Multi-agent processing method and device, storage medium, and program product

Abstract

The present disclosure relates to the technical field of computers, and in particular to a multi-agent processing method and device, a storage medium, and a program product. The multi-agent processing method comprises: determining a plurality of agent groups and agents in each agent group on the basis of information related to at least one content work, wherein the at least one content work comprises a plurality of characters, each character corresponds to one agent, and each agent group corresponds to a category of characters in the at least one content work; and displaying at least one agent group among the plurality of agent groups to a user, so that the user interacts with agents in the at least one agent group. In the present disclosure, the user can be assisted in quickly locating agents the user is interested in, thereby improving the user experience.

Description

Processing methods and devices for multi-agent applications, storage media, and program products Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a processing method and apparatus, storage medium, and program product for multi-agent systems. Background Technology

[0002] With the development of artificial intelligence technology, the application of intelligent agents has permeated all aspects of our lives, such as intelligent question answering and intelligent voice assistants.

[0003] In related technologies, users select a single intelligent agent of interest from a large number of intelligent agents and interact with that single intelligent agent individually.

[0004] Summary of the Invention

[0005] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] According to a first aspect of some embodiments of this disclosure, a processing method for multiple agents is provided, comprising:

[0007] Based on information related to at least one content work, multiple groups of intelligent agents and intelligent agents in each group of intelligent agents are determined, wherein the at least one content work includes multiple roles, each role corresponds to an intelligent agent, and each group of intelligent agents corresponds to a type of role in the at least one content work;

[0008] At least one of the multiple agent groups is presented to the user so that the user can interact with the agents in the at least one agent group.

[0009] According to a second aspect of some embodiments of the present disclosure, a processing apparatus for multiple agents is provided, comprising:

[0010] The determination module is configured to determine multiple groups of intelligent agents and intelligent agents in each group of intelligent agents based on information related to at least one content work, wherein the at least one content work includes multiple roles, each role corresponds to an intelligent agent, and each group of intelligent agents corresponds to a type of role in the at least one content work;

[0011] The display module is configured to display at least one of the plurality of agent groups to a user, so that the user can interact with the agents in the at least one agent group.

[0012] According to a third aspect of some embodiments of the present disclosure, a processing apparatus for multiple agents is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute a processing method for multiple agents according to any embodiment of the present disclosure based on instructions stored in the memory.

[0013] According to a fourth aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs a multi-agent processing method according to any embodiment of the present disclosure.

[0014] According to a fifth aspect of some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the processing method for multiple agents of any of the embodiments.

[0015] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0017] Figure 1 is a flowchart illustrating a multi-agent processing method according to some embodiments of the present disclosure;

[0018] Figure 2A is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0019] Figure 2B is a flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0020] Figure 2C is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0021] Figure 2D is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0022] Figure 3A is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0023] Figure 3B is a flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0024] Figure 3C is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0025] Figure 4A is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure;

[0026] Figure 4B is a flowchart illustrating the process of determining the interaction content of each agent in response to user content according to some embodiments of the present disclosure.

[0027] Figure 4C is a flowchart illustrating the process of determining the interaction content of each agent in response to user content according to other embodiments of the present disclosure.

[0028] Figure 4D is a schematic flowchart illustrating the process of determining the interaction content of each agent according to some embodiments of the present disclosure;

[0029] Figure 5A is a schematic diagram illustrating a user interface for displaying an intelligent agent group according to some embodiments of the present disclosure;

[0030] Figure 5B is a schematic diagram illustrating a user interface for accessing an intelligent agent group according to some embodiments of the present disclosure;

[0031] Figure 6 is a block diagram illustrating a processing apparatus for multiple agents according to some embodiments of the present disclosure;

[0032] Figure 7 is a block diagram illustrating a processing apparatus for multiple agents according to some embodiments of the present disclosure;

[0033] Figure 8 shows a block diagram of an electronic device according to other embodiments of the present disclosure.

[0034] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0035] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0036] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0037] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0038] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0039] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0040] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0041] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0042] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0043] In related technologies, with the continuous development of artificial intelligence technology, the number and types of intelligent agents are increasing, making it difficult for users to quickly select the intelligent agent they are interested in from a large number of intelligent agents.

