Task generation method and device, storage medium and electronic equipment

Abstract

The invention discloses a task generation method and device, a storage medium and electronic equipment, and a server can analyze the preference of a target user and the state of a virtual role of the target user according to the preference characteristics of the target user and the state data of the virtual role operated by the target user, so that the target user can generate a task from each preset basic task unit. According to the method, a suitable target task unit is selected for a target user to form a customized to-be-executed task, and the customized to-be-executed task is recommended to the target user, so that the target user performs task execution according to the recommended to-be-executed task and obtains an award, and a virtual role operated by the user can grow according to a customized growth path.

Description

Technical Field

[0001] The present invention relates to the field of reinforcement learning technology, and in particular to a task generation method, device, storage medium and electronic device. Background Art

[0002] At present, the character growth system has been widely used in various game platforms because it can enhance the depth of the game and bring a good sense of participation to players.

[0003] Typically, a character growth system consists of a fixed skill tree subsystem, an experience value subsystem, and an attribute point allocation subsystem. While these subsystems provide players with a basic growth experience, they also have significant limitations. That is, the player's growth path is fixed, and different players often have different needs for growth paths, resulting in the fixed growth path recommended for players not being able to meet their needs.

[0004] Therefore, how to improve the accuracy of the growth path recommended for players is an urgent problem to be solved. Summary of the invention

[0005] This specification provides a task generation method, device, storage medium and electronic device to partially solve the above problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a task generation method, including:

[0008] Receive a task generation request;

[0009] Determining, according to the task generation request, state data of a virtual character operated by a target user in a terminal device and preference characteristics of the target user, wherein the state data is used to reflect the attribute state of the virtual character and the execution state of historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks;

[0010] According to the status data and the preference characteristics, each target task unit is determined from the preset basic task units, and based on each target task unit, a to-be-executed task is generated, and the to-be-executed task is displayed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different basic task unit combinations result in different task objectives and / or task rewards.

[0011] Optionally, the step of determining the preference characteristics of the target user and the status data of the virtual character operated by the target user in the client according to the task generation request specifically includes:

[0012] Acquire, according to the task generation request, a historical operation record of the target user, wherein the historical operation record includes various historical operations performed by the target user in the terminal device;

[0013] According to the historical operation records, the preference category of the target user is determined, and according to the preference category, the preference characteristics of the target user are determined.

[0014] Optionally, the step of determining the preference category of the target user according to the historical operation record specifically includes:

[0015] Determining user operation characteristics of the target user according to the historical operation records;

[0016] According to the similarity between the user operation feature and each preset cluster center feature, a cluster center feature matching the target user is determined from each cluster center feature, and the preference category corresponding to the cluster center feature matching the target user is used as the preference category of the target user.

[0017] Optionally, the step of determining each target task unit from each preset basic task unit according to the state data and the preference feature specifically includes:

[0018] The state data and the preference characteristics are input into a preset task generation model, so that the task generation model determines each target task unit from each preset basic task unit according to the state data and the preference characteristics.

[0019] Optionally, the step of inputting the state data and the preference characteristics into a preset task generation model so that the task generation model determines each target task unit from each preset basic task unit according to the state data and the preference characteristics specifically includes:

[0020] The state data and the preference characteristics are input into a preset task generation model, so that the task generation model determines the current state value of the virtual character according to the state data and the preference characteristics, determines each candidate task unit set from each preset basic task unit according to the current state value and the probability value corresponding to each preset basic task unit, determines the reward value corresponding to the candidate task composed of each basic task unit in the candidate task unit set for each candidate task unit set, and determines a target task unit set from each candidate task unit set according to the reward value, takes the candidate task composed of each target task unit included in the target task unit set as the task executed by the virtual character, and re-determines the state value of the virtual character, and updates the probability value corresponding to each basic task unit according to the reward value, re-determines each candidate task unit set according to the updated state value and the updated probability value corresponding to each basic task unit, until a preset termination condition is reached, determines the target probability value corresponding to each basic task unit, and re-determines each target task unit from each preset basic task unit according to the target probability value corresponding to each basic task unit.

