CN113642294A - Method, apparatus, device, medium and product for generating a conference summary - Google Patents
Method, apparatus, device, medium and product for generating a conference summary Download PDFInfo
- Publication number
- CN113642294A CN113642294A CN202110930151.7A CN202110930151A CN113642294A CN 113642294 A CN113642294 A CN 113642294A CN 202110930151 A CN202110930151 A CN 202110930151A CN 113642294 A CN113642294 A CN 113642294A
- Authority
- CN
- China
- Prior art keywords
- information
- conference
- sample
- target
- point
- 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
-
- 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
- G06F16/35—Clustering; Classification
Abstract
The present disclosure provides methods, apparatus, devices, media and products for generating a conference summary, relating to the field of computer technology, in particular to the field of artificial intelligence technology. The specific implementation scheme is as follows: acquiring initial conference information; filtering the initial conference information to obtain target conference information; determining classification information of the target conference information based on the target conference information and a preset information classification model; the classified information at least comprises meeting point information and meeting non-point information; generating a meeting summary based on the meeting point information and the meeting non-point information. This implementation can improve the conference summary generation efficiency.
Description
Technical Field
The present disclosure relates to the field of computer technology, and more particularly to the field of artificial intelligence technology.
Background
At present, in an office scene, a conference is often required to be organized, and a corresponding conference summary is generated according to conference contents. Wherein, effectual meeting brief can go on backtracking and deposit to the meeting to can assist improvement work efficiency.
The current generation mode of the conference summary is generally to manually summarize the conference content to obtain the conference summary. However, the way of manually summarizing the conference content to obtain the conference summary has the problem that the conference summary generation efficiency is low.
Disclosure of Invention
The present disclosure provides a method, apparatus, device, medium, and article of manufacture for generating a conference summary.
According to an aspect of the present disclosure, there is provided a method for generating a conference summary, comprising: acquiring initial conference information; filtering the initial conference information to obtain target conference information; determining classification information of the target conference information based on the target conference information and a preset information classification model; the classified information at least comprises meeting point information and meeting non-point information; generating a meeting summary based on the meeting point information and the meeting non-point information.
According to another aspect of the present disclosure, there is provided an apparatus for generating a conference summary, comprising: an information acquisition unit configured to acquire initial conference information; the information filtering unit is configured to filter the initial conference information to obtain target conference information; an information classification unit configured to determine classification information of the target conference information based on the target conference information and a preset information classification model; the classified information at least comprises meeting point information and meeting non-point information; a conference summary generation unit configured to generate a conference summary based on the conference point information and the conference non-point information.
According to another aspect of the present disclosure, there is provided an electronic device including: one or more processors; a memory for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method for generating a conference summary as any one of above.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method for generating a conference summary as any one of the above.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method for generating a conference summary as any one of the above.
According to the technology disclosed by the invention, the method for generating the conference summary is provided, and the generation efficiency of the conference summary can be improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present disclosure may be applied;
FIG. 2 is a flow diagram for one embodiment of a method for generating a meeting summary according to the present disclosure;
FIG. 3 is a schematic diagram of one application scenario of a method for generating a conference summary according to the present disclosure;
FIG. 4 is a flow diagram of another embodiment of a method for generating a meeting summary according to the present disclosure;
FIG. 5 is a schematic block diagram of one embodiment of an apparatus for generating a conference summary according to the present disclosure;
FIG. 6 is a block diagram of an electronic device for implementing a method for generating a conference summary of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, and 103 may be electronic devices such as a mobile phone, a computer, and a tablet, the terminal devices 101, 102, and 103 may be installed with software for performing an online conference, and a user may perform a multi-person conference through the software, and the software may have an intelligent conference summary generation function. When the user selects to start the intelligent conference summary generation function, the terminal devices 101, 102, and 103 may convert the voice of each user participating in the conference into initial conference information in text form, and send the initial conference information to the server 105 through the network 104, so that the server 105 returns the corresponding conference summary.