[0044] This disclosure provides a technical solution that can help users quickly locate intelligent agents that they are interested in, thereby improving the user experience.

[0045] Figure 1 is a schematic flowchart illustrating a multi-agent processing method according to some embodiments of the present disclosure.

[0046] As shown in Figure 1, the processing method for multiple agents includes: step S10, determining multiple agent groups and agents in each agent group based on information related to at least one content work, wherein the at least one content work includes multiple roles, each role corresponds to an agent, and each agent group corresponds to a type of role in the at least one content work; and step S20, displaying at least one agent group among the multiple agent groups to the user so that the user can interact with the agents in the at least one agent group.

[0047] Any content work disclosed herein may be a reading material of various types or themes on a reading platform, including but not limited to novels, audiobooks, plays, and comics. The multiple characters mentioned refer to various characters in novels, audiobooks, plays, and comics, including but not limited to human figures and other creatures. An intelligent agent group is a group comprising intelligent agents, which may include one or more intelligent agents. This disclosure does not limit how the intelligent agent corresponding to each character is constructed. In this disclosure, an intelligent agent may belong to only one intelligent agent group or simultaneously belong to multiple intelligent agent groups.

[0048] In the above embodiments, intelligent agents corresponding to a certain type of role are grouped into an intelligent agent group and displayed to the user, so that the user can quickly locate intelligent agents of the same category, thereby enabling the user to quickly locate the intelligent agent that the user is interested in and improving the user experience.

[0049] The processing methods for multiple agents in other embodiments of this disclosure will now be described in detail with reference to Figures 2A to 5B.

[0050] Figure 2A is a flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 2A and Figure 1 is that steps S11 to S13 in Figure 2A are an implementation of step S10 in Figure 1. The following description will only focus on the differences between Figure 2A and Figure 1; the similarities will not be repeated.

[0051] As shown in Figure 2A, in step S11, multiple role types and the association between the multiple roles are determined based on at least one of the tag information of the at least one content work, user-generated content related to the at least one content work, and description information about the multiple roles in the at least one content work.

[0052] In step S12, multiple intelligent agent groups are determined according to the various role types, wherein each intelligent agent group corresponds to a role type.

[0053] In step S13, from the multiple agents corresponding to the multiple roles, the agent corresponding to the role type associated with each agent group is determined as the agent in each agent group.

[0054] The various role types mentioned can be determined based on character attributes such as personality and skills, the tasks performed by the character, or the content, plot, or theme related to the character. These role types include, but are not limited to, academic genius, stay-at-home dad, and palace intrigue. For example, academic genius and stay-at-home dad are determined based on character description information, while palace intrigue is determined based on tag information. For instance, the association between characters and role types can be determined through clustering. This is merely an example and does not constitute a specific limitation of this disclosure.

[0055] The association between each character and any character type includes whether each character belongs to any character type.

[0056] In this embodiment, the multiple role types and the association between the multiple roles are determined based on at least one of tag information, user-generated content (UGC), and descriptive information about the multiple roles. Then, the multiple intelligent agents are divided into intelligent agent groups based on the multiple role types and the association, which can further enrich the types of intelligent agent groups, give users more interaction options, and thus improve the user experience.

[0057] Figure 2B is a flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 2B and Figure 2A is that steps S111 to S113 in Figure 2B are an implementation of step S11 in Figure 2A. The following description will only focus on the differences between Figure 2B and Figure 2A; the similarities will not be repeated.

[0058] In some embodiments, the tag information of the at least one content work includes content tag information related to the content of the content work and character tag information related to the plurality of characters.

[0059] As shown in Figure 2B, in step S111, at least one character type related to the content of the at least one content work is determined based on the content tag information. In step S112, at least one character type related to the plurality of characters is determined based on the character tag information. In step S113, the association between the plurality of characters and the plurality of character types is determined based on the description information related to the plurality of characters in the at least one content work.

