Information processing method, electronic equipment and storage medium

Abstract

The invention provides an information processing method, electronic equipment and a storage medium, and relates to the technical field of video processing. The method comprises the steps that voice information in a network conference is counted, to-be-matched words with the word frequency higher than a preset frequency threshold value in the voice information are obtained, and the network conference is a conference discussed based on professional questions in a preset field; the to-be-matched words are matched with preset words in a preset knowledge base, a target statement is determined, the preset knowledge base is a database storing a plurality of preset words and information for explaining the preset words, and the preset words correspond to the professional questions; and displaying the target statement in the network conference. Through the target word, the participants of the network conference can be helped to better understand the core content of the network conference, the occurrence proportion of the phenomenon that the participants speaking on the network conference are interrupted due to the fact that the to-be-matched word is not understood is reduced, the network conference can be carried out more smoothly, and the information interaction efficiency in the network conference is improved.

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to an information processing method, an electronic device and a storage medium. Background Art

[0002] At present, when using network conferencing technology for multi-party conference interaction, the interaction is usually carried out by sending text messages or voice messages. This traditional interaction method not only limits the efficiency of information interaction among conference participants, but also interrupts conference participants who are speaking in the meeting, making it impossible for the speaker to explain the relevant topic normally, reducing the conference participants' understanding of the relevant topic and reducing the conference participants' experience. Summary of the invention

[0003] The present application provides an information processing method, an electronic device and a storage medium.

[0004] An embodiment of the present application provides an information processing method, which includes: performing statistics on voice information in an online conference to obtain words to be matched in the voice information whose frequency is higher than a preset frequency threshold, wherein the online conference is a conference for discussing professional issues in a preset field; matching the words to be matched with preset words in a preset knowledge base to determine a target sentence, wherein the preset knowledge base is a database storing multiple preset words and information explaining the preset words, and the preset words correspond to professional issues; and displaying the target sentence in the online conference.

[0005] An embodiment of the present application provides an electronic device, including: one or more processors; a memory, on which one or more programs are stored. When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the information processing methods in the embodiments of the present application.

[0006] An embodiment of the present application provides a readable storage medium, which stores a computer program. When the computer program is executed by a processor, any one of the information processing methods in the embodiments of the present application is implemented.

[0007] According to the information processing method, electronic device and storage medium of the embodiments of the present application, by collecting statistics on voice information in a network conference for discussing professional issues in a preset field, words to be matched whose frequency in the voice information is higher than a preset frequency threshold are obtained, and words to be matched whose frequency is higher than the preset frequency threshold can be screened out from the voice information to facilitate obtaining the core content of the network conference; the words to be matched are matched with preset words in a preset knowledge base to determine a target sentence, wherein the preset knowledge base is a database storing multiple preset words and information explaining the preset words, and the preset words correspond to professional issues. Then, the target sentence is displayed in the network conference, and the target words can help the participants of the network conference to better understand the core content of the network conference, reduce the proportion of participants who interrupt the speakers in the network conference due to misunderstanding of the matching words, enable the network conference to proceed more smoothly, and improve the efficiency of information interaction in the network conference.

[0008] With regard to the above embodiments and other aspects of the present application and their implementation, further description is provided in the accompanying drawings, detailed description and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flowchart of an information processing method provided in an embodiment of the present application is shown.

[0010] Figure 2 A block diagram showing the composition of an information processing system provided by an embodiment of the present application is shown.

[0011] Figure 3 A flow chart showing a method for processing information in a network conference by a server in an information processing system provided in an embodiment of the present application.

[0012] Figure 4 A schematic diagram showing a target sentence displayed in a network conference provided by an embodiment of the present application is shown.

[0013] Figure 5 A schematic diagram showing a target sentence displayed in a network conference provided by an embodiment of the present application is shown.

[0014] Figure 6 A block diagram showing the composition of an information processing device provided by an embodiment of the present application is shown.

[0015] Figure 7 A structural diagram showing an exemplary hardware architecture of a computing device capable of implementing the information processing method and apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present application more clear, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other arbitrarily without conflict.

[0017] When using network conferencing technology for multi-party conference interaction, the interaction is usually carried out by sending text messages or voice messages. This traditional interaction method not only limits the efficiency of information exchange among conference participants, but also interrupts conference participants who are speaking in the meeting, making it impossible for the speaker to explain the relevant topic normally, reducing the conference participants' understanding of the relevant topic and reducing the conference experience of the conference participants.