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, an in-vehicle computer, an in-vehicle tablet, a vehicle control device, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server providing various services, for example, the server 105 may obtain initial meeting information transmitted by the terminal devices 101, 102, and 103 through the network 104, filter the initial meeting information to obtain target meeting information, determine meeting point information and meeting non-point information based on the target meeting information and an information classification model, generate a meeting summary based on the meeting point information and the meeting non-point information, and return the meeting summary to the terminal devices 101, 102, and 103.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for generating a conference summary provided by the embodiment of the present disclosure may be executed by the terminal devices 101, 102, and 103, or may be executed by the server 105, and the apparatus for generating a conference summary may be disposed in the terminal devices 101, 102, and 103, or may be disposed in the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating a conference summary in accordance with the present disclosure is shown. The method for generating the conference summary of the embodiment comprises the following steps:
In the present embodiment, an executing subject (such as the terminal devices 101, 102, 103 or the server 105 in fig. 1) may acquire conference information generated in a conference. The conference information may be information for describing conference contents in various forms such as text, audio, video, and the like. The conference may be an online conference performed based on online conference software, or may be an offline conference, which is not limited in this embodiment. Preferably, the execution subject converts the speaking voice of each participant in the conference process into corresponding text information based on a voice-to-text technology in the conference process to obtain initial conference information. The initial conference information at this time is information for describing conference contents in a text form. Or, the executing agent may also directly use the audio or video form in the conference process as the initial conference information, and then determine the corresponding classification information for the conference information to generate the conference summary.
In this embodiment, the initial conference information collected by the execution subject is information generated based on the original conference content in the conference process, and includes the discussion situation of each participant, and a spoken language is often used in the conference discussion process of each participant. Thus, the executing agent, after obtaining the initial meeting information, may filter the initial meeting information to filter out these spoken languages. These spoken languages may include, but are not limited to, words with different tone, words with different pronunciation, etc. in spoken language, which is not limited by the embodiment. The executing agent may process the words using existing speech recognition techniques, such as filtering the words from the initial meeting information to obtain the target meeting information that conforms to the written language.
In some optional implementation manners of this embodiment, the filtering the initial conference information to obtain the target conference information may include: removing the spoken language from the initial conference information to obtain initial conference information after removal processing; and performing semantic analysis on the initial meeting information after the removal processing, replacing the words which do not accord with the written expression, and adjusting the word order which does not accord with the written expression to obtain target meeting information. With the optional implementation manner, the execution subject can convert the spoken initial conference information into the target conference information conforming to the written expression by means of word filtering, word replacement, word order adjustment and the like. Through carrying out information classification to the target meeting information that more accords with the written expression, generate the meeting summary, can further improve the precision of the meeting summary of generation.
In this embodiment, the preset information classification model is used to classify the target meeting information to obtain classification information of the target meeting information, that is, to obtain meeting point information and meeting non-point information in the target meeting information. The conference key information refers to key information in a conference, and the conference non-key information refers to common information in the conference. The meeting point information may include, but is not limited to, meeting backlog, meeting conclusion, and the like, where meeting backlog refers to backlog determined to be completed subsequently in a meeting, and the meeting conclusion is a conclusive description of the meeting. The conference non-essential point information may be all other information except the conference essential point information in the target conference information, or may also be information obtained by further screening all other information, which is not limited in this embodiment.
Further, after obtaining the target meeting information, the executing entity may input the target meeting information into a preset information classification model, so that the preset information classification model outputs a category corresponding to each statement in the target meeting information. The executive body can collect the sentences belonging to the conference main point category to obtain conference main point information, and collect the sentences belonging to the conference non-main points to obtain the conference non-main point information.
And step 204, generating a conference summary based on the conference point information and the conference non-point information.
In this embodiment, after determining that the meeting point information and the non-point information of the meeting are obtained, the executing entity may directly output the meeting point information as a meeting summary, or may output the meeting point information and the non-point information of the meeting together as the meeting summary, which is not limited in this embodiment.
