CN113010658A - Intelligent question-answering knowledge base construction method, system, terminal and storage medium - Google Patents
Intelligent question-answering knowledge base construction method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN113010658A CN113010658A CN202110375860.3A CN202110375860A CN113010658A CN 113010658 A CN113010658 A CN 113010658A CN 202110375860 A CN202110375860 A CN 202110375860A CN 113010658 A CN113010658 A CN 113010658A
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- knowledge base
- effective
- intelligent
- 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
Images
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
- G06F16/332—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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a method, a system, a terminal and a storage medium for constructing an intelligent question-answering knowledge base. The method comprises the following steps: obtaining chat logs of all visitors and manual customer service in a question-answering system, and generating effective question-answering pairs according to the chat logs; carrying out vector clustering operation on the effective question-answer pairs by using a clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category; and counting the number of effective question-answer pairs in each category, screening the categories of which the number of the effective question-answer pairs exceeds a set threshold value, and adding the question-answer representatives of the screened categories into an intelligent question-answer knowledge base. The method and the device can find new knowledge points with high occurrence frequency in time and update the intelligent question and answer knowledge base, so that the question and answer range of the intelligent question and answer system is automatically expanded, the reply accuracy of the intelligent question and answer system is improved, and the requirement of a user on the field knowledge is reduced.
Description
Technical Field
The application belongs to the technical field of intelligent question answering, and particularly relates to a method, a system, a terminal and a storage medium for constructing an intelligent question answering knowledge base.
Background
The intelligent question-answering system orderly and scientifically arranges the accumulated unordered corpus information and establishes knowledge-based classification models which can guide newly-added corpus consultation and service information, so that the human resources are saved, the automation of information processing is improved, and the operation cost of enterprise websites is reduced.
At present, a manual method is generally used for classifying and summarizing knowledge points, and the intelligent question and answer knowledge base is constructed by manual addition or batch import of customer service personnel. The method has high cognitive requirements for users and needs to fully understand domain knowledge; meanwhile, due to the knowledge limitation of people, the classification error rate is high, and the question and answer effect of the intelligent question and answer knowledge base is poor. Enterprises can bring more problems while expanding services, so that the intelligent question and answer knowledge base needs to be continuously updated in an iterative manner and maintained for a long time, newly-appeared knowledge points are difficult to find by customer service staff, and the question and answer range of the intelligent question and answer system is inconvenient to expand.
Disclosure of Invention
The application provides a method, a system, a terminal and a storage medium for constructing an intelligent question-answering knowledge base, and aims to solve at least one of the technical problems in the prior art to a certain extent.
In order to solve the above problems, the present application provides the following technical solutions:
a method for constructing an intelligent question-answering knowledge base comprises the following steps:
obtaining chat logs of all visitors and manual customer service in a question-answering system, and generating effective question-answering pairs according to the chat logs; wherein the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
carrying out vector clustering operation on the effective question-answer pairs by using a clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category;
and counting the number of effective question-answer pairs in each category, screening the categories of which the number of the effective question-answer pairs exceeds a set threshold value, and adding the question-answer representatives of the screened categories into an intelligent question-answer knowledge base.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the generating of the effective question-answer pairs according to the chat logs is specifically as follows:
and performing intention identification on the chat logs through a text classification model, screening out the chat logs with non-chatting intentions, and generating effective question-answer pairs according to the screened chat logs.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the vector clustering operation on the effective question-answer pairs by using a clustering algorithm comprises the following steps:
carrying out vector coding on the questioning contents in the effective question-answer pair, and converting the questioning contents into vector representation;
the questioning content in each effective questioning and answering pair is in one-to-one correspondence with the corresponding vector representation, and the mapping relation between the questioning content and the corresponding vector representation is established;
clustering the vector representation of the questioning content by using a DBSCAN clustering algorithm;
and dividing the effective question-answer pairs into different categories according to the corresponding mapping relation according to the clustering result represented by the vector.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the clustering of the vector representation of the question content by using the DBSCAN clustering algorithm specifically comprises:
and calculating the distance between the two vectors in the high latitude, and dividing the two vectors with the distance smaller than a set distance threshold value into the same class.
The technical scheme adopted by the embodiment of the application further comprises the following steps: screening out the category that the number of the effective question-answer pairs exceeds the set threshold value further comprises:
and judging whether the intelligent question-answer knowledge base has the similar questions of the category or not, and if not, adding the question-answer representatives of the screening category as new knowledge points into the intelligent question-answer knowledge base.
