Online conference automatic reply processing method and device and related equipment

Abstract

The invention belongs to the technical field of financial science and technology, provides an automatic reply processing method and device for an online conference, computer equipment and a computer readable storage medium, and aims to solve the problem of poor communication effect in the online conference in the traditional technology. The method comprises the following steps: acquiring a participant identifier corresponding to a participant, judging whether the participant is a historical participant corresponding to a historical online conference according to the participant identifier, determining an individual historical chat style corresponding to the participant under the condition that the participant is the historical participant, generating target reply content corresponding to chat content according to the individual historical chat style, and sending the target reply content to a user according to the target reply content. And the target reply content is replied to the participants, so that personalized automatic replies are generated according to the personal historical chat styles of the participants, and the communication effect of the online conference is improved, for example, in the field of financial science and technology, for the online conference of the insurance service of an insurance company, the chat effect of the insurance service can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to an automatic reply processing method, device, computer equipment and computer-readable storage medium for online conferences. Background Art

[0002] In the field of financial technology, for example, insurance companies have a large number of online meetings due to the nature of their business. Participants in online meetings can be called online participants. Online participants often face the need to chat with other online participants. However, when online participants initiate a chat, they cannot get timely and personalized replies due to various reasons. The so-called timely and personalized replies refer to timely replies that are suitable for the characteristics of online participants, which reduces the communication effect of online communication. Summary of the invention

[0003] The present application provides an online conference automatic reply processing method, device, computer equipment and computer-readable storage medium, which can solve the technical problem of poor communication effect in online conferences in traditional technologies.

[0004] In a first aspect, the present application provides an automatic reply processing method for an online conference, including: responding to chat content initiated by an online conference participant, obtaining a participant identifier corresponding to the participant; judging, based on the participant identifier, whether the participant is a historical participant corresponding to a historical online conference; if the participant is the historical participant, determining the personal historical chat style corresponding to the participant; generating target reply content corresponding to the chat content based on the personal historical chat style, and replying the target reply content to the participant.

[0005] In the second aspect, the present application provides an automatic reply processing device for an online conference, including: a first acquisition unit, used to respond to the chat content initiated by an online conference participant, and obtain the participant identification corresponding to the participant; a first judgment unit, used to judge whether the participant is a historical participant corresponding to a historical online conference based on the participant identification; a first determination unit, used to determine the personal historical chat style corresponding to the participant when the participant is the historical participant; a first reply unit, used to generate target reply content corresponding to the chat content based on the personal historical chat style, and reply the target reply content to the participant.

[0006] In a third aspect, the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the online conference automatic reply processing method are implemented.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the online conference automatic reply processing method.

[0008] The present application provides an online conference automatic reply processing method, device, computer equipment and computer-readable storage medium. The method obtains a participant identifier corresponding to the participant by responding to the chat content initiated by the online conference participant, and determines whether the participant is a historical participant corresponding to the historical online conference based on the participant identifier. If the participant is a historical participant, the participant's personal historical chat style is determined, and target reply content corresponding to the chat content is generated based on the personal historical chat style, and the target reply content is replied to the participant. The embodiment of the present application generates and replies to the personal historical chat style corresponding to the personal historical chat style of the historical participant through the personal historical chat style corresponding to the historical participant, so as to realize the generation of personalized corresponding automatic replies based on the personal historical chat style such as the participant's style and language characteristics, which can improve the communication effect of the online conference. For example, in the field of financial technology, for an online conference on the insurance business of an insurance company, the chat effect of the insurance business can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A flowchart of an automatic reply processing method for an online conference provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of the first sub-flow of the online conference automatic reply processing method provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of a second sub-flow of the online conference automatic reply processing method provided in an embodiment of the present application;

[0013] Figure 4 A schematic block diagram of an automatic reply processing device for an online conference provided in an embodiment of the present application;

[0014] Figure 5 A schematic block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0017] An embodiment of the present application provides an automatic reply processing method for online conferences, which can be applied to but not limited to computer devices such as smart phones, tablet computers, laptops, desktop computers, servers, and is used to automatically reply to online participants in online conferences including but not limited to the financial technology field, for example, in online conferences of insurance companies.

[0018] In the face of the technical problem of poor communication effect in online meetings in traditional technologies, the inventors proposed an automatic reply processing method for online meetings in the embodiments of the present application. The core idea of ​​the embodiments of the present application is: based on the historical chat content of all historical participants of the online meeting, a chat style model is constructed, and based on the chat style model, the personal chat style of each historical participant is determined according to the historical chat content of a single historical participant. When the historical participant participates in the online meeting again and needs to automatically reply to the online meeting, reply content corresponding to the personal chat style is generated, and the reply content is automatically replied to the corresponding participant. Personalized automatic replies can be generated according to the style and language characteristics of the participants to improve the communication effect of the online meeting.