[0021] Optionally, the step of determining, for each candidate task unit set, a reward value corresponding to a candidate task composed of each basic task unit in the candidate task unit set specifically includes:

[0022] For each candidate task unit set, the candidate task composed of the basic task units in the candidate task unit set is input into a preset prediction model to determine the matching degree between the target user and the candidate task through the prediction model, and based on the matching degree, determine the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set, wherein the prediction model is trained based on the historical operation records of the target user and the historical operation records of a reference user, and the preference characteristics of the reference user are similar to the preference characteristics of the target user.

[0023] Optionally, the step of determining, for each candidate task unit set, a reward value corresponding to a candidate task composed of each basic task unit in the candidate task unit set specifically includes:

[0024] For each candidate task unit set, determining the target user's feedback data on the candidate task composed of the basic task units in the candidate task unit set, wherein the feedback data is used to reflect the target user's acceptance of the candidate task composed of the basic task units in the candidate task unit set;

[0025] According to the feedback data, a reward value corresponding to a candidate task composed of the basic task units in the candidate task unit set is determined.

[0026] This specification provides a task generation device, including:

[0027] A receiving module, used for receiving a task generation request;

[0028] A determination module, configured to determine, according to the task generation request, the state data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user, wherein the state data is used to reflect the attribute state of the virtual character and the execution state of the historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks;

[0029] A generation module is used to determine each target task unit from the preset basic task units according to the status data and the preference characteristics, and generate a task to be executed according to each target task unit, and present the task to be executed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different basic task unit combinations obtain different task objectives and / or task rewards.

[0030] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0031] In the task generation method provided in the present specification, a task generation request is received, and based on the received task generation request, the status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user are determined, wherein the status data is used to reflect the attribute status of the virtual character and the execution status of the historical tasks, and the preference characteristics are used to reflect the target user's demand tendency for different tasks, and then based on the status data and the preference characteristics, each target task unit is determined from the preset basic task units, and based on each target task unit, a task to be executed is generated, and the task to be executed is displayed to the target user, wherein different basic task units are used to represent different task goals or task rewards, and different basic task unit combinations result in different task goals and / or task rewards.

[0032] It can be seen from the above method that the server can analyze the target user's preferences and the status of the target user's virtual character based on the target user's preference characteristics and the status data of the virtual character operated by the target user, so that the server can select suitable target task units for the target user from the preset basic task units to form customized tasks to be performed and recommend them to the target user, thereby enabling the target user to perform tasks according to the recommended tasks to be performed and obtain rewards, so that the virtual character operated by the user can grow according to the customized growth path. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0034] Figure 1 A flowchart of a task generation method provided in this specification;

[0035] Figure 2 A flowchart of generating tasks to be performed provided in this specification;

[0036] Figure 3 A schematic diagram of a task generation device provided in this specification;

[0037] Figure 4 A method corresponding to the Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0039] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0040] At present, the character growth system has been widely used by various game platforms because it can enhance the depth of the game and bring a good sense of participation to players. Among them, the character growth system consists of a fixed skill tree subsystem, experience value subsystem and attribute point allocation subsystem. Players can obtain task rewards such as skills, experience points, attribute points, etc. by executing various growth tasks recommended to players by the business platform, and then use the obtained task rewards to make the virtual character operated by the player grow according to a fixed growth path.

[0041] However, different players have different demands for the growth paths of virtual characters, so providing players with fixed tasks so that the characters operated by players grow along a fixed growth path often cannot meet the needs of players. Therefore, it is particularly important to accurately recommend growth tasks that meet the players' demands for the growth paths of virtual characters.

[0042] Figure 1 A flowchart of a task generation method provided in this specification includes the following steps:

[0043] S101: receiving a task generation request.

[0044] In this specification, when a designated application running on a terminal device used by a target user determines that the virtual character operated by the target user meets preset generation conditions, a task generation request can be sent to a business platform. The business platform can generate a to-be-executed task for the target user based on the received task generation request, and display the generated to-be-executed task to the target user through the designated application, so that the target user can control the virtual character in the designated application to execute the generated to-be-executed task.

[0045] There may be multiple types of the above-mentioned designated application programs, such as client applications, World Wide Web (Web) applications, and the like.