The technical scheme adopted by the embodiment of the application further comprises the following steps: before adding the question-answer representatives of the screening categories into the intelligent question-answer knowledge base, the method further comprises the following steps:
and optimizing the question-answer representatives of the categories.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the optimization of the question-answer representatives of the screening categories is specifically as follows:
and performing book-surface modification on the spoken question content and the reply content in the question-answer representation.
Another technical scheme adopted by the embodiment of the application is as follows: an intelligent question-answering knowledge base construction system comprises:
a data acquisition module: the system comprises a chat log acquisition module, a question and answer module and a client service module, wherein the chat log acquisition module is used for acquiring chat logs of all visitors and manual customer service in a question and answer system and generating effective question and answer pairs according to the chat logs; wherein the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
a data classification module: the system comprises a clustering algorithm, a database and a database, wherein the clustering algorithm is used for carrying out vector clustering operation on the effective question-answer pairs by using a clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category;
the data screening module: the intelligent question and answer knowledge base is used for counting the number of effective question and answer pairs in each category, screening the categories of which the number of the effective question and answer pairs exceeds a set threshold value, and adding the question and answer representatives of the screened categories into the intelligent question and answer knowledge base.
The embodiment of the application adopts another technical scheme that: a terminal comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the intelligent question-answering knowledge base construction method;
the processor is configured to execute the program instructions stored by the memory to control intelligent question-answering knowledge base construction.
The embodiment of the application adopts another technical scheme that: a storage medium storing program instructions executable by a processor to perform the intelligent question-answering knowledge base construction method.
Compared with the prior art, the embodiment of the application has the advantages that: according to the method for constructing the intelligent question-answer knowledge base, by obtaining chat logs of all visitors and manual customer service in the question-answer system, effective question-answer pairs are generated according to the chat logs, then the effective question-answer pairs are divided into different categories by using a clustering algorithm, and the categories with the number exceeding a certain value of the effective question-answer pairs are used as new knowledge points to be added into the intelligent question-answer knowledge base. The embodiment of the application can find new knowledge points with high occurrence frequency in time and update the intelligent question-answering knowledge base, so that the question-answering range of the intelligent question-answering system is automatically expanded, the reply accuracy of the intelligent question-answering system is improved, and the requirement of a user on the field knowledge is reduced.
Drawings
FIG. 1 is a flow chart of a method for constructing an intelligent question and answer knowledge base according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of an intelligent question-answering knowledge base construction system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a terminal according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Please refer to fig. 1, which is a flowchart of a method for constructing an intelligent question and answer knowledge base according to an embodiment of the present application. The method for constructing the intelligent question-answering knowledge base comprises the following steps:
s1: obtaining chat logs of all visitors and manual customer service in a question-answering system; the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
s2: performing intention identification on the chat logs through a text classification model, screening out the chat logs with non-chatting intentions, and generating effective question-answer pairs according to the screened chat logs;
in this step, the intention (intent) refers to the intended purpose of the question content of the visitor in the question and answer process. The question-answer pair is a fixed collocation formed by the question content and the reply content in the chat log. According to the embodiment of the application, two text corpora of the service text and the chatting text are collected, a text classification model is trained by using deep learning models such as lstm and bert, and whether chatting logs belong to chatting or service question and answer is judged through the text classification model.
S3: vector coding (vector coding) is carried out on the questioning contents in the effective question-answer pairs, and the questioning contents are converted into vector representation;
in this step, vector encoding is a general term for a group of techniques in Natural Language Processing (NLP), i.e. mapping a sentence to a real vector.
S4: the questioning content in each effective questioning and answering pair is in one-to-one correspondence with the vector representation of the questioning content, and the mapping relation between the questioning content and the vector representation of the questioning content is established;
s5: clustering the vector representation of the questioning content by using a DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise) Clustering algorithm;
in this step, the classification manner of vector representation is specifically: and calculating the distance between any two vectors in the high latitude, and dividing the two vectors with the distance smaller than a set distance threshold value into the same class.
