Conference content display method, readable storage medium, program product and equipment

Abstract

One or more embodiments of the invention provide a conference content display method, a readable storage medium, a program product and equipment. The method comprises the following steps: acquiring original speaking content and speaking gesture of a target participant in a target conference; adjusting the original speaking content according to the speaking gesture to generate target speaking content; and displaying the target speaking content.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of augmented reality (AR) technology, and in particular, to a method for displaying conference content, a readable storage medium, a program product, and a device. Background Art

[0002] With the development of information technology, the form of modern meetings has evolved from traditional face-to-face communication to online virtual meetings and even new meeting modes that integrate augmented reality (AR) technology. Participants' understanding of a topic or presentation materials such as images, music, and presentations often requires the speaker's explanation to fully grasp it. Once the speaker has problems such as unclear speech or too lengthy expression, the speech content will become difficult to understand, which will in turn affect the understanding of other participants.

[0003] In related technologies, speakers can usually repeat their speeches to re-express to participants the speech content that was previously unclear or needed to be emphasized, but this method will interrupt the continuity of the meeting and increase the time cost while reducing the efficiency of participants' understanding. Alternatively, the above speech content can be recognized and displayed through technologies such as voice recognition to ensure that participants can quickly understand the speech content. However, this method also has objective problems such as high misrecognition, which not only makes it impossible for participants to better understand the speech content, but may also introduce more misunderstandings. Summary of the invention

[0004] In view of this, one or more embodiments of this specification provide the following technical solutions:

[0005] According to a first aspect of one or more embodiments of this specification, a method for presenting conference content is provided, the method comprising:

[0006] Obtain the original speech content and speech gestures of the target participant in the target meeting;

[0007] Adjusting the original speech content according to the speech gesture to generate target speech content;

[0008] The target speech content is displayed.

[0009] Optionally, adjusting the original speech content according to the speech gesture includes:

[0010] Determine a corresponding first keyword according to the speaking gesture, where the first keyword is used to represent a specific implementation of at least one second keyword;

[0011] In the case where the first keyword matches the target second keyword in the original speech content, the target second keyword in the original speech content is replaced with the first keyword.

[0012] Optionally, adjusting the original speech content according to the speech gesture includes:

[0013] Determine a corresponding emotion keyword according to the speech gesture, wherein the emotion keyword is used to represent the user's speech emotion;

[0014] In the case where the emotion keyword matches the original speech content, the display style of the original speech content is adjusted according to the speech emotion.

[0015] Optionally, the types of the target meeting include online virtual meetings and offline virtual meetings, at least some of the participants of the online virtual meeting are in different meeting scenes, and all the participants of the offline virtual meeting are in the same meeting scene.

[0016] Optionally, the method further includes:

[0017] In the case that the target meeting is the offline virtual meeting, the acquisition operation of the speech gesture is canceled, and the target speech content is generated according to the original speech content.

[0018] Optionally, obtaining the original speech content and speech gestures of the target participant in the target conference includes:

[0019] In the case where the target participant is a user, collecting the original speech content and the speech gesture of the user through the conference content display device of the user;

[0020] In the case that the target participant is another participant other than the user, the original speech content and the speech gesture of the other participant collected by the conference content display device of the other participant are received.

[0021] Optionally, the conference content display device is configured with a speaking mode and a listening mode;

[0022] The collecting of the original speech content and the speech gesture of the user through the conference content display device of the user comprises: when the conference content display device of the user is in the speech mode and the user is speaking, collecting the original speech content and the speech gesture of the user through the conference content display device of the user;

[0023] The receiving the original speech content and the speaking gestures of the other participants collected by the conference content display device of the other participants includes: when the conference content display device of the user is in the listening mode and the other participants are speaking, receiving the original speech content and the speaking gestures of the other participants collected by the conference content display device of the other participants.

