CN114090789B - Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance - Google Patents
Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance Download PDFInfo
- Publication number
- CN114090789B CN114090789B CN202111369070.0A CN202111369070A CN114090789B CN 114090789 B CN114090789 B CN 114090789B CN 202111369070 A CN202111369070 A CN 202111369070A CN 114090789 B CN114090789 B CN 114090789B
- Authority
- CN
- China
- Prior art keywords
- traditional chinese
- chinese medicine
- graph
- entity
- knowledge
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/338—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the field of artificial intelligent knowledge graphs, and provides a traditional Chinese medicine health preserving intelligent multi-round interaction system based on the knowledge graphs. The interactive system adopts the interactive mode of multi-round dialogue, and is higher than the conventional single-round interactive question-answering system in the experience of the terminal user and the conclusion accuracy of the traditional Chinese medicine health care consultation question-answering. The invention aims at entity link of the identified entities in the context, and solves entity omission and reference resolution of sentences in multiple rounds of conversations by combining the entity link model of the text information based on the memory sequence.
Description
Technical Field
The invention belongs to the field of artificial intelligence knowledge graphs, and particularly relates to a traditional Chinese medicine health maintenance intelligent multi-round interaction system based on a knowledge graph.
Background
The state establishes a management system which accords with the characteristics of the traditional Chinese medicine, so that the traditional Chinese medicine fully plays an important role in the field of medicine and health of China, and the traditional Chinese medicine health maintenance is an important component of the traditional Chinese medicine in the field of medicine and health of China. Along with the popularization of mobile internet, people perform related knowledge consultation of traditional Chinese medicine health maintenance through mobile terminals, and become a normalized application scene. The intelligent interactive systems in the traditional Chinese medicine health maintenance field are mainly question-answering systems, and most of the question-answering systems are single-round intelligent interactive systems, namely users ask questions, the system returns answers according to the questions, and when the users ask questions again, the previous question-asking systems are not associated, namely the systems have no memory capacity. This can result in a large number of repeated questions being required by the user to obtain answers to the questions, and even no accurate answer can be obtained.
At present, a plurality of question-answering systems also adopt a multi-round interaction mode, but in the multi-round interaction process, as a conventional session generation model is used for splicing front and rear texts of interaction, modeling is carried out on the spliced texts, but the front and rear texts are composed of a plurality of text sentences, the spliced texts are long, front and rear text vector information obtained by the modeling mode can be imperfect because the front information is scattered, the session between a user and the system can be subjected to reference resolution and entity omission, and the situation can cause great trouble on entity linkage, so that the user can not obtain an accurate answer to the questions.
Disclosure of Invention
The invention aims to solve the problems and aims to provide a knowledge graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance.
The invention provides a knowledge graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which has the characteristics that: the entity extraction module is used for extracting entities in clinical information input by a user in each round of interaction; the entity link module is used for carrying out reference resolution and entity disambiguation on the entity to obtain a processed entity; the entity query module is used for acquiring a plurality of triples related to the processed entity from a prestored traditional Chinese medicine health-preserving knowledge graph; the extraction and sorting module is used for screening a plurality of related triples of clinical information which needs to be input again by a user, sorting the triples according to preset priorities to obtain a triplet priority sequence and determining the highest priority triplet; the session generation module is used for generating a problem according to the highest priority triplet and the prestored traditional Chinese medicine health maintenance knowledge graph so as to ask a question of the user in the next round; and the result generation module is used for generating health care suggestion results according to the clinical information input by the user for many times and the prestored traditional Chinese medicine health care knowledge graph, wherein the entity linking module comprises a front and rear Wen Bianma device, an input text encoder, a candidate text encoder, an attention mechanism layer and an output result layer.
Effects and effects of the invention
According to the knowledge graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which is disclosed by the invention, because the interaction system has the memory capacity, the content interacted with a user can be actively associated, after the user inputs clinical manifestations to the system, the system can actively ask the user for related complaint manifestations according to the characteristics of the clinical manifestations input by the user, the user inputs related feedback content to the system according to the question of the system, and the intelligent interaction system finally gives the traditional Chinese medicine health maintenance suggestion with higher accuracy to the user after the user interacts with the system for many rounds. Moreover, the interactive system of the invention adopts the interactive form of multi-round dialogue, which is higher than the conventional single-round interactive question-answering system in the experience of the terminal user and the conclusion accuracy of the traditional Chinese medicine health care consultation question-answering. In addition, the invention aims at entity link of the entities identified in the context, and provides an entity link model based on a memory sequence by combining text information of the context to solve entity omission and reference resolution of sentences in multiple rounds of conversations.