S6: dividing the effective question-answer pairs into different categories according to the corresponding mapping relation according to the clustering result represented by the vector, and taking any one effective question-answer pair in each category as a question-answer representative of the whole category;
in this step, the meaning of each effective question and answer pair to be expressed in the same category is the same, namely the question content of the visitor is closer to the customer service reply content. The classification mode of the effective question-answer pairs is specifically as follows: assuming that the vector representations of "hello" and "hello" are (0,1,0) and (0,1,1), respectively, if (0,1,0) and (0,1,1) are of the same class, then "hello" and "hello" are also classified into the same class.
S7: counting the number of valid question-answer pairs of each category, judging whether the number of valid question-answer pairs of each category exceeds a set threshold value, and if so, executing S8; otherwise, go to S10;
in this step, if the number of valid question-answer pairs in a certain category exceeds a set threshold, which indicates that the number of questions asked for that category of question is large (i.e., the concern of the visitor to the category of question is high), it is necessary to add the category of question to the intelligent question-answer knowledge base. If the number of the effective question-answer pairs in a certain class does not exceed the set threshold, the question is presented less frequently (namely the attention of the visitor to the question is low), and the question does not need to be added into the intelligent question-answer knowledge base.
S8: judging whether the intelligent question-answering knowledge base has the problems or not, and executing S9 if the intelligent question-answering knowledge base does not have the problems; otherwise, go to S10;
s9: after the question-answer representatives of the category are optimized, the question-answer representatives are used as new knowledge points and added into an intelligent question-answer knowledge base;
in this step, the question-answer representative optimization method specifically includes performing book-oriented modification on the spoken question content and the reply content in the question-answer representative.
S10: and (6) ending.
According to the method for constructing the intelligent question-answer knowledge base, by obtaining chat logs of all visitors and manual customer service in the question-answer system, effective question-answer pairs are generated according to the chat logs, then the effective question-answer pairs are divided into different categories by using a clustering algorithm, and the categories with the number exceeding a certain value of the effective question-answer pairs are used as new knowledge points to be added into the intelligent question-answer knowledge base. The embodiment of the application can find new knowledge points with high occurrence frequency in time and update the intelligent question-answering knowledge base, so that the question-answering range of the intelligent question-answering system is automatically expanded, the reply accuracy of the intelligent question-answering system is improved, and the requirement of a user on the field knowledge is reduced.
Please refer to fig. 2, which is a schematic structural diagram of a system for constructing an intelligent question and answer knowledge base according to an embodiment of the present application. The intelligent question-answering knowledge base construction system 40 of the embodiment of the application comprises:
the data acquisition module 41: the system comprises a chat log acquisition module, a question and answer module and a client service module, wherein the chat log acquisition module is used for acquiring chat logs of all visitors and manual customer service in a question and answer system and generating effective question and answer pairs according to the chat logs; the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
data classification module 42: the system comprises a clustering algorithm, a database and a database, wherein the clustering algorithm is used for carrying out vector clustering operation on effective question-answer pairs by using the clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category;
the data screening module 43: the method is used for counting the number of effective question-answer pairs in each category, screening out the categories of which the number of the effective question-answer pairs exceeds a set threshold value, and adding the question-answer representatives of the screened categories into an intelligent question-answer knowledge base.
Please refer to fig. 3, which is a schematic diagram of a terminal structure according to an embodiment of the present application. The terminal 50 comprises a processor 51, a memory 52 coupled to the processor 51.
The memory 52 stores program instructions for implementing the intelligent question-answering knowledge base construction method described above.
The processor 51 is operative to execute program instructions stored in the memory 52 to control the intelligent question and answer knowledge base construction.
The processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having signal processing capabilities. The processor 51 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Please refer to fig. 4, which is a schematic structural diagram of a storage medium according to an embodiment of the present application. The storage medium of the embodiment of the present application stores a program file 61 capable of implementing all the methods described above, where the program file 61 may be stored in the storage medium in the form of a software product, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for constructing an intelligent question-answering knowledge base is characterized by comprising the following steps:
obtaining chat logs of all visitors and manual customer service in a question-answering system, and generating effective question-answering pairs according to the chat logs; wherein the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
carrying out vector clustering operation on the effective question-answer pairs by using a clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category;
and counting the number of effective question-answer pairs in each category, screening the categories of which the number of the effective question-answer pairs exceeds a set threshold value, and adding the question-answer representatives of the screened categories into an intelligent question-answer knowledge base.
