CN113113018B - Enterprise intelligent management system and method based on big data - Google Patents

Enterprise intelligent management system and method based on big data Download PDF

Info

Publication number
CN113113018B
CN113113018B CN202110409593.7A CN202110409593A CN113113018B CN 113113018 B CN113113018 B CN 113113018B CN 202110409593 A CN202110409593 A CN 202110409593A CN 113113018 B CN113113018 B CN 113113018B
Authority
CN
China
Prior art keywords
word
conference
text
enterprise
meeting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110409593.7A
Other languages
Chinese (zh)
Other versions
CN113113018A (en
Inventor
李静芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Saisheng Technology Co ltd
Original Assignee
Beijing Saisheng Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Saisheng Technology Co ltd filed Critical Beijing Saisheng Technology Co ltd
Priority to CN202110409593.7A priority Critical patent/CN113113018B/en
Publication of CN113113018A publication Critical patent/CN113113018A/en
Application granted granted Critical
Publication of CN113113018B publication Critical patent/CN113113018B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/12—Digital output to print unit, e.g. line printer, chain printer
    • G06F3/1201—Dedicated interfaces to print systems
    • G06F3/1202—Dedicated interfaces to print systems specifically adapted to achieve a particular effect
    • G06F3/1203—Improving or facilitating administration, e.g. print management
    • G06F3/1205—Improving or facilitating administration, e.g. print management resulting in increased flexibility in print job configuration, e.g. job settings, print requirements, job tickets
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/12—Digital output to print unit, e.g. line printer, chain printer
    • G06F3/1201—Dedicated interfaces to print systems
    • G06F3/1223—Dedicated interfaces to print systems specifically adapted to use a particular technique
    • G06F3/1237—Print job management
    • G06F3/1253—Configuration of print job parameters, e.g. using UI at the client
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
    • G06Q10/1093—Calendar-based scheduling for persons or groups
    • G06Q10/1095—Meeting or appointment
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/04—Segmentation; Word boundary detection
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Acoustics & Sound (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Economics (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Telephonic Communication Services (AREA)
  • Document Processing Apparatus (AREA)

Abstract

The invention discloses an enterprise intelligent management system and method based on big data, which are used for solving the problem of inaccurate conference content transmission caused by manual recording and manual transmission of conference content in the original enterprise conference.

