Conference speaking control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a conference speaking control method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring conference system data of a target conference; constructing an AI map taking conference members of the target conference as entities based on the conference system data; generating a speaking rule of the target conference according to the AI map; and controlling the plurality of conference members in the target conference to speak based on the speaking rule. Through the embodiment of the invention, the speaking rule is automatically generated, the conference is controlled to speak orderly, and the conference control efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of conference control, and in particular to a conference speech control method and device, electronic equipment, and storage medium. Background Art

[0002] With the popularity of remote work and online collaboration, video conferencing has become an indispensable part of modern work. However, traditional video conferencing software often relies on manual management of the speaking order. The speakers of the video conference need to be manually input into the settings by the conference controller (rules include: managing the speaking queue and allocating speaking rights), which is very cumbersome during the meeting. This is not only inefficient, but also prone to errors. Summary of the invention

[0003] In view of the above problems, a conference speech control method and device, electronic device, and storage medium are proposed to overcome the above problems or at least partially solve the above problems, including:

[0004] A conference speech control method, the method comprising:

[0005] Obtain conference system data of the target conference;

[0006] Constructing an AI graph based on the conference system data with conference members of the target conference as entities;

[0007] Generate speech rules for the target meeting according to the AI ​​graph;

[0008] Based on the speech rule, multiple conference members in the target conference are controlled to speak.

[0009] In one embodiment of the present invention, generating the speech rules of the target conference according to the AI ​​graph includes:

[0010] Determine the vector information corresponding to each entity in the AI ​​graph;

[0011] Determine distance information between two entities based on the vector information;

[0012] The speech rules of the target conference are generated according to the distance information.

[0013] In one embodiment of the present invention, each entity includes vector information of multiple dimensions, the multiple dimensions are determined according to conference system data, and the generating of the speech rules of the target conference according to the distance information includes:

[0014] Determine the shortest distance among the distance information calculated based on the vector information of multiple dimensions;

[0015] The speech rules for the target conference are generated based on the target dimension corresponding to the shortest distance.

[0016] In one embodiment of the present invention, the step of constructing an AI graph based on the conference system data with the conference members of the target conference as entities includes:

[0017] Determine conference members of the target conference based on the conference system data;

[0018] Determining the membership relationship between the conference members based on the conference system data;

[0019] Construct an AI graph with the conference members as entities and the member relationships as entity relationships.

[0020] In one embodiment of the present invention, controlling multiple conference members in the target conference to speak based on the speech rule includes:

[0021] Determine the target conference member who will speak next based on the speaking rule;

[0022] generating a target notification message for notifying the target conference member to prepare to speak;

[0023] The target notification message is sent to the conference terminal corresponding to the target conference member.

[0024] In one embodiment of the present invention, it also includes:

[0025] Determining location information of the target conference member;

[0026] The capturing angle of view of the image capturing device at the meeting place where the target meeting is located is adjusted based on the location information.

[0027] In one embodiment of the present invention, before constructing the AI ​​graph based on the conference system data with the conference members of the target conference as entities, the method further includes:

[0028] The conference system data is converted into structured data.

[0029] A conference speech control device, the device comprising:

[0030] A conference system data acquisition module, used to acquire conference system data of a target conference;

[0031] An AI graph construction module, used to construct an AI graph with conference members of the target conference as entities based on the conference system data;

[0032] A speech rule generation module, used to generate the speech rules of the target conference according to the AI ​​graph;

[0033] The speech control module is used to control multiple conference members in the target conference to speak based on the speech rules.

[0034] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the conference speech control method as described above when executed by the processor.

[0035] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the conference speech control method as described above is implemented.

[0036] The embodiments of the present invention have the following advantages:

[0037] The embodiment of the present invention obtains the conference system data of the target conference, and constructs an AI graph with the conference members of the target conference as entities based on the conference system data. Then, the speech rules of the target conference can be generated according to the AI ​​graph, and multiple conference members in the target conference can be controlled to speak based on the speech rules. This realizes the automatic generation of speech rules, controls the orderly speech in the conference, and improves the efficiency of conference control. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0039] Figure 1 This is a flowchart of a conference speech control method provided by an embodiment of the present invention;

[0040] Figure 2 is a flowchart of another conference speech control method provided by an embodiment of the present invention;

[0041] Figure 3 is a flowchart of another conference speech control method provided by an embodiment of the present invention;

