CN111666746A - Method and device for generating conference summary, electronic equipment and storage medium - Google Patents
Method and device for generating conference summary, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111666746A CN111666746A CN202010506982.7A CN202010506982A CN111666746A CN 111666746 A CN111666746 A CN 111666746A CN 202010506982 A CN202010506982 A CN 202010506982A CN 111666746 A CN111666746 A CN 111666746A
- Authority
- CN
- China
- Prior art keywords
- conference summary
- target information
- conference
- information set
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Abstract
The application provides a method and a device for generating a conference summary, an electronic device and a storage medium, wherein voice recognition is performed on the audio of a speaker to obtain a speech text of the speaker, and a conference summary first draft is generated according to the speech text corresponding to each speaker in a conference, so that the problem of low recording accuracy caused by the fact that manual recording speed is slow or artificial subjective factors are adopted can be avoided, meanwhile, a target information set corresponding to keywords (such as key work items) of the conference summary first draft is obtained from a preset knowledge base, and the target information set is written into a preset position of the conference summary first draft to obtain the conference summary. Because the target information set includes information associated with the historical information of the keywords, information of the development history of the key work items can be known from the conference summary.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a method and an apparatus for generating a conference summary, an electronic device, and a storage medium.
Background
In the management process of a company, conference report discussion is often required to be performed on each work, and in a conference, the contents of each speaker in the conference are usually recorded and sorted by a conference recorder to form a conference summary. At present, the conference summary obtained by a manual recording mode is often low in accuracy (for example, part of content is omitted due to low recording speed, recording deviation is caused by artificial subjective factors, and the like), and the recorded conference summary only shows the situation of the conference, so that the development process of each key work item discussed in the conference is not convenient to understand.
Therefore, how to improve the accuracy of the conference summary and more comprehensively display the information of each work item of the conference becomes a problem to be solved urgently.
Disclosure of Invention
In order to achieve the above object, the present application provides the following technical solutions:
a method of generating a conference summary, comprising:
generating a conference summary according to a speech text corresponding to each speaker in a conference, wherein the speech text is obtained by performing voice recognition on speech audio of the speaker;
determining keywords included in the conference summary primary draft;
acquiring a target information set corresponding to the keyword, wherein the target information set comprises historical information associated with the keyword;
and writing the target information set into the conference summary primary draft to obtain a conference summary.
Optionally, the method for generating a conference summary draft according to the speech text corresponding to each speaker in the conference includes:
determining the connection sequence of each speaking text according to the marking time of each speaking text and the logical connection relation between the speaking texts; the marking time is an initial time point for collecting a speech audio corresponding to the speech text;
adding the identity information of a speaker corresponding to the speech text for each speech text; the identity information of a speaker corresponding to the speaking text is determined according to the speaking audio of the speaker and the pre-stored voiceprint characteristics of the speaker;
analyzing each speaking text added with the identity information, and reserving preset sentence components in the speaking text to obtain a target text corresponding to the speaking text;
sequentially writing each target text into a preset conference summary template according to the connection sequence of the speaking texts corresponding to each target text; and obtaining the conference summary primary draft.
Optionally, in the method, the obtaining of the target information set corresponding to the keyword includes:
determining a target entity node, wherein the target entity node is an entity node corresponding to the keyword in a pre-constructed knowledge graph model; the entity nodes included in the knowledge graph are obtained according to knowledge points included in historical conference summary;
and taking all the entity nodes with connecting edges with the target entity node as target information included in the target information set.
Optionally, the method further includes, after obtaining the meeting summary:
and outputting the conference summary, and storing all knowledge points included in the conference summary as the entity nodes in the knowledge graph after receiving an instruction for confirming that the conference summary is correct and input by a user.
Optionally, the determining the keyword included in the conference summary first draft includes:
and inputting the conference summary into an identification model, and enabling the identification model to extract and output the keywords from the conference summary according to a preset keyword extraction algorithm.
Optionally, in the method, writing the target information set into the conference summary first draft to obtain the conference summary, includes:
setting matching marks for the target information set and keywords corresponding to the target information set; the matching identifier is used for indicating that the target information set corresponds to the keyword; the keywords corresponding to the target information set are obtained by the target information set according to the keywords;
and writing the target information set carrying the matching identification into a preset position of the conference summary first draft to obtain the conference summary.