[0019] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] See also Figure 1 , Figure 1 The following is a flow chart of the automatic reply processing method for online conferences provided in the embodiment of the present application. Figure 1 As shown, in this embodiment, the method includes but is not limited to the following steps S11-S15:

[0021] S11. Respond to the chat content initiated by the online conference participant and obtain the participant identifier corresponding to the participant.

[0022] Explanatory terms, the participants of an online conference are the online conference participants. To participate in an online conference, the participants need to log in to the online conference system, generally using a participant ID. When initiating a chat, the chat content will be sent to the chat partner. The online conference chat automatic reply system receives the chat content sent by the participant, responds to the chat content initiated by the online conference participant, and obtains the participant ID corresponding to the participant, where the participant ID represents the unique identity identification code for the participant to log in to the online conference. The participant ID includes but is not limited to the participant's registration number, login name, ID, mobile phone number, and ID number.

[0023] For example, in the field of financial technology, such as in an insurance company, for an online meeting on a certain insurance product, relevant insurance practitioners participating in the online meeting can use their own participant ID to log in to the online conference system of the insurance system to participate in the online meeting of the insurance product.

[0024] S12: judging, according to the participant identifier, whether the participant is a historical participant corresponding to a historical online conference.

[0025] Explanatory, an online meeting that has been held is a historical online meeting, and participants who have participated in a historical online meeting are historical participants. For a historical online meeting, each historical participant is recorded, and the historical participants can be organized into a historical participant database, which contains historical participant information including but not limited to participant identification.

[0026] After obtaining the participant ID, it is determined whether the participant is a historical participant corresponding to the historical online conference based on the participant ID and in combination with the historical participant records of the historical online conference, that is, whether the participant has participated in the historical online conference.

[0027] For example, in the field of financial technology, such as in an insurance company, for an online meeting of a certain insurance product, after obtaining the participant identification, the participant is judged based on the participant identification and combined with the historical participant records of the historical online meetings of the insurance product to determine whether the participant is a historical participant corresponding to the historical online meeting, that is, to determine whether the participant has participated in the historical online meeting of the insurance product.

[0028] S13, when the participant is not the historical participant, determining the personal historical chat style corresponding to the participant;

[0029] S14: When the participant is the historical participant, determine the personal historical chat style corresponding to the participant.

[0030] Explanatoryly, when the participant is not a historical participant, it indicates that the participant has not participated in any online conference before, that is, the historical chat content of the participant will not be retained. The participant may be participating in the online conference for the first time, and there is no basis for determining the chat style of the participant. The participant's corresponding personal historical chat style is not determined, and the preset standard automatic reply method can be used for reply, instead of the automatic reply method based on personal chat style in the embodiment of the present application.

[0031] Similarly, when the participant is a historical participant, it means that the participant has participated in previous online meetings and the historical chat content of the participant is preserved. The chat style of the participant can be determined based on the historical chat content, and then the participant's corresponding personal historical chat style can be determined. The personal historical chat style is generally the chat style of the participant. The "history" in the historical chat style is only used to distinguish different chat styles for the convenience of describing technical solutions, and is not used to limit the chat style. Other similarities apply. Personal historical chat styles include but are not limited to humor, seriousness, care, straightforwardness, philosophy, optimism, playfulness, calmness, excitement, sarcasm, romance, simplicity, storytelling, and logic.

[0032] S15. Generate target reply content corresponding to the chat content according to the personal historical chat style, and reply the target reply content to the participant.

[0033] Explanatory, based on the personal historical chat style of the participant, target reply content corresponding to the chat content is generated, and the target reply content is replied to the participant, so as to perform automatic replies in a targeted and customized style according to the chat style characteristics of the participant.

[0034] For example, in the field of financial technology, such as in an insurance company, for an online meeting on a certain insurance product, if the chat content sent by a participant is "Is this insurance product cost-effective?", and the participant's personal historical chat style is storytelling, that is, the participant tends to express his or her content in a storytelling way, then based on the participant's chat style, the reply content of telling the story about whether the insurance product is cost-effective or not can be automatically replied to the participant, thereby making a customized reply based on the participant's chat style to improve the effectiveness of chat communication.

[0035] In the embodiment of the present application, by responding to the chat content initiated by the online conference participant, the participant identification corresponding to the participant is obtained, and based on the participant identification, whether the participant is a historical participant corresponding to the historical online conference is determined, and if the participant is a historical participant, the personal historical chat style corresponding to the participant is determined, and according to the personal historical chat style, target reply content corresponding to the chat content is generated, and the target reply content is replied to the participant. In the embodiment of the present application, reply content corresponding to the personal historical chat style is generated and replied through the personal historical chat style corresponding to the historical participant, thereby realizing the generation of personalized corresponding automatic replies based on the personal historical chat style such as the participant's style and language characteristics, which can improve the communication effect of the online meeting.

[0036] In one embodiment, determining the personal historical chat style corresponding to the participant includes:

[0037] Determine the historical chat style according to the first historical chat content corresponding to all historical participants of the historical online conference;

[0038] Constructing a historical chat style model according to the historical chat style;

[0039] Based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, the personal historical chat style corresponding to the participant is determined.

[0040] Explanatory, the chat contents of all historical participants of historical online conferences are recorded, and the chat contents of all historical participants of all historical online conferences are the first historical chat contents. The first historical chat contents are generally text chat contents. For chat contents that are voice or pictures, the contents of the voice or pictures can be converted into text for recording, so as to facilitate the processing and analysis of the first historical chat contents. Among them, the first historical chat content involves only the first one to distinguish different historical chat contents, and is not used to limit different historical chat contents. The historical chat content is the content involved in the chats that have occurred. In the case of multiple historical online conferences and multiple chats between multiple historical participants, due to the different expression habits and language expression abilities of different historical participants, a first historical chat content with rich corpus will be formed.

[0041] Natural language analysis and processing are performed on the first historical chat content corresponding to all historical participants of the historical online conference to determine the historical chat style involved in the first historical chat content. The historical chat style represents the chat style that has occurred and is involved in the chat process of the online conference. The historical chat style includes but is not limited to humor, seriousness, care, straightforwardness, philosophy, optimism, playfulness, calmness, excitement, sarcasm, romance, simplicity, storytelling, and logic, which mainly depends on the chat style of the historical participants. If all chat styles are a set, then the historical chat style is a subset of the above set.

[0042] According to the historical chat style, a historical chat style model is constructed. The historical chat style model includes but is not limited to deep learning models LSTM and Transformer. The historical chat style model is trained with labeled training samples. The training samples include historical chat content and its corresponding historical chat style. For example, training sample A is: the historical chat style corresponding to historical chat content segment A is "straightforward". The historical chat style model includes historical chat style and its corresponding quantitative expression. The historical chat style is a qualitative expression of the chat style. The quantitative expression is to convert the qualitative expression of the historical chat style into a specific expression form or expression content, that is, the characteristic expression of the qualitative expression. The quantitative expression can be represented by the historical chat style feature corresponding to the historical chat style. The historical chat style feature can be a vector or a parameter of the historical chat style model, so that the historical chat style model can capture the language text features of different chat styles.

[0043] Based on the historical chat style model, natural language processing and analysis are performed on the second historical chat content corresponding to the participant in the historical online conference, including but not limited to text preprocessing and feature extraction, and then matched with the historical chat style contained in the historical chat style model to analyze the chat style involved in the second historical chat content, that is, the participant's personal chat style, which is the chat style that the participant has shown, to determine the participant's corresponding personal historical chat style. The personal historical chat style represents the chat style shown by the participant in the chat process of the previous online conference. The personal historical chat style is a subset of the above historical chat styles. The personal historical chat style includes but is not limited to humor, seriousness, care, straightforwardness, philosophy, optimism, playfulness, calmness, excitement, irony, romance, simplicity, storytelling, and logic. A person can express different chat styles, even opposite chat styles in different states. For example, a participant can express concentrated chat styles such as optimism, playfulness, straightforwardness, and simplicity at the same time. Similarly, a participant can express a calm chat style in one state and an excited chat style that is opposite to calmness in another state.

[0044] For example, in the field of financial technology, such as in insurance companies, for online meetings of a certain insurance product, the historical chat style involved in the online meetings of the insurance product is determined based on the first historical chat content corresponding to all historical participants of all historical online meetings of the insurance product. The historical chat style includes but is not limited to humor, seriousness, care, straightforwardness, philosophy, optimism, playfulness, calmness, excitement, sarcasm, romance, simplicity, storytelling, and logic. Based on the historical chat style, a historical chat style model is constructed. The historical chat style model includes but is not limited to deep learning models LSTM and Transformer. Based on the historical chat style model and based on the second historical chat content corresponding to the participant in the historical online meeting, the personal historical chat style corresponding to the participant is determined.

[0045] In the embodiment of the present application, a historical chat style is determined based on the first historical chat content corresponding to all historical participants of the historical online conference, and a historical chat style model is constructed based on the historical chat style. Based on the historical chat style model, and based on the second historical chat content corresponding to the participant in the historical online conference, the personal historical chat style corresponding to the participant is determined, thereby determining the personal historical chat style of the participant based on the chat content of the participant in the historical online conference, and then generating a personalized corresponding automatic reply based on the personal historical chat style of the participant, which can improve the communication effect of the online conference.

[0046] In one embodiment, see Figure 2 , Figure 2 This is a schematic diagram of the first sub-flow of the online conference automatic reply processing method provided in the embodiment of the present application. Figure 2 As shown, in this embodiment, according to the first historical chat content corresponding to all historical participants of the historical online conference, the historical chat style is determined, including:

[0047] S21, obtaining the first historical chat content corresponding to all historical participants of the historical online conference;

[0048] S22, performing text preprocessing on the first historical chat content to obtain a first text;

[0049] S23, performing feature extraction on the first text based on a preset feature extraction algorithm to obtain first text features;

[0050] S24. Based on a preset chat style recognition method, identify the chat style corresponding to the first text feature to obtain a historical chat style.

[0051] Explanatory, the first historical chat content corresponding to all historical participants of the historical online conference is obtained. The first historical chat content is generally text. The first historical chat content is subjected to text preprocessing including but not limited to word segmentation, removal of stop words, and stem extraction to obtain a first text.

[0052] A preset feature extraction algorithm including but not limited to TF-iDF or word2Vec is used to extract text features from the first text to obtain a first text feature, and a preset chat style recognition method including but not limited to a clustering algorithm (including but not limited to Kmeans) and a classification algorithm (including but not limited to a support vector machine SVM) is used to identify the chat style involved in the first text feature to obtain the chat style corresponding to the first text feature, that is, the historical chat style. The historical chat style includes but is not limited to humor, seriousness, care, straightforwardness, philosophy, optimism, playfulness, calmness, excitement, sarcasm, romance, simplicity, storytelling, and logic.

[0053] Exemplarily, in the field of financial technology, such as in insurance companies, for online meetings of a certain insurance product, based on the first historical chat content corresponding to all historical participants of all historical online meetings of the insurance product, the first historical chat content related to the insurance product is subjected to text preprocessing including but not limited to word segmentation, removal of stop words, and stem extraction to obtain a first text, and a preset feature extraction algorithm including but not limited to TF-iDF and word2Vec is used to extract text features from the first text to obtain a first text feature, and a preset chat style recognition method including but not limited to clustering algorithms (including but not limited to Kmeans) and classification algorithms (including but not limited to support vector machines SVM) is used to identify the chat style involved in the first text feature, and obtain the chat style corresponding to the first text feature, that is, the historical chat style is obtained, and the historical chat style involved in the online meeting of the insurance product is determined.

[0054] In an embodiment of the present application, first historical chat content corresponding to all historical participants of a historical online conference is obtained, text preprocessing is performed on the first historical chat content to obtain a first text, feature extraction is performed on the first text based on a preset feature extraction algorithm to obtain a first text feature, and based on a preset chat style recognition method, a chat style corresponding to the first text feature is identified to obtain a historical chat style, thereby using the chat content of all historical participants in the historical online conference as a basis, and analyzing the first historical chat content through natural language processing to determine the historical chat style corresponding to the historical participant, and based on the historical chat style, determining the participant's personal historical chat style, and then generating a personalized corresponding automatic reply based on the participant's personal historical chat style, which can improve the communication effect of the online conference.

[0055] In one embodiment, see Figure 3 , Figure 3 This is a schematic diagram of the second sub-flow of the online conference automatic reply processing method provided in the embodiment of the present application. Figure 3 As shown, in this embodiment, based on a preset chat style recognition method, the chat style corresponding to the first text feature is recognized to obtain the historical chat style, including:

[0056] S31, clustering the first text features based on a preset clustering algorithm to obtain a first text feature cluster;

[0057] S32, converting the first text feature cluster into a vector to obtain a first text feature cluster vector;

[0058] S33, obtaining a preset chat style vector corresponding to the preset chat style;

[0059] S34, calculating the style similarity between the first text feature cluster vector and the preset chat style vector;

[0060] S35, determining whether the style similarity is greater than or equal to a preset style similarity threshold;

[0061] S36: When the style similarity is greater than or equal to a preset style similarity threshold, use the preset chat style as the chat style corresponding to the first text feature cluster vector to obtain a historical chat style;

[0062] S37: When the style similarity is less than a preset style similarity threshold, the preset chat style is not used as the chat style corresponding to the first text feature cluster vector.

[0063] Explanatory, based on a preset clustering algorithm including but not limited to Kmeans, the first text features are clustered to form a number of first text feature clusters, each of which contains a number of text features, and then a method of converting text into a vector including but not limited to a word embedding model, a bag-of-words model, TF-IDF, an N-gram model, Word2vec, and Doc2vec is used to convert each first text feature cluster into a vector to obtain a first text feature cluster vector, the vectors corresponding to the several first text feature clusters form a vector sequence, and a preset chat style vector corresponding to a preset chat style is obtained, the preset chat style is first described using a chat feature text, and then the chat feature text is converted into a text vector, that is, the preset chat style vector is obtained, Then, the style similarity between the first text feature cluster vector and the preset chat style vector is calculated, and then it is determined whether the style similarity is greater than or equal to the preset style similarity threshold. When the style similarity is greater than or equal to the preset style similarity threshold, it indicates that the text feature corresponding to the first text feature cluster vector is similar to the preset chat style. The preset chat style is used as the chat style corresponding to the first text feature cluster vector to obtain the historical chat style, thereby obtaining several historical chat styles contained in the first historical chat content. When the style similarity is less than the preset style similarity threshold, it indicates that the text feature corresponding to the first text feature cluster vector is not similar to the preset chat style, and the preset chat style is not used as the chat style corresponding to the first text feature cluster vector.

[0064] In the embodiment of the present application, the chat style is identified by the first historical chat content to obtain the corresponding historical chat style, so as to extract the chat style characteristics from the first historical chat content, thereby taking the chat content of the participants in the historical online conference as a basis, and analyzing the first historical chat content through natural language processing to determine the historical chat style, and then generating personalized corresponding automatic replies according to the personal historical chat style of the participants, which can improve the communication effect of the online conference.

[0065] In one embodiment, based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, determining the personal historical chat style corresponding to the participant includes:

[0066] Obtaining a second historical chat content corresponding to the participant in the historical online conference;

[0067] The second historical chat content is matched with the historical chat style included in the historical chat style model to obtain the personal historical chat style corresponding to the participant.

[0068] Explanatoryly, the second historical chat content corresponding to the participant in the historical online conference is obtained, the second historical chat content is subjected to natural language processing, and the chat style features involved are extracted therefrom, and then matched with the features of the same dimension corresponding to the historical chat style contained in the historical chat style model, for example, by calculating the similarity between the chat style text features contained in the second historical chat content and the text features corresponding to the historical chat style. When the similarity is greater than or equal to a preset similarity threshold, it indicates that the second historical chat content contains the historical chat style, and the historical chat style is determined as the personal historical chat style corresponding to the participant, and the personal historical chat style corresponding to the participant is obtained. When the similarity is less than the preset similarity threshold, it indicates that the second historical chat content does not contain the historical chat style, and the historical chat style is not determined as the personal historical chat style corresponding to the participant. In this way, the chat style contained in the second historical chat content is matched with several historical chat styles contained in the historical chat style model to obtain several personal historical chat styles corresponding to the participant.

[0069] In the embodiment of the present application, by obtaining the second historical chat content corresponding to the participant in the historical online meeting, the second historical chat content is matched with the historical chat style included in the historical chat style model to obtain the personal historical chat style corresponding to the participant, thereby using the chat content of the participant in the historical online meeting as a basis, and analyzing the first historical chat content through natural language processing to determine several personal historical chat styles of the participant, and then generating personalized corresponding automatic replies based on the personal historical chat style of the participant, which can improve the communication effect of the online meeting.

[0070] In one embodiment, generating target reply content corresponding to the chat content according to the personal historical chat style includes:

[0071] Based on a preset text generation model, generate an initial reply text corresponding to the chat content;

[0072] The personal historical chat style is injected into the initial reply text to obtain the target reply content.

[0073] Explanatory, based on preset text generation models including but not limited to generative adversarial networks (GANs), variational autoencoders (VAEs), and pre-trained language models (such as GPT-4 or BERT), an initial reply text corresponding to the chat content is generated, and then an injection method including but not limited to style transfer, vector multiplication, and matrix multiplication is adopted, wherein the vector multiplication and matrix multiplication injection method is to multiply the vector or matrix corresponding to the personal historical chat style with the vector or matrix corresponding to the initial reply text to inject the personal historical chat style into the initial reply text to obtain the target reply content.

[0074] Among them, generative adversarial networks (GANs) are used to generate natural language text with a specific style. GANs include a generator and a discriminator, which can generate text in a specific style through adversarial training; variational autoencoders (VAEs) are also a generative model that generates text in a certain style by modeling the latent space. VAEs are suitable for generating diverse natural language content; pre-trained language models, such as GPT-4 or BERT, can be fine-tuned on the basis of style adaptation to generate text in a specific style. Based on the preset text generation models including but not limited to the above, the generated text can be made more in line with the specified style by adjusting the training data and parameters of the model.