In some optional implementations of this embodiment, generating the meeting summary based on the meeting point information and the meeting non-point information may include: acquiring a target conference summary template, wherein the target conference summary template comprises a conference key point area and a conference non-key point area; and filling the meeting point information into a meeting point area in a meeting summary template, and filling the meeting non-point information into a meeting non-point area in the meeting summary template to obtain a meeting summary. By adopting the mode, the personalized conference summary template can be adopted, and the conference key point information and the conference non-key point information are filled into the corresponding positions in the template, so that the display diversity of the conference summary is improved.
With continued reference to fig. 3, a schematic diagram of one application scenario of a method for generating a conference summary in accordance with the present disclosure is shown. In the application scenario of fig. 3, each participant can perform an online conference, a conference video screen 301 may be displayed in the application software for performing the online conference, and the participant can control and display information such as a shared desktop or a face screen in the conference video screen 301. And during the conference discussion by the participants, the executive agent may display the textual content of the discussion by each participant A, B, C in real-time in conference information display area 302. The executive body can acquire the voice information of the participants, convert the voice information into text information, and output the text information in the conference information display area 302 in real time. Optionally, the execution main body may further filter the text information, so that the filtered text information is updated synchronously with the output content of the conference information display area 302. The specific filtering manner herein may refer to a manner of filtering the initial conference information to obtain the target conference information, and is not described herein again. Then, the execution main body may determine the filtered text information as input data of a preset information classification model, and obtain classification information of the text information output by the preset information classification model, that is, a category corresponding to each text statement in the text information, where the category includes a conference conclusion, a conference to be dealt with, and a conference non-point. The executive body may aggregate the sentences of each category in the text information based on the classification information to generate a meeting summary 303. The conference summary 303 includes a text statement set corresponding to a conference conclusion, a text statement set corresponding to a conference to be dealt with, and a text statement set corresponding to a conference non-essential point.
According to the method for generating the conference summary provided by the embodiment of the disclosure, the initial conference information is filtered to obtain the target conference information, the classification information of the target conference information is determined based on the target conference information and the preset information classification model, and the conference summary is generated based on the conference key point information and the conference non-key point information in the classification information, so that the automatic generation of the conference summary can be realized, and the generation efficiency of the conference summary is improved.
With continued reference to FIG. 4, a flow 400 of another embodiment of a method for generating a conference summary in accordance with the present disclosure is shown. As shown in fig. 4, the method for generating a conference summary of the present embodiment may include the following steps:
In this embodiment, the executive agent may set a pre-training task that requires training the pre-training model in advance. The pre-training task is used for training the identification of key information in the designated information. The key information may include, but is not limited to, a key subject, a key object, a key action, and the like in the specific information, which is not limited in this embodiment. For example, the pre-training task may be a preset sentence set, each sentence in the sentence set includes a subject, an action, and an object, each sentence in the pre-training task is used as input data of the pre-training model, the pre-training model is trained to output the subject, the action, and the object corresponding to the sentence, and the target pre-training model after training can identify the subject, the action, and the object corresponding to each sentence more accurately.
In some optional implementation manners of this embodiment, pre-training the pre-training model based on a preset pre-training task, and obtaining the trained target pre-training model may include: determining task input data and task marking data corresponding to a pre-training task; inputting the task input data into a pre-training model so that the pre-training model outputs a key information identification result corresponding to the task input data; and continuously adjusting model parameters of the pre-training model based on the key information identification result and the task marking data to obtain a trained target pre-training model.
In this implementation, the pre-training task may correspond to a plurality of preset sentences, and the execution subject may determine the plurality of preset sentences as task input data corresponding to the pre-training task. And each preset sentence can be labeled with the subject, action and object of the sentence in advance. That is, the pre-labeled subjects, actions, and objects are the task labeling data corresponding to the pre-training task. Then, the executive subject may input the task input data into the pre-training model, so that the pre-training model identifies the key information in the task input data, that is, identifies the subject, the action, and the object corresponding to each sentence. And then, the execution main body can obtain a key information identification result which is output by the pre-training model and corresponds to the task input data, substitutes a loss function based on the key information identification result and the task marking data, and continuously adjusts the model parameters of the pre-training model based on the difference between the key information identification result and the task marking data so that the key information identification result continuously approaches the task marking data, so that the loss function is converged, and the trained target pre-training model is obtained.
