Method and computer program product for conference interaction based on personal agents

Abstract

The present application relates to the technical field of intelligent conference, in particular to a conference interaction method and computer program product based on personal intelligent agent, comprising sending conference basic data and personal intelligent agent participation request to a person who intends to participate in the conference; receiving participation feedback of the person who intends to participate in the conference in response to the personal intelligent agent participation request; according to the participation feedback, organizing the personal intelligent agent to conduct virtual conference according to the conference basic data, obtaining intelligent agent conference record; sending the intelligent agent conference record to all participating personal intelligent agent corresponding participating persons, so that the participating persons modify and confirm; receiving the modification data of the personal intelligent agent speech sent by the participating persons; calling AI to adjust the intelligent agent conference record according to the modification data, generating conference summary; sending the conference summary to all participating persons for confirmation. The problem of how to balance the demand of the participating person for the right to participate in the conference and the right to participate in the conference of the personal intelligent agent is better solved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent conferencing technology, and in particular to a conferencing interaction method and computer program product based on a personal intelligent agent. Background Technology

[0002] This section is intended to provide background or context for the embodiments disclosed herein. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] With the rapid development of artificial intelligence technology, personal intelligent agents have emerged. Compared to general artificial intelligence (AI), personal intelligent agents can remember user preferences and habits, access personal knowledge bases, and complete tasks independently without frequent human intervention, similar to a user's personal assistant or a digital avatar. Currently, the development of intelligent agent technology has already impacted the field of intelligent conferencing. For example, patent CN119155134B discloses the ability to invoke intelligent agents to participate in meetings based on meeting requests, allowing the intelligent agents to act as hosts, observers, and speakers; and patent CN117938561A discloses the use of robots to participate in meetings in place of users.

[0004] However, existing technologies lack meeting interaction methods tailored to the aforementioned characteristics of personal intelligent agents. In current meeting interaction methods, users struggle to balance the need for centralized and decentralized control over the participation of personal intelligent agents, hindering the application of personal intelligent agent technology in the field of intelligent conferencing. Summary of the Invention

[0005] Therefore, it is necessary to provide a meeting interaction method and computer program product based on personal intelligent agents to address the above-mentioned technical problems and help users balance the need to centralize and delegate authority over the participation of personal intelligent agents in meetings.

[0006] Firstly, this disclosure provides a meeting interaction method based on a personal intelligent agent. The method includes:

[0007] Send basic meeting data and personal intelligent agent participation requests to individuals who intend to attend the meeting; the basic meeting data includes at least one of meeting agenda data, meeting background data, and meeting objective data.

[0008] Receive participation feedback from the individual intending to attend the meeting in response to the participation request from the personal intelligent agent; when the participation feedback includes confirmation of participation, the participation feedback also includes authorization to call the corresponding personal intelligent agent;

[0009] Based on the feedback from the participants, the organization determines the participating individual agents to conduct a virtual meeting based on the basic meeting data, and obtains the agent meeting record; the agent meeting record includes all the speeches of the individual agents.

[0010] The meeting minutes of the intelligent agents are sent to the individual participants corresponding to all the participating individual intelligent agents, so that the participants can modify and confirm the speech of their individual intelligent agents;

[0011] Receive modified data of the personal intelligent agent speech sent by the participating individuals;

[0012] The AI ​​is invoked to adjust the meeting minutes of the intelligent agent according to the modified data, and a meeting summary is generated;

[0013] The meeting summary will be sent to all participants for confirmation.

[0014] Optionally, the method further includes:

[0015] Based on the feedback from all participating personal AI agents, determine whether the participating personal AI agents meet the meeting requirements and obtain the first judgment result;

[0016] The virtual meeting is organized only when the first determination result includes meeting requirements.

[0017] Optionally, there may be multiple meeting summaries, and the method further includes:

[0018] Receive voting results from participants on multiple meeting summaries;

[0019] Based on the voting results, the meeting summary with the highest number of votes will be determined as the meeting resolution;

[0020] The meeting resolutions will be sent to all participants for confirmation.