The above method, optionally, further includes: and when the target information set comprises a plurality of pieces of different target information, sequentially arranging the pieces of target information in the target information set according to the sequence of the generation time of each piece of target information.
An apparatus for generating a conference summary, comprising:
the conference system comprises a first generation unit, a second generation unit and a third generation unit, wherein the first generation unit is used for generating a conference summary draft according to a speech text corresponding to each speaker in a conference, and the speech text is obtained by performing voice recognition on speech audio of the speakers;
the determining unit is used for determining keywords included in the conference summary primary draft;
an obtaining unit, configured to obtain a target information set corresponding to the keyword, where the target information set includes history information associated with the keyword;
and the second generation unit is used for writing the target information set into the conference summary primary draft to obtain a conference summary.
An electronic device, comprising: a processor and a memory for storing a program; the processor is used for running the program to realize the method for generating the conference summary.
A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method of generating a conference summary described above.
According to the method and the device, voice recognition is carried out on the audio of a speaker to obtain the speech text of the speaker, a conference summary manuscript is generated according to the speech text corresponding to each speaker in a conference, the problem of low recording accuracy caused by the fact that manual recording speed is slow or artificial subjective factors are adopted can be solved, meanwhile, a target information set corresponding to keywords (such as key work items) of the conference summary manuscript is obtained from a preset knowledge base, and the target information set is written into the conference summary manuscript to obtain the conference summary. Because the target information set includes historical information associated with the keywords, information about the development history of the key work items can be known from the meeting summary.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for generating a conference summary disclosed in an embodiment of the present application;
fig. 2 is a flowchart of a method for generating a conference summary manuscript according to a speech text corresponding to each speaker in a conference disclosed in the embodiment of the present application;
fig. 3 is a schematic structural diagram of a conference summary generation apparatus disclosed in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a method for generating a conference summary provided in this application, which may include the following steps:
s101, generating a conference summary draft according to the speech text corresponding to each speaker in the conference.
In this embodiment, the speech audio of each speaker in the conference is collected in real time, and speech recognition is performed on the speech audio based on a preset speech recognition tool, so as to obtain corresponding speech content. Specific speech recognition methods can be found in the prior art.
In this step, the generated conference summary manuscript is a text obtained by preprocessing each utterance text, and a specific implementation manner may refer to a flowchart shown in fig. 2.
S102, determining keywords included in the conference summary primary draft.
The implementation mode of the step can be as follows: and inputting the conference summary into a preset identification model, and extracting and outputting keywords from the conference summary by the identification model according to a preset keyword extraction algorithm. The keyword extraction algorithm may be a TF-IDF algorithm or a TextRank algorithm, etc., and the detailed process of obtaining the keywords of the document using the TF-IDF algorithm or the TextRank algorithm may refer to the prior art.
Certainly, the conference summary manuscript may also be matched with a preset keyword library, and words included in the conference summary manuscript and existing in the keyword library are used as keywords of the conference summary manuscript. The words included in the keyword library can be set by self according to requirements.
S103, acquiring a target information set corresponding to the keyword.
In this embodiment, the target information set includes history information associated with a keyword, for example, if the keyword is a certain item, the associated history information may be introduction information about the item, historical progress information of the item, and the like.
Specific embodiments of this step may include steps a1 through a 2:
and step A1, determining the target entity node.
The target entity node is the entity node corresponding to the keyword in the pre-constructed knowledge graph model.
The established knowledge graph is composed of a plurality of entity nodes, the entity nodes in the knowledge graph comprise knowledge points in historical conference summary, and the historical conference summary is a conference summary generated by a historical held conference. Further, each entity node in the knowledge graph of this embodiment may carry a conference name and a conference holding time of a corresponding conference, and the conference corresponding to the entity node is a conference summary knowledge point of the conference. In this embodiment, the detailed process of constructing the knowledge graph according to the knowledge points may refer to the prior art. And will not be described in detail herein.
In this step, the keywords may be matched with each entity node in the knowledge graph, and the entity node obtained through matching is determined as the entity node corresponding to the keyword in the knowledge graph model. The matching between the keyword and the entity node may be that the keyword is the same as the entity node, or the similarity reaches a preset threshold.
