CN106802951B - A kind of topic abstracting method and system for Intelligent dialogue - Google Patents
A kind of topic abstracting method and system for Intelligent dialogue Download PDFInfo
- Publication number
- CN106802951B CN106802951B CN201710030377.5A CN201710030377A CN106802951B CN 106802951 B CN106802951 B CN 106802951B CN 201710030377 A CN201710030377 A CN 201710030377A CN 106802951 B CN106802951 B CN 106802951B
- Authority
- CN
- China
- Prior art keywords
- label
- dialogue
- topic
- corpus
- contribution degree
- 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
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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
Abstract
The invention discloses a kind of topic abstracting methods and system for Intelligent dialogue, and by extracting the session log of visitor and customer service, dialogue label is arranged to the session log；Each topic in the session log is counted to the contribution degree of the dialogue label；Each topic under dialogue label each in corpus is ranked up according to the contribution degree, and extracts the biggish topic of contribution degree, regard the problems in the topic as recommendation problem, and using answer corresponding in the topic as recommendation answer；The problem of being proposed according to visitor automatically extracts current problem label, and the current problem label is matched with the dialogue label in corpus, provides recommendation answer corresponding to the recommendation problem under the dialogue label in the biggish topic of contribution degree to visitor；To realize that dialogue topic is extracted in automation, so that intelligent customer service is more acurrate, complete the problem of answering visitor, visitor's experience is more preferable.
Description
Technical field
It is especially a kind of to be somebody's turn to do for the topic abstracting method of Intelligent dialogue and its application the present invention relates to field of communication technology
The system of method.
Background technique
As internet and the popularization and application of e-commerce, intelligent customer service are also more and more.Intelligent customer service is extensive
The Industry-oriented application to grow up on the basis of knowledge processing, it is related to extensive Knowledge Processing Technology, natural language reason
Solution technology, Knowledge Management Technology, automatically request-answering system, inference technology etc. have industry universal, and only enterprise does not provide
Fine granularity Knowledge Management Technology, the communication also between enterprise and mass users establish a kind of fast having based on natural language
The technological means of effect；Statistical analysis information needed for fine-grained management can also being provided for enterprise simultaneously, and can be saved for enterprise
A large amount of human resources and cost.
In the realization of the entire technology of intelligent customer service, relate generally to dialogue corpus pretreatment, model construction, it is semantic parse,
The technologies such as intensified learning, because of the extensive knowledge and profound scholarship of Chinese, often there are many form of presentation for the same dialogue topic, such as there are same
Adopted word, near synonym, expressed intact, simplified expression, ambiguity etc., this allows for each identical topic in dialogue corpus, past
Toward there are a variety of expression；That is, a dialogue topic is not only made of a problem and an answer, but may be by multiple problems
It is formed with multiple answers.Wherein ideal question and answer sentence how is positioned and accurately extracted, the correct of Intelligent dialogue is related to
Property and integrality and the Experience Degree of user.
Summary of the invention
The present invention passes through to solve the above problems, provide a kind of topic abstracting method and system for Intelligent dialogue
Session log is subjected to tag processes and quantum chemical method, to realize that dialogue topic is extracted in automation, so that intelligent customer service is answered
More acurrate when the problem of visitor, visitor's experience is more preferable.
To achieve the above object, the technical solution adopted by the present invention are as follows:
A kind of topic abstracting method for Intelligent dialogue comprising following steps:
10) by extracting the session log of visitor and customer service, dialogue label is arranged to the session log；
20) each topic in the session log is counted to the contribution degree of the dialogue label；
30) each topic under dialogue label each in corpus is ranked up according to the contribution degree, and extracts tribute
The biggish topic of degree of offering regard the problems in the topic as recommendation problem, and answers answer corresponding in the topic as recommendation
Case；
40) the problem of being proposed according to visitor automatically extracts current problem label, and by current the problem label and language
Dialogue label in material library is matched, and the recommendation problem institute under the dialogue label in the biggish topic of contribution degree is provided to visitor
Corresponding recommendation answer.
Preferably, before the step 10), building label model is also carried out in advance, according to the corpus in corpus
Conversation subject classify to all corpus, dialogue label is configured to different types of corpus, obtains label model.
Preferably, it is configured dialogue label in the step 10), is according to the dialogue label in the label model
The session log is carried out to select and set corresponding dialogue label.