[0021] Optionally, the method further includes:

[0022] Before the virtual meeting takes place, each participant sets their personal agent's participation control parameters based on the meeting's basic data; the participation control parameters include at least one of the following parameters: database access scope, personal participation goal, and agent personality parameters.

[0023] Optionally, the method further includes:

[0024] The personal intelligent agent generates the first speech based on the basic meeting data and the participation control parameters;

[0025] The personal intelligent agent sets the second speech draft as the preset speech draft for participating in the virtual meeting; the second speech draft is the speech draft modified by the participating individual from the first speech draft.

[0026] Optionally, the virtual meeting includes:

[0027] Obtain the individual identity data of the participating intelligent agents;

[0028] The AI ​​is invoked to generate the meeting agenda based on the basic meeting data and the individual participant identity data;

[0029] Organize the virtual meeting according to the stated meeting agenda.

[0030] Optionally, the virtual meeting includes:

[0031] The individual intelligent agent that determines which individual needs to speak based on the current agenda is called the associated intelligent agent;

[0032] The associated intelligent agents are organized to speak first in a preset order;

[0033] An individual intelligent agent that is not part of the associated intelligent agent may decide whether to make a second statement; the second statement may include supplementary statements and / or corrective statements; the number of words in the second statement shall not exceed the first preset number of words.

[0034] Optionally, the method further includes:

[0035] Send a first instruction to the participating individual intelligent agents. The content of the first instruction includes: using existing conference speeches as a reference for the content of newly generated conference speeches.

[0036] The meeting minutes and the meeting summary of the intelligent agent will be sent to all participants for confirmation.

[0037] Optionally, the method further includes:

[0038] AI is invoked to identify abnormal statements in the meeting records of the intelligent agent, and the identification results are obtained; the abnormal statements include contradictory statements and suspected erroneous statements.

[0039] When the identification result includes the presence of abnormal speech, AI is invoked to analyze the cause of the abnormality and provide suggested solutions to resolve the abnormality.

[0040] The intelligent agent meeting records are marked as abnormal based on the identification results, the reasons for the anomalies, and the suggested solutions.

[0041] When an individual agent's speech is flagged as abnormal, the abnormality alert and the meeting minutes of the flagged agent are simultaneously sent to the corresponding participating individual.

[0042] Secondly, this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0043] Send basic meeting data and personal intelligent agent participation requests to individuals who intend to attend the meeting; the basic meeting data includes at least one of meeting agenda data, meeting background data, and meeting objective data.

[0044] Receive participation feedback from the individual intending to attend the meeting in response to the participation request from the personal intelligent agent; when the participation feedback includes confirmation of participation, the participation feedback also includes authorization to call the corresponding personal intelligent agent;

[0045] Based on the feedback from the participants, the organization determines the participating individual agents to conduct a virtual meeting based on the basic meeting data, and obtains the agent meeting record; the agent meeting record includes all the speeches of the individual agents.

[0046] The meeting minutes of the intelligent agents are sent to the individual participants corresponding to all the participating individual intelligent agents, so that the participants can modify and confirm the speech of their individual intelligent agents;

[0047] Receive modified data of the personal intelligent agent speech sent by the participating individuals;

[0048] The AI ​​is invoked to adjust the meeting minutes of the intelligent agent according to the modified data, and a meeting summary is generated;

[0049] The meeting summary will be sent to all participants for confirmation.

[0050] The aforementioned meeting interaction method based on personal intelligent agents proposes a novel meeting interaction mode. In this mode, all participants use personal intelligent agents to represent themselves, unlike traditional physical or online meetings. The meeting is conducted virtually through these personal intelligent agents. To balance the need for centralized and decentralized control over the participation of personal intelligent agents, the decision to attend or not is given to the individual participant, while the decision on how to speak is given to the personal intelligent agent. However, the right to modify the speaker's speech remains with the individual participant. This leverages the efficiency of personal intelligent agent participation while ensuring individual control over participation permissions and meeting outcomes. Compared to physical meetings, this interaction mode is shorter and more efficient. Since participants modify and confirm the speech of their personal intelligent agents, the influence of the actual meeting environment on their individual speeches is effectively shielded, allowing for more objective and rational discussions. Compared to human participants, virtual meetings are less affected by real-world factors, and meeting times are easier to schedule. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0052] Figure 1 This is an application environment diagram of a conference interaction method based on personal intelligent agents in one embodiment.