At step 402, sample information is obtained.
In this embodiment, the sample information includes meeting information in the historical meeting record, for example, the meeting information may be a text-form meeting record obtained by converting voices of participants in the historical meeting.
In this embodiment, the preset information condition is used to roughly filter the sample information, preliminarily filter each category in the sample information, and preliminarily determine information that is not a sample point in the sample information. Specifically, the preset information condition may include, but is not limited to, occurrence of a specified keyword, a length smaller than a specified length threshold, a length larger than a specified threshold, and the like, which is not limited in this embodiment. The specified keyword is a preset keyword in which the non-main point information frequently appears. And since a shorter length is not generally a sample gist, information having a length smaller than a specified length threshold is determined as sample non-gist information. And since a longer length is generally not suitable as a sample gist, information having a length greater than a specified length threshold is determined as sample non-gist information. Further optionally, after roughly screening the sample information based on the preset information condition, the execution subject may mark the roughly screened sample non-point information, output the roughly screened sample point information to the user, receive a further label of the roughly screened sample point information from the user, determine information labeled as the sample point information by the user as final sample point information, and determine information labeled as the sample non-point information by the user as final sample non-point information.
In response to determining that the information quantity difference between the sample non-point information and the sample point information is greater than a preset threshold, resampling the sample information, step 404.
In this embodiment, since the number of information of non-points in the conference information is generally larger than that of points in practice, there is a problem of sample imbalance. After obtaining the sample non-point information and the sample point information, the execution subject may further determine an information quantity difference between the sample non-point information and the sample point information, where the quantity difference may be a quantity difference of the text statements. Under the condition that the information quantity difference value between the sample non-point information and the sample point information is larger than a preset threshold value, the sample information needs to be resampled to realize sample equalization. The resampling process may adopt various resampling techniques in the prior art, which is not limited in this embodiment. Specifically, the execution subject may further determine an information quantity difference between the sample non-point information and the sample point information after resampling, and if the information quantity difference is greater than a preset threshold, the resampling process may be continued until the information quantity difference is less than or equal to the preset threshold. Alternatively, the execution subject may also calculate a ratio between the sample non-point information and the sample point information, preset a threshold corresponding to the ratio, and resample the sample information if the ratio is greater than the threshold corresponding to the ratio. The resampling process may include, but is not limited to, reducing the number of sample non-point information, increasing the number of sample point information, and the like, which is not limited in this embodiment.
In this embodiment, the sample annotation data may be annotation data corresponding to each piece of information in the sample information, and the annotation data is a main point or a non-main point. The main points and non-main points herein can be further subdivided into more detailed categories, for example, the main points include pending matters and conclusions, which are not limited in this embodiment. The execution subject can add corresponding category labels based on the sample non-point information and the sample point information to generate sample labeling data.
And step 406, training the target pre-training model based on the sample information and the sample labeling data so that the target pre-training model outputs a sample classification corresponding to the sample information, and adjusting model parameters of the target pre-training model based on the sample classification, the sample labeling data and a preset loss function until the preset loss function is converged to obtain a preset information classification model.
In this embodiment, the sample classification includes a sample gist and a sample non-gist; and the weight corresponding to the sample important point in the loss function is larger than the weight corresponding to the sample non-important point. The execution subject may input the sample information into the target pre-training model to obtain information that belongs to sample points in the sample information output by the target pre-training model and information that belongs to non-sample points in the sample information, that is, sample classification corresponding to the sample information. And then, the execution subject can substitute the sample classification and sample labeling data corresponding to the sample information into a preset loss function, and continuously adjust the model parameters of the target pre-training model until the preset loss function is converged to obtain the preset information classification model.
In this embodiment, the target conference category is a conference that is not suitable for point, non-point classification, for example, the target conference category may be an interview. The execution subject may determine an information category of the initial conference information based on an information analysis technique, and acquire the initial conference information when the information category is not the target conference category.