[0024] Optionally, the conference content display device of the user is in the listening mode, and the method further includes:

[0025] Collecting, by means of the conference content display device of the user, a feedback gesture of the user with respect to the target speech content, wherein the feedback gesture is used to indicate the consistency between the target speech content and the original speech content;

[0026] When the feedback gesture indicates that the target speech content is inconsistent with the original speech content, an adjustment strategy of the speech gesture for the original speech content is adjusted.

[0027] According to a second aspect of one or more embodiments of the present specification, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0028] According to a third aspect of one or more embodiments of the present specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.

[0029] According to a fourth aspect of one or more embodiments of this specification, a conference content display device is provided, the device comprising: a speech content acquisition unit, used to acquire the original speech content and speech gestures of a target participant in a target conference;

[0030] A speech content adjustment unit, configured to adjust the original speech content according to the speech gesture to generate target speech content;

[0031] The speech content display unit is used to display the target speech content.

[0032] In the technical solution provided in this specification, the original speech content and speech gestures of the target participant in the target meeting can be obtained, and the obtained original speech content can be adjusted according to the speech gestures, so as to generate and display the target speech content. Among them, since the behavior of executing the speech gesture is independent of the speech behavior, the entire process from adjusting the original speech content according to the speech gesture to displaying the target speech content will not interrupt the continuity of the target meeting, thereby improving the efficiency of understanding of the participants. In addition, the above-mentioned target speech content is generated based on the original speech content with reference to the speech gesture, and the speech gesture, as a subconscious behavior naturally generated by the target participant during the speech process, can be used to strengthen the target participant's speech intention. Therefore, the target speech content generated according to the above-mentioned speech gesture is easier to help participants understand the actual meaning of the corresponding content than the original speech content. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 It is a schematic diagram of the architecture of a conference content display system provided by an exemplary embodiment;

[0035] Figure 2 It is a flowchart of a method for displaying conference content provided by an exemplary embodiment;

[0036] Figure 3 It is a flowchart of another method for displaying conference content provided by an exemplary embodiment;

[0037] Figure 4 is a schematic structural diagram of an electronic device provided by an exemplary embodiment;

[0038] Figure 5 It is a structural schematic diagram of a device for displaying conference content provided by an exemplary embodiment. DETAILED DESCRIPTION

[0039] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the present invention.

[0040] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0041] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0042] Figure 1 FIG. 1 is a schematic diagram of the architecture of a conference content display system provided by an exemplary embodiment. Figure 1 As shown, the system includes a conference content display device 11.

[0043] The conference content display device 11 is an electronic device for displaying the speech content of the participants, and can also have the ability to obtain and process the speech content and speech gestures of the participants, such as: personal computer (PC) terminal devices, mobile terminal devices, Internet of Things devices, AR devices and other forms of smart devices, etc. Taking AR devices as an example, assuming that the conference content display device 11 is specifically a wearable device such as AR glasses, it can combine virtual content with the real world by superimposing digital information in the user's field of view. At this time, the conference content display device 11 can be used to obtain the original speech content of the participant 12 in the meeting and display the processed speech content. During the operation of the system, the conference content display device 11 can obtain the original speech content and speech gesture corresponding to the speech of the participant 12 in the meeting, and adjust the original speech content according to the speech gesture, so as to generate the target speech content for display, so that other participants can further understand the actual meaning expressed by the original speech content through the displayed target speech content.

[0044] Figure 2 This is a flowchart of a method for presenting conference content provided by an exemplary embodiment; the method may include the following steps:

[0045] Step S202, obtaining the original speech content and speech gestures of the target participant in the target conference.

