CN110110077A - Sorter based on machine learning knowledge - Google Patents
Sorter based on machine learning knowledge Download PDFInfo
- Publication number
- CN110110077A CN110110077A CN201711463482.4A CN201711463482A CN110110077A CN 110110077 A CN110110077 A CN 110110077A CN 201711463482 A CN201711463482 A CN 201711463482A CN 110110077 A CN110110077 A CN 110110077A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- crucial words
- words
- crucial
- classification
- 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
- 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
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G06F16/355—Class or cluster creation or modification
-
- 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)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of sorter based on machine learning knowledge, which includes: classifying rules module, and the classification behavior for acquiring user derives categorical reasoning rule；Module is obtained, for obtaining knowledge to be sorted；Extraction module, for extracting the crucial words in knowledge content according to participle method, wherein crucial words includes keyword and phrase；Calculation processing module, for calculating the frequency and position that crucial words occurs；Output module is detected, for detecting the crucial words for meeting predeterminated frequency and predeterminated position, exports crucial words as classification results.The crucial words in knowledge content is extracted using participle method, nearest-neighbors set is established according to the classification behavior of user, comprehensive analysis is carried out in conjunction with the weighting of crucial words, transformation, mixing, feature, first rank, obtain the crucial words of optimum combination, both the precision of the labeling of knowledge had been improved, retrieval rate is improved, again convenient for information recommendation and filtering information.
Description
Technical field
The present invention relates to field of artificial intelligence, more particularly to a kind of sorter based on machine learning knowledge.
Background technique
The technology that knowledge is sorted out by preassigned classification can be traced back into the sixties in last century.But, nearest
In 10 years, the bring mass data due to text knowledge's digitlization causes us to have to classify these knowledge.By
This, the automatic classification of knowledge has obtained extensive concern and quickly development.
Currently, there are mainly two types of in order to solve knowledge classification method: it is a kind of, it is the method for based on knowledge engineering, leads to
Professional is crossed, can be determined that for a large amount of inference rule of each class declaration if knowledge is able to satisfy these inference rules
Belong to the category；Another kind is the knowledge classification in knowledge based library, i.e., establishes keyword and classification number according to knowledge content first
Corresponding relationship, form descriptor, the knowledge base that classification number, 3 tuple of degree of membership are constituted, then provided according to knowledge to be sorted
Descriptor, add up descriptor where classification degree of membership, degree of membership total value it is highest be the knowledge where classification.
Although above-mentioned existing way can solve the problems, such as knowledge classification to a certain extent, both methods all exists
Obvious shortcoming: (1) rule that the quality classified depends on professional to specify；(2) do not have replicability, different fields needs
Construct different categorizing systems；(3) in the descriptor that knowledge to be sorted provides, only fraction has positive meaning to classification
Justice, it is necessary to the keyword duplicate removal to be sorted provided, weighting.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of based on machine learning knowledge
Sorter when machine classifies to learning knowledge in the prior art for solution, needs artificially participation, classification effectiveness and accuracy rate
Not high problem.
In order to achieve the above objects and other related objects, the application's in a first aspect, the present invention provide it is a kind of based on machine
The sorter of learning knowledge, comprising: one or more processors；Memory；And one or more programs, wherein described one
A or multiple programs are stored in the memory and are configured as being executed instruction by one or more of processors, described
The instruction that one or more processors execute includes following procedure module:
Classifying rules module, the classification behavior for acquiring user derive categorical reasoning rule；
Module is obtained, for obtaining knowledge to be sorted；
Extraction module, for extracting the crucial words in the knowledge content according to participle method, wherein the key words
Include keyword and phrase；
Calculation processing module, for calculating the frequency and position that the crucial words occurs；
It detects output module and exports the keyword for detecting the crucial words for meeting predeterminated frequency and predeterminated position
Word is as classification results.
As described above, the sorter of the invention based on machine learning knowledge, has the advantages that
Crucial words in knowledge content is extracted using participle method, user's arranged row is searched in Knowledge Management Platform
For；Nearest-neighbors set is established according to the classification behavior of the user, in conjunction with the weighting of crucial words, transformation, mixing, feature, member
Rank carries out comprehensive analysis, obtains the crucial words of optimum combination, first improves the precision of the labeling of knowledge, moreover
During knowledge retrieval, retrieval rate is improved, convenient for information recommendation and filtering information.
Detailed description of the invention
Fig. 1 is shown as a kind of sorter structural block diagram based on machine learning knowledge provided by the invention.
Specific embodiment
Presently filed embodiment is illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book understands other advantages and effect of the application easily.
In described below, with reference to attached drawing, attached drawing describes several embodiments of the application.It should be appreciated that also can be used
Other embodiments, and can be carried out without departing substantially from spirit and scope of the present disclosure mechanical composition, structure, electrically with
And the operational detailed description changed below should not be considered limiting, and the range of embodiments herein
Only the limited of claims of the patent by announcing term used herein is merely to describe specific embodiment, and be not
It is intended to limit the application.The term of space correlation, for example, "upper", "lower", "left", "right", " following ", " lower section ", " lower part ",
" top ", " top " etc. can be used in the text in order to an elements or features and another element or spy shown in explanatory diagram
The relationship of sign.
Although term first, second etc. are used to describe various elements herein in some instances, these elements
It should not be limited by these terms.These terms are only used to distinguish an element with another element.For example, first is pre-
If threshold value can be referred to as the second preset threshold, and similarly, the second preset threshold can be referred to as the first preset threshold, and
The range of various described embodiments is not departed from.First preset threshold and preset threshold are to describe a threshold value, still
Unless context otherwise explicitly points out, otherwise they are not the same preset thresholds.Similar situation further includes first
Volume and the second volume.
Furthermore as used in herein, singular " one ", "one" and "the" are intended to also include plural number shape
Formula, unless having opposite instruction in context it will be further understood that term "comprising", " comprising " show that there are the spies
Sign, step, operation, element, component, project, type, and/or group, but it is not excluded for one or more other features, step, behaviour
Work, element, component, project, the presence of type, and/or group, appearance or addition term "or" used herein and "and/or" quilt
Be construed to inclusive, or mean any one or any combination therefore, " A, B or C " or " A, B and/or C " mean " with
Descend any one: A；B；C；A and B；A and C；B and C；A, B and C " is only when element, function, step or the combination of operation are in certain modes
Under it is inherently mutually exclusive when, just will appear the exception of this definition.
The application provides a kind of screen rotation control system, device and setting, suitable for electronic equipment, in actual reality
Apply in mode, the electronic equipment be, for example, include but is not limited to laptop, tablet computer, mobile phone, smart phone,
Media player, personal digital assistant (PDA), navigator, smart television, smartwatch, digital camera etc., further include wherein
Two or multinomial combinations.It should be appreciated that the application electronic equipment described in embodiment is an application example, it should
The component of equipment can have more or fewer components than diagram, or with different component Configurations.Draw each of diagram
Kind of component can realize with the combination of hardware, software or software and hardware, including one or more signal processings and/or dedicated integrated
Circuit.In a specific embodiment of the present application, it will be illustrated so that the electronic equipment is smart phone as an example.
The electronic equipment include memory, Memory Controller, one or more processing unit (CPU), Peripheral Interface,
RF circuit, voicefrequency circuit, loudspeaker, microphone, input/output (I/O) subsystem, touch screen, other outputs or control equipment,
And outside port.These components are communicated by one or more communication bus or signal wire.The electronic equipment also wraps
Include the power-supply system for powering for various assemblies.The power-supply system may include power-supply management system, one or more power supplys
(such as battery, alternating current (AC)), charging system, power failure detection circuit, power adapter or inverter, power supply status refer to
Show device (such as light emitting diode (LED)), and in portable device electric energy generate, manage and be distributed it is associated other
Any component.
The electronic equipment supports various application programs, such as one or more of the following terms: drawing application program,
Application program, word-processing application, website creation application program, disk editor application program, spreadsheet application journey is presented
Sequence, game application, telephony application, videoconference application, email application, instant message application journey
Sequence, body-building support application program, photo management application program, digital camera applications program, digital video camcorder application program,
Web page browsing application program, digital music player application and/or video frequency player application program.
