Conference opinion display method, device and storage medium

Abstract

The present invention discloses a method, device, and storage medium for displaying conference opinions. The method comprises: collecting user opinions expressed during a video conference, classifying the opinions, and displaying the classified opinions. The present invention improves the discussion efficiency of video conferences and enhances the user experience of video conferences.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a conference viewpoint display method, device and storage medium. Background Art

[0002] Video conferencing has become a common way of working. When multiple users hold a video conference for a discussion, a large number of users may turn on their cameras and microphones at the same time. Participants are unaware of the content or opinions expressed by other users. In existing video conferences, discussions during the video conference are not recorded, resulting in low discussion efficiency and affecting user experience. Summary of the Invention

[0003] The main purpose of the present invention is to provide a conference viewpoint display method, device and storage medium, aiming to solve the problem of how to improve the discussion efficiency of video conferences.

[0004] To achieve the above-mentioned object, the present invention provides a method for displaying conference opinions, which comprises the following steps:

[0005] Collecting users' opinions during the video conference and classifying the opinions;

[0006] Display the categorized opinions.

[0007] Optionally, the step of displaying the classified opinions further includes the following:

[0008] Display the opinions expressed directly in the opinion area of ​​its category;

[0009] Upon receiving a speech opinion display instruction, displaying the speech opinion in the opinion area of ​​its category;

[0010] The user information associated with the speech opinion is directly displayed in the opinion display area of ​​the opinion area where the category is located.

[0011] Optionally, the step of directly displaying the user information associated with the speech opinion in the opinion display area of ​​the opinion area where the category of the user information is located includes:

[0012] If a trigger instruction of the opinion area is detected, the video frame of the user corresponding to the corresponding category of speech opinion is displayed in the opinion display area, and the user information includes the video frame;

[0013] The video frames corresponding to the same viewpoint are spliced ​​in a preset display order and have the same identifier.

[0014] Optionally, the step of displaying the classified speech opinions includes:

[0015] If there is a viewpoint area corresponding to the category of the speech opinion, the speech opinion is displayed in the viewpoint area of ​​the category;

[0016] If there is no viewpoint area corresponding to the category of the opinion, then create a new viewpoint area corresponding to the category of the opinion, and display the opinion in the new viewpoint area;

[0017] After the step of displaying the classified opinions, the method further includes:

[0018] If the category of the speech opinion changes, the opinion area of ​​the opinion category before the change will be grayed out, the opinion area where the changed speech opinion is located will be determined, and the speech opinion will be displayed in the opinion area where its category is located.

[0019] Optionally, the step of classifying the speech opinions includes:

[0020] If the target opinion is found in the opinion list corresponding to the opinion area according to the opinion object and subject of the opinion, the opinion features of the opinion are obtained, which include sentiment polarity, content attribute features and other attribute features;

[0021] Matching the speech opinion with the target opinion based on the opinion feature to determine the degree of matching between the opinion and the target opinion;

[0022] If the matching degree is less than a preset degree threshold, it is determined that the speech viewpoint is classified as a sub-viewpoint of the target viewpoint.

[0023] Optionally, the step of collecting the user's speech opinions during the video conference includes:

[0024] During the video conference, the user's voice signal is acquired and semantic recognition is performed to obtain the text content;

[0025] Determining the opinion object and opinion features based on the text content, wherein the opinion features include sentiment polarity, content attribute features, and other attribute features;

[0026] The speech opinion is determined according to the opinion object and the opinion characteristics.

[0027] To achieve the above-mentioned object, the present invention provides a method for displaying conference opinions, which comprises the following steps:

[0028] Obtain each user's opinions during the video conference;

[0029] Classifying the opinions and adding them to a list of opinions according to the categories of the opinions;

[0030] Determine the speech opinions to be displayed in the opinion area in the opinion list, and send the speech opinions to be displayed in the opinion area to the terminal device.

[0031] Optionally, after the step of adding the speech opinions to the opinion list according to the category of the speech opinions, the method further includes:

[0032] Determining the support level of the opinion expressed in the speech based on the number of occurrences of the opinion expressed in the speech;

[0033] The opinion to be displayed in the opinion area is determined according to the support level.

[0034] To achieve the above-mentioned object, the present invention further provides a conference opinion display device, comprising:

[0035] A collection module is used to collect the opinions expressed by users during a video conference and classify the opinions expressed;

[0036] The display module is used to display the classified speech opinions and the corresponding user information.

[0037] To achieve the above-mentioned object, the present invention further provides a conference opinion display device, comprising:

[0038] The acquisition module is used to obtain the opinions of each user during the video conference;

[0039] A classification module, configured to classify the speech opinions and add the speech opinions to a viewpoint list according to the categories of the speech opinions;

[0040] The determination module is configured to determine the speech opinions to be displayed in the opinion area in the opinion list, and send the speech opinions to be displayed in the opinion area to the terminal device.