[0060] The content tag information for each content work is used to describe the theme or main plot of each content work. The character tag information for each content work is used to describe the characteristics or traits of the characters in each content work. The descriptive information related to the characters in each content work includes the character's task information, character attribute information, etc.

[0061] In this embodiment, the role type is determined not only based on content tag information but also based on role tag information, further enriching the role types and thus the types of intelligent agent groups. This allows users to select intelligent agent groups that interest them not only based on the role itself but also based on the content, thereby further enhancing the user experience.

[0062] Figure 2C is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 2C and Figure 2A is that step S114 in Figure 2C is an implementation of step S11 in Figure 2A. Only the differences between Figure 2C and Figure 2A will be described below; similarities will not be repeated.

[0063] As shown in Figure 2C, in step S114, natural language processing is performed on the user-generated content related to the at least one content work to obtain the association relationship between at least one role type and the multiple roles.

[0064] In user-generated content related to the at least one content work, users typically post content related to the theme, plot, or characters of the at least one content work. By performing natural language processing on this content related to the theme, plot, or characters of the at least one content work, the association between at least one character type and the multiple characters can be directly obtained.

[0065] Users can post topics or comments in topic squares or book circles on the reading platform as user-generated content.

[0066] For example, a user-generated content post is "Looking for books about stay-at-home dads similar to Character 1". By performing natural language processing on this user-generated content, it can be determined that Character 1 belongs to the character type "stay-at-home dad".

[0067] For example, given the user-generated content "Looking for books about stay-at-home dads, including characters like 'Character 1'", other users commented, "Character 2 in book 1 is a stay-at-home dad." By performing natural language processing on the other users' comments, it can be determined that Character 2 belongs to the "stay-at-home dad" character type.

[0068] In this embodiment, by performing natural language processing on user-generated content, not only can the role type and the relationship between roles be quickly determined, thereby improving the grouping efficiency of intelligent agent groups, but role types can also be divided from the user's perspective, so that the intelligent agent group division meets user needs and further improves the user experience.

[0069] Figure 2D is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 2D and Figure 2A is that step S115 in Figure 2D is an implementation of step S11 in Figure 2A. Only the differences between Figure 2D and Figure 2A will be described below; similarities will not be repeated.

[0070] As shown in Figure 2D, in step S115, natural language processing is performed on the descriptive information about the multiple characters in the at least one content work to obtain the association relationship between at least one character type and the multiple characters.

[0071] For example, the description of character 1 in content work 1 includes "Character 1 has finally gone from being single to becoming a stay-at-home dad." By performing natural language processing on the description of character 1 in content work 1, "Character 1 has finally gone from being single to becoming a stay-at-home dad," it can be determined that character 1 belongs to the character type "stay-at-home dad."

[0072] For example, the description of character 1 in content work 1 also includes "character 1 consistently ranked at the top of their class during their student years." By performing natural language processing on the description of character 1 in content work 1, "character 1 consistently ranked at the top of their class during their student years," it can be determined that character 1 belongs to the character type "academic star."

[0073] Natural language processing includes natural language understanding, among other things.

[0074] In this embodiment, by performing natural language processing on the descriptive information about the multiple characters in the at least one content work, the relationship between character types and characters can be determined quickly and accurately, thereby improving the grouping efficiency and accuracy of intelligent agent groups and further enhancing the user experience.

[0075] In the above embodiments, there is no strict execution order among steps S111 to S113 in Figure 2B, step S114 in Figure 2C, and step S115 in Figure 2D. These steps can exist individually or coexist.

[0076] Figure 3A is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 3A and Figure 1 is that step S21 in Figure 3A is an implementation of step S20 in Figure 1. The following description will only focus on the differences between Figure 3A and Figure 1; the similarities will not be repeated.

[0077] As shown in Figure 3A, in step S21, the user is shown at least one group of intelligent agents that have a preset association with popular content related to the at least one content work.

[0078] For example, reading platforms typically contain topics that users frequently discuss and popular content, which can all be considered popular content. For instance, at least one intelligent agent group related to a user's frequently discussed topic can be displayed to the user, or at least one intelligent agent group related to popular content can be displayed to the user.

