S303, a method for generating the first falling policy corresponding to the first party based on the history falling record may be the same as or different from a method for generating the second falling policy corresponding to the second party based on the current falling position and the history falling record in S102.

In some embodiments, after the prediction is completed in S301, a first party winning rate corresponding to each candidate location corresponding to the first party may be obtained.

S302, determining a first party winning rate corresponding to the current falling position based on the first party winning rate corresponding to each first position to be selected; and determining a first party winning rate corresponding to the current falling position as the chess force quantification value.

In some embodiments, the current drop position of the user in the current round has been obtained in response to a drop event of the first party in the current round. And searching a corresponding target candidate position in each candidate position obtained in the step S301 based on the current drop position, and taking a first party winning rate corresponding to the target candidate position as the chess force quantification value.

In some embodiments, in the prediction process of S301, all the positions to be selected and the corresponding first party winning rates have not been output yet, at this time, a drop event of the first party in the current round has been received, at least one position to be selected that has been obtained in S301 and the first party winning rate corresponding to each position to be selected are obtained, a matched target position to be selected is searched for in the obtained at least one position to be selected based on the current drop position of the drop event in the current round, if the matched target position to be selected can be found, the prediction process of S301 is stopped, and the first party winning rate corresponding to the obtained target position to be selected is used as the chess force quantization value; if the matched target candidate position is not found, the prediction process of S301 is continuously executed until the target candidate position matched with the current falling sub-position is obtained.

S303, determining a target falling position in the second positions to be selected based on the first party winning rate corresponding to the current falling position; and a mapping relation exists between the second party rate of the target landing position and the first party rate.

In some embodiments, after obtaining a plurality of candidate positions corresponding to the second party and a second party winning rate corresponding to each candidate position, a target drop position where the second party winning rate and the first party winning rate have a mapping relationship may be determined in the plurality of second candidate positions based on the chess force quantization value, that is, the first party winning rate corresponding to the current drop position.

The target fall position where the second party winning rate and the first party winning rate have a mapping relation can be determined in the plurality of second candidate positions through at least one of the following implementation manners:

(1) determining a second candidate position with a second party winning rate being the same as the first party winning rate in the plurality of second candidate positions as the target falling position; by the implementation mode, the play condition of the doffer of the second party is completely the same as that of the doffer of the first party in the current turn, and further, the effect of a real chess seam opponent is realized.

(2) Determining a second candidate position with the minimum distance between a second party's winning rate and the first party's winning rate in a plurality of second candidate positions as the target landing position; by the implementation mode, the play situation of the doffer of the second party is close to the play situation of the doffer of the first party in the current turn, and the effect of a chess seam opponent is further realized to a certain extent.

(3) Acquiring a preset mapping function relationship, and converting the first party rate based on the mapping function to obtain a converted first party rate; and determining a second candidate position with the second party winning rate being the same as or the distance between the second party winning rate and the first party winning rate being the minimum from the plurality of second candidate positions as the target landing position.

The preset mapping function relationship can be determined by a basic first party winning rate and an offset parameter, wherein the basic first party winning rate can be set by a user, the default value is 50%, the difficulty of representing that the user wants the first party is high under the condition that the basic first party winning rate exceeds the default value, and the difficulty of representing that the user wants the first party is low under the condition that the basic first party winning rate is less than the default value; the offset parameter is used to scale a difference between the first party's rate and the base first party's rate, and further determine a transformed first party's rate, wherein the mapping function relationship may be represented as:

P_{after conversion}＝P_Foundation+k(P_{Before conversion}-P_Foundation)

Wherein, P_{After conversion}Representing the first odds, P, after conversion_{Before conversion}Representing a first party's rate, P, corresponding to the current drop position_FoundationRepresenting the base first party rate, k is the offset parameter. By the implementation mode, the winning rate of the fall of the second party can be realized in the current round, and the winning rate of the first party based on the current fall position can fluctuate around the basic first party winning rate on the basis of maintaining the current round at the 'potential average enemy'.

Referring to fig. 4, fig. 4 is an optional schematic flow chart of the man-machine playing method provided by the embodiment of the present disclosure, based on any of the above embodiments, taking fig. 1 as an example, S102 in fig. 1 may be updated to S401 to S404, and the steps shown in fig. 4 will be described.

S401, acquiring the average falling time length of the first party based on the historical falling record; the average falling time length of the first party is used for representing the falling speed of the first party after falling in the second party.

In some embodiments, the above-mentioned obtaining the average fall duration of the first party based on the history fall record may be implemented by steps S4011 to S4012:

s4011, determining at least one first time interval based on at least one fall time of the first party and at least one fall time of the second party in the historical fall records; the first time interval is the time interval between the falling time of the second falling and the falling time of the adjacent first falling.

S4012, based on the at least one first time interval, generating an average drop time length of the first party.

S402, under the condition that the average falling time of the first party meets a preset condition, predicting a third falling strategy of the first party in the current round based on the historical falling record; the third drop strategy comprises a plurality of third candidate positions; the third candidate position is associated with a chess force quantification of the first party in a historical turn.

In some embodiments, it may be determined whether the average fall time book of the first party satisfies the preset condition by:

(1) acquiring a preset falling time threshold, and determining that the average falling time of the first party meets the preset condition when the average falling time of the first party is greater than or equal to the falling time threshold; determining that the average falling time of the first party does not meet the preset condition under the condition that the average falling time of the first party is smaller than the falling time threshold;

(2) acquiring the average falling time length of the second party based on the historical falling record; the average falling time length of the second party is used for representing the falling speed of the second party after the falling of the first party; determining that the average falling time of the first party meets the preset condition when the average falling time of the first party is greater than or equal to the average falling time of the second party; and under the condition that the average falling time of the first party is smaller than the average falling time of the second party, determining that the average falling time of the first party does not meet the preset condition.

In some embodiments, before receiving a current fall position of a first party in a current round, a third fall strategy of the first party in the current round may be obtained by predicting the fall position of the first party in the current round based on a historical fall record. Wherein the third drop strategy comprises a plurality of third candidate positions and a first party winning rate corresponding to each third candidate position, and at least one third candidate position related to the historical level of the first party can be determined based on the chess force quantification value (including the first party winning rate) of each historical turn of the first party in the historical drop record. It should be noted that, in the third-party policy, all third candidate locations that can be fallen may be included, or only a part of the third candidate locations related to the history level of the first party may be included.

S403, aiming at each third candidate position, generating a fourth falling strategy corresponding to the second party based on the third candidate position and the historical falling record; the fourth falling strategy comprises a plurality of fourth candidate positions and a second winning rate corresponding to each fourth candidate position.

In some embodiments, for each third candidate position in the third falling strategy, based on the same falling strategy generation method as that in S102, a fourth falling strategy corresponding to the second party corresponding to each third candidate position is obtained; the fourth falling strategy comprises a plurality of fourth candidate positions and a second winning rate corresponding to each fourth candidate position.

S404, responding to a falling event of the first party in the current round, and acquiring the second falling strategy in a fourth falling strategy corresponding to each third position to be selected based on the current falling position corresponding to the falling event.

Referring to fig. 5, fig. 5 is an optional schematic flow chart of the man-machine playing method provided in the embodiment of the present disclosure, and based on any of the above embodiments, taking fig. 1 as an example, the method in fig. 1 may further include S501 to S502, which will be described with reference to the steps shown in fig. 5.

S501, obtaining a chess force quantification value of the first party in the historical turn.

S502, generating prompt information based on the chess force quantized value of the first party in the historical turn and the chess force quantized value of the first party in the current turn; the prompt message is used for representing the chess force change condition of the first party in different rounds.

In some embodiments, the historical rounds may only include a previous round, where the previous round is an adjacent historical round of the current round, in S501, the quantified value of the playing force of the first party in the previous round is obtained first, and in combination with the previously obtained quantified value of the playing force of the first party in the current round, corresponding prompt information may be generated, where the prompt information is used to characterize the playing force variation of the first party in the current round relative to the previous round.

And under the condition that the chess force quantified value of the first party in the current round is greater than the chess force quantified value of the last round, first prompt information can be generated, and the first prompt information can be used for representing that the chess force of the first party is improved. For example, the first prompt message may be a prompt message indicating that the real user has improved playing force, such as "good chess", or "true chess". In the case that the chess force quantification value of the first party in the current round is smaller than the chess force quantification value of the last round, second prompt information can be generated, and the second prompt information can be used for representing that the chess force of the first party is reduced. For example, the first prompt message may be a prompt message indicating that the actual user has reduced playing force, such as "go", "miss", or "why" the game was played.

In some embodiments, the historical rounds may only include a plurality of historical rounds before the current round, in S501, the chess force quantified value of the first party in each historical round is obtained first, and in combination with the previously obtained chess force quantified value of the first party in the current round, corresponding prompt information is generated according to the number of rounds, and the prompt information is used for characterizing a variation curve corresponding to the chess force quantified value of the first party along with variation of the number of rounds.

Next, an exemplary application of the embodiment of the present application in a practical application scenario will be described.

With the development of artificial intelligence, the use of the man-machine chess is more and more extensive. However, in the current relevant products for man-machine chess playing, AI (artificial intelligence) chess force models with different levels are usually preset, and are manually set by a user before each game starts according to the personal judgment and selection, and the mode depends on the subjective judgment capability of the user, so that the selection is usually wrong due to the difficulty in judgment of the self capability. Therefore, in the playing process, the setting is too simple, and the user plays games without achievement feeling; or the setting is too difficult, and the user loses confidence; or some schemes can adjust the grade of the chess force model according to the win or loss after the chess playing is finished, and the scheme usually needs the user to spend a plurality of plays for a long time to obtain the model which is relatively in accordance with the chess force of the user. It is difficult to let the user experience the feeling of a chess seam opponent quickly, thereby influencing the playing interest of the user.

Based on the above problems, the embodiments of the present disclosure provide two specific man-machine playing methods, which can refer to the flow diagrams provided in fig. 6 and 7.

In some embodiments, by using the chess force evaluation model, the chess force of the user is judged in real time according to the existing chess falling of the current game of the user during the chess playing process, and the corresponding AI chess playing and falling strategy is selected according to the current chess force of the user, so that the effect that the AI chess playing strategy engine is matched with the chess force of the user is achieved. Referring to fig. 6, fig. 6 is an optional flowchart of the man-machine playing method provided in the embodiment of the present disclosure, and will be described with reference to the steps shown in fig. 6.

S601, recording the positions of the user and the AI in each round in the man-machine game process of the game, and obtaining a history falling record.

Wherein, the history falling record comprises all falling positions of the users and all falling positions of the AI in the game process.

And S602, after each step of falling of the user, determining a chess force quantification value of the user through a chess force evaluation model based on the current falling and the historical falling records of the user.

Wherein the chess force quantification value is used for representing the chess force level of the user.

S603, determining the current falling piece of the AI corresponding to the current falling piece of the user based on the chess force quantitative value and the chess playing strategy model of the user.

The chess force level and the chess playing strategy model based on the user can be realized through S6031 to S6032, and the current falling piece of the AI corresponding to the current falling piece of the user is determined:

s6031, obtaining a plurality of positions of the to-be-selected fell and the corresponding winning rates of different positions of the to-be-selected fell through an AI chess playing strategy model based on the current fell and the historical fell records of the user.

S6032, determining a target falling position in a plurality of falling positions to be selected according to the chess force quantification value of the user; and the winning rate corresponding to the target falling position has a mapping relation with the chess force quantitative value of the user.

In some embodiments, the plurality of different candidate drop positions are sorted in order of the winning rate from high to low. Meanwhile, a plurality of preset threshold conditions are obtained, and a mapping relation exists between each threshold condition and the winning rate sequence. For example, there are 3 threshold conditions, where a first threshold condition is mapped to a first win ratio, a second threshold condition is mapped to a second win ratio, and a third threshold condition is mapped to a third win ratio. And then, determining a target threshold condition which is satisfied by the chess force quantification value of the user in the plurality of threshold conditions, and determining a to-be-selected drop position corresponding to a target winning rate with a mapping relation with the target threshold condition as the target drop position.

Based on the embodiment, through the steps S601 to S602, the playing level of the user can be dynamically identified in the playing process, and the AI playing strategy engine is dynamically switched to the level matched with the playing level of the user; in addition, the strategy in the chess playing process is further refined through the step S603, the strategy of the AI chess playing engine for the winning rate in the wartime is dynamically adjusted, the AI chess playing strategy model can be switched to the grade matched with the chess strength of the user, the playing condition of the user in the chess playing process is further matched, and the chess playing level of the user is better matched.

In some embodiments, in the process of playing chess, an AI strategy model is used for simulating the falling of a user, the winning rates of different falling positions of the user are judged, and the falling position of the AI side is selected as the falling position corresponding to the winning rate according to the actual falling position of the user, so that the condition that the winning rates of the two sides are consistent in the process of playing chess is achieved, and the self-adaption of the AI to the chess force of the user is achieved. Referring to fig. 7, fig. 7 is an optional flowchart of the man-machine playing method according to the embodiment of the present disclosure, and will be described with reference to the steps shown in fig. 7.

And S701, recording the positions of the user and AI in each turn in the man-machine game process of the game, and obtaining a historical falling record.

S702, before the user drops, based on the historical dropping records, the winning rates of different dropping positions of the user are calculated through an AI chess playing strategy model.

And S703, obtaining the winning rate corresponding to the current falling position of the user after the user falls.

S704, obtaining a plurality of positions of the chess to be selected and the winning rates corresponding to different positions of the chess to be selected through the AI chess playing strategy model based on the current position of the user and the historical record of the chess.

S705, determining a target falling position in a plurality of falling positions to be selected based on the winning rate corresponding to the current falling position of the user side; and the winning rate corresponding to the target falling position and the winning rate corresponding to the current falling position of the user side have a mapping relation.

Fig. 8 is a schematic structural diagram of a composition of a human-computer playing device according to an embodiment of the present disclosure, and as shown in fig. 8, the human-computer playing device 800 includes:

the recording module 801 is used for recording the falling positions of the first party and the second party in the playing process to obtain a historical falling record;

a generating module 802, configured to, in response to a fall event of the first party in a current round, generate a second fall policy corresponding to the second party based on a current fall position corresponding to the fall event and the historical fall record; the second drop strategy comprises a plurality of second candidate positions and a second winning rate corresponding to each second candidate position;

a determining module 803, configured to determine a quantified value of chess force of the first party in the current round based on the historical drop record and the current drop position; the board force quantification value is used to characterize a board force level of the first party;

a falling-off module 804, configured to determine a target falling-off position in the second candidate positions; and the second square winning rate corresponding to the target falling position is matched with the chess force quantification value.

In some embodiments, the determining module 803 is further configured to:

In some embodiments, the drop module 804 is further configured to:

In some embodiments, before the generating a second fall strategy corresponding to the second party based on a first current fall corresponding to the fall event and the historical fall record in response to a fall event of the first party in a current round, the generating module 802 is further configured to: predicting a first falling strategy corresponding to the first party based on the historical falling records; the first drop strategy comprises a plurality of first positions to be selected and a first party rate corresponding to each first position to be selected;

the determining module 803 is further configured to: determining a first party winning rate corresponding to the current falling position based on a first party winning rate corresponding to each first position to be selected; and determining a first party winning rate corresponding to the current falling position as the chess force quantification value.

In some embodiments, the drop module 804 is further configured to:

In some embodiments, the generating module 802 is further configured to:

The above description of the apparatus embodiments, similar to the above description of the method embodiments, has similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus of the present disclosure, reference is made to the description of the embodiments of the method of the present disclosure.

In the embodiments of the present disclosure, if the human-computer playing method is implemented in the form of a software functional module and sold or used as a standalone product, the software functional module may be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a device to perform all or part of the methods of the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. As such, the disclosed embodiments are not limited to any specific combination of hardware and software.

Fig. 9 is a schematic diagram of hardware entities of a human-computer playing device provided in an embodiment of the present disclosure, and as shown in fig. 9, the hardware entities of the human-computer playing device 900 include: a processor 901 and a memory 902, wherein the memory 902 stores a computer program operable on the processor 901, and the processor 901 implements the steps in the method of any of the above embodiments when executing the program. In some embodiments, the apparatus 900 for receiving the refunded gaming chips at the gaming table may be a detection apparatus as described in any of the embodiments above.

The Memory 902 stores a computer program that can be executed on the processor, and the Memory 902 is configured to store instructions and applications executable by the processor 901, and can also cache data (e.g., image data, audio data, voice communication data, and video communication data) to be processed or already processed by each module in the processor 901 and the human gaming device 900, which can be implemented by a FLASH Memory (FLASH) or a Random Access Memory (RAM).

The processor 901 implements the steps of any one of the above-described man-machine playing methods when executing the program. The processor 901 typically controls the overall operation of the human gaming device 900.

The disclosed embodiments provide a computer storage medium storing one or more programs that are executable by one or more processors to implement the steps of the human-computer playing method of any one of the above embodiments.

Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present disclosure, reference is made to the description of the embodiments of the method of the present disclosure.

The Processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that the electronic device implementing the above processor function may be other, and the embodiments of the present disclosure are not particularly limited.

The computer storage medium/Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM), and the like; but may also be various terminals such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment of the present disclosure" or "a previous embodiment" or "some embodiments" means that a target feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "the disclosed embodiment" or "the foregoing embodiments" or "some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the described features, structures, or characteristics of the objects may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present disclosure, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure. The above-mentioned serial numbers of the embodiments of the present disclosure are merely for description and do not represent the merits of the embodiments.

Without being specifically described, the detection device performs any step in the embodiments of the present disclosure, and the processor of the detection device may perform the step. Unless otherwise specified, the disclosed embodiments do not limit the order in which the detection device performs the following steps. In addition, the data may be processed in the same way or in different ways in different embodiments. It should be further noted that any step in the embodiments of the present disclosure may be executed independently by the detection device, that is, when the detection device executes any step in the above embodiments, the detection device may not depend on the execution of other steps.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, all the functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The methods disclosed in the several method embodiments provided in this disclosure may be combined arbitrarily without conflict to arrive at new method embodiments.

Features disclosed in several of the product embodiments provided in this disclosure may be combined in any combination to yield new product embodiments without conflict.

The features disclosed in the several method or apparatus embodiments provided in this disclosure may be combined in any combination to arrive at a new method or apparatus embodiment without conflict.

Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.

Alternatively, the integrated unit of the present disclosure may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a detection device, or a network device) to execute all or part of the methods described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.

In the embodiments of the present disclosure, the descriptions of the same steps and the same contents in different embodiments may be mutually referred to. In the embodiments of the present disclosure, the term "not" does not affect the order of the steps.

The above description is only an embodiment of the present disclosure, but the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present disclosure, and all the changes or substitutions should be covered by the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A human-computer playing method, characterized by comprising:

2. The method of claim 1, wherein said determining a chess force quantification value for said first party based on said historical drop record and said current drop position comprises:

3. The method of claim 2, wherein the determining a target landing position among the second plurality of candidate positions comprises:

4. The method of claim 2, wherein the determining a target landing position among the second plurality of candidate positions comprises:

5. The method of claim 1, wherein prior to the generating, in response to a fall event of the first party in a current round, a second fall strategy corresponding to the second party based on a first current fall corresponding to the fall event and the historical fall record, the method further comprises: predicting a first falling strategy corresponding to the first party based on the historical falling records; the first drop strategy comprises a plurality of first positions to be selected and a first party rate corresponding to each first position to be selected;

6. The method of claim 5, wherein the determining a target landing position among the second plurality of candidate positions comprises:

7. The method of claims 1-6, wherein the historical fall record comprises a fall time; the method further comprises the following steps:

8. The method of claim 7, wherein obtaining the average fall duration of the first party based on the historical fall records comprises:

9. The method of claims 1 to 8, further comprising:

10. A human-computer playing device, comprising:

11. A human-computer playing device, comprising: a memory and a processor, wherein the processor is capable of,

the memory stores a computer program operable on the processor,

the processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 9.

12. A computer storage medium, characterized in that the computer storage medium stores one or more programs executable by one or more processors to implement the steps in the method of any one of claims 1 to 9.