Drawings
FIG. 1 is a block diagram of a knowledge-based intelligent multi-round interaction system for traditional Chinese medical health maintenance in an embodiment of the invention;
fig. 2 is a hardware architecture diagram of a knowledge-based intelligent multi-round interaction system for traditional Chinese medical health maintenance in an embodiment of the invention;
FIG. 3 is a software architecture diagram of a knowledge-based intelligent multi-round interaction system for traditional Chinese medical health maintenance in an embodiment of the invention;
fig. 4 is a working logic diagram of an entity link module of the intelligent multi-round interaction system for traditional Chinese medical health maintenance based on a knowledge graph in the embodiment of the invention;
fig. 5 is a flowchart for constructing a knowledge graph of traditional Chinese medicine health care based on a knowledge graph intelligent multi-round interaction system of traditional Chinese medicine health care in an embodiment of the invention;
FIG. 6 is a working logic diagram of a session generation module of the intelligent multi-round interaction system for traditional Chinese medical health maintenance based on a knowledge graph in an embodiment of the invention;
fig. 7 is a flowchart of generating a corpus in a corpus storage module of the knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medical health maintenance in an embodiment of the invention;
fig. 8 is a logic diagram of operation of the intelligent multi-round interaction system for traditional Chinese medicine health maintenance based on a knowledge graph in the embodiment of the invention.
Detailed Description
In order to make the technical means, creation characteristics, achievement purposes and effects realized by the invention easy to understand, the following embodiment specifically describes the knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance by combining with the attached drawings.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: wherein the front and back Wen Bianma are used to extract the features of the entities in the two adjacent rounds of interaction.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: wherein, the front and back Wen Bianma devices, the input text encoder, the candidate text encoder all include two-way long-short-term memory neural network.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance provided by the invention can also have the characteristics that the system further comprises: the knowledge graph storage module is used for storing a traditional Chinese medicine health-preserving knowledge graph, and the traditional Chinese medicine health-preserving knowledge graph comprises traditional Chinese medicine health-preserving ontology knowledge and a traditional Chinese medicine health-preserving custom dictionary.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: the source data of the traditional Chinese medicine health-preserving knowledge graph comprises a middle hospital case report form, and the contents of the middle hospital case report form comprise: sex, age, occupation, ethnicity, marital, heart rate, blood pressure, respiration, first time of onset, course of illness, complaints, clinical manifestations, other medical history, brief medical history, examination sheets, pathology report, tongue pulse, western medicine diagnosis, traditional Chinese medicine differentiation, traditional Chinese medicine diagnosis, prescription, treatment regimen, maintenance regimen, diet, exercise, lifestyle, massage manipulation.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: the construction of the traditional Chinese medicine health-preserving knowledge graph comprises the following steps of: step S1, entity extraction, relation extraction and attribute extraction are carried out on the content of a hospital case report table, and an entity extraction result, a relation extraction result and an attribute extraction result are obtained; and S2, performing node creation and relationship creation according to the entity extraction result, the relationship extraction result and the attribute extraction result, and obtaining the traditional Chinese medicine health-preserving knowledge graph.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: and the corpus storage module is used for providing the corpus for the conversation generation module and the result generation module.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: the generation process of the corpus stored in the corpus storage module comprises the following steps: step A1, analyzing entities and entity relations in a traditional Chinese medicine health-preserving knowledge graph to obtain an entity relation graph; step A2, converting the entity relation graph into a directed graph; step A3, traversing the directed graph to obtain a path graph by taking each entity of the entity relation graph as a starting point; step A4, dividing and combining paths in the path diagram to obtain sub-paths; and step A5, corresponding the entity and entity relation in the traditional Chinese medicine health-preserving knowledge graph to each sub-path to obtain corpus.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance provided by the invention can also have the characteristics that the system further comprises: and the service side communication module is used for receiving the clinical information data sent by the user.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance can also have the following characteristics: the service side communication module comprises an Nginx proxy cluster server, a load balancer and a Web application cluster server.
In the embodiment, an Android mobile phone terminal is taken as a user terminal for example to explain the knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, wherein a plurality of user terminals are held by users.
It will be understood by those skilled in the art that, although the Android mobile phone terminal is taken as an example of the user terminal in the embodiment, the user terminal may be a user terminal such as an IOS mobile phone terminal or a PC terminal.