Description

Enterprise intelligent management system and method based on big data
Technical Field
The invention belongs to the technical field of big data, relates to an enterprise intelligent management technology, and particularly relates to an enterprise intelligent management system and method based on big data.
Background
Enterprise management is a general term for a series of activities such as planning, organizing, commanding, coordinating and controlling the production and operation activities of enterprises, and is an objective requirement for social mass production. The enterprise management aims at achieving the purposes of saving, speeding up, increasing and improving resources and achieving the maximum input-output efficiency by using resources such as manpower, material resources, financial resources, information and the like of the enterprise as much as possible.
The existing enterprise management layer needs to record manually when a meeting is carried out, then the management layer transmits meeting content to subordinate employees, when the meeting content is more, and when the meeting is recorded, the meeting content is not accurately transmitted because the meeting content is not completely recorded, and meanwhile, manual recording wastes time and labor, so that the enterprise intelligent management system and method based on big data are provided.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an enterprise intelligent management system and method based on big data.
The technical problem to be solved by the invention is as follows:
how to need not artifical record and artifical meeting content of conveying when enterprise meeting, solve because meeting content record is incomplete to lead to the inaccurate problem of meeting content conveying.
The purpose of the invention can be realized by the following technical scheme: an enterprise intelligent management system based on big data comprises a registration login module, a data acquisition module, a voice recognition module, a conference recording module, a generation printing module, an intelligent transmission module and a server;
the data acquisition module sends the voice information corresponding to each enterprise conference data to the voice recognition module; the voice recognition module receives voice information of the enterprise conference data and is used for carrying out voice recognition on the voice information of the enterprise conference data, and the voice recognition process specifically comprises the following steps:
step S1: extracting voice information in the enterprise conference data, and dividing a plurality of voice words Yu, u =1,2, … … and x of the voice information in the enterprise conference by a Chinese word segmentation method;
step S2: acquiring a conference theme in enterprise conference data, comparing the conference theme with text phrases word by word to obtain word number information of the text phrases repeated with the conference theme, and marking the word number information as H1; marking the total word number of the conference theme as H2, and obtaining the overlapping rate H3 of the text phrases by using a formula H3= H1/H2;
and step S3: judging the overlapping rate H3 of the text phrases;
and step S4: traversing and comparing each voice word Yu with the text words in the preferred identification group, and recording a plurality of text words in the preferred identification group as Wi, i =1,2, … …, x; calculating the similarity ratio Xu of each voice word by using a formula Xu = Wi/Yu;
step S5: selecting an upper limit value of the similarity rate of each voice word to obtain a corresponding text word;
the server is in data connection with a Chinese word stock through the Internet, and matching scores among text words are stored in the Chinese word stock; the voice recognition module sends the text words recognized by the voice information in the enterprise conference to the conference recording module one by one; the conference recording module is used for carrying out online splicing recording on the text words after receiving the text words sent by the voice recognition module, and the online splicing recording comprises the following working steps:
step SS1: acquiring a first word and a last word of each text word;
step SS2: respectively matching the pinyin of the first-order word and the pinyin of the last-order word with characters in a Chinese word stock, setting characters in the Chinese word stock corresponding to successful matching of the first-order word of the text word as first candidate characters, and setting characters in the Chinese word stock corresponding to successful matching of the last-order word of the text word as last candidate characters;
step SS3: arranging the first candidate character and the last candidate character according to the mode that the last candidate character is in front of the first candidate character and the first candidate character is behind the last candidate character to form a plurality of candidate words;
and step SS4: calculating a matching score corresponding to each candidate word, taking the first three words after the matching scores corresponding to each candidate word are arranged in a descending order, obtaining a first candidate word and a last candidate word corresponding to the first three words of each candidate word, and finally obtaining a first word and a last word corresponding to the first candidate word and the last candidate word respectively;
and step SS5: combining the text words of the first word and the text words of the last word to form three groups of conference content sentences;
step SS6: and sending the three groups of conference content sentences to the user terminal, and selecting the conference content sentences which best accord with the conference content of the enterprise by enterprise management personnel of the user terminal and feeding the conference content sentences back to the server.
Furthermore, the registration login module is used for performing registration login after the enterprise staff inputs personal information through the user terminal and sending the personal information to the server for storage;
the personal information comprises the name, sex, age, identification card number, mobile phone number of real-name authentication, affiliated department and enterprise work number of the enterprise employee.
Further, the data acquisition module comprises a sound and video recording unit;
the sound and video recording unit is used for recording the sound and video of the enterprise conference in the whole process; the data acquisition module is used for acquiring enterprise conference data and sending the acquired enterprise conference data to the server; the enterprise conference data comprises departments corresponding to the enterprise conference, enterprise conference subjects, and video information and voice information corresponding to the enterprise conference;
a plurality of text phrases are stored in the server, and the text phrases correspond to the conference subjects one by one; and a plurality of text words are correspondingly arranged in each text phrase, and the text words of each text phrase are combined into a corresponding voice recognition group.
Further, the determination process of the text word overlap ratio specifically includes:
when the H3 is larger than or equal to the set value X1, obtaining text words with the highest overlapping rate, marking the voice recognition group corresponding to the text words as a preferred recognition group, executing the step S4, and marking the rest voice recognition groups as alternative recognition groups;
and when the H3 is smaller than the set value X1, judging that the text phrase has errors at the moment, and acquiring a substitute recognition group to perform word-by-word comparison with the conference theme.