[0018] The present application provides an information processing method, an electronic device and a storage medium to solve the above problems.

[0019] Figure 1 The flowchart of the information processing method provided by the embodiment of the present application is shown. The method can be applied to an information processing device, and the information processing device can be set in a server. Figure 1 As shown, the information processing method in the embodiment of the present application includes but is not limited to the following steps.

[0020] Step S101 , collect statistics on voice information in the network conference to obtain words to be matched in the voice information whose frequency is higher than a preset frequency threshold.

[0021] Among them, online conferences are meetings for discussing professional issues in preset fields.

[0022] For example, the professional problems in the preset field may be problems in the communication field, such as problems analyzing certain business data; the professional problems in the preset field may also be problems based on discussions on a certain biological flora in the biological field, etc.

[0023] The above professional issues in the preset fields are only examples, and specific settings can be made according to actual needs. Other professional issues in the preset fields that are not described are also within the protection scope of this application and will not be repeated here.

[0024] Step S102, matching the words to be matched with the preset words in the preset knowledge base to determine the target sentence.

[0025] The preset knowledge base is a database storing a plurality of preset words and information explaining the preset words, and the preset words correspond to professional questions.

[0026] For example, when the professional problem in the preset field is a problem of analyzing certain business data in the communication field, professional terms such as Channel Quallity Indecation (CQI) and Hybrid Automatic Repeat Request (HARQ) may appear during the online conference. The participants in the conference discussion may not be familiar with the above professional terms, and the preset terms stored in the preset knowledge base include the above different professional terms, so that when matching the words to be matched with the preset terms in the preset knowledge base, professional terms such as CQI and HARQ can be quickly found from the preset knowledge base, as well as information explaining professional terms such as CQI and HARQ, and then the target sentence is determined based on the above information, which better helps the participants to understand the above professional terms more accurately.

[0027] Step S103: display the target sentence in the network conference.

[0028] In this embodiment, by collecting statistics on voice information in an online conference that discusses professional issues in a preset field, words to be matched whose frequency in the voice information is higher than a preset frequency threshold are obtained, and words to be matched whose frequency is higher than the preset frequency threshold can be screened out from the voice information to facilitate obtaining the core content of the online conference; the words to be matched are matched with preset words in a preset knowledge base to determine a target sentence, wherein the preset knowledge base is a database that stores multiple preset words and information explaining the preset words, and the preset words correspond to professional issues. Then, the target sentence is displayed in the online conference, and the target words can help the participants of the online conference to better understand the core content of the online conference, reduce the proportion of participants who interrupt the speakers in the online conference due to misunderstanding of the matching words, enable the online conference to proceed more smoothly, and improve the efficiency of information interaction in the online conference.

[0029] In some exemplary embodiments, before executing step S101 of counting the voice information in the network conference to obtain the words to be matched in the voice information whose frequency is higher than a preset frequency threshold, the method also includes: obtaining the voice information in the network conference; and storing the obtained voice information in a preset storage unit.

[0030] The preset storage unit may be a data storage unit (e.g., a database, etc.) in a server corresponding to the network conference. By storing the acquired voice information in the preset storage unit, it is convenient to organize and count the voice information in the network conference, and obtain the words to be matched in the voice information whose word frequency is higher than the preset frequency threshold.

[0031] It should be noted that during the online conference, there is not only voice information, but also text information and image information for interaction between participants. In some embodiments, the above text information and image information can also be stored in a preset storage unit, thereby enriching the information stored in the preset storage unit and making the statistically obtained words to be matched richer.

[0032] In some exemplary embodiments, the step S101 of collecting statistics on the voice information in the network conference to obtain the to-be-matched words in the voice information whose word frequency is higher than a preset frequency threshold can be implemented in the following manner:

[0033] At every preset time interval, the voice information in the network conference received within the preset time is counted to obtain the word frequency corresponding to each candidate word in the voice information; according to the word frequency corresponding to each candidate word, multiple candidate words in the voice information are sorted to obtain a sorting result; based on the sorting result, the to-be-matched word is determined, and the to-be-matched word is a word whose word frequency among the multiple candidate words is higher than a preset frequency threshold.

[0034] The preset duration can be configured according to actual needs, for example, the preset duration is 20 seconds, 30 seconds, 1 minute, etc. The above preset duration is only an example, and other unspecified preset durations are also within the protection scope of this application and will not be repeated here.