In the model training phase, the historical conference record corresponding to the acquired sample information may also be a historical conference record that is not of the target conference category.
And step 408, filtering the tone words in the initial conference information to obtain the filtered initial conference information.
In this embodiment, the execution subject may filter the mood words in the initial meeting information after acquiring the initial meeting information. Optionally, the execution main body may preset a to-be-filtered vocabulary, and by matching the initial conference information with the to-be-filtered vocabulary, it is possible to filter out a vocabulary word matched with the to-be-filtered vocabulary in the initial conference information, and obtain the filtered initial conference information. The settings of the vocabulary to be filtered may be determined based on both manual settings and historical meeting record mining. When the historical conference records are mined to determine the language and qi words to be filtered, the occurrence frequency of the language and qi words serving as independent sentences in the historical conference records can be counted, the occurrence frequency of the language and qi words serving as dependent sentences in the historical conference records can be counted, and then the language and qi words with high occurrence frequency are further mined.
And step 409, filtering repeated words in the filtered initial conference information to obtain target conference information.
In this embodiment, the execution subject may determine repeated words in the filtered initial conference information based on an existing text recognition technology, remove the repeated words, implement filtering of the repeated words, and obtain the target conference information.
In some optional implementation manners of this embodiment, the filtering repeated words in the filtered initial conference information to obtain the target conference information may include: determining meaningful repeated words in the filtered initial conference information; and filtering the repeated words except the meaningful repeated words in the filtered initial conference information to obtain the target conference information.
In this implementation manner, the execution subject may preset a repeated word white list, where the repeated word white list is a set of meaningful repeated words, and the meaningful repeated words may be words such as "seeing" and "considering". When repeating word filtering is performed, words matched with the repeating words in the repeating word white list in the filtered initial conference information can be determined, that is, meaningful repeating words are determined. And then, the executive body can remove the words of the non-meaningful repeated words without removing the meaningful repeated words to obtain the target meeting information. The repeated word white list can be set based on corpus mining of written text records, and meaningful repeated words which frequently meet the standard are determined and added to the repeated word white list.
In this embodiment, the information classification model obtained through the training in the model training step can output corresponding classification information based on the input target meeting information. The classification information is a classification result of each piece of information in the target conference information, that is, conference key point information belonging to key points in the target conference information and conference non-key point information belonging to non-key points in the target conference information are output.
In this embodiment, please refer to the detailed description of step 204 for the detailed description of step 411, which is not repeated herein.
The method for generating the conference summary provided by the embodiment of the disclosure can also perform the filtering of the language words and the filtering of the repeated words on the initial conference information, and can obtain more accurate target conference information. And when repeated words are filtered, the removal of meaningful repeated words is considered, so that the filtering accuracy of the repeated words is improved. In addition, in the training process of the information classification model, the model can be assisted in training based on a preset pre-training task, and the recognition capability of the model on key information is improved. And when the sample information category is determined, rough screening can be performed on the basis of preset information conditions, sample classification can be obtained on the basis of rough screening and manual labeling, and the sample classification accuracy can be improved. And, to the unbalanced problem of sample, can carry out resampling to the sample, realized sample equilibrium. And for the conference categories which are not suitable for determining the key points and the non-key points, the direct filtering can be carried out, the key points and the non-key points are not classified, and the classification reliability is further improved.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present disclosure provides an embodiment of an apparatus for generating a conference summary, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to electronic devices such as a terminal device, a server, and the like.
As shown in fig. 5, the apparatus 500 for generating a conference summary of the present embodiment includes: an information acquisition unit 501, an information filtering unit 502, an information classification unit 503, and a conference schedule generation unit 504.
An information acquisition unit 501 configured to acquire initial conference information.
And an information filtering unit 502 configured to filter the initial conference information to obtain target conference information.
An information classification unit 503 configured to determine classification information of the target conference information based on the target conference information and a preset information classification model; the classification information includes at least meeting gist information and meeting non-gist information.