Further, the server adds the meeting department and the meeting theme to the meeting content sentence to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module; the intelligent transmission module receives a conference file with a company file number sent by the server and is used for intelligently transmitting the conference file to a corresponding department according to a conference department;
when the meeting file needs to be generated and printed, the intelligent transmission module sends the meeting file with the company file number and the printing requirement to the generation and printing module, and after the generation and printing module receives the meeting file with the company file number and the printing requirement sent by the intelligent transmission module, the meeting file with the company file number is generated and printed according to the printing requirement.
Further, the printing requirements comprise the number of printing copies, the printing page mode, the printing specification and the printing paper specification.
An enterprise intelligent management method based on big data comprises the following specific steps:
firstly, enterprise employees register and log in an enterprise intelligent management system through a registration and logging module, and send personal information to a server for storage; when a company carries out various conferences, enterprise conference data is acquired through a data acquisition module;
step two, the data acquisition module sends the voice information corresponding to the enterprise conference data to the voice recognition module, the voice recognition module carries out voice recognition on the voice information of the enterprise conference data, extracts the voice information in the enterprise conference data, obtains conference subjects in the enterprise conference data simultaneously through a Chinese word segmentation method, compares the conference subjects with text phrases word groups word by word to obtain word number information of the text phrase repeated with the conference subjects and total word number of the conference subjects, calculates the overlapping rate of the text phrase, and when the overlapping rate of the text phrase is more than or equal to a set value, marks the text phrase with the highest overlapping rate as a preferred recognition group corresponding to the voice recognition group, and marks the rest voice recognition groups as replacement recognition groups; when the overlapping rate of the text words is smaller than a set value, judging that the text word group has errors at the moment, acquiring a substitute recognition group and a conference theme to perform word-by-word comparison, performing traversal comparison on each voice word and the text word in the preferred recognition group, calculating to obtain the similarity rate of each voice word, and selecting the upper limit value of the similarity rate of each voice word to obtain the corresponding text word;
step three, the voice recognition module sends the text words recognized by the voice information in the enterprise meeting to a meeting recording module one by one, the meeting recording module receives the text words sent by the voice recognition module and then is used for carrying out online splicing recording on the text words to obtain a first word and a last word of each text word, the pinyin of the first word and the pinyin of the last word are respectively matched with characters in a Chinese word library, characters in the Chinese word library corresponding to successful matching of the first word of the text words are set as first candidate characters, characters in the Chinese word library corresponding to successful matching of the last word of the text words are set as last candidate characters, the first candidate characters and the last candidate characters are arranged to form a plurality of candidate words according to the mode that the last candidate characters are in front and the first candidate characters are behind, matching scores corresponding to each candidate word are calculated, the first three candidate characters and the last candidate characters are taken after the matching scores corresponding to each candidate word are arranged in a descending order, the first word and the last word corresponding candidate characters of each candidate word are obtained, and the contents of the first word and the last word corresponding candidate words are sent to a meeting terminal text sentence management server of the enterprise user, and the contents of the meeting text words are fed back to the meeting terminal sentence, and the meeting user terminal sentence, and the meeting user;
and step four, the server adds the meeting department and the meeting theme to the meeting content statement to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module, the intelligent transmission module intelligently transmits the meeting file to the corresponding department according to the meeting department, when the meeting file needs to be generated and printed, the intelligent transmission module sends the meeting file with the company file number and the printing requirement to the generation and printing module, and the generation and printing module generates and prints the meeting file with the company file number according to the printing requirement.
Compared with the prior art, the invention has the beneficial effects that:
1. the method comprises the steps of carrying out voice recognition on voice information of enterprise conference data through a voice recognition module, carrying out word-by-word comparison on a conference theme and text phrases through a Chinese word segmentation method to obtain a plurality of text phrases of the voice information in the enterprise conference, obtaining a conference theme in the enterprise conference data, obtaining the overlapping rate of the text phrases, comparing the overlapping rate of the text phrases with a set value, marking a voice recognition group corresponding to the text phrase with the highest overlapping rate as a preferred recognition group when the overlapping rate of the text phrases is greater than or equal to the set value, marking the rest voice recognition groups as alternate recognition groups, judging that the text phrase has an error at the moment when the overlapping rate of the text phrases is smaller than the set value, obtaining the alternate recognition groups to carry out word-by-word comparison on the conference theme, carrying out traversal comparison on each voice phrase and the text phrase in the preferred recognition group, calculating the similarity rate of each voice phrase, selecting the upper limit value of the similarity rate of each voice phrase, and obtaining the corresponding text phrase;
2. the method comprises the steps of performing online splicing recording on text words through a conference recording module, respectively matching pinyin of a first word and pinyin of a last word with characters in a Chinese word library through a first word and a last word of each text word to obtain a first candidate word and a last candidate word, calculating a matching score corresponding to each candidate word, and taking the first three words after the matching scores corresponding to each candidate word are arranged in a descending order, so that the corresponding text words are combined to form three groups of conference content sentences, the three groups of conference content sentences are sent to a user terminal, and an enterprise manager of the user terminal selects the conference content sentences which best accord with the conference content of enterprises and feeds back the conference content sentences to a server;
3. the conference file with the company file number is generated by adding a conference department and a conference subject to a conference content statement and is sent to the intelligent transmission module, the intelligent transmission module intelligently transmits the conference file to a corresponding department according to the conference department, meanwhile, when the conference file needs to be generated and printed, the intelligent transmission module sends the conference file with the company file number and a printing requirement to the generation and printing module, and the generation and printing module generates and prints the conference file with the company file number according to the printing requirement.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is an overall system block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, an enterprise intelligent management system based on big data includes a registration module, a data acquisition module, a voice recognition module, a conference recording module, a generation and printing module, an intelligent transmission module, and a server;
the registration login module is used for performing registration login after the enterprise staff inputs personal information through the user terminal and sending the personal information to the server for storage; the personal information comprises the name, sex, age, identification card number, mobile phone number of real-name authentication, affiliated department, enterprise employee number and the like of the enterprise employee;
the data acquisition module comprises a sound and video recording unit; the audio and video recording unit is used for recording the audio and video of the enterprise meeting in the whole process; the data acquisition module is used for acquiring enterprise conference data and sending the acquired enterprise conference data to the server; the enterprise conference data comprises departments corresponding to the enterprise conference, enterprise conference subjects, video information and voice information corresponding to the enterprise conference and the like;
a plurality of text phrases are stored in the server, and the text phrases correspond to the conference subjects one by one; each text phrase is correspondingly provided with a plurality of text words, and the text words of each text phrase are combined into a corresponding voice recognition group;
the data acquisition module sends the voice information corresponding to the enterprise conference data to the voice recognition module; the voice recognition module receives voice information of the enterprise conference data and is used for carrying out voice recognition on the voice information of the enterprise conference data, and the voice recognition process specifically comprises the following steps:
step S1: extracting voice information in the enterprise conference data, and dividing a plurality of voice words Yu, u =1,2, … … and x of the voice information in the enterprise conference by a Chinese word segmentation method;
step S2: acquiring a conference theme in enterprise conference data, comparing the conference theme with text phrases word by word to obtain word number information of the text phrases repeated with the conference theme, and marking the word number information as H1; marking the total word number of the conference theme as H2, and obtaining the overlapping rate H3 of the text phrases by using a formula H3= H1/H2;
and step S3: judging the overlapping rate H3 of the text phrases;
when the H3 is larger than or equal to the set value X1, obtaining text words with the highest overlapping rate, marking the voice recognition group corresponding to the text word group as a preferred recognition group, executing the step S4, and marking the rest voice recognition groups as alternative recognition groups;
when H3 is smaller than a set value X1, judging that the text phrase has an error at the moment, and acquiring a substitute recognition group to perform word-by-word comparison with the conference theme;
and step S4: traversing and comparing each voice word Yu with the text words in the preferred identification group, and recording a plurality of text words in the preferred identification group as Wi, i =1,2, … …, x; calculating the similarity ratio Xu of each voice word by using a formula Xu = Wi/Yu;
step S5: selecting an upper limit value of the similarity rate of each voice word to obtain a corresponding text word;
for example, the following steps are carried out: the preferred recognition group comprises text words Wi = { W1, W2, W3, … …, wx }, if the text word corresponding to the voice word Y3 is W2, when the voice word Y4 is subjected to traversal comparison with the preferred recognition group, the voice word Y4 is not compared with the text word W2 in the preferred recognition group any more, but certain similarity between the voice word Y4 and the voice word Y3 is not excluded, the similarity can also be set to be a threshold, if the similarity ratio between the voice word Y4 and the voice word Y3 exceeds the threshold, the voice word Y4 does not need to be subjected to traversal comparison with the preferred recognition group, and the text word W2 corresponding to the voice word Y3 is directly disclosed to the voice word Y4;
the server is in data connection with a Chinese word bank through the Internet, and matching scores among text words are stored in the Chinese word bank; the voice recognition module sends the text words recognized by the voice information in the enterprise conference to the conference recording module one by one; the conference recording module is used for carrying out online splicing recording on the text words after receiving the text words sent by the voice recognition module, and the online splicing recording comprises the following working steps:
step SS1: acquiring a head word and a tail word of each text word;
step SS2: respectively matching the pinyin of the first-order word and the pinyin of the last-order word with characters in a Chinese word stock, setting characters in the Chinese word stock corresponding to successful matching of the first-order word of the text word as first candidate characters, and setting characters in the Chinese word stock corresponding to successful matching of the last-order word of the text word as last candidate characters;
and step SS3: arranging the first candidate character and the last candidate character according to the mode that the last candidate character is in front of the first candidate character and the first candidate character is behind the last candidate character to form a plurality of candidate words;
and step SS4: calculating a matching score corresponding to each candidate word, taking the first three words after the matching scores corresponding to each candidate word are arranged in a descending order, obtaining a first candidate word and a last candidate word corresponding to the first three words of each candidate word, and finally obtaining a first word and a last word corresponding to the first candidate word and the last candidate word respectively;
and step SS5: combining the text words of the first word and the text words of the last word to form three groups of conference content sentences;
step SS6: the three groups of conference content sentences are sent to the user terminal, and enterprise management personnel of the user terminal selects the conference content sentences which best meet the conference content of the enterprise and feeds the conference content sentences back to the server;
for example, the following steps are carried out: the text words comprise the following words in the evening, the communication part, the whole dinner party, the place, the drunk high-rise building, the necessity and the on-time arrival, and the first word and the last word of each text word are respectively as follows: d, D; a through part; preparing and eating; a ground part and a place part; drunkenness and storied building; affair, must; carrying out standard and standard;
first and last words of individual text words: ": the previous and present; a through part; preparing and eating; a ground part and a place part; drunkenness and storied building; affair, must; matching the standard word and the standard word with the Chinese word stock successfully;
the matching scores of the last word 'up' and other first words 'part', 'whole', 'ground', 'drunk', 'affair' and 'quasi' are calculated, and the matching scores of the last word 'part', 'meal', 'on', 'building', 'must', 'reached' and other first words are calculated by analogy;
the Chinese word stock stores matching scores of 'upper' and 'part', 'whole', 'ground', 'drunk', 'quasi' of 100, 50, 20, 10, 8.5 and 2 respectively; the matching score is obtained by obtaining sentence rules, sentence habits, sentence smoothness and the like among a plurality of Chinese characters through daily sentence sorting and analysis, and can be set in a midday word stock;
at the moment, three candidate words which are matched with the first three scores and are formed by the last word, the first word, the second word and the ground are taken as the upper part, the upper part and the lower part, corresponding text words are respectively obtained, and then a conference content sentence, namely a communication part at the night today, a whole dinner at the night today and a place at the night today, is formed, and an enterprise manager selects the communication part at the night today which is most consistent with the conference content of the enterprise and feeds back the conference content to the server;
the server adds the meeting department and the meeting theme to the meeting content sentence to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module; the intelligent transmission module receives a conference file with a company file number sent by the server and is used for intelligently transmitting the conference file to a corresponding department according to a conference department;
when the conference file needs to be generated and printed, the intelligent transmission module sends the conference file with the company file number and the printing requirement to the generation and printing module, and the generation and printing module generates and prints the conference file with the company file number according to the printing requirement after receiving the conference file with the company file number and the printing requirement sent by the intelligent transmission module;
the printing requirements include: the number of copies to be printed, the page printing method (single-sided printing, double-sided printing), the printing specification, the printing paper specification, and the like.
Example two
Based on another concept of the same invention, the enterprise intelligent management method based on big data comprises the following specific steps:
firstly, enterprise employees register and log in an enterprise intelligent management system through a registration and logging module, and send personal information to a server for storage; when a company carries out various conferences, enterprise conference data is acquired through a data acquisition module;
step two, the data acquisition module sends the voice information corresponding to the enterprise conference data to the voice recognition module, the voice recognition module carries out voice recognition on the voice information of the enterprise conference data, extracts the voice information in the enterprise conference data, obtains conference subjects in the enterprise conference data simultaneously through a Chinese word segmentation method, compares the conference subjects with text phrases word groups word by word to obtain word number information of the text phrase repeated with the conference subjects and total word number of the conference subjects, calculates the overlapping rate of the text phrase, and when the overlapping rate of the text phrase is more than or equal to a set value, marks the text phrase with the highest overlapping rate as a preferred recognition group corresponding to the voice recognition group, and marks the rest voice recognition groups as replacement recognition groups; when the overlapping rate of the text words is smaller than a set value, judging that the text word group has errors at the moment, acquiring a substitute recognition group and a conference theme to perform word-by-word comparison, performing traversal comparison on each voice word and the text word in the preferred recognition group, calculating to obtain the similarity rate of each voice word, and selecting the upper limit value of the similarity rate of each voice word to obtain the corresponding text word;
step three, the voice recognition module sends the text words recognized by voice information in the enterprise meeting to a meeting recording module one by one, the meeting recording module receives the text words sent by the voice recognition module and then is used for carrying out online splicing recording on the text words to obtain a first word and a last word of each text word, the pinyin of the first word and the pinyin of the last word are respectively matched with the characters in a Chinese word library, the characters in the Chinese word library corresponding to successful matching of the first word of the text words are set as first candidate words, the characters in the Chinese word library corresponding to successful matching of the last word of the text words are set as last candidate words, the first word and the last candidate words are arranged to form a plurality of candidate words according to the mode that the last candidate words are in front and the first candidate words are in back, the matching score corresponding to each candidate word is calculated, the first three candidate words are taken after the matching score corresponding to each candidate word is arranged in descending order, the first word and the last word corresponding to each candidate word are obtained, finally the first candidate word and the last word corresponding to obtain the first candidate word and the last word corresponding candidate word and the last word, the first word and last word corresponding candidate word and last word are combined with the meeting terminal word content of the meeting words of the meeting statement, and the conference statement of the conference user, and the conference user terminal statement, and the conference user are fed back to the conference user management server, and the conference user terminal statement, and the conference user is fed back to the conference user;
and step four, the server adds a meeting department and a meeting subject to the meeting content statement to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module, the intelligent transmission module intelligently transmits the meeting file to a corresponding department according to the meeting department, when the meeting file needs to be generated and printed, the intelligent transmission module sends the meeting file with the company file number and a printing requirement to the generation and printing module, and the generation and printing module generates and prints the meeting file with the company file number according to the printing requirement.
The above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula which obtains the latest real situation by acquiring a large amount of data and performing software simulation, and the preset parameters in the formula are set by the technical personnel in the field according to the actual situation.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand the invention for and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims (2)

1. An enterprise intelligent management system based on big data is characterized by comprising a registration login module, a data acquisition module, a voice recognition module, a conference recording module, a generation printing module, an intelligent transmission module and a server;
the data acquisition module sends the voice information corresponding to each enterprise conference data to the voice recognition module; the voice recognition module receives voice information of the enterprise conference data and is used for carrying out voice recognition on the voice information of the enterprise conference data, and the voice recognition process specifically comprises the following steps:
step S1: extracting voice information in the enterprise conference data, and dividing a plurality of voice words Yu, u =1,2, … … and x of the voice information in the enterprise conference by a Chinese word segmentation method;
step S2: acquiring a conference theme in the enterprise conference data, comparing the conference theme with the text phrases word by word to obtain word number information of the text phrases which are repeated with the conference theme, and marking the word number information as H1; marking the total word number of the conference theme as H2, and obtaining the overlapping rate H3 of the text phrases by using a formula H3= H1/H2;
and step S3: judging the overlapping rate H3 of the text phrases;
and step S4: traversing and comparing each voice word Yu with the text words in the preferred identification group, and recording a plurality of text words in the preferred identification group as Wi, i =1,2, … …, x; calculating to obtain the similarity ratio Xu of each voice word;
step S5: selecting an upper limit value of the similarity rate of each voice word to obtain a corresponding text word;
the server is in data connection with a Chinese word stock through the Internet, and matching scores among text words are stored in the Chinese word stock; the voice recognition module sends the text words recognized by the voice information in the enterprise conference to the conference recording module one by one; the conference recording module is used for carrying out online splicing recording on the text words after receiving the text words sent by the voice recognition module, and the online splicing recording comprises the following working steps:
step SS1: acquiring a first word and a last word of each text word;
step SS2: respectively matching the pinyin of the first-order word and the pinyin of the last-order word with characters in a Chinese word stock, setting characters in the Chinese word stock corresponding to successful matching of the first-order word of the text word as first candidate characters, and setting characters in the Chinese word stock corresponding to successful matching of the last-order word of the text word as last candidate characters;
and step SS3: arranging the first candidate character and the last candidate character according to the mode that the last candidate character is in front of the first candidate character and the first candidate character is behind the last candidate character to form a plurality of candidate words;
and step SS4: calculating a matching score corresponding to each candidate word, taking the first three words after the matching scores corresponding to each candidate word are arranged in a descending order, obtaining a first candidate word and a last candidate word corresponding to the first three words of each candidate word, and finally obtaining a first word and a last word corresponding to the first candidate word and the last candidate word respectively;
and step SS5: combining the text words of the first word and the text words of the last word to form three groups of conference content sentences;
step SS6: the three groups of conference content sentences are sent to the user terminal, and enterprise management personnel of the user terminal selects the conference content sentences which best meet the conference content of the enterprise and feeds the conference content sentences back to the server;
the registration login module is used for performing registration login after the enterprise staff inputs personal information through the user terminal and sending the personal information to the server for storage;
the personal information comprises the name, sex, age, identification card number, mobile phone number of real-name authentication, affiliated department and enterprise work number of the enterprise employee;
the data acquisition module comprises a sound and video recording unit;
the sound and video recording unit is used for recording the sound and video of the enterprise conference in the whole process; the data acquisition module is used for acquiring enterprise conference data and sending the acquired enterprise conference data to the server; the enterprise conference data comprises departments corresponding to the enterprise conference, enterprise conference subjects, and video information and voice information corresponding to the enterprise conference;
a plurality of text phrases are stored in the server, and the text phrases correspond to the conference subjects one by one; each text phrase is correspondingly provided with a plurality of text words, and the text words of each text phrase are combined into a corresponding voice recognition group;
the text word overlapping rate determination process specifically comprises the following steps:
when the H3 is larger than or equal to the set value X1, obtaining text words with the highest overlapping rate, marking the voice recognition group corresponding to the text word group as a preferred recognition group, executing the step S4, and marking the rest voice recognition groups as alternative recognition groups;
when H3 is smaller than a set value X1, judging that the text phrase has an error at the moment, and acquiring a substitute recognition group to perform word-by-word comparison with the conference theme;
the server adds the meeting department and the meeting theme to the meeting content sentence to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module; the intelligent transmission module receives a conference file with a company file number sent by the server and is used for intelligently transmitting the conference file to a corresponding department according to a conference department;
when the conference file needs to be generated and printed, the intelligent transmission module sends the conference file with the company file number and the printing requirement to the generation and printing module, and the generation and printing module generates and prints the conference file with the company file number according to the printing requirement after receiving the conference file with the company file number and the printing requirement sent by the intelligent transmission module;
the printing requirements comprise the number of printing copies, the page printing mode, the printing specification and the printing paper specification.
2. The method as claimed in claim 1, wherein the method comprises the following steps:
firstly, an enterprise employee registers and logs in an enterprise intelligent management system through a registration and logging module, and sends personal information to a server for storage; when a company carries out various conferences, enterprise conference data is acquired through a data acquisition module;
step two, the data acquisition module sends the voice information corresponding to the enterprise conference data to the voice recognition module, the voice recognition module carries out voice recognition on the voice information of the enterprise conference data, and enterprise conferences are extracted
The voice information in the conference data is obtained by a plurality of voice words of the voice information in the enterprise conference through a Chinese word segmentation method, the conference theme in the enterprise conference data is obtained at the same time, the conference theme and the text phrases are compared word by word to obtain word number information of the text phrases repeated with the conference theme and the total word number of the conference theme, the overlapping rate of the text phrases is obtained through calculation, when the overlapping rate of the text phrases is more than or equal to a set value, the voice recognition group corresponding to the text phrase with the highest overlapping rate is marked as a preferred recognition group, and the other voice recognition groups are marked as alternative recognition groups; when the overlapping rate of the text words is smaller than a set value, judging that the text word group has errors at the moment, acquiring a substitute recognition group and a conference theme to perform word-by-word comparison, performing traversal comparison on each voice word and the text word in the preferred recognition group, calculating to obtain the similarity rate of each voice word, and selecting the upper limit value of the similarity rate of each voice word to obtain the corresponding text word;
step three, the voice recognition module sends the text words recognized by the voice information in the enterprise meeting to a meeting recording module one by one, the meeting recording module receives the text words sent by the voice recognition module and then is used for carrying out online splicing recording on the text words to obtain a first word and a last word of each text word, the pinyin of the first word and the pinyin of the last word are respectively matched with characters in a Chinese word library, characters in the Chinese word library corresponding to successful matching of the first word of the text words are set as first candidate characters, characters in the Chinese word library corresponding to successful matching of the last word of the text words are set as last candidate characters, the first candidate characters and the last candidate characters are arranged to form a plurality of candidate words according to the mode that the last candidate characters are in front and the first candidate characters are behind, matching scores corresponding to each candidate word are calculated, the first three candidate characters and the last candidate characters are taken after the matching scores corresponding to each candidate word are arranged in a descending order, the first word and the last word corresponding candidate characters of each candidate word are obtained, and the contents of the first word and the last word corresponding candidate words are sent to a meeting terminal text sentence management server of the enterprise user, and the contents of the meeting text words are fed back to the meeting terminal sentence, and the meeting user terminal sentence, and the meeting user;
and step four, the server adds the meeting department and the meeting theme to the meeting content statement to generate a meeting file with a company file number, and sends the meeting file with the company file number to the intelligent transmission module, the intelligent transmission module intelligently transmits the meeting file to the corresponding department according to the meeting department, when the meeting file needs to be generated and printed, the intelligent transmission module sends the meeting file with the company file number and the printing requirement to the generation and printing module, and the generation and printing module generates and prints the meeting file with the company file number according to the printing requirement.
CN202110409593.7A 2021-04-16 2021-04-16 Enterprise intelligent management system and method based on big data Active CN113113018B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110409593.7A CN113113018B (en) 2021-04-16 2021-04-16 Enterprise intelligent management system and method based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110409593.7A CN113113018B (en) 2021-04-16 2021-04-16 Enterprise intelligent management system and method based on big data

Publications (2)

Publication Number Publication Date
CN113113018A CN113113018A (en) 2021-07-13
CN113113018B true CN113113018B (en) 2022-10-04

Family

ID=76717742

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110409593.7A Active CN113113018B (en) 2021-04-16 2021-04-16 Enterprise intelligent management system and method based on big data

Country Status (1)

Country Link
CN (1) CN113113018B (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7043426B2 (en) * 1998-04-01 2006-05-09 Cyberpulse, L.L.C. Structured speech recognition
CN111063355A (en) * 2018-10-16 2020-04-24 上海博泰悦臻网络技术服务有限公司 Conference record generation method and recording terminal
CN110457466A (en) * 2019-06-28 2019-11-15 谭浩 Generate method, computer readable storage medium and the terminal device of interview report
CN110335612A (en) * 2019-07-11 2019-10-15 招商局金融科技有限公司 Minutes generation method, device and storage medium based on speech recognition
CN111243590A (en) * 2020-01-17 2020-06-05 中国平安人寿保险股份有限公司 Conference record generation method and device
CN112346697A (en) * 2020-09-14 2021-02-09 北京沃东天骏信息技术有限公司 Method, device and storage medium for controlling equipment

Also Published As

Publication number Publication date
CN113113018A (en) 2021-07-13

Similar Documents

Publication Publication Date Title
CN109582949B (en) Event element extraction method and device, computing equipment and storage medium
CN110717031B (en) Intelligent conference summary generation method and system
CN110674639B (en) Natural language understanding method based on pre-training model
CN107766371B (en) Text information classification method and device
CN111104498B (en) Semantic understanding method in task type dialogue system
CN104598445B (en) Automatically request-answering system and method
CN104050160B (en) Interpreter's method and apparatus that a kind of machine is blended with human translation
WO2018000272A1 (en) Corpus generation device and method
CN110457689B (en) Semantic processing method and related device
CN107680019A (en) A kind of implementation method of Examination Scheme, device, equipment and storage medium
CN110807328A (en) Named entity identification method and system oriented to multi-strategy fusion of legal documents
CN113505586A (en) Seat-assisted question-answering method and system integrating semantic classification and knowledge graph
WO2021036439A1 (en) Method for responding to complaint, and device
CN107733782A (en) The method, apparatus and system of group is generated according to task
CN111428480B (en) Resume identification method, device, equipment and storage medium
WO2021017296A1 (en) Information recognition method, device, apparatus, and storage medium
CN110020327A (en) A kind of resume resolution system based on vertical search engine
CN114186983B (en) Video interview multidimensional scoring method, system, computer equipment and storage medium
CN112541095A (en) Video title generation method and device, electronic equipment and storage medium
CN113591489A (en) Voice interaction method and device and related equipment
CN107590121B (en) Text normalization method and system
CN109446522B (en) Automatic test question classification system and method
CN113113018B (en) Enterprise intelligent management system and method based on big data
TW202034207A (en) Dialogue system using intention detection ensemble learning and method thereof
US20210319481A1 (en) System and method for summerization of customer interaction

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20220907

Address after: 8th Floor, Building 1, Yard 35, Lugu Road, Shijingshan District, Beijing 100040

Applicant after: Beijing Saisheng Technology Co.,Ltd.

Address before: 535000 3rd floor, No.8 wisdom Park, No.1 Zhongma street, Zhongma Qinzhou Industrial Park, Qinzhou City, Guangxi Zhuang Autonomous Region

Applicant before: Qinzhou yunzhihui Big Data Technology Co.,Ltd.

GR01 Patent grant
GR01 Patent grant