[0046] The above generation conditions can be set according to actual needs. For example, when it is determined that the virtual character operated by the target user logs in for the first time that day, it can be regarded as satisfying the above generation conditions.

[0047] For another example: when it is determined that the status data of the virtual character operated by the target user reaches a specified threshold, it can be regarded as meeting the above-mentioned generation conditions. The status data here can be used to reflect the attribute status of the virtual character and the execution status of historical tasks, such as: location coordinates, level, experience value, attribute value, skill cooling time, equipment or props carried, historical task execution records, etc.

[0048] In this specification, the execution subject used to implement the task generation method can refer to a designated device such as a server set up on a business platform, or it can refer to a terminal device such as a desktop computer, a laptop computer, etc. For the sake of ease of description, the task generation method provided in this specification is explained below using the server as the execution subject as an example.

[0049] S102: Determine, based on the task generation request, the status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user, wherein the status data is used to reflect the attribute status of the virtual character and the execution status of the historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks.

[0050] In this specification, the server can determine the status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user according to the task generation request, and then can generate customized tasks to be executed for the target user based on the determined status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user.

[0051] Among them, the above-mentioned preference characteristics are used to reflect the target user's demand tendencies for different tasks. The above-mentioned preference characteristics can be obtained by the server after analyzing the historical operation records of the target user. The historical operation records of the target user here can be obtained by the server from the log data recorded by the log system contained in the specified application, or obtained by the server from the specified application through the external data interface provided by the specified application.

[0052] In the above content, the historical operation record of the target user may include various historical operations performed by the target user in the terminal device. The historical operations here may refer to the specific actions performed by the target user to control the virtual character through interactive behaviors such as pressing buttons, touching the screen, and clicking the mouse (for example, controlling the direction and speed of the virtual character's movement, controlling the virtual character to use weapons or skills, controlling the virtual character to communicate with other characters in a specified application or selecting dialogue options, etc.). Of course, the historical operations here may also refer to the decisions made by the target user during the game through the above-mentioned interactive behaviors (for example, the target user chooses to accept or refuse a task, the target user controls the virtual character to choose a virtual scene to go to, the target user chooses to allocate the acquired attribute points to those attributes, the target user chooses to join a team, etc.).

[0053] In the above content, the method in which the server analyzes the historical operation records of the target user to determine the above preference characteristics can generate a request for the server according to the task received, obtain the historical operation records of the target user, and thus determine the target user's preference category based on the target user's historical operation records, and further determine the target user's preference characteristics based on the determined target user's preference category.

[0054] Specifically, the server can input the historical operation records of the target user into a preset classification model to determine the target user's preference category based on the target user's historical operation records through the preset classification model, and then determine the preference features corresponding to the target user's preference category based on the preference features corresponding to each preset preference category. As the preference features of the target user, the preference features corresponding to each of the above-mentioned preference categories can be determined in advance based on the historical operation records of different users of the specified application.

[0055] Of course, the server can also perform feature extraction on the historical operation records of the target user to determine the user operation features of the target user, and then determine the cluster center features that match the target user from the cluster center features based on the similarity between the user operation features of the target user and the preset cluster center features, and use the preference category corresponding to the cluster center features that match the target user as the preference category of the target user, and then use the cluster center features corresponding to the preference category of the target user as the preference feature of the target user, wherein there is a one-to-one correspondence between each cluster center feature and each preference category.

[0056] The aforementioned cluster center features and the aforementioned preference categories may be determined in advance by performing cluster analysis on historical operation records of users of a designated application.

[0057] Specifically, the server can obtain historical operation records of each user of the specified application as sample operation records, and for each preference category actually corresponding to each sample operation record, take maximizing the similarity between the sample operation features of the determined sample operation records belonging to the preference category compared to the similarity between the sample operation features of the sample operation records belonging to the preference category and the sample operation features of the sample operation records belonging to other preference categories as the adjustment target, and adjust the sample operation features of each sample operation record until the preset adjustment conditions are met. At this time, for each preference category, the cluster center feature corresponding to the preference category can be determined based on the adjusted sample operation features of the sample operation records belonging to the preference category.

