CN113127633A

CN113127633A - Intelligent conference management method and device, computer equipment and storage medium

Info

Publication number: CN113127633A
Application number: CN202110673946.4A
Authority: CN
Inventors: 廖伯轩; 张天一; 郑天琦; 王士鑫; 钟坯平; 单允赟; 刘美汐
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-06-17
Filing date: 2021-06-17
Publication date: 2021-07-16
Anticipated expiration: 2041-06-17
Also published as: CN113127633B

Abstract

The embodiment of the application belongs to the field of artificial intelligence and relates to an intelligent conference management method which comprises the steps of analyzing a conference establishment request to obtain a conference label when the conference establishment request is received; acquiring a preset target neural network, and performing prediction sequencing on conference labels according to the target neural network to obtain a recommended conference flow; inputting a recommended conference flow to a preset knowledge graph, and determining target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm; calculating target conference characteristic information and target user information through a preset collaborative filtering algorithm to obtain a display template; and acquiring target text information, and filling the target text information into a display template to obtain target display data. The application also provides an intelligent conference management device, computer equipment and a storage medium. In addition, the present application also relates to a blockchain technique, and target show data can be stored in the blockchain. The method and the device realize intelligent recommendation and data display of the conference process.

Description

Intelligent conference management method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to an intelligent conference management method and apparatus, a computer device, and a storage medium.

Background

With the rapid development of science and technology, the online and intelligent business trend of enterprises is inevitable. Through the intelligent enterprise office, a large amount of manpower and material resources can be saved, and the data utilization rate and the event processing efficiency can be improved.

The conference usually bears the landing functions of multiple business scenes such as training development, performance index tracking, business scheme promotion and the like in the daily work of enterprise office. If the attendance rate of a department is low, the communication of daily management is disabled, and the learning atmosphere of the department is further reduced. The existing conference management system or software usually adopts manual data collection and conference calling personnel to carry out conferences, and can not realize intelligent data management and display of conference processes from the aspects of conference subject preparation, conference process formulation, conference material support, material style template recommendation and the like.

Disclosure of Invention

An object of the embodiments of the present application is to provide an intelligent conference management method, an intelligent conference management device, a computer device, and a storage medium, so as to solve a technical problem that intelligent management cannot be performed on a conference.

In order to solve the above technical problem, an embodiment of the present application provides an intelligent conference management method, which adopts the following technical solutions:

when a conference establishment request is received, analyzing the conference establishment request to obtain a conference label;

acquiring a preset target neural network, and performing prediction sequencing on the conference label according to the target neural network to obtain a recommended conference flow;

inputting the recommended conference flow to a preset knowledge graph, and determining target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm;

calculating the target conference characteristic information and the target user information through a preset collaborative filtering algorithm to obtain a display template;

and acquiring target text information, and filling the target text information into the display template to obtain target display data corresponding to the recommended conference flow.

Further, the step of calculating the target conference feature information and the target user information through a preset collaborative filtering algorithm to obtain a display template specifically includes:

calculating a first multi-dimensional label vector of the target user information and the stored standard user information according to the collaborative filtering algorithm, and calculating a second multi-dimensional label vector of the target conference feature information and the stored standard conference feature information;

and carrying out weighted summation on the first multi-dimensional label vector and the second multi-dimensional label vector to obtain total similarity, calculating final adaptation according to the total similarity, and determining a template corresponding to the maximum value of the final adaptation as the display template.

Further, the step of acquiring the target text information specifically includes:

acquiring stored historical text information, and a first text label and a second text label of the historical text information;

and matching the first text label with the target conference characteristic information, matching the second text label with the target user information, and determining that the text information corresponding to the first text label and the second text label which are successfully matched with the target conference characteristic information and the target user information is the target text information.

Further, the step of acquiring the stored historical text information specifically includes:

recording courseware information of each meeting, and identifying the courseware information through OCR to obtain corresponding courseware text information;

and performing cyclic redundancy check and XOR check on the courseware text information, and storing the courseware text information as the historical text information in a database when the courseware text information passes the check.

Further, the step of obtaining the target text information further includes:

calculating the similarity between the target user information and preset labels, and selecting a preset number of preset labels as interactive labels according to the similarity from high to low;

obtaining scores of the interactive tags on stored information data, calculating matching degree according to the scores and the interactive tags, and selecting an information set corresponding to the target user information according to the matching degree;

and screening out the marked information data in the information set according to the history record to obtain residual information data, and using the residual information data as the target text information.

Further, after the step of obtaining the target presentation data corresponding to the recommended conference flow, the method further includes:

acquiring a label vector of the conference feature information and a feature vector of a stored report, inputting the label vector and the feature vector into a preset prediction model, and calculating to obtain prediction connection probabilities between different reports corresponding to the target display data according to the prediction model;

and sequencing the report according to the predicted connection probability to obtain a target display report corresponding to the target display data.

Further, before the step of inputting the label vector and the feature vector into a preset prediction model, the method further includes:

obtaining a basic prediction model, wherein the basic prediction model comprises a gradient lifting decision tree and a logistic regression model;

obtaining historical label data, historical characteristic data and historical interaction data, and training the gradient lifting decision tree and the logistic regression model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the prediction model.

In order to solve the above technical problem, an embodiment of the present application further provides an intelligent conference management device, which adopts the following technical solutions:

the analysis module is used for analyzing the conference establishment request to obtain a conference label when the conference establishment request is received;

the prediction module is used for acquiring a preset target neural network, and performing prediction sequencing on the conference label according to the target neural network to obtain a recommended conference flow;

the confirming module is used for inputting the recommended conference flow to a preset knowledge graph and determining target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm;

the calculation module is used for calculating the target conference characteristic information and the target user information through a preset collaborative filtering algorithm to obtain a display template;

and the filling module is used for acquiring target text information, filling the target text information into the display template, and obtaining target display data corresponding to the recommended conference flow.

In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, where the processor implements the steps of the intelligent conference management method when executing the computer readable instructions.

In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, where computer-readable instructions are stored, and when executed by a processor, the computer-readable instructions implement the steps of the intelligent conference management method.

According to the intelligent conference management method, when a conference establishment request is received, the conference establishment request is analyzed to obtain a conference label; then, a preset target neural network is obtained, and the conference labels are subjected to prediction sequencing according to the target neural network to obtain a recommended conference flow, so that the high-efficiency prediction of the recommended conference flow is realized; then, inputting a recommended conference flow to a preset knowledge graph, and determining target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm, so that the target conference characteristic information and the target user information are accurately acquired; calculating target conference characteristic information and target user information through a preset collaborative filtering algorithm to obtain a display template, and further realizing accurate recommendation of the display template corresponding to the conference; and finally, target text information is obtained, the target text information is filled into the display template, and target display data corresponding to the recommended conference flow are obtained, so that intelligent recommendation and data display of the conference flow are realized, meanwhile, data required in the conference are automatically tracked, and the data processing efficiency and the conference resource utilization rate are improved.

Drawings

In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of an intelligent meeting management method according to the present application;

FIG. 3 is a schematic block diagram of one embodiment of an intelligent meeting management apparatus according to the present application;

FIG. 4 is a schematic block diagram of one embodiment of a computer device according to the present application.

Reference numerals: intelligent conference management device 300, parsing module 301, prediction module 302, validation module 303, calculation module 304, and population module 305.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

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, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the

terminal devices

101, 102, 103.

It should be noted that, the intelligent conference management method provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the intelligent conference management apparatus is generally disposed in the server/terminal device.

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 diagram of one embodiment of a method of intelligent meeting management is shown, in accordance with the present application. The intelligent conference management method comprises the following steps:

step S201, when receiving a conference establishment request, analyzing the conference establishment request to obtain a conference label;

in this embodiment, when a conference establishment request is received, the conference establishment request is analyzed to obtain a conference tag corresponding to the conference establishment request, where the conference tag is a name of a conference module, and a complete conference process can be split into multiple conference modules. Specifically, when a conference establishment request is received, the conference establishment request is analyzed, and a corresponding local database is read according to the conference establishment request. Tag information (namely conference tags) corresponding to different process modules after a plurality of historical conference processes are modularized is stored in the local database, and the historically stored conference tags can be directly obtained from the local database.

Step S202, acquiring a preset target neural network, and performing prediction sequencing on the conference label according to the target neural network to obtain a recommended conference flow;

in this embodiment, the target neural network is a neural network trained in advance, such as a recurrent neural network. And when the conference label is obtained, inputting the conference label to the target neural network, and outputting through the target neural network to obtain a recommended conference flow corresponding to the conference label. The recommended conference flow is obtained by sequencing input conference labels through a target neural network. Specifically, before the target neural network is obtained, the basic neural network is trained, and the trained basic neural network is the target neural network. And when the basic neural network is trained, acquiring a plurality of groups of stored historical conference labels and historical conference flows. And taking the historical conference label as the input of a basic neural network, obtaining a prediction recommendation process through the output of the basic neural network, and adjusting the parameters of the basic neural network according to the prediction recommendation process and the historical conference process. And taking the basic neural network with the adjusted parameters as a target neural network. And when the conference label is obtained, inputting the conference label into the target neural network, and calculating to obtain a recommended conference flow corresponding to the conference label through an input layer, a hidden layer and an output layer.

Step S203, inputting the recommended conference process to a preset knowledge graph, and determining target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm;

in this embodiment, the preset knowledge graph is a relationship network graph describing relationships among a conference, a conference place and a user, and mainly includes three relationship dimension graphs, specifically, a geographical relationship graph, a conference relationship graph and a user relationship graph, and the three relationship dimension graphs together form the preset knowledge graph. The geographical relationship map represents the distance relationship between each department and the current meeting place, and the distance weight of the relationship can be adjusted according to the floor of the meeting room and the actual geographical position; meeting relationship maps representing relationships between different meeting roomsThe distance weight of the relationship is adjusted according to the frequency of holding in a specific meeting room; the user relationship map represents the relationship between different users and the conference, and the distance weight of the relationship is adjusted according to the importance of the participants (i.e. users) in the conference and the frequency of the past participants in the conference. And acquiring a historical conference record, taking the conference name, the conference place and the user in the conference information as entities according to the conference information in the historical conference record, and taking the mutual relation among the conference, the conference place and the user as the connection relation of the knowledge graph. Arranging the connection relation and the entity into a three-metadata database which can be used

It is shown that, among others,

and

representing a set of different types of entities,

representing the connection between two entities. And establishing a relation network diagram based on the three relation dimensions in the three-dimensional database to obtain the preset knowledge graph.

And when the recommended conference flow is obtained, inputting the recommended conference flow to the preset knowledge graph, and determining optimal target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm (such as an breadth-first algorithm). The target conference feature information is feature information such as a target conference place, and the target user information is information of personnel needing to participate in the conference at present, such as a participant, a speaker and a host. Specifically, when a recommended conference flow is acquired, determining a corresponding conference type, such as an early meeting and a late meeting, according to the recommended conference flow; the conference type in combination with the conference time may then determine the final conference name, such as morning conference 1, morning conference 2. When the meeting name is obtained, finding the target user information with the shortest distance corresponding to the meeting name from the preset knowledge graph; and then, taking the conference name and the target user information as input items of a preset knowledge graph, and finding out target conference characteristic information optimal to the target user information from the preset knowledge graph according to a traversal algorithm.

The following proposes a traversal algorithm for calculating the shortest path:

and setting a queue q for storing nodes to be optimized, taking out a head node u of the queue each time during optimization, and performing relaxation operation on a node v pointed by a leaving u point by using a current shortest path estimation value of a u point, namely putting the v point into the head column of the queue for sequential ordering if the v point is the shortest path, and putting the v point into the tail of the queue for subsequent consideration if the distance is adjusted in expansion and the v point is not in the current queue.

And continuously taking out the nodes from the queue to carry out the operation until the queue is empty. And finally, the calculation of the distance compares the direct distance of the two nodes i and j with all indirect distances of the nodes which are placed at the tail of the queue, and the node with the shortest distance is taken.

When the conference name and the target user information are obtained, according to the mode, the conference name and the target user information are used as input items, and the target conference feature information optimal to the target user information is found from the preset knowledge graph.

Step S204, calculating the target conference characteristic information and the target user information through a preset collaborative filtering algorithm to obtain a display template;

in this embodiment, when obtaining the feature information of the target conference and the target user information, the display template may be obtained by calculating the target conference information and the target user information through a preset collaborative filtering algorithm. The collaborative filtering algorithm is a recommendation algorithm, a display template matched with the current target conference feature information and the target user information can be obtained through calculation through the collaborative filtering algorithm, and the display template is template data required to be displayed in the current conference, such as a slide template. Specifically, the target conference feature information and the target user information are respectively matched with the stored standard conference feature information and the stored standard user information, and a first multi-dimensional label vector and a second multi-dimensional label vector are obtained through cosine similarity calculation, wherein the first multi-dimensional label vector is the cosine similarity of the target user information and the standard user information, and the second multi-dimensional label vector is the cosine similarity of the target conference feature information and the standard conference feature information. And calculating the first multi-dimensional label vector and the second multi-dimensional label vector to obtain the final adaptation degree corresponding to the target characteristic information and the target user information, and determining the display template corresponding to the final adaptation degree of the maximum value as the display template matched with the target conference characteristic information and the target user information.

Step S205, obtaining target text information, and filling the target text information into the display template to obtain target display data corresponding to the recommended conference process.

In this embodiment, the target text information is data information that needs to be displayed in the display template. And acquiring corresponding target text information from the stored historical text information according to the target conference feature information and the target user information. Specifically, the target conference feature information and the historical conference feature information in the historical text information are respectively compared with the target user information and the historical user information in the historical text information, and the text information with the highest average value of matching degrees with the target feature information and the target user information in the historical text information is used as the target text information. And when the target text information is obtained, identifying field information in the display template, and filling the target text information into the display template according to the field information to obtain target display data corresponding to the current recommended conference flow.

It is emphasized that, in order to further ensure the privacy and security of the target presentation data, the target presentation data may also be stored in a node of a block chain.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

According to the embodiment, intelligent recommendation and data display of a conference process are realized, meanwhile, data required in the conference are automatically tracked, and the data processing efficiency and the conference resource utilization rate are improved.

In some embodiments of the present application, the calculating the target conference feature information and the target user information through a preset collaborative filtering algorithm to obtain the presentation template includes:

In this embodiment, the standard user information is a plurality of different pieces of user information collected in advance, and the first multidimensional label vector of the target user information and the first multidimensional label vector of the standard user information are calculated according to a collaborative filtering algorithm. Specifically, the feature set of the standard user information is represented as { u }₁,u₂,u₃,..u_mThe feature set of the template style label is q₁,q₂,q₃,..q_KAnd taking the use times or the total times of each template style by a standard user as a scoring vector n_ijObtaining the operation vector I of the standard user information to the template_MKThe operation vector is as follows:

and when the target user information is obtained, calculating to obtain the operation vector of the target user information to the template according to the calculation mode of the operation vector. Then, according to the cosine similarity, calculating the similarity between different users, namely a first multi-dimensional label vector, wherein a calculation formula of the first multi-dimensional label vector is as follows:

wherein the content of the first and second substances,

the operation vector corresponding to the target user information,

and the operation vector corresponding to the standard user information is obtained.

The calculation modes of the second multi-dimensional label vector and the first multi-dimensional label vector are the same, specifically, the standard conference feature information is a plurality of different conference information collected in advance, and the feature set of the standard conference feature information is expressed as { U }₁,U₂,U₃,..U_LThe feature set of the template style label is q₁,q₂,q₃,..q_KAnd taking the use times or the total times of each template style on different conferences as a scoring vector N_ijObtaining the operation vector of the standard meeting characteristic information to the template

The operation vector is as follows:

the formula for calculating the second multi-dimensional label vector is as follows:

wherein the content of the first and second substances,

an operation vector of the template for the target conference feature information,

and (4) an operation vector of the standard meeting characteristic information to the template.

And finally, carrying out weighted summation on the first multi-dimensional label vector and the second multi-dimensional label vector to obtain total similarity, calculating according to the total similarity to obtain final adaptation, and selecting a template corresponding to the maximum value in the final adaptation as a display template matched with the feature information of the target conference and the information of the target user.

The calculation formula of the total similarity is as follows:

wherein the content of the first and second substances,

for the first multi-dimensional label vector is,

for the second multi-dimensional label vector,

is a preset weight parameter.

The calculation formula of the final adaptation degree is as follows:

wherein the content of the first and second substances,

、

is the score and mean of similar reporter v, N (u) is the reporterThe set of neighbors of (a) is,

is the total similarity.

According to the embodiment, the similarity is calculated through the collaborative filtering algorithm, the display template is determined according to the similarity, and the display template is rapidly acquired, so that the adaptive display template can be rapidly matched through the conference characteristic information and the user information, the data acquisition efficiency is improved, and the template acquisition duration is saved.

In some embodiments of the present application, the obtaining of the target text information includes:

In the present embodiment, the history text information is history recorded text information, such as text information of courseware, which is stored in the database. And acquiring the stored historical text information, and a first text label and a second text label of the historical text information, wherein the first text label and the second text label are historical conference feature information and historical user information corresponding to each piece of historical text information. For example, if the historical conference feature information corresponding to a certain historical text information is an a conference at a location a, and the historical user information is a B user participating in the conference, the first text label and the second text label corresponding to the historical text information may be represented as (a, B). And matching the target conference characteristic information and the target user information with the first text label and the second text label, and determining that the text information corresponding to the first text label and the second text label which are successfully matched with the target conference characteristic information and the target user information is the target text information.

According to the embodiment, the target text information matched with the conference characteristic information and the user information is automatically acquired, so that the data needing to be displayed in the conference can be efficiently acquired.

In some embodiments of the application, the acquiring the stored historical text information includes:

In this embodiment, OCR (Optical Character Recognition) refers to a process in which an electronic device checks a Character printed on paper, determines its shape by detecting dark and light patterns, and then translates the shape into a computer text by a Character Recognition method. And recording courseware information of each meeting, and recognizing the courseware information through OCR to obtain courseware text information. And when the courseware text information is obtained, performing cyclic redundancy check and BCC exclusive OR check on the courseware text information, wherein the cyclic redundancy check is used for error detection by using the principles of division and remainder. In practical application, the sending end calculates a CRC value and sends the CRC value to the receiving end together with the courseware text information, the receiving end recalculates the CRC on the received data and compares the CRC with the received CRC, and if the two CRC values are different, the data communication is wrong; if the two CRC values are the same, the data communication is correct, and the correct courseware text information is received. And carrying out exclusive or Check on BCC (Block Check Character), receiving all courseware text information into a memory of the computer during Check, then calculating a BCC Check value, splicing the received BCC value into a hexadecimal number, then comparing the two values, and if the two values are equal, judging that the received card number of the non-contact card reader is correct. And when the cyclic redundancy check and the BCC exclusive-OR check both pass, determining that the text information of the textbook passes the check, and storing the text information of the courseware as historical text information in a database.

In the embodiment, the courseware text information obtained through identification is verified and then stored in the database as the historical text information, so that the integrity of the stored data is ensured, errors possibly caused in the transmission process of the data are avoided, and the accurate and complete display of the data is further realized when the data are displayed through the historical text information.

In some embodiments of the present application, the acquiring target text information further includes:

In this embodiment, the recommended information data may be determined according to the obtained target user information, and the information data may be used as the target text information. Specifically, the similarity between the target user information and a preset label is calculated, wherein the preset label is a plurality of pieces of user information collected in advance. And selecting preset labels with a preset number as interactive labels according to the similarity from high to low, wherein if k preset labels with the highest similarity are selected as interactive labels, the interactive labels are the user label set similar to the target user information. Then, obtaining the score of the interactive tag on the stored information data, and calculating to obtain the matching degree according to the score and the interactive tag; and selecting an information collection corresponding to the target user information according to the matching degree. Wherein the information data is the image and text contents such as current affairs information. And finally, acquiring a history record of information recommendation of the user in the interactive label, taking information data recommended to the user in the interactive label in the acquired information collection as marked information data according to the history record, screening the marked information data, and taking the rest information data as target text information.

In the embodiment, the matched recommended information is obtained through the tag information matrix, so that the accurate pushing of the information data is realized, and the richness of the displayed data content is improved.

In some embodiments of the present application, after obtaining the target presentation data corresponding to the recommended conference flow, the method further includes:

In this embodiment, the tag vector is a vector obtained by converting the meeting feature information through feature engineering, and the feature vector is a vector obtained by converting the report type through feature engineering. After the target display data is obtained, the conference feature information is converted into a label vector through feature engineering, such as unique hot coding, and a report type corresponding to a stored report is obtained, wherein the report comprises a digital report and a chart. The prediction model is a sequencing prediction model of the report corresponding to the current conference, and the prediction model adopts a combined structure of a gradient lifting decision tree and a logistic regression model. When the label vector of the current conference feature information and the feature vector of the report are obtained, the label vector and the feature vector are input into the gradient lifting decision tree, and a plurality of discrete features are obtained through the path output of each leaf node of the gradient lifting decision tree. Carrying out single-hot coding on the discrete characteristics to obtain coding characteristics, and then carrying out linear weighted summation on the coding characteristics of each leaf node to obtain a summation value; and finally, inputting the summation value to a logistic regression model, and outputting through the logistic regression model to obtain the predicted connection probability. The predicted link probability is the probability value of the occurrence of another report after each report is output, such as the probability value of the occurrence of report B after report A and the probability value of the occurrence of report C after report B.

And when the predicted connection probability is obtained, sequencing the reports of the conference according to the predicted connection probability to obtain a sequencing result, wherein the sequencing result is the sequencing sequence of each report. For example, the predicted join probability of the report B to the report a is the largest, the report B is joined after the report a, the predicted join probability of the report C to the report B is the largest, the report C is joined after the report B, and the final obtained sorting result is A, B, C. And after the sequencing result is obtained, matching the corresponding report with the target display data of the conference according to the sequencing result, and finally obtaining the target display report corresponding to the target display data.

According to the embodiment, the display report of the conference is sequenced and predicted, so that the report of the conference is automatically generated, and the conference information can be quickly and directly acquired through the report.

In some embodiments of the present application, before the inputting the label vector and the feature vector into the preset prediction model, the method includes:

In this embodiment, a basic prediction model is obtained, which includes a gradient boosting decision tree and a logistic regression model. The gradient lifting decision tree is formed by a plurality of decision trees, multiple rounds of iteration are carried out on the gradient lifting decision tree, each round of decision tree generates one decision tree, and each decision device is trained on the basis of the residual error of the last round of classifier to finally obtain an optimal decision tree. The logistic regression model is a classification mathematical model, the property of the article can be judged through the logistic regression model, the adaptability probability of the article and the target is predicted, and the article is sequenced, in this embodiment, the prediction result finally obtained by the logistic regression model is the connection probability value between the report and the report.

And acquiring multiple groups of historical label data, historical characteristic data and historical interaction data as sample data, wherein the historical label data are historically stored conference characteristic labels, the historical characteristic data are historically stored report type data, and the historical interaction data are linking information of reports corresponding to each conference characteristic label. Training the gradient lifting decision tree and the logistic regression model according to the historical label data, the historical characteristic data and the historical interactive data, obtaining a minimum value in a loss function of the trained gradient lifting decision tree and the trained logistic regression model, and determining a model obtained by combining the trained gradient lifting decision tree and the trained logistic regression model as a target prediction model when the verification accuracy of verification data is greater than or equal to a preset threshold value. The verification data are historical label data, historical characteristic data and historical interaction data with preset proportion numbers.

According to the embodiment, the prediction model is trained, so that the report sequencing of the conference can be efficiently predicted through the prediction model, and the conference data can be efficiently managed.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an intelligent conference management apparatus, 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 various electronic devices.

As shown in fig. 3, the intelligent conference management device 300 according to the present embodiment includes: parsing module 301, prediction module 302, validation module 303, calculation module 304, and population module 304. Wherein:

the analysis module 301 is configured to, when a conference establishment request is received, analyze the conference establishment request to obtain a conference tag;

in this embodiment, when a conference establishment request is received, the conference establishment request is analyzed to obtain a conference tag corresponding to the conference establishment request, where the conference tag is a name of a conference module, and a complete conference process can be split into multiple conference modules. One or more conference tags may be obtained by parsing the conference setup request.

The prediction module 302 is configured to obtain a preset target neural network, and perform prediction sorting on the conference tag according to the target neural network to obtain a recommended conference flow;

The confirming module 303 is configured to input the recommended conference process to a preset knowledge graph, and determine target conference feature information and target user information from the preset knowledge graph according to a traversal algorithm;

in this embodiment, the preset knowledge graph is a relationship network graph describing relationships among a conference, a conference place and a user, and mainly includes three relationship dimension graphs, specifically, a geographical relationship graph, a conference relationship graph and a user relationship graph, and the three relationship dimension graphs together form the preset knowledge graph. The geographical relationship map represents the distance relationship between each department and the current meeting place, and the distance weight of the relationship can be adjusted according to the floor of the meeting room and the actual geographical position; the conference relation map represents the relation between different conference rooms, and the distance weight of the relation is adjusted according to the holding frequency of a specific conference room; the user relationship map represents the relationship between different users and the conference, and the distance weight of the relationship is adjusted according to the importance of the participants (i.e. users) in the conference and the frequency of the past participants in the conference.

And when the recommended conference flow is obtained, inputting the recommended conference flow to the preset knowledge graph, and determining optimal target conference characteristic information and target user information from the preset knowledge graph according to a traversal algorithm (such as an breadth-first algorithm). The target conference feature information is feature information such as a target conference place, and the target user information is information of personnel needing to participate in the conference at present, such as a participant, a speaker and a host. Specifically, when the recommended conference flow is obtained, the corresponding conference type, such as an early meeting and a late meeting, is determined according to the recommended conference flow, and the final conference name, such as an early meeting 1 and an early meeting 2, can be determined by combining the conference type with the conference time. When the meeting name is obtained, finding the target user information with the shortest distance corresponding to the meeting name from the preset knowledge graph; and then, taking the conference name and the target user information as input items of a preset knowledge graph, and finding out target conference characteristic information optimal to the target user information from the preset knowledge graph according to a traversal algorithm.

The following proposes a traversal algorithm for calculating the shortest path:

The calculation module 304 is configured to calculate the target conference feature information and the target user information through a preset collaborative filtering algorithm to obtain a display template;

wherein, the calculating module 304 comprises:

the matching unit is used for calculating a first multi-dimensional label vector of the target user information and the stored standard user information according to the collaborative filtering algorithm and calculating a second multi-dimensional label vector of the target conference characteristic information and the stored standard conference characteristic information;

and the selecting unit is used for carrying out weighted summation on the first multi-dimensional label vector and the second multi-dimensional label vector to obtain total similarity, calculating final adaptation degree according to the total similarity, and determining a template corresponding to the maximum value of the final adaptation degree as the display template.

In this embodiment, when obtaining the feature information of the target conference and the target user information, the display template may be obtained by calculating the target conference information and the target user information through a preset collaborative filtering algorithm. The collaborative filtering algorithm is a recommendation algorithm, a display template matched with the current target conference feature information and the target user information can be obtained through calculation through the collaborative filtering algorithm, and the display template is template data required to be displayed in the current conference, such as a slide template. Specifically, the target conference feature information and the target user information are respectively matched with the stored standard conference feature information and the stored standard user information, and a first multi-dimensional label vector and a second multi-dimensional label vector are obtained through cosine similarity calculation, wherein the first multi-dimensional label vector is the cosine similarity of the target user information and the standard user information, and the second multi-dimensional label vector is the cosine similarity of the target conference feature information and the standard conference feature information. And calculating the first multi-dimensional label vector and the second multi-dimensional label vector to obtain the final adaptation degree corresponding to the target characteristic information and the target user information, and determining the template corresponding to the final adaptation degree of the maximum value as a display template matched with the target conference characteristic information and the target user information.

And a filling module 305, configured to obtain target text information, and fill the target text information into the display template to obtain target display data corresponding to the recommended conference process.

Wherein the filling module 305 comprises:

the device comprises a first acquisition unit, a second acquisition unit and a display unit, wherein the first acquisition unit is used for acquiring stored historical text information and a first text label and a second text label of the historical text information;

and the confirming unit is used for matching the first text label with the target conference characteristic information, matching the second text label with the target user information, and determining that the text information corresponding to the first text label and the second text label which are successfully matched with the target conference characteristic information and the target user information is the target text information.

Wherein, the acquisition unit includes:

the recording subunit is used for recording courseware information of each meeting and identifying the courseware information through OCR to obtain corresponding courseware text information;

and the checking subunit is used for performing cyclic redundancy check and XOR check on the courseware text information, and storing the courseware text information as the historical text information in a database when the courseware text information passes the check.

Wherein, the filling module 305 further comprises:

the calculating unit is used for calculating the similarity between the target user information and preset labels, and selecting the preset labels with preset number as interactive labels according to the similarity from high to low;

the second acquisition unit is used for acquiring the scores of the interactive tags on the stored information data, calculating the matching degree according to the scores and the interactive tags, and selecting the information set corresponding to the target user information according to the matching degree;

and the screening unit is used for screening out the marked information data in the information set according to the history record to obtain residual information data, and using the residual information data as the target text information.

The intelligent conference management device provided by this embodiment further includes:

the first acquisition module is used for acquiring a tag vector of the conference feature information and a feature vector of a stored report, inputting the tag vector and the feature vector into a preset prediction model, and calculating according to the prediction model to obtain a prediction connection probability between different reports corresponding to the target display data;

and the sequencing module is used for sequencing the report according to the predicted connection probability to obtain a target display report corresponding to the target display data.

The second obtaining module is used for obtaining a basic prediction model, wherein the basic prediction model comprises a gradient lifting decision tree and a logistic regression model;

and the training module is used for acquiring historical label data, historical characteristic data and historical interaction data, and training the gradient lifting decision tree and the logistic regression model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the prediction model.

The intelligent conference management device provided by the embodiment realizes intelligent recommendation and data display of a conference process, automatically tracks data required in a conference, and improves data processing efficiency and conference resource utilization rate.

In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4, fig. 4 is a block diagram of a basic structure of a computer device according to the present embodiment.

The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only a computer device 6 having components 61-63 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.

The memory 61 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal storage unit of the computer device 6 and an external storage device thereof. In this embodiment, the memory 61 is generally used for storing an operating system installed in the computer device 6 and various application software, such as computer readable instructions of the intelligent conference management method. Further, the memory 61 may also be used to temporarily store various types of data that have been output or are to be output.

The processor 62 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute computer readable instructions stored in the memory 61 or process data, for example, execute computer readable instructions of the intelligent conference management method.

The network interface 63 may comprise a wireless network interface or a wired network interface, and the network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.

The computer equipment provided by the embodiment realizes intelligent recommendation and data display of a conference process, automatically tracks data required in a conference, and improves the data processing efficiency and the utilization rate of conference resources.

The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the intelligent conference management method as described above.

The computer-readable storage medium provided by the embodiment realizes intelligent recommendation and data display of a conference process, and meanwhile, automatically tracks data required in a conference, thereby improving the data processing efficiency and the utilization rate of conference resources.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.

Claims

1. An intelligent conference management method is characterized by comprising the following steps:

2. The intelligent conference management method according to claim 1, wherein the step of calculating the target conference feature information and the target user information through a preset collaborative filtering algorithm to obtain a presentation template specifically comprises:

3. The intelligent conference management method according to claim 1, wherein the step of obtaining the target text information specifically comprises:

4. The intelligent conference management method according to claim 3, wherein the step of obtaining the stored historical text information specifically comprises:

5. The intelligent conference management method according to claim 1, wherein the step of obtaining target text information further comprises:

6. The intelligent conference management method according to claim 1, further comprising, after the step of obtaining the target presentation data corresponding to the recommended conference flow:

7. The intelligent conference management method according to claim 6, further comprising, before the step of inputting the tag vector and the feature vector to a preset prediction model:

8. An intelligent meeting management device, comprising:

9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the intelligent conference management method of any one of claims 1 to 7.

10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the intelligent conference management method of any of claims 1 to 7.