[0042] Figure 4 It is a structural diagram of a conference speech control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Reference Figure 1 , shows a flowchart of a conference speech control method provided by an embodiment of the present invention, which may specifically include the following steps:

[0045] Step S101, obtaining conference system data of a target conference;

[0046] Among them, the conference system data is the target conference in the embodiment of the present invention, which can be a video network conference, or a conference that combines a video network conference and an Internet conference. The conference system data at least includes conference members and other data used to characterize the relationship between members. Specifically, the conference system data in the embodiment of the present invention can include any one or more of the following:

[0047] Original data: conference member ID, network identification (such as video network number or IP address), login terminal number, login terminal identification screen, conference files, etc.;

[0048] Data in the meeting: meeting member IDs, time and location information, voice recognition, uploaded meeting files, etc. after the meeting starts;

[0049] Historical information about meeting members’ participation in meetings, such as whether meeting members spoke, whether meeting members shared meeting documents, and network status of meeting members.

[0050] In one embodiment of the present invention, before constructing an AI graph (Artificial Intelligence) with the meeting members of the target meeting as entities based on the conference system data, the conference system data can be converted into structured data so as to quickly construct the AI ​​graph using the structured data. The structured data includes: structured data, unstructured data, and semi-structured data.

[0051] Among them, structured data refers to data that follows a fixed format and pattern. Structured data can be stored in a relational database, such as tables, rows, and columns. Because structured data follows a consistent structure, it is basically easy to search, analyze, and process.

[0052] Unstructured data refers to data without a fixed format or pattern, such as text, pictures, audio, video, etc. Unstructured data is not stored in traditional databases, but exists in the form of files, logs, messages, etc. The processing and analysis of unstructured data requires the use of technologies such as natural language processing, image recognition, and speech recognition.

[0053] Semi-structured data is between structured data and unstructured data. Although it has a certain structure, it does not follow a strict pattern. Examples include XML (Extensible Markup Language) files, JSON (JavaScript Object Notation) data, and some types of log files. Semi-structured data can contain tags or other markers so that data elements can be identified and parsed, but their structure is not as strict as that of a relational database.

[0054] In an embodiment of the present invention, the target conference is a conference controlled by a conference system in the first network. The conference system in the first network can be provided with a network interface connected to the second network, and the AI ​​function in the second network can be called through the network interface to realize the generation of a corresponding AI graph for the conference system data in the first network, and then generate corresponding speech rules for speech control. By calling the existing AI function in the second network through the network interface, the AI ​​function of the second network can be applied without changing the structure of the conference system in the first network.

[0055] Specifically, the conference system in the first network can obtain the conference system data of the target conference, and send the conference system data to the AI ​​module of the second network through the network interface. The AI ​​module constructs an AI graph with the conference members of the target conference as entities based on the conference system data, and sends the AI ​​graph to the conference system. The conference system generates the speaking rules of the target conference based on the AI ​​graph, and then controls the multiple conference members in the target conference to speak in an orderly manner based on the speaking rules.

[0056] Among them, the first network may be a visual Internet network, and the second network may be other networks other than the visual Internet network, such as the Internet network.

[0057] Step S102, constructing an AI graph with conference members of the target conference as entities based on conference system data;

[0058] After determining the conference system data, an AI graph can be constructed based on the conference system data. Each entity in the constructed AI graph can represent a conference member, and the entity relationship represents the relationship between conference members. In the constructed AI graph, each entity has features of different dimensions, and the features of different dimensions of the entity can be extracted from the conference system data.

[0059] For example, historical information about participating in a meeting may include whether meeting members spoke, whether meeting members shared meeting files, and the network status of meeting members. Therefore, the characteristics of an entity may include characteristics of dimensions such as speaking status, meeting file sharing status, and network status.

[0060] In one example, after the AI ​​graph is generated, the AI ​​graph can be displayed on the conference control interface or the conference terminal interface corresponding to the conference members, so that users can quickly access the conference system data and understand the relationship between the conference members.

[0061] In one embodiment of the present invention, an AI graph with conference members of a target conference as entities is constructed based on conference system data, including: determining conference members of the target conference based on the conference system data; determining member relationships between conference members based on the conference system data; and constructing an AI graph with conference members as entities and member relationships as entity relationships.

