Conference screen operation method, conference screen control apparatus, conference screen, device, medium and product

Abstract

Provided in the present disclosure is a conference screen operation method. The method comprises: acquiring identity information of each conference participant; acquiring conference data; on the basis of the identity information of each conference participant, determining, from the conference data, matching data corresponding to each conference participant; and on the basis of the matching data, executing a corresponding operation. Further provided in the present disclosure are a conference screen control apparatus using the conference screen operation method, and a conference screen comprising the conference screen control apparatus. In addition, the present disclosure further relates to a computer device, a computer-readable storage medium and a computer program product, which can be used for implementing steps of the conference screen operation method.

Description

Conference screen operation methods and control devices, conference screens, equipment, media and products Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to a conference screen operation method and a conference screen control device using the conference screen operation method, a conference screen including the conference screen control device, and also to a computer device, a computer-readable storage medium, and a computer program product, wherein the computer device, computer-readable storage medium, and computer program product can be used to implement the steps of the above-described conference screen operation method. Background Technology

[0002] In recent years, thanks to the rapid development of technologies such as Natural Language Processing (NLP), speech recognition, and knowledge graphs, smart conference screens have been used more and more. Existing smart conference screens can typically achieve functions such as real-time transcription of meeting speech, automatic multilingual translation, and keyword extraction. When combined with deep learning models, they can also automatically generate meeting minutes.

[0003] However, existing conference screens cannot perform personalized operations, cannot meet the individualized needs of different participants, and cannot provide a better meeting experience. For example, existing conference screens cannot intelligently assign tasks or generate personalized meeting minutes based on participants' different positions, levels, or experiences. Summary of the Invention

[0004] According to a first aspect of this disclosure, a method for operating a conference screen is provided, comprising: acquiring the identity information of each participant; acquiring conference data; determining matching data corresponding to each participant from the conference data based on the identity information of each participant; and performing a corresponding operation based on the matching data.

[0005] According to some exemplary embodiments of this disclosure, determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: obtaining the personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; identifying at least one task that needs to be performed by an employee from the meeting data; matching each of the at least one task with the personal matching features of each participant; and generating assigned tasks for participants when a match is successful, wherein each assigned task corresponds to at least one participant as the task bearer, and the assigned task is determined as the matching data.

[0006] According to some exemplary embodiments of this disclosure, the method further includes: obtaining personal matching features of designated personnel who did not attend the meeting from the employee database; matching each of the at least one task with the personal matching features of the designated personnel who did not attend the meeting; and generating assigned tasks for the non-attending personnel if the matching is successful, wherein each assigned task for the non-attending personnel corresponds to the designated personnel who are the task bearers, and the assigned tasks for the non-attending personnel are also determined as the matching data.

[0007] According to some exemplary embodiments of this disclosure, the employee database also includes outsourced personnel data stored in a hypergraph format, and the attendees and / or the designated non-attendees include the outsourced personnel.

[0008] According to some exemplary embodiments of this disclosure, the step of performing the corresponding operation based on the matching data includes: organizing the tasks assigned to the participants and the tasks assigned to the non-participants into a set of tasks to be done, wherein each task to be done corresponds to at least one person in charge of the task; and displaying the tasks to be done and the names of the people in charge of the tasks corresponding to the tasks to be done on the conference screen.

[0009] According to some exemplary embodiments of this disclosure, the step of performing the corresponding operation based on the matching data further includes: in response to receiving a personnel addition command for the pending task, matching the task assignee to be added with the pending task; in response to receiving a personnel deletion command for the pending task, disassociating the task assignee to be deleted from the pending task; in response to receiving a personnel replacement command for the pending task, replacing the task assignee to be replaced with the task assignee specified by the personnel replacement command; and updating the display of the pending task and the name of the task assignee corresponding to the pending task.

[0010] According to some exemplary embodiments of this disclosure, performing the corresponding operation based on the matching data includes: when the task bearer corresponding to the to-do task includes a participant, sending all to-do tasks corresponding to the participant to the participant's private meeting screen.

[0011] According to some exemplary embodiments of this disclosure, performing the corresponding operation based on the matching data includes: when the task assignee of the pending task includes a designated person who did not attend the meeting, sending the task name and brief description of the pending task to the designated person who did not attend the meeting via SMS and / or email.

[0012] According to some exemplary embodiments of this disclosure, determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: obtaining the personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; identifying content that can be used as meeting minutes from the meeting data; matching the content that can be used as meeting minutes with the personal matching features of each participant to generate private meeting minutes for each participant, and the private meeting minutes are determined as the matching data.

[0013] According to some exemplary embodiments of this disclosure, performing the corresponding operation based on the matching data includes: sending the private meeting minutes to the private meeting screen of the corresponding participant.

[0014] According to some exemplary embodiments of this disclosure, the step of performing the corresponding operation based on the matching data further includes: modifying the private meeting minutes of the participants in response to receiving a command to modify the private meeting minutes of the participants.

[0015] According to some exemplary embodiments of this disclosure, determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: obtaining the personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; identifying content that can be displayed in the meeting display interface from the meeting data; matching the content that can be displayed in the meeting display interface with the personal matching features of each participant to generate private meeting display content for each participant, and the private meeting display content is determined as the matching data.

[0016] According to some exemplary embodiments of this disclosure, performing the corresponding operation based on the matching data includes: sending the private meeting display interface to the private meeting screen of the corresponding participant.

[0017] According to some exemplary embodiments of this disclosure, acquiring meeting data includes: acquiring meeting-related document attachments. Correspondingly, determining matching data corresponding to each participant from the meeting data based on the participant's identity information includes: acquiring each participant's personal matching features from an employee database based on their identity information, wherein the employee database stores employee data for each participant in a hypergraph format; determining document attachment comparison features based on the document attachments; matching the document attachment comparison features with each participant's personal matching features to generate each participant's private meeting materials, and the private meeting materials are determined as the matching data.

[0018] According to some exemplary embodiments of this disclosure, determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: obtaining the personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; and determining the matching data using a pre-trained matching model based on the meeting data and the personal matching features.

[0019] According to a second aspect of this disclosure, a conference screen control device is provided, comprising: a participant identity acquisition module, a conference data acquisition module, a matching data determination module, and an adaptation operation execution module. The participant identity acquisition module is configured to acquire the identity information of each participant. The conference data acquisition module is configured to acquire conference data. The matching data determination module is configured to determine matching data corresponding to each participant from the conference data based on the participant's identity information. The adaptation operation execution module is configured to execute a corresponding operation based on the matching data.

[0020] According to some exemplary embodiments of this disclosure, the matching data determination module includes: a personal matching feature acquisition module, a task identification module, and a task allocation module. The personal matching feature acquisition module is configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The task identification module is configured to: identify at least one task that needs to be performed by an employee from the meeting data. The task allocation module is configured to: match the at least one task with the personal matching features of each participant to generate allocated tasks, wherein each allocated task corresponds to at least one participant, and the allocated tasks are used as the matching data.

[0021] According to some exemplary embodiments of this disclosure, the matching data determination module includes: a personal matching feature acquisition module, a meeting minutes determination module, and a private meeting minutes generation module. The personal matching feature acquisition module is configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The meeting minutes determination module is configured to: identify content that can be used as meeting minutes from the meeting data. The private meeting minutes generation module is configured to: match the content that can be used as meeting minutes with the personal matching features of each participant to generate private meeting minutes for each participant, and the private meeting minutes are determined as the matching data.

[0022] According to some exemplary embodiments of this disclosure, the matching data determination module includes: a personal matching feature acquisition module, a meeting display interface determination module, and a private meeting display interface generation module. The personal matching feature acquisition module is configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The meeting display interface determination module is configured to: determine the meeting display interface from the meeting data. The private meeting display interface generation module is configured to: match the meeting display interface with the personal matching features of each participant to generate a private meeting display interface for each participant, and the private meeting display interface is determined as the matching data.