[0053] Figure 2 This is a flowchart illustrating a meeting interaction method based on a personal intelligent agent in one embodiment;

[0054] Figure 3 This is an interactive diagram of a meeting interaction method based on a personal intelligent agent in one embodiment;

[0055] Figure 4 This is an interactive diagram of a conference interaction method based on personal intelligent agents in another embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description, in conjunction with the accompanying drawings and embodiments, provides a more comprehensive understanding of this disclosure. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this disclosure. In the following detailed description of this application, certain specific details are described in detail. Those skilled in the art can fully understand this application even without these detailed descriptions. To avoid obscuring the essence of this application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0057] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0058] The meeting interaction method based on personal intelligent agents provided in this disclosure can be applied to various application environments. For example... Figure 1In the illustrated application environment, each participant 10 has their own personal intelligent agent 12. The personal intelligent agent 12 can be deployed on a local or cloud server. Participant 10 can interact with their personal intelligent agent 12 via terminal 14. The personal intelligent agent 12 can attend the meeting on behalf of its owner after authorization. Participant 10 can also interact with the meeting server 16, which is responsible for initiating and organizing the meeting, via terminal 14, and can control whether to grant the meeting server 16 permission to access their personal intelligent agent 12. The meeting server processes and interacts with data according to a specific procedure. For example, the meeting server 16 can interact with the meeting initiator 20 via terminal 18 to obtain data on the proposed participants and basic meeting data. The meeting initiator 20 can be an individual or an intelligent agent. The meeting server 16 can be a local server or a cloud server. The meeting server 16 sends basic meeting data and personal intelligent agent participation requests to the proposed participants; the basic meeting data includes at least one of meeting agenda data, meeting background data, and meeting target data. The conference server 16 receives participation feedback from the individuals intending to participate in the conference, responding to the participation request of the personal AI agent. When the participation feedback includes confirmation of participation, it also includes authorization to call the corresponding personal AI agent. Based on the participation feedback, the conference server 16 organizes the confirmed personal AI agents 12 to conduct a virtual meeting based on the conference data, obtaining AI agent meeting records. The AI ​​agent meeting records include all personal AI agent speeches. The conference server 16 sends the AI ​​agent meeting records to all participating individuals 10 corresponding to the personal AI agents 12, allowing them to modify and confirm their personal AI agent 12's speeches. The conference server 16 receives the modified personal AI agent speeches sent by the participating individuals 10. The conference server 16 calls the AI ​​to adjust the AI ​​agent meeting records according to the modified data, generating a meeting summary. The conference server 16 sends the meeting summary to all participating individuals 10 corresponding to the personal AI agents 12 for confirmation. Terminals 14 and 18 can be, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The conference server 16 can be implemented using a standalone server or a server cluster consisting of multiple servers. It should be noted that the conference initiator can also be a prospective participant or a prospective participant's personal intelligent agent.

[0059] In one embodiment, such as Figure 2 and Figure 3As shown, a meeting interaction method based on personal intelligent agents is provided. Taking the application of this method in the above-mentioned application scenario as an example, the method includes the following steps:

[0060] Step 102: Send basic meeting data and personal intelligent agent participation requests to the individuals who intend to participate in the meeting; the basic meeting data includes at least one of meeting topic data, meeting background data, and meeting objective data.

[0061] Here, "proposed attendee" can refer to the person the meeting initiator wishes to attend. "Attending individual" can refer to the person who decides to use a personal intelligent agent to attend on their behalf. "Personal intelligent agent participation request" can be an authorization request containing the message "call the proposed attendee's personal intelligent agent to attend the meeting." "Personal intelligent agent" can be an intelligent agent with access to a personal knowledge base whose access permissions are controlled by the individual. "Meeting agenda data" can refer to data containing the meeting agenda and matters to be discussed. "Meeting background data" can refer to data containing background information about the meeting, such as the reasons for holding the meeting, its necessity, urgency, and industry developments. "Meeting objective data" can refer to data containing the meeting's purpose and the desired outcomes.