[0079] For example, popular content could be content about characters and / or content about plot, and preset associations could be that the character type corresponding to the agent group is related to content about characters and / or content about plot.

[0080] In this embodiment, displaying user-related intelligent agent groups with popular content can recommend intelligent agent groups that the user may be interested in, thereby improving the user experience.

[0081] Figure 3B is a flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 3B and Figure 1 is that step S22 in Figure 3B is an implementation of step S20 in Figure 1. The following description will only focus on the differences between Figure 3B and Figure 1; the similarities will not be repeated.

[0082] As shown in Figure 3B, in step S22, the user is shown at least one group of intelligent agents that have a preset association relationship with the roles whose user behavior data authorized by the user meets the first preset condition.

[0083] For example, if the proportion of topics and / or comments related to role 1 in user-posted topics and / or comments exceeds a certain threshold, at least one group of agents related to role 1 will be displayed to the user.

[0084] In this embodiment, guided by user behavior data, intelligent agent groups are displayed to the user. Intelligent agent groups that the user is interested in can be recommended, so that different intelligent agent groups can be recommended to different users, thereby achieving personalized recommendations and improving the overall user experience.

[0085] Figure 3C is a schematic flowchart illustrating a multi-agent processing method according to some other embodiments of the present disclosure. The difference between Figure 3C and Figure 1 is that step S23 in Figure 3C is an implementation of step S20 in Figure 1. Only the differences between Figure 3C and Figure 1 will be described below; the similarities will not be repeated.

[0086] As shown in Figure 3C, in step S23, the user is shown that at least one intelligent agent group among the plurality of intelligent agent groups has an intelligent agent quantity that satisfies the second preset condition.

[0087] For example, determine the number of agents in each agent group and show the user at least one agent group with a number of agents greater than a threshold.

[0088] For example, it is also possible to show the user the N agent groups with the most agents among all agent groups, where N is a positive integer.

[0089] In this embodiment, since the number of agents in an agent group can determine the preferences of most users to a certain extent, showing the user at least one agent group whose number of agents in the plurality of agent groups meets the second preset condition can recommend agent groups that the user is interested in, thereby improving the user experience.

[0090] There is no strict execution order among steps S21 in Figure 3A, S22 in Figure 3B, and S23 in Figure 3C. These three steps can exist individually in the processing method, or at least two of them can exist simultaneously in the processing method.

[0091] Figure 4A is a schematic flowchart illustrating a multi-agent processing method according to some embodiments of the present disclosure. Figure 4A differs from Figure 1 in that it illustrates additional steps S30 of the multi-agent processing method in some embodiments of the present disclosure. Only the differences between Figure 4A and Figure 1 will be described below; similarities will not be repeated.

[0092] As shown in Figure 4A, in step S30, in response to the user inputting user content in the target group, the interaction content of each agent in the target group in response to the user content is displayed. The target group is any one of the at least one agent group or a group created by the user. The user-created group includes the agents selected by the user from the at least one agent group.

[0093] In this embodiment, users can interact with one or more agents in an agent group or a new group constructed based on the agents in the agent group, which enriches the interaction methods between users and agents and can further enhance the user experience.

[0094] Figure 4B is a schematic flowchart illustrating the process of determining the interaction content of each agent in response to user content according to some embodiments of the present disclosure.

[0095] As shown in Figure 4B, the interaction content of each intelligent agent with respect to the user content is determined through the following steps S41 and S42.

[0096] In step S41, reference content related to the user content is determined from the content works to which the role corresponding to each intelligent agent belongs.

[0097] In step S42, interactive content for each agent is generated using a machine learning model based on reference content related to the user content.

[0098] For example, references to user-generated content could be plot elements within the content itself.

[0099] In this embodiment, for the same user content, the intelligent agent corresponding to each role determines the interactive content of each intelligent agent based on the content in the content work to which the role belongs. This can enrich the user's interactive content, increase the fun of the user's interaction with the intelligent agent, and thus improve the user experience.