[0046] When the user wants to display the speech content of the target participant in the target meeting, the original speech content and the corresponding speech gesture of the target participant can be obtained by using the conference content display device (for example, wearing AR glasses, turning on the mobile phone, etc.), and then the target speech content for display can be generated. Among them, the original speech content can be a readable text obtained by converting the speech of the target participant when speaking based on speech recognition technology, and the speech gesture can be a hand gesture made synchronously when the target participant speaks. Specifically, a corresponding relationship can be established between the original speech content and the speech gesture based on the time dimension, for example, each speech gesture or a gesture combination consisting of multiple speech gestures can be matched with the speech content in the corresponding time period according to the execution time point, duration and other time parameters of the gesture, so as to establish a corresponding relationship. Alternatively, a corresponding relationship can also be established between the original speech content and the speech gesture based on the acquisition order, for example, each speech gesture or a gesture combination consisting of multiple speech gestures can be matched with the speech content of the same acquisition order according to the acquisition order of the gesture, so as to establish a corresponding relationship, wherein the original speech content can be split into multiple sub-speech contents by sentence pauses or context analysis, etc., and this specification does not limit this.

[0047] For example, in a company meeting, a department manager said, "According to the data analysis last week, our customer satisfaction has improved significantly. I think this is mainly due to the customer service improvement measures we recently launched." In the process of talking about "significant improvement", the first action of thumbs-up was made, and the second action of spreading both hands was made when talking about "customer service improvement measures". Then the entire speech can be obtained through voice recognition to obtain the same text as the original speech content. The first action can be used as a speech gesture to establish a corresponding relationship with the excerpt of "customer service improvement measures" in the original speech content. Similarly, the second action can also be used as a speech gesture to establish a corresponding relationship with the excerpt of "significant improvement".

[0048] In addition, each time parameter can be set with a certain margin parameter, so that the same speech gesture can match the original speech content in more time periods near the above-mentioned execution time point when the execution time is shorter, thereby playing a role in adjusting the matching sensitivity between the original speech content and the speech gesture.

[0049] In addition to the readable text, the original speech content may also include multimedia data such as images, videos, tables or electronic documents that have a preset corresponding relationship with the readable text, and are displayed with the readable text through the target speech content, thereby increasing the diversity of the speech content. The corresponding relationship may be, for example, the readable text "pet dog" and the puppy image, the readable text "2024 annual financial report" and the corresponding financial data summary diagram, etc., which is not limited in this specification.

[0050] For the acquisition process of the above-mentioned original speech content and speech gestures, different acquisition methods can be provided in this specification according to the identity of the target participant. For example: when the target participant is the wearer of the above-mentioned conference content display device, the original speech content and speech gestures of the target participant can be directly collected through sensors such as sound sensors and image sensors in the conference content display device; for example: when the target participant is other participants other than the user, the user can receive the data collected by the conference content display devices of other participants through his own conference content display device, thereby indirectly obtaining the original speech content and speech gestures of other participants. Considering the physical distance between different participants and the influence of the complex and changeable data collection environment on the data collection quality of the conference content display device, compared with the user's conference content display device directly collecting the original speech content and speech gestures of other participants, the above indirect acquisition of the original speech content and speech gestures of other participants can effectively improve the accuracy of the data. At the same time, different conference content display devices in this example can realize long-distance data transmission between each other based on technologies such as wireless LANs such as Bluetooth, wireless fidelity (wireless fidelity, Wi-Fi) or 5G networks, which is not limited in this specification.

[0051] Based on the different acquisition methods for original speech content and speech gestures provided above, this manual can further configure speaking mode and listening mode in the conference content display device, so that the user can independently switch the required acquisition method by methods such as triggering a physical button, issuing voice commands, or making specific physical movements. Among them, the so-called speaking mode and listening mode can be regarded as two basic working states of the conference content display device in the meeting. When the user needs to speak in the target meeting and display the speech content to other participants, the user can switch to the speaking mode, or when the user needs to listen to the speeches of other participants in the target meeting and browse the speech content they display, the user can switch to the listening mode.