[0062] Specifically, the meeting initiator can first identify the individuals who need to attend or wish to attend the meeting, and then send basic meeting data and personal agent participation requests to all potential participants through the meeting server (hereinafter referred to as the system), seeking authorization to invoke the personal agents of the potential participants. The potential participants may include the meeting initiator himself.

[0063] Step 104: Receive the participation feedback from the proposed participant in response to the participation request of the personal intelligent agent; when the participation feedback includes confirmation of participation, the participation feedback also includes the authorization to call the corresponding personal intelligent agent.

[0064] Among them, the feedback from participants can refer to whether they agree to have a personal intelligent agent used to attend the meeting on their behalf.

[0065] Specifically, after receiving the basic meeting data and the personal AI agent's participation request, the prospective participant can decide whether to delegate their personal AI agent to participate on their behalf, based on the content of the basic meeting data. After making a decision, the prospective participant can send their participation feedback to the system. The feedback can include disagreement to participate, or agreement to participate and authorization to invoke the personal AI agent. When a prospective participant has multiple personal AI agents, they can choose one to participate on their behalf and provide authorization to invoke that agent in their participation feedback. Authorization can be provided using authorization codes or other credentials. When organizing the virtual meeting in subsequent steps, the system can send these credentials to the corresponding personal AI agent. The personal AI agent verifies the credentials, and upon successful verification, participates in the meeting according to the methods provided by the system.

[0066] Step 106: Based on the participant feedback, the organization determines the participating individual agents to conduct a virtual meeting based on the meeting data, and obtains the agent meeting record; the agent meeting record includes all the speeches of the individual agents.

[0067] In this context, a virtual meeting can refer to a meeting conducted via the internet without the direct participation of any real person. Personal intelligent agent speech can refer to the speech given by participating personal intelligent agents in a virtual meeting.

[0068] Specifically, based on the meeting feedback, the system can determine which individual AI agents are eligible to participate and obtain permission to invoke these agents. Then, the system organizes a virtual meeting for the identified participating AI agents. The system provides the participating AI agents with access to the meeting and requires all participating AI agents to use basic meeting data as one of the bases for generating their meeting speeches. The system records the speeches of all AI agents, obtaining the AI ​​agent meeting minutes. Existing technologies already enable the organization of multiple AIs for group chats, thus enabling the invocation of multiple individual AI agents to discuss specific content, i.e., conducting virtual meetings. This embodiment does not restrict how the virtual meeting is organized; technicians can choose from existing technological solutions as needed.

[0069] Step 108: Send the meeting minutes of the intelligent agent to the individual participants corresponding to all participating individual intelligent agents, so that the participants can modify and confirm the speech of their individual intelligent agents.

[0070] Specifically, the system sends the meeting minutes to the individual participants corresponding to all participating individual agents. Participants can view the statements made by all individual agents in the virtual meeting, and can review their own agent's statements. If any statements do not conform to their wishes, they can modify them and then confirm that the modified statements reflect their true intentions. If no modifications are needed, participants can directly confirm their own agent's statements. Participants cannot modify or confirm the statements of other individuals' individual agents.

[0071] Step 110: Receive the modified data of the personal intelligent agent speech sent by the participating individual.

[0072] Specifically, the modified data includes changes made by individual participants to their personal agent's speech, which may include adjustments to the specific content of the speech or no adjustments at all. After modifying and confirming their speech, individual participants send the modified data to the system, which can receive and aggregate all the modified data.

[0073] Step 112: Call the AI ​​to adjust the intelligent agent's meeting minutes according to the modified data and generate a meeting summary.

[0074] In this context, a meeting summary can refer to a summary of the meeting's content, including the consensus reached and the decisions made.

[0075] Specifically, AI can be invoked to adjust the agent's meeting minutes based on the modified data sent by individual participants. The adjusted agent meeting minutes can be considered a record of each participant's actual speech during the meeting. Then, the AI ​​generates a meeting summary based on the adjusted agent meeting minutes. Since the system can automatically invoke AI to complete this step, therefore... Figure 3 There is no interaction corresponding to step 112.

[0076] Step 114: Send the meeting summary to all participants for confirmation.