Preferably, each topic is ranked up in the step 30), is referred to by newly-increased session log and to corpus
All topics in dialog history record in library, carry out the sequence of contribution degree, also, every under corresponding dialogue label
Then automatic rearrangement after secondary newly-increased session log.
Corresponding, the present invention also provides a kind of topic extraction systems for Intelligent dialogue comprising:
Talk with label setup module, by extracting the session log of visitor and customer service, to session log setting pair
Talk about label；
Contribution degree computing module, for counting contribution of each topic in the session log to the dialogue label
Degree；
Topic abstraction module arranges each topic under dialogue label each in corpus according to the contribution degree
Sequence, and extract the biggish topic of contribution degree regard the problems in the topic as recommendation problem, and by answer corresponding in the topic
As recommendation answer；
Intelligent dialogue module, the problem of being proposed according to visitor, automatically extract current problem label, and this is current
Problem label is matched with the dialogue label in corpus, is provided under the dialogue label in the biggish topic of contribution degree to visitor
Recommendation problem corresponding to recommendation answer.
Preferably, further include model construction module, according to the conversation subject of the corpus in corpus to all corpus into
Row classification, is configured dialogue label to different types of corpus, obtains label model.
Preferably, the dialogue label setup module is to be remembered according to the dialogue label in the label model to the dialogue
Record carries out select andding set corresponding dialogue label.
Preferably, each topic is ranked up in the topic abstraction module, refers to session log that will be newly-increased and right
All topics in dialog history record in corpus carry out the sequence of contribution degree under corresponding dialogue label, and
And then automatic rearrangement after newly-increased session log every time.
The beneficial effects of the present invention are:
(1) a kind of topic abstracting method and system for Intelligent dialogue of the invention, by each session log
Setting dialogue label, by calculating each topic under the dialogue label to the contribution degree of the dialogue label, and according to tribute
Degree of offering size is ranked up the topic, by the way that session log is carried out tag processes and quantum chemical method, and by contribution degree compared with
The problems in big topic and answer as recommendation problem and recommend answer, thus realize that dialogue topic is extracted in automation, so that
The problem of intelligent customer service answer visitor, is more acurrate, complete, and visitor's experience is more preferable；
(2) present invention remembers by building label model, and to newly-increased session log and to the dialog history in corpus
Record is configured dialogue label, and all topics is carried out to the sequence of contribution degree under corresponding dialogue label, also, every
Then automatic rearrangement, enables label model circulation continuous to update after secondary newly-increased session log, and enables corpus
It persistently automatically updates and perfect, visitor's experience is become better and better.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the general flow chart of topic abstracting method in Intelligent dialogue of the invention；
Fig. 2 is the general flow chart of Intelligent dialogue system of the invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Closing accompanying drawings and embodiments, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
As depicted in figs. 1 and 2, a kind of topic abstracting method for Intelligent dialogue of the invention comprising following steps:
10) by extracting the session log of visitor and customer service, dialogue label is arranged to the session log；
20) each topic in the session log is counted to the contribution degree of the dialogue label；
30) each topic under dialogue label each in corpus is ranked up according to the contribution degree, and extracts tribute
The biggish topic of degree of offering regard the problems in the topic as recommendation problem, and answers answer corresponding in the topic as recommendation
Case；
40) the problem of being proposed according to visitor automatically extracts current problem label, and by current the problem label and language
Dialogue label in material library is matched, and the recommendation problem institute under the dialogue label in the biggish topic of contribution degree is provided to visitor
Corresponding recommendation answer.
Traditional intelligent customer service system mainly carries out autonomous learning in the following ways:
1. Similar Problems are recommended the problem having in library；
2. merging the very high problem of similarity automatically.
But such autonomous learning still has very big defect for intelligent customer service system: on the one hand, needing artificial
More new problems or Similar Problems are imported, corpus is unable to rapid growth and updates；On the other hand, the outstanding customer service in part is excellent
Show words art, cannot be found and learn in time.
Circulating rolling reinforcement is carried out by building label model in the present embodiment and to model, corpus is can be realized and continues
It automatically updates and perfect, visitor's experience is become better and better.It is specific:
Before the step 10), building label model is also carried out in advance, according to the dialogue master of the corpus in corpus
Topic classifies to all corpus, is configured dialogue label to different types of corpus, obtains label model.