[0075] The embodiment of the present application generates an initial reply text corresponding to the chat content based on a preset text generation model, injects the personal historical chat style into the initial reply text, obtains the target reply content, and realizes the generation of personalized corresponding automatic reply content and automatic reply according to the personal historical chat style of the participant, which can improve the communication effect of the online meeting.

[0076] In one embodiment, before replying the target reply content to the participant, the method further includes:

[0077] Determining whether the target reply content meets the preset reply content conditions;

[0078] If the target reply content meets the preset reply content conditions, reply the target reply content to the participant;

[0079] When the target reply content does not meet the preset reply content conditions, the target reply content will not be replied to the participant.

[0080] Explanatory, it is determined whether the target reply content meets the preset reply content conditions. The preset reply content conditions include but are not limited to not involving politics, not involving negativity, not involving uncivilized content and meeting the chat style requirements. If the target reply content meets the preset reply content conditions, the target reply content is compliant and meets the chat style requirements. In order to meet the customized chat style requirements, the target reply content is automatically replied to the participant and displayed in the chat interface of the online meeting. If the target reply content does not meet the preset reply content conditions, the target reply content will not be replied to the participant.

[0081] In the embodiment of the present application, by judging whether the target reply content meets the preset reply content conditions, if the target reply content meets the preset reply content conditions, the target reply content is replied to the participant, and if the target reply content does not meet the preset reply content conditions, the target reply content is not replied to the participant, so as to automatically review the target reply content to ensure that the target reply content meets the preset reply content conditions, so as to avoid misunderstanding or non-compliance, and can further improve the communication effect of the online meeting.

[0082] It should be noted that the online conference automatic reply processing method described in the above embodiments can recombine the technical features contained in different embodiments as needed to obtain a combined implementation plan, but all of them are within the scope of protection required by this application.

[0083] See also Figure 4 , Figure 4 This is a schematic block diagram of an online conference automatic reply processing device provided in an embodiment of the present application. Corresponding to the above-mentioned online conference automatic reply processing method, the embodiment of the present application also provides an online conference automatic reply processing device. Figure 4 As shown, the online conference automatic reply processing device includes a unit for executing the above-mentioned online conference automatic reply processing method, and the online conference automatic reply processing device can be configured in a computer device. Figure 4 The online conference automatic reply processing device 40 includes a first acquisition unit 41, a first judgment unit 42, a first determination unit 43 and a first reply unit 44.

[0084] The first acquisition unit 41 is used to respond to the chat content initiated by the online conference participant and acquire the participant identifier corresponding to the participant;

[0085] A first judging unit 42 is used to judge whether the participant is a historical participant corresponding to a historical online conference according to the participant identifier;

[0086] A first determining unit 43 is used to determine the personal historical chat style corresponding to the participant when the participant is the historical participant;

[0087] The first reply unit 44 is used to generate target reply content corresponding to the chat content according to the personal historical chat style, and reply the target reply content to the participant.

[0088] In one embodiment, the first determining unit 43 includes:

[0089] A first determining subunit is used to determine the historical chat style according to the first historical chat content corresponding to all historical participants of the historical online conference;

[0090] A construction subunit, used to construct a historical chat style model according to the historical chat style;

[0091] The second determining subunit is used to determine the personal historical chat style corresponding to the participant based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference.

[0092] In one embodiment, the first determining subunit includes:

[0093] A first acquisition subunit is used to acquire first historical chat content corresponding to all historical participants of the historical online conference;

[0094] A preprocessing subunit, configured to perform text preprocessing on the first historical chat content to obtain a first text;

[0095] An extraction subunit, configured to extract features from the first text based on a preset feature extraction algorithm to obtain first text features;

[0096] The first identification subunit is used to identify the chat style corresponding to the first text feature based on a preset chat style identification method to obtain a historical chat style.

[0097] In one embodiment, the first identification subunit includes:

[0098] A clustering subunit, configured to cluster the first text features based on a preset clustering algorithm to obtain a first text feature cluster;

[0099] A conversion subunit, used for converting the first text feature cluster into a vector to obtain a first text feature cluster vector;

[0100] A second acquisition subunit is used to acquire a preset chat style vector corresponding to the preset chat style;

[0101] A first calculation subunit, configured to calculate a style similarity between the first text feature cluster vector and the preset chat style vector;

[0102] A first judging subunit, used to judge whether the style similarity is greater than or equal to a preset style similarity threshold;

[0103] The third determining subunit is configured to, when the style similarity is greater than or equal to a preset style similarity threshold, use the preset chat style as the chat style corresponding to the first text feature cluster vector to obtain a historical chat style.

[0104] In one embodiment, the second determining subunit includes:

[0105] The third acquisition subunit is used to acquire the second historical chat content corresponding to the historical online conference of the participant;

[0106] The matching subunit is used to match the second historical chat content with the historical chat style included in the historical chat style model to obtain the personal historical chat style corresponding to the participant.

[0107] In one embodiment, the first reply unit 44 includes:

[0108] A first generating subunit, configured to generate an initial reply text corresponding to the chat content based on a preset text generation model;

[0109] The injection subunit is used to inject the personal historical chat style into the initial reply text to obtain the target reply content.

[0110] In one embodiment, the online conference automatic reply processing device 40 further includes:

[0111] A second judgment unit is used to judge whether the target reply content meets the preset reply content condition;

[0112] The first reply unit 44 is specifically configured to reply the target reply content to the participant if the target reply content meets a preset reply content condition.

[0113] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned online conference automatic reply processing device and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0114] At the same time, the division and connection method of each unit in the above-mentioned online conference automatic reply processing device is only used for illustration. In other embodiments, the online conference automatic reply processing device can be divided into different units as needed, and the units in the online conference automatic reply processing device can also adopt different connection sequences and methods to complete all or part of the functions of the above-mentioned online conference automatic reply processing device.

[0115] The above-mentioned online conference automatic reply processing device can be implemented in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer device shown.

[0116] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a computer device such as a desktop computer or a server, or may be a component or part in other devices.

[0117] See also Figure 5 The computer device 500 includes a processor 502, a memory and a network interface 505 connected via a system bus 501, wherein the memory may include a non-volatile storage medium 503 and an internal memory 504, and the memory may also be a volatile storage medium.

[0118] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the above-mentioned online conference automatic reply processing method.

[0119] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0120] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the above-mentioned online conference automatic reply processing method.

[0121] The network interface 505 is used to communicate with other devices over the network. Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the computer device 500 to which the present application scheme is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and the processor are the same as those of the present application scheme. Figure 5 The embodiments shown are consistent and will not be described again here.

[0122] Among them, the processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: respond to the chat content initiated by the online meeting participant, obtain the participant identification corresponding to the participant; based on the participant identification, determine whether the participant is a historical participant corresponding to the historical online meeting; if the participant is the historical participant, determine the personal historical chat style corresponding to the participant; based on the personal historical chat style, generate target reply content corresponding to the chat content, and reply the target reply content to the participant.

[0123] In one embodiment, the processor 502 specifically implements the following steps when determining the personal historical chat style corresponding to the participant:

[0124] Determine the historical chat style according to the first historical chat content corresponding to all historical participants of the historical online conference;

[0125] Constructing a historical chat style model according to the historical chat style;

[0126] Based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, the personal historical chat style corresponding to the participant is determined.

[0127] In one embodiment, when the processor 502 determines the historical chat style according to the first historical chat content corresponding to all historical participants of the historical online conference, the processor 502 specifically implements the following steps:

[0128] Obtain the first historical chat content corresponding to all historical participants of the historical online conference;

[0129] Performing text preprocessing on the first historical chat content to obtain a first text;

[0130] Based on a preset feature extraction algorithm, feature extraction is performed on the first text to obtain first text features;

[0131] Based on a preset chat style recognition method, the chat style corresponding to the first text feature is identified to obtain a historical chat style.

[0132] In one embodiment, when the processor 502 implements the preset chat style recognition method to identify the chat style corresponding to the first text feature and obtain the historical chat style, the processor 502 specifically implements the following steps:

[0133] Based on a preset clustering algorithm, clustering the first text features to obtain a first text feature cluster;

[0134] Converting the first text feature cluster into a vector to obtain a first text feature cluster vector;

[0135] Obtaining a preset chat style vector corresponding to the preset chat style;

[0136] Calculating the style similarity between the first text feature cluster vector and the preset chat style vector;

[0137] Determining whether the style similarity is greater than or equal to a preset style similarity threshold;

[0138] When the style similarity is greater than or equal to a preset style similarity threshold, the preset chat style is used as the chat style corresponding to the first text feature cluster vector to obtain a historical chat style.

[0139] In one embodiment, when the processor 502 determines the personal historical chat style corresponding to the participant based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, the processor 502 specifically implements the following steps:

[0140] Obtaining a second historical chat content corresponding to the participant in the historical online conference;

[0141] The second historical chat content is matched with the historical chat style included in the historical chat style model to obtain the personal historical chat style corresponding to the participant.

[0142] In one embodiment, when the processor 502 generates the target reply content corresponding to the chat content according to the personal historical chat style, it specifically implements the following steps:

[0143] Based on a preset text generation model, generate an initial reply text corresponding to the chat content;

[0144] The personal historical chat style is injected into the initial reply text to obtain the target reply content.

[0145] In one embodiment, before replying the target reply content to the participant, the processor 502 further implements the following steps:

[0146] Determining whether the target reply content meets the preset reply content conditions;

[0147] When the target reply content meets the preset reply content conditions, the target reply content is replied to the participant.

[0148] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0149] Those skilled in the art will appreciate that all or part of the processes in the method for implementing the above embodiment can be completed by a computer program, which can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0150] Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the following steps:

[0151] A computer program product, when running on a computer, enables the computer to execute the steps of the online conference automatic reply processing method described in the above embodiments.

[0152] The computer-readable storage medium may be an internal storage unit of the aforementioned device, such as a hard disk or memory of the device. The computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device.

[0153] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0154] The storage medium is a physical, non-transient storage medium, for example, it can be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, etc., which can store computer programs.

[0155] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0156] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0157] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0158] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for an electronic device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0159] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for automatically replying to an online conference, characterized in that: include: Responding to the chat content initiated by the online conference participant, obtaining the participant identifier corresponding to the participant; According to the participant identifier, determining whether the participant is a historical participant corresponding to a historical online conference; In the case where the participant is the historical participant, determining the personal historical chat style corresponding to the participant; According to the personal historical chat style, target reply content corresponding to the chat content is generated, and the target reply content is replied to the participant.

2. The method for automatically replying to an online conference according to claim 1, characterized in that: Determine the personal historical chat style corresponding to the participant, including: Determine the historical chat style according to the first historical chat content corresponding to all historical participants of the historical online conference; Constructing a historical chat style model according to the historical chat style; Based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, the personal historical chat style corresponding to the participant is determined.

3. The method for automatically replying to an online conference according to claim 2, characterized in that: Determine the historical chat style based on the first historical chat content corresponding to all historical participants of the historical online conference, including: Obtain the first historical chat content corresponding to all historical participants of the historical online conference; Performing text preprocessing on the first historical chat content to obtain a first text; Based on a preset feature extraction algorithm, feature extraction is performed on the first text to obtain first text features; Based on a preset chat style recognition method, the chat style corresponding to the first text feature is identified to obtain a historical chat style.

4. The method for automatically replying to an online conference according to claim 3, characterized in that: Based on a preset chat style recognition method, identifying the chat style corresponding to the first text feature to obtain the historical chat style includes: Based on a preset clustering algorithm, clustering the first text features to obtain a first text feature cluster; Converting the first text feature cluster into a vector to obtain a first text feature cluster vector; Obtaining a preset chat style vector corresponding to the preset chat style; Calculating the style similarity between the first text feature cluster vector and the preset chat style vector; Determining whether the style similarity is greater than or equal to a preset style similarity threshold; When the style similarity is greater than or equal to a preset style similarity threshold, the preset chat style is used as the chat style corresponding to the first text feature cluster vector to obtain a historical chat style.

5. The method for automatically replying to an online conference according to claim 2, characterized in that: Based on the historical chat style model and according to the second historical chat content corresponding to the participant in the historical online conference, determining the personal historical chat style corresponding to the participant includes: Obtaining a second historical chat content corresponding to the participant in the historical online conference; The second historical chat content is matched with the historical chat style included in the historical chat style model to obtain the personal historical chat style corresponding to the participant.

6. The method for automatically replying to an online conference according to claim 1, characterized in that: Generating target reply content corresponding to the chat content according to the personal historical chat style, including: Generate an initial reply text corresponding to the chat content based on a preset text generation model; The personal historical chat style is injected into the initial reply text to obtain the target reply content.

7. The method for automatically replying to an online conference according to claim 1, characterized in that: Before replying the target reply content to the participant, it also includes: Determining whether the target reply content meets the preset reply content conditions; When the target reply content meets the preset reply content conditions, the target reply content is replied to the participant.

8. An automatic reply processing device for an online conference, characterized in that: include: A first acquisition unit, configured to respond to a chat content initiated by an online conference participant and acquire a participant identifier corresponding to the participant; A first judgment unit, configured to judge, according to the participant identifier, whether the participant is a historical participant corresponding to a historical online conference; A first determining unit, configured to determine, when the participant is the historical participant, a personal historical chat style corresponding to the participant; The first reply unit is used to generate target reply content corresponding to the chat content according to the personal historical chat style, and reply the target reply content to the participant.

9. A computer device, characterized in that: The computer device comprises a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 can be implemented.

Images