[0100] Figure 4C is a flowchart illustrating the determination of interaction content for each agent in response to user content according to other embodiments of the present disclosure. The difference between Figure 4C and Figure 4B is that steps S421 and S422 in Figure 4C are an implementation of step S42 in Figure 4B. Only the differences between Figure 4C and Figure 4B will be described below; similarities will not be repeated.

[0101] As shown in Figure 4C, in step S421, the character information of the character corresponding to each intelligent agent is determined based on the content work to which the character belongs. In step S422, interactive content that conforms to the character information of the character corresponding to each intelligent agent is generated using a machine learning model based on reference content related to the user content.

[0102] Character profile information includes, but is not limited to, the character's personality and language style.

[0103] In this embodiment, incorporating character information into the interactive content allows users to experience the characters within the content during interaction with the intelligent agent, thereby further enhancing the user experience.

[0104] In some embodiments, the user-generated content includes at least one of comment content and topic content; and / or the content tagging information includes at least one of plot tagging information and topic tagging information.

[0105] Taking a reading platform that includes a topic square or a comment square as an example, topic content comes from the topic square, and comment content comes from the comment square. Here, the topic square and comment square are two functional modules within the reading platform, which can be understood as the user interface that displays topics and comments.

[0106] In some embodiments, the machine learning model disclosed herein may be a Large Language Model (LLM) or other models.

[0107] The following will use a large language model as an example, and describe in conjunction with Figure 4D the process of determining the interaction content of each agent in some embodiments of this disclosure.

[0108] Figure 4D is a schematic flowchart illustrating the process of determining the interaction content of each agent according to some embodiments of the present disclosure.

[0109] As shown in Figure 4D, agents 1 and 2 receive user content. Both agents 1 and 2 search from the knowledge base of the content works. Agents 1 and 2 send the search results to the large language model, which then outputs interactive content 1 and interactive content 2. The knowledge base of content works can include content from multiple content works. Agent 1 searches the knowledge base for content from the content works containing the role corresponding to Agent 1, and Agent 2 searches the knowledge base for content from the content works containing the role corresponding to Agent 2. Agents 1 and 2 can be agents in a group of agents, or agents selected by the user from multiple groups of agents, i.e., agents in a user-constructed group.

[0110] Figure 5A is a schematic diagram illustrating a user interface for a group of intelligent agents according to some embodiments of the present disclosure.

[0111] As shown in Figure 5A, the user interface includes two agent groups: "Dad" and "Top Student." Each agent group corresponds to a "Enter Group" control. Users can enter each agent group to chat by activating the "Enter Group" control. The "Enter Group" control can be, for example, a button; this disclosure does not limit this.

[0112] Figure 5B is a schematic diagram illustrating a user interface for accessing an intelligent agent group according to some embodiments of the present disclosure.

[0113] As shown in Figure 5B, the user interface displays the interface for entering the "Dad" agent group. In the chat interface of the "Dad" agent group, Agent 1 publishes interactive content 1 in response to the user's input. Agent 2 publishes interactive content 2 in response to the user's input.

[0114] Figures 5A and 5B are merely examples of this disclosure and do not constitute a specific limitation on the technical solution of this disclosure.

[0115] The above describes content publishing methods provided in some embodiments of this disclosure. The content publishing apparatus in some embodiments of this disclosure will now be described with reference to FIG6.

[0116] Figure 6 is a block diagram illustrating a processing apparatus for multiple agents according to some embodiments of the present disclosure.

[0117] As shown in Figure 6, the processing device 6 for multiple agents includes a determination module 61 and a display module 62.

[0118] The determination module 61 is configured to determine multiple agent groups and agents within each agent group based on information related to at least one content work, wherein the at least one content work includes multiple roles, each role corresponds to an agent, and each agent group corresponds to a type of role in the at least one content work. The display module 62 is configured to display at least one agent group from the multiple agent groups to a user, so that the user can interact with the agents in the at least one agent group.

[0119] The processing device 6 for multi-agent systems can be used to execute steps S10 to S20 of FIG1. ​​In some embodiments, the processing device 6 for multi-agent systems can also execute any of the steps shown in FIG2A to 4A.

