Intelligent agent interaction method and device, medium, equipment and computer program product

Abstract

The invention provides an agent interaction method and device, a medium, equipment and a computer program product. The method comprises the steps that interaction information corresponding to interaction operation is acquired; an interaction agent is determined from target agents, the target agents comprise a plurality of sub-agents with the incidence relation, different sub-agents correspond to different prompt words, and the interaction agent is one of the multiple sub-agents; determining a reasoning result of the interaction information based on a prompt word corresponding to the interaction agent and a model corresponding to the interaction agent; and determining response information of the interaction information based on the reasoning result, and outputting the response information. Therefore, writing and application of the cue words corresponding to the intelligent agent can be facilitated, the complexity of the cue words is reduced, the efficiency and accuracy of reasoning by the intelligent agent are improved, and the efficiency and accuracy of responding to the interaction information are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to an agent interaction method, apparatus, medium, device, and computer program product. Background Art

[0002] An Agent is usually used to represent an intelligent agent that autonomously perceives the environment and takes actions to achieve goals. It can be implemented based on the large language model LLM (Large Language Model) to possess the abilities of planning and thinking, memory, and using tool functions.

[0003] In related technologies, when an Agent processes tasks in multiple scenarios, to ensure its handling of tasks in multiple scenarios, a large number of prompts are usually written and multiple tools are designed. However, during the adjustment and testing of the prompts and tools, it is easy to cause the Agent's performance to deteriorate and it is difficult to be tested. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a brief form, which will be described in detail in the following Detailed Description section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides an agent interaction method, the method including: Obtaining interaction information corresponding to an interaction operation; Determining an interaction agent from a target agent, where the target agent includes a plurality of sub-agents having an association relationship, and different sub-agents correspond to different prompts, and the interaction agent is one of the plurality of sub-agents; Based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent, determining an inference result for the interaction information; Based on the inference result, determining a response information for the interaction information, and outputting the response information.

[0006] In a second aspect, the present disclosure provides an agent interaction apparatus, the apparatus including: An obtaining module, configured to obtain interaction information corresponding to an interaction operation; A first determining module, configured to determine an interaction agent from a target agent, where the target agent includes a plurality of sub-agents having an association relationship, and different sub-agents correspond to different prompts, and the interaction agent is one of the plurality of sub-agents; A second determination module, configured to determine an inference result of the interaction information based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent; A processing module, configured to determine a response message for the interaction information based on the inference result and output the response message.

[0007] In a third aspect, the present disclosure provides a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processing device, the steps of the method described in the first aspect are implemented.

[0008] In a fourth aspect, the present disclosure provides an electronic device, including: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In the above technical solution, when a user interacts with a target agent, a corresponding interaction agent can be determined from multiple associated sub-agents in the target agent, so that an inference result of the interaction information can be determined based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent, and then a response message for the interaction information of the interaction operation can be determined. Thus, through the above technical solution, the target agent includes multiple associated sub-agents, and the prompts corresponding to different sub-agents are different, so that the interaction of a single agent with a long prompt and numerous tools can be converted into an interaction with multiple sub-agents with different prompts, which can facilitate the writing and application of the prompts corresponding to the agents, reduce the complexity of the prompts, improve the efficiency and accuracy of the inference of the agents, and thus improve the efficiency and accuracy of the response to the interaction information. In addition, based on the above technical solution, when adjusting the prompt or the tools of the agent, it is possible to adjust a single sub-agent, avoiding the impact of the adjustment of the prompt on the entire target agent, effectively reducing the complexity and scope of influence of the agent adjustment, and thus ensuring the accuracy and efficiency of the agent debugging, and providing effective support for ensuring accurate response messages.

[0011] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the original elements and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a flowchart of an agent interaction method provided according to an embodiment of the present disclosure.

[0013] Figure 2 is a schematic diagram of a directed graph provided based on an embodiment of the present disclosure.

[0014] Figure 3 is a block diagram of an agent interaction device provided according to an embodiment of the present disclosure.

[0015] Figure 4 shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. Detailed Description

[0016] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0017] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0018] As used herein, the term "including" and its variants are open-ended, i.e., "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules, or units.

[0020] It should be noted that the modifiers "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] It can be understood that before using the technical solutions disclosed in the embodiments of this disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in this disclosure should be informed to users and the authorization of users should be obtained through appropriate means in accordance with relevant laws and regulations.

[0023] For example, when responding to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application program, server, or storage medium that performs the operations of the technical solutions of this disclosure according to the prompt message.

[0024] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving an active request from the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0025] It can be understood that the above process of notifying and obtaining user authorization is only illustrative and does not constitute a limitation on the implementation manners of this disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manners of this disclosure.

[0026] At the same time, it can be understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of corresponding laws, regulations and related regulations.

[0027] Figure 1 Shown is a flowchart of an agent interaction method provided according to an embodiment of this disclosure. As Figure 1 shown, the method may include: In step 11, obtain interaction information corresponding to the interaction operation.

[0028] Among them, the interaction operation can be a text input operation or a voice input operation by the user in the interaction interface. When the interaction operation is a text input, the text input can be used as the interaction information. When the interaction operation is a voice input, the text obtained after speech recognition of the voice input can be used as the interaction information.

[0029] As an example, the interaction operation in the present disclosure is the interaction during a conversation between the user and the intelligent agent. For example, the question-answer pair of the interaction between the user and the intelligent agent is regarded as one round of conversation. One or more rounds of conversations can be included in one session between the user and the intelligent agent, and each round of conversation belongs to a certain session process.

[0030] In step 12, an interaction intelligent agent is determined from the target intelligent agent. Among them, the target intelligent agent includes multiple sub-intelligent agents with an associated relationship, and the prompt words corresponding to different sub-intelligent agents are different. The interaction intelligent agent is one of the multiple sub-intelligent agents.

[0031] Among them, the target intelligent agent can be an intelligent agent Agent implemented based on one or more LLMs. Among them, the prompt words corresponding to the multiple sub-intelligent agents are different, so that different sub-intelligent agents can implement different functions. The models corresponding to different sub-intelligent agents can be the same or different. The multiple sub-intelligent agents can be intelligent agents split from the same intelligent agent with multiple sets of prompt words and partial tools, and each sub-intelligent agent is responsible for a type of task. And in this step, there is an associated relationship between different sub-intelligent agents, so as to provide data support for the selection of the interaction intelligent agent.

[0032] In step 13, based on the prompt words corresponding to the interaction intelligent agent and the model corresponding to the interaction intelligent agent, the inference result of the interaction information is determined.

[0033] As an example, a prompt text prompt can be constructed based on the interaction information and the prompt words corresponding to the interaction intelligent agent. For example, the interaction information can be spliced into a preset position in the prompt words to obtain the prompt text. Furthermore, the prompt text can be input into the model corresponding to the interaction intelligent agent, so that the model can perform data analysis and inference based on the prompt text to obtain an output result, that is, the inference result of the interaction information. Among them, the model corresponding to the interaction intelligent agent can be a model implemented based on an LLM.

[0034] In step 14, the response information of the interaction information is determined based on the inference result, and the response information is output.

[0035] As an example, it is possible to determine whether the inference result can be used as an answer to the interaction information based on the inference result. If so, the inference result is used as the response information. As an example, the output response information can be to display the text corresponding to the response information in the interaction interface, such as displaying the text corresponding to the response information in the form of a dialog box. As another example, the output response information can be to perform speech synthesis based on the text corresponding to the response information to obtain the voice corresponding to the response information, and then output the voice in the interaction interface. Among them, the way to output the response information can be determined based on the way of the user's interaction operation, that is, when the user interacts through text, the response information is output in text form, and when the user interacts through voice, the response information is output in voice form.

[0036] In the above technical solution, when a user interacts with a target intelligent agent, an interaction intelligent agent can be determined from multiple associated sub-intelligent agents in the target intelligent agent, so that an inference result of the interaction information can be determined based on the prompt corresponding to the interaction intelligent agent and the model corresponding to the interaction intelligent agent, and then the response information to the interaction information of the interaction operation can be determined. Thus, through the above technical solution, the target intelligent agent includes multiple associated sub-intelligent agents, and the prompts corresponding to different sub-intelligent agents are different, so that the interaction of a single intelligent agent with a long prompt and many tools can be converted into an interaction with multiple sub-intelligent agents with different prompts, which can facilitate the writing and application of the prompts corresponding to the intelligent agent, reduce the complexity of the prompts, improve the efficiency and accuracy of the intelligent agent's inference, and thus improve the efficiency and accuracy of the response to the interaction information. In addition, based on the above technical solution, when adjusting the prompt or the tool of the intelligent agent, it is possible to adjust a single sub-intelligent agent, avoiding the impact of the adjustment of the prompt on the entire target intelligent agent, effectively reducing the complexity and scope of influence of the intelligent agent adjustment, and thus ensuring the accuracy and efficiency of the intelligent agent debugging, providing effective support for ensuring accurate response information.

[0037] In some embodiments, the association relationship of the multiple sub-intelligent agents is represented by a directed graph, and each sub-intelligent agent corresponds to a node in the directed graph. For example Figure 2As shown in the figure, it is a schematic diagram of a directed graph provided based on an embodiment of the present disclosure. Among them, the start node Start is the default starting node when the agent processes a new conversation. The root node Root Agent is a successor node of the start node, and there is only one root node among multiple sub-agents. The sub-agent node Agent is used to represent multiple sub-agents included in the target agent, which can include existing agents or newly created agents by the user. For example, when the user creates a multi-agent (i.e., the target agent), multiple sub-agents can be pre-registered in the target agent, each agent is used as a sub-agent, and the association relationships of different sub-agents are planned. Among them, the directed graph can be obtained by pre-configuration based on the actual application scenario.

[0038] Correspondingly, determining the interaction agent from the target agent may include: Determine the current node in the directed graph.

[0039] Among them, the directed graph indicates the process of the target agent responding to interaction information, and the current node can be used to represent the currently required node determined based on the directed graph.

[0040] As an example, determining the current node in the directed graph may include: Obtain the configuration information of the target agent.

[0041] Among them, the configuration information can be configured by the user based on the actual application scenario when creating the target agent. For example, in some scenarios, each round of conversation needs to start from the start node, and in some scenarios, each round of conversation does not need to start from the start node. The initial node of each round of conversation can be configured through the configuration information.

[0042] As an example, the configuration interface of the target agent may include a configuration box for whether to start from the start node. If "yes" is selected, the generated configuration information indicates that the initial node of the interaction operation is the start node. If "no" is selected or not selected, the configuration information does not indicate that the initial node of the interaction operation is the start node. Correspondingly, the initial node of each round of conversation can be determined based on the configuration information.

[0043] If the configuration information indicates that the initial node of the interaction operation is the start node, then use the start node in the directed graph as the current node. In this scenario, when receiving the user's interaction operation, it all starts from the start node of the directed graph.

[0044] If the initial node of the interaction operation is not indicated as the start node in the configuration information, the node corresponding to the sub-agent of the previous round of interaction operation is used as the current node. This scenario means that it is not necessary to execute from the start node in each round of conversation. At this time, the interaction can continue based on the historical interaction, so the node corresponding to the sub-agent of the previous round of interaction operation can be used as the current node. As an example, as Figure 2 shown, if the sub-agent of the previous round of interaction operation is Agent1, then the current node is Agent1 after obtaining the interaction information in this round of interaction. If there are multiple sub-agents executed in the previous round of interaction operation, the last sub-agent is used as the sub-agent of the previous round of interaction operation to determine the current node.

[0045] Thus, through the above technical solution, the current node of each round of conversation interaction in the session of the target agent can be determined based on the configuration information of the target agent, providing effective data support for the subsequent selection of sub-agents based on the directed graph.

[0046] After determining the current node, if the current node is the start node in the directed graph, candidate agents are determined from the multiple sub-agents based on the directed graph; Based on the interaction information, the candidate agents, and the large language model, an interaction agent is determined, where the interaction agent is one of the candidate agents.

[0047] Among them, if the current node is the start node in the directed graph, it can automatically transition to the root node in the directed graph. As an example, the successor nodes of the root node can be used as the candidate agents, such as Agent1, Agent2, and Agent3 can be used as candidate agents.

[0048] Furthermore, a prompt text prompt can be constructed based on the interaction information and the candidate agents. For example, the interaction information and the relevant information of the candidate agents can be concatenated into the prompt text. The relevant information of the candidate agent can include the identifier and function description information of the candidate agent, etc. Then the prompt text is input into the large language model to enable the large language model to determine an interaction agent from the candidate agents. The large language model is a pre-trained model, which can be obtained by fine-tuning and training based on the existing large language model, and will not be elaborated here. As an example, in the non-first-round conversation interaction of the same session, the historical conversation content in the current session can be concatenated into the prompt text to provide more data support for the large language model to select the interaction agent.

[0049] Thus, through the above technical solution, when the current node is the initial node, the interaction agent that responds to the interaction information can be determined based on the association relationship between the sub-agents indicated in the directed graph, realizing the rapid and effective selection of the sub-agents and ensuring the matching degree between the interaction agent and the interaction information.

[0050] In some embodiments, determining the interaction agent from the target agents may further include: If the current node is the node corresponding to the sub-agent of the previous interaction operation, the sub-agent corresponding to the current node is used as the interaction agent.

[0051] As described above, in some scenarios, each round of conversation does not need to start from the start node in the directed graph, and can also be executed based on the order of the sub-agents in the previous interaction. Then the determined current node is the node corresponding to the sub-agent of the previous interaction operation. As described above, the sub-agent of the previous interaction operation is Agent1. Then in this round of interaction, after obtaining the interaction information, the current node is Agent1. At this time, this Agent1 can be further determined as the interaction agent. On the one hand, it can realize the rapid selection of the interaction agent. On the other hand, directly processing based on the sub-agent of the previous interaction operation in this round of interaction can also ensure the coherence and fluency of the response information in the user interaction process to a certain extent, improving the user experience.

[0052] In some embodiments, determining the response information of the interaction information based on the reasoning result may include: Determining the candidate agent corresponding to the interaction agent from the multiple sub-agents based on the directed graph.

[0053] As an example, after determining the reasoning result based on the interaction agent, it can be further determined whether the reasoning result can solve the problem of the interaction information. In this step, the selection of the next agent can be further performed based on the directed graph.

[0054] As an example, determining the candidate agent corresponding to the interaction agent from the multiple sub-agents based on the directed graph includes: If the interaction agent is of the first type, the existing candidate agents and the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph are used as the candidate agents.

[0055] Among them, the candidate agent can be a global variable, so as to record the candidate agent determined during the process execution. The type of each sub-agent can be configured according to the actual application scenario during the registration of the sub-agent. In this embodiment, the initial node is the start node and automatically transitions to the root node. At this time, the existing candidate agents are empty. Based on the directed graph, the successor nodes Agent1, Agent2, and Agent3 of the root node can be used as candidate agents, and Agent1 is selected as the interaction agent from them. Further, if the interaction agent Agent1 is of the first type, the existing candidate agents and the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph can be used as the candidate agents. At this time, the existing candidate agents are Agent1, Agent2, and Agent3, and the agents corresponding to the successor nodes of the node of the interaction agent Agent1 are Agent11 and Agent12. Then, the determined candidate agents at this time include Agent1, Agent2, Agent3, Agent11, and Agent12. That is, in this scenario, the candidate agent NextStepNodes is determined in the following way: NextStepNodes = NextStepNodes + the successor nodes of the current interaction agent node.

[0056] If the interaction agent is of the second type, the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph are used as the candidate agents.

[0057] As another example, in another session process, the initial node is the start node and automatically transitions to the root node. At this time, the existing candidate agents are empty. Based on the directed graph, the successor nodes Agent1, Agent2, and Agent3 of the root node can be used as candidate agents, and Agent2 is selected as the interaction agent from them. Further, if the interaction agent Agent2 is of the second type, the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph can be used as the candidate agents. At this time, the existing candidate agents are Agent1, Agent2, and Agent3, and the agents corresponding to the successor nodes of the node of the interaction agent Agent2 are Agent21 and Agent22. Then, the determined candidate agents at this time include Agent21 and Agent12. That is, in this scenario, the candidate agent NextStepNodes is determined in the following way: NextStepNodes = the successor nodes of the current interaction agent node.

[0058] Thus, through the above technical solution, the candidate agent corresponding to the interactive agent can be determined based on the type of the interactive agent, so as to select the next agent from the candidate agents subsequently, providing effective data support for the selection of the next agent. At the same time, it can also avoid the waste of resources caused by taking all sub-agents as candidate agents and improve the efficiency of selecting the next agent.

[0059] After determining the candidate agents, the next agent can be determined based on the inference result, the interaction information, the candidate agents, and the large language model, where the next agent is one of the candidate agents.

[0060] As an example, for the first type of interactive agent, a prompt text can be constructed based on the inference result, the interaction information, and the candidate agents. The prompt text is as follows: You can obtain the user's tasks and requirements through the conversation history. The last object is the current interaction information user_input. You must select the most suitable Agent.

[0061] # The following is a list of candidate agents: {Agent} Only reply with agent_id and nothing else.

[0062] {Conversation history} It is necessary to understand the above conversation history. When the user's intention changes, find an agent from the list of candidate agents that can help the user solve the problem and return its agent_id.

[0063] Among them, the conversation history may include the inference result. If the current interaction is the first-round interaction operation in the conversation, it includes the interaction information and the inference result. If the current interaction is a non-first-round interaction operation in the conversation, it may include the interaction content of the previous rounds in this conversation, as well as the interaction information and the inference result of this round. Thus, the above information can be spliced into the corresponding positions in the prompt text, and then the prompt text is input into the large language model, enabling the large language model to select and return the identifier of an agent from multiple agents.

[0064] As an example, for the second type of interactive agent, the interactive agent can also be determined in the above manner. As another example, determining the next agent based on the inference result, the interaction information, the candidate agents, and the large language model may include: If the interactive agent is a node of the second type, a tool for constructing the interactive agent is built based on the candidate agent, and the large language model determines a target tool from the tool set of the interactive agent according to the inference result and the interactive information, where the tool set includes the tools built by the candidate agent.

[0065] In this step, the tool can be built based on the candidate agent according to the general tool building method of Agent in the art, which will not be elaborated here. Then, the candidate agent can be used as multiple tools carried by the interactive agent. For example, in the above example, Agent21 and Agent22 can be used to build Tool 21 and Tool 22. Furthermore, a prompt text can be built through the inference result, the interactive information, and the tool set and input into the large language model, so that the large language model can select a target tool from the tool set based on the tool selection logic. The tool selection logic can be implemented based on the existing Agent tool selection logic in the art, so as to realize the reuse of the existing logic code and reduce the complexity of the implementation code of the method of the present disclosure.

[0066] Determine the next agent based on the target tool.

[0067] If the target tool is a tool built by a candidate agent, the candidate agent corresponding to the target tool can be used as the next agent.

[0068] Further, after determining the next agent, it can be determined whether to continue the reasoning based on the next agent.

[0069] As an example, the interactive agent is of the first type; correspondingly, determining whether to continue the reasoning based on the next agent may include: If the next agent is different from the interactive agent, it is determined that the reasoning needs to continue. That is, the next agent is another agent, and it needs to perform a different data reasoning process. At this time, it is considered that the reasoning needs to continue, and then it can be transferred to the next agent for data reasoning.

[0070] If the next agent is the same as the interactive agent, it is determined that there is no need to continue the reasoning. That is, the next agent is still the current interactive agent, and its reasoning process has been completed and there is no need to reason again. At this time, it can be considered that there is no need to continue the reasoning, that is, the reasoning process of the target agent ends.

[0071] As an example, the interactive agent is of the second type; correspondingly, determining whether to continue the reasoning based on the next agent may include: If the target tool is a tool constructed based on the candidate agent, it is determined that reasoning needs to continue. That is, the selected target tool is the tool corresponding to the sub-agent in the directed graph. At this time, data reasoning needs to be further performed based on the agent corresponding to the selected target tool, so it is considered that reasoning needs to continue, and then it can be transferred to the agent corresponding to the target tool for data reasoning.

[0072] If the target tool is not a tool constructed based on the candidate agent, it is determined that reasoning does not need to continue. At this time, it is considered that there is no need to further perform data reasoning based on the sub-agent in the directed graph, so it can be considered that reasoning does not need to continue, that is, the reasoning process of the target agent ends.

[0073] Thus, through the above technical solution, it can be accurately determined whether it is necessary to continue reasoning based on the sub-agent in the directed graph, so as to determine whether the reasoning process of the target agent is completed, so as to ensure the accuracy and effectiveness of the finally determined response information.

[0074] If it is determined that reasoning does not need to continue, the reasoning result determined by the latest interactive agent is used as the response information.

[0075] If it is determined that reasoning does not need to continue, that is, the reasoning process of the target agent is completed. At this time, the reasoning result determined by the latest interactive agent is used as the response information. For example, if the next agent determined by Agent1 is Agent1, it is determined that reasoning does not need to continue, and the reasoning result of Agent1 is used as the response information.

[0076] Thus, through the above technical solution, the response information corresponding to the interaction information can be obtained by determining whether it is necessary to continue reasoning, so as to ensure the matching degree between the response information and the interaction information.

[0077] In some embodiments, determining the response information of the interaction information based on the reasoning result may further include: If it is determined that reasoning needs to continue, the next agent is used as the new interactive agent, and based on the reasoning result, the prompt corresponding to the new interactive agent, and the model corresponding to the new interactive agent, the reasoning result of the interaction information is determined, and the step of determining the candidate agent corresponding to the interactive agent from the multiple sub-agents based on the directed graph is returned.

[0078] As an example, the current interactive agent is Agent1, and the next agent determined by it is Agent11. If they are different, it is determined that reasoning needs to continue. At this time, the next agent Agent11 can be used as the new interactive agent, and based on the reasoning result, the prompt corresponding to the new interactive agent Agent11, and the model corresponding to the new interactive agent Agent11, the reasoning result of the interactive information is determined. For example, a prompt text can be constructed based on the reasoning result of Agent1, the interactive information, and the prompt corresponding to Agent11, and the prompt text is input into the model corresponding to Agent11 to obtain the reasoning result of Agent11 for the interactive information.

[0079] And return to execute the step of determining the candidate agent corresponding to the interactive agent from the multiple sub-agents based on the directed graph, the step of determining the next agent based on the reasoning result, the interactive information, the candidate agent, and the large language model, and the step of determining whether to continue reasoning based on the next agent until it is determined that no further reasoning is required.

[0080] That is, afterwards, Agent11 is used as the interactive agent, and further, the candidate agent of Agent11 is determined based on the directed graph, and the next agent is determined, so as to determine whether to continue reasoning based on the next agent. The specific implementation manners of the above steps have been described above and will not be elaborated here.

[0081] Thus, through the above technical solution, the sub-agent executed during the execution of the target agent can be dynamically determined based on the directed graph, improving the diversity during the execution of the target agent and the matching degree with the actual application scenario. Moreover, since the prompts of different sub-agents are different, that is, the reasoning tasks they handle are different, different sub-agents can focus on a type of task, reducing the complexity of the model task processing of the sub-agents, thereby improving the accuracy of the reasoning results of each interactive agent, and further improving the accuracy of the finally determined response information, meeting the user's usage requirements, and enhancing the user experience.

[0082] Based on the same inventive concept, the present disclosure also provides an intelligent agent interaction device, as Figure 3 shown, the device 10 includes: An acquisition module 100, configured to acquire interactive information corresponding to an interactive operation; A first determination module 200, configured to determine an interactive agent from a target agent, where the target agent includes multiple sub-agents with an association relationship, and the prompts corresponding to different sub-agents are different, and the interactive agent is one of the multiple sub-agents; The second determination module 300 is configured to determine the inference result of the interaction information based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent; The processing module 400 is configured to determine the response information of the interaction information based on the inference result and output the response information.

[0083] Optionally, the association relationship of the multiple sub-agents is represented by a directed graph, and each sub-agent corresponds to a node in the directed graph; The first determination module includes: The first determination sub-module is configured to determine the current node in the directed graph; The second determination sub-module is configured to, if the current node is the start node in the directed graph, determine the candidate agents from the multiple sub-agents based on the directed graph; The third determination sub-module is configured to determine the interaction agent based on the interaction information, the candidate agents, and the large language model, where the interaction agent is one of the candidate agents.

[0084] Optionally, the first determination module further includes: The fourth determination sub-module is configured to, if the current node is the node corresponding to the sub-agent of the previous interaction operation, use the sub-agent corresponding to the current node as the interaction agent.

[0085] Optionally, the first determination sub-module includes: The acquisition sub-module is configured to acquire the configuration information of the target agent; The fifth determination sub-module is configured to, if the initial node indicating the interaction operation in the configuration information is the start node, use the start node in the directed graph as the current node; The sixth determination sub-module is configured to, if the initial node indicating the interaction operation in the configuration information is not the start node, use the node corresponding to the sub-agent of the previous round of interaction operation as the current node.

[0086] Optionally, the processing module includes: The seventh determination sub-module is configured to determine the candidate agents corresponding to the interaction agent from the multiple sub-agents based on the directed graph; The eighth determination sub-module is configured to determine the next agent based on the inference result, the interaction information, the candidate agents, and the large language model, where the next agent is one of the candidate agents; The ninth determination sub-module is configured to determine whether to continue the inference based on the next agent; The first processing sub-module is used to, if it is determined that further reasoning is not required, use the reasoning result determined by the latest interaction agent as the response information.

[0087] Optionally, the processing module further includes: The second processing sub-module is used to, if it is determined that further reasoning is required, use the next agent as the new interaction agent, and based on the reasoning result, the prompt corresponding to the new interaction agent, and the model corresponding to the new interaction agent, determine the reasoning result of the interaction information, and trigger the seventh determination sub-module to determine the candidate agent corresponding to the interaction agent from the multiple sub-agents based on the directed graph.

[0088] Optionally, the seventh determination sub-module is further used to: If the interaction agent is of the first type, use the existing candidate agents and the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph as the candidate agents; If the interaction agent is of the second type, use the agents corresponding to the successor nodes of the node of the interaction agent in the directed graph as the candidate agents.

[0089] Optionally, the eighth determination sub-module is further used to: If the interaction agent is a node of the second type, construct the tool of the interaction agent based on the candidate agents, and use the large language model to determine the target tool from the tool set of the interaction agent according to the reasoning result and the interaction information, where the tool set contains the tools constructed by the candidate agents; Determine the next agent based on the target tool.

[0090] Optionally, the ninth determination sub-module includes: The tenth determination sub-module is used to, if the target tool is a tool constructed based on the candidate agents, determine that further reasoning is required; if the target tool is not a tool constructed based on the candidate agents, determine that further reasoning is not required.

[0091] Optionally, the interaction agent is of the first type; The ninth determination sub-module includes: The eleventh determination sub-module is used to, if the next agent is different from the interaction agent, determine that further reasoning is required; if the next agent is the same as the interaction agent, determine that further reasoning is not required.

[0092] Next, refer to Figure 4It shows a schematic structural diagram of an electronic device (such as a terminal device or a server) 600 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The shown electronic device is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0093] As Figure 4 shown, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage device 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0094] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 4 it shows the electronic device 600 having various devices, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be alternatively implemented or had.

[0095] Particularly, according to the embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiments of the present disclosure are executed.

[0096] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0097] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0098] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately without being assembled into the electronic device.

[0099] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: obtain interaction information corresponding to an interaction operation; determine an interaction agent from target agents, where the target agents include a plurality of sub-agents having an association relationship, and different sub-agents correspond to different prompts, and the interaction agent is one of the plurality of sub-agents; determine an inference result of the interaction information based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent; determine a response message for the interaction information based on the inference result, and output the response message.

[0100] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0102] The modules involved in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the module itself in some cases. For example, the acquisition module can also be described as "the module for acquiring interaction information corresponding to the interaction operation".

[0103] The functions described above herein can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0104] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on 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 disc read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0105] According to one or more embodiments of the present disclosure, Example 1 provides an agent interaction method, the method comprising: Obtaining interaction information corresponding to an interaction operation; Determining an interaction agent from target agents, wherein the target agent includes a plurality of sub-agents having an association relationship, and different sub-agents correspond to different prompt messages, and the interaction agent is one of the plurality of sub-agents; Based on the prompt message corresponding to the interaction agent and the model corresponding to the interaction agent, determining an inference result of the interaction information; Based on the inference result, determining a response message for the interaction information, and outputting the response message.

[0106] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, wherein the association relationship of the plurality of sub-agents is represented by a directed graph, and each sub-agent corresponds to a node in the directed graph; Determining the interactive agent from the target agent includes: Determine the current node in the directed graph; If the current node is the start node in the directed graph, determine candidate agents from the multiple sub-agents based on the directed graph; Determine the interactive agent based on the interaction information, the candidate agents, and the large language model, where the interactive agent is one of the candidate agents.

[0107] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, where determining the interactive agent from the target agent further includes: If the current node is the node corresponding to the sub-agent of the previous interaction operation, use the sub-agent corresponding to the current node as the interactive agent.

[0108] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 2, where determining the current node in the directed graph includes: Obtain the configuration information of the target agent; If the initial node indicating the interaction operation in the configuration information is the start node, use the start node in the directed graph as the current node; If the initial node indicating the interaction operation in the configuration information is not the start node, use the node corresponding to the sub-agent of the previous round of interaction operation as the current node.

[0109] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 1, where determining the response information of the interaction information based on the inference result includes: Determine the candidate agents corresponding to the interactive agent from the multiple sub-agents based on the directed graph; Determine the next agent based on the inference result, the interaction information, the candidate agents, and the large language model, where the next agent is one of the candidate agents; Determine whether to continue reasoning based on the next agent; If it is determined not to continue reasoning, use the inference result determined by the latest interactive agent as the response information.

[0110] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 5, where determining the response information of the interaction information based on the inference result further includes: If it is determined that further reasoning is required, then use the next agent as the new interactive agent, and based on the reasoning result, the prompt corresponding to the new interactive agent, and the model corresponding to the new interactive agent, determine the reasoning result of the interactive information, and return the step of determining the candidate agent corresponding to the interactive agent from the multiple sub-agents based on the directed graph.

[0111] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 5, wherein determining the candidate agent corresponding to the interactive agent from the multiple sub-agents based on the directed graph includes: If the interactive agent is of the first type, then use the existing candidate agents and the agents corresponding to the successor nodes of the node of the interactive agent in the directed graph as the candidate agents; If the interactive agent is of the second type, then use the agents corresponding to the successor nodes of the node of the interactive agent in the directed graph as the candidate agents.

[0112] According to one or more embodiments of the present disclosure, Example 8 provides the method of Example 7, wherein determining the next agent based on the reasoning result, the interactive information, the candidate agent, and the large language model includes: If the interactive agent is a node of the second type, then construct the tool of the interactive agent based on the candidate agent, and use the large language model to determine the target tool from the tool set of the interactive agent according to the reasoning result and the interactive information, wherein the tool set contains the tools constructed by the candidate agent; Determine the next agent based on the target tool.

[0113] According to one or more embodiments of the present disclosure, Example 9 provides the method of Example 8, wherein determining whether further reasoning is required based on the next agent includes: If the target tool is a tool constructed based on the candidate agent, then determine that further reasoning is required; If the target tool is not a tool constructed based on the candidate agent, then determine that further reasoning is not required.

[0114] According to one or more embodiments of the present disclosure, Example 10 provides the method of Example 7, wherein the interactive agent is of the first type; Determining whether further reasoning is required based on the next agent includes: If the next agent is different from the interactive agent, then determine that further reasoning is required; If the next agent is the same as the interactive agent, then determine that further reasoning is not required.

[0115] According to one or more embodiments of the present disclosure, Example 11 provides an agent interaction device, which includes: An acquisition module, configured to acquire interaction information corresponding to an interaction operation; A first determination module, configured to determine an interaction agent from target agents, where the target agents include multiple sub-agents with an association relationship, and different sub-agents correspond to different prompts, and the interaction agent is one of the multiple sub-agents; A second determination module, configured to determine an inference result of the interaction information based on the prompt corresponding to the interaction agent and the model corresponding to the interaction agent; A processing module, configured to determine a response message for the interaction information based on the inference result and output the response message.

[0116] According to one or more embodiments of the present disclosure, Example 12 provides a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processing device, the steps of the method described in any one of Examples 1-10 are implemented.

[0117] According to one or more embodiments of the present disclosure, Example 13 provides an electronic device, including: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method described in any one of Examples 1-10.

[0118] According to one or more embodiments of the present disclosure, Example 14 provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of Examples 1-10 are implemented.

[0119] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features with similar functions disclosed in the present disclosure.

[0120] Moreover, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features that are described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0121] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. With regard to the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

Claims

1. An agent interaction method, characterized in that: The method comprises: Obtain interaction information corresponding to the interaction operation; Determine an interactive agent from a target agent, wherein the target agent includes a plurality of sub-agents having association relationships, different sub-agents correspond to different prompts, and the interactive agent is one of the plurality of sub-agents; Determining the inference result of the interaction information based on the prompt corresponding to the interactive agent and the model corresponding to the interactive agent; Response information of the interaction information is determined based on the inference result, and the response information is output.

2. The method according to claim 1, characterized in that The association relationship of the plurality of sub-agents is represented by a directed graph, and each of the sub-agents corresponds to a node in the directed graph; The step of determining the interactive agent from the target agent comprises: Determining a current node in the directed graph; If the current node is a starting node in the directed graph, determining a candidate agent from the plurality of sub-agents based on the directed graph; The interacting agent is determined based on the interaction information, the candidate agents and the large language model, wherein the interacting agent is one of the candidate agents.

3. The method according to claim 2, characterized in that The step of determining the interactive agent from the target agent further includes: If the current node is the node corresponding to the sub-agent of the last interactive operation, the sub-agent corresponding to the current node is used as the interactive agent.

4. The method according to claim 2, characterized in that: The determining of the current node in the directed graph comprises: Obtaining configuration information of the target agent; If the initial node indicating the interactive operation in the configuration information is the start node, taking the start node in the directed graph as the current node; If the configuration information does not indicate that the initial node of the interactive operation is the starting node, the node corresponding to the sub-agent in the previous round of interactive operation is used as the current node.

5. The method according to claim 1, characterized in that The determining the response information of the interaction information based on the inference result includes: Determining a candidate agent corresponding to the interactive agent from the plurality of sub-agents based on the directed graph; Determine a next agent based on the inference result, the interaction information, the candidate agents and the large language model, wherein the next agent is one of the candidate agents; Determining whether to continue reasoning based on the next agent; If it is determined that there is no need to continue reasoning, the reasoning result determined by the latest interactive intelligent agent is used as the response information.

6. The method according to claim 5, characterized in that The determining the response information of the interaction information based on the inference result further includes: If it is determined that reasoning needs to continue, the next agent is used as a new interactive agent, and the reasoning result of the interactive information is determined based on the reasoning result, the prompt corresponding to the new interactive agent and the model corresponding to the new interactive agent, and the step of determining the candidate agent corresponding to the interactive agent from the multiple sub-agents based on the directed graph is returned.

7. The method according to claim 5, characterized in that The step of determining a candidate agent corresponding to the interactive agent from the plurality of sub-agents based on the directed graph comprises: If the interactive agent is of the first type, the existing candidate agents and the agents corresponding to the successor nodes of the nodes of the interactive agent in the directed graph are used as the candidate agents; If the interactive agent is of the second type, the agent corresponding to the successor node of the node of the interactive agent in the directed graph is used as the candidate agent.

8. The method according to claim 7, characterized in that The step of determining the next agent based on the inference result, the interaction information, the candidate agents and the large language model comprises: If the interactive agent is a node of the second type, constructing a tool for the interactive agent based on the candidate agent, and determining a target tool from a tool set of the interactive agent according to the reasoning result and the interaction information through the large language model, wherein the tool set includes the tool constructed by the candidate agent; Based on the target tool, the next agent is determined.

9. The method according to claim 8, characterized in that The determining whether to continue reasoning based on the next agent includes: If the target tool is a tool built based on the candidate agent, determining that reasoning needs to be continued; If the target tool is not a tool built based on the candidate agent, it is determined that there is no need to continue reasoning.

10. The method according to claim 7, characterized in that The interactive agent is of the first type; The determining whether to continue reasoning based on the next agent includes: If the next agent and the interacting agent are different, it is determined that the reasoning needs to be continued; If the next agent and the interacting agent are the same, it is determined that there is no need to continue reasoning.

11. An intelligent agent interaction device, characterized in that: The device comprises: An acquisition module, used to acquire interaction information corresponding to the interaction operation; A first determination module is used to determine an interactive agent from a target agent, wherein the target agent includes a plurality of sub-agents having association relationships, different sub-agents correspond to different prompts, and the interactive agent is one of the plurality of sub-agents; A second determination module is used to determine the inference result of the interaction information based on the prompt corresponding to the interactive agent and the model corresponding to the interactive agent; A processing module is used to determine response information of the interaction information based on the reasoning result and output the response information.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 10 are implemented.

13. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images