[0035] The word frequency corresponding to the candidate word is the number of times the candidate word appears in the voice information received in the network conference within a preset time period.

[0036] By sorting multiple candidate words in the voice information according to the word frequency corresponding to each candidate word, the obtained sorting result can reflect the number of times each candidate word appears in the voice information in the online conference, thereby screening out words with a higher number of appearances in the voice information (that is, words with a word frequency higher than a preset frequency threshold), and then using the words with a word frequency higher than the preset frequency threshold as words to be matched, so that the words to be matched that appear a higher number of times in the voice information in the online conference can be selected and explained (for example, matching the words to be matched with preset words in a preset knowledge base, determining a target sentence, and using the target sentence to explain the words to be matched), thereby improving the participants' understanding of the information in the online conference.

[0037] In some exemplary embodiments, displaying the target sentence in the network conference in step S103 may be implemented in the following manner: the target sentence is popped up in real time in an interactive window corresponding to the network conference.

[0038] For example, the target sentence may be popped up in the interactive window corresponding to the online conference in real time by using the bullet screen method, so that the participants can obtain the target sentence in the interactive window in real time, thereby enabling the participants to better understand the words in the online conference.

[0039] For another example, a window can be fixed in the display interface of the network conference for displaying the target sentence. The above display method of the target sentence is only an example, and the display method of the target sentence can be set according to actual needs. Other unspecified display methods of the target sentence are also within the scope of protection of this application and will not be repeated here.

[0040] In some exemplary embodiments, the step S102 of matching the words to be matched with the preset words in the preset knowledge base to determine the target sentence can be implemented in the following manner:

[0041] The words to be matched are matched with a plurality of preset words in a preset knowledge base respectively for similarity, and a target word with a word similarity greater than a preset similarity threshold is obtained; a target sentence is generated based on the target word and its corresponding text description information.

[0042] The text description information corresponding to the target word is the information explaining the target word stored in the preset knowledge base.

[0043] For example, the words to be matched can be displayed in the form of a string, and then the string corresponding to the words to be matched is matched with the strings corresponding to each preset word in the preset knowledge base, such as using the edit distance algorithm (EditDistance) to calculate the similarity between the string corresponding to the words to be matched and the strings corresponding to each preset word in the preset knowledge base. The higher the cost of converting one string into another, the lower the similarity between the two strings. Then, based on the similarities between the obtained multiple strings, the word similarities between the words to be matched and each preset word in the preset knowledge base are determined, and from the multiple word similarities, the words with word similarities greater than the preset similarity threshold are selected as target words, thereby obtaining the target words and their corresponding text description information, and generating the target sentence based on the target words and their corresponding text description information.

[0044] For another example, the similarity between the word to be matched and each preset word is determined based on the Euclidean distance. The Euclidean distance is to map the word to be matched and the preset word to two points in the plane space respectively, then calculate the Euclidean distance between the two points, and determine which preset word the word to be matched is more similar to based on the length of each Euclidean distance.

[0045] If the Euclidean distance between the point corresponding to the to-be-matched word and the point corresponding to a preset word is shorter, it indicates that the to-be-matched word is more similar to the preset word; conversely, if the Euclidean distance between the point corresponding to the to-be-matched word and the point corresponding to the preset word is longer, it indicates that the similarity between the to-be-matched word and the preset word is very low. Further, by sorting based on the obtained multiple Euclidean distances, the preset word corresponding to the point with the shortest Euclidean distance can be obtained, and the preset word corresponding to the point with the shortest Euclidean distance is used as the target word.

[0046] By screening out target words whose similarity is greater than a preset similarity threshold in different ways, the text description information corresponding to the target word in the preset knowledge base can be obtained, so as to better explain the words to be matched based on the text description information, so that the generated target sentences can help participants better understand the words in the online conference and improve the interaction efficiency of the online conference.

[0047] In some exemplary embodiments, a target sentence is generated based on a target word and its corresponding textual description information, including: determining the location information of the textual description information corresponding to the target word in a preset knowledge base; generating a jump link based on the location information; and generating a target sentence based on the target word and the jump link.

[0048] The jump link is used for participants in the online conference to operate in the interactive window corresponding to the online conference to obtain the target word and its corresponding text description information.