Step a2, using all entity nodes having connection edges with the target entity node as target information included in the target information set.
In this embodiment, any two entity nodes connected by the connection edge are nodes having an association relationship, and any one entity node may be connected to a plurality of different entity nodes by the connection edge. For example, if the first entity node is a project name, the second entity node connected to the first entity node may be a project establishment time, a person in charge of the project, or a progress of the project.
In this embodiment, all entity nodes having a connection edge with an entity node are used as target information included in a target information set, so that each target information included in the target information set is information associated with a keyword. Further, because the entity nodes included in the knowledge graph include knowledge points in the historically generated conference summary, the target information included in the target information set is information related to the historical conference associated with the keywords.
And S104, writing the target information set into the primary draft of the conference summary to obtain the conference summary.
The specific implementation mode of the step comprises a step B1 and a step B2:
and step B1, setting matching identifiers for the target information set and the keywords corresponding to the target information set.
The matching identification is used for indicating that the target information set corresponds to the keyword, and the keyword corresponding to the target information set is obtained by the target information set according to the keyword. The matching identifier may be a matching code, or a matching line connecting the target information set and the keyword, and any identifier that can indicate that the target information set corresponds to the keyword may be used as the matching identifier.
And step B2, writing the target information set carrying the matching identification into a preset position of the primary draft of the conference summary to obtain the conference summary.
In this step, the target information set carrying the matching identifier is written into the conference summary first draft, so that the obtained conference summary can show the target information associated with the keywords.
In this embodiment, when the target information set includes a plurality of different pieces of target information, the entry target information may be sequentially arranged in the target information set according to a sequence of time points (for example, time points of a conference), included in each piece of target information, so that the displayed target information in the target information set is arranged according to the time sequence, and thus, better readability is achieved.
According to the method provided by the embodiment, voice recognition is performed on the audio of the speaker to obtain the speech text of the speaker, and the conference summary first draft is generated according to the speech text corresponding to each speaker in the conference, so that the problem of low recording accuracy caused by the adoption of the factors of low manual recording speed or human subjectivity can be avoided, meanwhile, a target information set corresponding to keywords (such as key work items) of the conference summary first draft is obtained from a preset knowledge base, and the target information set is written into the preset position of the conference summary first draft to obtain the conference summary. Because the set of target information is included as historical information associated with the keywords, information about the development history of the key work items can be learned from the meeting summary.
In the above embodiment, after the conference summary is obtained, the conference summary is output, and after an instruction for confirming that the conference summary is correct, which is input by a user, is received, the conference summary is stored, each knowledge point in the conference summary is obtained, and each knowledge point included in the conference summary is stored in the knowledge graph as an entity node.
Fig. 2 is a specific implementation manner of generating a conference summary first draft according to a speech text corresponding to each speaker in the conference in S101 in the foregoing embodiment, and may include the following steps:
s201, determining the connection sequence of the speaking texts according to the marking time of the speaking texts and the logical connection relation between the speaking texts.
In this embodiment, the marked time of the speech text is an initial time point at which a speech audio corresponding to the speech text is collected, and is also a time point at which a speaker starts to speak.
The specific implementation manner of the step is as follows: taking the sequence of the marked time of each utterance text from front to back as the first connection sequence of each utterance text, determining the logical connection relationship between the utterance texts by adopting a natural language processing technology, and adjusting the first connection sequence of each utterance text based on the logical connection relationship between the utterance texts, wherein the first connection sequence of each utterance text is, for example: and the speaking text A-speaking text B-speaking text C-speaking text D, wherein the logical connection relationship between the speaking texts is that the speaking text A is connected with the speaking text D, and the first connection sequence is adjusted to be the speaking text A-speaking text D-speaking text B-speaking text C. And finally, taking the adjusted connection sequence of each speech text as a final connection sequence. The logical connection relationship includes a context logical relationship, an event association relationship, and the like. In particular, the detailed manner of determining the logical connection relationship between the speaking texts by using the natural language processing technology can refer to the prior art.
And S202, adding the identity information of the speaker corresponding to the speech text for each speech text.