[0052] In one embodiment, when the conference content display device is in the speaking mode and the user is speaking, the above-mentioned original speech content and the above-mentioned speaking gestures of the user can be collected by the corresponding sensor. At this time, the user is the target participant, and the speaking behavior is consistent with his speaking mode, so the original speech content and speaking gestures can be correctly obtained. Of course, when the conference content display device is in the speaking mode and the user is not speaking, then at this time, the user is the target participant, and the speaking behavior is inconsistent with his speaking mode. The conference content display device can display relevant information to prompt the user to speak, or automatically switch to the listening mode when the mode conversion conditions are met. The mode conversion conditions include but are not limited to the above-mentioned user's non-speaking time length being greater than the preset maximum waiting time threshold, and receiving a mode capture request from the above-mentioned user or the above-mentioned target conference administrator.

[0053] In another embodiment, when the conference content display device is in the listening mode and the other participants are speaking, the original speech content and the speaking gestures collected by the conference content display devices of the other participants from the other participants can be received. At this time, the other participants serve as target participants, and their speaking behaviors are consistent with their speaking modes, so the original speech content and speaking gestures can be correctly obtained. Of course, when the conference content display device is in the listening mode and the other participants have not spoken, then at this time, the other participants serve as target participants, and their speaking behaviors are inconsistent with their speaking modes. The conference content display device can ask the user whether to send a speech prompt message to the other participants, or the target participant can exchange requests to exchange identities with the other participants and switch to the speaking mode.

[0054] In the above two embodiments, the speaking mode and listening mode of each participant can be handed over to the target conference administrator to maintain and manage the conference configuration information of the target conference, wherein the above conference configuration information can manage the speaking mode and listening mode of each participant by dimensions such as speaking duration, number of speeches, number of simultaneous speakers, etc. For example, there is a conference configuration information of a target conference, which requires participant A to be only in listening mode and never in speaking mode; participant B can choose to be in listening mode or speaking mode, but the total speaking time in speaking mode is 3 minutes, and after exceeding the total speaking time, he can only be in listening mode. Of course, in addition to the above-mentioned conference configuration information, which is the preset information, the target conference administrator or other participants who are granted mode management authority can also directly switch the basic working status of any participant in the target conference, and the mode management authority can be set to follow or ignore the restrictions in the above-mentioned conference configuration information.

[0055] The types of the above-mentioned target meetings can be further divided into online virtual meetings and offline virtual meetings, wherein at least some of the participants in the online virtual meeting are in different meeting scenes. Taking into account the differences between different meeting scenes, the above-mentioned online virtual meeting can be based on a preset virtual meeting scene as a unified meeting scene for all participants, that is, no matter what meeting scene the participants are in, they can advance the meeting in the same virtual meeting scene after joining the target meeting; while all participants of the offline virtual meeting are in the same meeting scene, and there is no problem of conflict in meeting scenes. Therefore, in addition to the virtual meeting scene, the meeting scene of the above-mentioned offline virtual meeting can also directly adopt the actual meeting scene, and combine AR technology, virtual reality (VR), mixed reality (MR) and other technologies to display the corresponding target speech content in the actual meeting scene.

[0056] It should be noted that in offline virtual meetings, face-to-face communication between participants has actually greatly enhanced the participants' sense of participation. Even without wearing AR glasses or other conference content display devices, other participants can observe the target participant's speech gestures with their naked eyes, thereby having a more accurate understanding of the actual meaning of the original speech content. Therefore, when the target meeting is an offline virtual meeting, the conference content display device can cancel the acquisition operation of speech gestures and generate the above target speech content based on the above original speech content. In other words, the conference content display device at this time only needs to play the role of acquiring the original speech content in the target meeting, and is used to assist the wearer to understand the original speech content based on the speech gestures he sees. This method utilizes the particularity of offline meeting scenes to avoid the amount of calculation caused by the conference content display device for operations such as acquiring speech gestures, thereby reducing the performance threshold and equipment cost of the conference content display device.

[0057] Step S204: adjusting the original speech content according to the speech gesture to generate target speech content.