[0049] For example, if the target sentence is "MM" and the location information of the text description information corresponding to the target word in the preset knowledge base is "http: / / abc.789.com", the generated target sentence can be "MM: http: / / abc.789.com". This enables participants to obtain the network address "http: / / abc.789.com" corresponding to "MM" in the interactive window corresponding to the online conference, and use the network address to obtain the text description information of "MM" in the preset knowledge base, so as to better understand "MM".

[0050] For another example, "MM" can be used as a hyperlink to generate a target sentence, where the address connected to the hyperlink is "http: / / abc.789.com". This allows participants to operate the hyperlink displayed in the form of "MM" in the interactive window corresponding to the online conference, obtain the text description information of "MM" in the preset knowledge base, and better understand "MM".

[0051] In some exemplary embodiments, before performing step S103 of displaying the target sentence in the online conference, the method further includes: applying to a preset knowledge base for preset information reading permission when it is determined that the participant of the online conference does not have preset information reading permission.

[0052] The preset information reading permission is the permission to obtain text description information corresponding to the target sentence in the preset knowledge base based on the jump link.

[0053] For example, the terminal corresponding to the participant of the online conference sends a permission request message to the preset knowledge base, and the permission request message includes a request identifier for obtaining permission to read the preset information; when it is determined that the permission response message fed back by the preset knowledge base carries an authorization license, the participant can access the preset sentences and their corresponding text description information in the preset knowledge base based on the authorization license.

[0054] Furthermore, when a participant clicks on a jump link, since the participant has authorization permission to access preset sentences and their corresponding text description information in the preset knowledge base, he or she can obtain the target sentence corresponding to the jump link in the preset knowledge base and the text description information corresponding to the target sentence based on the authorization permission.

[0055] Among them, the preset knowledge base can be a data knowledge base within a certain enterprise, or it can be a knowledge base unique to a department within a certain enterprise. Therefore, when accessing data to the preset knowledge base, it is necessary to have preset information reading permissions to reduce the possibility of data leakage in the preset knowledge base and improve data security.

[0056] In some exemplary embodiments, after executing step S103 of displaying the target sentence in the online conference, the method also includes: generating initial meeting minutes based on the voice information stored in a preset storage unit; updating the initial meeting minutes according to the target sentence to generate target meeting minutes; and sending the target meeting minutes to the terminals corresponding to the participants of the online conference.

[0057] In some embodiments, the voice information can be converted into text information based on manual recognition or artificial intelligence recognition, and then the initial meeting minutes are generated based on the text information. The initial meeting minutes include the core information of the online meeting (for example, the technical solution, the information discussed by each participant on the core content of the technical solution, etc.).

[0058] Furthermore, the target words and their corresponding textual description information in the target sentence are also added to the initial meeting minutes, so that the participants can better understand the core information of the online meeting. The target sentence can include the target word and its corresponding jump link; the target sentence can also include the explanation information of the target word (i.e., the textual description information corresponding to the target word, etc.).

[0059] The target meeting minutes are sent to the corresponding terminals of the participants of the online meeting through the conference assistant notification or email notification, so that each participant can easily and quickly obtain the target meeting minutes, facilitate the follow-up work related to the topics discussed in the online meeting, and improve work efficiency.

[0060] Figure 2 FIG. 1 is a block diagram showing the composition of the information processing system provided by the embodiment of the present application. Figure 2 As shown, the information processing system includes but is not limited to the following devices: a server 210, a plurality of terminals (eg, a first terminal 221, a second terminal 222, ..., an nth terminal 22n, where n is an integer greater than 1).

[0061] The multiple terminals conduct a network conference through the server 210, so that the multiple terminals can conduct remote problem discussions, technical solution negotiations, and other processes.

[0062] The server 210 can implement any information processing method provided in the embodiments of the present application. In addition, each terminal can display the interactive interface of the network conference through its display device, as well as the target sentence displayed in the interactive interface, wherein the target sentence is the target sentence determined by the server 210 performing statistics on the voice information in the network conference, obtaining the words to be matched in the voice information with a word frequency higher than a preset frequency threshold, and matching the words to be matched with the preset words in the preset knowledge base.

[0063] Figure 3 The flowchart of the method for processing information in a network conference by a server in an information processing system provided by an embodiment of the present application is shown. Figure 3 As shown, the method for the server in the information processing system to process the information in the network conference includes but is not limited to the following steps.