[0120] It should be noted that the above modules are logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above modules can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the modules shown in the accompanying drawings with dashed lines indicate that these modules may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0121] The above are some embodiments of the content publishing device described in this disclosure.

[0122] Figure 7 is a block diagram illustrating a processing apparatus for multiple agents according to some embodiments of the present disclosure.

[0123] As shown in FIG7, the processing device 7 for multiple agents includes: a memory 71; and a processor 72 coupled to the memory 71, the processor 72 being configured to execute the processing method for multiple agents as described in any of the foregoing embodiments based on instructions stored in the memory 71.

[0124] Memory 71 is used to store one or more computer-readable instructions. Memory 71 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 71 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.

[0125] The processor 72 is configured to execute computer-readable instructions to implement the multi-agent processing method described in any of the foregoing embodiments. Specific implementations of each step of the multi-agent processing method can be found in the above embodiments; repeated details will not be elaborated upon here.

[0126] The processor 72 and the memory 71 can communicate with each other directly or indirectly. For example, the processor 72 and the memory 71 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 72 and the memory 71 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0127] It should be noted that the components of the electronic device 7 shown in Figure 7 are merely exemplary and not limiting. The processing device 7 for multi-agent applications may also have other components depending on the specific application requirements. The processor 72 may be combined with other components in the processing 7 for multi-agent applications to perform the desired functions.

[0128] Processing devices for multi-agent systems can be implemented in software, firmware, and / or hardware and can be integrated into electronic devices with relevant applications installed.

[0129] Figure 8 shows a block diagram of an electronic device according to other embodiments of the present disclosure.

[0130] The electronic device 8 shown in Figure 8 can be a computer system with a dedicated hardware structure, capable of performing corresponding functions when relevant applications are installed.

[0131] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0132] As shown in Figure 8, the Central Processing Unit (CPU) 81 performs various processes based on programs stored in the Read-Only Memory (ROM) 82 or programs loaded from the storage section 88 into the Random Access Memory (RAM) 83. The RAM 83 stores data required as needed when the CPU 81 performs various processes. The CPU is merely exemplary and can also be other types of processors, such as the various processors described above. The ROM 82, RAM 83, and storage section 88 can be various forms of computer-readable storage media. It should be noted that although the ROM 82, RAM 83, and storage section 88 are shown separately in Figure 8, one or more of them can be combined or located in the same or different memories or storage modules.

[0133] CPU 81, ROM 82 and RAM 83 are interconnected via bus 84. Input / output interface 85 is also connected to bus 84.

[0134] The following components are connected to the input / output interface 85: input section 86, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 87, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 88, including hard disk, magnetic tape, etc.; and communication section 89, including network interface cards such as LAN cards, modems, etc. The communication section 89 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the electronic device 8 shown in Figure 8 communicate via bus 84, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and / or any combination of wireless and wired networks.

[0135] As needed, drive 810 is also connected to input / output interface 85. Removable media 811, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 810 as needed, so that computer programs read from them can be installed into storage section 88 as needed.

[0136] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 811.

[0137] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to implement the multi-agent processing method described in any of the foregoing embodiments. The computer program product includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 89, or installed from storage section 88, or installed from ROM 82. When the computer program is executed by CPU 81, the multi-agent processing method of the embodiments of this disclosure is performed.

[0138] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0140] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. A computer program is stored on the computer-readable storage medium that, when executed by a processor, implements the processing method for multi-agent systems described in any of the foregoing embodiments.

[0141] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0142] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0143] In some embodiments, a computer program product is also provided, which, when run on a computer, causes the computer to implement the multi-agent processing method described in any of the above embodiments.

[0144] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the processing method for multiple agents according to any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0145] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0147] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0148] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for processing multiple agents, comprising: Based on information related to at least one content work, multiple groups of intelligent agents and intelligent agents in each group of intelligent agents are determined, wherein the at least one content work includes multiple roles, each role corresponds to an intelligent agent, and each group of intelligent agents corresponds to a type of role in the at least one content work; At least one of the multiple agent groups is presented to the user so that the user can interact with the agents in the at least one agent group.

2. The treatment method of claim 1, wherein, Based on information related to at least one content work, identifying multiple groups of agents and at least one agent in each group includes: Based on at least one of the tag information of the at least one content work, user-generated content related to the at least one content work, and descriptive information about the multiple roles in the at least one content work, determine multiple role types and the association between the multiple roles and the multiple role types; Based on the various role types, multiple intelligent agent groups are determined, wherein each intelligent agent group corresponds to one role type; From the multiple agents corresponding to the multiple roles, determine the agents corresponding to the roles that have an association with the role type of each agent group, and use them as agents in each agent group.

3. The processing method according to claim 2, wherein: The tag information of the at least one content work includes content tag information related to the content of the content work and character tag information related to the plurality of characters; The step of determining multiple role types and the association between the multiple roles and the multiple role types based on at least one of the tag information of the at least one content work, user-generated content related to the at least one content work, and descriptive information about the multiple roles in the at least one content work includes: Based on the content tag information, at least one character type related to the content of the at least one content work is determined; Based on the character tag information, at least one character type related to the plurality of characters is determined; Based on the descriptive information related to the multiple characters in the at least one content work, the multiple characters are determined. The relationship between color and the various role types.

4. The treatment method according to claim 2 or 3, wherein, Determining multiple role types and the association between the multiple roles and the multiple role types based on at least one of the following: tag information of the at least one content work, user-generated content related to the at least one content work, and descriptive information about the multiple roles in the at least one content work. Natural language processing is performed on user-generated content related to at least one content work to obtain the association between at least one role type and the plurality of roles; and / or Natural language processing is performed on the descriptive information about the plurality of characters in at least one content work to obtain the association relationship between at least one character type and the plurality of characters.

5. The treatment method according to any one of claims 1-3, wherein, Presenting at least one of the multiple agent groups to the user includes: Show the user at least one group of intelligent agents that have a preset association with popular content related to the at least one content work; and / or Show the user at least one group of intelligent agents that have a preset association relationship with roles whose user behavior data, authorized by the user, meets a first preset condition; and / or The user is shown that at least one intelligent agent group among the plurality of intelligent agent groups has an intelligent agent count that satisfies a second preset condition.

6. The processing method according to any one of claims 1-3, further comprising: In response to the user entering user content in a target group, the interaction content of each agent in the target group in response to the user content is displayed, wherein the target group is any one of the at least one agent group or a group created by the user, and the user-created group includes agents selected by the user from the at least one agent group.

7. The processing method according to claim 6, wherein, The interaction content of each intelligent agent in response to the user content is determined in the following way: From the content works belonging to the roles corresponding to each intelligent agent, determine those related to the user content. Reference content; Based on reference content related to the user content, interactive content for each agent is generated using a machine learning model.

8. The processing method according to claim 7, wherein, Based on reference content related to the user content, and using a machine learning model, the interactive content generated for each agent in relation to the user content includes: Based on the content works to which the character belongs to each intelligent agent, determine the character information of the character corresponding to each intelligent agent; Based on reference content related to the user content, a machine learning model is used to generate interactive content that conforms to the persona information corresponding to the role of each intelligent agent.

9. The processing method according to claim 3, wherein: The user-generated content includes at least one of comment content and topic content; and / or The content tag information includes at least one of plot tag information and topic tag information.

10. A processing device for multiple agents, comprising: The determination module is configured to determine multiple groups of intelligent agents and intelligent agents in each group of intelligent agents based on information related to at least one content work, wherein the at least one content work includes multiple roles, each role corresponds to an intelligent agent, and each group of intelligent agents corresponds to a type of role in the at least one content work; The display module is configured to display at least one of the plurality of agent groups to a user, so that the user can interact with the agents in the at least one agent group.

11. A processing device for multiple agents, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the processing method for multiple agents as described in any one of claims 1 to 9 based on instructions stored in the memory.

12. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the processing method for multiple agents as described in any one of claims 1 to 9.

13. A computer program product, when run on a computer, causes the computer to implement the processing method for multiple agents as described in any one of claims 1 to 9.

Images