[0023] According to a third aspect of this disclosure, a conference screen is provided, which includes the conference screen control device described in the second aspect of this disclosure and its various exemplary embodiments.

[0024] According to a fourth aspect of this disclosure, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored on the memory, and wherein, when the processor executes the computer program, it implements the steps of the conference screen operation method according to the first aspect of this disclosure and its exemplary embodiments.

[0025] According to a fifth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, wherein, when executed by a processor, the computer program implements the steps of the conference screen operation method according to the first aspect of this disclosure and its exemplary embodiments.

[0026] According to a sixth aspect of this disclosure, a computer program product is provided, comprising a computer program, wherein, when executed by a processor, the computer program implements the steps of the conference screen operation method according to the first aspect of this disclosure and its exemplary embodiments. Attached Figure Description

[0027] The exemplary embodiments of this disclosure will be described in detail below with reference to the accompanying drawings; in the drawings:

[0028] Figure 1 schematically illustrates, in the form of a flowchart, a method for operating a conference screen according to an exemplary embodiment of the present disclosure;

[0029] Figure 2A further illustrates details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0030] Figure 2B further illustrates details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0031] Figure 3 schematically illustrates a display interface for assigning tasks according to an exemplary embodiment of the present disclosure;

[0032] Figure 4 further illustrates the details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0033] Figure 5 further illustrates details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0034] Figure 6 schematically illustrates a private meeting screen display interface according to an exemplary embodiment of the present disclosure;

[0035] Figure 7 further illustrates details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0036] Figure 8 further illustrates details of the conference screen operation method shown in Figure 1 according to an exemplary embodiment of the present disclosure;

[0037] Figure 9 schematically illustrates a method for constructing an employee database according to an exemplary embodiment of the present disclosure;

[0038] Figure 10 schematically illustrates a method for constructing a matching model according to an exemplary embodiment of the present disclosure;

[0039] Figure 11 schematically illustrates a conference screen control device according to an exemplary embodiment of the present disclosure in the form of a block diagram;

[0040] Figure 12 further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of the present disclosure;

[0041] Figure 13 further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of the present disclosure;

[0042] Figure 14 further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of the present disclosure;

[0043] Figure 15 further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of the present disclosure;

[0044] Figure 16 schematically illustrates a conference screen according to an exemplary embodiment of the present disclosure in the form of a block diagram;

[0045] Figure 17 schematically illustrates a computer device according to an exemplary embodiment of the present disclosure in the form of a block diagram.

[0046] It should be understood that the accompanying drawings are merely schematic illustrations of exemplary embodiments of the present disclosure and are not intended to limit the present disclosure, nor need they be drawn to scale. Furthermore, in the drawings, the same or similar features are indicated by the same or similar reference numerals. Detailed Implementation

[0047] Several embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings to enable those skilled in the art to implement the technical solutions of the present disclosure. The technical solutions of the present disclosure may be embodied in many different forms, but should not be limited to the embodiments set forth herein. These embodiments are provided to make the technical solutions of the present disclosure clear and complete, but the described embodiments do not limit the scope of protection of the present disclosure.

[0048] Unless otherwise defined, all terms used in this disclosure (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. It should be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the relevant field and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0049] Before detailing the various embodiments of this disclosure, some related concepts will first be explained.

[0050] 1. Natural Language Processing (NLP): NLP is a branch of artificial intelligence that aims to enable computers to understand, generate, and process human language. Its core is to analyze text or speech data using algorithms to extract semantics, sentiment, and intent. Basic NLP technologies include word segmentation, syntactic analysis, and word embedding (converting words into numerical forms), while advanced applications rely on deep learning models (such as Transformer and BERT) to capture contextual relationships. NLP is mainly divided into two categories of tasks: language understanding (such as classification and question-answering systems) and language generation (such as automatic writing and chatbots). Typical applications include machine translation, intelligent customer service, sentiment analysis, and voice assistants, among others.

[0051] 2. Hypergraphs and Hyperedges: Hypergraphs are a more powerful topological structure, a generalization of graphs, or an extension of ordinary graphs. In ordinary graphs, edges can only connect two nodes (vertices), representing binary relations. In hypergraphs, each hyperedge can connect any number of nodes (two, three, or more), thus describing the connections between these nodes. Therefore, a hypergraph can be represented as H = (V, E), where V is the set of nodes, E is the set of hyperedges, and each hyperedge e ∈ E is a non-empty subset of the node set V. In summary, hypergraphs and hyperedges break through the binary relation limitations of ordinary graphs. Hyperedges can represent group relations of any size (binary, ternary, or higher order), and a single hyperedge can directly capture the overall association of multiple nodes, rather than the superposition of pairwise relationships. Therefore, hypergraphs and hyperedges allow for more flexible modeling of complex relationships.

[0052] Referring to Figure 1, which schematically illustrates a conference screen operation method according to an exemplary embodiment of the present disclosure in the form of a flowchart. As shown in Figure 1, the conference screen operation method 100 may include steps 110, 120, 130, and 140.

[0053] In step 110, obtain the identity information of each participant.

[0054] It should be understood that data in any form that can identify attendees can be obtained in any suitable manner. For example, attendee lists can be obtained directly from a database or conference service platform, attendees can register by scanning a QR code before the meeting to obtain their identity information, barcodes or radio frequency identification (RFID) tags can be assigned to attendees to obtain their identity information, or biometric technology can be used to identify attendees directly. This disclosure does not impose any restrictions on the specific form of data containing attendee identity information or the specific method of obtaining attendee identity information. It should also be noted that the specific form of data containing attendee identity information and the method of obtaining it should comply with relevant legal provisions.

[0055] In step 120, obtain the meeting data.

[0056] Meeting data includes, but is not limited to, video files, audio files, and / or text files related to the meeting. In some embodiments, meeting data may also include detailed meeting materials attachments related to the meeting, such as: pre-meeting preparation materials such as meeting notices, agendas, and background information; materials presented during the meeting such as PowerPoint presentations, slides, and charts; key data reports such as project schedules, financial statements, and market analysis reports; and links to relevant past documents such as historical meeting minutes and detailed documents related to the project, etc.

[0057] It should be understood that the process of acquiring meeting data typically includes preprocessing of the collected raw data. For example, audio files recording a meeting can be converted from speech to text, and then the resulting text data can be processed using NLP to generate feature vectors needed for matching operations. Similarly, video files recording a meeting can be processed through denoising, frame segmentation, sampling, feature extraction, principal component analysis, etc., to generate corresponding feature vectors.

[0058] In step 130, based on the identity information of each participant, matching data corresponding to each participant is determined from the meeting data;

[0059] In step 140, the corresponding operation is performed based on the matching data.

[0060] Therefore, the conference screen operation method 100 disclosed herein can determine the corresponding matching data from the conference data for each participant and perform the corresponding operation (here, the corresponding operation refers to the relevant operation based on the matching data and actual needs, such as the display and communication operation based on the task allocation result described in detail below, generating private meeting minutes, generating a private meeting display interface, generating private meeting materials, etc.). Thus, it is possible to implement conference screen operation specific to each participant, thereby meeting the personalized needs of different participants and providing them with a better meeting experience.

[0061] Depending on actual needs, steps 130 and 140 in the above-described conference screen operation method 100 can be implemented in different specific forms. For example, at least one task that needs to be performed by employees can be identified based on meeting data, and the at least one task can be assigned, with corresponding display or communication operations performed based on the assignment results; or meeting minutes can be determined based on meeting data, and the meeting minutes can be matched with the personal matching characteristics of each participant to generate a private meeting minutes for each participant; or a meeting display interface can be determined based on meeting data, and the meeting display interface can be matched with the personal matching characteristics of each participant to generate a private meeting display interface for each participant, and so on. The details of the above-described conference screen operation method will be further described below in conjunction with specific embodiments of this disclosure.