Referring to Fig. 1, being a kind of sorter flow chart based on machine learning knowledge provided by the invention, it is described in detail such as
Under:
The device includes: one or more processors；Memory；And one or more programs, wherein it is one or
Multiple programs are stored in the memory and are configured as being executed instruction by one or more of processors, one
Or the instruction that multiple processors execute includes following procedure module:
Classifying rules module 1, the classification behavior for acquiring user derive categorical reasoning rule；
Module 2 is obtained, for obtaining knowledge to be sorted；
Wherein, the main body where the knowledge can be the forms such as image, picture, text, webpage.
Extraction module 3, for extracting the crucial words in the knowledge content according to participle method, wherein the keyword
Word includes keyword and phrase；
Extraction unit 31 is segmented, for extracting the crucial words in knowledge content using participle method, in Knowledge Management Platform
Middle search user classification behavior；
Crucial words extraction unit 32, for establishing nearest-neighbors set according to the classification behavior of the user, in conjunction with pass
The weighting of key words, transformation, mixing, feature, first rank carry out comprehensive analysis, obtain the crucial words of optimum combination.
Calculation processing module 4, for calculating the frequency and position that the crucial words occurs；
Specifically, processing unit 41 is filtered out, for filtering out forbidden character, modal particle and stop words in the crucial words；
Calculation processing unit 42 positions crucial in the main body for carrying out participle and part-of-speech tagging for main body corresponding to knowledge
The position of words counts the frequency that the crucial words occurs.
It detects output module 5 and exports the keyword for detecting the crucial words for meeting predeterminated frequency and predeterminated position
Word is as classification results.
In the present embodiment, the crucial words in knowledge content is extracted using participle method, is searched in Knowledge Management Platform
User classification behavior；Nearest-neighbors set is established according to the classification behavior of the user, weight, convert in conjunction with crucial words,
Mixing, feature, first rank carry out comprehensive analysis, obtain the crucial words of optimum combination, first improve the labeling of knowledge
Precision improve retrieval rate moreover during knowledge retrieval, convenient for information recommendation and filtering information.
Referring to Fig. 1, being classifying rules module in a kind of sorter based on machine learning knowledge provided by the invention
Structural block diagram, details are as follows:
Data acquisition unit 11, for acquiring a large number of users knowledge classification behavioral data in Knowledge Management Platform；
Specifically, which includes: article, topic, discussion, expert, special topic, examination question, examination paper, user's practice mistake, uses
The mass datas such as family browsing behavior are to derive word frequency, word frequency, word, word and the relationship of behavior with above-mentioned data.
Words extraction unit 12, for extracting the crucial words of knowledge in the data；The crucial words is calculated to occur
Frequency determines itself and classification behavior relation；
Classifying rules unit 13, for according to the crucial words of knowledge all kinds of in the data and the power of classification behavior relation
Weight constructs weighted factor, transformation, mixing rule, obtains knowledge classification inference rule.
In the present embodiment, specifically, pass through word frequency, word frequency, word, word and the relationship of behavior, in conjunction with article, knowledge architecture
Derive word, word, relationship weight, building weighted factor, transformation, mixing rule, the final rule for exporting knowledge classification.
For example, the natural language processing of Chinese includes following several big modules.Wherein, each module is of crucial importance, point
Coming also all is a research direction.Each functions of modules is as follows, and what Chinese word segmentation was mainly completed is the function of participle, can
Spending thousand bones love white chessman to draw ＂ cutting ＂ is that ＂ spends thousand bone ＂, ＂ to like that ＂, ＂ white chessman draw these three words of ＂.
The part of speech of these three words is marked in part-of-speech tagging respectively, then dependency analysis, analyzes and comes word and word
Between relationship what is, it is a subject-predicate relationship that wherein ＂, which is spent between thousand bone ＂ and ＂ love ＂, and it is one dynamic that ＂ love ＂ and ＂ white chessman, which draws ＂,
Guest's structure: last semantic role analysis analyzes major semantic role of sentence.