Fig. 1 is a block diagram of a knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance in an embodiment of the invention.
As shown in fig. 1, the knowledge-graph-based intelligent multi-round interaction system 100 for traditional Chinese medicine health maintenance may include: the system comprises an entity extraction module 10, an entity linking module 20, an entity query module 30, an extraction ordering module 40, a session generation module 50, a result generation module 60, a knowledge graph storage module 70, a corpus storage module 80 and a service side communication module 90.
The service-side communication module 90 may be configured to accept clinical information data sent by a user.
Fig. 2 is a hardware architecture diagram of a knowledge-based intelligent multi-round interaction system for health care of traditional Chinese medicine in an embodiment of the invention. Fig. 3 is a software architecture diagram of a knowledge-based intelligent multi-round interaction system for health care of traditional Chinese medicine in an embodiment of the invention.
As shown in fig. 2 and 3, the service-side communication module includes an nginnx proxy cluster server 91, a load balancer 92, and a Web application cluster server 93.
The service side communication module receives a data packet sent by a user through an API interface of a network layer, wherein a carrier of the user is an Android client, and the Android client sends a JSON character string to interact data with the system according to RESTFUL interface requirements and provides an interaction UI front-end interface for the user; the Spring Boot is responsible for integrating services such as Nginx and the like to a server; spring MVC is responsible for providing Model, view, controller interface to a server and providing restul interface service.
The entity extraction module 10 may be used to extract entities in clinical information entered by the user in each round of interactions.
The entity linking module 20 may be configured to perform reference resolution and entity disambiguation on the entity to obtain a processed entity.
Fig. 4 is a working logic diagram of an entity link module of the intelligent multi-round interaction system for traditional Chinese medical health maintenance based on a knowledge graph in the embodiment of the invention.
As shown in fig. 4, the entity linking module 20 includes front and rear Wen Bianma devices, an input text encoder, a candidate text encoder, an attention mechanism layer, and an output result layer. Among them, the front and rear Wen Bianma devices are responsible for extracting features of the front and rear. The front and back Wen Bianma devices, the input text encoder and the candidate text encoder are both two-way LSTM, taking the input text encoder as an example, the input text { w } 1 ，w 2 ，...，w n }(w n I.e. the nth word in w), i.e. at time f, forward LSTM derives
Reverse LSTM gives->
Output w at time f f Can be spliced->
And->
Obtained. The formula is as follows:
and finally, transferring the candidate vector c, the context vector s and the input text vector w calculated by using the attention mechanism to a reply layer to obtain an entity link result. The calculation formula is as follows:
s＝Attention(c，w)
c＝Attention(s，w)
in the embodiment, valuable features in multiple interactive sessions are extracted by using an attention mechanism layer, content features which are weakened or disappear due to forward transmission with time in the bidirectional LSTM are extracted, invalid features are filtered out, and finally effective entity links are obtained.
The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance is to fuse relevant information together in a knowledge-graph node entity discovery and link mode and the like, so that multi-round interaction is realized. In the session process of traditional Chinese medicine health care consultation, the problems of user consultation are related and have continuity, and in order to ensure the accuracy and the richness of the system reply content, the reply needs to be carried out by combining the interactive history information and the interactive knowledge graph.
Modeling of the traditional Chinese medicine health-preserving intelligent multi-round interaction system based on the knowledge graph is completed by adopting a point-to-point generation model, the knowledge graph, the interaction history and the current input of a user are modeled, and then decoding and replying are carried out according to modeling information. The interaction history, the knowledge graph and the generated replies are not in one-to-one mapping relation, so that correct selection of the knowledge graph and the interaction history and correct selection of the modeling mode can have a great influence on the effect of generating replies by the interaction system.
The entity query module 30 may be configured to obtain a plurality of triples related to the processed entity from a pre-stored healthcare knowledge graph of traditional Chinese medicine.
The knowledge graph storage module 70 may be configured to store a traditional Chinese medical health knowledge graph including a traditional Chinese medical health ontology knowledge and a traditional Chinese medical health custom dictionary.
The source data of the traditional Chinese medicine health care knowledge graph comprises a middle hospital case report form, and the contents of the middle hospital case report form comprise: sex, age, occupation, ethnicity, marital, heart rate, blood pressure, respiration, first time of onset, course of illness, complaints, clinical manifestations, other medical history, brief medical history, examination sheets, pathology report, tongue pulse, western medicine diagnosis, traditional Chinese medicine differentiation, traditional Chinese medicine diagnosis, prescription, treatment regimen, maintenance regimen, diet, exercise, lifestyle, massage manipulation.