[0058] After obtaining the above-mentioned original speech content and the above-mentioned speech gesture, the corresponding original speech content can be adjusted according to the speech gesture, wherein the speech gesture is a subconscious behavior naturally generated by the target participant during the speech process, so that the above-mentioned target speech content after adjustment by the above-mentioned speech gesture can more fully express the actual speech intention of the target participant than the original speech content before adjustment.

[0059] The adjustment of the original speech content by the above-mentioned speech gesture may be based on multiple dimensions, such as the content of the original speech content and the display style of the original speech content.

[0060] In one embodiment, the corresponding first keyword can be determined according to the speech gesture, and the above-mentioned first keyword can be used to characterize the specific implementation of at least one second keyword; when the above-mentioned first keyword matches the target second keyword in the above-mentioned original speech content, the above-mentioned target second keyword in the above-mentioned original speech content can be replaced with the above-mentioned first keyword. Assume that in a meeting, participant A is speaking as the target participant, and his speech content is converted into text through voice recognition technology: "Take out your food!" At the same time, participant A makes a speech gesture of imitating the keyboard with his fingers. In this embodiment, the first keyword "keyboard" corresponding to the gesture recognized by the conference content display device, assuming that there is a preset corresponding relationship between the first keyword and multiple second keywords such as "production tools", "office equipment" and "food", then "food" can be selected from the original speech content as the target second keyword matching the first keyword, and the above-mentioned target second keyword in the above-mentioned original speech content is replaced with the above-mentioned first keyword, and the adjusted speech content "Take out your keyboard!" is obtained.

[0061] The preset correspondence in the above embodiment can usually include keywords with high frequency of daily use and some user-defined keywords. In some scenarios, it is often difficult to complete the matching, resulting in the absence of a second keyword matching any first keyword in the original speech content. At this time, the words and sentences in the original speech content whose similarity with the first keyword is greater than the preset similarity threshold can be determined in real time through corpus analysis or natural language processing (Natural Language Processing, NLP) and other technologies, and used as the corresponding target second keyword. For example, when the first keyword "keyboard" only has a preset correspondence relationship with the second keywords "production tools" and "office equipment", the target second keyword "food" that has a high semantic similarity with "keyboard" can be determined in the original speech content, and then replaced with the above-mentioned first keyword "keyboard".

[0062] Of course, when it is determined based on the above-mentioned preset correspondence or NLP and other technologies that there is no target second keyword related to the first keyword in the above-mentioned original speech content, you can try to directly add the above-mentioned first keyword to the beginning, end, etc. of the original speech content, or directly replace the entire original speech content corresponding to the speech gesture, to remind the user that the target participant made the above-mentioned speech gesture when making the above-mentioned original speech content, so as to assist the user in understanding the original speech content.

[0063] In another embodiment, the corresponding emotional keywords can be determined according to the speaking gesture, and the above emotional keywords can be used to characterize the user's speaking emotions, such as excitement, loss, calmness, etc.; when the emotional keywords match the above original speech content, the display style of the corresponding original speech content can be adjusted according to the above speech emotions. Suppose in a meeting, participant B is speaking as the target participant, and his speech content is converted into text through voice recognition technology: "Our sales this year exceeded 10 million!" At the same time, participant B made a speaking gesture with a fist raised while shouting "10 million". In this embodiment, the emotional keyword "excitement" corresponding to the gesture recognized by the conference content display device can be adjusted to make the display style of the speech content "10 million" more visually impactful, such as enlarging the font size, thickening the lines, and setting the color to high-contrast warm colors such as bright red.

[0064] Among them, the so-called matching of emotional keywords with the original speech content can be to perform emotional analysis on the original speech content through NLP and other technologies, and compare the obtained analysis results with the above emotional keywords. If the similarity between the two meets the preset comparison conditions, the display style of the original speech content is adjusted. Here, the above original speech content "Our sales this year exceeded 10 million!" is still taken as an example. If the analysis result of the emotional analysis is that the content has an 80% probability of excitement and a 20% probability of fear, and the preset comparison condition is that the emotional keywords are consistent with the analysis result with the highest probability, then the conference content display device can adjust the display style of the original speech content.

[0065] Of course, as mentioned above, the original speech content may also include multimedia data such as images, videos, tables or electronic documents. The above-mentioned emotional keywords can act on the basic parameters corresponding to these multimedia data, such as the zoom ratio of the picture, video filters, etc., and this manual does not limit this.

[0066] In addition to speaking gestures, the original speech content can also be actively translated into a language that the user can understand when the language options set by the target participant and the user are inconsistent, so that the user can understand the meaning of the original speech content even if he does not know the language used by the target participant when speaking.

[0067] Step S206: display the target speech content.

[0068] After the target speech content is generated, the conference content display device can display the target speech content, wherein the display target can also be divided according to the identity of the target participant. For example, when the target participant is a user, the above-mentioned target speech content is essentially the user's speech content. Except for the case where the user wishes to actively check whether the adjusted target speech content is in line with his or her own speech intention, the conference content display device does not need to display the target speech content to the user by default. On the contrary, the conference content display device can send the target speech content to the conference content display devices corresponding to other participants. When the target participant is other participants, it is only necessary to receive the target speech content from other conference content display devices and display it. In terms of display method, the conference content display device can display the target speech content in the form of subtitles, stickers, etc. on the display screen of the conference content display device, or repeat it through voice broadcasting, etc., which is not limited in this manual.

[0069] In addition to the target speech content, the conference content display device can also obtain additional information such as the identity information of the target participant, the relative position information with the user or the original speech content, and display it together, so that the user can quickly locate the identity and position of the current target participant, and even the difference between the target speech content generated by the conference content display device and the original speech content, so as to have a deeper understanding of the ideas expressed by the target participant.

[0070] In addition, for the conference content display device in the listening mode, the feedback gesture of the user for the target speech content can be collected through the corresponding sensor. When the feedback gesture indicates that the target speech content is inconsistent with the original speech content, the adjustment strategy of the speech gesture for the original speech content is adjusted, wherein the feedback gesture can be used to characterize the consistency of the target speech content with the original speech content, so that the user can actively feedback when the target speech content conflicts with the original speech content. For example, if the user thinks that the keyword replacement in the target speech content is inaccurate or the emotional expression is inappropriate, this can be pointed out through a specific gesture. After receiving the feedback gesture, the corresponding conference content display device can optimize and modify the adjustment strategy of the original speech content, such as deleting the preset correspondence between the first keyword and the second keyword corresponding to the speech gesture, modifying the emotional keyword corresponding to the speech gesture, and adjusting the translation logic of the original speech content. The above optimization and modification means can be used in conjunction with the machine learning model, and by learning a large amount of feedback data, the accuracy and intelligence of the conference content display device in adjusting the speech content can be gradually improved, so that the speech content adjustment in similar situations in the future is more in line with actual needs. In addition, this mechanism also allows the system to continuously improve itself over time, reduce misjudgments, and better adapt to the personalized needs of different users.

[0071] Combine the following Figure 3 The overall process of the method for presenting conference content is introduced. As shown in the figure, the method includes the following steps:

[0072] Step S302: The user wears AR glasses and enters the conference system.

[0073] In one embodiment, a project manager of a company, as a user, wears pre-paired AR glasses as a conference content display device before attending an online virtual meeting on product development progress. The glasses are synchronized with the conference system via wireless connection, ensuring that the company's information can be shared in real time with all participants across the country.

[0074] Step S304, determining whether the wearer is speaking for the target participant.