Chinese Automatic Word Segmentation function is step most basic and crucial in Chinese language processing.Since initial data includes bulletin,
The different forms such as statistical table, consistent semi-structured and structural data, needs having in initial data in order to obtain
Effect data extract.In order to achieve the above objectives, initial data need to be segmented, to will wherein required data cut
It branches away.
Chinese word segmentation is to mark off according to meaning when using by the vocabulary in sentence.Due to not having between Chinese word and word
There is space, therefore direct like that without normal direction English for the extraction of Chinese character file information.What therefore data cutting faced first asks
Topic is the automatic word segmentation of Chinese.Many has had substantial progress about the research of Chinese word segmenting.
There are mainly two types of for existing segmentation methods:
The first is the mechanical matching algorithm based on dictionary (Dictionary-Based), which is to be easy to real
Existing, effect is fine when of less demanding to accurate rate.But disadvantage is completeness deficiency, can not solve unregistered word largely occur
(OOV includes the case where naming entity and neologisms).Wherein, name entity includes: name, place name, organization name, time word, number
Word etc..
It can be summarized as the participle device of statistics for second, it is a large amount of that the advantages of device is that it can be provided from us
Induction and conclusion is carried out in case.But for the device, the selection shadow of the corpus of the scale and different field of training corpus
Sound is very big.
Based on the above situation, since Knowledge Management Platform has certain code requirement, data have certain profession
Property and consistency, therefore the segmentation methods that use of device are to be combined the device of the device of statistics and dictionary, to original number
Valid data in extract, the semi-structured and structural data after being arranged.
Memory space and raising treatment effeciency are saved in order to improve, needs to filter out certain before underway text automatic word segmentation
A little words or vocabulary, these become as stop words, if encounter these stop words just will stop at once, by it in text-processing
It throws away, to reduce the index amount of data, increases recall precision.
It after the arrangement of complete paired data, in order to realize subsequent need, need to classify to different data, i.e., be arranged to data
It labels, to complete the classification of knowledge data.
Referring to Fig. 1, being to detect output module in a kind of sorter based on machine learning knowledge provided by the invention
Structural block diagram, details are as follows:
Detection unit 51, for detect frequency number that the crucial words occurs in the main body position it is whether full
Foot is in predeterminated frequency number and preset body position range；
First output unit 52, for when the crucial words frequency of occurrences number is in predeterminated frequency numbers range and institute
When the position of main body is met within the scope of preset body position where stating crucial words, then tied using the crucial words as classification
Fruit；
Second output unit 53, for working as the crucial words frequency of occurrences number not within the preset frequency range, or, working as
When the position of main body is not met within the scope of preset body position where the key words, then the crucial words can not be made
For classification results.
In the present embodiment, by detecting the frequency number and appearance position of crucial words, make to export crucial words
For classification results, machine is improved to knowledge classification standard, convenient for retrieval and study.
In certain embodiments, the processor is also operatively coupled to the port I/O and input structure, the end I/O
Mouth aloows electronic equipment 20 to interact with various other electronic equipments, which aloows user and electricity
Sub- equipment 20 interacts.Therefore, input structure may include button, keyboard, mouse, Trackpad etc..In addition, electronic console can
Including touching component, the touch component by test object touch the generation of its screen (for example, surface of electronic console) with/
Or position promotes the user to input.
The processor is operationally coupled with memory and/or non-volatile memory device.More specifically, processor can
The instruction stored in memory and/or non-volatile memory device is executed to execute operation in calculating equipment, is such as generated
Image data and/or image data is transferred to electronic console.In this way, processor may include one or more general micro processs
Device, one or more application specific processor (ASIC), one or more Field Programmable Logic Array (FPGA) or theirs is any
Combination.
The memory may include high-speed random access memory, and may also include nonvolatile memory, such as one
A or multiple disk storage equipments, flash memory device or other non-volatile solid-state memory devices.In certain embodiments, memory
It can also include the memory far from one or more processors, such as via RF circuit or outside port and communication network
The network attached storage of (not shown) access, wherein the communication network can be internet, one or more intranets, office
Domain net (LAN), wide area network (WLAN), storage area network (SAN) etc. or its is appropriately combined.Memory Controller controllable device
Such as CPU and Peripheral Interface etc access of the other assemblies to memory.
In conclusion the present invention extracts the crucial words in knowledge content using participle method, searched in Knowledge Management Platform
Seek user classification behavior；Nearest-neighbors set is established according to the classification behavior of the user, in conjunction with the weighting of crucial words, is become
It changes, mix, feature, first rank progress comprehensive analysis, obtaining the crucial words of optimum combination, first improve the label point of knowledge
The precision of class, moreover during knowledge retrieval, retrieval rate is improved, convenient for information recommendation and filtering information.Institute
With the present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (5)
1. a kind of sorter based on machine learning knowledge, which is characterized in that described device includes: one or more processing
Device；Memory；And one or more programs, wherein one or more of programs are stored in the memory and are matched
It is set to and is executed instruction by one or more of processors, the instruction that one or more of processors execute includes following procedure
Module:
Classifying rules module, the classification behavior for acquiring user derive categorical reasoning rule；
Module is obtained, for obtaining knowledge to be sorted；
Extraction module, for extracting the crucial words in the knowledge content according to participle method, wherein it is described key words include
Keyword and phrase；
Calculation processing module, for calculating the frequency and position that the crucial words occurs；
Output module is detected, for detecting the crucial words for meeting predeterminated frequency and predeterminated position, the crucial words is exported and makees
For classification results.
2. the sorter according to claim 1 based on machine learning knowledge, which is characterized in that institute's classifying rules module
Include:
Data acquisition unit, for acquiring a large number of users knowledge classification behavioral data in Knowledge Management Platform；
Words extraction unit, for extracting the crucial words of knowledge in the data；It is true to calculate the crucial words frequency of occurrences
Determine itself and classification behavior relation；
Classifying rules unit, for according to the crucial words of knowledge all kinds of in the data and the weight of classification behavior relation, structure
Weighted factor, transformation, mixing rule are built, knowledge classification inference rule is obtained.
3. the sorter according to claim 1 based on machine learning knowledge, which is characterized in that the extraction module packet
It includes:
Extraction unit is segmented, for extracting the crucial words in knowledge content using participle method, is searched in Knowledge Management Platform
User classification behavior；
Crucial words extraction unit, for establishing nearest-neighbors set according to the classification behavior of the user, in conjunction with crucial words
Weighting, transformation, mixing, feature, first rank carry out comprehensive analysis, obtain the crucial words of optimum combination.
4. the sorter according to claim 1 based on machine learning knowledge, which is characterized in that the calculation processing mould
Block includes:
Processing unit is filtered out, for filtering out forbidden character, modal particle and stop words in the crucial words；
Calculation processing unit is positioned in the main body and is closed for carrying out participle and part-of-speech tagging for main body corresponding to knowledge
The position of key words counts the frequency that the crucial words occurs.
5. the sorter according to claim 1 based on machine learning knowledge, which is characterized in that the detection exports mould
Block includes:
Detection unit, for detect frequency number that the crucial words occurs in the main body position whether meet pre-
If frequency number and preset body position range；
First output unit, for when the crucial words frequency of occurrences number is in predeterminated frequency numbers range and the key
When the position of main body is met within the scope of preset body position where words, then using the crucial words as classification results；
Second output unit, for working as the crucial words frequency of occurrences number not within the preset frequency range, or, working as the pass
It, then can not be using the crucial words as classification when the position of main body is not met within the scope of preset body position where key words
As a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711463482.4A CN110110077A (en) | 2017-12-28 | 2017-12-28 | Sorter based on machine learning knowledge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711463482.4A CN110110077A (en) | 2017-12-28 | 2017-12-28 | Sorter based on machine learning knowledge |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110110077A true CN110110077A (en) | 2019-08-09 |
Family
ID=67482985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711463482.4A Pending CN110110077A (en) | 2017-12-28 | 2017-12-28 | Sorter based on machine learning knowledge |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110077A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI765322B (en) * | 2020-08-21 | 2022-05-21 | 伊斯酷軟體科技股份有限公司 | Knowledge management device, method, and computer program product for a software project |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980211A (en) * | 2010-11-12 | 2011-02-23 | 百度在线网络技术（北京）有限公司 | Machine learning model and establishing method thereof |
| CN105335371A (en) * | 2014-06-11 | 2016-02-17 | 富士通株式会社 | Information processing method, information processing apparatus, and information recommendation method |
| CN105930503A (en) * | 2016-05-09 | 2016-09-07 | 清华大学 | Combination feature vector and deep learning based sentiment classification method and device |
| CN106897437A (en) * | 2017-02-28 | 2017-06-27 | 北明智通（北京）科技有限公司 | The many sorting techniques of high-order rule and its system of a kind of knowledge system |
| CN107169001A (en) * | 2017-03-31 | 2017-09-15 | 华东师范大学 | A kind of textual classification model optimization method based on mass-rent feedback and Active Learning |
-
2017
- 2017-12-28 CN CN201711463482.4A patent/CN110110077A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980211A (en) * | 2010-11-12 | 2011-02-23 | 百度在线网络技术（北京）有限公司 | Machine learning model and establishing method thereof |
| CN105335371A (en) * | 2014-06-11 | 2016-02-17 | 富士通株式会社 | Information processing method, information processing apparatus, and information recommendation method |
| CN105930503A (en) * | 2016-05-09 | 2016-09-07 | 清华大学 | Combination feature vector and deep learning based sentiment classification method and device |
| CN106897437A (en) * | 2017-02-28 | 2017-06-27 | 北明智通（北京）科技有限公司 | The many sorting techniques of high-order rule and its system of a kind of knowledge system |
| CN107169001A (en) * | 2017-03-31 | 2017-09-15 | 华东师范大学 | A kind of textual classification model optimization method based on mass-rent feedback and Active Learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI765322B (en) * | 2020-08-21 | 2022-05-21 | 伊斯酷軟體科技股份有限公司 | Knowledge management device, method, and computer program product for a software project |
| US11704625B2 (en) | 2020-08-21 | 2023-07-18 | Iscoollab Co., Ltd. | Knowledge management device, method, and computer program product for a software project |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182279B (en) | Object classification method, device and computer equipment based on text feature | |
| CN107609121B (en) | News text classification method based on LDA and word2vec algorithm | |
| US11645517B2 (en) | Information processing method and terminal, and computer storage medium | |
| Kanakaraj et al. | NLP based sentiment analysis on Twitter data using ensemble classifiers | |
| Li et al. | Twiner: named entity recognition in targeted twitter stream | |
| WO2021068339A1 (en) | Text classification method and device, and computer readable storage medium | |
| WO2020253503A1 (en) | Talent portrait generation method, apparatus and device, and storage medium | |
| Fang et al. | Word-of-mouth understanding: Entity-centric multimodal aspect-opinion mining in social media | |
| CN110134792B (en) | Text recognition method and device, electronic equipment and storage medium | |
| Liu et al. | A new method for knowledge and information management domain ontology graph model | |
| CN110619051B (en) | Question sentence classification method, device, electronic equipment and storage medium | |
| Psomakelis et al. | Comparing methods for twitter sentiment analysis | |
| CN113095080B (en) | Theme-based semantic recognition method and device, electronic equipment and storage medium | |
| CN111309916B (en) | Digest extracting method and apparatus, storage medium, and electronic apparatus | |
| CN113722483B (en) | Topic classification method, device, equipment and storage medium | |
| CN112052356A (en) | Multimedia classification method, apparatus and computer-readable storage medium | |
| CN112148881A (en) | Method and apparatus for outputting information | |
| Rafeeque et al. | A survey on short text analysis in web | |
| Tabak et al. | Comparison of emotion lexicons | |
| Hassan et al. | Automatic document topic identification using wikipedia hierarchical ontology | |
| CN114676698A (en) | Equipment fault key information extraction method and system based on knowledge graph | |
| CN110110077A (en) | Sorter based on machine learning knowledge | |
| CN110019556A (en) | A kind of topic news acquisition methods, device and its equipment | |
| CN117057349A (en) | News text keyword extraction method, device, computer equipment and storage medium | |
| CN114970553B (en) | Information analysis method and device based on large-scale unmarked corpus and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |
|
| RJ01 | Rejection of invention patent application after publication |