The identity information of the speaker can be the name of the speaker, the identity information of the speaker corresponding to the speaking text, determined according to the audio frequency of the speaker and the pre-stored voiceprint characteristics of the speaker,
the specific implementation manner of the step is as follows: and carrying out voiceprint recognition on the collected speech audio to obtain voiceprint characteristics of the speaker, matching the voiceprint characteristics of the speaker with the prestored voiceprint characteristics, and presetting corresponding identity information of the voiceprint characteristics obtained through matching to be used as identity information of the speaker corresponding to the speech text. When the voiceprint feature of the speaker is matched with the prestored voiceprint feature and a matching result cannot be obtained, the preset standby identity information can be adopted as the identity information of the speaker corresponding to the speech text. And finally, according to the sentence components, taking the identity information of the speaker as a subject of the speech text, and adding the identity information of the speaker into the speech text.
And S203, analyzing each speech text added with the identity information, and reserving preset sentence composition components in the speech text to obtain a target text corresponding to the speech text.
In this step, each utterance text is preprocessed by a self-language processing method, unnecessary sentence components (e.g., adjective components) such as various moods are deleted, and preset sentence components (e.g., subject components, predicate components, object components, etc.) in the utterance text are retained, so as to obtain a target text corresponding to the utterance text.
And S204, sequentially writing each target text in a preset conference summary template according to the connection sequence of the speaking texts corresponding to each target text to obtain a conference summary manuscript.
In this step, the target texts can be written into the conference summary template in sequence in a line feed mode among the target texts.
According to the method provided by the embodiment, the sequence of the utterance text corresponding to each speaker in the conference summary manuscript is determined according to the sequence from front to back of the marking time of each utterance text and the logical connection relation, the sentence components of the utterance text are preprocessed, the necessary sentence components preset in the utterance text are reserved, and the obtained conference summary manuscript has better readability.
Fig. 3 is a schematic structural diagram of an apparatus 300 for generating a conference summary, provided in an embodiment of the present application, including:
the first generating unit 301 is configured to generate a conference summary according to a speech text corresponding to each speaker in the conference, where the speech text is obtained by performing speech recognition on speech audio of the speaker.
A determining unit 302, configured to determine a keyword included in the conference summary manuscript.
An obtaining unit 303, configured to obtain a target information set corresponding to a keyword, where the target information set includes history information associated with the keyword.
And a second generating unit 304, configured to write the target information set into the first draft of the conference summary, so as to obtain the conference summary.
Optionally, the apparatus 300 further includes a storage unit 305, configured to output the conference summary, and store each knowledge point included in the conference summary as an entity node in the knowledge graph after receiving an instruction input by a user to confirm that the conference summary is error-free.
Optionally, the specific implementation manner of generating the conference summary first draft by the first generating unit 301 according to the speech text corresponding to each speaker in the conference is as follows:
determining the connection sequence of each speaking text according to the marking time of each speaking text and the logical connection relation between the speaking texts; marking time as an initial time point for collecting a speech audio corresponding to the speech text;
adding the identity information of a speaker corresponding to the speech text for each speech text; the identity information of a speaker corresponding to the speaking text is determined according to the speaking audio of the speaker and the pre-stored voiceprint characteristics of the speaker;
analyzing each speech text added with the identity information, and reserving necessary sentence components preset in the speech text to obtain a target text corresponding to the speech text;
and according to the connection sequence of the speaking texts corresponding to the target texts, sequentially writing the target texts in a preset conference summary template to obtain a conference summary manuscript.
Optionally, the specific implementation manner of acquiring the target information set corresponding to the keyword by the acquiring unit 303 is to determine an entity node corresponding to the keyword in a pre-constructed knowledge graph model; the entity nodes included in the knowledge graph are obtained according to the historical conference summary including the knowledge points; and taking all entity nodes with connecting edges existing with the entity nodes as target information included in the target information set.
Optionally, the determining unit 302 determines the keywords included in the conference summary manuscript, including: and inputting the conference summary into the recognition model, so that the recognition model extracts and outputs keywords from the conference summary according to a preset keyword extraction algorithm.
Optionally, the second generating unit 304 writes the target information set into the primary manuscript of the conference summary, and a specific implementation manner of obtaining the conference summary is as follows: setting matching identification for the target information set and the keywords corresponding to the target information set; the matching identification is used for indicating that the target information set corresponds to the keyword; the keywords corresponding to the target information set are obtained by the target information set according to the keywords; and writing the target information set carrying the matching identification into a preset position of the primary draft of the conference summary to obtain the conference summary.
Optionally, the second generating unit 304 is further configured to, in a case that the target information set includes a plurality of pieces of different target information, sequentially arrange the pieces of target information in the target information set according to an order of generation time of each piece of target information.
The device provided by the application carries out speech recognition to the audio frequency of speaker and obtains the speech text of speaker to according to the speech text that every speaker corresponds in the meeting, generate the first draft of meeting summary, can avoid adopting the problem that the artifical recording speed is slow or the recording accuracy that artificial subjective factor leads to is low, simultaneously, obtain the target information set that the keyword (for example key work item) of the first draft of meeting summary corresponds from the knowledge base that predetermines, and write in the predetermined position of the first draft of meeting summary with the target information set, obtain the meeting summary. Because the set of target information is included as historical information associated with the keywords, information about the development history of the key work items can be learned from the meeting summary.
An embodiment of the present application further provides an electronic device 400, a schematic structural diagram of which is shown in fig. 4, and the electronic device specifically includes: a processor 401 and a memory 402, the memory 402 being for storing programs; the processor 401 is configured to run a program to implement the method for generating a conference summary in the embodiment of the present application.
The embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer is enabled to execute the method for generating the conference summary in the embodiment of the present application.
The functions described in the method of the embodiment of the present application, if implemented in the form of software functional units and sold or used as independent products, may be stored in a storage medium readable by a computing device. Based on such understanding, part of the contribution to the prior art of the embodiments of the present application or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for generating a conference summary, comprising:
generating a conference summary according to a speech text corresponding to each speaker in a conference, wherein the speech text is obtained by performing voice recognition on speech audio of the speaker;
determining keywords included in the conference summary primary draft;
acquiring a target information set corresponding to the keyword, wherein the target information set comprises historical information associated with the keyword;
and writing the target information set into the conference summary primary draft to obtain a conference summary.
2. The method of claim 1, wherein generating a conference summary draft according to the utterance text corresponding to each speaker in the conference comprises:
determining the connection sequence of each speaking text according to the marking time of each speaking text and the logical connection relation between the speaking texts; the marking time is an initial time point for collecting a speech audio corresponding to the speech text;
adding the identity information of a speaker corresponding to the speech text for each speech text; the identity information of a speaker corresponding to the speaking text is determined according to the speaking audio of the speaker and the pre-stored voiceprint characteristics of the speaker;
analyzing each speaking text added with the identity information, and reserving preset sentence components in the speaking text to obtain a target text corresponding to the speaking text;
sequentially writing each target text into a preset conference summary template according to the connection sequence of the speaking texts corresponding to each target text; and obtaining the conference summary primary draft.
3. The method according to claim 1, wherein the obtaining of the target information set corresponding to the keyword comprises:
determining a target entity node, wherein the target entity node is an entity node corresponding to the keyword in a pre-constructed knowledge graph model; the entity nodes included in the knowledge graph are obtained according to knowledge points included in historical conference summary;
and taking all the entity nodes with connecting edges with the target entity node as target information included in the target information set.
4. The method of claim 3, wherein after obtaining the meeting summary, further comprising:
and outputting the conference summary, and storing all knowledge points included in the conference summary as the entity nodes in the knowledge graph after receiving an instruction for confirming that the conference summary is correct and input by a user.
5. The method of claim 1, wherein determining keywords included in the conference summary manuscript comprises:
and inputting the conference summary into an identification model, and enabling the identification model to extract and output the keywords from the conference summary according to a preset keyword extraction algorithm.
6. The method of claim 1, wherein writing the target set of information into the conference summary manuscript to obtain the conference summary comprises:
setting matching marks for the target information set and keywords corresponding to the target information set; the matching identifier is used for indicating that the target information set corresponds to the keyword; the keywords corresponding to the target information set are obtained by the target information set according to the keywords;
and writing the target information set carrying the matching identification into a preset position of the conference summary first draft to obtain the conference summary.
7. The method of claim 6, further comprising: and when the target information set comprises a plurality of pieces of different target information, sequentially arranging the pieces of target information in the target information set according to the sequence of the generation time of each piece of target information.