[0064] Step S301 : multiple participants start a multi-party interactive network conference on a network conference platform provided by the server 210 based on their corresponding terminals.

[0065] Step S302, determining whether to start statistical processing of information in the network conference.

[0066] If it is determined to start statistical processing of the information in the network conference, step S303 is executed; otherwise, the process ends.

[0067] Step S303, obtaining voice information in the network conference, and storing the obtained voice information in a preset storage unit.

[0068] Step S304: At each preset time interval, the voice information received in the network conference within the preset time is counted to obtain the to-be-matched words in the voice information whose frequency is higher than a preset frequency threshold.

[0069] In some embodiments, based on the word frequency corresponding to each candidate word in the voice information, multiple candidate words in the voice information are sorted to obtain a sorting result; the words to be matched are determined based on the sorting result, and the words to be matched are words among the multiple candidate words whose word frequency is higher than a preset frequency threshold.

[0070] The preset duration can be configured according to actual needs, for example, the preset duration is 20 seconds, 30 seconds, 1 minute, etc. The above preset duration is only an example, and other unspecified preset durations are also within the protection scope of this application and will not be repeated here.

[0071] Step S305, matching the words to be matched with the preset words in the preset knowledge base to determine the target sentence.

[0072] Among them, the words to be matched can be used to generate a word vector corresponding to the words to be matched based on artificial intelligence, and then the word vector to be matched can be compared with the preset word vectors corresponding to each preset word in the preset knowledge base, so as to determine the preset word vector with the highest matching degree as the target word vector; and then generate the target sentence according to the target word corresponding to the target word vector and the text description information corresponding to the target word.

[0073] In some embodiments, the target word can be obtained in the following manner: the word to be matched is matched with multiple preset words in a preset knowledge base for similarity, and a target word is obtained whose word similarity is greater than a preset similarity threshold (for example, the preset similarity threshold can be configured to 85%, 90%, etc.).

[0074] The text description information corresponding to the target word is the information explaining the target word stored in the preset knowledge base.

[0075] Step S306: Pop up the target sentence in the interactive window corresponding to the online conference in real time, so that the participants in the online conference can obtain the target word and its corresponding text description information.

[0076] Participants can clarify the meaning of target words based on the target words and their corresponding text description information that pop up in the interactive window, so that participants can have an in-depth understanding of the content of the online conference and promote the smooth progress of the online conference.

[0077] Figure 4 A schematic diagram showing a target sentence displayed in a network conference provided by an embodiment of the present application is shown. Figure 4 As shown, the display interface of the network conference 400 includes an interactive interface 410 of the network conference and a participant list 420 .

[0078] The participant list 420 includes member 1, member 2, member 3, ..., member k, which can be an integer greater than or equal to 2, and k represents the number of participants participating in the network conference.

[0079] In the interactive interface 410 of the online conference, each participant will communicate in the form of voice messages, text messages, etc., and during the online conference, the target words and their corresponding text description information will pop up in the form of bullet screens, etc. For example, Figure 4 The "Video conference: a meeting in which people in two or more locations have face-to-face conversations through communication equipment and the Internet" and "PC: Personal Computer" etc. shown can enable participants to know the specific meaning of the target words that appear during the online conference and increase participants' understanding of the target words.

[0080] In some embodiments, in some embodiments, the content that pops up in the interactive window may also include a jump link, which is a link generated based on the location information of the text description information corresponding to the target word in the preset knowledge base.

[0081] For example, Figure 5 A schematic diagram showing a target sentence displayed in a network conference provided by an embodiment of the present application is shown. Figure 5 As shown, Figure 5 The various display windows and their components in the network conference 400 Figure 4 The same as shown, no further description is given here.

[0082] However, in Figure 5 In the event, the jump link will be displayed in the form of a bullet screen. If the text description information for a target word is too long, the jump link method is used to allow participants to click on the jump link according to their own needs, which can reduce the display area of ​​the bullet screen and make it suitable for more participants to view.

[0083] For example, Figure 5The barrage information includes "Video conference: http: / / 123.xyz.com", "PC: http: / / 456.abz.com", etc., where "http: / / 123.xyz.com" and "http: / / 456.abz.com" both represent the location information of the text description information corresponding to the target word in the preset knowledge base.