[0075] In one embodiment, the AR glasses can be built-in to detect whether they are currently in speaking mode or listening mode. If they are in speaking mode and the project manager is detected to start speaking, step S306 is executed; if the wearer is not detected speaking or it is determined that the AR glasses are in listening mode, step S312 can be executed.

[0076] Step S306, obtaining the original speech content and speech gestures of the target participant in the target conference.

[0077] In one embodiment, when the wearer starts speaking, the sound sensor built into the AR glasses starts recording the speech audio and converts it into the original speech content in text form through speech recognition technology. At the same time, the image sensor captures various gestures made by the wearer during the speech, which may include nodding, waving, or other actions to express emotions.

[0078] Step S308: adjusting the original speech content according to the speech gesture to generate the target speech content.

[0079] In one embodiment, the system analyzes the captured gestures and adjusts the original speech content accordingly based on the meaning of these gestures. For example, if the wearer is detected waving his hands when mentioning a project milestone, the system may mark this part of the speech in red to emphasize its importance.

[0080] Step S310, sending the target speech content to other participants.

[0081] In one embodiment, the adjusted target speech content can be sent to the AR glasses of other participants via a wireless network. In this way, even if some participants fail to hear or hear the wearer's speech in time due to network delay or other reasons, they can still see the adjusted speech content through the AR glasses.

[0082] Step S312, receiving and displaying the target speech content from the AR glasses of the target participant.

[0083] In one embodiment, after receiving the adjusted speech content through AR glasses of other participants, it will be displayed in the user's field of view in the form of augmented reality. These contents may appear next to the speaker's name in the form of a floating window, or directly overlay on the conference background, so that participants can read or view the adjusted speech content while listening to the speech.

[0084] Figure 4 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 4 At the hardware level, the device includes a processor 402, an internal bus 404, a network interface 406, a memory 408, and a non-volatile memory 410, and may also include hardware required for other functions. One or more embodiments of this specification may be implemented based on software, such as the processor 402 reading the corresponding computer program from the non-volatile memory 410 into the memory 408 and then running it. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0085] Corresponding to the embodiment of the method for displaying the content of a conference, this specification also provides an embodiment of a device for displaying the content of a conference. Figure 5 , the device comprises:

[0086] The speech content acquisition unit 502 is used to acquire the original speech content and speech gestures of the target participant in the target conference;

[0087] A speech content adjustment unit 504, configured to adjust the original speech content according to the speech gesture to generate target speech content;

[0088] The speech content display unit 506 is used to display the target speech content.

[0089] Optionally, the speech content adjustment unit 504 is specifically configured to:

[0090] Determine a corresponding first keyword according to the speaking gesture, where the first keyword is used to represent a specific implementation of at least one second keyword;

[0091] In the case where the first keyword matches the target second keyword in the original speech content, the target second keyword in the original speech content is replaced with the first keyword.

[0092] Optionally, the speech content adjustment unit 504 is specifically configured to:

[0093] Determine a corresponding emotion keyword according to the speech gesture, wherein the emotion keyword is used to represent the user's speech emotion;

[0094] In the case where the emotion keyword matches the original speech content, the display style of the original speech content is adjusted according to the speech emotion.

[0095] Optionally, the types of the target meeting include online virtual meetings and offline virtual meetings, at least some of the participants of the online virtual meeting are in different meeting scenes, and all the participants of the offline virtual meeting are in the same meeting scene.

[0096] Optionally, the device further comprises:

[0097] The speech gesture canceling unit is used to cancel the acquisition operation of the speech gesture when the target meeting is the offline virtual meeting, and generate the target speech content according to the original speech content.

[0098] Optionally, the device further comprises:

[0099] A speech content collection unit, used for collecting the original speech content and the speech gesture of the user through the conference content display device of the user when the target participant is a user;

[0100] The speech content receiving unit is used to receive the original speech content and the speech gesture of the other participant collected by the conference content display device of the other participant when the target participant is other participants other than the user.