2. The method for constructing an intelligent question-answer knowledge base according to claim 1, wherein the step of generating effective question-answer pairs according to the chat logs specifically comprises the steps of:
and performing intention identification on the chat logs through a text classification model, screening out the chat logs with non-chatting intentions, and generating effective question-answer pairs according to the screened chat logs.
3. The method for constructing an intelligent question-answer knowledge base according to claim 1 or 2, wherein the vector clustering operation on the effective question-answer pairs by using a clustering algorithm comprises the following steps:
carrying out vector coding on the questioning contents in the effective question-answer pair, and converting the questioning contents into vector representation;
the questioning content in each effective questioning and answering pair is in one-to-one correspondence with the corresponding vector representation, and the mapping relation between the questioning content and the corresponding vector representation is established;
clustering the vector representation of the questioning content by using a DBSCAN clustering algorithm;
and dividing the effective question-answer pairs into different categories according to the corresponding mapping relation according to the clustering result represented by the vector.
4. The method for constructing an intelligent question-answering knowledge base according to claim 3, wherein the clustering of the vector representation of the question content by using the DBSCAN clustering algorithm specifically comprises:
and calculating the distance between the two vectors in the high latitude, and dividing the two vectors with the distance smaller than a set distance threshold value into the same class.
5. The method for constructing an intelligent question-answer knowledge base according to claim 1, wherein the step of screening out the categories of which the number of effective question-answer pairs exceeds a set threshold value further comprises the steps of:
and judging whether the intelligent question-answer knowledge base has the similar questions of the category or not, and if not, adding the question-answer representatives of the screening category as new knowledge points into the intelligent question-answer knowledge base.
6. The method for building an intelligent question-answer knowledge base according to claim 5, wherein before adding the question-answer representatives of the screening categories into the intelligent question-answer knowledge base, the method further comprises:
and optimizing the question-answer representatives of the categories.
7. The method for constructing an intelligent question-answer knowledge base according to claim 6, wherein the optimization of the question-answer representatives of the screening categories is specifically as follows:
and performing book-surface modification on the spoken question content and the reply content in the question-answer representation.
8. An intelligent question-answering knowledge base construction system is characterized by comprising:
a data acquisition module: the system comprises a chat log acquisition module, a question and answer module and a client service module, wherein the chat log acquisition module is used for acquiring chat logs of all visitors and manual customer service in a question and answer system and generating effective question and answer pairs according to the chat logs; wherein the chat log comprises the questioning content of the visitor and the reply content of the manual customer service;
a data classification module: the system comprises a clustering algorithm, a database and a database, wherein the clustering algorithm is used for carrying out vector clustering operation on the effective question-answer pairs by using a clustering algorithm, dividing the effective question-answer pairs into different categories, and taking any one of the effective question-answer pairs in each category as a question-answer representative of the whole category;
the data screening module: the intelligent question and answer knowledge base is used for counting the number of effective question and answer pairs in each category, screening the categories of which the number of the effective question and answer pairs exceeds a set threshold value, and adding the question and answer representatives of the screened categories into the intelligent question and answer knowledge base.
9. A terminal, comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the intelligent question-answering knowledge base construction method according to any one of claims 1 to 7;
the processor is configured to execute the program instructions stored by the memory to control intelligent question-answering knowledge base construction.
