CN111753055B - Automatic prompt method and device for customer questions and answers - Google Patents
Automatic prompt method and device for customer questions and answers Download PDFInfo
- Publication number
- CN111753055B CN111753055B CN202010599496.4A CN202010599496A CN111753055B CN 111753055 B CN111753055 B CN 111753055B CN 202010599496 A CN202010599496 A CN 202010599496A CN 111753055 B CN111753055 B CN 111753055B
- Authority
- CN
- China
- Prior art keywords
- automatic
- input information
- result
- knowledge
- text input
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012163 sequencing technique Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 18
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 241000274965 Cyrestis thyodamas Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a client question-answering automatic prompting method and device, which are characterized in that a knowledge base with a correlation relationship of knowledge units is established, original text input information is processed to obtain key text input information, the key text input information and the knowledge units are subjected to similarity calculation and sequencing based on the knowledge base to obtain a pre-automatic prompting result, and sequencing is adjusted based on the correlation relationship, so that the accuracy of the client question-answering automatic prompting result can be greatly improved, and further the working efficiency and client question-answering experience are improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a client question-answering automatic prompting method and device.
Background
With the continuous development of science and technology, various enterprises are continuously improved in the field of customer service to improve the quality of customer service.
However, the workload of the agents in the current customer service field is still very huge, when the customer describes the encountered problems, the agents usually need to input a large section of characters to search a knowledge base, the input process time is long, and most of the existing customer service knowledge bases simply analyze and process the problems to prompt the solution information related to the problems.
Obviously, the hit rate of extracting the problem-related answering information in the current processing mode is low, so that the problem of a client cannot be solved, and the time consumption is long.
Disclosure of Invention
In view of the above, in order to solve the above problems, the present invention provides a method and an apparatus for automatically prompting a client question and answer, which have the following technical solutions:
a client question-answer automatic prompting method, the client question-answer automatic prompting method comprising:
establishing a knowledge base, wherein knowledge units in the knowledge base have association relations;
receiving original text input information of a client;
processing the original text input information to obtain key text input information;
based on the knowledge base, carrying out similarity calculation and sequencing on the key text input information and the knowledge units to obtain a pre-automatic prompting result;
judging whether an association relationship exists between knowledge units in the pre-automatic prompt result;
if yes, the arrangement sequence of the knowledge units is adjusted based on the pre-automatic prompt result, and a target automatic prompt result is obtained.
Preferably, in the automatic client question-answering prompting method, the automatic client question-answering prompting method further includes:
and when no association relation exists between knowledge units in the pre-automatic prompt result, the pre-automatic prompt result is the target automatic prompt result.
Preferably, in the automatic client question-answering prompting method, the receiving the original text input information of the client includes:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question and answer service is in, the original text input information is input through the set input area.
Preferably, in the automatic client question-answering prompting method, the obtaining a pre-automatic prompting result includes:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
Preferably, in the automatic prompt method for client question and answer, the adjusting the arrangement sequence of the knowledge units based on the pre-automatic prompt result to obtain the target automatic prompt result includes:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
A client question-answering automatic prompting device, the client question-answering automatic prompting device comprising:
the building module is used for building a knowledge base, and knowledge units in the knowledge base have association relations;
the receiving module is used for receiving original text input information of a client;
the processing module is used for processing the original text input information to obtain key text input information;
the similarity calculation module is used for carrying out similarity calculation and sequencing on the key text input information and the knowledge units based on the knowledge base to obtain a pre-automatic prompt result;
the judging module is used for judging whether the association relation exists between the knowledge units in the pre-automatic prompting result;
and the adjusting module is used for adjusting the arrangement sequence of the knowledge units based on the pre-automatic prompting result if so, and obtaining a target automatic prompting result.
Preferably, in the automatic client question-answering prompting device, the automatic client question-answering prompting device further includes:
and the confirmation module is used for determining the pre-automatic prompt result as the target automatic prompt result when the association relation does not exist between the knowledge units in the pre-automatic prompt result.
Preferably, in the automatic client question-answering prompting device, the receiving module is specifically configured to:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question and answer service is in, the original text input information is input through the set input area.
Preferably, in the automatic client question-answering prompting device, the similarity calculating module is specifically configured to:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
Preferably, in the automatic client question-answering prompting device, the adjusting module is specifically configured to:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a client question-answering automatic prompting method, which comprises the following steps: establishing a knowledge base, wherein knowledge units in the knowledge base have association relations; receiving original text input information of a client; processing the original text input information to obtain key text input information; based on the knowledge base, carrying out similarity calculation and sequencing on the key text input information and the knowledge units to obtain a pre-automatic prompting result; judging whether an association relationship exists between knowledge units in the pre-automatic prompt result; if yes, the arrangement sequence of the knowledge units is adjusted based on the pre-automatic prompt result, and a target automatic prompt result is obtained. The client question-answering automatic prompting method has the advantages that the hit rate of extracting the question-related answer information is high, and the time consumption is short.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a client question-answering automatic prompting method provided by an embodiment of the invention;
FIG. 2 is a flowchart of another automatic client question-answering prompting method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an automatic client question-answering prompt device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another automatic client question-answering prompting device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Referring to fig. 1, fig. 1 is a flow chart of a method for automatically prompting a client question and answer according to an embodiment of the present invention.
The automatic prompting method for the client question and answer comprises the following steps:
s101: and establishing a knowledge base, wherein knowledge units in the knowledge base have association relations.
In this step, the knowledge units are basic units stored in the knowledge base and include attributes such as a scene, a title, a map label, a personality label, a source document, a user group, an effective time, and an expiration time, and in this application, at least two knowledge units are formed into a knowledge unit with an association relationship through a common feature, for example, two knowledge units have the same source document or multiple knowledge units have a common map label, and then the knowledge units are associated.
And, as many associated attributes as possible in the present application, the degree of closeness between knowledge units increases.
S102: original text input information of a customer is received.
S103: and processing the original text input information to obtain key text input information.
In this step, operations such as character filtering, word segmentation and mark filtering are performed on the original text input information.
Firstly, character filtering processing is carried out on original text input information, such as filtering meaningless characters < p > < html > or other characters, by carrying out standardization processing on random, irregular and even wrong character strings; secondly, word segmentation is carried out on the original text input information, including Chinese, english or other languages, and words with independent meanings are output; and finally, marking and filtering the segmented words to output key text input information.
For example, the original text input signal is: how to transact the woolen cloth by ETC, the key text input information obtained after the processing is as follows: ETC how to do. The meaning of the word "woolen" is removed.
S104: and based on the knowledge base, carrying out similarity calculation and sequencing on the key text input information and the knowledge units to obtain a pre-automatic prompting result.
S105: judging whether an association relationship exists between knowledge units in the pre-automatic prompt result.
S106: if yes, the arrangement sequence of the knowledge units is adjusted based on the pre-automatic prompt result, and a target automatic prompt result is obtained.
In this embodiment, a knowledge base with a knowledge unit having an association relationship is first established, the original text input information is processed to obtain key text input information, similarity calculation is performed on the key text input information and the knowledge unit based on the knowledge base, a pre-automatic prompt result is obtained, and the ranking is adjusted based on the association relationship, so that accuracy of the automatic prompt result of the client question and answer can be greatly improved, and further work efficiency and client question and answer experience are improved.
Further, according to the above embodiment of the present invention, referring to fig. 2, fig. 2 is a flow chart of another automatic client question-answering prompting method according to the embodiment of the present invention.
The automatic prompting method for the client question and answer further comprises the following steps:
s107: and when no association relation exists between knowledge units in the pre-automatic prompt result, the pre-automatic prompt result is the target automatic prompt result.
In this embodiment, if the knowledge units in the pre-automatic prompting result have no association relationship, the ranking is only performed according to the similarity calculation result.
Further, according to the above embodiment of the present invention, the receiving the original text input information of the client includes:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question and answer service is in, the original text input information is input through the set input area.
Further, according to the above embodiment of the present invention, the obtaining the pre-automatic prompting result includes:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
In the embodiment, knowledge units with similarity to the key text input information are selected, and the knowledge units are ranked according to the similarity score from high to low, so that the accuracy of the automatic prompt result of the client question and answer can be improved.
Further, according to the above embodiment of the present invention, the adjusting the arrangement order of the knowledge units based on the pre-automatic prompting result to obtain the target automatic prompting result includes:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
In this embodiment, in the pre-automatic prompting result, when the knowledge units arranged in the first position and the knowledge units arranged in the eighth position have an association relationship, but the knowledge units arranged in the first position and the knowledge units arranged in the second position do not have an association relationship, the knowledge units arranged in the eighth position may be arranged in the second position, and the other knowledge units are sequentially arranged in the backward order.
In this way, the relevant answers to the client question questions can be concentrated and still arranged according to the similarity scores, and the accuracy of the client question and answer automatic prompt results can be further improved.
Based on all the above embodiments of the present invention, another embodiment of the present invention further provides a client question-answering automatic prompting device, and referring to fig. 3, fig. 3 is a schematic structural diagram of a client question-answering automatic prompting device provided by the embodiment of the present invention.
The automatic prompt device for the client question and answer comprises:
the establishing module 31 is configured to establish a knowledge base, where knowledge units in the knowledge base have an association relationship.
Specifically, the knowledge units are basic units stored in the knowledge base and include attributes such as scenes, titles, atlas labels, personality labels, source documents, user groups, effective time and dead time, and in the application, at least two knowledge units are formed into knowledge units with association relations through common features, for example, two knowledge units have the same source documents or a plurality of knowledge units have common atlas labels, and then the knowledge units are associated.
And, as many associated attributes as possible in the present application, the degree of closeness between knowledge units increases.
A receiving module 32 for receiving the original text input information of the customer.
Specifically, the method comprises, but is not limited to, performing character filtering, word segmentation, mark filtering and other operations on the original text input information.
Firstly, character filtering processing is carried out on original text input information, such as filtering meaningless characters < p > < html > or other characters, by carrying out standardization processing on random, irregular and even wrong character strings; secondly, word segmentation is carried out on the original text input information, including Chinese, english or other languages, and words with independent meanings are output; and finally, marking and filtering the segmented words to output key text input information.
For example, the original text input signal is: how to transact the woolen cloth by ETC, the key text input information obtained after the processing is as follows: ETC how to do. The meaning of the word "woolen" is removed.
And the processing module 33 is used for processing the original text input information to obtain key text input information.
And the similarity calculation module 34 is configured to perform similarity calculation and ranking on the key text input information and the knowledge units based on the knowledge base, so as to obtain a pre-automatic prompt result.
And the judging module 35 is configured to judge whether an association relationship exists between the knowledge units in the pre-automatic prompting result.
And the adjusting module 36 is configured to adjust the arrangement sequence of the knowledge units based on the pre-automatic prompting result if yes, and obtain a target automatic prompting result.
In this embodiment, a knowledge base with a knowledge unit having an association relationship is first established, the original text input information is processed to obtain key text input information, similarity calculation is performed on the key text input information and the knowledge unit based on the knowledge base, a pre-automatic prompt result is obtained, and the ranking is adjusted based on the association relationship, so that accuracy of the automatic prompt result of the client question and answer can be greatly improved, and further work efficiency and client question and answer experience are improved.
Further, according to the above embodiment of the present invention, referring to fig. 4, fig. 4 is a schematic structural diagram of another automatic client question-answering prompting device according to the embodiment of the present invention.
The automatic client question-answering prompting device further comprises:
and the confirmation module 37 is configured to, when no association relationship exists between the knowledge units in the pre-automatic prompting result, determine that the pre-automatic prompting result is the target automatic prompting result.
In this embodiment, if the knowledge units in the pre-automatic prompting result have no association relationship, the ranking is only performed according to the similarity calculation result.
Further, according to the above embodiment of the present invention, the receiving module is specifically configured to:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question and answer service is in, the original text input information is input through the set input area.
Further, according to the above embodiment of the present invention, the similarity calculation module is specifically configured to:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
In the embodiment, knowledge units with similarity to the key text input information are selected, and the knowledge units are ranked according to the similarity score from high to low, so that the accuracy of the automatic prompt result of the client question and answer can be improved.
Further, according to the above embodiment of the present invention, the adjusting module is specifically configured to:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
In this embodiment, in the pre-automatic prompting result, when the knowledge units arranged in the first position and the knowledge units arranged in the eighth position have an association relationship, but the knowledge units arranged in the first position and the knowledge units arranged in the second position do not have an association relationship, the knowledge units arranged in the eighth position may be arranged in the second position, and the other knowledge units are sequentially arranged in the backward order.
In this way, the relevant answers to the client question questions can be concentrated and still arranged according to the similarity scores, and the accuracy of the client question and answer automatic prompt results can be further improved.
According to the automatic client question-answering prompting method provided by the invention, the knowledge base with the association relation of the knowledge units is established, the original text input information is processed to obtain the key text input information, the key text input information and the knowledge units are subjected to similarity calculation and sequencing based on the knowledge base to obtain the pre-automatic prompting result, and the sequencing is adjusted based on the association relation, so that the accuracy of the automatic client question-answering prompting result can be greatly improved, and the working efficiency and the client question-answering experience are further improved.
The above describes in detail a method and apparatus for automatically prompting a client question and answer provided by the present invention, and specific examples are applied herein to illustrate the principles and embodiments of the present invention, and the above examples are only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include, or is intended to include, elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. 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 invention. Thus, the present invention 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 (4)
1. The automatic client question-answering prompting method is characterized by comprising the following steps of:
establishing a knowledge base, and forming knowledge units with association relations by at least two knowledge units in the knowledge base through common characteristics;
receiving original text input information of a client;
processing the original text input information to obtain key text input information;
based on the knowledge base, carrying out similarity calculation and sequencing on the key text input information and the knowledge units to obtain a pre-automatic prompting result;
judging whether an association relationship exists between knowledge units in the pre-automatic prompt result;
if yes, adjusting the arrangement sequence of the knowledge units based on the pre-automatic prompt result to obtain a target automatic prompt result;
the automatic prompting method for the client question and answer further comprises the following steps:
when no association relation exists between knowledge units in the pre-automatic prompt result, the pre-automatic prompt result is the target automatic prompt result;
wherein, the receiving the original text input information of the client comprises:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question-answering service is in, inputting the original text input information through a set input area;
the step of adjusting the arrangement sequence of the knowledge units based on the pre-automatic prompt result to obtain a target automatic prompt result comprises the following steps:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
2. The automatic client question-answering prompting method according to claim 1, wherein the obtaining of the pre-automatic prompting result includes:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
3. The automatic client question-answering prompting device is characterized by comprising:
the system comprises a building module, a knowledge base, a storage module and a storage module, wherein the building module is used for building a knowledge base, and forming knowledge units with association relations by at least two knowledge units in the knowledge base through common characteristics;
the receiving module is used for receiving original text input information of a client;
the processing module is used for processing the original text input information to obtain key text input information;
the similarity calculation module is used for carrying out similarity calculation and sequencing on the key text input information and the knowledge units based on the knowledge base to obtain a pre-automatic prompt result;
the judging module is used for judging whether the association relation exists between the knowledge units in the pre-automatic prompting result;
the adjusting module is used for adjusting the arrangement sequence of the knowledge units based on the pre-automatic prompting result if yes, and obtaining a target automatic prompting result;
wherein, the automatic prompt device for client question and answer further comprises:
the confirmation module is used for determining that the pre-automatic prompt result is the target automatic prompt result when the association relation does not exist between the knowledge units in the pre-automatic prompt result;
the receiving module is specifically configured to:
when the system is in question-answering service, generating original text input information according to the original voice input information of a client;
when the manual question-answering service is in, inputting the original text input information through a set input area;
the adjusting module is specifically configured to:
and according to the association relation between the knowledge units in the pre-automatic prompt result, adjusting the knowledge units with low scores in the similarity calculation result to the knowledge units with high scores, which have association relation with the knowledge units.