[0062] Referring to FIG2A, which further illustrates details of step 130 in the conference screen operation method 100 shown in FIG1 according to an exemplary embodiment of the present disclosure. As shown in FIG2A, in this embodiment, step 130 may include steps 131a, 132a, and 133a:

[0063] In step 131a, based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format;

[0064] In step 132a, at least one task that needs to be performed by an employee is identified from the meeting data; and

[0065] In step 133a, each of the at least one task is matched with the personal matching features of each participant. If the match is successful, the assigned tasks of the participants are generated, wherein each assigned task of the participants corresponds to at least one participant who is the task bearer, and the assigned tasks of the participants are determined as the matching data.

[0066] The employee database in step 131a can be constructed and managed using a Hypergraph Neural Network (HGNN). Compared to traditional Graph Neural Networks (GNNs), HGNNs can more naturally represent and model high-dimensional complex relationships, such as multiple roles among employees, project collaborations, and complementary skills. Therefore, an employee database built based on a HGNN can more naturally represent and model high-dimensional complex relationships. The identification of meeting data in step 132a can be achieved using a pre-trained identification model. The matching operation in step 133a can be achieved using a pre-trained matching model. The construction of the employee database and the training of the identification and matching models will be described in detail below.

[0067] Referring to Figure 2B, which further illustrates details of step 130 in the conference screen operation method 100 shown in Figure 1 according to an exemplary embodiment of the present disclosure. Compared to Figure 2A, in the embodiment shown in Figure 2B, step 130 may include steps 134a and 135a in addition to steps 131a, 132a, and 133a. Therefore, only this difference will be described below, and the same parts will not be repeated.

[0068] In step 134a, the personal matching characteristics of the designated personnel who did not attend the meeting are obtained from the employee database;

[0069] In step 135a, each of the at least one task is matched with the personal matching features of the designated person who did not attend the meeting. If the match is successful, the assigned tasks for the non-attendee person are generated, wherein each assigned task for the non-attendee person corresponds to the designated person who did not attend the meeting as the task bearer, and the assigned tasks for the non-attendee person are also determined as the matching data.

[0070] It should be understood that the term "designated personnel who did not attend the meeting" should be interpreted broadly here. This includes not only designated personnel who meet specific conditions in certain situations (e.g., have specific permissions for task assignment), but also all personnel in the employee database who did not attend the meeting if no conditions are explicitly specified. Furthermore, the matching operation in step 135a can be implemented using the same pre-trained matching model as in step 133a.

[0071] Furthermore, in some embodiments, the employee database may also include outsourced personnel data stored in a hypergraph format. It should be understood that outsourced personnel here refers to individuals from other companies who are not employees of this company but have a collaborative relationship with this company (e.g., undertaking projects commissioned by this company). In this case, the employee database includes both employee data of this company's employees and employee data of outsourced personnel who are not employees of this company but have a collaborative relationship. Accordingly, the attendees and / or designated non-attendees in the various embodiments described above may include outsourced personnel.

[0072] In an embodiment where assigned tasks are identified as matching data, step 140 may include: organizing the assigned tasks of the attendees and the non-attendees into a single pending task, with each pending task corresponding to at least one task assignee; and displaying the pending task and the name of the task assignee on the conference screen. In other words, step 140 organizes the assigned tasks of attendees and non-attendees, grouping attendees and non-attendees corresponding to the same task into a single pending task and its corresponding task assignee. The organized result can then be displayed on the conference screen as a pending task and its assignee.

[0073] In some embodiments, step 140 may include: in response to receiving a personnel addition command for the pending task, assigning the personnel to be added to the pending task; in response to receiving a personnel deletion command for the pending task, removing the personnel to be deleted from the pending task; in response to receiving a personnel replacement command for the pending task, replacing the personnel to be replaced with the personnel specified in the personnel replacement command; and updating the display of the pending task and the name of the personnel corresponding to the pending task.

[0074] In some embodiments, step 140 may include: if the person responsible for the task corresponding to the to-do task includes a meeting participant, sending all to-do tasks corresponding to the meeting participant to the meeting participant's private meeting screen. In some embodiments, step 140 may include: if the person responsible for the task corresponding to the to-do task includes a designated person who did not attend the meeting, sending the task name and brief description of the to-do task to the designated person who did not attend the meeting via SMS and / or email.

[0075] Referring to Figure 3, which schematically illustrates a display interface for task assignment according to an exemplary embodiment of the present disclosure. As shown in Figure 3, a task assignment interface 200 can be displayed on the conference screen, which may include a list of attendees 210, a task button 220, a task content input text box 230, a task list 240, and a task assignment result display box 250.

[0076] The task button 220 can be used to trigger the process of identifying tasks that need to be performed by employees from meeting data. For example, the displayed task button 220 can be pressed by touch with a finger or stylus, thereby triggering the task recognition function. Subsequent meeting data, such as speech, can be converted into text data and then processed by natural language processing (NLP) technology (e.g., analyzing keywords or phrases in the text, such as "task," "task assignment," etc.) to accurately identify the subject assigning the task. Furthermore, in some embodiments, meeting speeches can be monitored in real time, and the speech content can be converted into text by a speech recognition system. NLP technology can then be used to analyze keywords or phrases in the text, such as "task," "task assignment," etc., to accurately identify the subject assigning the task. This method not only improves the accuracy of meeting records but also helps participants quickly capture key information.

[0077] The task content input text box 230 can be used to manually input task content, thereby establishing tasks that need to be performed by employees. Furthermore, in some embodiments, the input content in the task content input text box 230 can also be achieved by recognizing speech and converting it into text.

[0078] Task list 240 is used to display the identified tasks, and the "+" and "-" buttons on the right side of the list can be used to manually add and delete identified tasks, respectively. It should be understood that the embodiment shown in Figure 3 displays three identified tasks; however, fewer or more identified tasks are also possible.

[0079] The task assignment result display box 250 displays the specific information of the pending tasks, namely, the pending tasks and the names of the corresponding task assignees. It should be understood that the pending tasks and corresponding task assignees displayed in the task assignment result display box 250 are the result of a unified compilation of tasks assigned to attendees and non-attendees. The "+" and "-" buttons on the far right of each pending task row can be used to manually add and delete the task assignees corresponding to that pending task, respectively. Furthermore, clicking the name of the task assignee corresponding to a pending task in the task assignment result display box 250 can replace that task assignee with another person. For example, clicking the "+" button generates a command to add a person to the pending task; clicking the "-" button generates a command to delete a person; and clicking the displayed name of the corresponding task assignee generates a command to replace a person. This executes the corresponding personnel addition, deletion, or replacement operations, and then updates the display of the pending task and the name of the corresponding task assignee. Furthermore, in some embodiments, the task allocation display interface shown in FIG3 may also include, for example, corresponding operation buttons, so as to: send all tasks corresponding to the participants to the participants' private meeting screens when the task assignee of the task includes a meeting attendee; and / or, when the task assignee of the task includes a designated person who did not attend the meeting, send the task name and brief description of the task to the designated person who did not attend the meeting via SMS and / or email.

[0080] Therefore, the meeting screen operation method disclosed herein can identify tasks that need to be handled by employees from meeting data, and can intelligently allocate tasks according to the different positions, job levels and experiences of employees in the employee database, which greatly improves meeting efficiency and provides a better meeting experience for participants.

[0081] Referring to Figure 4, which further illustrates details of step 130 in the conference screen operation method 100 shown in Figure 1 according to an exemplary embodiment of the present disclosure. As shown in Figure 4, in this embodiment, step 130 may include steps 131b, 132b, and 133b.

[0082] In step 131b, based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database. The employee database stores the employee data of each participant in a hypergraph format. The employee database may contain employee information, organizational structure, project associations, etc. This database contains rich employee information, such as personal resumes and professional skills; organizational structure information, clearly defining the hierarchy and relationships of each department; and project association information, recording the specific connections between employees and the projects they participate in, providing crucial support for personalized customization.

[0083] In step 132b, content that can be used as meeting minutes is identified from the meeting data.

[0084] In step 133b, the content that can be used as meeting minutes is matched with the personal matching features of each participant to generate private meeting minutes for each participant, and these private meeting minutes are identified as the matching data. In some embodiments, step 133b may include key information extraction and personalization adjustments. Key information extraction includes extracting key information from the meeting, such as main topics, decision points, and task assignments, based on the output of the NLP model and the query results of the Hypergraph database. Personalization adjustments include adjusting the generation logic and display method of the summary according to the user's preferences or the type of meeting (such as a decision-making meeting, progress report, etc.). Thus, private meeting minutes for each participant can be generated.

[0085] The employee database in step 131b can also be constructed and managed using HGNN, the identification of meeting data in step 132b can also be achieved using a pre-trained identification model, and the matching operation in step 133b can also be achieved using a pre-trained matching model. Therefore, these will not be elaborated further here.

[0086] In an embodiment where private meeting minutes are identified as matching data, step 140 may include sending the private meeting minutes to the corresponding participant's private meeting screen. This allows the corresponding private meeting minutes to be displayed on the private meeting screen. In some embodiments, step 140 may further include modifying the participant's private meeting minutes in response to receiving a command to modify them. For example, when a participant believes the generated private meeting minutes need modification, they can use interactive buttons on the private meeting screen to generate a command to modify the minutes. The meeting screen operation method can then check and modify the content related to the command (e.g., background measures can be taken, such as replaying audio or video recordings of the relevant time period, allowing participants to carefully review the information).

[0087] Therefore, the meeting screen operation method disclosed herein can match meeting content with the characteristics of the employee database and customize private meeting minutes during the meeting, especially in discussion sessions where participants need to interact with the moderator. It can not only automatically identify key information in the meeting content, but also combine relationship information in the employee database to provide participants with more comprehensive and in-depth meeting analysis and summaries, thereby better adapting to each participant, greatly improving meeting efficiency and enhancing the meeting experience.

[0088] Referring to Figure 5, which further illustrates details of step 130 in the conference screen operation method 100 shown in Figure 1 according to an exemplary embodiment of the present disclosure. As shown in Figure 5, in this embodiment, step 130 may include steps 131c, 132c, and 133c:

[0089] In step 131c, based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format;

[0090] In step 132c, content that can be displayed in the conference display interface is identified from the conference data;

[0091] In step 133c, the content that can be displayed as a meeting display interface is matched with the personal matching characteristics of each participant to generate private meeting display content for each participant, and the private meeting display content is determined as the matching data.

[0092] In an embodiment where the private meeting display content is determined as matching data, step 140 may include sending the private meeting display interface to the private meeting screen of the corresponding participant. This allows the corresponding private meeting content to be displayed on the participant's private meeting screen. In this scenario, there is typically a main meeting screen and multiple private meeting screens. The main meeting screen can be projected by the meeting host, and each private meeting screen can be associated with a participant.

[0093] Referring to Figure 6, a private meeting screen display interface is schematically illustrated according to an exemplary embodiment of the present disclosure. As shown in Figure 6, the private meeting screen display interface 300 may include: private historical meeting minutes 310, relevant personnel 320, private meeting minutes 330, interactive buttons 340, and a main meeting screen display interface 350. According to the meeting screen operation method of the present disclosure, the private meeting display content of each participant (e.g., private historical meeting minutes 310, relevant personnel 320, and private meeting minutes 330 shown in Figure 6) can be determined based on the display content identified from meeting data and the personal matching characteristics of each participant, and then the private meeting display content can be sent to the private meeting screen for display.

[0094] Therefore, the meeting screen operation method disclosed herein can match meeting content based on the characteristics of the employee database during the meeting, determine the private meeting display content for each participant, and provide a private meeting display interface, thereby greatly improving the meeting experience.

[0095] Referring to Figure 7, which further illustrates details of step 130 in the conference screen operation method 100 shown in Figure 1, according to an exemplary embodiment of the present disclosure.

[0096] In this embodiment, obtaining meeting data as described in step 120 also includes obtaining meeting-related supporting documents. The collection of supporting documents can come from various sources, such as: pre-meeting preparation materials like meeting notices, agendas, and background information; meeting presentation materials like PowerPoint presentations, charts, and graphs; key data reports like project schedules, financial statements, and market analysis reports; and links to related documents such as historical meeting minutes and detailed documents of relevant projects. The collected supporting documents can also be categorized and indexed. For example, these supporting documents can be categorized as project documents (e.g., design documents, requirements documents, technical documents, etc.), decision records (e.g., meeting resolutions, task assignments, action guidelines, etc.), data reports (e.g., progress reports, financial statements, market analyses, etc.), and reference materials (e.g., industry standards, external research reports, related links, etc.). A unique index or short link can be generated for each document to facilitate quick location and review by participants in the meeting minutes. The index information can include the document name, type, source, and related topics. In some embodiments, different access permissions can be set for collected document attachments based on their sensitivity and the roles of the participants. For example, confidential documents can be accessible only to the project leader and core team members, while general documents can be accessible to all participants. Furthermore, a permission adjustment function can be provided, allowing meeting organizers to adjust permission settings according to actual circumstances.

[0097] As shown in Figure 7, if the acquisition of meeting data described in step 120 also includes acquiring meeting-related document attachments, then step 130 may include steps 131d, 132d, and 133d:

[0098] In step 131d, based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format;

[0099] In step 132d, the comparison features of the document attachments are determined based on the document attachments;

[0100] In step 133d, the data attachment comparison features are matched with the personal matching features of each participant to generate private meeting data for each participant, and the private meeting data is determined as the matching data.

[0101] In some embodiments, successfully matched attachments can be copied to a private document folder specifically created for the participant. To facilitate subsequent management and retrieval, detailed metadata such as filename, file type, file size, creation time, modification time, and match score with the private meeting minutes will be recorded. If a match fails, the document will be skipped without being saved. This ensures that the final private document collection contains only content highly relevant to the participant's private meeting minutes, thereby improving the quality and usability of the materials. Once all attachments have been traversed, evaluated, and processed, the process of customizing private documents is complete. At this point, participants can conveniently access these specially customized attachments in their private document folders. These materials help participants better understand the meeting content, follow up on work tasks, and improve work efficiency.

[0102] Referring to Figure 8, which further illustrates details of step 130 in the conference screen operation method 100 shown in Figure 1 according to an exemplary embodiment of the present disclosure. As shown in Figure 8, in this embodiment, step 130 may include steps 131e and 132e:

[0103] In step 131e, based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format;

[0104] In step 132e, the matching data is determined using a pre-trained matching model based on the meeting data and the individual matching features.

[0105] [Correction 30.05.2025 based on Rule 91] It should be understood that steps 131e and 132e in the embodiment shown in Figure 8, after constructing the employee database and matching model in a suitable manner and training them with the corresponding data, can be used to implement the conference screen operation methods in the various application scenarios shown in Figures 2A to 7, respectively. The employee database and matching model will be described separately below.

[0106] Referring to Figure 9, which illustrates a method for constructing an employee database according to an exemplary embodiment of this disclosure. As mentioned above, the employee database used in the conference screen operation methods described in the various exemplary embodiments of this disclosure can be constructed and managed using a hypergraph neural network. Compared to traditional graph neural networks, hypergraph neural networks can more naturally represent and model high-dimensional complex relationships, such as multiple roles among employees, project collaboration, and complementary skills. Therefore, an employee database constructed based on a hypergraph neural network can better represent and model high-dimensional complex relationships. As shown in Figure 9, the employee database construction method 400 includes steps 410, 420, 430, 440, and 450.

[0107] In step 410, employee data is collected.

[0108] For example, comprehensive basic information about all employees within the company can be collected, including but not limited to name, position, work experience, educational background, and professional skills certificates. In some embodiments, employee data collection may include multi-source heterogeneous data integration and knowledge graph augmentation. Multi-source heterogeneous data integration may include the following: structured data, unstructured data, and dynamic data monitoring. Structured data may include, for example, automatically synchronizing employee files (position / length of service / performance) through the application interface of the human resources system, and obtaining project participation records through the project management system interface. Unstructured data may include, for example, parsing employee weekly reports / project documents using NLP (e.g., extracting skill keywords using Spacy+TextRank); performing fine-grained entity recognition of resume text using the BERT-BiLSTM-CRF model; and collecting technical contribution data through GitHub / Lab platform APIs. Dynamic data monitoring may include, for example, accessing enterprise instant messaging (IM) tools (such as DingTalk / Teams) to record collaboration network graphs. Knowledge graph augmentation can be used to build an industry skills ontology.

[0109] In some embodiments, for specific application scenarios, data related to those scenarios can also be collected during data collection. For example, in a task allocation scenario, historical task allocation data can be collected to understand the matching relationship between tasks and personnel, providing data support for subsequent model training. Detailed information such as the time, type, difficulty, and requirements of each task can be collected. This information helps the model understand the characteristics and needs of the task. Personal information such as the names, departments, positions, skills, and work experience of participants, as well as their recent work arrangements and workload, can be collected. Records of past task allocations can also be collected, including which personnel were assigned which tasks and the results of task completion. These records provide valuable learning samples for the model.

[0110] In step 420, data preprocessing is performed.

[0111] Data preprocessing refers to using technical means to clean, preprocess, transform, and prepare raw text data so that the model can better understand and process it. This removes duplicate, erroneous, or irrelevant information, ensuring the accuracy and integrity of the data. Data preprocessing mainly includes: text cleaning, such as removing special characters and stop words; vocabulary generation and index mapping; text correction, etc. Data preprocessing is a crucial step in building efficient models.

[0112] In step 430, the data is stored in a structured manner.

[0113] Structured data storage includes designing the database architecture and building a hypergraph. Designing the database architecture involves designing database table structures based on data characteristics and requirements, such as employee tables, project tables, and skill tables. Hypergraph construction involves using entities like employees, projects, and skills as nodes, and the complex relationships between them (e.g., employees participating in projects, employees possessing skills related to projects) as hyperedges to build a hypergraph model. As an example, the node types in the constructed hypergraph model could include: employees (attributes: skill vector / load coefficient), tasks (attributes: complexity / urgency), devices (attributes: location / status), etc. Hyperedge design could include: collaboration hyperedges: connecting all members working together to complete a project and related tools; skill combination hyperedges: associating task clusters requiring Python + Spark and incorporating statistical knowledge; and spatiotemporal constraint hyperedges: binding key tasks requiring personnel to be present during specific time periods.

[0114] As an example, the structure of a hypergraph model H is illustrated below:

[0115] In the above text, node represents the set of nodes in the hypergraph model H, and hyperedges represents the set of hyperedges in the hypergraph model, which includes the constructed collaborative hyperedges, skill combination hyperedges, and spatiotemporal constraint hyperedges.

[0116] In step 440, a hypergraph neural network model is constructed.

[0117] Building a hypergraph neural network model (i.e., HGNN model) mainly includes: model selection, feature engineering, and model training.

[0118] First, in the model selection phase, a suitable HGNN model can be chosen based on the specific task, such as HyperGCN or HyperSAGE. These models are specifically designed for processing hypergraph data and can capture the complex relationships between nodes and hyperedges.

[0119] Secondly, feature engineering mainly includes designing appropriate feature representations for nodes and hyperedges. For example, employees' educational background and work experience can be used as node features, while project type and skill requirements can be used as hyperedge features.

[0120] Finally, model training mainly involves training the HGNN model using historical data to learn the complex relationships between nodes and hyperedges. In some embodiments, cross-entropy loss can be used as the loss function. In some embodiments, model hyperparameters, such as learning rate, batch size, and number of iterations, can be adjusted using methods such as grid search, random search, or Bayesian optimization. During training, the model can be trained using labeled data and evaluated on a validation set to monitor model performance and prevent overfitting. Taking the HyperGCN model as an example, this model transforms the hypergraph into a regular graph using clique unrolling and then applies improved graph convolution to learn the relationships between nodes and hyperedges. Furthermore, during training, primary and secondary tasks can be set. The primary task can be employee matching prediction (binary classification), while the secondary task can be hyperedge existence prediction (contrastive learning). Using negative sampling techniques to generate multiple negative samples for each existing positive hyperedge can improve model accuracy and training speed. In some embodiments, dynamic weight allocation and adaptive regularization can also be used to accelerate network training and prevent network collapse.

[0121] In addition, model training also includes model evaluation and optimization, mainly comprising evaluation metrics, error analysis, and model tuning. Evaluation metrics primarily involve selecting appropriate metrics to assess model performance, such as accuracy, recall, and F1 score. Error analysis mainly involves analyzing the model's errors on the validation set, identifying common error types and causes, and optimizing the model accordingly. Model tuning mainly involves adjusting the model structure, hyperparameters, or data preprocessing steps based on the results of error analysis, and retraining the model.

[0122] In step 450, the database interface is designed. This step involves designing the database API interface to facilitate other systems or applications in calling the employee database service.

[0123] The employee database constructed using the above method utilizes a hypergraph neural network for database building and management, thereby enabling a more natural representation and modeling of high-dimensional complex relationships, such as multiple roles among employees, project collaborations, and complementary skills. Therefore, an employee database built based on a hypergraph neural network is better suited for representing and modeling high-dimensional complex relationships.

[0124] Referring to Figure 10, which illustrates a method for constructing a matching model according to an exemplary embodiment of the present disclosure. As shown in Figure 10, the matching model construction method 500 may include steps 510, 520, 530, 540, and 550.

[0125] In step 510, training data is collected.

[0126] Training data collection refers to the process of gathering meeting data, including relevant information, according to application needs. Meeting data may include video, audio, and / or text data from meeting recordings. It should be understood that the collected training data should contain corresponding information for different application scenarios.

[0127] [Corrected according to Rule 91, May 2025] Taking the task allocation application scenarios shown in Figures 2A and 2B as examples, the collected training data should contain clear information about the task subject and task content so that it can be used to train the matching model for task allocation. For example, historical task allocation data can be collected to understand the matching relationship between tasks and personnel, providing data support for subsequent model training. Detailed information such as the time, type, difficulty, and requirements of each task can be collected. This information helps the model understand the characteristics and needs of the task. Personal information such as the names, departments, positions, skills, and work experience of participants, as well as their recent work arrangements and workload, can be collected. Records of past task allocations can also be collected, including which personnel were assigned to which tasks and the results of task completion. These records provide valuable learning samples for the model.

[0128] For the application scenario of generating private meeting minutes as shown in Figure 4, the collected training data should contain explicit meeting records, and these records should include content relevant to individual employees. For the application scenario of generating private meeting display content as shown in Figure 5, the collected training data should include the display content of both the main meeting screen and the employee's private meeting screen. Therefore, the training data used for the matching model is not limited to specific content or formats, but can be selected according to the needs of the application scenario, meaning that the resulting matching model, after deployment, can be applied to the required application scenario.

[0129] In step 520, training data preprocessing is performed.