[0101] Optionally, the conference content display device is configured with a speaking mode and a listening mode;

[0102] The speech content collection unit is specifically used to: when the user is in the speech mode and speaks, collect the original speech content and the speech gesture of the user through the conference content display device of the user;

[0103] The speech content receiving unit is specifically used to: when in the listening mode and the other participant is speaking, receive the original speech content and the speech gesture of the other participant collected by the conference content display device of the other participant.

[0104] Optionally, the conference content display device of the user is in the listening mode, and the method further includes:

[0105] A gesture feedback unit, used to collect the user's feedback gestures for the target speech content through the user's conference content display device, wherein the feedback gestures are used to indicate the consistency between the target speech content and the original speech content;

[0106] When the feedback gesture indicates that the target speech content is inconsistent with the original speech content, an adjustment strategy of the speech gesture for the original speech content is adjusted.

[0107] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0108] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0109] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

[0110] Although the present invention includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments of the present invention may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0111] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0112] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for displaying conference content, characterized in that: The method comprises: Obtain the original speech content and speech gestures of the target participant in the target meeting; Adjusting the original speech content according to the speech gesture to generate target speech content; The target speech content is displayed.

2. The method according to claim 1, characterized in that The adjusting the original speech content according to the speech gesture includes: Determine a corresponding first keyword according to the speaking gesture, where the first keyword is used to represent a specific implementation of at least one second keyword; In the case where the first keyword matches the target second keyword in the original speech content, the target second keyword in the original speech content is replaced with the first keyword.

3. The method according to claim 1, characterized in that The adjusting the original speech content according to the speech gesture includes: Determine a corresponding emotion keyword according to the speech gesture, wherein the emotion keyword is used to represent the user's speech emotion; In the case where the emotion keyword matches the original speech content, the display style of the original speech content is adjusted according to the speech emotion.

4. The method according to claim 1, characterized in that: The types of the target conference include online virtual conferences and offline virtual conferences. At least some of the participants of the online virtual conference are in different conference scenes, and all the participants of the offline virtual conference are in the same conference scene.

5. The method according to claim 4, characterized in that The method further comprises: In the case that the target meeting is the offline virtual meeting, the acquisition operation of the speech gesture is canceled, and the target speech content is generated according to the original speech content.

6. The method according to claim 1, characterized in that The obtaining of the original speech content and speech gestures of the target participant in the target conference includes: In the case where the target participant is a user, collecting the original speech content and the speech gesture of the user through the conference content display device of the user; In the case that the target participant is another participant other than the wearer, the original speech content and the speech gesture of the other participant collected by the conference content display device of the other participant are received.

7. The method according to claim 6, characterized in that The conference content display device is configured with a speaking mode and a listening mode; The collecting of the original speech content and the speech gesture of the user through the conference content display device of the user comprises: when the conference content display device of the user is in the speech mode and the user is speaking, collecting the original speech content and the speech gesture of the user through the conference content display device of the user; The receiving the original speech content and the speaking gestures of the other participants collected by the conference content display device of the other participants includes: when the conference content display device of the user is in the listening mode and the other participants are speaking, receiving the original speech content and the speaking gestures of the other participants collected by the conference content display device of the other participants.

8. The method according to claim 7, characterized in that The conference content display device of the user is in the listening mode, and the method further includes: Collecting, by means of the conference content display device of the user, a feedback gesture of the user with respect to the target speech content, wherein the feedback gesture is used to indicate the consistency between the target speech content and the original speech content; When the feedback gesture indicates that the target speech content is inconsistent with the original speech content, an adjustment strategy of the speech gesture for the original speech content is adjusted.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

11. A conference content display device, characterized in that: The device comprises: A speech content acquisition unit, used to acquire the original speech content and speech gestures of the target participant in the target meeting; A speech content adjustment unit, configured to adjust the original speech content according to the speech gesture to generate target speech content; The speech content display unit is used to display the target speech content.

Images