It is configured dialogue label in the step 10), is according to the dialogue label in the label model to described
Session log carries out select andding set corresponding dialogue label.
Each topic is ranked up in the step 30), is referred to by newly-increased session log and in corpus
All topics in dialog history record carry out the sequence of contribution degree under corresponding dialogue label, also, newly-increased every time
Then automatic rearrangement after session log.
In addition, the present invention also provides a kind of topic extraction systems corresponding with aforementioned topic abstracting method comprising:
Model construction module classifies to all corpus according to the conversation subject of the corpus in corpus, to difference
The corpus of type is configured dialogue label, obtains label model；
Talk with label setup module, by extracting the session log of visitor and customer service, to session log setting pair
Talk about label；
Contribution degree computing module, for counting contribution of each topic in the session log to the dialogue label
Degree；
Topic abstraction module arranges each topic under dialogue label each in corpus according to the contribution degree
Sequence, and extract the biggish topic of contribution degree regard the problems in the topic as recommendation problem, and by answer corresponding in the topic
As recommendation answer；
Intelligent dialogue module, the problem of being proposed according to visitor, automatically extract current problem label, and this is current
Problem label is matched with the dialogue label in corpus, is provided under the dialogue label in the biggish topic of contribution degree to visitor
Recommendation problem corresponding to recommendation answer.
In the present embodiment, the dialogue label setup module is according to the dialogue label in the label model to described right
Words record carries out select andding set corresponding dialogue label.Each topic is ranked up in the topic abstraction module, is referred to
By newly-increased session log and to all topics in the dialog history record in corpus, under corresponding dialogue label
The sequence of contribution degree is carried out, also, then automatic rearrangement after newly-increased session log every time.
Specifically, topic extraction process of the invention is as follows:
1. constructing model
Corpus is combed first, according to conversation subject and keyword, is configured dialogue mark for all corpus
Label, the dialogue label classifies generally according to conversation subject, for example including quality, price, logistics, after-sale service etc., from
And form label model.
2. labelling
When in use, completely talk with for such as one group, the dialogue interaction for sharing 10 visitors and intelligent customer service records.First with
Label model is that corresponding dialogue label is sticked in this dialogue, is formed by label when the dialogue label is from building model
(one group is completely talked with, and may include multiple labels).
3. calculating contribution degree
It calculates in the dialogue of this group, the contribution degree for the dialogue label that every a word (each topic) talks with this group, and uses number
Value is indicated.Because there may be multiple dialogue labels for one group of dialogue, meanwhile, it in short may be to two or more dialogues
Label generate contribution degree or more words can the same dialogue label generate contribution degree, so being that this group talks with contribution has been calculated
After degree, under each corresponding label, the more sentence pairs for producing contribution degree to it accordingly will be generated and talked about, contribution degree is pressed into these dialogues
Value is ranked up.
4. extracting topic automatically
When intelligent customer service answer visitor question when, extract first problem label corresponding to its visitor's problem (for example, according to
Keyword in problem), and matched with the dialogue label in constructed model.After completing tag match, by the dialogue
The biggish topic of contribution degree or problem (recommend problem) under label by numerical ordering extract, and by the topic or problem institute
Corresponding answer (recommending answer) is for the problem of answering visitor, so that visitor be made to obtain, more accurate and perfect problem is answered
It is multiple.
5. circulating rolling reinforces model
When thering is new corpus and label to generate, model continuous updating, and according to the calculating of contribution degree, continuous updating is each
The contribution degree numerical value of corresponding problem under label and reply the problem of sorting, persistently improve Intelligent dialogue.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For system class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.Also, herein, the terms "include", "comprise" or its any other variant
It is intended to non-exclusive inclusion, so that including that the process, method, article or equipment of a series of elements not only includes
Those elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of person's equipment.In the absence of more restrictions, the element limited by sentence "including a ...", not
There is also other identical elements in the process, method, article or apparatus that includes the element for exclusion.In addition, this field
Those of ordinary skill is understood that realize that all or part of the steps of above-described embodiment may be implemented by hardware, can also lead to
Program is crossed to instruct relevant hardware to complete, the program can store in a kind of computer readable storage medium, above-mentioned
The storage medium mentioned can be read-only memory, disk or CD etc..