[0130] [Corrected under Rule 91 30.05.2025]Training data preprocessing may include data annotation, data cleaning and data vectorization. Data annotation refers to manually annotating conference data, marking content corresponding to the matched application scenario in the conference data. Also taking the task assignment application scenario shown in Figures 2A and 2B as an example, data annotation may target entities (such as person names, organization names, etc.) and task content (that is, specific discussed matters or action points) involved in corresponding conference data. Data annotation is usually a time-consuming but critical step. Data cleaning refers to cleaning data to remove noise, such as irrelevant conversations, repeated content, etc., and ensuring the consistency and accuracy of the data. For example, data cleaning may include: performing word segmentation processing according to the language used (special word segmentation processing may be required for Chinese); removing stop words (for example, removing words that are common in the text but do not contribute substantially to understanding entities and task content, such as "de", "le", etc.). Furthermore, in some embodiments, data cleaning may further include entity recognition, that is: a pre-trained entity recognition model can be used to assist in annotating entities, such as person names, organization names, etc. Data vectorization refers to converting data into a numerical form that can be understood by machines, for example, a long vector form. By way of example, both video data and audio data can be processed through denoising, framing, sampling, feature extraction, principal component analysis and other processes to generate corresponding long vectors. Text data can be segmented according to a certain length, and then feature extraction can be performed on the segmented text data to generate text data feature vectors. Existing text vectorization methods may include, for example, bag-of-words model, TF-IDF, word embedding (such as Word2Vec, GloVe) or more advanced context embedding (such as BERT), etc.

[0131] In step 530, model selection is performed.

[0132] In the model selection stage, a suitable model can be selected according to the specific task. For example, when the task involves identifying specific segments (entities and task content) in text, a sequence labeling model such as BiLSTM-CRF can be used; considering that the task involves two sub-tasks (identifying entities and identifying task content), a multi-task learning framework can be considered to optimize these two tasks simultaneously. Furthermore, pre-trained NLP models (such as BERT, RoBERTa, GPT, etc.) can also be used for fine-tuning. These models have been trained on a large amount of text and already have powerful text representation capabilities.

[0133] In step 540, model training, evaluation and optimization are performed.

[0134] Model training mainly includes: designing the loss function, hyperparameter tuning, and training and validation. Designing the loss function can involve designing an appropriate loss function based on task requirements; for example, cross-entropy loss is typically used for sequence labeling tasks. Hyperparameter tuning can involve adjusting model hyperparameters, such as learning rate, batch size, and number of iterations, using methods like grid search, random search, or Bayesian optimization. Training and validation can involve training the model using labeled data and evaluating it on a validation set to monitor model performance and prevent overfitting.

[0135] Evaluation and optimization mainly include: evaluation metrics, error analysis, and iterative optimization. Evaluation metrics refer to selecting appropriate metrics to assess model performance, such as accuracy, recall, and F1 score. Error analysis involves analyzing the model's errors on the validation set, identifying common error types and causes, and optimizing the model accordingly. Iterative optimization involves adjusting the model structure, hyperparameters, or data preprocessing steps based on the results of error analysis, and retraining the model.

[0136] [Corrected according to Rule 91, May 2025] Similarly, model training, evaluation, and optimization can be implemented for different application scenarios. Taking the task allocation application scenario shown in Figures 2A and 2B as an example, by training the model, it can automatically learn the matching relationship between tasks and personnel, and predict which personnel should be assigned to new tasks. If for the application scenario of generating private meeting minutes shown in Figure 4, by training the model, it can automatically learn the matching relationship between meeting data and personnel, identify the meeting content corresponding to each participant, and thus accurately generate private meeting minutes.

[0137] In step 550, the model is deployed.

[0138] Therefore, the matching model construction method of this disclosure can be based on existing meeting content association matching models and customized training using private meeting data, thereby improving the ability to identify specific company cultures, terminology, and styles. Furthermore, for application scenarios requiring rapid operation, the matching model construction method of this disclosure can optimize the model's inference speed, such as by using a lighter model architecture or performing model pruning, thereby achieving real-time optimization.

[0139] Referring again to Figure 8, in some embodiments, the matching model according to this disclosure can utilize similarity calculation to implement the matching algorithm. For example, the cosine similarity algorithm can be used. Specifically, long text A can be generated based on employee data in hypergraph form obtained from an employee database (which may include identity identifiers, organizational levels, responsible projects, etc.). Next, long text B can be generated based on meeting data. Then, long texts A and B are respectively converted into vector representations of equal length, i.e., feature vectors. Feature vector It should be understood that, as mentioned above, if the meeting data includes video and / or audio data, then the video and / or audio data can also be used to generate corresponding feature vectors using the methods described above. In generating feature vectors... and eigenvectors Then, the cosine similarity between the two can be calculated using the following formula:

[0140] Where n is an integer greater than or equal to 1. When the calculated cosine similarity is greater than a preset similarity threshold (for example, the threshold can be 0.5), it can be determined that the two feature vectors are similar, thereby determining that the personal matching features of the participants match the conference data.

[0141] Referring to Figure 11, a block diagram schematically illustrates a conference screen control device according to an exemplary embodiment of the present disclosure. As shown in Figure 11, the conference screen control device 600 may include: a participant identity acquisition module 610, a conference data acquisition module 620, a matching data determination module 630, and an adaptation operation execution module 640. The participant identity acquisition module 610 may be configured to acquire the identity information of each participant. The conference data acquisition module 620 may be configured to acquire conference data. The matching data determination module 630 may be configured to determine matching data corresponding to each participant from the conference data based on the identity information of each participant. The adaptation operation execution module 640 may be configured to execute a corresponding operation based on the matching data. In some embodiments, the conference screen control device 600 may be arranged within a conference screen for controlling corresponding operations of the conference screen. In other embodiments, the conference screen control device 600 may be a separate device that can be arranged independently of the conference screen and communicatively connected to the conference screen, thereby enabling corresponding operations on the conference screen.

[0142] [Correction 30.05.2025 according to Details 91] In some embodiments, the matching data determination module 630 may be further configured to: obtain the personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; and determine the matching data using a pre-trained matching model based on the meeting data and the personal matching features. Thus, after constructing the employee database and matching model in a suitable manner and training them with the corresponding data, the conference screen control device 600 can be used to implement the steps of the conference screen operation method taught in this disclosure in various application scenarios shown in Figures 2A to 7.

[0143] Referring to Figure 12, which further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of this disclosure. As shown in Figure 12, the matching data determination module 630 included in the conference screen control device 600 may include: a personal matching feature acquisition module 631, a task identification module 632, and a task allocation module 633. The personal matching feature acquisition module 631 may be configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The task identification module 632 is configured to: identify at least one task that needs to be performed by an employee from the conference data. The task allocation module 633 may be configured to: match each of the at least one task with the personal matching features of each participant, and generate assigned tasks for participants when a match is successful, wherein each assigned task corresponds to at least one participant as the task bearer, and the assigned task is determined as the matching data. Therefore, the conference screen control device according to this disclosure can identify tasks that need to be handled by employees from the conference data, and can intelligently allocate tasks according to the different positions, ranks and experiences of the participants, which greatly improves the efficiency of the conference and provides a better conference experience for the participants.

[0144] In some embodiments, the personal matching feature acquisition module 631 can be configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format; and acquire personal matching features of designated non-participating personnel from the employee database. Furthermore, the task allocation module 633 can be configured to: match each of the at least one task with the personal matching features of each participant; if a match is successful, generate assigned tasks for the participants, wherein each assigned task corresponds to at least one participant as the task undertaker, and the assigned tasks are determined as the matching data; and match each of the at least one task with the personal matching features of the designated non-participating personnel; if a match is successful, generate assigned tasks for non-participating personnel, wherein each assigned task corresponds to the designated non-participating personnel as the task undertaker, and the assigned tasks are also determined as the matching data. Therefore, the conference screen control device according to this disclosure can identify tasks that need to be processed by employees from the conference data and distribute them across the entire scope of the employee database (including attendees and non-attendees), thereby improving the flexibility and efficiency of task allocation.

[0145] Furthermore, in some embodiments, the employee database may also include outsourced personnel data stored in a hypergraph format. That is, the employee database includes not only the employee data of the company's own employees but also the employee data of outsourced personnel with whom the company has a collaborative relationship. In such a scenario, the attendees and / or designated non-attending personnel in the embodiments described above may include outsourced personnel. This further improves the flexibility and efficiency of task allocation.

[0146] Referring to Figure 13, which further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of this disclosure. As shown in Figure 13, the matching data determination module 630 included in the conference screen control device 600 may include: a personal matching feature acquisition module 631, a meeting minutes determination module 634, and a private meeting minutes generation module 635. The personal matching feature acquisition module 631 may be configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The meeting minutes determination module 634 may be configured to: identify content that can be used as meeting minutes from the meeting data. The private meeting minutes generation module 635 may be configured to: match the content that can be used as meeting minutes with the personal matching features of each participant to generate private meeting minutes for each participant, and the private meeting minutes are determined as the matching data. Therefore, the conference screen control device disclosed herein can match the conference content with the characteristics of the employee database and customize private meeting minutes during the conference, especially in discussion sessions where everyone needs to communicate with the host, thereby better adapting to each participant, greatly improving conference efficiency and enhancing the participant experience.

[0147] Referring to Figure 14, which further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of this disclosure. As shown in Figure 14, the matching data determination module 630 included in the conference screen control device 600 may include: a personal matching feature acquisition module 631, a conference display interface determination module 636, and a private conference display interface generation module 637. The personal matching feature acquisition module 631 may be configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The conference display interface determination module 636 may be configured to: determine the conference display interface from the conference data. The private conference display interface generation module 637 may be configured to: match the conference display interface with the personal matching features of each participant to generate a private conference display interface for each participant, and the private conference display interface is determined as the matching data. Therefore, the conference screen control device according to this disclosure can match the conference content with the characteristics of the employee database during the conference, determine the private conference display content for each participant, and provide a private conference display interface, thereby greatly improving the conference experience.

[0148] Referring to Figure 15, which further illustrates details of the conference screen control device shown in Figure 11 according to an exemplary embodiment of this disclosure. As shown in Figure 15, the matching data determination module 630 included in the conference screen control device 600 may include: a personal matching feature acquisition module 631, a document attachment comparison feature determination module 638, and a private meeting data determination module 639. The personal matching feature acquisition module 631 may be configured to: acquire personal matching features of each participant from an employee database based on the identity information of each participant, wherein the employee database stores employee data of each participant in a hypergraph format. The document attachment comparison feature determination module 638 may be configured to: determine document attachment comparison features based on the acquired document attachments. The private meeting data determination module 639 may be configured to: match the document attachment comparison features with the personal matching features of each participant to generate private meeting data for each participant, and the private meeting data is determined as the matching data. Therefore, the conference screen control device disclosed herein can ensure that the final generated collection of private documents contains only content highly relevant to the participants' private meeting minutes, thereby improving the quality and usability of the materials. Once all document attachments have been traversed, evaluated, and processed, the process of customizing private documents is complete. At this point, participants can conveniently access these specially customized document attachments in their own private document folders. These materials help participants better understand the meeting content, follow up on work tasks, and improve work efficiency.

[0149] Referring to Figure 16, a conference screen is schematically illustrated in block diagram form according to an exemplary embodiment of the present disclosure. As shown in Figure 16, the conference screen 700 may include a display device 710 and a conference screen control device 720. The display device 710 may be any suitable device capable of displaying information, including but not limited to a display screen, a projection device, etc. The conference screen control device 720 may be any of the various conference screen control devices described in detail above in conjunction with Figures 11 to 15.

[0150] It should be understood that the conference screen control device and its various modules taught in the embodiments of this disclosure can be implemented in hardware, software, firmware, or any combination thereof, thereby realizing the steps of the conference screen operation method taught in the content shown in Figures 1 to 8 of this disclosure. Furthermore, it should be understood that if implemented in software, the steps of the above-described conference screen operation method can be stored as one or more instructions or code on or transmitted via a computer-readable medium, and can be executed by a hardware-based processor. For example, the above-described conference screen operation method can be implemented by a computing device that may include a processor and a memory storing executable instructions, which, when executed by the processor, implement the steps of the above-described conference screen operation method.

[0151] Referring to FIG17, a computer device according to an exemplary embodiment of the present disclosure is schematically illustrated in block diagram form. As shown in FIG17, the computer device 800 can be used in the various exemplary embodiments described in the present disclosure, and can implement the steps in the conference screen operation method described in the various exemplary embodiments of the present disclosure.

[0152] Computer device 800 may include at least one processor 802, memory 804, multiple communication interfaces 806, display device 808, other input / output (I / O) devices 810, and one or more mass storage devices 812 that are capable of communicating with each other, such as via system bus 814 or other suitable means.

[0153] Processor 802 may be a single processing unit or multiple processing units, and all processing units may include single or multiple computing units or multiple cores. Processor 802 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, processor 802 may be configured to acquire and execute computer-readable instructions stored in memory 804, mass storage device 812, or other computer-readable storage media, such as program code of operating system 816, program code of application program 818, program code of other program 820, etc.

[0154] Memory 804 and mass storage device 812 are examples of computer-readable storage media for storing instructions that can be executed by processor 802 to perform the various functions described above. For example, memory 804 can generally include both volatile and non-volatile memory (e.g., RAM, ROM, etc.). Furthermore, mass storage device 812 can generally include hard disk drives, solid-state drives, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CDs, DVDs), storage arrays, network-attached storage, storage area networks, etc. Both memory 804 and mass storage device 812 can be collectively referred to herein as computer-readable memory or computer-readable storage media, and can be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer-executable code, which can be executed by processor 802 as a specific machine configured to perform the operations and functions described in the various exemplary embodiments of this application.

[0155] Multiple program modules may be stored on mass storage device 812. These program modules may include operating system 816, one or more application programs 818, other programs 820, and program data 822, and they may be executed by processor 802. Examples of such application programs or program modules may include, for example, computer program logic (e.g., computer-executable code or instructions) for implementing the various components / modules / functions described above (e.g., see Figures 11 to 15).

[0156] Although illustrated in Figure 17 as stored in memory 804 of computer device 800, the various modules described above, or portions thereof, may be implemented using any form of computer-readable storage medium accessible by computer device 800. Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, Digital Universal Disc (DVD), or other optical storage devices, magnetic cassettes, magnetic tapes, disk storage devices or other magnetic storage devices, or any other non-transfer medium that can be used to store information for access by a computing device.

[0157] The computer device 800 may also include one or more communication interfaces 806 for exchanging data with other devices, such as via a network, direct connection, etc. The communication interface 806 can facilitate communication across various network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. The communication interface 806 can also provide communication with external storage devices (not shown), such as storage arrays, network-attached storage, storage area networks, etc.

[0158] In some examples, computer device 800 may also include a display device 808, such as a monitor, for displaying information and images. Other I / O devices 810 may be devices that receive various inputs from a target object and provide various outputs to the target object, including but not limited to touch input devices, gesture input devices, cameras, keyboards, remote controls, mice, printers, audio input / output devices, and so on.

[0159] This disclosure also relates to a computer-readable storage medium configured to store computer-executable instructions configured to, when executed on a processor, cause the processor to perform various steps of the conference screen operation method according to the exemplary embodiments of this application. It should be understood that the computer-readable storage medium should be any suitable storage medium, including, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD), or other optical storage devices, magnetic cassettes, magnetic tapes, disk storage devices or other magnetic storage devices, or semiconductor media (e.g., solid-state drives), or any other non-transmission medium that can be used to store information for access by a computing device. This disclosure does not limit the scope of the computer-readable storage medium.

[0160] Furthermore, this disclosure also relates to a computer program product comprising computer-executable instructions configured to, when executed on a processor, cause the processor to perform various steps of the conference screen operation method according to exemplary embodiments of this disclosure. Specifically, the computer program product may include one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to exemplary embodiments of this disclosure is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or may be transmitted from one computer-readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0161] The terminology used in this disclosure is for the purpose of describing embodiments thereof and is not intended to limit the disclosure. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and “including,” as used herein, refer to the presence of the stated feature but do not exclude the presence of one or more other features or the addition of one or more other features. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items. It will be understood that although the terms “first,” “second,” “third,” etc., may be used in this disclosure to describe various features, these features should not be limited by these terms. These terms are used only to distinguish one feature from another.

[0162] Unless otherwise defined, all terms used in this disclosure (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. It should also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the relevant field and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined in this disclosure.

[0163] In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example that is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction or violation of technical principles, those skilled in the art can combine and integrate the different embodiments or examples and features described in this specification, or omit some technical features from the different embodiments or examples described in this specification, and embodiments or examples obtained based on such combinations, arrangements, or omissions are also considered to fall within the scope of this disclosure.

[0164] The methods described in this disclosure include one or more steps or actions. These method steps and / or actions do not necessarily have to be performed in the order described in this disclosure, but can be performed in different orders, such as simultaneously or in reverse order, as long as this does not contradict the principles of the technical solutions described in this disclosure. Furthermore, depending on actual needs, the steps or actions in the methods described in this disclosure can be replaced with different steps or actions, or additional steps or actions may be included.

[0165] Although this disclosure has been described in detail with reference to some exemplary embodiments, it is not limited to the particular forms described herein. Rather, the scope of this disclosure is defined only by the appended claims.

Claims

1. A method for operating a conference screen, characterized in that, include: Obtain the identity information of each participant; Obtain meeting data; Based on the identity information of each participant, matching data corresponding to each participant is determined from the meeting data; Perform the corresponding operation based on the matched data.

2. The conference screen operation method according to claim 1, characterized in that, The step of determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: Based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format. Identify at least one task that needs to be performed by an employee from the meeting data; Each of the at least one task is matched with the personal matching features of each participant. If a match is successful, a participant-assigned task is generated, wherein each participant-assigned task corresponds to at least one participant who is the task bearer, and the participant-assigned task is determined as the matching data.

3. The conference screen operation method according to claim 2, characterized in that, Also includes: Retrieve the personal matching characteristics of the specified personnel who did not attend the meeting from the employee database; Each of the at least one task is matched with the personal matching features of the designated person who did not attend the meeting. If the match is successful, an assigned task for the non-attendee person is generated. Each assigned task for the non-attendee person corresponds to the designated person who is the task bearer, and the assigned task for the non-attendee person is also determined as the matching data.

4. The conference screen operation method according to claim 3, characterized in that, The employee database also includes outsourced personnel data stored in Hypergraph format, and the attendees and / or the designated non-attendees include the outsourced personnel.

5. The conference screen operation method according to claim 4, characterized in that, The operation performed based on the matching data includes: The tasks assigned to the attendees and the tasks assigned to the non-attendees are compiled into a set of tasks to be done, and each task to be done corresponds to at least one person in charge of the task. The pending tasks and the names of the people responsible for those tasks are displayed on the conference screen.

6. The conference screen operation method according to claim 5, characterized in that, The operation based on the matching data further includes: In response to receiving the command to add personnel for the pending task, the personnel to be added are matched with the pending task. In response to the personnel who received the pending task's deletion command, the personnel responsible for the task to be deleted are no longer associated with the pending task; In response to receiving the personnel replacement command for the pending task, the task assignee to be replaced is replaced with the task assignee specified in the personnel replacement command; The update displays the pending tasks and the name of the person responsible for each task.

7. The conference screen operation method according to claim 4, characterized in that, The operation performed based on the matching data includes: If the person in charge of the task to be done includes a participant, all tasks to be done corresponding to the participant will be sent to the participant's private meeting screen.

8. The conference screen operation method according to claim 4, characterized in that, The operation performed based on the matching data includes: If the person in charge of the task to be done includes a designated person who did not attend the meeting, the task name and brief description of the task to be done shall be sent to the designated person who did not attend the meeting via SMS and / or email.

9. The conference screen operation method according to claim 1, characterized in that, The step of determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: Based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format. Identify content that can be used as meeting minutes from the aforementioned meeting data; The content that can be used as meeting minutes is matched with the personal matching characteristics of each participant to generate a private meeting minutes for each participant, and the private meeting minutes are identified as the matching data.

10. The conference screen operation method according to claim 9, characterized in that, The operation performed based on the matching data includes: Send the private meeting minutes to the corresponding participants' private meeting screens.

11. The conference screen operation method according to claim 9, characterized in that, The operation based on the matching data further includes: In response to receiving an order to modify the private meeting minutes of a participant, the private meeting minutes of the participant are modified.

12. The conference screen operation method according to claim 1, characterized in that, The step of determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: Based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format. Identify content that can be displayed in the meeting display interface from the meeting data; The content that can be displayed as a meeting display interface is matched with the personal matching characteristics of each participant to generate private meeting display content for each participant, and the private meeting display content is determined as the matching data.

13. The conference screen operation method according to claim 12, characterized in that, The operation performed based on the matching data includes: Send the private meeting display interface to the private meeting screen of the corresponding participant.

14. The conference screen operation method according to claim 1, characterized in that: The acquisition of meeting data includes: acquiring meeting-related documents and attachments; The step of determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: Based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format. Based on the aforementioned document attachments, determine the document attachment comparison characteristics; The document attachment comparison features are matched with the personal matching features of each participant to generate private meeting materials for each participant, and the private meeting materials are identified as the matching data.

15. The conference screen operation method according to claim 1, characterized in that, The step of determining the matching data corresponding to each participant from the meeting data based on the identity information of each participant includes: Based on the identity information of each participant, the personal matching features of each participant are obtained from the employee database, wherein the employee database stores the employee data of each participant in a hypergraph format. Based on the meeting data and the individual matching features, the matching data is determined using a pre-trained matching model.

16. A conference screen control device, characterized in that, include: The participant identification module is configured to: obtain the identity information of each participant. The meeting data acquisition module is configured to acquire meeting data. The matching data determination module is configured to: determine matching data corresponding to each participant from the meeting data based on the identity information of each participant; The adaptation operation execution module is configured to perform the corresponding operation based on the matching data.

17. The conference screen control device according to claim 16, characterized in that, The matching data determination module includes: The personal matching feature acquisition module is configured to: acquire the personal matching features of each participant from the employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; A task identification module is configured to identify at least one task that needs to be performed by an employee from the meeting data; The task allocation module is configured to: match each of the at least one task with the personal matching features of each participant; and generate the assigned tasks for the participants if the matching is successful. Each assigned task corresponds to at least one participant who is the task bearer, and the assigned tasks are determined as the matching data.

18. The conference screen control device according to claim 16, characterized in that, The matching data determination module includes: The personal matching feature acquisition module is configured to: acquire the personal matching features of each participant from the employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; The meeting minutes determination module is configured to: identify content from the meeting data that can be used as meeting minutes; A private meeting minutes generation module is configured to: match the content that can be used as meeting minutes with the personal matching characteristics of each participant to generate private meeting minutes for each participant, and the private meeting minutes are identified as the matching data.

19. The conference screen control device according to claim 16, characterized in that, The matching data determination module includes: The personal matching feature acquisition module is configured to: acquire the personal matching features of each participant from the employee database based on the identity information of each participant, wherein the employee database stores the employee data of each participant in a hypergraph format; A meeting display interface determination module is configured to determine the meeting display interface from the meeting data. A private meeting display interface generation module is configured to: match the meeting display interface with the personal matching characteristics of each participant to generate a private meeting display interface for each participant, and the private meeting display interface is determined as the matching data.

20. A conference screen, characterized in that, The conference screen includes a conference screen control device according to any one of claims 16 to 19.

21. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the conference screen operation method according to any one of claims 1 to 15.

22. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the conference screen operation method according to any one of claims 1 to 15.

23. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the conference screen operation method according to any one of claims 1 to 15.

Images