8. An apparatus for generating a conference summary, comprising:
the conference system comprises a first generation unit, a second generation unit and a third generation unit, wherein the first generation unit is used for generating a conference summary draft according to a speech text corresponding to each speaker in a conference, and the speech text is obtained by performing voice recognition on speech audio of the speakers;
the determining unit is used for determining keywords included in the conference summary primary draft;
an obtaining unit, configured to obtain a target information set corresponding to the keyword, where the target information set includes history information associated with the keyword;
and the second generation unit is used for writing the target information set into the conference summary primary draft to obtain a conference summary.
9. An electronic device, comprising: a processor and a memory for storing a program; the processor is configured to run the program to implement the method of generating a conference summary of any of claims 1-7.
10. A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method of generating a conference summary of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506982.7A CN111666746B (en) | 2020-06-05 | 2020-06-05 | Conference summary generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506982.7A CN111666746B (en) | 2020-06-05 | 2020-06-05 | Conference summary generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111666746A true CN111666746A (en) | 2020-09-15 |
| CN111666746B CN111666746B (en) | 2023-09-29 |
Family
ID=72386829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506982.7A Active CN111666746B (en) | 2020-06-05 | 2020-06-05 | Conference summary generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111666746B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307085A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112328653A (en) * | 2020-10-30 | 2021-02-05 | 北京百度网讯科技有限公司 | Data identification method and device, electronic equipment and storage medium |
| CN112861510A (en) * | 2021-02-08 | 2021-05-28 | 北京字跳网络技术有限公司 | Summary processing method, apparatus, device and storage medium |
| CN113014540A (en) * | 2020-11-24 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| CN113113016A (en) * | 2021-04-08 | 2021-07-13 | 百度在线网络技术（北京）有限公司 | Audio processing method and device |
| CN113256262A (en) * | 2021-06-04 | 2021-08-13 | 上海明略人工智能(集团)有限公司 | Automatic generation method and system of conference summary, storage medium and electronic equipment |
| CN113691382A (en) * | 2021-08-25 | 2021-11-23 | 平安国际智慧城市科技股份有限公司 | Conference recording method, conference recording device, computer equipment and medium |
| CN113794853A (en) * | 2021-09-07 | 2021-12-14 | 广州朗堃电子科技有限公司 | Conference summary generation method for remote video conference and conference terminal |
| CN114531563A (en) * | 2022-02-16 | 2022-05-24 | 广州市哲闻信息科技有限公司 | Video conference control method and system |
| CN116304109A (en) * | 2023-03-30 | 2023-06-23 | 上海云思智慧信息技术有限公司 | Conference knowledge graph-based retrieval method, system, medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314638A (en) * | 2010-06-30 | 2012-01-11 | 国际商业机器公司 | Be used for the historical method and system of managerial meeting |
| CN108022583A (en) * | 2017-11-17 | 2018-05-11 | 平安科技（深圳）有限公司 | Meeting summary generation method, application server and computer-readable recording medium |
| JP2018163435A (en) * | 2017-03-24 | 2018-10-18 | Kddi株式会社 | Conference minutes support device |
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109388701A (en) * | 2018-08-17 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Minutes generation method, device, equipment and computer storage medium |
| CN109817245A (en) * | 2019-01-17 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Generation method, device, computer equipment and the storage medium of meeting summary |
| CN110765753A (en) * | 2019-12-27 | 2020-02-07 | 广东博智林机器人有限公司 | Method, system, computer device and storage medium for generating file |
-
2020
- 2020-06-05 CN CN202010506982.7A patent/CN111666746B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314638A (en) * | 2010-06-30 | 2012-01-11 | 国际商业机器公司 | Be used for the historical method and system of managerial meeting |
| JP2018163435A (en) * | 2017-03-24 | 2018-10-18 | Kddi株式会社 | Conference minutes support device |
| CN108022583A (en) * | 2017-11-17 | 2018-05-11 | 平安科技（深圳）有限公司 | Meeting summary generation method, application server and computer-readable recording medium |
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109388701A (en) * | 2018-08-17 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Minutes generation method, device, equipment and computer storage medium |