The preferred embodiment of the present invention has shown and described in above description, it should be understood that the present invention is not limited to this paper institute
The form of disclosure, should not be regarded as an exclusion of other examples, and can be used for other combinations, modifications, and environments, and energy
Enough in this paper invented the scope of the idea, modifications can be made through the above teachings or related fields of technology or knowledge.And people from this field
The modifications and changes that member is carried out do not depart from the spirit and scope of the present invention, then all should be in the protection of appended claims of the present invention
In range.
Claims (4)
1. a kind of topic abstracting method for Intelligent dialogue, which comprises the following steps:
10) by extracting the session log of visitor and customer service, dialogue label is arranged to the session log；
20) each topic in the session log is counted to the contribution degree of the dialogue label；
30) each topic under dialogue label each in corpus is ranked up according to the contribution degree, and extracts contribution degree
Biggish topic regard the problems in the topic as recommendation problem, and using answer corresponding in the topic as recommendation answer；
40) the problem of being proposed according to visitor automatically extracts current problem label, and by current the problem label and corpus
In dialogue label matched, provided corresponding to the recommendation problem under the dialogue label in the biggish topic of contribution degree to visitor
Recommendation answer；
Wherein, before the step 10), building label model is also carried out in advance, according to the dialogue of the corpus in corpus
Theme classifies to all corpus, is configured dialogue label to different types of corpus, obtains label model；The step
It is rapid 10) in be configured dialogue label, be to be selected according to the dialogue label in the label model the session log
With the corresponding dialogue label of setting.
2. a kind of topic abstracting method for Intelligent dialogue according to claim 1, it is characterised in that: the step
30) each topic is ranked up in, is referred to by newly-increased session log and to the institute in the dialog history record in corpus
There is topic, the sequence of contribution degree, also, then automatic weight after each newly-increased session log are carried out under corresponding dialogue label
New sort.
3. a kind of topic extraction system for Intelligent dialogue characterized by comprising
Talk with label setup module, by extracting the session log of visitor and customer service, dialogue mark is arranged to the session log
Label；
Contribution degree computing module, for counting each topic in the session log to the contribution degree of the dialogue label；
Topic abstraction module is ranked up each topic under dialogue label each in corpus according to the contribution degree,
And the biggish topic of contribution degree is extracted, it regard the problems in the topic as recommendation problem, and answer corresponding in the topic is made
To recommend answer；
Intelligent dialogue module, the problem of being proposed according to visitor, automatically extract current problem label, and by the current problem
Label is matched with the dialogue label in corpus, provides pushing away in the biggish topic of contribution degree under the dialogue label to visitor
Recommend recommendation answer corresponding to problem；
Wherein, further include model construction module, classified according to the conversation subject of the corpus in corpus to all corpus,
Dialogue label is configured to different types of corpus, obtains label model；The dialogue label setup module is according to
Dialogue label in label model carries out the session log to select and set corresponding dialogue label.
4. a kind of topic extraction system for Intelligent dialogue according to claim 3, it is characterised in that: the topic is taken out
Each topic is ranked up in modulus block, is referred to by newly-increased session log and in the dialog history record in corpus
All topics carry out the sequence of contribution degree under corresponding dialogue label, also, then automatic after newly-increased session log every time
Rearrangement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030377.5A CN106802951B (en) | 2017-01-17 | 2017-01-17 | A kind of topic abstracting method and system for Intelligent dialogue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030377.5A CN106802951B (en) | 2017-01-17 | 2017-01-17 | A kind of topic abstracting method and system for Intelligent dialogue |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106802951A CN106802951A (en) | 2017-06-06 |
| CN106802951B true CN106802951B (en) | 2019-06-11 |
Family
ID=58985428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710030377.5A Active CN106802951B (en) | 2017-01-17 | 2017-01-17 | A kind of topic abstracting method and system for Intelligent dialogue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106802951B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832433B (en) * | 2017-11-15 | 2020-08-11 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on conversation interaction |