[0062] In practical applications, the AI ​​graph is composed of entity-relationship-entity. The conference system data may include the identification of the conference members participating in the target conference and the characteristic data of different dimensions of each conference member. The identification of the conference member is used to distinguish different conference members. In the AI ​​graph, the identification of the conference member can be used as the entity of the AI ​​graph. The relationship between entities is determined based on the characteristic data of different dimensions, so that the AI ​​graph in the embodiment of the present invention is constructed through entity-relationship-entity.

[0063] Step S103, generating speech rules for the target conference according to the AI ​​graph;

[0064] The speaking rules may include but are not limited to speaking time, speaking order, and speaking authority.

[0065] After building the AI ​​graph, the speaking rules for the target meeting can be automatically generated based on the relationships between entities within the AI ​​graph.

[0066] In an embodiment of the present invention, step S103 may include the following sub-steps:

[0067] Sub-step 11, determining the vector information corresponding to each entity in the AI ​​graph;

[0068] In practical applications, each entity can be converted into vector information, and in one example, each entity (such as a conference member) can be represented as a multi-dimensional vector, with each dimension representing a specific feature (such as the number of historical speeches, participation, file sharing frequency, etc. of the conference member). Specifically, entity vectorization technology can be used to convert entities into vector information to facilitate vector calculations. For example, entity vectorization technology can include embedding technology.

[0069] Sub-step 12, determining distance information between two entities based on the vector information;

[0070] After determining the vector information of each entity, the distance information between entities can be calculated by vectors, and the distance information can be determined by Euclidean distance, cosine similarity, etc. The distance information of vectors can be used to measure the similarity or correlation between entities. The smaller the distance, the higher the similarity of the two vectors, and thus the higher the correlation of the corresponding entities.

[0071] Sub-step 13, generating the speaking rules of the target conference according to the distance information.

[0072] After determining the distance information, since the distance information actually shows the degree of association between entities, the speaking rules of the target meeting can be automatically generated according to the distance information.

[0073] Specifically, each entity includes vector information of multiple dimensions, and the multiple dimensions are determined according to the conference system data. The speaking rules of the target conference are generated according to the distance information, including: determining the shortest distance in the distance information calculated based on the vector information of multiple dimensions; and generating the speaking rules of the target conference based on the target dimension corresponding to the shortest distance.

[0074] In practical applications, in the AI ​​graph, the entity distance between any two entities can be calculated according to different dimensions, and then the entity pair with the shortest distance among multiple distance information can be determined (in a multidimensional vector space, the entity pair with the shortest distance refers to the entity pair with the smallest Euclidean distance or the largest cosine similarity), and then the speech rules are automatically generated according to the target dimension corresponding to the shortest distance. The target dimension is the most similar or relevant feature between two entities.

[0075] For example, when the target dimension of the shortest distance is "historical number of speeches", the conference system can formulate speaking rules that give priority to members with a higher number of historical speeches, so as to ensure the continuity and efficiency of the meeting.

[0076] In one embodiment of the present invention, as the meeting progresses, the conference system data continues to change, and the corresponding AI graph also changes accordingly, so that speaking rules can be automatically generated at different stages of the meeting, conference speech control can be achieved, and conference control efficiency can be improved.

[0077] Step S104: Control multiple conference members in the target conference to speak based on the speaking rule.

[0078] After determining the speaking rules, the speaking rules can be used to restrict how conference members speak in the target conference, and then during the conference, multiple conference members can be controlled to speak in an orderly manner according to the speaking rules, thereby improving the efficiency of the meeting.

[0079] In one embodiment of the present invention, multiple conference members in a target conference are controlled to speak based on speech rules, including: determining the target conference member who is to speak next based on the speech rules; generating a target notification message for notifying the target conference member to prepare to speak; and sending the target notification message to the conference terminal corresponding to the target conference member.

[0080] In actual applications, the speaking rules may include a speaking order, and the next speaking member may be determined according to the speaking order, and then the user may be informed to prepare to speak by generating a target notification message. Specifically, the conference system may obtain the first conference member identifier of the current speaking member, and determine whether the first conference member identifier exists in the speaking order. When the first conference member identifier does not exist in the speaking order, the conference member corresponding to the first conference member identifier in the speaking order is determined as the next speaking member; when the first conference member identifier exists in the speaking order, the second conference member identifier that is arranged one position after the first conference member identifier is determined from the speaking order, and the speaking member corresponding to the second conference member identifier is determined as the next speaking member. When there is no conference member in the target conference currently in the speaking state, the conference system cannot obtain the first conference member identifier. At this time, the target conference may determine the conference member corresponding to the first conference member identifier in the speaking order as the next speaking member.