[0058] In addition, the server can also determine the target user's preference category based on preset classification rules, the status data of the virtual character operated by the target user in the terminal device and the target user's historical operation records, and determine the target user's preference characteristics based on the target user's preference category.

[0059] Among them, the above classification rules can be set according to actual needs. For example: if it is determined based on the historical operation records of the target user that among the historical tasks performed by the target user, the number of tasks whose task objectives are to collect props accounts for more than a preset proportion threshold, then it can be determined that the target user's preference category is the collection task category.

[0060] For another example: if it is determined based on the status data of the virtual character operated by the target user in the terminal device that among the skills equipped by the virtual character operated by the target user, the number of skills for fighting with other virtual characters exceeds a preset quantity threshold, then it can be determined that the target user's preference category is the category of fighting with other virtual players.

[0061] S103: According to the state data and the preference characteristics, target task units are determined from the preset basic task units, and tasks to be performed are generated according to the target task units, and the tasks to be performed are displayed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different combinations of basic task units result in different task objectives and / or task rewards.

[0062] In this specification, the server can input the status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user into a preset task generation model, so that the task generation model determines each target task unit from the preset basic task units based on the above status data and the above preference characteristics.

[0063] Specifically, the above-mentioned task generation model can be a reinforcement learning model. In this case, the server can input the determined state data and the preference characteristics of the target user into the preset task generation model, so that the task generation model determines the current state value of the virtual character operated by the target user according to the determined state data and the preference characteristics of the target user, determines each candidate task unit set from the preset basic task units according to the determined current state value and the probability value corresponding to each preset basic task unit, determines for each candidate task unit set the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set, and determines the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set according to the probability value corresponding to each basic task unit in the candidate task unit set. The reward value corresponding to the candidate tasks composed is determined, a target task unit set is determined from each candidate task unit set, the candidate tasks composed of each target task unit contained in the target task unit set are taken as the tasks executed by the virtual character, and the state value of the virtual character is re-determined, and the probability value corresponding to each basic task unit is updated according to the reward value, and each candidate task unit set is re-determined according to the updated state value and the updated probability value corresponding to each basic task unit, until the preset termination condition is reached, the target probability value corresponding to each basic task unit is determined, and each target task unit is re-determined from the preset basic task units according to the target probability value corresponding to each basic task unit.

[0064] The above different basic task units are used to represent different task objectives or task rewards, and different combinations of basic task units result in different task objectives and / or task rewards. For example, the task objective represented by the above basic task unit may be that the target user operates the virtual character to defeat a specified number of other virtual characters, and the above task reward may be one of a specified number of attribute points, experience points, or gold coins.

[0065] For another example, the task goal represented by the above-mentioned basic task unit may be that the target user operates the virtual character to collect a specified number of props and items, and the above-mentioned task reward may be equipment set in the client.

[0066] The above-mentioned task generation model determines the current state value of the virtual character operated by the target user based on the determined state data and the target user's preference characteristics. The method may be to perform feature encoding on the determined state data to obtain the state characteristics of the virtual character operated by the target user, and then fuse the state characteristics of the virtual character operated by the target user with the target user's preference characteristics to obtain the current state value of the virtual character operated by the target user (here, the feature representation obtained by fusing the state characteristics of the virtual character operated by the target user with the target user's preference characteristics may be used as the current state value of the virtual character operated by the target user, or the feature representation obtained by fusing the state characteristics of the virtual character operated by the target user with the target user's preference characteristics may be used as the current state value of the virtual character operated by the target user).

[0067] The above-mentioned server can have multiple methods for determining the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set. For example: the server displays the candidate task composed of the basic task units in the candidate task unit set to the target user, and obtains the target user's feedback data on the candidate task composed of the basic task units in the candidate task unit set, and then can determine the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set according to the target user's feedback data. The feedback data here is used to reflect the target user's acceptance of the candidate task composed of the basic task units, such as: the target user's operating instructions to accept the task, the target user's operating instructions to refuse to accept the task, the target user's operating instructions to abandon the task (i.e., abandon after accepting the task), the target user's task execution time for executing the candidate task, etc.