| CN109033356A (en) * | 2018-07-25 | 2018-12-18 | 深圳追科技有限公司 | The method and customer service system to label for customer service system log |
| CN110049134B (en) * | 2019-04-22 | 2020-04-14 | 苏州紫焰网络科技有限公司 | Customer service chat method, customer service chat device, customer service end, server and storage medium |
| CN110502639B (en) * | 2019-07-09 | 2022-09-06 | 平安银行股份有限公司 | Information recommendation method and device based on problem contribution degree and computer equipment |
| CN111177350A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Method, device and system for forming dialect of intelligent voice robot |
| CN111553144A (en) * | 2020-04-28 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Topic mining method and device based on artificial intelligence and electronic equipment |
| CN113035191B (en) * | 2021-02-26 | 2023-11-10 | 光禹莱特数字科技(上海)有限公司 | Voice interaction method, device, storage medium and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
| CN101097573A (en) * | 2006-06-28 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| CN101599071A (en) * | 2009-07-10 | 2009-12-09 | 华中科技大学 | The extraction method of conversation text topic |
| CN103049433A (en) * | 2012-12-11 | 2013-04-17 | 微梦创科网络科技（中国）有限公司 | Automatic question answering method, automatic question answering system and method for constructing question answering case base |
| CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Automatic question-answering system and method |
| CN105975511A (en) * | 2016-04-27 | 2016-09-28 | 乐视控股（北京）有限公司 | Intelligent dialogue method and apparatus |
-
2017
- 2017-01-17 CN CN201710030377.5A patent/CN106802951B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097573A (en) * | 2006-06-28 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
| CN101599071A (en) * | 2009-07-10 | 2009-12-09 | 华中科技大学 | The extraction method of conversation text topic |
| CN103049433A (en) * | 2012-12-11 | 2013-04-17 | 微梦创科网络科技（中国）有限公司 | Automatic question answering method, automatic question answering system and method for constructing question answering case base |
| CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Automatic question-answering system and method |
| CN105975511A (en) * | 2016-04-27 | 2016-09-28 | 乐视控股（北京）有限公司 | Intelligent dialogue method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106802951A (en) | 2017-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106802951B (en) | A kind of topic abstracting method and system for Intelligent dialogue | |
| CN106484801B (en) | A kind of dialogue method and its knowledge base management system of intelligent customer service robot | |
| Akhtar et al. | The potential of chatbots: analysis of chatbot conversations | |
| Girgis et al. | Deep learning algorithms for detecting fake news in online text | |
| CN104951433B (en) | The method and system of intention assessment is carried out based on context | |
| CN106570708B (en) | Management method and system of intelligent customer service knowledge base | |
| Misopoulos et al. | Uncovering customer service experiences with Twitter: the case of airline industry | |
| CN106844344A (en) | For the contribution degree computational methods and subject extraction method and system talked with | |
| Suttles et al. | Distant supervision for emotion classification with discrete binary values | |
| Kumar et al. | Analyzing Twitter sentiments through big data | |
| CN110168535B (en) | Information processing method and terminal, computer storage medium | |
| CN106777257B (en) | Intelligent dialogue model construction system and method based on dialect | |
| US10977448B2 (en) | Determining personality profiles based on online social speech | |
| CN111460221B (en) | Comment information processing method and device and electronic equipment | |
| CN108021660B (en) | Topic self-adaptive microblog emotion analysis method based on transfer learning | |
| CN109871439A (en) | A kind of Ask-Answer Community problem method for routing based on deep learning | |
| Song et al. | Opinion mining in e-learning system | |
| CN109308332B (en) | Target user acquisition method and device and server | |
| CN110807086A (en) | Text data labeling method and device, storage medium and electronic equipment | |
| CN110287305B (en) | Intelligent question-answering management system based on natural language processing | |
| Wang | Using machine learning and natural language processing to analyze library chat reference transcripts | |
| CN106407271B (en) | Intelligent customer service system and updating method of intelligent customer service knowledge base thereof | |
| Bhat et al. | A new framework for social media content mining and knowledge discovery | |
| CN114048294B (en) | Similar population extension model training method, similar population extension method and device | |
| Zhao et al. | Leveraging Lexical Link Analysis (LLA) to discover new knowledge |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A topic extraction method and system for intelligent conversation Effective date of registration: 20221202 Granted publication date: 20190611 Pledgee: Industrial Bank Limited by Share Ltd. Xiamen branch Pledgor: XIAMEN KUAISHANGTONG TECH. Corp.,Ltd. Registration number: Y2022980024751 |