Fig. 5 is a flowchart for constructing a knowledge graph of traditional Chinese medicine health care based on a knowledge graph intelligent multi-round interaction system of traditional Chinese medicine health care in an embodiment of the invention.
As shown in fig. 5, the construction of the traditional Chinese medicine health-preserving knowledge graph comprises the following steps:
step S1, entity extraction, relation extraction and attribute extraction are carried out on the content of a hospital case report table, and an entity extraction result, a relation extraction result and an attribute extraction result are obtained;
and S2, performing node creation and relationship creation according to the entity extraction result, the relationship extraction result and the attribute extraction result, and obtaining the traditional Chinese medicine health-preserving knowledge graph.
The extraction and sorting module 40 is configured to screen a plurality of relevant triples of clinical information that needs to be input again by a user, sort the triples according to a preset priority, obtain a triplet priority sequence, and determine a highest priority triplet.
In the process of intelligent multi-round interaction, the condition of reference resolution and entity omission occurs in the session, and the condition can cause great trouble to entity linkage, so the invention aims at entity linkage of entities identified in the context, and provides that the entity omission and reference resolution of sentences in the multi-round session are solved based on the entity linkage module 20 by combining text information of the context.
The method comprises the steps of firstly splicing triples related to entities identified in the context into candidate texts, then splicing candidate vectors c output by a candidate text encoder, context vectors s output by the context encoder and text vectors w output by an input text encoder by using a full-connection layer, and then carrying out linear change, and finally calculating an output result reply by a softmax function, wherein the formula is as follows:
reply＝softmax(F·[c；s；w]
f in the formula is the full connection layer parameter.
The session generation module 50 may be configured to generate questions according to the highest priority triplet and the pre-stored traditional Chinese medical health knowledge graph to ask the user for the next round.
Fig. 6 is a working logic diagram of a session generation module of the intelligent multi-round interaction system for traditional Chinese medical health maintenance based on a knowledge graph in the embodiment of the invention.
As shown in fig. 6, the present embodiment proposes that text information of a sentence is modeled using one encoder, and front and rear text information of a sentence composition is modeled using another encoder, and this model is generated based on the memory capacity of the entity linking module 20. The encoder used by the session generation module 50 based on the entity linking module 20 is composed of a unidirectional GRU and a bidirectional GRU, the encoder used by the text information before and after the sentence is composed of a unidirectional GRU, and the encoder used by the text information of the sentence is a bidirectional GRU.
One context is composed of { s } 1 ,s 2 ,...,s n Composition, s n Is in the context of the nth sentence, s n ＝{w n1 ，w 21 ，...，w nn }，w nn Is s n The Encoder used by Word Encoder is a bi-directional GRU that will every sentence { s }, in the context 1 ,s 2 ,...,s n Coding into sentence vectors
The Encoder used by the Context Encoder is a unidirectional GRU that uses sentence vectors +.>
Encoding into a context vector t, and calculating the context vector t as follows:
t＝s n ＝GRU(s n ，s n-1 )
the result generation module 60 may be configured to generate a health care advice result according to clinical information input by the user a plurality of times and a pre-stored traditional Chinese medicine health care knowledge graph.
Fig. 7 is a flowchart of generating a corpus in a corpus storage module of the knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medical health maintenance in an embodiment of the invention.
The generation process of the corpus stored in the corpus storage module 80 as in fig. 7 includes the steps of:
step A1, analyzing entities and entity relations in a traditional Chinese medicine health-preserving knowledge graph to obtain an entity relation graph;
step A2, converting the entity relation graph into a directed graph;
step A3, traversing the directed graph to obtain a path graph by taking each entity of the entity relation graph as a starting point;
step A4, dividing and combining paths in the path diagram to obtain sub-paths;
and step A5, corresponding the entity and entity relation in the traditional Chinese medicine health-preserving knowledge graph to each sub-path to obtain corpus.
Fig. 8 is a logic diagram of operation of the intelligent multi-round interaction system for traditional Chinese medicine health maintenance based on a knowledge graph in the embodiment of the invention.