| CN109817245A (en) * | 2019-01-17 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Generation method, device, computer equipment and the storage medium of meeting summary |
| CN110765753A (en) * | 2019-12-27 | 2020-02-07 | 广东博智林机器人有限公司 | Method, system, computer device and storage medium for generating file |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307085A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112328653A (en) * | 2020-10-30 | 2021-02-05 | 北京百度网讯科技有限公司 | Data identification method and device, electronic equipment and storage medium |
| CN112307085B (en) * | 2020-10-30 | 2024-04-09 | 北京百度网讯科技有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN112328653B (en) * | 2020-10-30 | 2023-07-28 | 北京百度网讯科技有限公司 | Data identification method, device, electronic equipment and storage medium |
| CN113014540A (en) * | 2020-11-24 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| CN113014540B (en) * | 2020-11-24 | 2022-09-27 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| WO2022166962A1 (en) * | 2021-02-08 | 2022-08-11 | 北京字跳网络技术有限公司 | Method and apparatus for processing minutes, device, and storage medium |
| CN112861510A (en) * | 2021-02-08 | 2021-05-28 | 北京字跳网络技术有限公司 | Summary processing method, apparatus, device and storage medium |
| CN113113016B (en) * | 2021-04-08 | 2022-10-11 | 百度在线网络技术（北京）有限公司 | Audio processing method and device |
| CN113113016A (en) * | 2021-04-08 | 2021-07-13 | 百度在线网络技术（北京）有限公司 | Audio processing method and device |
| CN113256262A (en) * | 2021-06-04 | 2021-08-13 | 上海明略人工智能(集团)有限公司 | Automatic generation method and system of conference summary, storage medium and electronic equipment |
| CN113691382A (en) * | 2021-08-25 | 2021-11-23 | 平安国际智慧城市科技股份有限公司 | Conference recording method, conference recording device, computer equipment and medium |
| CN113794853A (en) * | 2021-09-07 | 2021-12-14 | 广州朗堃电子科技有限公司 | Conference summary generation method for remote video conference and conference terminal |
| CN114531563A (en) * | 2022-02-16 | 2022-05-24 | 广州市哲闻信息科技有限公司 | Video conference control method and system |
| CN116304109A (en) * | 2023-03-30 | 2023-06-23 | 上海云思智慧信息技术有限公司 | Conference knowledge graph-based retrieval method, system, medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111666746B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666746B (en) | Conference summary generation method and device, electronic equipment and storage medium | |
| US9014363B2 (en) | System and method for automatically generating adaptive interaction logs from customer interaction text | |
| CN109767787B (en) | Emotion recognition method, device and readable storage medium | |
| CN108062955B (en) | Intelligent report generation method, system and equipment | |
| CN110493019B (en) | Automatic generation method, device, equipment and storage medium of conference summary | |
| CN112560449B (en) | Text quality detection method and device, electronic equipment and storage medium | |
| CN113379398B (en) | Project requirement generation method and device, electronic equipment and storage medium | |
| JP5025353B2 (en) | Dialog processing apparatus, dialog processing method, and computer program | |
| KR102476099B1 (en) | METHOD AND APPARATUS FOR GENERATING READING DOCUMENT Of MINUTES | |
| CN111063355A (en) | Conference record generation method and recording terminal | |
| CN110825840B (en) | Word bank expansion method, device, equipment and storage medium | |
| CN112363903A (en) | Fault report generation method and device, electronic equipment and computer readable medium | |
| CN112395391A (en) | Concept graph construction method and device, computer equipment and storage medium | |
| CN113782026A (en) | Information processing method, device, medium and equipment | |
| CN110598008A (en) | Data quality inspection method and device for recorded data and storage medium | |
| CN113095204B (en) | Double-recording data quality inspection method, device and system | |
| CN110738061A (en) | Ancient poetry generation method, device and equipment and storage medium | |
| KR102030551B1 (en) | Instant messenger driving apparatus and operating method thereof | |
| EP4187463A1 (en) | An artificial intelligence powered digital meeting assistant | |
| CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
| KR20130073709A (en) | Method and apparatus of recognizing business card using image and voice information | |
| CN115691503A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN109344388A (en) | A kind of comment spam recognition methods, device and computer readable storage medium | |
| KR20180073226A (en) | System and method for counseling record summarizing and computer readable record medium thereof | |
| CN114155841A (en) | Voice recognition method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |