CN112270166A - Method for quickly making and creating 5G message - Google Patents
Method for quickly making and creating 5G message Download PDFInfo
- Publication number
- CN112270166A CN112270166A CN202011153336.3A CN202011153336A CN112270166A CN 112270166 A CN112270166 A CN 112270166A CN 202011153336 A CN202011153336 A CN 202011153336A CN 112270166 A CN112270166 A CN 112270166A
- Authority
- CN
- China
- Prior art keywords
- message
- messages
- creating
- automatic classification
- authoring
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method for quickly making and creating a 5G message, which comprises the following steps of S1, inputting a message in equipment; s2, performing word segmentation on the input message; s3, intention recognition: the device divides the input message into corresponding intention categories through automatic classification; s4, extracting: extracting the characteristic content of the message after dividing the intention types; s5, filling: and filling the extracted characteristic content into a message template, namely obtaining the 5G message. The invention converts the common message into the 5G (RCS) message, adopts automatic conversion without human intervention, increases the efficiency, ensures the reliability of the quick construction of the 5G (RCS) message, reduces the labor cost and greatly accelerates the feeling of using the 5G (RCS) message by common users.
Description
Technical Field
The invention relates to the technical field of messages, in particular to a method for quickly making and creating a 5G message.
Background
With the evolution of communication technology, 5g (rcs) is a large-scale commercial year in 2020, and chinese operators will vigorously develop 5g (rcs) new infrastructure construction and upgrade the basic communication service comprehensively. The traditional text short messages and common multimedia messages do not meet the requirements of the existing enterprises, the traditional message display form is single, visual fatigue is brought to users, 5G (RCS) messages bring a brand-new man-machine interaction mode, the users can complete one-stop business experience of service searching, finding, interacting, paying and the like in a message window, and a brand-new message service entrance is constructed.
Because the 5g (rcs) message is a new message service, creating a 5g (rcs) message is much more complex than a traditional short message. The 5g (rcs) message adds many functions, such as: card, video, audio, built-in buttons, hover buttons, etc. The current industry solutions are all interface operations, which, although possible, also greatly increase the learning cost of the average person.
Disclosure of Invention
Aiming at the defects in reality, the invention provides a method for quickly making and creating the 5G message.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a method for rapidly making and creating 5G messages comprises the following steps,
s1, messaging the input within the device;
s2, performing word segmentation on the input message;
s3, intention recognition: the equipment divides the input message into corresponding types through automatic classification;
s4, extracting: extracting the characteristic content of the message after the type division;
s5, filling: and filling the extracted characteristic content into a message template, namely obtaining the 5G message.
Preferably, the message template is generated according to Natural Language Processing (NLP) semantic analysis.
Preferably, the training method for automatic classification includes: character preprocessing and feature obtaining; the word processing is to obtain the participles in the forms of the ending participles and the dictionary; the feature acquisition is to use text similarity calculation, the word is divided and then matched with the type feature, and the higher the similarity is, the more the description is matched with a certain type.
Preferably, the dictionary is a word stock, and common words are added in the word stock.
Preferably, the automatic classification training is performed in a plurality of fields, and the input message is classified into the corresponding fields when the automatic classification training is matched with the type.
Preferably, the training method adopts a traditional machine learning method or a deep learning method.
Preferably, the traditional learning method is bayes or svm.
Preferably, the deep learning method is fastText or TextCNN.
By adopting the technical scheme, the invention converts the common message into the 5G (RCS) message, adopts automatic conversion without human intervention, increases the efficiency, ensures the reliability of quick construction of the 5G (RCS) message, reduces the labor cost and greatly accelerates the feeling of using the 5G (RCS) message by common users.
Detailed Description
It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In one embodiment, a method for rapid authoring of a create 5G message comprises the steps of,
s1, messaging the input within the device;
s2, performing word segmentation on the input message;
s3, intention recognition: the equipment divides the input message into corresponding types through automatic classification;
s4, extracting: extracting the characteristic content of the message after the type division;
s5, filling: and filling the extracted characteristic content into a message template, namely obtaining the 5G message.
Further, the message template is generated according to Natural Language Processing (NLP) semantic analysis.
Further, the training method for automatic classification comprises the following steps: character preprocessing and feature obtaining; the word processing is to obtain the participles in the forms of the ending participles and the dictionary; the feature acquisition is to use text similarity calculation, the word is divided and then matched with the type feature, and the higher the similarity is, the more the description is matched with a certain type.
Further, the dictionary is a word stock, and common words are added into the word stock.
Further, the automatic classification training is performed in a plurality of fields, and when the automatic classification training is matched with the type, the input message is divided into the corresponding fields.
Further, the training method adopts a traditional machine learning method or a deep learning method.
Further, the traditional learning method is bayes or svm.
Further, the deep learning method is fastText or TextCNN.
It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (8)
1. A method for rapidly producing and creating 5G messages is characterized by comprising the following steps,
s1, messaging the input within the device;
s2, performing word segmentation on the input message;
s3, intention recognition: the equipment divides the input message into corresponding types through automatic classification;
s4, extracting: extracting the characteristic content of the message after the type division;
s5, filling: and filling the extracted characteristic content into a message template, namely obtaining the 5G message.
2. The method for rapid authoring and creating 5G messages as claimed in claim 1, wherein: the message template is generated according to Natural Language Processing (NLP) semantic analysis.
3. The method for rapid authoring and creating 5G messages as claimed in claim 1, wherein: the training method for automatic classification comprises the following steps: character preprocessing and feature obtaining; the word processing is to obtain the participles in the forms of the ending participles and the dictionary; the feature acquisition is to use text similarity calculation, the word is divided and then matched with the type feature, and the higher the similarity is, the more the description is matched with a certain type.
4. A method for rapid authoring to create 5G messages as claimed in claim 3, wherein: the dictionary is a word stock, and common words are added in the word stock.
5. A method for rapid authoring to create 5G messages as claimed in claim 3, wherein: the automatic classification training is performed in a plurality of fields, and when the automatic classification training is matched with the type, the input message is divided into corresponding fields.
6. A method for rapid authoring to create 5G messages as claimed in claim 3, wherein: the training method adopts a traditional machine learning method or a deep learning method.
7. The method for rapid authoring and creating 5G messages as claimed in claim 6, wherein: the traditional learning method is Bayes or svm.
8. The method for rapid authoring and creating 5G messages as claimed in claim 6, wherein: the deep learning method is fastText or TextCNN.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011153336.3A CN112270166A (en) | 2020-10-26 | 2020-10-26 | Method for quickly making and creating 5G message |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011153336.3A CN112270166A (en) | 2020-10-26 | 2020-10-26 | Method for quickly making and creating 5G message |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112270166A true CN112270166A (en) | 2021-01-26 |
Family
ID=74342081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011153336.3A Pending CN112270166A (en) | 2020-10-26 | 2020-10-26 | Method for quickly making and creating 5G message |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112270166A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113543047A (en) * | 2021-07-01 | 2021-10-22 | 南京路云数据科技有限公司 | Method, system and device for making 5G message |
CN115499793A (en) * | 2021-06-18 | 2022-12-20 | 深圳艾派网络科技股份有限公司 | 5G short message making method and system and 5G short message system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110413769A (en) * | 2018-04-25 | 2019-11-05 | 北京京东尚科信息技术有限公司 | Scene classification method, device, storage medium and its electronic equipment |
CN110413767A (en) * | 2019-08-05 | 2019-11-05 | 浙江核新同花顺网络信息股份有限公司 | System and method based on spatial term rendering content |
US20200090643A1 (en) * | 2019-07-01 | 2020-03-19 | Lg Electronics Inc. | Speech recognition method and device |
CN111291156A (en) * | 2020-01-21 | 2020-06-16 | 同方知网(北京)技术有限公司 | Question-answer intention identification method based on knowledge graph |
-
2020
- 2020-10-26 CN CN202011153336.3A patent/CN112270166A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110413769A (en) * | 2018-04-25 | 2019-11-05 | 北京京东尚科信息技术有限公司 | Scene classification method, device, storage medium and its electronic equipment |
US20200090643A1 (en) * | 2019-07-01 | 2020-03-19 | Lg Electronics Inc. | Speech recognition method and device |
CN110413767A (en) * | 2019-08-05 | 2019-11-05 | 浙江核新同花顺网络信息股份有限公司 | System and method based on spatial term rendering content |
CN111291156A (en) * | 2020-01-21 | 2020-06-16 | 同方知网(北京)技术有限公司 | Question-answer intention identification method based on knowledge graph |
Non-Patent Citations (1)
Title |
---|
化柏林编著: "文本信息分析与全文检索技术", 科学技术文献出版社, pages: 182 - 185 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115499793A (en) * | 2021-06-18 | 2022-12-20 | 深圳艾派网络科技股份有限公司 | 5G short message making method and system and 5G short message system |
CN115499793B (en) * | 2021-06-18 | 2024-02-27 | 深圳艾派网络科技股份有限公司 | 5G short message making method, system and 5G short message system |
CN113543047A (en) * | 2021-07-01 | 2021-10-22 | 南京路云数据科技有限公司 | Method, system and device for making 5G message |
CN113543047B (en) * | 2021-07-01 | 2022-04-22 | 南京路云数据科技有限公司 | Method, system and device for making 5G message |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109189901B (en) | Method for automatically discovering new classification and corresponding corpus in intelligent customer service system | |
US20140067842A1 (en) | Information processing method and apparatus | |
US11386354B2 (en) | Information processing apparatus, information processing method, and program | |
CN106372053B (en) | Syntactic analysis method and device | |
CN112270166A (en) | Method for quickly making and creating 5G message | |
CN111144102B (en) | Method and device for identifying entity in statement and electronic equipment | |
CN116108857B (en) | Information extraction method, device, electronic equipment and storage medium | |
CN109783623A (en) | The data analysing method of user and customer service dialogue under a kind of real scene | |
EP4137966A1 (en) | Method and apparatus of extracting table information, electronic device and storage medium | |
CN112507702A (en) | Text information extraction method and device, electronic equipment and storage medium | |
CN106569996A (en) | Chinese-microblog-oriented emotional tendency analysis method | |
CN111061838B (en) | Text feature keyword determination method and device and storage medium | |
CN106446051A (en) | Deep search method of Eagle media assets | |
CN115146124A (en) | Question-answering system response method and device, equipment, medium and product thereof | |
CN111444720A (en) | Named entity recognition method for English text | |
CN110110326A (en) | A kind of text cutting method based on subject information | |
CN110413972B (en) | Intelligent table name field name complementing method based on NLP technology | |
CN112148852A (en) | Intelligent customer service method and device, storage medium and computer equipment | |
CN116303951A (en) | Dialogue processing method, device, electronic equipment and storage medium | |
CN111427996A (en) | Method and device for extracting date and time from human-computer interaction text | |
CN109408621B (en) | Dialogue emotion analysis method and system | |
CN111368532A (en) | Topic word embedding disambiguation method and system based on LDA | |
CN105373530A (en) | Chinese name identification method and apparatus | |
CN107133226A (en) | A kind of method and device for distinguishing theme | |
CN111640025B (en) | Method for realizing information labeling processing based on label system |
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 |
Effective date of registration: 20230613 Address after: No. 01-1, floor 2, building 1, No. 25, lantianchang South Road, Haidian District, Beijing 100097 Applicant after: Beijing Guodu Internet Technology Co.,Ltd. Address before: 100097 no.01-2, 2 / F, building 1, 25 lantianchang South Road, Haidian District, Beijing Applicant before: Mosent (Beijing) Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right |