Method for recalling old players of turn-based games by phone and related products

Abstract

The present application provides a processing method and related products for recalling old players of a turn-based game by phone, wherein the implementation of the method includes: obtaining at least one game record set corresponding to at least one game plot node of the turn-based game of the target user, and the time interval between the time when the target user last logged into the turn-based game and the current system time is greater than a preset duration; determining the target game strategy of the target user at the target game plot node according to at least one game record set, and the target game plot node is a game plot node in at least one game plot node; determining a human-computer dialogue script for executing a telephone recall service for the target user according to the target game plot node and the target game strategy; and making a voice call with a terminal device according to the human-computer dialogue script. The method of the embodiment of the present application is adopted to realize the personalized determination of the human-computer dialogue script and improve the user's willingness to return to the turn-based game.

Description

Technical Field

[0001] The present application relates to the general data processing technology field of the Internet industry, and in particular to a processing method for recalling old players of a turn-based game by phone and related products. Background Art

[0002] With the rapid development of computer technology and the increasing variety of software programs, turn-based games such as Landlords on smart terminal devices have become a popular form of entertainment. However, as the number of software functions that people can use on smart terminal devices increases and the number of software functions increases, user churn has become a major problem for turn-based games to maintain stable operations.

[0003] At present, most of the measures taken by developers of turn-based games to deal with the problem of user churn are to call old users to recall them. However, the current telephone recall method often uses a fixed human-computer dialogue script for any user, and does not formulate targeted human-computer dialogue scripts based on the actual situation of different users in turn-based games. This makes it difficult for users to be interested in the stereotyped telephone recall, which in turn leads to low efficiency in user recall. Summary of the invention

[0004] The embodiments of the present application provide a processing method and related products for recalling old players of a turn-based game by phone. The implementation of the embodiments of the present application can increase the user's willingness to return to the turn-based game.

[0005] In a first aspect, an embodiment of the present application provides a method for recalling old players of a turn-based game by phone, which is applied to a server of a game marketing system, wherein the game marketing system includes a server and a terminal device for logging into a character account of a target user, and the method includes:

[0006] Acquire at least one game record set corresponding to at least one game plot node of the turn-based game of the target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event of the corresponding game plot node, and the time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset time length;

[0007] Determining a target game strategy of a target user at a target game plot node according to at least one game record set, where the target game plot node is a game plot node in at least one game plot node;

[0008] According to the plot nodes and strategies of the target game, determine the human-computer dialogue script for executing the telephone recall service for the target user;

[0009] Make voice calls with the terminal device according to the human-computer dialogue script.

[0010] In a possible example, the at least one game record set includes a plurality of game record sets; and determining the target game strategy of the target user at the target game plot node according to the at least one game record set includes:

[0011] Sort the multiple game record sets in descending order of the number of game records contained therein to obtain a game record set sequence;

[0012] Taking the game plot node corresponding to the first game record set in the game record set sequence as the target game plot node;

[0013] Determine the target game strategy for the target user based on the game record collection of the target game plot node.

[0014] It can be seen that in the embodiment of the present application, by taking the game plot node corresponding to the first game record set in the game record set sequence containing the largest number of game records as the target game plot node, it is determined that the target game strategy of the target user contains the most game records, and then the target game strategy that is closer to the target user can be determined based on the larger number of game records.

[0015] In a possible example, the game record set of the target game plot node includes multiple game records, and the game event refers to a game process event in which the user fully participates from the starting point to the end point of the same game plot node, the starting point refers to the start time node of the corresponding game plot node, and the end point refers to the end time node of the corresponding game plot node;

[0016] The above-mentioned game record set based on the plot node of the target game determines the target game strategy of the target user, including:

[0017] If the target game plot node requires only one game character, perform the following operations:

[0018] Analyze game data of at least one game round in each of the multiple game records to obtain a reference game strategy adopted by the target user in each game record;

[0019] Determine a target game strategy according to a plurality of reference game strategies corresponding to the obtained plurality of game records;

[0020] If the target game plot node requires multiple game characters, perform the following operations:

[0021] Grouping multiple game records according to game characters to obtain at least one game record group, wherein the game character combinations in any two game record groups are different, and the same game record group includes one or more game records, and the game character combinations corresponding to any two game records in a single game record group including multiple game records are the same;

[0022] For each game record group in at least one game record group, analyzing game data of at least one game round of each game record in the currently processed game record group to determine a reference game strategy adopted by the target user, and obtaining one or more reference game strategies corresponding to one or more game records in each game record group;

[0023] According to one or more reference game strategies of each game record group, a target game strategy for a target user under different game character combinations is determined.

[0024] It can be seen that in the embodiment of the present application, in the process of determining the target game strategy of the target user based on the game record set of the target game plot node, if the game character required by the target game plot node is single, the game data of at least one game round in each game record of the multiple game records is analyzed to obtain a reference game strategy adopted by the target user in each game record, and the target game strategy is determined based on the multiple reference game strategies corresponding to the obtained multiple game records; and if the target game plot node requires multiple game characters, the multiple game records are grouped according to the game characters to obtain at least one game record grouping, and for each game record group in the at least one game record grouping, the game data of at least one game round of each game record in the currently processed game record grouping is analyzed to determine the reference game strategy adopted by the target user, and one or more reference game strategies corresponding to one or more game records of each game record grouping are obtained, and finally the target game strategy of the target user under different game character combinations is determined based on the one or more reference game strategies of each game record grouping.

[0025] In a possible example, the game data of at least one game round in each of the multiple game records is analyzed to obtain a reference game strategy adopted by the target user in each game record, including:

[0026] If at least one game round of the currently processed game record is a single game round, determining a reference game strategy adopted by the target user in the currently processed game record according to the user game data in the single game round;

[0027] If at least one of the game rounds of the currently processed game record is multiple game rounds, perform the following operations:

[0028] Analyze the correlation of user-side operation strategies before adjacent game rounds in multiple game rounds, converge game rounds with consistent correlation into a single reference game round, and obtain an updated game round sequence;

[0029] Determine the interaction complexity of the target game plot node according to the updated game turn sequence;

[0030] If the interaction complexity is greater than or equal to the preset complexity, manually summarizing the updated game turn sequence to determine a reference game strategy adopted by the target user in the currently processed game record;

[0031] If the interaction complexity is lower than the preset complexity, the reference game strategy adopted by the target user in the currently processed game record is determined according to the user game data in the updated game round sequence.

[0032] It can be seen that in the embodiment of the present application, when analyzing the game data of at least one game round in each game record of multiple game records to obtain the reference game strategy adopted by the target user in each game record, if at least one game round of the game record currently being processed is a single game round, the reference game strategy adopted by the target user in the game record currently being processed is determined based on the user game data in the single game round; and if at least one game round of the game record currently being processed is multiple game rounds, the correlation of the user-side operation strategies before adjacent game rounds in the multiple game rounds is analyzed, and the game rounds with the correlation as consistent operations are converged into a single reference game round to obtain an updated game round sequence, and the interaction complexity of the target game plot node is determined based on the updated game round sequence, and if the interaction complexity is greater than or equal to the preset complexity, the updated game round sequence is manually summarized to determine the reference game strategy adopted by the target user in the game record currently being processed, and if the interaction complexity is lower than the preset complexity, the reference game strategy adopted by the target user in the game record currently being processed is determined based on the user game data in the updated game round sequence. This makes the process of determining the reference game strategy adopted by the target user in each game record more personalized and targeted, and improves the accuracy of the reference game strategy.

[0033] In a possible example, determining the interaction complexity of the target game plot node according to the updated game turn sequence includes:

[0034] Determine the average number of user operations per round of the game round sequence according to the number of user operations in the game data of each game round in the updated game round sequence;

[0035] The interaction complexity of the target game plot nodes is determined based on the number of rounds contained in the game round sequence and the average number of user operations in a single round.

[0036] It can be seen that in the embodiment of the present application, when determining the interaction complexity of the target game plot node according to the updated game round sequence, the average number of user operations per round of the game round sequence is determined according to the number of user operations in the game data of each game round in the updated game round sequence, and finally the interaction complexity of the target game plot node is determined according to the number of rounds included in the game round sequence and the average number of user operations per round. The interaction complexity of the target game plot node is determined by the number of rounds and the number of user operations included in the game round sequence, so that the determination process of the interaction complexity of the target game plot node is closer to the operational characteristics of turn-based games.

[0037] In a possible example, determining the target game strategy according to the multiple reference game strategies corresponding to the obtained multiple game records includes:

[0038] The reference game strategy with the largest number of repetitions among multiple reference game strategies is used as the target game strategy; or,

[0039] The reference game strategy whose game event is closest to the current system time among multiple reference game strategies is used as the target game strategy.

[0040] It can be seen that in the embodiment of the present application, when determining the target game strategy according to the multiple reference game strategies corresponding to the obtained multiple game records, the reference game strategy with the largest number of repetitions among the multiple reference game strategies is used as the target game strategy, so as to determine that the obtained target game strategy is more in line with the game habits of the target user; or, the reference game strategy whose game event is closest to the current system time among the multiple reference game strategies is used as the target game strategy, so as to determine that the obtained target game strategy is closer in time to the target user and has a clearer game impression. Finally, the final determined target game strategy has more reference applicability.

[0041] In a possible example, if at least one game plot node requires a single game character, the human-computer dialogue script includes a guiding speech and a human-computer dialogue plot node, and the guiding speech includes an introduction to the single game character;

[0042] If at least one game plot node requires multiple game characters, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes, and the guiding words include introductions to the multiple game characters.

[0043] It can be seen that in the embodiment of the present application, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes. The guiding words include an introduction to the game characters, so that the human-computer dialogue script is closer to the game scene of the turn-based game, thereby further awakening the target user's game memory of the turn-based game, and then increasing the target user's willingness to return to the turn-based game.

[0044] In a possible example, the human-machine dialogue script includes a preset machine call and a preset user call, and a call sequence of the preset machine call and the preset user call. The above-mentioned voice call with the terminal device according to the human-machine dialogue script includes:

[0045] Output voice call statements to the terminal device according to the call sequence of the preset machine call;

[0046] receiving a user call fed back by a terminal device, performing semantic recognition on the user call, and obtaining a semantic recognition result of the user call, wherein the semantic recognition result includes a reference triplet;

[0047] According to the matching relationship between the reference triplet and the triplet subset of the preset user call, and the call sequence, the next hop target preset machine call corresponding to the user call is output.

[0048] It can be seen that in the embodiment of the present application, a voice call is made with a terminal device through a human-computer dialogue script with a certain dialogue sequence and jump conditions, thereby improving the fun and interactivity of the voice call for the target user, awakening the target user's interactive memory of the turn-based game, and thereby increasing the user's willingness to return to the turn-based game.

[0049] In a possible example, the above-mentioned preset machine call and the call sequence of the preset machine call are determined by the game interaction scenario of the turn-based game.

[0050] It can be seen that in the embodiment of the present application, since the preset machine call and the call sequence of the preset machine call are determined by the game interaction scenario of the turn-based game, the content of the voice call is closely integrated with the game interaction scenario of the turn-based game, so that the voice call can further awaken the target user's memory of the turn-based game and thereby increase the user's willingness to return to the turn-based game.

[0051] In a possible example, the outputting of the next hop target preset machine call corresponding to the user call according to the matching relationship between the semantic recognition result and the triplet subset of the preset user call and the call sequence of the preset user call includes:

[0052] Determine whether there is a matching relationship between the reference triplet and a subset of triplet of a preset user call;

[0053] If there is a matching relationship between the reference triplet and the preset user call triplet subset, outputting the preset machine call that satisfies the call sequence with the preset user call to the terminal device as the next-hop target preset machine call;

[0054] If there is no matching relationship between the reference triplet and the preset user call triplet subset, the target emotional tendency corresponding to the user call is determined according to the semantic recognition result, and the next-hop target preset machine call matching the target emotional tendency is obtained from the emotional sentence library according to the target emotional tendency, wherein the emotional sentence library includes the correspondence between multiple preset emotional tendencies and multiple preset machine calls.

[0055] It can be seen that in the embodiments of the present application, the flexibility and intelligence of the human-computer dialogue script for voice calls are improved, thereby increasing the fun and interactivity of voice calls for target users, awakening the target users' interactive memory of turn-based games, and thereby increasing the users' willingness to return to turn-based games.

[0056] In a possible example, the semantic recognition of the user call is performed to obtain the semantic recognition result of the user call, including:

[0057] Determine the user call text according to the user call;

[0058] Determine a parsing graph of the user's call text, the parsing graph comprising a plurality of parsing nodes and at least one parsing node relationship line, the parsing node is a single word, and the parsing node relationship line is a line between two parsing nodes having a semantic relationship and / or a grammatical relationship;

[0059] A reference triple included in the semantic recognition result is obtained according to the parsing graph, wherein the reference triple includes a target parsing node for representing a user intended execution event and a target parsing node relationship line corresponding to the target parsing node.

[0060] It can be seen that in the embodiments of the present application, by improving the accuracy of semantic recognition, the human-computer dialogue script for the user's game strategy can be determined more personalized and accurately, further improving the user's willingness to return to turn-based games.

[0061] In a possible example, the method further includes:

[0062] Expanding the same attribute words for each of the multiple parsing nodes according to a preset vocabulary to obtain multiple expanded parsing nodes;

[0063] Establishing extended parsing node relationship lines between a plurality of extended parsing nodes and other extended parsing nodes and / or parsing nodes;

[0064] If there is a matching relationship between the reference triplet and the preset user call triplet subset, then determine whether there is a matching relationship between the extended reference triplet and other preset user call triplet subsets, the extended reference triplet includes a target extended parsing node for characterizing the user intention execution event and a target extended parsing node relationship line corresponding to the target extended parsing node, and other preset user calls are preset user calls other than the preset user calls that have a matching relationship with the reference triplet;

[0065] If there is a matching relationship between the extended reference triplet and other preset user call triplet subsets, then other preset machine calls that meet the call sequence with other preset user calls are used as the prepared next-hop target preset machine calls. After the preset machine call that meets the call sequence with the preset user call is output as the next-hop target preset machine call, the prepared next-hop target preset machine call is output when there is no matching relationship between the user call received again and the preset user call;

[0066] If there is no matching relationship between the reference triplet and the preset user call triplet subset, determining whether there is a matching relationship between the extended reference triplet and the preset user call triplet subset;

[0067] If there is a matching relationship between the extended reference triplet and the preset user call triplet subset, the preset machine call that satisfies the call sequence with the preset user call is taken as the next-hop target preset machine call.

[0068] It can be seen that in the embodiment of the present application, the same attribute words are expanded for each of the multiple parsing nodes through a preset vocabulary, thereby achieving a more accurate characterization of the target user's intended execution event, thereby improving the semantic recognition accuracy of the user's calls by improving the semantic recognition success rate of the user's calls.

[0069] In a possible example, after conducting a voice call with the terminal device according to the human-computer dialogue script, the method further includes:

[0070] Obtain the target answer record of the terminal device in the voice call;

[0071] Determine target high-frequency words, where the high-frequency words are words in the target answer record that are used to represent the interaction difficulties of the turn-based game and are mentioned more than a preset number of times by the terminal device;

[0072] Determine the target props and send them to the target user's character account. The target props are used to reduce the difficulty of the interaction.

[0073] It can be seen that in the embodiments of the present application, by satisfying the target users' demand for props in turn-based games, the target users' willingness to return to turn-based games is increased.

[0074] In a possible example, the triplet subset of the preset user call includes multiple triples corresponding to historical matching frequencies, the triplet subset of the preset user call includes multiple triplet subsets divided according to user score intervals, and according to the matching relationship between the reference triplet and the triplet subset of the preset user call, and the call sequence of the preset user call, the next hop target preset machine call corresponding to the user call is output, including:

[0075] Obtain the target user points corresponding to the role account of the target user, and determine the target triplet subset into which the points interval corresponding to the target user points falls;

[0076] Obtain multiple triplets in the target triplet subset whose historical matching frequency is within the preset proportion of the first target, match the reference triplet with the multiple triplets whose historical matching frequency is within the preset proportion of the first target, obtain a first matching relationship, and output the next-hop target preset machine call corresponding to the user call according to the first matching relationship.

[0077] It can be seen that in the embodiment of the present application, the matching efficiency of the triples is improved by determining the matching relationship of the reference triples from the high-frequency matching triples in the target triple subset corresponding to the target user points.

[0078] Furthermore, when the multiple triples whose historical matching frequency is within the front first target preset ratio in the above-mentioned target triplet subset are obtained and the reference triplet is matched with the multiple triples of the first target preset ratio, it is also possible to obtain multiple triples whose historical matching frequency is within the front second target preset ratio in the remaining triplet subsets of the preset user call except the target triplet subset, and match the reference triplet with the multiple triples whose historical matching frequency is within the front second target preset ratio to obtain a second matching relationship, and output the next hop target preset machine call corresponding to the user call according to the first matching relationship and the second matching relationship, wherein the second target preset ratio is smaller than the first target preset ratio.

[0079] It can be seen that in the embodiment of the present application, the accuracy of the matching relationship of the reference triplet is ensured by matching the reference triplet with multiple triplets in the triplet subset corresponding to the score interval that the target user's score does not fall into, whose historical matching frequency is within the preset proportion of the first and second targets.

[0080] Furthermore, the high-frequency online time of the target user may also be obtained, and the online time includes the working day time, the weekend time and the holiday time. If the high-frequency online time of the target user is the weekend time and the holiday time, then after determining that the user score interval is greater than at least one high-score triplet subset of the target triplet subset, the above-mentioned acquisition of the triplet subset of the preset user call except the target triplet subset includes a plurality of triples whose historical matching frequency is located in the front second target preset ratio, and the reference triplet is matched with the plurality of triples whose historical matching frequency is located in the front second target preset ratio, including:

[0081] Acquire multiple triples whose historical matching frequency is within the top third target preset ratio in at least one high-scoring triplet subset, and match the reference triples with the multiple triples whose historical matching frequency is within the top third target preset ratio, wherein the third target preset ratio is greater than the first target preset ratio.

[0082] It can be seen that in the embodiment of the present application, the matching process of the reference triples is more targeted to the target users, ensuring the accuracy and personalization of the matching relationship of the reference triples.

[0083] In a second aspect, an embodiment of the present application provides a processing device for recalling old players of a turn-based game by phone, which is applied to a server of a game marketing system. The game marketing system includes a server and a terminal device for logging into a character account of a target user. The above device includes:

[0084] an acquisition unit, configured to acquire at least one game record set corresponding to at least one game plot node of a turn-based game by a target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event at the corresponding game plot node, and a time interval between a time when the target user last logged into the turn-based game and a current system time is greater than a preset time length;

[0085] A first determining unit is used to determine a target game strategy of a target user at a target game plot node according to at least one game record set, where the target game plot node is a game plot node in at least one game plot node;

[0086] A second determination unit is used to determine a human-computer dialogue script for executing a telephone recall service for a target user according to a target game plot node and a target game strategy;

[0087] The call unit is used to make voice calls with the terminal device according to the human-computer dialogue script.

[0088] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and computer execution instructions stored in the memory and executable on the processor, wherein when the computer execution instructions are executed, the electronic device executes part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0089] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a communication device, the communication device executes part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0090] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiment of the present application. The computer program product can be a software installation package.

[0091] It can be seen that in the embodiment of the present application, at least one game record set corresponding to at least one game plot node of the turn-based game of the target user is obtained, and the time interval between the time when the target user last logged into the turn-based game and the current system time is greater than the preset duration; according to at least one game record set, the target game strategy of the target user at the target game plot node is determined, and the target game plot node is a game plot node in at least one game plot node; according to the target game plot node and the target game strategy, a human-computer dialogue script for executing the telephone recall service for the target user is determined; and a voice call is made with the terminal device according to the human-computer dialogue script. By determining the human-computer dialogue script for executing the telephone recall service for the target user according to the target game plot node and the target game strategy, the personalized determination of the human-computer dialogue script is realized, and the user's willingness to return to the turn-based game is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0093] Figure 1 is an example schematic diagram of a user recall system provided in an embodiment of the present application;

[0094] Figure 2 It is a flowchart of a method for recalling old players of a turn-based game by phone provided in an embodiment of the present application;

[0095] Figure 3 It is a schematic diagram of the architecture of a game marketing system provided by an embodiment of the present application;

[0096] Figure 4 This is a schematic diagram of another example of a method for recalling old players of a turn-based game by phone provided in an embodiment of the present application;

[0097] Figure 5 This is a schematic diagram of an example of a parsing diagram of a user call text provided in an embodiment of the present application;

[0098] Figure 6 This is a schematic diagram of another example of a method for recalling old players of a turn-based game by phone provided in an embodiment of the present application;

[0099] Figure 7 It is a structural schematic diagram of a processing device for recalling old players of a turn-based game by phone provided in an embodiment of the present application;

[0100] Figure 8 It is a schematic diagram of the server structure of the hardware operating environment of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0101] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0102] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0103] The following is an introduction to the devices involved in the embodiments of the present application in conjunction with the accompanying drawings.

[0104] Figure 1 is an example schematic diagram of a user recall system provided in an embodiment of the present application, such as Figure 1As shown, the system includes a server and a terminal device for logging into the character account of the target user, the activities associated with the character account include turn-based games, the terminal device corresponds to the target user, and when the turn-based game wants to recall the target user, the server initiates a voice call to the terminal device so that the target user receives the recall information. However, in the above recall process, since the voice call is a fixed template preset for turn-based interactive interaction, it is not personalized for the game strategy corresponding to the historical game rounds of the target user in the turn-based game, so that the target user is difficult to raise the willingness to return to the turn-based game when faced with the same recall words.

[0105] Based on this, the embodiment of the present application provides a processing method for recalling old players of a turn-based game by phone, which is applied to a server of a game marketing system. The game marketing system includes a server and a terminal device for logging into a character account of a target user. Figure 2 , Figure 2 is a flow chart of a method for recalling old players of a turn-based game by phone provided in an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0106] 101: Obtain at least one game record set corresponding to at least one game plot node of a turn-based game of a target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event of the corresponding game plot node, and the time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset duration.

[0107] Among them, the turn-based game, in a specific implementation, can be a strategy game, and further, can also be a turn-based strategy game. Exemplarily, the turn-based game can be a landlord game in a card game.

[0108] Among them, in the specific implementation, if the turn-based game is a story-telling game, then the game plot nodes are developed in multiple plot lines according to the story narrative logic line; if the turn-based game is a card game, such as the Landlord game, then the game plot nodes are the only two plot nodes, that is, the game plot nodes in which the target user plays the role of the landlord, and the game plot nodes in which the target user plays the role of the farmer.

[0109] Among them, the preset duration, in specific implementation, can be 3 months, 6 months or other durations.

[0110] 102: Determine a target game strategy of a target user at a target game plot node according to at least one game record set, where the target game plot node is a game plot node in the at least one game plot node.

[0111] Among them, the target game strategy, in a specific implementation, can be the game strategy used by the target user when playing against the human-computer or other players at the target game plot node.

[0112] 103: Determine a human-computer dialogue script for executing a telephone recall service for a target user according to the target game plot nodes and the target game strategy.

[0113] Among them, the human-computer dialogue script, in the specific implementation, can be a manual customer service call script template with a certain call sequence and corresponding voice jump conditions.

[0114] 104: Conduct a voice call with the terminal device according to the human-computer dialogue script.

[0115] Among them, a voice call is made with the terminal device according to the human-computer dialogue script, that is, a call is made to the terminal device according to the human-computer dialogue script, and a voice call is made with the target user corresponding to the terminal device through an artificial customer service call, so as to awaken the target user's memory of the turn-based game, thereby increasing the target user's willingness to return to the turn-based game.

[0116] For example, see Figure 3 , Figure 3 Schematic diagram of the architecture of a game marketing system provided by an embodiment of the present application. Figure 3 As shown, the game marketing system includes a server and a terminal device for logging into a character account of a target user. When a turn-based game hopes to improve the online activity of the target user, the server obtains at least one game record set corresponding to at least one game plot node of the turn-based game for the target user. The server determines a target game strategy for the target user at the target game plot node based on the at least one game record set. The server determines a human-computer dialogue script for executing a telephone recall service for the target user based on the target game plot node and the target game strategy. Finally, the server initiates a voice call to the terminal device corresponding to the target user according to the human-computer dialogue script, and conducts the voice call after the terminal device is connected.

[0117] It can be seen that in the embodiment of the present application, at least one game record set corresponding to at least one game plot node of the turn-based game of the target user is obtained, and the time interval between the time when the target user last logged into the turn-based game and the current system time is greater than the preset duration; according to at least one game record set, the target game strategy of the target user at the target game plot node is determined, and the target game plot node is a game plot node in at least one game plot node; according to the target game plot node and the target game strategy, a human-computer dialogue script for executing the telephone recall service for the target user is determined; and a voice call is made with the terminal device according to the human-computer dialogue script. By determining the human-computer dialogue script for executing the telephone recall service for the target user according to the target game plot node and the target game strategy, the personalized determination of the human-computer dialogue script is realized, and the user's willingness to return to the turn-based game is improved.

[0118] In a possible example, the at least one game record set includes a plurality of game record sets; and determining the target game strategy of the target user at the target game plot node according to the at least one game record set includes:

[0119] Sort the multiple game record sets in descending order of the number of game records contained therein to obtain a game record set sequence;

[0120] Taking the game plot node corresponding to the first game record set in the game record set sequence as the target game plot node;

[0121] Determine the target game strategy for the target user based on the game record collection of the target game plot node.

[0122] It can be seen that in the embodiment of the present application, by taking the game plot node corresponding to the first game record set in the game record set sequence containing the largest number of game records as the target game plot node, it is determined that the target game strategy of the target user contains the most game records, and then the target game strategy that is closer to the target user can be determined based on the larger number of game records.

[0123] In a possible example, the game record set of the target game plot node includes multiple game records, and the game event refers to a game process event in which the user fully participates from the starting point to the end point of the same game plot node, the starting point refers to the start time node of the corresponding game plot node, and the end point refers to the end time node of the corresponding game plot node;

[0124] The above-mentioned game record set based on the plot node of the target game determines the target game strategy of the target user, including:

[0125] If the target game plot node requires only one game character, perform the following operations:

[0126] Analyze the game data of at least one game round in each of the multiple game records to obtain a reference game strategy adopted by the target user in each game record;

[0127] Determine a target game strategy according to a plurality of reference game strategies corresponding to the obtained plurality of game records;

[0128] If the target game plot node requires multiple game characters, perform the following operations:

[0129] Grouping multiple game records according to game characters to obtain at least one game record group, wherein the game character combinations in any two game record groups are different, and the same game record group includes one or more game records, and the game character combinations corresponding to any two game records in a single game record group including multiple game records are the same;

[0130] For each game record group in at least one game record group, analyzing game data of at least one game round of each game record in the currently processed game record group to determine a reference game strategy adopted by the target user, and obtaining one or more reference game strategies corresponding to one or more game records in each game record group;

[0131] According to one or more reference game strategies of each game record group, a target game strategy for a target user under different game character combinations is determined.

[0132] Among them, in a specific implementation, the game character may refer to the game character included in the character account of the target user, which may be a single or multiple game characters; it may also refer to the game characters included in the character accounts of the target user and other users.

[0133] Among them, the plurality of game records are grouped according to the game characters to obtain at least one game record group. In a specific implementation, if the turn-based game is a role-playing battle game, a combination of five game characters may be included in one game record group. The game character combinations corresponding to any two game records in a single game record group including a plurality of game records are the same, that is, the game character combinations corresponding to the game records in one game record group are the same without any difference, so that the game record grouping is more targeted and accurate in determining the reference game strategy adopted by the target user.

[0134] For example, see Figure 4 , Figure 4 is an example schematic diagram of another processing method for recalling old players of a turn-based game by phone provided in an embodiment of the present application, such as Figure 4As shown, the turn-based game is a role-playing game, so multiple game records are grouped according to the game characters to obtain two game record groups, wherein game record group 1 includes two game records, game record 1 and game record 2, and the game character combinations corresponding to the two game records are A, B, C, and D, and game record group 2 includes one game record, game record 3, and the corresponding game character combinations are B, C, and E.

[0135] It can be seen that in the embodiment of the present application, in the process of determining the target game strategy of the target user based on the game record set of the target game plot node, if the game character required by the target game plot node is single, the game data of at least one game round in each game record of the multiple game records is analyzed to obtain a reference game strategy adopted by the target user in each game record, and the target game strategy is determined based on the multiple reference game strategies corresponding to the obtained multiple game records; and if the target game plot node requires multiple game characters, the multiple game records are grouped according to the game characters to obtain at least one game record grouping, and for each game record group in the at least one game record grouping, the game data of at least one game round of each game record in the currently processed game record grouping is analyzed to determine the reference game strategy adopted by the target user, and one or more reference game strategies corresponding to one or more game records of each game record grouping are obtained, and finally the target game strategy of the target user under different game character combinations is determined based on the one or more reference game strategies of each game record grouping.

[0136] In a possible example, the game data of at least one game round in each of the multiple game records is analyzed to obtain a reference game strategy adopted by the target user in each game record, including:

[0137] If at least one game round of the currently processed game record is a single game round, determining a reference game strategy adopted by the target user in the currently processed game record according to the user game data in the single game round;

[0138] If at least one of the game rounds of the currently processed game record is multiple game rounds, perform the following operations:

[0139] Analyze the correlation of user-side operation strategies before adjacent game rounds in multiple game rounds, converge game rounds with consistent correlation into a single reference game round, and obtain an updated game round sequence;

[0140] Determine the interaction complexity of the target game plot node according to the updated game turn sequence;

[0141] If the interaction complexity is greater than or equal to the preset complexity, manually summarizing the updated game turn sequence to determine a reference game strategy adopted by the target user in the currently processed game record;

[0142] If the interaction complexity is lower than the preset complexity, the reference game strategy adopted by the target user in the currently processed game record is determined according to the user game data in the updated game round sequence.

[0143] Among them, the correlation of user-side operation strategies before adjacent game rounds in multiple game rounds is analyzed, and the game rounds with consistent correlation are converged into a single reference game round to obtain an updated game round sequence. In a specific implementation, it can be determined based on game data of adjacent game rounds that are critical to the game plot or game strategy in multiple game rounds.

[0144] Among them, the interaction complexity of the target game plot node is determined according to the updated game round sequence. In a specific implementation, it can be determined by weighted calculation of the number of rounds corresponding to the updated game round sequence and the average number of operations in a single round.

[0145] Exemplarily, if the turn-based game is a Landlord game, and the game plot node is that the target user plays the landlord role, then the updated game turn sequence is manually summarized to determine the reference game strategy adopted by the target user in the currently processed game record. In a specific implementation, the reference game strategy can be that the target user tends to run single cards first, then pairs, and finally keep a king bomb; it can also be an artificial convergence of the target user's selection tendency in a specific game situation, etc.

[0146] It can be seen that in the embodiment of the present application, when analyzing the game data of at least one game round in each game record of multiple game records to obtain the reference game strategy adopted by the target user in each game record, if at least one game round of the game record currently being processed is a single game round, the reference game strategy adopted by the target user in the game record currently being processed is determined based on the user game data in the single game round; and if at least one game round of the game record currently being processed is multiple game rounds, the correlation of the user-side operation strategies before adjacent game rounds in the multiple game rounds is analyzed, and the game rounds with the correlation as consistent operations are converged into a single reference game round to obtain an updated game round sequence, and the interaction complexity of the target game plot node is determined based on the updated game round sequence, and if the interaction complexity is greater than or equal to the preset complexity, the updated game round sequence is manually summarized to determine the reference game strategy adopted by the target user in the game record currently being processed, and if the interaction complexity is lower than the preset complexity, the reference game strategy adopted by the target user in the game record currently being processed is determined based on the user game data in the updated game round sequence. This makes the process of determining the reference game strategy adopted by the target user in each game record more personalized and targeted, and improves the accuracy of the reference game strategy.

[0147] In a possible example, determining the interaction complexity of the target game plot node according to the updated game turn sequence includes:

[0148] Determine the average number of user operations per round of the game round sequence according to the number of user operations in the game data of each game round in the updated game round sequence;

[0149] The interaction complexity of the target game plot nodes is determined based on the number of rounds contained in the game round sequence and the average number of user operations in a single round.

[0150] It can be seen that in the embodiment of the present application, when determining the interaction complexity of the target game plot node according to the updated game round sequence, the average number of user operations per round of the game round sequence is determined according to the number of user operations in the game data of each game round in the updated game round sequence, and finally the interaction complexity of the target game plot node is determined according to the number of rounds included in the game round sequence and the average number of user operations per round. The interaction complexity of the target game plot node is determined by the number of rounds and the number of user operations included in the game round sequence, so that the determination process of the interaction complexity of the target game plot node is closer to the operational characteristics of turn-based games.

[0151] In a possible example, determining the target game strategy according to the multiple reference game strategies corresponding to the obtained multiple game records includes:

[0152] The reference game strategy with the largest number of repetitions among multiple reference game strategies is used as the target game strategy; or,

[0153] The reference game strategy whose game event is closest to the current system time among multiple reference game strategies is used as the target game strategy.

[0154] It can be seen that in the embodiment of the present application, when determining the target game strategy according to the multiple reference game strategies corresponding to the obtained multiple game records, the reference game strategy with the largest number of repetitions among the multiple reference game strategies is used as the target game strategy, so as to determine that the obtained target game strategy is more in line with the game habits of the target user; or, the reference game strategy whose game event is closest to the current system time among the multiple reference game strategies is used as the target game strategy, so as to determine that the obtained target game strategy is closer in time to the target user and has a clearer game impression. Finally, the final determined target game strategy has more reference applicability.

[0155] In a possible example, if at least one game plot node requires a single game character, the human-computer dialogue script includes a guiding speech and a human-computer dialogue plot node, and the guiding speech includes an introduction to the single game character;

[0156] If at least one game plot node requires multiple game characters, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes, and the guiding words include introductions to the multiple game characters.

[0157] Among them, the guiding words include the introduction of a single game character. In a specific implementation, the guiding words may include introduction information such as the character skills, skill effects, etc. of a single game character.

[0158] Among them, the human-computer dialogue plot nodes can be determined according to the type of turn-based game in a specific implementation. For example, when the turn-based game is a Landlord game, the game plot nodes can include plot nodes such as "user confirms hand cards" and "user plays cards", thereby determining the human-computer dialogue plot nodes based on the game plot nodes.

[0159] It can be seen that in the embodiment of the present application, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes. The guiding words include an introduction to the game characters, so that the human-computer dialogue script is closer to the game scene of the turn-based game, thereby further awakening the target user's game memory of the turn-based game, and then increasing the target user's willingness to return to the turn-based game.

[0160] In a possible example, the human-machine dialogue script includes a preset machine call and a preset user call, and a call sequence of the preset machine call and the preset user call. The above-mentioned voice call with the terminal device according to the human-machine dialogue script includes:

[0161] Output voice call statements to the terminal device according to the call sequence of the preset machine call;

[0162] receiving a user call fed back by a terminal device, performing semantic recognition on the user call, and obtaining a semantic recognition result of the user call, wherein the semantic recognition result includes a reference triplet;

[0163] According to the matching relationship between the reference triplet and the triplet subset of the preset user call, and the call sequence, the next hop target preset machine call corresponding to the user call is output.

[0164] Among them, semantic recognition is performed on user calls to obtain semantic recognition results of user calls. In a specific implementation, it can be obtained by using a DNN-HMM speech recognition system or by using a natural language processing tool Stanford Core NLP.

[0165] Among them, in a specific implementation, the reference triple is constructed according to at least two lexical nodes, one or more semantic relations and / or grammatical relations after converting the text corresponding to the user call into a semantic parsing graph through word segmentation processing to obtain at least two lexical nodes. A reference triple is formed by one or more semantic relations and / or grammatical relations in a sentence and lexical nodes connected at both ends of the semantic relations and / or grammatical relations. Lexical nodes can be words, phrases, entities, etc. The expression form of the reference triple can be {r(x, y)}, wherein x represents the lexical node at the first end of the reference triple, y represents the lexical node at the second end of the reference triple, and r represents the semantic relation and / or grammatical relation between the lexical node x and the lexical node y. In a user call, there may be two or more lexical nodes and multiple semantic relations and / or grammatical relations. Therefore, there may be at least one reference triple in a user call.

[0166] Furthermore, the semantic recognition result includes a reference triple. In a specific implementation, the semantic recognition result and the reference triple may be completely consistent in wording, or the meaning of the semantic recognition result may be consistent with the meaning of the reference triple. For example, if the semantic recognition result is "which cards I can play", the reference triple may be "which cards I can play" which is completely consistent with the semantic recognition result in wording, or may be a reference triple such as "what cards I have", "what cards I can play", "which cards I have", "what cards I can play" which is consistent with the meaning of the semantic recognition result.

[0167] The preset triplet subset of user calls, in a specific implementation, refers to a subset consisting of multiple reference triples that may appear in the preset user call process.

[0168] Exemplarily, if the semantic recognition result of the user call includes a matching relationship between the reference triplet and the triplet subset of the preset user call as "What cards do I have to play", and the response result to "What cards do I have to play" in the call sequence of the preset user call is "You have XX cards...XX cards", then the next-hop target preset machine call corresponding to the output user call is to inform the target user corresponding to the terminal device of his or her specific cards, so as to guide the target user to select the cards he or she wants to use.

[0169] It can be seen that in the embodiment of the present application, when a voice call is made with a terminal device according to a human-computer dialogue script, a voice call statement is output to the terminal device according to a call sequence of a preset machine call, and a user call fed back by the terminal device is received, and semantic recognition is performed on the user call to obtain a semantic recognition result of the user call, and finally, according to the matching relationship between the reference triple and the triple subset of the preset user call, and the call sequence of the preset user call, the preset machine call corresponding to the next hop target of the user call is output. Through a human-computer dialogue script with a certain dialogue sequence and jump conditions, a voice call is made with a terminal device, which improves the fun and interactivity of the voice call for the target user, awakens the target user's interactive memory of the turn-based game, and thus improves the user's willingness to return to the turn-based game.

[0170] In a possible example, the above-mentioned preset machine call and the call sequence of the preset machine call are determined by the game interaction scenario of the turn-based game.

[0171] Among them, the preset machine call, in a specific implementation, may include background sound configuration information, voice configuration information of manual customer service, and call plot configuration information, etc. The background sound configuration information may be the background music of a turn-based game; the voice configuration information of manual customer service may be the narration sound of a turn-based game; the call plot configuration information may be the game scene narration in a turn-based game, such as explanations and prompts of the game scene, etc.

[0172] The game interaction scene of the turn-based game, in a specific implementation, may be an actual game scene of the turn-based game. For example, if the turn-based game is a Landlord game, the game interaction scene of the turn-based game is a card duel.

[0173] For example, during a voice call with a terminal device according to a human-computer dialogue script, the background sound can be set to the background music of a turn-based game to awaken the target user's memory of the turn-based game through hearing. Moreover, if there is no reply from the target user from the terminal device for a long time, the server can broadcast the game scene narration through the voice of an artificial customer service representative, "Hurry up, the flowers I've been waiting for are all withered!" to prompt the target user corresponding to the terminal device to initiate the next command.

[0174] It can be seen that in the embodiment of the present application, since the preset machine call and the call sequence of the preset machine call are determined by the game interaction scenario of the turn-based game, the content of the voice call is closely integrated with the game interaction scenario of the turn-based game, so that the voice call can further awaken the target user's memory of the turn-based game and thereby increase the user's willingness to return to the turn-based game.

[0175] In a possible example, the outputting of the next hop target preset machine call corresponding to the user call according to the matching relationship between the semantic recognition result and the triplet subset of the preset user call and the call sequence of the preset user call includes:

[0176] Determine whether there is a matching relationship between the reference triplet and a subset of triplet of a preset user call;

[0177] If there is a matching relationship between the reference triplet and the preset user call triplet subset, outputting the preset machine call that satisfies the call sequence with the preset user call to the terminal device as the next-hop target preset machine call;

[0178] If there is no matching relationship between the reference triplet and the preset user call triplet subset, the target emotional tendency corresponding to the user call is determined according to the semantic recognition result, and the next-hop target preset machine call matching the target emotional tendency is obtained from the emotional sentence library according to the target emotional tendency, wherein the emotional sentence library includes the correspondence between multiple preset emotional tendencies and multiple preset machine calls.

[0179] Among them, determining whether there is a matching relationship between the reference triple and the triple subset of the preset user call, in a specific implementation, can be to determine whether the reference triple included in the semantic recognition result contains a triple that is completely identical in terms of literal meaning in the triple subset of the preset user call, or it can be to determine whether the reference triple included in the semantic recognition result contains a triple that is consistent in terms of meaning in the triple subset of the preset user call.

[0180] For example, in a specific implementation, the preset machine call that satisfies the call sequence may be that if the target user wishes to confirm the hand, the preset machine call is to broadcast the hand information to the target user corresponding to the terminal device; if the target user wishes to play a card, the preset machine call is to broadcast the opponent's card information to the target user corresponding to the terminal device based on the card played by the target user. By analogy, there is a question-answer logic correspondence relationship between the call sequence and the preset machine call.

[0181] Among them, the target emotional tendency corresponding to the user's call is determined according to the semantic recognition result. In the specific implementation, it means determining the target emotional tendency corresponding to the user's call through semantic sentiment analysis in semantic analysis.

[0182] The target emotional tendency may include positive emotion, negative emotion or other emotional tendencies. Correspondingly, according to the classification of the target emotional tendency, the emotional sentence library may be constructed corresponding to the target emotional classification. For example, if the target emotional tendency includes positive emotion and negative emotion, the emotional sentence library may include a positive emotional sentence library and a negative emotional sentence library.

[0183] Exemplarily, if the reference triplet is "Why are these cards so bad?" which does not exist in the preset user call triplet subset, then the target emotional tendency corresponding to the user call is determined to be negative emotion based on the semantic recognition result. Then, based on the target emotional tendency of negative emotion, the next-hop target preset machine call that matches it is obtained from the negative emotional sentence library. Combined with the interactive scenario of Landlord, the next-hop target preset machine call corresponding to the above reference triplet can be set to "Do you need to use XX props" to guide the user to issue the next instruction.

[0184] It can be seen that in the embodiment of the present application, when the next-hop target preset machine call corresponding to the user call is output according to the matching relationship between the semantic recognition result and the triplet subset of the preset user call, and the call sequence of the preset user call, if there is a matching relationship between the reference triplet and the preset user call triplet subset, the preset machine call that satisfies the call sequence with the preset user call is output to the terminal device as the next-hop target preset machine call; if there is no matching relationship between the reference triplet and the preset user call triplet subset, the target emotional tendency corresponding to the user call is determined according to the semantic recognition result, and the next-hop target preset machine call matching the target emotional tendency is obtained from the emotional sentence library according to the target emotional tendency. Thereby improving the flexibility and intelligence of the human-computer dialogue script for voice calls, thereby improving the fun and interactivity of voice calls for target users, awakening the target user's interactive memory of turn-based games, and thereby improving the user's willingness to return to turn-based games.

[0185] In a possible example, the semantic recognition of the user call is performed to obtain the semantic recognition result of the user call, including:

[0186] Determine the user call text according to the user call;

[0187] Determine a parsing graph of the user's call text, the parsing graph comprising a plurality of parsing nodes and at least one parsing node relationship line, the parsing node is a single word, and the parsing node relationship line is a line between two parsing nodes having a semantic relationship and / or a grammatical relationship;

[0188] A reference triple included in the semantic recognition result is obtained according to the parsing graph, wherein the reference triple includes a target parsing node for representing a user intended execution event and a target parsing node relationship line corresponding to the target parsing node.

[0189] Among them, the user call text is determined according to the user call. In a specific implementation, the meaning of the user call referred to by semantic recognition can be converted into text form to obtain the user call text.

[0190] Among them, the semantic relationship and / or grammatical relationship, in a specific implementation, may include dependency relationships in the natural language processing tool Stanford CoreNLP, for example, verb (give) -> direct object (dobj), the main component of a sentence (generally a verb) -> subject (nominal subject, nsubj), dependency relationship (dependent, dep), modal verb modifier (modal verb modifier, mmod) and other dependency relationships.

[0191] For example, see Figure 5 , Figure 5 is an example schematic diagram of a parsing diagram of a user call text provided in an embodiment of the present application, such as Figure 5 As shown, when the user call text is "Xiao Ming wants to sit down and play Dou Dizhu", "Xiao Ming" is the subject, "want" is the modal verb modifier, "sit down" is the main component of the sentence, "play" is the verb, and "Dou Dizhu" is the direct object. Therefore, in the analysis diagram of the user call text "I want to sit down and play Dou Dizhu", the relationship between "sit down" and "Xiao Ming" is the main component of the sentence --> subject, "want" is the modal verb modifier of "sit down", there is a dependency relationship between "sit down" and "play", and the relationship between "play" and "Dou Dizhu" is the verb --> direct object.

[0192] It can be seen that in the embodiment of the present application, when semantic recognition is performed on user calls to obtain semantic recognition results of the user calls, the user call text is determined based on the user calls and then the parsing graph of the user call text is determined, and the reference triples included in the semantic recognition results are obtained based on the parsing graph, wherein the reference triples include a target parsing node for characterizing the user's intended execution event and a target parsing node relationship line corresponding to the target parsing node, thereby improving the accuracy of semantic recognition, and thereby enabling the human-computer dialogue script for the user's game strategy to be determined more personalized and accurately, thereby further improving the user's willingness to return to turn-based games.

[0193] In a possible example, the method further includes:

[0194] Expanding the same attribute words for each of the multiple parsing nodes according to a preset vocabulary to obtain multiple expanded parsing nodes;

[0195] Establishing extended parsing node relationship lines between a plurality of extended parsing nodes and other extended parsing nodes and / or parsing nodes;

[0196] If there is a matching relationship between the reference triplet and the preset user call triplet subset, then determine whether there is a matching relationship between the extended reference triplet and other preset user call triplet subsets, the extended reference triplet includes a target extended parsing node for characterizing the user intention execution event and a target extended parsing node relationship line corresponding to the target extended parsing node, and other preset user calls are preset user calls other than the preset user calls that have a matching relationship with the reference triplet;

[0197] If there is a matching relationship between the extended reference triplet and other preset user call triplet subsets, then other preset machine calls that meet the call sequence with other preset user calls are used as the prepared next-hop target preset machine calls. After the preset machine call that meets the call sequence with the preset user call is output as the next-hop target preset machine call, the prepared next-hop target preset machine call is output when there is no matching relationship between the user call received again and the preset user call;

[0198] If there is no matching relationship between the reference triplet and the preset user call triplet subset, determining whether there is a matching relationship between the extended reference triplet and the preset user call triplet subset;

[0199] If there is a matching relationship between the extended reference triplet and the preset user call triplet subset, the preset machine call that satisfies the call sequence with the preset user call is taken as the next-hop target preset machine call.

[0200] Among them, the preset vocabulary, in a specific implementation, can be an activity terminology vocabulary of a turn-based game.

[0201] Among them, the same attribute words are expanded for each of the multiple parsing nodes according to a preset vocabulary to obtain multiple extended parsing nodes. In a specific implementation, the expanded parsing nodes can be obtained by determining the synonyms of the lexical meaning referred to by the parsing node. For example, if the lexical meaning referred to by the parsing node is "exam", then the multiple extended parsing nodes obtained after the lexical meaning of the parsing node is expanded with the same attribute words may include synonyms of "exam" such as "assessment", "inspection", and "test"; the expanded parsing nodes can also be obtained by determining replacement words that may point to the same thing as the lexical meaning referred to by the parsing node. For example, if the lexical meaning referred to by the parsing node is "exam", then the multiple extended parsing nodes obtained after the lexical meaning of the parsing node is expanded with the same attribute words may include replacement words such as "score", "grade", "test paper", and "review" that point to the same thing as "exam".

[0202] For example, see Figure 6 , Figure 6 is an example schematic diagram of another processing method for recalling old players of a turn-based game by phone provided in an embodiment of the present application, such as Figure 6 As shown, there are parsing nodes A and B. The server performs the same attribute word expansion on parsing nodes A and B according to the preset vocabulary to obtain extended parsing nodes including A, B, A1, A2, B1, and B2. The above extended parsing nodes are connected in pairs to obtain multiple extended parsing node relationship lines. Finally, the server determines the target parsing node representing the target user's intended execution event and the target parsing node relationship line corresponding to the target parsing node according to the multiple extended parsing nodes and multiple extended parsing node relationship lines obtained after the same attribute word expansion. Obviously, after the same attribute word expansion is performed, the target parsing node representing the target user's intended execution event and the target parsing node relationship line corresponding to the target parsing node can be determined more accurately.

[0203] It can be seen that in the embodiment of the present application, the same attribute words are expanded for each of the multiple parsing nodes according to the preset vocabulary to obtain multiple extended parsing nodes, and extended parsing node relationship lines between the multiple extended parsing nodes and other extended parsing nodes and / or parsing nodes are established, so that if there is a matching relationship between the reference triple and the preset user call triple subset, it is determined whether there is a matching relationship between the extended reference triple and the other preset user call triple subset. If there is a matching relationship between the extended reference triple and the other preset user call triple subset, other preset machine calls that meet the call sequence with other preset user calls are used as the preparatory next-hop target preset machine calls; and if there is no matching relationship between the reference triple and the preset user call triple subset, it is determined whether there is a matching relationship between the extended reference triple and the preset user call triple subset. If there is a matching relationship between the extended reference triple and the preset user call triple subset, the preset machine call that meets the call sequence with the preset user call is used as the next-hop target preset machine call. By using a preset vocabulary to expand the same attribute words for each of the multiple parsing nodes, it is possible to more accurately characterize the target user's intended execution events, thereby improving the semantic recognition accuracy of user calls by increasing the semantic recognition success rate of user calls.

[0204] In a possible example, after conducting a voice call with the terminal device according to the human-computer dialogue script, the method further includes:

[0205] Obtain the target answer record of the terminal device in the voice call;

[0206] Determine target high-frequency words, where the high-frequency words are words in the target answer record that are used to represent the interaction difficulties of the turn-based game and are mentioned more than a preset number of times by the terminal device;

[0207] Determine the target props and send them to the target user's character account. The target props are used to reduce the difficulty of the interaction.

[0208] Among them, the target answer record, in a specific implementation, can be a collection of sentences fed back by the target user corresponding to the terminal device in response to the voice call.

[0209] The preset number of times may be 3 times or other times in a specific implementation.

[0210] Among them, the interactive difficulty of the turn-based game can be determined according to the activity characteristics of the turn-based game in a specific implementation. For example, if the turn-based game is a landlord game, the interactive difficulty includes no specific hand cards, no points, etc.

[0211] Among them, the target props, in the specific implementation, if the turn-based game is a Landlord game, can be game props in the Landlord game such as "card counter" props, "negative score clearing" props, and "points double" props.

[0212] It can be seen that in the embodiment of the present application, after making a voice call with the terminal device according to the human-computer dialogue script, by obtaining the target answer record of the terminal device in the voice call, and determining the target high-frequency words in the target answer record that are used to characterize the interaction difficulties of the turn-based game and are mentioned more than the preset number of times by the terminal device, the target props used to reduce the difficulty of the interaction difficulties are determined and sent to the character account of the target user. By satisfying the target user's demand for props in turn-based games, the target user's willingness to return to turn-based games is increased.

[0213] In a possible example, the triplet subset of the preset user call includes multiple triples corresponding to historical matching frequencies, the triplet subset of the preset user call includes multiple triplet subsets divided according to user score intervals, and according to the matching relationship between the reference triplet and the triplet subset of the preset user call, and the call sequence of the preset user call, the next hop target preset machine call corresponding to the user call is output, including:

[0214] Obtain the target user points corresponding to the role account of the target user, and determine the target triplet subset into which the points interval corresponding to the target user points falls;

[0215] Obtain multiple triplets in the target triplet subset whose historical matching frequency is within the preset proportion of the first target, match the reference triplet with the multiple triplets whose historical matching frequency is within the preset proportion of the first target, obtain a first matching relationship, and output the next-hop target preset machine call corresponding to the user call according to the first matching relationship.

[0216] Exemplarily, the triplet subsets of preset user calls include multiple triplet subsets divided according to user point ranges. In a specific implementation, if the user point range of a turn-based game is 0 to 10,000, it can be divided into three triplet subsets, namely, a first triplet subset, a second triplet subset and a third triplet subset, according to the user point range. The first triplet subset corresponds to a user point range of 6,667 to 10,000, the second triplet subset corresponds to a user point range of 3,334 to 6,666, and the third triplet subset corresponds to a user point range of 0 to 3,333.

[0217] It can be seen that in the embodiment of the present application, by determining the target triplet subset into which the score interval corresponding to the target user's score falls, and then matching the reference triplet with multiple triplets whose historical matching frequency is at a preset ratio of the first target, the matching relationship of the reference triplet is determined from the high-frequency matching triples in the target triplet subset corresponding to the target user's score, thereby improving the matching efficiency of the triplet.

[0218] Furthermore, when the multiple triples whose historical matching frequency is within the front first target preset ratio in the above-mentioned target triplet subset are obtained and the reference triplet is matched with the multiple triples of the first target preset ratio, it is also possible to obtain multiple triples whose historical matching frequency is within the front second target preset ratio in the remaining triplet subsets of the preset user call except the target triplet subset, and match the reference triplet with the multiple triples whose historical matching frequency is within the front second target preset ratio to obtain a second matching relationship, and output the next hop target preset machine call corresponding to the user call according to the first matching relationship and the second matching relationship, wherein the second target preset ratio is smaller than the first target preset ratio.

[0219] It can be seen that in the embodiment of the present application, the accuracy of the matching relationship of the reference triplet is ensured by matching the reference triplet with multiple triplets in the triplet subset corresponding to the score interval that the target user's score does not fall into, whose historical matching frequency is within the preset proportion of the first and second targets.

[0220] Furthermore, the high-frequency online time of the target user may also be obtained, and the online time includes the working day time, the weekend time and the holiday time. If the high-frequency online time of the target user is the weekend time and the holiday time, then after determining that the user score interval is greater than at least one high-score triplet subset of the target triplet subset, the above-mentioned acquisition of the triplet subset of the preset user call except the target triplet subset includes a plurality of triples whose historical matching frequency is located in the front second target preset ratio, and the reference triplet is matched with the plurality of triples whose historical matching frequency is located in the front second target preset ratio, including:

[0221] Acquire multiple triples whose historical matching frequency is within the top third target preset ratio in at least one high-scoring triplet subset, and match the reference triples with the multiple triples whose historical matching frequency is within the top third target preset ratio, wherein the third target preset ratio is greater than the first target preset ratio.

[0222] It can be seen that in the embodiment of the present application, by obtaining the high-frequency online time of the target user, when the target user's active time is only the weekend time and holiday time of the week, it can be known that the target user has a strong interactive ability for turn-based games, then multiple triples with a historical matching frequency in the top third target preset ratio in at least one high-scoring triple subset are obtained, and the reference triples are matched with multiple triples with a historical matching frequency in the top third target preset ratio. This makes the matching process of the reference triples more targeted for the target user, ensuring the accuracy and personalization of the matching relationship of the reference triples.

[0223] With the above Figure 2 For details on the embodiments shown in the drawings, please refer to Figure 7 , Figure 7 is a schematic diagram of the structure of a processing device for recalling old players of a turn-based game by phone provided in an embodiment of the present application, such as Figure 7 As shown:

[0224] A processing device for recalling old players of a turn-based game by phone is applied to a server of a game marketing system. The game marketing system includes a server and a terminal device for logging into a character account of a target user. The device includes:

[0225] An acquisition unit 201 is used to acquire at least one game record set corresponding to at least one game plot node of a turn-based game by a target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event at the corresponding game plot node, and the time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset time length;

[0226] A first determining unit 202 is used to determine a target game strategy of a target user at a target game plot node according to at least one game record set, where the target game plot node is a game plot node in at least one game plot node;

[0227] The second determining unit 203 is used to determine a human-computer dialogue script for executing a telephone recall service for a target user according to the target game plot node and the target game strategy;

[0228] The conversation unit 204 is used to make a voice conversation with the terminal device according to the human-computer dialogue script.

[0229] It can be seen that in the device provided in the embodiment of the present application, at least one game record set corresponding to at least one game plot node of the turn-based game of the target user is obtained, and the time interval between the time when the target user last logged into the turn-based game and the current system time is greater than the preset duration; according to at least one game record set, the target game strategy of the target user at the target game plot node is determined, and the target game plot node is a game plot node in at least one game plot node; according to the target game plot node and the target game strategy, a human-computer dialogue script for executing a telephone recall service for the target user is determined; and a voice call is made with the terminal device according to the human-computer dialogue script. The device provided in the embodiment of the present application determines the human-computer dialogue script for executing a telephone recall service for the target user according to the target game plot node and the target game strategy, so as to realize the personalized determination of the human-computer dialogue script and improve the user's willingness to return to the turn-based game.

[0230] Specifically, the embodiment of the present application can divide the functional units of the processing device for recalling old players of the turn-based game by phone according to the above method example. For example, each functional unit can be divided corresponding to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0231] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0232] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0233] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0234] If the above-mentioned integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0235] With the above Figure 2 The embodiment shown is consistent with the embodiment shown, the embodiment of the present application provides an electronic device, see Figure 8 , Figure 8 is a schematic diagram of a server structure of a hardware operating environment of an electronic device provided in an embodiment of the present application, such as Figure 8 As shown, the electronic device includes a processor, a memory, and computer execution instructions stored in the memory and executable on the processor. When the computer execution instructions are executed, the electronic device executes instructions including any step of the processing method for recalling old players of a turn-based game by phone.

[0236] Among them, the processor is CPU (Central Processing Unit).

[0237] Among them, the memory, optionally, the memory can be a high-speed RAM memory, or a stable memory, such as a disk memory.

[0238] Those skilled in the art will understand that Figure 8 The structure of the server shown in the figure does not constitute a limitation thereof, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0239] like Figure 8As shown, the memory may include an operating system, a network communication module, and a computer execution instruction of a method for recalling old players of a turn-based game by phone. The operating system is used to manage and control server hardware and software resources and support the operation of computer execution instructions. The network communication module is used to realize communication between components inside the memory, and communication with other hardware and software inside the server. Communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), etc.

[0240] exist Figure 8 In the server shown, the processor is used to execute computer-executable instructions for personnel management stored in the memory to implement the following steps: obtaining at least one game record set corresponding to at least one game plot node of a turn-based game of a target user, a single game record set including at least one game record of at least one game event of the user at the corresponding game plot node, a single game record including game data of at least one game round generated by the user in a single game event of the corresponding game plot node, and the time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset time length; determining a target game strategy of the target user at a target game plot node based on at least one game record set, the target game plot node being a game plot node in at least one game plot node; determining a human-computer dialogue script for executing a telephone recall service for the target user based on the target game plot node and the target game strategy; and making a voice call with the terminal device according to the human-computer dialogue script.

[0241] The specific implementation of the server involved in this application can be found in the various embodiments of the above-mentioned processing method for recalling old players of turn-based games by phone, which will not be described in detail here.

[0242] The embodiment of the present application provides a computer-readable storage medium, in which a computer instruction is stored. When the computer instruction is executed on a communication device, the communication device executes the following steps: obtaining at least one game record set corresponding to at least one game plot node of a turn-based game of a target user, a single game record set includes at least one game record of at least one game event of the user in the corresponding game plot node, a single game record includes game data of at least one game round generated by the user in a single game event of the corresponding game plot node, and the time interval between the time when the target user last logged into the turn-based game and the current system time is greater than a preset time length; determining a target game strategy of the target user in a target game plot node according to at least one game record set, the target game plot node being a game plot node in at least one game plot node; determining a human-computer dialogue script for executing a telephone recall service for the target user according to the target game plot node and the target game strategy; and making a voice call with a terminal device according to the human-computer dialogue script. The above-mentioned computer includes an electronic device.

[0243] Among them, electronic terminal devices include mobile phones, tablet computers, personal digital assistants, wearable devices, etc.

[0244] Among them, the computer-readable storage medium can be an internal storage unit of the electronic device described in the above embodiment, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the above electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Further, the computer-readable storage medium can also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer-executable instructions and other computer-executable instructions and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0245] The specific implementation of the computer-readable storage medium involved in the present application can be found in the various embodiments of the above-mentioned processing method for recalling old players of a turn-based game by phone, which will not be described in detail here.

[0246] An embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to cause a computer to perform part or all of the steps of any one of the methods for recalling old players of a turn-based game by telephone as recorded in the above method embodiments. The computer program product can be a software installation package.

[0247] It should be noted that, for the sake of simplicity, any of the aforementioned embodiments of the processing method for recalling old players of a turn-based game by phone are described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present application.

[0248] The above is a detailed introduction to the embodiments of the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application's method for recalling old players of a turn-based game by phone. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for a general technician in this field, based on the idea of ​​the present application's method for recalling old players of a turn-based game by phone, there will be changes in the specific implementation method and scope of application. In summary, the content of this specification should not be understood as a limitation on the present application.

[0249] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude multiple situations. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0250] A person skilled in the art can understand that all or part of the steps in the various methods of any of the above-mentioned method embodiments for recalling old players of a turn-based game by phone can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated: ROM), a random access memory (English: Random Access Memory, abbreviated: RAM), a disk or an optical disk, etc.

[0251] Obviously, those skilled in the art can make various changes and modifications to the processing method for recalling old players of a turn-based game by phone provided by the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for recalling old players of a turn-based game by phone, characterized in that: A server applied to a game marketing system, the game marketing system comprising the server and a terminal device for logging into a character account of a target user, the method comprising: Acquire at least one game record set corresponding to at least one game plot node of the turn-based game by the target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event at the corresponding game plot node, and the time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset time length; Determining a target game strategy of the target user at a target game plot node according to the at least one game record set, wherein the target game plot node is a game plot node in the at least one game plot node; when the at least one game record set includes multiple game record sets, determining the target game strategy of the target user at the target game plot node according to the at least one game record set comprises: sorting the multiple game record sets in descending order of the number of game records included to obtain a game record set sequence; taking a game plot node corresponding to a first game record set in the game record set sequence as the target game plot node; determining the target game strategy of the target user according to the game record set of the target game plot node; Determine a human-computer dialogue script for executing a telephone recall service for the target user according to the target game plot node and the target game strategy; Conduct a voice call with the terminal device according to the human-computer dialogue script.

2. The method according to claim 1, characterized in that The game record set of the target game plot node includes multiple game records, and the game event refers to a game process event in which the user fully participates from the starting point to the end point of the same game plot node, the starting point refers to the start time node of the corresponding game plot node, and the end point refers to the end time node of the corresponding game plot node; The determining the target game strategy of the target user according to the game record set of the target game plot node includes: If the target game plot node requires a single game character, perform the following operations: Analyze the game data of at least one game round in each of the multiple game records to obtain a reference game strategy adopted by the target user in each game record; Determining the target game strategy according to the obtained multiple reference game strategies corresponding to the multiple game records; If the target game plot node requires multiple game characters, perform the following operations: The plurality of game records are grouped according to game characters to obtain at least one game record group, wherein the game character combinations in any two game record groups are different, and the same game record group includes one or more game records, and the game character combinations corresponding to any two game records in a single game record group including multiple game records are the same; For each game record group in the at least one game record group, analyzing the game data of at least one game round of each game record in the currently processed game record group to determine a reference game strategy adopted by the target user, and obtaining one or more reference game strategies corresponding to one or more game records of each game record group; The target game strategy of the target user under different game character combinations is determined according to the one or more reference game strategies of each game record group.

3. The method according to claim 2, characterized in that The analyzing the game data of at least one game round in each of the plurality of game records to obtain a reference game strategy adopted by the target user in each game record includes: If at least one game round of the currently processed game record is a single game round, determining a reference game strategy adopted by the target user in the currently processed game record according to the user game data in the single game round; If at least one of the game rounds of the currently processed game record is multiple game rounds, perform the following operations: Analyzing the correlation of user-side operation strategies before adjacent game rounds in the multiple game rounds, converging game rounds with consistent correlation into a single reference game round, and obtaining an updated game round sequence; Determining the interaction complexity of the target game plot node according to the updated game round sequence; If the interaction complexity is greater than or equal to a preset complexity, manually summarizing the updated game round sequence to determine a reference game strategy adopted by the target user in the currently processed game record; If the interaction complexity is lower than the preset complexity, a reference game strategy adopted by the target user in the currently processed game record is determined according to the user game data in the updated game round sequence.

4. The method according to claim 3, characterized in that Determining the interaction complexity of the target game plot node according to the updated game round sequence includes: Determine the average number of user operations per round in the game round sequence according to the number of user operations in the game data of each game round in the updated game round sequence; The interaction complexity of the target game plot node is determined according to the number of rounds included in the game round sequence and the average number of user operations in a single round.

5. The method according to any one of claims 2 to 4, characterized in that: Determining the target game strategy according to the obtained multiple reference game strategies corresponding to the multiple game records includes: The reference game strategy with the largest number of repetitions among the multiple reference game strategies is used as the target game strategy; or The reference game strategy whose game event is closest to the current system time among the multiple reference game strategies is used as the target game strategy.

6. The method according to any one of claims 2 to 4, characterized in that: If the game character required by the at least one game plot node is single, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes, and the guiding words include an introduction to the single game character; If the at least one game plot node requires multiple game characters, the human-computer dialogue script includes guiding words and human-computer dialogue plot nodes, and the guiding words include introductions to the multiple game characters.

7. A processing device for recalling old players of a turn-based game by phone, characterized in that: A server applied to a game marketing system, the game marketing system comprising the server and a terminal device for logging into a character account of a target user, the device comprising: an acquisition unit, configured to acquire at least one game record set corresponding to at least one game plot node of the turn-based game by the target user, wherein a single game record set includes at least one game record of at least one game event of the user at the corresponding game plot node, and a single game record includes game data of at least one game round generated by the user in a single game event at the corresponding game plot node, and a time interval between the last time the target user logged into the turn-based game and the current system time is greater than a preset time length; A first determining unit is configured to determine a target game strategy of the target user at a target game plot node according to the at least one game record set, wherein the target game plot node is a game plot node in the at least one game plot node; when the at least one game record set includes multiple game record sets, determining the target game strategy of the target user at the target game plot node according to the at least one game record set comprises: sorting the multiple game record sets in descending order of the number of game records included to obtain a game record set sequence; taking the game plot node corresponding to the first game record set in the game record set sequence as the target game plot node; and determining the target game strategy of the target user according to the game record set of the target game plot node; A second determining unit is used to determine a human-computer dialogue script for executing a telephone recall service for the target user according to the target game plot node and the target game strategy; A conversation unit is used to make a voice conversation with the terminal device according to the human-computer conversation script.

8. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and computer-executable instructions stored in the memory and executable on the processor. When the computer-executable instructions are executed, the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images