[0081] In one embodiment of the present invention, the location information of the target conference member can be determined; when the target conference member speaks, the capture angle of view of the image capture device at the target conference venue is adjusted based on the location information.

[0082] In actual application, the target conference site may be provided with an image acquisition device for capturing the image of the member currently speaking. The viewing angle of the image acquisition device may be adjusted according to the position of the member currently speaking.

[0083] When the conference member currently speaking switches to the target conference member, the conference system can determine the location information of the target conference member based on the conference member identifier of the target conference member, and then adjust the viewing angle information of the image acquisition device in the conference venue based on the location information, so that the viewing angle of the image acquisition device can capture the image of the current speaking member.

[0084] For example, when it is a speaker's turn to speak, the conference system can notify the speaker through the user interface module and adjust the camera angle to focus on the speaker.

[0085] In an embodiment of the present invention, by acquiring the conference system data of the target conference, an AI graph with the conference members of the target conference as entities can be constructed based on the conference system data, and then the speech rules of the target conference are generated according to the AI ​​graph, and multiple conference members in the target conference are controlled to speak based on the speech rules, thereby realizing automatic generation of speech rules, controlling conference speeches, and improving conference control efficiency.

[0086] Reference Figure 2 , shows a flowchart of a conference speech control method provided by an embodiment of the present invention, which may specifically include the following steps:

[0087] Step S201, obtaining conference system data of the target conference;

[0088] Among them, the conference system data is the target conference in the embodiment of the present invention, which can be a video network conference, or a conference that combines a video network conference and an Internet conference. The conference system data at least includes conference members and other data used to characterize the relationship between members. Specifically, the conference system data in the embodiment of the present invention can include any one or more of the following:

[0089] Original data: conference member ID, network identification (such as video network number or IP address), login terminal number, login terminal identification screen, conference files, etc.;

[0090] Data in the meeting: meeting member IDs, time and location information, voice recognition, uploaded meeting files, etc. after the meeting starts;

[0091] Historical information about meeting members’ participation in meetings, such as whether meeting members spoke, whether meeting members shared meeting documents, and network status of meeting members.

[0092] Step S202, constructing an AI graph with conference members of the target conference as entities based on conference system data;

[0093] After determining the conference system data, an AI graph can be constructed based on the conference system data. Each entity in the constructed AI graph can represent a conference member, and the entity relationship represents the relationship between the members. In the constructed AI graph, each entity has features of different dimensions, and the features of different dimensions of the entity can be extracted from the conference system data.

[0094] Step S203, determining the vector information corresponding to each entity in the AI ​​graph;

[0095] In practical applications, each entity can be converted into vector information, and in one example, each entity (such as a meeting member) can be represented as a multidimensional vector, where each dimension represents a specific feature or attribute. The features or attributes may include but are not limited to the historical number of speeches, participation, file sharing frequency, etc. of the meeting members.

[0096] Step S204, determining the distance information between the two entities based on the vector information;

[0097] After determining the vector information of each entity, the distance information between entities can be calculated through the vectors, and the distance information can be determined by Euclidean distance, cosine similarity, etc. The distance information of the vectors can be used to measure the similarity or correlation between entities. The smaller the distance, the higher the similarity of the two vectors, and thus the higher the correlation of the corresponding entities.

[0098] Step S205: Generate speech rules for the target conference according to the distance information.

[0099] After determining the distance information, since the distance information actually shows the degree of association between entities, the speaking rules of the target meeting can be automatically generated according to the distance information.

[0100] Specifically, each entity includes vector information of multiple dimensions, and the multiple dimensions are determined according to the conference system data. The speaking rules of the target conference are generated according to the distance information, including: determining the shortest distance in the distance information calculated based on the vector information of multiple dimensions; and generating the speaking rules of the target conference based on the target dimension corresponding to the shortest distance.

[0101] In practical applications, in the AI ​​graph, the entity distance between any two entities can be calculated according to different dimensions, and then the entity pair with the shortest distance among multiple distance information can be determined (in a multidimensional vector space, the entity pair with the shortest distance refers to the entity pair with the smallest Euclidean distance or the largest cosine similarity), and then the speech rules are automatically generated according to the target dimension corresponding to the shortest distance. The target dimension is the most similar or relevant feature between two entities.

[0102] For example, when the target dimension of the shortest distance is "historical number of speeches", the conference system can formulate speaking rules that give priority to members with a higher number of historical speeches, so as to ensure the continuity and efficiency of the meeting.

[0103] Step S206: Control multiple conference members in the target conference to speak based on the speech rule.

[0104] In an embodiment of the present invention, by acquiring conference system data of a target conference, an AI graph with conference members of the target conference as entities can be constructed based on the conference system data, thereby determining vector information corresponding to each entity in the AI ​​graph; determining distance information between two entities based on the vector information; generating speech rules for the target conference according to the distance information, and controlling multiple conference members in the target conference to speak based on the speech rules, thereby realizing automatic generation of speech rules, controlling conference speeches, and improving conference control efficiency.

[0105] Reference Figure 3 , shows a flowchart of another conference speech control method provided by an embodiment of the present invention, which may specifically include the following steps:

[0106] (I) Obtaining conference system data:

[0107] After the meeting is booked, the conference system obtains the conference system data, obtains the conference member ID, visual network number or IP address, visual network login terminal number or login terminal identification screen, and conference files, and obtains the conference member ID, time and location information, voice recognition, uploaded conference files, and historical information of conference members participating in the meeting before the meeting starts, such as whether they spoke, whether they shared meeting files, network conditions, etc.

[0108] The acquired conference system data is converted into structured data, which may include: structured data, unstructured data, and semi-structured data.

[0109] (II) Building an AI Graph:

[0110] Various heterogeneous data are extracted and processed separately. The extraction process can be divided into entity extraction and relationship extraction. The extracted entities and relationships are combined to generate a preliminary AI graph, which is connected through member IDs. Among them, entity disambiguation and connection technology can be used in the process of building the AI ​​graph. Entity disambiguation and connection can ensure the consistency and accuracy of the data, so that each member in the AI ​​graph can be accurately identified and connected through its ID.

[0111] After the preliminary AI map is drawn, the data can be further integrated and optimized, multi-source data can be connected, and data of the same type can be connected to generate a multi-dimensional visual AI map; the purpose is to generate a multi-dimensional visual AI map to make the relationship between data clearer and easier to understand.

[0112] (III) Automatically calculate the conference speech rules using AI graph entity vectors

[0113] In the AI ​​graph, each entity (such as meeting members, meeting documents, etc.) is represented as a vector. These vectors contain the characteristics and attributes of the entity. By calculating the distance between these vectors, the similarity or correlation between entities can be measured.

[0114] In multidimensional space, finding the shortest distance vector means finding the entities that are closest or most related to each other. These shortest distance vectors may represent the most important information or the most active participants in the meeting. By accumulating these shortest distance vectors, we can further analyze and summarize the relationships and patterns between these entities. Based on the cumulatively calculated shortest distance dimensional data, the conference system can generate real-time automatic speaking rules according to the dimensional data. These rules may include determining speaking rights, speaking order, and speech content.

[0115] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0116] Reference Figure 4 , shows a schematic diagram of the structure of a conference speech control device provided by an embodiment of the present invention, which may specifically include the following modules:

[0117] Conference system data acquisition module 401, used to acquire conference system data of a target conference;

[0118] An AI graph construction module 402 is used to construct an AI graph with the conference members of the target conference as entities based on the conference system data;

[0119] A speech rule generation module 403, used to generate speech rules for the target conference according to the AI ​​graph;

[0120] The speech control module 404 is used to control multiple conference members in the target conference to speak based on the speech rules.

[0121] In one embodiment of the present invention, the speech rule generation module 303 may include:

[0122] A vector information determination submodule, used to determine the vector information corresponding to each entity in the AI ​​graph;

[0123] A distance signal determination submodule, used to determine the distance information between two entities based on the vector information;

[0124] The speech rule generation submodule is used to generate the speech rules of the target conference according to the distance information.

[0125] In one embodiment of the present invention, each entity includes vector information of multiple dimensions, and the multiple dimensions are determined according to conference system data. The speech rule generation submodule may include:

[0126] A shortest distance determination unit, used to determine the shortest distance in the distance information calculated based on the vector information of multiple dimensions;

[0127] The speech rule determination unit is used to determine and generate the speech rule of the target conference based on the target dimension corresponding to the shortest distance.

[0128] In one embodiment of the present invention, the AI ​​graph construction module 402 may include:

[0129] A conference member determination submodule, used to determine conference members of the target conference based on the conference system data;

[0130] A member relationship determination submodule, used to determine the member relationship between the conference members based on the conference system data;

[0131] The AI ​​graph construction submodule is used to construct an AI graph with the conference members as entities and the member relationships as entity relationships.

[0132] In one embodiment of the present invention, the speech control module 404 may include:

[0133] A target conference member determination submodule, used to determine the target conference member who will speak next based on the speaking rule;

[0134] A target notification message determination submodule, used to generate a target notification message for notifying the target conference member to prepare to speak;

[0135] The notification message sending module is used to send the target notification message to the conference terminal corresponding to the target conference member.

[0136] In one embodiment of the present invention, the device further comprises:

[0137] A location information determination module, used to determine the location information of the target conference member;

[0138] The viewing angle adjustment module is used to adjust the capturing viewing angle of the image capturing device at the meeting place where the target meeting is located based on the position information.

[0139] In one embodiment of the present invention, the device further comprises:

[0140] The data conversion module is used to convert the conference system data into structured data.

[0141] In an embodiment of the present invention, by acquiring conference system data of a target conference, an AI graph with conference members of the target conference as entities can be constructed based on the conference system data, and then speech rules for the target conference are generated according to the AI ​​graph. Based on the speech rules, multiple conference members in the target conference are controlled to speak, thereby realizing automatic generation of speech rules, controlling conference speeches, and improving conference control efficiency.

[0142] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the above conference speech control method is implemented.

[0143] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the conference speech control method as described above is implemented.

[0144] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0145] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0146] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0147] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0151] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0152] The above is a detailed introduction to a conference speech control method and device, electronic device, and storage medium. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A conference speech control method, characterized in that: The method comprises: Obtain conference system data of the target conference; Constructing an AI graph based on the conference system data with conference members of the target conference as entities; Generate speech rules for the target meeting according to the AI ​​graph; Based on the speech rule, multiple conference members in the target conference are controlled to speak.

2. The method according to claim 1, characterized in that The generating the speech rules of the target conference according to the AI ​​graph includes: Determine the vector information corresponding to each entity in the AI ​​graph; Determine distance information between two entities based on the vector information; The speech rules of the target conference are generated according to the distance information.

3. The method according to claim 2, characterized in that Each entity includes vector information of multiple dimensions, the multiple dimensions are determined according to conference system data, and the generating of the speech rules of the target conference according to the distance information includes: Determine the shortest distance among the distance information calculated based on the vector information of multiple dimensions; The speech rules for the target conference are generated based on the target dimension corresponding to the shortest distance.

4. The method according to claim 1, characterized in that: The step of constructing an AI graph based on the conference system data with the conference members of the target conference as entities includes: Determine conference members of the target conference based on the conference system data; Determining the membership relationship between the conference members based on the conference system data; Construct an AI graph with the conference members as entities and the member relationships as entity relationships.

5. The method according to claim 1, characterized in that The controlling multiple conference members in the target conference to speak based on the speaking rule includes: Determine the target conference member who will speak next based on the speaking rule; generating a target notification message for notifying the target conference member to prepare to speak; The target notification message is sent to the conference terminal corresponding to the target conference member.

6. The method according to claim 5, characterized in that Also includes: Determining location information of the target conference member; When the target conference member is speaking, the capturing angle of view of the image capturing device at the conference site where the target conference is located is adjusted based on the position information.

7. The method according to claim 1, characterized in that Before constructing the AI ​​graph with the conference members of the target conference as entities based on the conference system data, the method further includes: The conference system data is converted into structured data.

8. A conference speech control device, characterized in that: The device comprises: A conference system data acquisition module, used to acquire conference system data of a target conference; An AI graph construction module, used to construct an AI graph with conference members of the target conference as entities based on the conference system data; A speech rule generation module, used to generate the speech rules of the target conference according to the AI ​​graph; The speech control module is used to control multiple conference members in the target conference to speak based on the speech rules.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the conference speech control method according to any one of claims 1 to 7 is implemented.

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

Images