[0041] To achieve the above-mentioned purpose, the present invention also provides a conference opinion display device, which includes a memory, a processor, and a conference opinion display program stored in the memory and executable on the processor. When the conference opinion display program is executed by the processor, it implements the various steps of the conference opinion display method described above.

[0042] To achieve the above objectives, the present invention also provides a computer-readable storage medium, which stores a conference opinion display program. When the conference opinion display program is executed by a processor, it implements the various steps of the conference opinion display method described above.

[0043] The present invention provides a conference opinion display method, device and storage medium, which collect the speech opinions of users during a video conference and classify the speech opinions; display the classified speech opinions and the corresponding user information, so as to facilitate users to view and summarize the current conference discussion, avoid repeatedly raising the same speech opinions in the video conference, improve the discussion efficiency of the video conference, and enhance the user experience of the video conference. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the hardware structure of a conference opinion display device according to an embodiment of the present invention;

[0045] Figure 2 This is a flow chart of a first embodiment of a method for displaying conference opinions according to the present invention;

[0046] Figure 3 A schematic diagram of the viewpoint area and the viewpoint display area in the conference viewpoint display method of the present invention;

[0047] Figure 4 A schematic diagram of the viewpoint area and the viewpoint display area in the conference viewpoint display method of the present invention;

[0048] Figure 5 A schematic diagram of the viewpoint area and the viewpoint display area in the conference viewpoint display method of the present invention;

[0049] Figure 6 A schematic diagram of a main viewpoint and sub-viewpoints in a viewpoint area in a method for displaying conference viewpoints of the present invention;

[0050] Figure 7 This is a detailed flowchart of step S20 of the second embodiment of the method for displaying conference opinions of the present invention;

[0051] Figure 8 This is a detailed flowchart of step S10 of the third embodiment of the method for displaying conference opinions of the present invention;

[0052] Figure 9 4 is a detailed flowchart of step S10 of the fourth embodiment of the method for displaying conference opinions of the present invention;

[0053] Figure 10 1 is a flow chart of a fifth embodiment of a method for displaying conference opinions according to the present invention;

[0054] Figure 11 Schematic diagram of the logical structure of the conference opinion display device involved in an embodiment of the present invention;

[0055] Figure 12 This is a schematic diagram of the logical structure of a conference opinion display device according to an embodiment of the present invention.

[0056] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] The main solution of the embodiment of the present invention is: collecting the opinions of users during video conferences and classifying the opinions; displaying the classified opinions to facilitate users to view and summarize the current meeting discussion, avoid repeating the same opinions in video conferences, improve the discussion efficiency of video conferences, and enhance the user experience of video conferences.

[0059] As an implementation solution, the conference viewpoint display device can be Figure 1 shown.

[0060] The embodiment of the present invention relates to a conference viewpoint display device, which includes a processor 101, such as a CPU, a memory 102, and a communication bus 103. The communication bus 103 is used to achieve connection and communication between these components.

[0061] The memory 102 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Figure 1 As shown, the memory 102 as a computer-readable storage medium may include a conference opinion display program; and the processor 101 may be used to call the conference opinion display program stored in the memory 102 and perform the following operations:

[0062] Collecting users' opinions during the video conference and classifying the opinions;

[0063] Display the categorized opinions.

[0064] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0065] Display the opinions expressed directly in the opinion area of ​​its category;

[0066] Upon receiving a speech opinion display instruction, displaying the speech opinion in the opinion area of ​​its category;

[0067] The user information associated with the speech opinion is directly displayed in the opinion display area of ​​the opinion area where the category is located.

[0068] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0069] If a trigger instruction of the opinion area is detected, the video frame of the user corresponding to the corresponding category of speech opinion is displayed in the opinion display area, and the user information includes the video frame;

[0070] The video frames corresponding to the same viewpoint are spliced ​​in a preset display order and have the same identifier.

[0071] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0072] If there is a viewpoint area corresponding to the category of the speech opinion, the speech opinion is displayed in the viewpoint area of ​​the category;

[0073] If there is no viewpoint area corresponding to the category of the opinion, then create a new viewpoint area corresponding to the category of the opinion, and display the opinion in the new viewpoint area;

[0074] After the step of displaying the classified opinions, the method further includes:

[0075] If the category of the speech opinion changes, the opinion area of ​​the opinion category before the change will be grayed out, the opinion area where the changed speech opinion is located will be determined, and the speech opinion will be displayed in the opinion area where its category is located.

[0076] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0077] If the target opinion is found in the opinion list corresponding to the opinion area according to the opinion object and subject of the opinion, the opinion features of the opinion are obtained, which include sentiment polarity, content attribute features and other attribute features;

[0078] Matching the speech opinion with the target opinion based on the opinion feature to determine the degree of matching between the opinion and the target opinion;

[0079] If the matching degree is less than a preset degree threshold, it is determined that the speech viewpoint is classified as a sub-viewpoint of the target viewpoint.

[0080] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0081] During the video conference, the user's voice signal is acquired and semantic recognition is performed to obtain the text content;

[0082] Determining the opinion object and opinion features based on the text content, wherein the opinion features include sentiment polarity, content attribute features, and other attribute features;

[0083] The speech opinion is determined according to the opinion object and the opinion characteristics.

[0084] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0085] Obtain each user's opinions during the video conference;

[0086] Classifying the opinions and adding them to a list of opinions according to the categories of the opinions;

[0087] Determine the speech opinions to be displayed in the opinion area in the opinion list, and send the speech opinions to be displayed in the opinion area to the terminal device.

[0088] Optionally, the processor 101 may be configured to call a conference viewpoint display program stored in the memory 102 and perform the following operations:

[0089] Determining the support level of the opinion expressed in the speech based on the number of occurrences of the opinion expressed in the speech;

[0090] The opinion to be displayed in the opinion area is determined according to the support level.

[0091] Based on the hardware architecture of the above-mentioned conference opinion display device, an embodiment of the conference opinion display method of the present invention is proposed.

[0092] Reference Figure 2 , Figure 2 This is a first embodiment of the method for displaying conference opinions of the present invention, and the method for displaying conference opinions includes the following steps:

[0093] Step S10: collecting the opinions of users during the video conference and classifying the opinions.

[0094] Optionally, the executor of the conference opinion display method is a terminal device, wherein the terminal device can be a mobile phone, a tablet computer, a personal computer and other devices.

[0095] Optionally, the opinions expressed are generated based on the user's voice signals during the video conference. When multiple people express their opinions, user identification is required. For example, voiceprint recognition can be performed based on the voice signals to determine the user's identity and identify the user who expressed the opinion. Optionally, opinions are associated with an opinion object and a subject. For example, if the opinion object is a project, the subject is the project's feasibility, or if the opinion object is a digital camera, the subject is the camera's functionality.

[0096] Optionally, the opinions expressed are classified, wherein the categories of the opinions expressed can be opinions that are different from an existing target opinion, opinions that are the same as an existing target opinion, or opinions that are sub-opinions of an existing target opinion. The existing target opinion can be an opinion displayed in the opinion area or an opinion stored in the opinion list of the terminal device.

[0097] Step S20: displaying the classified opinions.

[0098] Optionally, for users holding the same viewpoint, a nickname or avatar is determined and assigned the same identifier; for users holding different views, different identifiers are assigned. Determining the user's nickname or avatar can be performed by obtaining the user's name based on the voice packet during the speech. Optionally, if viewpoints a1 and a2 are identical, the identifier corresponding to the video frame of viewpoint a1 is the same as the identifier corresponding to the video frame of viewpoint a2. For example, the identifier in the video frames of viewpoints a1 and a2 is a green dot in the upper right corner.

[0099] Optionally, when a user's speech opinion is formed during the video conference, the specific content of the speech opinion can be expanded by a plus sign, such as Figure 4 and Figure 5 Optionally, the user can click the plus sign to view who currently holds the same viewpoint and what content they support, such as Figure 5 shown.

[0100] Optionally, the user's voice signal is continuously collected for semantic recognition to obtain speech opinions. For repeated speech opinions of different users, the corresponding viewpoint list is adjusted according to the number of times the speech opinion appears, so as to determine the viewpoint with the highest support and display it in the viewpoint area.

[0101] Optionally, step S20 includes: if there is an opinion area corresponding to the category of the speech opinion, the speech opinion is displayed in the opinion area where its category is located; if there is no opinion area corresponding to the category of the speech opinion, a new opinion area corresponding to the opinion category is created, and the speech opinion is displayed in the newly created opinion area.

[0102] Optionally, after step S20, it also includes: if the category of the speech opinion changes, the opinion area of ​​the opinion category before the change will be grayed out, and the video frame in the speech opinion in the opinion display area will be removed, the opinion area where the changed speech opinion is located will be determined, and the speech opinion will be displayed in the opinion area where its category is located.

[0103] Optionally, if the user proposes a new idea to form a sub-viewpoint based on the existing opinion in the opinion area, that is, the main opinion, click the plus sign to view the opinion changes based on this main opinion. The content in the plus sign is as follows: Figure 6 As shown, part a in the figure represents keywords that are the same as the main idea, and the other parts are new extended sub-ideas based on the main idea.

[0104] In the technical solution of this embodiment, the opinions of users during video conferencing are collected and classified; the classified opinions are displayed to facilitate users to view and summarize the current meeting discussion, avoid repeating the same opinions in the video conference, improve the discussion efficiency of the video conference, and enhance the user experience of the video conference.

[0105] Reference Figure 7 , Figure 7 This is a second embodiment of the method for displaying conference opinions of the present invention, based on the first embodiment, and step S20 includes:

[0106] Step S21, directly displaying the opinion in the opinion area of ​​its category;

[0107] Step S22, upon receiving the speech opinion display instruction, displaying the speech opinion in the opinion area of ​​its category;

[0108] Step S23 : directly displaying the user information associated with the opinion expressed in the opinion display area of ​​the opinion area where the category of the opinion is located.

[0109] Optionally, the speech opinion is directly displayed in the opinion area where its category is located. For example, when the speech opinion is a new opinion, that is, the speech opinion is different from the opinions in the opinion area, the speech opinion is directly displayed in the opinion area where its category is located.

[0110] Optionally, if a trigger instruction of the opinion area is detected, the video frames of users corresponding to the corresponding category of speaking opinions are spliced ​​and displayed in the opinion display area, and the user information includes the video frames; wherein, the video frames corresponding to the same opinion are spliced ​​in a preset display order and have the same identification.

[0111] Optionally, the preset display order can be the speaking order of users with the same opinion. For example, the users holding opinion a are user b1, user b2 and user b3, and the speaking order is user b2, user b1 and user b3, then the preset display order is user b2, user b1 and user b3, wherein the video frame of user b2 is displayed at the first display position in the opinion display area, the video frame of user b1 is displayed at the second display position in the opinion display area, and the video frame of user b3 is displayed at the third display position in the opinion display area.

[0112] Optionally, the preset display order can be the chronological order of opinion formation. For example, the users holding opinion a are user b1, user b2 and user b3, and the chronological order of opinion formation is user b1, user b2 and user b3, then the preset display order is user b1, user b2 and user b3, wherein the video frame of user b1 is displayed at the first display position in the opinion display area, the video frame of user b2 is displayed at the second display position in the opinion display area, and the video frame of user b3 is displayed at the third display position in the opinion display area.

[0113] Optionally, since users may speak multiple times during a discussion, the preset display order may be based on the order of the time points at which the users last spoke. For example, at the first moment, the users holding opinion a are user b1, user b2, and user b3, and the order of the time points at which they last spoke is user b1, user b2, and user b3. The preset display order is user b1, user b2, and user b3, wherein user b1's video frame is displayed at the first display position in the opinion display area, user b2's video frame is displayed at the second display position in the opinion display area, and user b3's video frame is displayed at the third display position in the opinion display area. At the second moment, since user b3 speaks again, the order of the time points at which they last spoke is user b3, user b1, and user b2. The preset display order is user b3, user b1, and user b2. The video frame of user b3 is displayed at the first display position in the opinion display area, the video frame of user b1 is displayed at the second display position in the opinion display area, and the video frame of user b2 is displayed at the third display position in the opinion display area.

[0114] Optionally, if the number of user video frames exceeds the display quantity of the viewpoint display area, other video frames can be viewed by sliding the video frame.

[0115] Optionally, when a speech opinion display instruction is received, the speech opinion is displayed in the opinion area where its category is located. For example, when the speech opinion is the same as the opinion in the opinion area, the speech opinion is not displayed before the speech opinion display instruction is received. After the speech opinion display instruction is received, the speech opinion is displayed in the opinion area where its category is located.

[0116] Optionally, the user information associated with the speech point of view is directly displayed in the point of view display area of ​​the point of view area where the category is located, wherein the user information includes the video frame of the user corresponding to the speech point of view, and the audio and video of the user expressing the speech point of view can be played in the user's video frame. Optionally, the video frames of the users corresponding to the speech points of view of the corresponding category are spliced ​​and displayed in the point of view display area, wherein the point of view display area can display the user information corresponding to different points of view, and the point of view display area can be located below the point of view area, such as Figure 3 As shown. For example, the viewpoint area includes viewpoint a, viewpoint b and viewpoint c. If the user clicks viewpoint a, the video frame of viewpoint a will be displayed in the viewpoint display area, as shown in FIG. Figure 3 Similarly, by clicking on other viewpoints in the viewpoint display area, the display content in the viewpoint display area will switch to the corresponding viewpoint video frame. Optionally, when the viewpoint display area displays the user information corresponding to viewpoint a, when a user corresponding to viewpoint c speaks, the display content in the viewpoint display area will switch to the corresponding viewpoint video frame, clearly showing the current speaker and allowing other users to promptly understand the real-time discussion status.

[0117] In the technical solution of this embodiment, the classified speech opinions are displayed to facilitate users to view and summarize the current meeting discussion, avoid repeating the same speech opinions in the video conference, improve the discussion efficiency of the video conference, and enhance the user experience of the video conference.

[0118] Reference Figure 8 , Figure 8 This is a third embodiment of the method for displaying conference opinions of the present invention, based on the first or second embodiment, wherein step S10 includes:

[0119] Step S11: if the target opinion is found in the opinion list corresponding to the opinion area according to the opinion object and subject of the opinion, then the opinion features of the opinion are obtained, the opinion features including sentiment polarity, content attribute features and other attribute features;

[0120] Step S12, matching the speech opinion with the target opinion based on the opinion feature, and determining the degree of matching between the opinion and the target opinion;

[0121] Step S13: If the matching degree is less than a preset threshold, the classification of the speech opinion is determined to be a sub-opinion of the target opinion.

[0122] Optionally, each opinion expressed may have corresponding opinion features, wherein opinion features include sentiment polarity, content attribute features and other attribute features. For example, sentiment polarity may be "agree" or "disagree"; content attribute features may be content features such as "which place"; and other attribute features may be features such as "speech time".

[0123] Optionally, the opinion features of the speech opinions can be listed as a json (JavaScript Object Notation) string, as shown below:

[0124] {Attribute_characteristics: "{xxx, xxx, xxx, xxx}",

[0125] Emotional_characteristics: "xxxx",

[0126] Other_characteristics: "xxx",

[0127] Topic: "{xxx, xxx, xxx, xxx}"}

[0128] When a user has expressed his opinion a, and another user expresses his opinion b, a match will be made between opinion a and opinion b. The opinion is matched with the target opinion based on the opinion feature to determine the degree of match between the opinion and the target opinion. Optionally, the target opinion is found in the opinion list corresponding to the opinion area based on the opinion object and subject of the opinion. If the opinion and the target opinion are about the same topic and are describing the same opinion object, they are matched based on the sentiment polarity. If the sentiment polarity is the same, the opinion and the target opinion belong to the same opinion and are listed as the same opinion in the opinion list. If the sentiment polarity is different, the opinion and the target opinion belong to different opinions. The sentiment polarity can be determined by using the frequency statistics of the emotional color of adjectives to distinguish whether the content of the speech signal is positive or negative, such as support or dissupport.

[0129] If the sentiment polarity is the same, for example, both opinions are supportive, content attribute feature matching is performed. If the first match X of the keywords contained in the content of the speech opinion and the target opinion is greater than 0 and less than 30%, the speech opinion and the target opinion are determined to be basically consistent; if the first match X of the content of the speech opinion and the target opinion is greater than 30% and less than 60%, the speech opinion and the target opinion are determined to be consistent; if the first match X of the content of the speech opinion and the target opinion is greater than 60%, the speech opinion and the target opinion are completely consistent.

[0130] After matching the content attribute features, other attribute feature matching is performed. If the second matching degree Y of the keywords contained in the content of the speech opinion and the target opinion is greater than 0 and less than 30%, it is determined that the speech opinion and the target opinion are basically consistent; when the second matching degree Y of the content of the speech opinion and the target opinion is greater than 30% and less than 60%, it is determined that the speech opinion and the target opinion are consistent; when the third matching degree Y of the content of the speech opinion and the target opinion is greater than 60%, they are completely consistent.

[0131] When determining whether it is a sub-viewpoint, the first matching degree X is based on the content attribute characteristics. Therefore, the first matching degree X is closer to the topic, its priority will be higher, and its weight will be greater. The second matching degree Y is based on other attribute characteristics to match the viewpoint, and its weight will be relatively small. Among them, 100 samples were drawn for testing, as shown below:

[0132]

[0133]

[0134] After statistics, the proportion of most sub-viewpoints is between 0.6 and 0.4. Therefore, the weight is set to 6 to 4, and the error value is between 0.025. Among them, the measurement value is obtained according to the error calculation formula (AE) / (E / 100)A. When E is the normal value, the error is 0.025.

[0135] The calculation method of matching degree is shown in the following formula

[0136] Z=X*0.60+Y*0.40-0.025;

[0137] Among them, Z is the matching degree, X is the first matching degree, and Y is the second matching degree. If Z is less than 0.55, the speaking opinion is determined to be a sub-opinion of the target opinion. If Z is greater than or equal to 0.55, the speaking opinion is the same as the target opinion.

[0138] In the technical solution of this embodiment, the speech opinions are classified based on whether they are sub-opinions, making the classification of speech opinions more accurate, making it easier for users to determine the changing route of opinions, keep up with the progress of the current video conference, avoid repeatedly raising the same speech opinions, and improve the discussion efficiency of the video conference.

[0139] Reference Figure 9 , Figure 9 This is a fourth embodiment of the method for displaying conference opinions of the present invention, based on any one of the first to third embodiments, wherein step S10 includes:

[0140] Step S14: During the video conference, the user's voice signal is acquired and semantic recognition is performed to obtain text content;

[0141] Step S15, determining the opinion object and opinion features according to the text content, wherein the opinion features include sentiment polarity, content attribute features, and other attribute features;

[0142] Step S16: determining the speech opinion according to the opinion object and the opinion feature.

[0143] Optionally, NLP (Natural Language Processing) can be used to extract the opinions expressed in the user's voice signal. Video conferences typically revolve around a theme and an opinion object. For example, if the opinion object is a project and the theme is the project's effectiveness, then the content attributes are closely related to the theme, such as project profits or losses. Other attributes are less closely related to the theme, such as the project's execution time and location.

[0144] The object of the viewpoint is the subject of the discussion, such as a digital camera; the topic revolves around the content of the argument, such as the functions of a digital camera. The sentiment polarity of the opinion expressed, for example, includes positive, negative, and neutral sentiment polarity. For example, I would say "agree," "disagree," or "either way." Content attribute characteristics are the characteristics of the object of the viewpoint. For example, evaluating the advantages and disadvantages of digital camera A, where the advantages and disadvantages are content attribute characteristics. Project profits or losses are also related to the topic and are content attribute characteristics. Therefore, content attribute characteristics can also be called related behavior characteristics. Optionally, irrelevant features of the viewpoint are other attribute characteristics. When describing other situations outside the topic of the opinion, other attribute characteristics include the time and location of the project execution. Although other attribute characteristics are related to the object of the viewpoint, they are not as closely related to the topic.

[0145] Optionally, a Subjective Genre Classification algorithm is used to identify the topic and the arguments being discussed, a Sentiment Classification algorithm is used to determine the sentiment polarity in the arguments, and various content attribute features of the opinions are obtained through text summaries.

[0146] Optionally, determine the opinion content of the text, including sentiment, content attributes, and other attributes, and compare them with a dataset to improve accuracy. Create a set of adjectives, which will be used in natural language processing. For each opinion word, identify the opinion orientation, such as support or opposition. WordNet, an English vocabulary database, can be used to identify opinion orientation. Determine the opinion orientation of the sentence based on the opinion characteristics of the text content, and refine the speech's opinion based on the opinion orientation.

[0147] In the technical solution of this embodiment, during a video conference, the user's voice signal is acquired and semantically recognized to obtain text content. Based on the text content, the viewpoint object and viewpoint features are determined. Viewpoint features include sentiment polarity, content attribute features, and other attribute features. The speaker's viewpoint is then determined based on the viewpoint object and viewpoint features. Accurately determining the viewpoint based on the viewpoint object and viewpoint features facilitates user follow-up of the current video conference progress, improving the user's video conferencing experience.

[0148] Reference Figure 10 , Figure 10 This is a fifth embodiment of the method for displaying conference opinions of the present invention, and the method includes the following steps:

[0149] Step S40, obtaining the opinions of each user during the video conference;

[0150] Step S50, classifying the speech opinions and adding the speech opinions to a viewpoint list according to the categories of the speech opinions;

[0151] Step S60: determining the speech opinions to be displayed in the opinion area in the opinion list, and sending the speech opinions to be displayed in the opinion area to the terminal device.

[0152] Optionally, this embodiment is applied to a server to statistically classify the speech opinions of multiple users and determine the relationship between the speech opinions, wherein the speech opinion may be the same as the opinion in the opinion list, or the speech opinion may be different from the opinion in the opinion list, or the relationship between the speech opinion and the opinion in the opinion list is the main opinion and sub-opinion.

[0153] Optionally, if the opinion expressed is the same as the opinion in the opinion list, the number of supporters of the opinion in the opinion list is updated, and the support level of the opinion can be determined based on the number of supporters.

[0154] Optionally, if the opinion expressed is different from the opinions in the opinion list, the opinion expressed is added to the opinion list.

[0155] Optionally, if the relationship between the speech viewpoint and the viewpoint in the viewpoint list is a main viewpoint and a sub-viewpoint, the speech viewpoint is associated with the viewpoint in the viewpoint list and stored in the viewpoint list.

[0156] Optionally, the speech opinions are classified. If the target opinion is found in the opinion list based on the opinion object and subject of the speech opinion, the opinion features of the speech opinion are obtained, which include sentiment polarity, content attribute features and other attribute features. The speech opinion is matched with the target opinion based on the opinion features to determine the degree of matching between the opinion and the target opinion. If the degree of matching is less than a preset degree threshold, the speech opinion is classified as a sub-opinion of the target opinion. Please refer to the above embodiment and will not be repeated here.

[0157] Optionally, collecting the user's speech opinions during a video conference can include acquiring the user's voice signal and performing semantic recognition to obtain text content during the video conference; determining the opinion object and opinion characteristics based on the text content, where the opinion characteristics include sentiment polarity, content attribute characteristics, and other attribute characteristics; and determining the speech opinion based on the opinion object and opinion characteristics. Alternatively, obtaining the speech opinion identified by the terminal device can be described in the aforementioned embodiment and will not be repeated here.

[0158] Optionally, the support level of the speech opinion is determined based on the number of times the speech opinion appears; the speech opinion to be displayed in the opinion area is determined based on the support level, and the speech opinion to be displayed in the opinion area is sent to the terminal device, and the terminal device creates an opinion area to display the speech opinion, and creates a video frame in the opinion display area to display the same speech opinion.

[0159] In the technical solution of this embodiment, the server classifies the speech opinions and determines the speech opinions to be displayed in the opinion area of ​​the terminal device, thereby avoiding insufficient processing power of the terminal device, resulting in a low video conference processing speed, and improving the processing efficiency of speech opinions.

[0160] Reference Figure 11 The present invention further provides a conference opinion display device, the conference opinion display device comprising:

[0161] The collection module 100 is used to collect the opinions expressed by users during the video conference and classify the opinions expressed;

[0162] The display module 200 is used to display the classified speech opinions.

[0163] Optionally, the step of displaying the classified opinions further includes the following:

[0164] Display the opinions expressed directly in the opinion area of ​​its category;

[0165] Upon receiving a speech opinion display instruction, displaying the speech opinion in the opinion area of ​​its category;

[0166] The user information associated with the speech opinion is directly displayed in the opinion display area of ​​the opinion area where the category is located.

[0167] Optionally, the step of directly displaying the user information associated with the speech opinion in the opinion display area of ​​the opinion area where the category of the user information is located includes:

[0168] If a trigger instruction of the opinion area is detected, the video frame of the user corresponding to the corresponding category of speech opinion is displayed in the opinion display area, and the user information includes the video frame;

[0169] The video frames corresponding to the same viewpoint are spliced ​​in a preset display order and have the same identifier.

[0170] Optionally, the step of displaying the classified speech opinions includes:

[0171] If there is a viewpoint area corresponding to the category of the speech opinion, the speech opinion is displayed in the viewpoint area of ​​the category;

[0172] If there is no viewpoint area corresponding to the category of the opinion, then create a new viewpoint area corresponding to the category of the opinion, and display the opinion in the new viewpoint area;

[0173] After the step of displaying the classified opinions, the method further includes:

[0174] If the category of the speech opinion changes, the opinion area of ​​the opinion category before the change will be grayed out, the opinion area where the changed speech opinion is located will be determined, and the speech opinion will be displayed in the opinion area where its category is located.

[0175] Optionally, the step of classifying the speech opinions includes:

[0176] If the target opinion is found in the opinion list corresponding to the opinion area according to the opinion object and subject of the opinion, the opinion features of the opinion are obtained, which include sentiment polarity, content attribute features and other attribute features;

[0177] Matching the speech opinion with the target opinion based on the opinion feature to determine the degree of matching between the opinion and the target opinion;

[0178] If the matching degree is less than a preset degree threshold, it is determined that the speech viewpoint is classified as a sub-viewpoint of the target viewpoint.

[0179] Optionally, the step of collecting the user's speech opinions during the video conference includes:

[0180] During the video conference, the user's voice signal is acquired and semantic recognition is performed to obtain the text content;

[0181] Determining the opinion object and opinion features based on the text content, wherein the opinion features include sentiment polarity, content attribute features, and other attribute features;

[0182] The speech opinion is determined according to the opinion object and the opinion characteristics.

[0183] Reference Figure 11 The present invention further provides a conference opinion display device, the conference opinion display device comprising:

[0184] The acquisition module 300 is used to obtain the opinions expressed by each user during the video conference;

[0185] A classification module 400 is used to classify the speech opinions and add the speech opinions to a viewpoint list according to the categories of the speech opinions;

[0186] The determination module 500 is configured to determine, in the viewpoint list, a speech viewpoint to be displayed in the viewpoint area, and send the speech viewpoint to be displayed in the viewpoint area to the terminal device.

[0187] Optionally, after the step of adding the speech opinions to the opinion list according to the category of the speech opinions, the method further includes:

[0188] Determining the support level of the opinion expressed in the speech based on the number of occurrences of the opinion expressed in the speech;

[0189] The opinion to be displayed in the opinion area is determined according to the support level.

[0190] The present invention also provides a conference opinion display device, which includes a memory, a processor, and a conference opinion display program stored in the memory and executable on the processor. When the conference opinion display program is executed by the processor, it implements the various steps of the conference opinion display method described in the above embodiment.

[0191] The present invention also provides a computer-readable storage medium, which stores a conference opinion display program. When the conference opinion display program is executed by a processor, it implements the various steps of the conference opinion display method described in the above embodiment.

[0192] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0193] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, system, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, system, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, system, article, or device comprising the element.

[0194] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment system can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, parking management equipment, air conditioner, or network equipment, etc.) to execute the system described in each embodiment of the present invention.

[0195] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for displaying conference opinions, characterized in that: Applied to a terminal device, the conference viewpoint display method includes: Collecting users' opinions during the video conference and classifying the opinions; Displaying the classified opinions includes: if there is an opinion area corresponding to the category of the opinion, displaying the opinion in the opinion area of ​​the category; if there is no opinion area corresponding to the category of the opinion, creating a new opinion area corresponding to the category and displaying the opinion in the new opinion area; After the step of displaying the classified opinions, the method further includes: If the category of the speech opinion changes, the opinion area of ​​the opinion category before the change will be grayed out, the opinion area where the changed speech opinion is located will be determined, and the speech opinion will be displayed in the opinion area where its category is located.

2. The method for displaying conference opinions according to claim 1, wherein: The step of displaying the classified opinions further includes the following: Display the opinions expressed directly in the opinion area of ​​its category; Upon receiving a speech opinion display instruction, displaying the speech opinion in the opinion area of ​​its category; The user information associated with the speech opinion is directly displayed in the opinion display area of ​​the opinion area where the category is located.

3. The method for displaying conference opinions according to claim 2, wherein: The step of directly displaying the user information associated with the speech opinion in the opinion display area of ​​the opinion area where the category of the user information is located includes: If a trigger instruction of the opinion area is detected, a video frame of a user corresponding to the corresponding category of speech opinion is displayed in the opinion display area, and the user information includes the video frame; The video frames corresponding to the same viewpoint are spliced ​​in a preset display order and have the same identifier.

4. The method for displaying conference opinions according to claim 1, wherein: The step of classifying the speech opinions includes: If the target opinion is found in the opinion list corresponding to the opinion area according to the opinion object and subject of the opinion, the opinion features of the opinion are obtained, which include sentiment polarity, content attribute features and other attribute features; Matching the speech opinion with the target opinion based on the opinion feature to determine the degree of matching between the opinion and the target opinion; If the matching degree is less than a preset degree threshold, it is determined that the speech viewpoint is classified as a sub-viewpoint of the target viewpoint.

5. The method for displaying conference opinions according to claim 1, wherein: The step of collecting the user's opinions during the video conference includes: During the video conference, the user's voice signal is acquired and semantic recognition is performed to obtain the text content; Determining the opinion object and opinion features based on the text content, wherein the opinion features include sentiment polarity, content attribute features, and other attribute features; The speech opinion is determined according to the opinion object and the opinion characteristics.

6. A method for displaying conference opinions, characterized in that: Applied to a server, the method includes: Obtain each user's opinions during the video conference; Classifying the opinions and adding them to a list of opinions according to the categories of the opinions; Determine the speech opinions to be displayed in the opinion area in the opinion list, send the speech opinions to be displayed in the opinion area to the terminal device, if there is a opinion area corresponding to the category of the speech opinion, then display the speech opinion in the opinion area where its category is located; if there is no opinion area corresponding to the category of the speech opinion, then create a new opinion area corresponding to the opinion category, and display the speech opinion in the newly created opinion area; if the category of the speech opinion changes, gray out the opinion area of ​​the opinion category before the change, determine the opinion area where the changed speech opinion is located, and display the speech opinion in the opinion area where its category is located.

7. The method for displaying conference opinions according to claim 6, wherein: After the step of adding the speech opinions to the opinion list according to the category of the speech opinions, the method further includes: Determining the support level of the opinion expressed in the speech based on the number of occurrences of the opinion expressed in the speech; The opinion to be displayed in the opinion area is determined according to the support level.

8. A conference opinion display device, characterized in that: The conference opinion display device includes a memory, a processor, and a conference opinion display program stored in the memory and executable on the processor. When the conference opinion display program is executed by the processor, it implements the various steps of the conference opinion display method as described in any one of claims 1-5 or 6-7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a conference opinion display program, and when the conference opinion display program is executed by a processor, each step of the conference opinion display method according to any one of claims 1 to 7 is implemented.

Images