As shown in fig. 8, the knowledge graph-based intelligent interaction system for traditional Chinese medicine health care carries out named entity recognition on the current conversation statement and the historical conversation statement of the traditional Chinese medicine health care problem consulted by the user to obtain an entity list related to the user problem, carries out reference resolution and entity disambiguation by using the entity link model based on the memory sequence, extracts the triplet information related to the entity from the traditional Chinese medicine health care knowledge graph, transmits the triplet information to the conversation system, and generates a reply transmitted to the user by using the generation model based on the memory sequence modeling.
Effects and effects of the examples
According to the knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, the interaction system has a memory capability, so that the content interacted with a user can be actively associated with the interaction system. After the user inputs the clinical manifestation to the system, the system actively asks the user about the related complaint manifestation according to the characteristics of the clinical manifestation input by the user, the user inputs the related feedback content to the system according to the question asked by the system, and the intelligent interaction system finally gives the user a traditional Chinese medicine health maintenance suggestion with higher accuracy after a plurality of interactions with the user by using the mode. Moreover, the interactive system of the embodiment adopts the interactive mode of multi-round dialogue, so that the experience of the terminal user and the conclusion accuracy of the traditional Chinese medicine health care consultation questioning and answering are higher than those of the normal single-round interactive questioning and answering system. In addition, the embodiment aims at entity link of the entities identified in the context, and provides entity omission and reference resolution of sentences in multiple conversations based on a memory sequence entity link model by combining text information of the context.
The above embodiments are preferred examples of the present invention, and are not intended to limit the scope of the present invention.
Claims (10)
1. A traditional Chinese medicine health preserving intelligent multi-round interaction system based on a knowledge graph is characterized by comprising:
the entity extraction module is used for extracting entities in clinical information input by a user in each round of interaction;
the entity link module is used for carrying out reference resolution and entity disambiguation on the entity to obtain the processed entity;
the entity query module is used for acquiring a plurality of triples related to the processed entity from a prestored traditional Chinese medicine health-preserving knowledge graph;
the extraction and sorting module is used for screening a plurality of related triples of the clinical information which are required to be input again by the user, sorting the related triples according to preset priorities to obtain a triplet priority sequence and determining the highest priority triplet;
the session generation module is used for generating a problem according to the highest priority triplet and the prestored traditional Chinese medicine health maintenance knowledge graph so as to ask the user for the next round; and
a result generation module for generating health care suggestion results according to the clinical information input by the user for a plurality of times and the prestored traditional Chinese medicine health care knowledge graph,
the entity link module comprises a front Wen Bianma device, a rear Wen Bianma device, an input text encoder, a candidate text encoder, an attention mechanism layer and an output result layer.
2. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which is characterized in that:
wherein the front and rear Wen Bianma are used to extract features of the entity in two adjacent rounds of interaction.
3. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which is characterized in that:
wherein the front and rear Wen Bianma encoders, the input text encoder, and the candidate text encoders each comprise a two-way long and short term memory neural network.
4. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance according to claim 1, further comprising:
the knowledge-graph storage module is used for storing the knowledge-graph,
wherein the knowledge graph storage module is used for storing the traditional Chinese medicine health-preserving knowledge graph,
the traditional Chinese medicine health knowledge graph comprises traditional Chinese medicine health ontology knowledge and a traditional Chinese medicine health custom dictionary.
5. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which is characterized in that:
wherein the source data of the traditional Chinese medicine health preserving knowledge graph comprises a case report form of a middle hospital,
the contents of the middle hospital case report form include: sex, age, occupation, ethnicity, marital, heart rate, blood pressure, respiration, first time of onset, course of illness, complaints, clinical manifestations, other medical history, brief medical history, examination sheets, pathology report, tongue pulse, western medicine diagnosis, traditional Chinese medicine differentiation, traditional Chinese medicine diagnosis, prescription, treatment regimen, maintenance regimen, diet, exercise, lifestyle, massage manipulation.
6. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance of claim 5, wherein the intelligent multi-round interaction system is characterized in that:
the construction of the traditional Chinese medicine health-preserving knowledge graph comprises the following steps of:
step S1, entity extraction, relation extraction and attribute extraction are carried out on the content of the middle hospital case report table, and an entity extraction result, a relation extraction result and an attribute extraction result are obtained;
and S2, performing node creation and relationship creation according to the entity extraction result, the relationship extraction result and the attribute extraction result, and obtaining the traditional Chinese medicine health-preserving knowledge graph.
7. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance according to claim 1, further comprising:
a corpus storage module, which is used for storing the corpus,
the corpus storage module is used for providing corpus for the session generation module and the result generation module.
8. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance of claim 7, wherein the intelligent multi-round interaction system is characterized in that:
the generation process of the corpus stored in the corpus storage module comprises the following steps:
step A1, analyzing the entity and entity relation in the traditional Chinese medicine health-preserving knowledge graph to obtain an entity relation graph;
a2, converting the entity relation graph into a directed graph;
step A3, traversing the directed graph to obtain a path graph by taking each entity of the entity relation graph as a starting point;
step A4, dividing and combining paths in the path diagram to obtain sub paths;
and step A5, the entity and the entity relationship in the traditional Chinese medicine health-preserving knowledge graph are corresponding to each sub-path, and the corpus is obtained.
9. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance according to claim 1, further comprising:
the service-side communication module is configured to communicate with the service-side communication module,
the service side communication module is used for receiving the clinical information data sent by the user.
10. The knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance, which is characterized in that:
the service side communication module comprises an Nginx proxy cluster server, a load balancer and a Web application cluster server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111369070.0A CN114090789B (en) | 2021-11-12 | 2021-11-12 | Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111369070.0A CN114090789B (en) | 2021-11-12 | 2021-11-12 | Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114090789A CN114090789A (en) | 2022-02-25 |
| CN114090789B true CN114090789B (en) | 2023-04-21 |
Family
ID=80301686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111369070.0A Active CN114090789B (en) | 2021-11-12 | 2021-11-12 | Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114090789B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116504414B (en) * | 2023-05-19 | 2024-03-22 | 北京百度网讯科技有限公司 | Medical data query method, device, electronic equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8594996B2 (en) * | 2007-10-17 | 2013-11-26 | Evri Inc. | NLP-based entity recognition and disambiguation |
| CN110377715A (en) * | 2019-07-23 | 2019-10-25 | 天津汇智星源信息技术有限公司 | Reasoning type accurate intelligent answering method based on legal knowledge map |
| CN113254659A (en) * | 2021-02-04 | 2021-08-13 | 天津德尔塔科技有限公司 | File studying and judging method and system based on knowledge graph technology |
| CN113590783B (en) * | 2021-07-28 | 2023-10-03 | 复旦大学 | Intelligent question and answer system for traditional Chinese medicine health care based on NLP natural language processing |
-
2021
- 2021-11-12 CN CN202111369070.0A patent/CN114090789B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114090789A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020201883B2 (en) | Call center system having reduced communication latency | |
| US20210287800A1 (en) | Ai supported personalized, natural language-based patient interface for medical-bot | |
| CN112271001B (en) | Medical consultation dialogue system and method applying heterogeneous graph neural network | |
| Khadija et al. | AI-powered health chatbots: toward a general architecture | |
| US11616740B2 (en) | Invoking chatbot in online communication session | |
| Kobayashi et al. | Communication robot for elderly based on robotic process automation | |
| CN110476169A (en) | Provide emotional care during the session | |
| CN112287232A (en) | Method and device for generating recommendation information | |
| Christopherjames et al. | Natural language processing based human assistive health conversational agent for multi-users | |
| CN112100406B (en) | Data processing method, device, equipment and medium | |
| US20250272556A1 (en) | Data processing method and apparatus, and electronic device | |
| WO2023029501A1 (en) | Smart interrogation method and apparatus, electronic device, and storage medium | |
| CN110993093A (en) | Deep learning-based ophthalmic pre-interrogation method and device | |
| CN112417117B (en) | Method, device and equipment for generating conversation message | |
| Inupakutika et al. | Integration of NLP and speech-to-text applications with chatbots | |
| WO2022041015A1 (en) | Neural network model optimisation method and apparatus | |
| CN117909463A (en) | Business scenario dialogue methods and related products | |
| Hossain et al. | Mr. dr. health-assistant chatbot | |
| JP6030659B2 (en) | Mental health care support device, system, method and program | |
| CN114090789B (en) | Knowledge-graph-based intelligent multi-round interaction system for traditional Chinese medicine health maintenance | |
| Nigam et al. | Self-diagnosis in healthcare systems using AI chatbots | |
| CN110456920A (en) | Semantic analysis-based content recommendation method and device | |
| CN110085316A (en) | A kind of hypertension question answering system and its system method for building up based on deep learning | |
| Roma et al. | A BERT-based approach to intent recognition | |
| Tan et al. | AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts |
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 |