[0068] As another example: for each candidate task unit set, the server inputs the candidate task composed of the basic task units in the candidate task unit set into a preset prediction model to determine the matching degree between the target user and the candidate task through the prediction model, and determines the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set based on the determined matching degree between the target user and the candidate task.

[0069] Among them, the above-mentioned prediction model is trained based on the historical operation records of the target user and the historical operation records of the reference user. The preference characteristics of the reference user here are similar to the preference characteristics of the target user (that is, the similarity between the preference characteristics of the reference user and the preference characteristics of the target user is greater than the preset similarity threshold).

[0070] The termination condition in the above content can be set according to actual needs. For example, when the number of iterations reaches a preset round number threshold, it can be regarded as meeting the preset termination condition.

[0071] For another example, when the difference between the probability value after the update and the probability value before the update corresponding to each basic task unit is less than a preset difference threshold, it can be regarded as meeting the preset termination condition.

[0072] In addition, the developers of the business platform may also combine the basic task units in advance to obtain basic tasks, wherein different basic tasks have different task objectives and / or task rewards.

[0073] Furthermore, the server can also input the determined status data and the preference characteristics of the target user into a preset task generation model, so that the task generation model determines the current status value of the virtual character operated by the target user according to the determined status data and the preference characteristics of the target user, determines the candidate tasks from the preset basic tasks according to the determined current status value and the preset probability value corresponding to each basic task, and determines the reward value corresponding to the candidate tasks, takes the above-mentioned candidate tasks as the tasks performed by the virtual character, and re-determines the status value of the virtual character, and updates the probability value corresponding to each basic task unit according to the reward value corresponding to the above-mentioned candidate tasks, and re-determines the candidate tasks according to the updated status value and the updated probability value corresponding to each basic task unit, until the preset termination condition is reached, at which time, the target probability value corresponding to each basic task is determined, and the target task is re-determined from the preset basic tasks according to the target probability value corresponding to each basic task.

[0074] In addition, the server determines each target task unit from the preset basic task units according to the status data and preference characteristics of the target user, and generates the task to be executed according to each target task unit. The method can also be to determine each initial task unit set from the preset basic task units according to the status data and preference characteristics of the target user, and determine each target task unit from the preset basic task units through multiple rounds of iterations.

[0075] Among them, for each round of iteration, the server can determine each candidate task unit set in the round of iteration, and for each candidate task unit set, determine the matching degree between the candidate task composed of each candidate task unit in the candidate task unit set and the target user, as the matching degree corresponding to the candidate task unit set, and then according to the matching degree corresponding to each candidate task unit set, at least part of the candidate task unit sets can be screened out from each candidate task unit set, and the remaining candidate task unit sets can be adjusted to obtain each candidate task unit set in the next round of iteration until the preset termination condition is reached. At this time, the server can determine the corresponding candidate task unit set with the highest matching degree from each candidate task unit set in the round of iteration as the target task unit set, and use each basic task unit in the target task unit set as each target task unit.

[0076] The above adjustment operation includes at least one of a crossover operation and a mutation operation.

[0077] The above crossover operation may be to randomly select two candidate task unit sets from each candidate task unit set, and exchange at least part of the basic task units in the two candidate task unit sets to obtain a new candidate task unit set.

[0078] The above-mentioned mutation operation can be to randomly select at least part of the basic task units from each basic task unit as the basic task units to be replaced, and replace at least part of the basic task units in a basic task unit set randomly selected from each basic task unit set with the basic task units to be replaced to obtain a new candidate task unit set.

[0079] The above is a detailed description of the task generation method provided in this specification. The following is a complete description of the process of the server customizing and generating tasks to be executed for the target user. Figure 2 shown.

[0080] Figure 2 This is a flowchart of generating tasks to be executed provided in this manual.

[0081] Combination Figure 2 It can be seen that the server can collect the historical operation records of the target user and the status data of the virtual character operated by the target user in the terminal device in response to the received task generation request, and then determine the preference characteristics of the target user based on the collected historical operation records of the target user, and then generate tasks to be performed for the target user and recommend them to the target user based on the status data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user, so that the target user controls the virtual character to perform the tasks to be performed and obtains corresponding rewards, thereby enabling the virtual character operated by the target user to grow according to a personalized growth path.

[0082] From the above content, it can be seen that the server can analyze the target user's preferences and the status of the target user's virtual character based on the target user's preference characteristics and the status data of the virtual character operated by the target user, so that it can select suitable target task units for the target user from the preset basic task units to form customized tasks to be performed and recommend them to the target user, thereby enabling the target user to perform tasks according to the recommended tasks to be performed and obtain rewards, so that the virtual character operated by the user can grow according to the customized growth path.

[0083] The above are one or more implementation task generation methods of this specification. Based on the same idea, this specification also provides a corresponding task generation device, such as Figure 3 shown.

[0084] Figure 3 A schematic diagram of a task generation device provided in this specification includes:

[0085] Receiving module 301, used for receiving a task generation request;

[0086] A determination module 302 is used to determine, according to the task generation request, the state data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user, wherein the state data is used to reflect the attribute state of the virtual character and the execution state of the historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks;

[0087] The generation module 303 is used to determine each target task unit from the preset basic task units according to the status data and the preference characteristics, and generate a task to be executed according to each target task unit, and present the task to be executed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different basic task unit combinations obtain different task objectives and / or task rewards.

[0088] Optionally, the determination module 302 is specifically used to obtain the historical operation record of the target user according to the task generation request, and the historical operation record includes various historical operations performed by the target user in the terminal device; determine the preference category of the target user according to the historical operation record, and determine the preference characteristics of the target user according to the preference category.

[0089] Optionally, the determination module 302 is specifically used to determine the user operation characteristics of the target user based on the historical operation records; determine the cluster center characteristics that match the target user from each cluster center characteristic based on the similarity between the user operation characteristics and each preset cluster center characteristic, and use the preference category corresponding to the cluster center characteristics that match the target user as the preference category of the target user.

[0090] Optionally, the generation module 303 is specifically used to input the state data and the preference characteristics into a preset task generation model, so that the task generation model determines each target task unit from each preset basic task unit according to the state data and the preference characteristics.

[0091] Optionally, the generation module 303 is specifically used to input the state data and the preference characteristics into a preset task generation model, so that the task generation model determines the current state value of the virtual character according to the state data and the preference characteristics, determines each candidate task unit set from each preset basic task unit according to the current state value and the probability value corresponding to each preset basic task unit, determines for each candidate task unit set a reward value corresponding to the candidate task composed of each basic task unit in the candidate task unit set, and determines the target task from each candidate task unit set according to the reward value. Unit set, taking the candidate task composed of the target task units contained in the target task unit set as the task executed by the virtual character, and re-determining the state value of the virtual character, and updating the probability value corresponding to each basic task unit according to the reward value, and re-determining each candidate task unit set according to the updated state value and the updated probability value corresponding to each basic task unit, until the preset termination condition is reached, determining the target probability value corresponding to each basic task unit, and re-determining each target task unit from the preset basic task units according to the target probability value corresponding to each basic task unit.

[0092] Optionally, the generation module 303 is specifically used to, for each candidate task unit set, input the candidate task composed of the basic task units in the candidate task unit set into a preset prediction model, so as to determine the matching degree between the target user and the candidate task through the prediction model, and determine the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set based on the matching degree, wherein the prediction model is trained based on the historical operation records of the target user and the historical operation records of the reference user, and the preference characteristics of the reference user are similar to the preference characteristics of the target user.

[0093] Optionally, the generation module 303 is specifically used to determine, for each candidate task unit set, the feedback data of the target user regarding the candidate task composed of the basic task units in the candidate task unit set, wherein the feedback data is used to reflect the target user's acceptance level of the candidate task composed of the basic task units in the candidate task unit set; and determine the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set based on the feedback data.

[0094] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provides a task generation method.

[0095] This manual also provides Figure 4 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 4 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0096] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0097] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0098] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0099] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0100] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0101] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0108] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0110] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0111] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A task generation method, characterized in that: include: Receive a task generation request; Determining, according to the task generation request, state data of a virtual character operated by a target user in a terminal device and preference characteristics of the target user, wherein the state data is used to reflect the attribute state of the virtual character and the execution state of historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks; According to the status data and the preference characteristics, each target task unit is determined from the preset basic task units, and based on each target task unit, a to-be-executed task is generated, and the to-be-executed task is displayed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different basic task unit combinations result in different task objectives and / or task rewards.

2. The method according to claim 1, characterized in that The step of determining the preference characteristics of the target user and the status data of the virtual character operated by the target user in the client according to the task generation request specifically includes: Acquire, according to the task generation request, a historical operation record of the target user, wherein the historical operation record includes various historical operations performed by the target user in the terminal device; The preference category of the target user is determined according to the historical operation record, and the preference feature of the target user is determined according to the preference category.

3. The method according to claim 2, characterized in that The step of determining the preference category of the target user according to the historical operation record specifically includes: Determining user operation characteristics of the target user according to the historical operation records; According to the similarity between the user operation feature and each preset cluster center feature, a cluster center feature matching the target user is determined from each cluster center feature, and the preference category corresponding to the cluster center feature matching the target user is used as the preference category of the target user.

4. The method according to claim 1, characterized in that The step of determining each target task unit from each preset basic task unit according to the state data and the preference characteristics specifically includes: The state data and the preference characteristics are input into a preset task generation model, so that the task generation model determines each target task unit from each preset basic task unit according to the state data and the preference characteristics.

5. The method according to claim 4, characterized in that The step of inputting the state data and the preference characteristics into a preset task generation model so that the task generation model determines each target task unit from each preset basic task unit according to the state data and the preference characteristics specifically includes: The state data and the preference characteristics are input into a preset task generation model, so that the task generation model determines the current state value of the virtual character according to the state data and the preference characteristics, determines each candidate task unit set from each preset basic task unit according to the current state value and the probability value corresponding to each preset basic task unit, determines the reward value corresponding to the candidate task composed of each basic task unit in the candidate task unit set for each candidate task unit set, and determines a target task unit set from each candidate task unit set according to the reward value, takes the candidate task composed of each target task unit included in the target task unit set as the task executed by the virtual character, and re-determines the state value of the virtual character, and updates the probability value corresponding to each basic task unit according to the reward value, re-determines each candidate task unit set according to the updated state value and the updated probability value corresponding to each basic task unit, until a preset termination condition is reached, determines the target probability value corresponding to each basic task unit, and re-determines each target task unit from each preset basic task unit according to the target probability value corresponding to each basic task unit.

6. The method according to claim 5, characterized in that The step of determining, for each candidate task unit set, a reward value corresponding to a candidate task composed of each basic task unit in the candidate task unit set specifically includes: For each candidate task unit set, the candidate task composed of the basic task units in the candidate task unit set is input into a preset prediction model to determine the matching degree between the target user and the candidate task through the prediction model, and based on the matching degree, determine the reward value corresponding to the candidate task composed of the basic task units in the candidate task unit set, wherein the prediction model is trained based on the historical operation records of the target user and the historical operation records of a reference user, and the preference characteristics of the reference user are similar to the preference characteristics of the target user.

7. The method according to claim 5, characterized in that The step of determining, for each candidate task unit set, a reward value corresponding to a candidate task composed of each basic task unit in the candidate task unit set specifically includes: For each candidate task unit set, determining the target user's feedback data on the candidate task composed of the basic task units in the candidate task unit set, wherein the feedback data is used to reflect the target user's acceptance of the candidate task composed of the basic task units in the candidate task unit set; According to the feedback data, a reward value corresponding to a candidate task composed of the basic task units in the candidate task unit set is determined.

8. A task generation device, characterized in that: include: A receiving module, used for receiving a task generation request; A determination module, configured to determine, according to the task generation request, the state data of the virtual character operated by the target user in the terminal device and the preference characteristics of the target user, wherein the state data is used to reflect the attribute state of the virtual character and the execution state of the historical tasks, and the preference characteristics are used to reflect the demand tendency of the target user for different tasks; A generation module is used to determine each target task unit from the preset basic task units according to the status data and the preference characteristics, and generate a task to be executed according to each target task unit, and present the task to be executed to the target user, wherein different basic task units are used to represent different task objectives or task rewards, and different basic task unit combinations result in different task objectives and / or task rewards.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

Images