4. The automatic client question-answering prompt device according to claim 3, wherein the similarity calculation module is specifically configured to:
performing similarity calculation on the key text input information and the knowledge unit;
and sorting the scores from high to low according to the similarity calculation result, and generating the pre-automatic prompt result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599496.4A CN111753055B (en) | 2020-06-28 | 2020-06-28 | Automatic prompt method and device for customer questions and answers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599496.4A CN111753055B (en) | 2020-06-28 | 2020-06-28 | Automatic prompt method and device for customer questions and answers |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111753055A CN111753055A (en) | 2020-10-09 |
| CN111753055B true CN111753055B (en) | 2024-01-26 |
Family
ID=72677691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010599496.4A Active CN111753055B (en) | 2020-06-28 | 2020-06-28 | Automatic prompt method and device for customer questions and answers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111753055B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
| CN108846029A (en) * | 2018-05-28 | 2018-11-20 | 哈尔滨工程大学 | The information association analysis method of knowledge based map |
| CN109460462A (en) * | 2018-11-15 | 2019-03-12 | 中通天鸿（北京）通信科技股份有限公司 | A kind of Chinese Similar Problems generation System and method for |
| CN109783624A (en) * | 2018-12-27 | 2019-05-21 | 联想(北京)有限公司 | Answer generation method, device and the intelligent conversational system in knowledge based library |
| CN109871428A (en) * | 2019-01-30 | 2019-06-11 | 北京百度网讯科技有限公司 | For determining the method, apparatus, equipment and medium of the text degree of correlation |
| CN110502621A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Answering method, question and answer system, computer equipment and storage medium |
| CN111309877A (en) * | 2018-12-12 | 2020-06-19 | 北京文因互联科技有限公司 | Intelligent question-answering method and system based on knowledge graph |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160041986A1 (en) * | 2014-08-08 | 2016-02-11 | Cuong Duc Nguyen | Smart Search Engine |
-
2020
- 2020-06-28 CN CN202010599496.4A patent/CN111753055B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
| CN108846029A (en) * | 2018-05-28 | 2018-11-20 | 哈尔滨工程大学 | The information association analysis method of knowledge based map |
| CN109460462A (en) * | 2018-11-15 | 2019-03-12 | 中通天鸿（北京）通信科技股份有限公司 | A kind of Chinese Similar Problems generation System and method for |
| CN111309877A (en) * | 2018-12-12 | 2020-06-19 | 北京文因互联科技有限公司 | Intelligent question-answering method and system based on knowledge graph |
| CN109783624A (en) * | 2018-12-27 | 2019-05-21 | 联想(北京)有限公司 | Answer generation method, device and the intelligent conversational system in knowledge based library |
| CN109871428A (en) * | 2019-01-30 | 2019-06-11 | 北京百度网讯科技有限公司 | For determining the method, apparatus, equipment and medium of the text degree of correlation |
| CN110502621A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Answering method, question and answer system, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111753055A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109918673B (en) | Semantic arbitration method and device, electronic equipment and computer-readable storage medium | |
| CN108764480B (en) | Information processing system | |
| CN108038234B (en) | Automatic question template generating method and device | |
| CN111309877A (en) | Intelligent question-answering method and system based on knowledge graph | |
| CN109189901B (en) | Method for automatically discovering new classification and corresponding corpus in intelligent customer service system | |
| CN101599071B (en) | Automatic extraction method of conversation text topic | |
| CN107153965A (en) | A kind of intelligent customer service solution of multiple terminals | |
| WO2017181834A1 (en) | Intelligent question and answer method and device | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN102033950A (en) | Construction method and identification method of automatic electronic product named entity identification system | |
| CN111966796B (en) | Question and answer pair extraction method, device and equipment and readable storage medium | |
| CN106844344B (en) | Contribution calculation method for conversation and theme extraction method and system | |
| CN107784048B (en) | Question classification method and device for question and answer corpus | |
| CN111026884A (en) | Dialog corpus generation method for improving quality and diversity of human-computer interaction dialog corpus | |
| CN112115252A (en) | Intelligent auxiliary writing processing method and device, electronic equipment and storage medium | |
| CN111046201A (en) | Garbage classification simulation system based on computer software | |
| JP5258056B2 (en) | Question sentence candidate presentation device | |
| CN111753055B (en) | Automatic prompt method and device for customer questions and answers | |
| CN114580407A (en) | Intelligent consulting method and system for industry recruitment in park based on maximum entropy | |
| US20090234836A1 (en) | Multi-term search result with unsupervised query segmentation method and apparatus | |
| CN111666472B (en) | Intelligent identification method for academic chain nodes | |
| CN111813919B (en) | MOOC course evaluation method based on syntactic analysis and keyword detection | |
| CN114911903A (en) | Intelligent assistant question-answering method facing social groups | |
| CN111159360B (en) | Method and device for obtaining query topic classification model and query topic classification | |
| CN114238595A (en) | Metallurgical knowledge question-answering method and system based on knowledge graph |
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 |