[0084] Participants can use the jump links in the point-set interaction window to view the explanation information of the target words in the preset knowledge base in real time, so as to learn more contextual information and background knowledge related to the topic of the online meeting, improve the interaction efficiency of the online meeting, and enhance the user experience.

[0085] Step S307: Generate initial meeting minutes based on the voice information stored in the preset storage unit.

[0086] Among them, the voice information can be converted into text information based on manual recognition or artificial intelligence recognition, and then the initial meeting minutes can be generated based on the text information.

[0087] Step S308, updating the initial meeting minutes according to the target sentence, generating a target meeting minutes, and sending the target meeting minutes to the terminals corresponding to the participants of the network conference.

[0088] The target meeting minutes can be obtained by the terminal corresponding to the participant of the network meeting through the conference assistant notification or email notification. In addition, the target meeting minutes can include the target words and their corresponding text description information displayed in the interactive window in step S306, and / or jump links, so that the participants can review them after the meeting.

[0089] Figure 6 FIG. 1 is a block diagram showing the composition of an information processing device provided by an embodiment of the present application. Figure 6 As shown, the information processing device 600 includes but is not limited to the following modules.

[0090] The statistics module 601 is configured to collect statistics on the voice information in the network conference and obtain the words to be matched in the voice information whose frequency is higher than a preset frequency threshold.

[0091] Among them, online conferences are meetings for discussing professional issues in preset fields.

[0092] The matching module 602 is configured to match the words to be matched with the preset words in the preset knowledge base to determine the target sentence.

[0093] The preset knowledge base is a database storing a plurality of preset words and information explaining the preset words, and the preset words correspond to professional questions.

[0094] The display module 603 is configured to display the target sentence in the network conference.

[0095] It should be noted that the information processing device 600 in this embodiment can implement any information processing method in the embodiments of the present application.

[0096] According to the device of the embodiment of the present application, the voice information in the network conference for discussing professional issues in a preset field is counted through the statistical module to obtain the to-be-matched words whose frequency in the voice information is higher than the preset frequency threshold, and the to-be-matched words whose frequency is higher than the preset frequency threshold can be screened out from the voice information to facilitate obtaining the core content of the network conference; the to-be-matched words are matched with the preset words in the preset knowledge base using the matching module to determine the target sentence, wherein the preset knowledge base is a database storing multiple preset words and information explaining the preset words, and the preset words correspond to the professional issues, and then, the target sentence is displayed in the network conference using the display module, and the target words can be used to help the participants of the network conference better understand the core content of the network conference through the target words, reduce the proportion of participants who interrupt the speakers in the network conference due to misunderstanding of the matching words, enable the network conference to proceed more smoothly, and improve the efficiency of information interaction in the network conference.

[0097] It should be clear that the present invention is not limited to the specific configurations and processes described in the above embodiments and shown in the figures. For the convenience and brevity of description, a detailed description of the known methods is omitted here, and the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, which will not be repeated here.

[0098] Figure 7 A structural diagram showing an exemplary hardware architecture of a computing device capable of implementing the information processing method and apparatus according to an embodiment of the present invention.

[0099] like Figure 7 As shown, the computing device 700 includes an input device 701, an input interface 702, a central processing unit 703, a memory 704, an output interface 705, and an output device 706. The input interface 702, the central processing unit 703, the memory 704, and the output interface 705 are connected to each other via a bus 707, and the input device 701 and the output device 706 are connected to the bus 707 via the input interface 702 and the output interface 705, respectively, and are further connected to other components of the computing device 700.

[0100] Specifically, the input device 701 receives input information from the outside and transmits the input information to the central processing unit 703 through the input interface 702; the central processing unit 703 processes the input information based on the computer executable instructions stored in the memory 704 to generate output information, temporarily or permanently stores the output information in the memory 704, and then transmits the output information to the output device 706 through the output interface 705; the output device 706 outputs the output information to the outside of the computing device 700 for user use.

[0101] In one embodiment, Figure 7 The computing device shown may be implemented as an electronic device, which may include: a memory configured to store a program; and a processor configured to run the program stored in the memory to execute the information processing method described in the above embodiment.

[0102] In one embodiment, Figure 7 The computing device shown may be implemented as an information processing system, which may include: a memory configured to store a program; and a processor configured to run the program stored in the memory to execute the information processing method described in the above embodiment.

[0103] The above is only an exemplary embodiment of the present application and is not intended to limit the scope of protection of the present application. In general, various embodiments of the present application can be implemented in hardware or special circuits, software, logic or any combination thereof. For example, some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, a microprocessor or other computing device, although the present application is not limited thereto.

[0104] Embodiments of the present application may be implemented by a processor executing computer program instructions, such as in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

[0105] The block diagram of any logic flow in the accompanying drawings of the present application can represent program steps, or can represent interconnected logic circuits, modules and functions, or can represent a combination of program steps and logic circuits, modules and functions. The computer program can be stored on a memory. The memory can have any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read-only memory (ROM), random access memory (RAM), optical memory device and system (digital versatile disc DVD or CD disc), etc. Computer-readable media may include non-transient storage media. The processor can be any type suitable for the local technical environment, such as but not limited to a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (FGPA) and a processor based on a multi-core processor architecture.

[0106] By way of exemplary and non-limiting examples, a detailed description of exemplary embodiments of the present application has been provided above. However, various modifications and adjustments to the above embodiments will be apparent to those skilled in the art when considered in conjunction with the accompanying drawings and claims, but will not depart from the scope of the present invention. Therefore, the proper scope of the present invention will be determined according to the claims.

Claims

1. An information processing method, characterized in that: The method comprises: Performing statistics on voice information in the online conference to obtain words to be matched in the voice information whose word frequency is higher than a preset frequency threshold, wherein the online conference is a conference for discussing professional issues in a preset field; Matching the words to be matched with preset words in a preset knowledge base to determine a target sentence, wherein the preset knowledge base is a database storing a plurality of the preset words and information explaining the preset words, and the preset words correspond to the professional question; The target sentence is displayed in the network conference.

2. The method according to claim 1, characterized in that The method of collecting statistics on the voice information in the network conference and obtaining the words to be matched in the voice information whose frequency is higher than a preset frequency threshold includes: At each preset time interval, the voice information in the network conference received within the preset time is counted to obtain the word frequency corresponding to each candidate word in the voice information; Sorting the multiple candidate words in the voice information according to the word frequencies corresponding to the candidate words to obtain a sorting result; The to-be-matched words are determined according to the ranking result, and the to-be-matched words are words whose frequency is higher than the preset frequency threshold among the multiple candidate words.

3. The method according to claim 1, characterized in that The displaying of the target sentence in the network conference includes: The target sentence is popped up in real time in the interactive window corresponding to the network conference.

4. The method according to claim 1, characterized in that: The step of matching the words to be matched with preset words in a preset knowledge base to determine a target sentence includes: Performing similarity matching on the words to be matched with a plurality of preset words in the preset knowledge base respectively, and obtaining target words whose word similarity is greater than a preset similarity threshold; The target sentence is generated based on the target word and its corresponding textual description information, wherein the textual description information corresponding to the target word is information explaining the target word stored in the preset knowledge base.

5. The method according to claim 4, characterized in that The step of generating the target sentence according to the target word and its corresponding text description information includes: Determine the location information of the text description information corresponding to the target word in the preset knowledge base; Generate a jump link according to the location information; The target sentence is generated according to the target word and the jump link.

6. The method according to claim 5, characterized in that The jump link is used for the participants in the network conference to operate in the interactive window corresponding to the network conference to obtain the target word and its corresponding text description information.

7. The method according to claim 5 or 6, characterized in that: Before displaying the target sentence in the network conference, the method further includes: When it is determined that the participant of the online conference does not have the preset information reading permission, an application is made to the preset knowledge base to obtain the preset information reading permission, wherein the preset information reading permission is the permission to obtain the text description information corresponding to the target sentence in the preset knowledge base based on the jump link.

8. The method according to claim 7, characterized in that Before the voice information in the network conference is counted and the words to be matched whose frequency in the voice information is higher than a preset frequency threshold are obtained, the method further includes: Obtaining voice information in the network conference; The acquired voice information is stored in a preset storage unit.

9. The method according to claim 8, characterized in that After displaying the target sentence in the network conference, the method further includes: Generating initial meeting minutes based on the voice information stored in the preset storage unit; The initial meeting minutes are updated according to the target sentence to generate a target meeting minutes, wherein the target sentence includes a target word and a corresponding jump link; The target conference minutes are sent to terminals corresponding to participants of the network conference.

10. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the information processing method according to any one of claims 1 to 9.

11. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the information processing method according to any one of claims 1 to 9 is implemented.

Images