A meeting summary generation unit 504 configured to generate a meeting summary based on the meeting point information and the meeting non-point information.
In some optional implementations of the present embodiment, the information filtering unit 502 is further configured to: filtering the tone words in the initial conference information to obtain filtered initial conference information; and filtering repeated words in the filtered initial conference information to obtain target conference information.
In some optional implementations of this embodiment, the apparatus further includes: the model training unit is configured to pre-train the pre-training model based on a preset pre-training task to obtain a trained target pre-training model; training the target pre-training model based on the sample information and the sample marking data to enable the target pre-training model to output a sample classification corresponding to the sample information, and adjusting model parameters of the target pre-training model based on the sample classification, the sample marking data and a preset loss function until the preset loss function is converged to obtain a preset information classification model.
In some optional implementations of this embodiment, the apparatus further includes: a sample acquisition unit configured to acquire sample information; determining sample non-point information and sample point information in the sample information based on preset information conditions; and determining sample marking data based on the sample non-point information and the sample point information.
In some optional implementations of this embodiment, the sample acquisition unit is further configured to: and in response to determining that the information quantity difference between the sample non-point information and the sample point information is greater than a preset threshold, resampling the sample information.
In some optional implementations of this embodiment, the sample classification includes a sample gist and a sample non-gist; and the weight corresponding to the sample important point in the loss function is larger than the weight corresponding to the sample non-important point.
In some optional implementations of this embodiment, the model training unit is further configured to: determining task input data and task marking data corresponding to a pre-training task; inputting the task input data into a pre-training model so that the pre-training model outputs a key information identification result corresponding to the task input data; and continuously adjusting model parameters of the pre-training model based on the key information identification result and the task marking data to obtain a trained target pre-training model.
In some optional implementations of this embodiment, the information obtaining unit 501 is further configured to: in response to determining that the information category of the initial meeting information is not the target meeting category, obtaining the initial meeting information.
It should be understood that the units 501 to 504 recited in the apparatus 500 for generating a conference summary correspond to respective steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method of using a car phone are equally applicable to the apparatus 500 and the units included therein and will not be described in detail here.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 601 performs the various methods and processes described above, such as the method for generating a conference summary. For example, in some embodiments, the method for generating a meeting summary may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM603 and executed by the computing unit 601, one or more steps of the method for generating a conference summary described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform the method for generating the conference summary.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (21)
1. A method for generating a conference summary, comprising:
acquiring initial conference information;
filtering the initial conference information to obtain target conference information;
determining classification information of the target conference information based on the target conference information and a preset information classification model; the classification information at least comprises meeting point information and meeting non-point information;
and generating a conference summary based on the conference point information and the conference non-point information.
2. The method of claim 1, wherein the filtering the initial meeting information to obtain target meeting information comprises:
filtering the language words in the initial conference information to obtain filtered initial conference information;
and filtering repeated words in the filtered initial conference information to obtain the target conference information.
3. The method of claim 2, wherein the filtering repeated words in the filtered initial meeting information to obtain the target meeting information comprises:
determining meaningful repeated words in the filtered initial conference information;
and filtering repeated words except the meaningful repeated words in the filtered initial conference information to obtain the target conference information.
4. The method of claim 1, wherein the preset information classification model is trained based on the following steps:
pre-training the pre-training model based on a preset pre-training task to obtain a trained target pre-training model;
training the target pre-training model based on sample information and sample labeling data to enable the target pre-training model to output a sample classification corresponding to the sample information, and adjusting model parameters of the target pre-training model based on the sample classification, the sample labeling data and a preset loss function until the preset loss function is converged to obtain the preset information classification model.
5. The method of claim 4, wherein the method further comprises:
obtaining sample information;
determining sample non-point information and sample point information in the sample information based on preset information conditions;
determining the sample annotation data based on the sample non-point information and the sample point information.
6. The method of claim 5, wherein the method further comprises:
resampling the sample information in response to determining that an information quantity difference between the sample non-point information and the sample point information is greater than a preset threshold.
7. The method of claim 4, wherein the sample classification includes a sample point and a sample non-point; and the weight corresponding to the sample point in the loss function is greater than the weight corresponding to the sample non-point.
8. The method of claim 4, wherein the pre-training model based on the preset pre-training task to obtain a trained target pre-training model comprises:
determining task input data and task marking data corresponding to the pre-training task;
inputting the task input data into the pre-training model so that the pre-training model outputs a key information identification result corresponding to the task input data;
and continuously adjusting model parameters of the pre-training model based on the key information identification result and the task marking data to obtain the trained target pre-training model.
9. The method of claim 1, wherein the obtaining initial meeting information comprises:
and acquiring the initial conference information in response to determining that the information category of the initial conference information is not a target conference category.
10. An apparatus for generating a conference summary, comprising:
an information acquisition unit configured to acquire initial conference information;
the information filtering unit is configured to filter the initial conference information to obtain target conference information;
an information classification unit configured to determine classification information of the target conference information based on the target conference information and a preset information classification model; the classification information at least comprises meeting point information and meeting non-point information;
a conference summary generating unit configured to generate a conference summary based on the conference point information and the conference non-point information.
11. The apparatus of claim 10, wherein the information filtering unit is further configured to:
filtering the language words in the initial conference information to obtain filtered initial conference information;
and filtering repeated words in the filtered initial conference information to obtain the target conference information.
12. The apparatus of claim 11, wherein the information filtering unit is further configured to:
determining meaningful repeated words in the filtered initial conference information;
and filtering repeated words except the meaningful repeated words in the filtered initial conference information to obtain the target conference information.
13. The apparatus of claim 10, wherein the apparatus further comprises:
the model training unit is configured to pre-train the pre-training model based on a preset pre-training task to obtain a trained target pre-training model; training the target pre-training model based on sample information and sample labeling data to enable the target pre-training model to output a sample classification corresponding to the sample information, and adjusting model parameters of the target pre-training model based on the sample classification, the sample labeling data and a preset loss function until the preset loss function is converged to obtain the preset information classification model.
14. The apparatus of claim 13, wherein the apparatus further comprises:
a sample acquisition unit configured to acquire sample information; determining sample non-point information and sample point information in the sample information based on preset information conditions; determining the sample annotation data based on the sample non-point information and the sample point information.
15. The apparatus of claim 14, wherein the sample acquisition unit is further configured to:
resampling the sample information in response to determining that an information quantity difference between the sample non-point information and the sample point information is greater than a preset threshold.
16. The apparatus of claim 13, wherein the sample classification includes a sample gist and a sample non-gist; and the weight corresponding to the sample point in the loss function is greater than the weight corresponding to the sample non-point.
17. The apparatus of claim 13, wherein the model training unit is further configured to:
determining task input data and task marking data corresponding to the pre-training task;
inputting the task input data into the pre-training model so that the pre-training model outputs a key information identification result corresponding to the task input data;
and continuously adjusting model parameters of the pre-training model based on the key information identification result and the task marking data to obtain the trained target pre-training model.
18. The apparatus of claim 10, wherein the information acquisition unit is further configured to:
and acquiring the initial conference information in response to determining that the information category of the initial conference information is not a target conference category.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.
21. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110930151.7A CN113642294B (en) | 2021-08-13 | 2021-08-13 | Method, apparatus, device, medium and product for generating meeting summary |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110930151.7A CN113642294B (en) | 2021-08-13 | 2021-08-13 | Method, apparatus, device, medium and product for generating meeting summary |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642294A true CN113642294A (en) | 2021-11-12 |
| CN113642294B CN113642294B (en) | 2023-08-04 |
Family
ID=78421711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110930151.7A Active CN113642294B (en) | 2021-08-13 | 2021-08-13 | Method, apparatus, device, medium and product for generating meeting summary |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642294B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090006982A1 (en) * | 2007-06-28 | 2009-01-01 | Microsoft Corporation | Collaborative generation of meeting minutes and agenda confirmation |
| US20130113804A1 (en) * | 2011-11-06 | 2013-05-09 | Ahmet Mufit Ferman | Methods, Systems and Apparatus for Summarizing a Meeting |
| CN107679525A (en) * | 2017-11-01 | 2018-02-09 | 腾讯科技（深圳）有限公司 | Image classification method, device and computer-readable recording medium |
| CN109473103A (en) * | 2018-11-16 | 2019-03-15 | 上海玖悦数码科技有限公司 | A kind of meeting summary generation method |
| CN110866110A (en) * | 2019-09-20 | 2020-03-06 | 平安科技（深圳）有限公司 | Conference summary generation method, device, equipment and medium based on artificial intelligence |
| CN112364912A (en) * | 2020-11-09 | 2021-02-12 | 腾讯科技（深圳）有限公司 | Information classification method, device, equipment and storage medium |
-
2021
- 2021-08-13 CN CN202110930151.7A patent/CN113642294B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090006982A1 (en) * | 2007-06-28 | 2009-01-01 | Microsoft Corporation | Collaborative generation of meeting minutes and agenda confirmation |
| US20130113804A1 (en) * | 2011-11-06 | 2013-05-09 | Ahmet Mufit Ferman | Methods, Systems and Apparatus for Summarizing a Meeting |
| CN107679525A (en) * | 2017-11-01 | 2018-02-09 | 腾讯科技（深圳）有限公司 | Image classification method, device and computer-readable recording medium |
| CN109473103A (en) * | 2018-11-16 | 2019-03-15 | 上海玖悦数码科技有限公司 | A kind of meeting summary generation method |
| CN110866110A (en) * | 2019-09-20 | 2020-03-06 | 平安科技（深圳）有限公司 | Conference summary generation method, device, equipment and medium based on artificial intelligence |
| CN112364912A (en) * | 2020-11-09 | 2021-02-12 | 腾讯科技（深圳）有限公司 | Information classification method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王涛;贾媚;: "一种文本信息抽取技术的研究", 计算机与网络, no. 09, pages 49 - 51 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642294B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046254B (en) | Method and apparatus for generating a model | |
| CN111666380A (en) | Intelligent calling method, device, equipment and medium | |
| CN111061881A (en) | Text classification method, equipment and storage medium | |
| CN111582360B (en) | Method, apparatus, device and medium for labeling data | |
| CN111861596B (en) | Text classification method and device | |
| CN112966082A (en) | Audio quality inspection method, device, equipment and storage medium | |
| CN112926306A (en) | Text error correction method, device, equipment and storage medium | |
| CN109190123B (en) | Method and apparatus for outputting information | |
| CN115982376A (en) | Method and apparatus for training models based on text, multimodal data and knowledge | |
| CN116150339A (en) | Dialogue method, dialogue device, dialogue equipment and dialogue storage medium | |
| CN114186681A (en) | Method, apparatus and computer program product for generating model clusters | |
| CN113378855A (en) | Method for processing multitask, related device and computer program product | |
| CN110675865B (en) | Method and apparatus for training hybrid language recognition models | |
| CN114141236B (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN114969195B (en) | Dialogue content mining method and dialogue content evaluation model generation method | |
| CN113642294B (en) | Method, apparatus, device, medium and product for generating meeting summary | |
| CN114171063A (en) | Real-time telephone traffic customer emotion analysis assisting method and system | |
| CN112632241A (en) | Method, device, equipment and computer readable medium for intelligent conversation | |
| CN112131379A (en) | Method, device, electronic equipment and storage medium for identifying problem category | |
| CN112836529B (en) | Method and device for generating target corpus sample | |
| CN113344405B (en) | Method, device, equipment, medium and product for generating information based on knowledge graph | |
| CN113241061B (en) | Method and device for processing voice recognition result, electronic equipment and storage medium | |
| CN114491040B (en) | Information mining method and device | |
| CN112735421A (en) | Real-time quality inspection method and device for voice call | |
| CN117992349A (en) | Method, device, equipment and storage medium for recommending joint debugging test environment |
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 |