[0077] Specifically, the system can send the generated meeting summary to all participating individual agents for their confirmation, essentially requiring each participant to sign off on the meeting results. The AI-adjusted agent meeting minutes from step 112, along with the meeting summary, can be sent to the participating individuals for confirmation.

[0078] This embodiment presents a novel meeting interaction mode where all participants use personal intelligent agents to represent themselves, unlike traditional physical or online meetings. The meeting is conducted virtually through these personal intelligent agents. To balance the need for centralized and decentralized control over the participation of personal intelligent agents, the decision to attend is given to the individual participant, while the decision on how to speak is given to the personal intelligent agent. However, the right to modify the speaker's speech remains with the individual participant. This leverages the efficiency of personal intelligent agent participation while ensuring individual control over participation permissions and meeting outcomes. Compared to physical meetings, this interaction mode is shorter and more efficient. Since participants modify and confirm the speech of their personal intelligent agents, the influence of the actual meeting environment on their speech is effectively eliminated, allowing for more objective and rational discussions. Compared to human participants, virtual meetings are less affected by real-world factors, and meeting time is easier to schedule.

[0079] In one embodiment, the method further includes:

[0080] Based on the feedback from all participating personal AI agents, determine whether the participating personal AI agents meet the meeting requirements and obtain the first judgment result;

[0081] The virtual meeting is organized only when the first determination result includes meeting requirements.

[0082] Among them, meeting requirements can refer to the pre-set prerequisites that must be met to hold a virtual meeting.

[0083] Specifically, meeting requirements can include a preset threshold for the percentage of invited participants agreeing to attend, or the requirement that specific invited individuals must agree to attend. The system can statistically analyze all individual agent participation feedback to determine whether the feedback meets the meeting requirements. The initial judgment result can include whether the requirements are met or not, along with specific indicators of non-compliance. Only when participating individuals meet the meeting requirements will the system automatically or with human intervention organize a virtual meeting.

[0084] In this embodiment, by setting a judgment procedure, a virtual meeting will only be organized when the participating individual intelligent agents meet the meeting requirements, which helps to ensure the quality of the meeting and avoid invalid meetings.

[0085] In one embodiment, reference Figure 4 As shown, there are multiple meeting summaries, and the method further includes:

[0086] Receive voting results from participants on multiple meeting summaries;

[0087] Based on the voting results, the meeting summary with the highest number of votes will be determined as the meeting resolution;

[0088] The meeting resolutions will be sent to all participants for confirmation.

[0089] Specifically, the AI ​​can automatically generate multiple meeting summaries based on existing meeting presentations. The system can then send these summaries to individual participants for voting. To ensure the voting's authority, different numbers of votes can be assigned to different participants. For example, in a company-level meeting, leaders can be given more votes to give their votes greater weight. Alternatively, voting rights can be restricted to only certain participants. Specific voting rules are not limited in this disclosure; technical personnel can configure them according to actual needs. After voting, the system can designate the summary with the most votes as the meeting resolution to reflect the democratic nature of the meeting. Finally, the system sends the meeting resolution to all participants for confirmation.

[0090] In one embodiment, reference Figure 4 As shown, the method further includes:

[0091] Before the virtual meeting takes place, each participant sets their personal agent's participation control parameters based on the meeting's basic data; the participation control parameters include at least one of the following parameters: database access scope, personal participation goal, and agent personality parameters.

[0092] Here, "database access scope" refers to the range of data that an individual intelligent agent can use when participating in a virtual meeting. "Individual meeting goal" refers to the meeting objectives that the participating individual hopes their individual intelligent agent can achieve in the virtual meeting. "Agent personality parameters" refers to quantifiable or structured characteristic parameters used to define and regulate the individual intelligent agent's behavioral tendencies, decision-making logic, and interaction style.

[0093] Specifically, the setup of basic meeting data can be completed either before or after participant feedback is sent, ideally before the individual AI agent is organized to participate. Agent personality parameters enable the individual AI agent to exhibit a consistent and human-like "personality" across different scenarios, thereby improving the naturalness of interaction and task adaptability. For example, agent personality parameters could be MBTI (Myers-Briggs Type Indicator) sixteen-type personality parameters. After understanding the content of the basic meeting data, participants can set participation control parameters to ensure their individual AI agent makes statements that better align with their needs and intentions during the virtual meeting. For example, by controlling the scope of database access, participants can prevent their individual AI agent from revealing unauthorized database content during the virtual meeting. Similarly, by controlling individual participation goals, important content standards can be provided for the individual AI agent's statements in the virtual meeting, enabling the agent to make statements that match the participant's intentions. For example, by setting personality parameters for the intelligent agent, it is possible to adjust the speaking and decision-making styles of an individual intelligent agent when participating in a virtual meeting, thereby meeting the personalized needs of the participants.

[0094] In one embodiment, reference Figure 4 As shown, the method further includes:

[0095] The personal intelligent agent generates the first speech based on the basic meeting data and the participation control parameters;

[0096] The personal intelligent agent sets the second speech draft as the preset speech draft for participating in the virtual meeting; the second speech draft is the speech draft modified by the participating individual from the first speech draft.

[0097] Among them, the preset speech can refer to a speech that has been pre-set and can be directly used by the personal intelligent agent in the virtual meeting.

[0098] Specifically, the second speech draft can be finalized before or after the participant feedback is sent, ideally before the individual agent is organized to participate in the meeting. The content of the individual agent's speeches in the virtual meeting, especially in the first round of speeches, can be pre-set by the participating individual. For example, the individual agent can first generate a first speech draft based on the basic meeting data and the participation control parameters; then, the participating individual can review and revise the first speech draft to obtain the second speech draft; finally, the second speech draft can be set as the preset speech draft. In this way, the participating individual can set the tone for the individual agent's speeches during the virtual meeting, providing specific content references and helping to ensure that the individual agent's speeches align with the participating individual's true intentions.

[0099] In one embodiment, the virtual meeting includes:

[0100] Obtain the individual identity data of the participating intelligent agents;

[0101] The AI ​​is invoked to generate the meeting agenda based on the basic meeting data and the individual participant identity data;

[0102] Organize the virtual meeting according to the stated meeting agenda.

[0103] The personal identification data of the participants can refer to data containing the personal identification information of the participants related to the virtual meeting. The meeting agenda can refer to the specific arrangements of the meeting, including the order of speaking.

[0104] Specifically, the system can obtain the individual identity data of the participating intelligent agents through a specific database or by requiring input from the participants. Then, it invokes AI, such as Doubao, Tongyi Qianwen, Deepseek (a Chinese AI), and chatGPT (an American AI), to generate a meeting agenda based on the basic meeting data and the individual participant identity data. The AI ​​will set the specific agenda and speaking order according to the participants' identities and the needs of the meeting. During the meeting, the system can organize a virtual meeting according to this agenda. This embodiment provides a method for creating a virtual meeting agenda, which helps to automatically create meeting agendas that meet actual needs using AI.

[0105] In one embodiment, the virtual meeting includes:

[0106] The individual intelligent agent that determines which individual needs to speak based on the current agenda is called the associated intelligent agent;

[0107] The associated intelligent agents are organized to speak first in a preset order;

[0108] An individual intelligent agent that is not part of the associated intelligent agent may decide whether to make a second statement; the second statement may include supplementary statements and / or corrective statements; the number of words in the second statement shall not exceed the first preset number of words.

[0109] Here, the preset order can refer to the pre-defined speaking order of individual intelligent agents. The first preset word count can refer to the pre-defined word limit for the second speech. The first speech can refer to the speech of an associated intelligent agent. The second speech can refer to the speech of an unassociated intelligent agent.

[0110] Specifically, the preset order can be part of the meeting agenda. A corresponding program can be set in the system to determine the speaking order of individual agents based on factors such as job level, job relevance to the topic, stroke order of participant names, and alphabetical order of participant names. Technical personnel can set the program to generate the speaking order as needed; this disclosure does not impose any restrictions. The meeting agenda is divided into multiple stages. In the current agenda, not all participants may be relevant to the discussion content; therefore, the individual agents representing them generally do not need to speak. The meeting agenda can include individual agents who need to speak in each stage. Thus, for the current agenda, the participating individual agents can be divided into relevant agents and unrelated agents. Relevant agents refer to agents that need to speak in the current agenda. Unrelated agents refer to individual agents that are not relevant agents in the current agenda, i.e., individuals who do not need to speak in the current agenda. For relevant agents, they can be arranged to speak first according to the preset order. For unrelated agents, they can be arranged to speak second as observers after their first speech. The second speech includes at least one of supplementary or corrective remarks. This allows the computing power of unconnected agents to be utilized, ensuring that the meeting discussions are thorough and scientific. To prevent unconnected agents from speaking too much or taking too long, a first preset word limit can be set for the second speaker. The first preset word limit can be set as needed, for example, 100-500 words, or 100, 200, 300, or 500 words.

[0111] In one embodiment, the method further includes:

[0112] Send a first instruction to the participating individual intelligent agents. The content of the first instruction includes: using existing conference speeches as a reference for the content of newly generated conference speeches.

[0113] Specifically, before the virtual meeting begins, the system or participating individuals can send a first instruction to their personal agents. This instruction requires the personal agents to consider existing meeting content when generating new remarks during the virtual meeting. This ensures that the remarks of each personal agent are coherent throughout the virtual meeting.

[0114] In one embodiment, the method further includes:

[0115] AI is invoked to identify abnormal statements in the meeting records of the intelligent agent, and the identification results are obtained; the abnormal statements include contradictory statements and suspected erroneous statements.

[0116] When the identification result includes the presence of abnormal speech, AI is invoked to analyze the cause of the abnormality and provide suggested solutions to resolve the abnormality.

[0117] The intelligent agent meeting records are marked as abnormal based on the identification results, the reasons for the anomalies, and the suggested solutions.

[0118] Anomaly alerts and the tagged agent's meeting minutes are simultaneously sent to the corresponding participants.

[0119] Among these, "abnormal alerts" can refer to alerts containing information such as "the personal AI agent's speech may contain abnormalities." "Contradictory speech" refers to speech that contradicts itself or the speech of other personal AI agents. "Suspected erroneous speech" refers to speech that the AI ​​has determined to be erroneous or potentially erroneous.

[0120] Specifically, before sending the intelligent agent meeting minutes to the participating individuals, an AI, such as a general AI, can be invoked to uniformly check the speeches of all individual intelligent agents, identifying contradictory or potentially erroneous statements, analyzing possible causes, and providing suggested solutions. Then, the intelligent agent meeting minutes are marked as abnormal based on the identification results. The identification results can include the specific content of the abnormal speech and the basis for the judgment, i.e., the reason for the abnormality. The abnormality and its cause analyzed by the AI ​​may not be accurate and require confirmation from the participating individuals. The abnormality marking should not only indicate the location of the abnormal content but also provide the basis for the AI's judgment, and may also include AI-provided modification suggestions. For cases with abnormalities, the abnormality alert and the marked intelligent agent meeting minutes can be sent together to the corresponding participating individuals to facilitate their adjustment and confirmation of the speech content. In this embodiment, by invoking AI for error correction, providing error resolution suggestions, and issuing error alerts before sending the intelligent agent meeting minutes to the participating individuals, it helps to facilitate the review and modification of the individual intelligent agent's speech content by the participating individuals.

[0121] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0122] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0123] Send basic meeting data and personal intelligent agent participation requests to individuals who intend to attend the meeting; the basic meeting data includes at least one of meeting agenda data, meeting background data, and meeting objective data.

[0124] Receive participation feedback from the individual intending to attend the meeting in response to the participation request from the personal intelligent agent; when the participation feedback includes confirmation of participation, the participation feedback also includes authorization to call the corresponding personal intelligent agent;

[0125] Based on the feedback from the participants, the organization determines the participating individual agents to conduct a virtual meeting based on the basic meeting data, and obtains the agent meeting record; the agent meeting record includes all the speeches of the individual agents.

[0126] The meeting minutes of the intelligent agents are sent to the individual participants corresponding to all the participating individual intelligent agents, so that the participants can modify and confirm the speech of their individual intelligent agents;

[0127] Receive modified data of the personal intelligent agent speech sent by the participating individuals;

[0128] The AI ​​is invoked to adjust the meeting minutes of the intelligent agent according to the modified data, and a meeting summary is generated;

[0129] The meeting summary will be sent to all participants for confirmation.

[0130] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0132] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (RRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this disclosure may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this disclosure may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0133] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the appended claims.

Claims

1. A meeting interaction method based on personal intelligent agents, characterized in that, The method includes: Send basic meeting data and personal intelligent agent participation requests to individuals who intend to attend the meeting; the basic meeting data includes at least one of meeting agenda data, meeting background data, and meeting objective data. Receive participation feedback from the individual intending to attend the meeting in response to the participation request from the personal intelligent agent; when the participation feedback includes confirmation of participation, the participation feedback also includes authorization to call the corresponding personal intelligent agent; Based on the feedback from the participants, the organization determines the participating individual agents to conduct a virtual meeting based on the basic meeting data, and obtains the agent meeting record; the agent meeting record includes all the speeches of the individual agents. The meeting minutes of the intelligent agents are sent to the individual participants corresponding to all the participating individual intelligent agents, so that the participants can modify and confirm the speech of their individual intelligent agents; Receive modified data of the personal intelligent agent speech sent by the participating individuals; The AI ​​is invoked to adjust the meeting minutes of the intelligent agent according to the modified data, and a meeting summary is generated; The meeting summary will be sent to all participants for confirmation.

2. The method according to claim 1, characterized in that, The method further includes: Based on the feedback from all participating personal AI agents, determine whether the participating personal AI agents meet the meeting requirements and obtain the first judgment result; The virtual meeting is organized only when the first determination result includes meeting requirements.

3. The method according to claim 1, characterized in that, There are multiple meeting summaries, and the method also includes: Receive voting results from participants on multiple meeting summaries; Based on the voting results, the meeting summary with the highest number of votes will be determined as the meeting resolution; The meeting resolutions will be sent to all participants for confirmation.

4. The method according to claim 1, characterized in that, The method further includes: Before the virtual meeting takes place, each participant sets their personal agent's participation control parameters based on the meeting's basic data; the participation control parameters include at least one of the following parameters: database access scope, personal participation goal, and agent personality parameters.

5. The method according to claim 4, characterized in that, The method further includes: The personal intelligent agent generates the first speech based on the basic meeting data and the participation control parameters; The personal intelligent agent sets the second speech draft as the preset speech draft for participating in the virtual meeting; the second speech draft is the speech draft modified by the participating individual from the first speech draft.

6. The method according to claim 1, characterized in that, The virtual meeting includes: Obtain the individual identity data of the participating intelligent agents; The AI ​​is invoked to generate the meeting agenda based on the basic meeting data and the individual participant identity data; Organize the virtual meeting according to the stated meeting agenda.

7. The method according to claim 1, characterized in that, The virtual meeting includes: The individual intelligent agent that determines which individual needs to speak based on the current agenda is called the associated intelligent agent; The associated intelligent agents are organized to speak first in a preset order; An individual intelligent agent that is not part of the associated intelligent agent may decide whether to make a second statement; the second statement may include supplementary statements and / or corrective statements; the number of words in the second statement shall not exceed the first preset number of words.

8. The method according to claim 1, characterized in that, The method further includes: Send a first instruction to the participating individual intelligent agents. The content of the first instruction includes: using existing conference speeches as a reference for the content of newly generated conference speeches. The meeting minutes and the meeting summary of the intelligent agent will be sent to all participants for confirmation.

9. The method according to claim 1, characterized in that, The method further includes: AI is invoked to identify abnormal statements in the meeting records of the intelligent agent, and the identification results are obtained; the abnormal statements include contradictory statements and suspected erroneous statements. When the identification result includes the presence of abnormal speech, AI is invoked to analyze the cause of the abnormality and provide suggested solutions to resolve the abnormality. The intelligent agent meeting records are marked as abnormal based on the identification results, the reasons for the anomalies, and the suggested solutions. When an individual agent's speech is flagged as abnormal, the abnormality alert and the meeting minutes of the flagged agent are simultaneously sent to the corresponding participating individual.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images