10. A storage medium storing program instructions executable by a processor to perform the method of constructing a knowledge base of intelligent question and answer set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110375860.3A CN113010658A (en) | 2021-04-08 | 2021-04-08 | Intelligent question-answering knowledge base construction method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110375860.3A CN113010658A (en) | 2021-04-08 | 2021-04-08 | Intelligent question-answering knowledge base construction method, system, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113010658A true CN113010658A (en) | 2021-06-22 |
Family
ID=76388092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110375860.3A Pending CN113010658A (en) | 2021-04-08 | 2021-04-08 | Intelligent question-answering knowledge base construction method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113010658A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113535980A (en) * | 2021-07-20 | 2021-10-22 | 南京市栖霞区民政事务服务中心 | Rapid establishing method of intelligent community knowledge base system based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150041908A (en) * | 2013-10-10 | 2015-04-20 | 포항공과대학교 산학협력단 | Method for automatically classifying answer type and apparatus, question-answering system for using the same |
| CN104679815A (en) * | 2014-12-08 | 2015-06-03 | 北京云知声信息技术有限公司 | Method and system for screening question and answer pairs and updating question and answer database in real time |
| CN109189803A (en) * | 2018-09-03 | 2019-01-11 | 深圳前海微众银行股份有限公司 | Question and answer are to construction method, device and computer readable storage medium |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110413755A (en) * | 2019-07-25 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A kind of extending method, device and server, the storage medium in question and answer library |
| CN110502622A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Common medical question and answer data creation method, device and computer equipment |
| CN111858891A (en) * | 2020-07-23 | 2020-10-30 | 平安科技（深圳）有限公司 | Question-answer library construction method and device, electronic equipment and storage medium |
| CN112148880A (en) * | 2020-09-28 | 2020-12-29 | 深圳壹账通智能科技有限公司 | Customer service dialogue corpus clustering method, system, equipment and storage medium |
-
2021
- 2021-04-08 CN CN202110375860.3A patent/CN113010658A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150041908A (en) * | 2013-10-10 | 2015-04-20 | 포항공과대학교 산학협력단 | Method for automatically classifying answer type and apparatus, question-answering system for using the same |
| CN104679815A (en) * | 2014-12-08 | 2015-06-03 | 北京云知声信息技术有限公司 | Method and system for screening question and answer pairs and updating question and answer database in real time |
| CN109189803A (en) * | 2018-09-03 | 2019-01-11 | 深圳前海微众银行股份有限公司 | Question and answer are to construction method, device and computer readable storage medium |
| CN110019149A (en) * | 2019-01-30 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of method for building up of service knowledge base, device and equipment |
| CN110502622A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Common medical question and answer data creation method, device and computer equipment |
| CN110413755A (en) * | 2019-07-25 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A kind of extending method, device and server, the storage medium in question and answer library |
| CN111858891A (en) * | 2020-07-23 | 2020-10-30 | 平安科技（深圳）有限公司 | Question-answer library construction method and device, electronic equipment and storage medium |
| CN112148880A (en) * | 2020-09-28 | 2020-12-29 | 深圳壹账通智能科技有限公司 | Customer service dialogue corpus clustering method, system, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘东明: "京东JIMI：智能客服机器", 《智能+AI赋能传统产业数字化转型》 * |
| 程静: "密度聚类", 《R语言数据分析与挖掘实战手册》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113535980A (en) * | 2021-07-20 | 2021-10-22 | 南京市栖霞区民政事务服务中心 | Rapid establishing method of intelligent community knowledge base system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11551007B2 (en) | Determining intent from a historical vector of a to-be-analyzed statement | |
| EP3144822A1 (en) | Tagging text snippets | |
| CN107402912B (en) | Method and device for analyzing semantics | |
| US11681872B2 (en) | Language sequence labeling method and apparatus, storage medium, and computing device | |
| CN108038208B (en) | Training method and device of context information recognition model and storage medium | |
| WO2022252636A1 (en) | Artificial intelligence-based answer generation method and apparatus, device, and storage medium | |
| WO2012126259A1 (en) | System having information distributing and searching functions and information distribution method | |
| CN114861889B (en) | Deep learning model training method, target object detection method and device | |
| US11120214B2 (en) | Corpus generating method and apparatus, and human-machine interaction processing method and apparatus | |
| CN111159409A (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
| CN111666400A (en) | Message acquisition method and device, computer equipment and storage medium | |
| US11494564B2 (en) | Unsupervised aspect-based multi-document abstractive summarization | |
| CN114168619A (en) | Training method and device of language conversion model | |
| KR20150041908A (en) | Method for automatically classifying answer type and apparatus, question-answering system for using the same | |
| CN113010658A (en) | Intelligent question-answering knowledge base construction method, system, terminal and storage medium | |
| CN110633468B (en) | Information processing method and device for object feature extraction | |
| AU2019298610B2 (en) | Search device and program | |
| CN117290478A (en) | Knowledge graph question-answering method, device, equipment and storage medium | |
| CN116775875A (en) | Question corpus construction method and device, question answering method and device and storage medium | |
| CN116955561A (en) | Question answering method, question answering device, electronic equipment and storage medium | |
| CN116127066A (en) | Text clustering method, text clustering device, electronic equipment and storage medium | |
| CN115934904A (en) | Text processing method and device | |
| CN111046191B (en) | Semantic enhancement method and device in power field | |
| CN114266255A (en) | Corpus classification method, apparatus, device and storage medium based on clustering model | |
| CN113010664A (en) | Data processing method and device and computer 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |