CN105725991A - Health monitoring system based on intelligent agent - Google Patents
Health monitoring system based on intelligent agent Download PDFInfo
- Publication number
- CN105725991A CN105725991A CN201610055061.7A CN201610055061A CN105725991A CN 105725991 A CN105725991 A CN 105725991A CN 201610055061 A CN201610055061 A CN 201610055061A CN 105725991 A CN105725991 A CN 105725991A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- module
- data
- monitoring system
- health monitoring
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
Abstract
The invention relates to a health monitoring system, in particular to a health monitoring system based on an intelligent agent. The problem that an existing monitoring system has difficulty in adapting to user requirements changing continuously and also has difficulty in combining information in all fields to monitor users in an environment space is solved. A data collecting module is used for collecting data of a temperature sensor, a pulse sensor and a blood pressure sensor and transmitting the collected data to an environment agent module; the environment agent module is used for processing the data collected by the data collecting module in a unified mode and transmitting the processed data serving as factual knowledge to a user agent module; the user agent module is used for reasoning process knowledge and rule knowledge according to received factual knowledge and knowledge base information in the user agent module and transmitting a reasoning result to the users through a network. A multi-intelligent-agent technology is adopted for conducting monitoring nursing on the users. The health monitoring system has certain universality and practicability to provide service for a monitoring task better.
Description
Technical field
The present invention relates to health monitoring system, be specifically related to the health monitoring system of a kind of active perception based on intelligent agent technology.
Background technology
Monitoring tasks in areas (as, Smart Home, health supervision etc.), traditional method simply utilizes wireless sensor network to carry out long distance monitoring often, system is difficult in adapt to the user's request being continually changing, it is also difficult in conjunction with every field information is omnibearing, user in environment space is guarded.In order to provide a new solution to health supervision problem, it is necessary to build the service mode of a kind of active perception formula, assist guardian to realize the long-range monitoring administration to user.
In order to provide the service mode of the dynamically change of a kind of active perception, it is necessary for tackling the user's request being continually changing and each different types of information (e.g., the information etc. of polytype sensor information, dissimilar user) at any time.Therefore, in order to adapt to the fusion changing rapidly and realizing much information of user intention, present invention application intelligent agent technology, internal each agency, carry out characterizing and making inferences with unified form by knowledge, to reach the purpose of multiple realm information interconnection, finally provide the user service.
Knowledge token and reasoning are one important foundations of artificial intelligence field.Usually there is due to different field problem different attributes and feature, thus expressing for knowledge method is also not quite similar.At present, knowledge token method, from the contact between the logic of knowledge, structure and knowledge, mainly has: predicate logic method, framework method, Object-Oriented Method, semantic network etc..
For same knowledge, generally can be indicated by multiple method, but generally all there is due to domain knowledge difference, thus the effect of each method for expressing is also different.In existing knowledge token method, it is difficult to this dynamic change of health supervision, the complication system that relates to many-sided domain knowledge characterizes.
Summary of the invention
The present invention solves that existing monitor system exists the user's request being difficult in adapt to be continually changing, it is also difficult in conjunction with the omnibearing problem that user in environment space is guarded of every field information, it is provided that a kind of health monitoring system based on intelligent agent.
Based on the health monitoring system of intelligent agent, this system includes data acquisition module, dynamic tier module and user agent module；
Described data acquisition module is used for collecting temperature sensor, pulse transducer, pressure transducer data, and is sent to dynamic tier module by gathering the data obtained；
Described dynamic tier module by data collecting module collected to data be uniformly processed, and using process after data be sent to user agent module as fact knowledge；
Described user agent module carries out the reasoning of procedural knowledge and rule knowledge according to the fact that receive knowledge and the knowledge base information within described user agent module, and by network, the reasoning results is sent to user.
Beneficial effects of the present invention: the present invention adopts Multi-Agent technology that user is monitored nursing.In order to set up the health supervision pattern of a kind of active perception formula, need inside intelligent agent, set up the machine-processed and a set of general reliable inference method of a set of simple and practical representation of knowledge, it is made to have certain universality and practicality, thus better providing service for monitoring task.
The advantage adopting above-mentioned inference method is:
(1) owing to based in the knowledge token method of framework, the groove for framework with the addition of additional process, automatically triggers and fills out groove action in framework, accelerates the speed of knowledge reasoning.
(2) for each domain knowledge framework, reasoning all carries out at its lower portion, rather than carry out under unified complete rule-based knowledge base, so, be conducive to improving the speed of coupling, decrease the number of rule in domain knowledge base simultaneously, enhance Reasoning Efficiency and be conducive to the concordance of knowledge base.
Accompanying drawing explanation
Fig. 1 is the high-level schematic functional block diagram of the health monitoring system based on intelligent agent of the present invention；
Fig. 2 is of the present invention based on the process schematic of knowledge reasoning in the health monitoring system of intelligent agent；
Fig. 3 is of the present invention based on the theory structure diagram of user agent module internal reasoning in the health monitoring system of intelligent agent；
Fig. 4 is of the present invention based on the schematic diagram of communication module in the health monitoring system of intelligent agent；
Fig. 5 is of the present invention based on the flow chart of knowledge reasoning in the health monitoring system of intelligent agent；
Fig. 6 is the flow chart of the health monitoring system based on intelligent agent of the present invention.
Detailed description of the invention
Detailed description of the invention one, in conjunction with Fig. 1 to Fig. 6, present embodiment being described, based on the health monitoring system of intelligent agent, this system includes data acquisition module, dynamic tier module and user agent module；
Described data acquisition module is used for collecting temperature sensor, pulse transducer, pressure transducer data, and is sent to dynamic tier module by gathering the data obtained；Described dynamic tier module by data collecting module collected to data be uniformly processed, and using process after data be sent to user agent module as fact knowledge；Described user agent module carries out the reasoning of procedural knowledge and rule knowledge according to the fact that receive knowledge and the knowledge base information within described user agent module, and by network, the reasoning results is sent to user.
Reasoning process concrete in present embodiment is, inference machine, according to the fact that communication module sends knowledge, compares one by one with the information in knowledge base, if identical with the information in knowledge base, then more next, if it is different, then more new knowledge base information.Described user agent module includes user agent, old man agency and doctor agency；According to the fact that each agency is internal knowledge, make inferences, it is achieved process the wish of old man, guardian and doctor.
Detailed description of the invention two, present embodiment being described in conjunction with Fig. 1 to Fig. 6, present embodiment is the embodiment of detailed description of the invention one:
In present embodiment, based on bottom sensor equipment, utilize multi-agent technology, it is achieved that many agengs service platform of integrated old man agency, doctor agency, monitoring agency and dynamic tier, provide respective service for service object.
Intelligent agent i.e. ageng, be one and can spontaneously realize function and the software entity being associated with related proxy in certain circumstances.Continuously, spontaneous requirement derives from the change of environment, it is desirable to the demand of user can be responded in real time in the way of flexible, intelligent by agency in the guiding of nobody with under interfering.
The knowledge of the fact that described in present embodiment: about the knowledge of some facts, such as the classification of things, attribute, scientific fact, objective fact etc..Emphasize the static state of knowledge, namely describe attribute and the mutual relation thereof of things.As, the current body temperature of old man is 37.5 degree and is a fact knowledge.
Procedural knowledge: procedural knowledge is the knowledge about " what if ".It emphasizes the dynamic of knowledge, namely represents that reasoning and search relevant fact etc. use the process of knowledge.The solution procedure of its relevant issues, craftsmenship knowledge, tell and how to make something.
Rule knowledge: be generally and there is causal knowledge.As, if current time is the morning, the behavior wish of old man is for trotting out.
In present embodiment, relate to all kinds of knowledge such as the fact, process and rule, it is necessary to different types of knowledge is adopted a kind of unified representation.Namely adopt the form of expression of framework, fact knowledge, procedural knowledge and rule knowledge are all fused in framework, formed and there is knowledge representation method satisfactory texture, complete.Adopting the knowledge representation method based on framework in present embodiment, basic framework is made up of three parts:
One, regular troughs (Slot): the place of framework storage information is mainly groove (Slot), and each groove can be made up of several sides (facet) again.One groove represents an attribute of object, and a side is for describing an aspect of respective attributes.The value that groove and side have is called slot value and side value.At one with, in the knowledge system of frame representation, generally all containing multiple framework, in order to distinguish different slots in different frameworks and a framework, not ipsilateral, it is necessary to give different names respectively, be called frame name, slot name and facet name.
In general slot value can have following several types:
Occurrence, this value is pressed practical situation and is given；
Process values, this value is a calculating process, and it utilizes other slot values of this framework, is calculated the occurrence (such as a certain method) obtained by given calculating process；
Another frame name, when slot value is another frame name, just constitutes framework and calls, material is thus formed a framework chain, and relevant frame aggregate is got up and just formed frame system.
The all right additional process of the groove of framework, is called process adnexa, including subprogram and certain reasoning process.Conventional additional process has:
If-needed: once affiliated slot value will be used (inquiry), then start additional process below；
If-added: once affiliated slot value will be assigned (amendment), then start additional process below；
Two, method groove (Methods): method groove is used for the method depositing in object, and it is a kind of special dynamic process in framework.The structure of method is defined by method name, method local variable and procedure body is constituted.After method is triggered, from the message sent, filter out required information for method procedure body, then perform procedure body.
Three, rule groove (Rules): rule groove is used for depositing production rule collection, each rule set is placed in rule groove as a value.Each rule leaves some rules concentratedly.
The static attribute etc. of framework is represented by present embodiment by regular troughs.Each regular troughs is indicated with " facet name side value " form, meanwhile, for each side value additional two processes, i.e. if-needed and if-added.Namely, when side value is used and is assigned, corresponding method in framework is triggered respectively.Here, additional process is option.
For rule groove, we use the form of " rule number, rule body " to be indicated；For method groove, we use the form of " Method method name " to be indicated.The definition procedure of wherein concrete method completes outside framework, according to Method method name, local variable definition, procedure body mode express.
The above-mentioned advantage based on the knowledge representation method of framework is adopted to be: frame knowledge representation method adopts the unified structure of " slot name facet name side value ", short and sweet, it is easy to understanding, meets the thinking habit of people.Multiple single knowledge representation method (rule, framework and process) is fused into a framework by frame knowledge representation method, have expressed all kinds of static state such as the fact, process and rule and dynamic and knowledge fully, compensate for the defect of single knowledge token method.
Present embodiment adopts the knowledge representation method based on a framework unification, pervasive, integrates and the representation of knowledge form of unified different agencies with this.Thus knowledge can be showed by certain pattern and store in computer, but to enable a computer to the knowledge using the knowledge grasped to infer the unknown, it is necessary to knowledge is made inferences.
Reasoning refers to the process releasing conclusion according to certain rule from the existing fact.Adopt the mode of a kind of forward reasoning based on data-driven herein.Need to accept from outside the agency of message, fill the slot value of its knowledge framework initially with the mode of method call (by the additional process of groove)；Then, reasoning process just carries out at lower portion, traversal rule groove, finds the rule matched, and makes inferences and produce corresponding the reasoning results.Reasoning process is as shown in Figure 5.
Specifically comprise the following steps that
(1) oneself knowledge initial user provided sends into knowledge base KB (KnowledgeBase)；
(2) according to the known fact in KB, trigger the additional process of groove, spontaneously carry out slot value filling；
(3) scan the Rlue keyword in the knowledge frame in corresponding field, check the knowledge wherein whether having applicable (can match with knowledge in the IF groove of Rule), if having, then turning (4), otherwise turning (6)；
(4) knowledge (i.e. knowledge in the Then groove of Rule) that is suitable for all of in Rule is all elected, constitute result set RS (ResultSet) applicatory, turn (5)；
(5) if RS is not empty, then RS is exported as final result；If RS is empty, then turn (6)；
(6) the fact that ask the user whether to supplement new further, if having, then supplement new fact, then turn (2)；Otherwise represent and can not seek solution, unsuccessfully exit.
Described communication module: according to the form of the communication information of agreement, outwardly sends message or accepts the information that external world's transmission comes.Wherein, the structure of communication information, in conjunction with Fig. 4, it is described as follows.
(1) message header contains system-level the characteristic information, such as the transmission time etc. of message.
(2) sender of the message: sender of the message identifies, such as system, dynamic tier, old man agency etc..
(3) message recipient: message recipient identifies, as old man acts on behalf of, guards agency, doctor agency etc..
(4) type of message: the mark of type of message, if this message is class signal message or informative messages.
(5) message body: the content in message body is exactly the data that message to be transmitted.According to knowledge frame described herein, we arrange, and message body is transmitted according to the form of " slot name facet name side value ".
Knowledge base described in present embodiment: store the knowledge and rule that need in knowledge processing procedure.At present, database technology application is very extensive, and data base interface is powerful, and the management for data base is also very convenient.Thus, select data base that the knowledge in specialist system is stored and there is powerful advantage.Chat on comprehensive, for the storage of knowledge, it is possible to the mode of employing data base, and the commercial product of comparative maturity can be selected, such as the MySQL database of Oracle company.
Use all kinds of knowledge in knowledge base to make inferences, obtain rational the reasoning results.
Based on internal module and the communication information of agency, the Booting sequence of whole system is illustrated.The start-up course of system is illustrated in fig. 6 shown below.It is described as follows:
(1) user's input: user is inputted by man machine interface, system sends the message of task start to each agency, starts whole system；
(2) request of data: user agent (old man agency/monitoring agency/doctor agency) sends request of data, the data of request dynamic tier by communication module to dynamic tier；
(3) reasoning monitoring: under the scheduling of reasoning module, make inferences according to all types of knowledge in knowledge base: if obtaining corresponding the reasoning results, then turn to result to export；Without obtaining the reasoning results, then continue the data please look for novelty to dynamic tier.
(4) result output: by final the reasoning results output.Result may finally be sent to user mobile phone via mobile network.
Claims (3)
1. based on the health monitoring system of intelligent agent, it is characterized in that, this system includes data acquisition module, dynamic tier module and user agent module；
Described data acquisition module is used for collecting temperature sensor, pulse transducer, pressure transducer data, and is sent to dynamic tier module by gathering the data obtained；
Described dynamic tier module by data collecting module collected to data be uniformly processed, and using process after data be sent to user agent module as fact knowledge；
Described user agent module carries out the reasoning of procedural knowledge and rule knowledge according to the fact that receive knowledge and the knowledge base information within described user agent module, and by network, the reasoning results is sent to user.
2. the health monitoring system based on intelligent agent according to claim 1, it is characterized in that, concrete reasoning process is, inference machine is according to the fact that communication module sends knowledge, compare one by one with the information in knowledge base, if identical with the information in knowledge base, then more next, if it is different, then more new knowledge base information.
3. the health monitoring system based on intelligent agent according to claim 1, it is characterised in that described user agent module includes user agent, old man agency and doctor agency；According to the fact that each agency is internal knowledge, make inferences, it is achieved process the wish of old man, guardian and doctor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610055061.7A CN105725991B (en) | 2016-01-27 | 2016-01-27 | health monitoring system based on intelligent agent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610055061.7A CN105725991B (en) | 2016-01-27 | 2016-01-27 | health monitoring system based on intelligent agent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105725991A true CN105725991A (en) | 2016-07-06 |
| CN105725991B CN105725991B (en) | 2019-01-01 |
Family
ID=56246641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610055061.7A Expired - Fee Related CN105725991B (en) | 2016-01-27 | 2016-01-27 | health monitoring system based on intelligent agent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105725991B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885010A (en) * | 2019-03-20 | 2019-06-14 | 中南大学 | The health combined based on multi-Agent and Internet of Things sees maintaining method, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1480884A (en) * | 2003-07-16 | 2004-03-10 | 中南大学 | Swarm intelligence man-machine decision method based on Internet structure |
| US20080103370A1 (en) * | 2006-10-24 | 2008-05-01 | Kent Dicks | Systems and methods for medical data interchange activation |
| CN102090930B (en) * | 2009-12-10 | 2013-01-09 | 中兴保全股份有限公司 | Home healthcare service management device |
| US20150157278A1 (en) * | 2013-12-10 | 2015-06-11 | Kabushiki Kaisha Toshiba | Electronic device, method, and storage medium |
-
2016
- 2016-01-27 CN CN201610055061.7A patent/CN105725991B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1480884A (en) * | 2003-07-16 | 2004-03-10 | 中南大学 | Swarm intelligence man-machine decision method based on Internet structure |
| US20080103370A1 (en) * | 2006-10-24 | 2008-05-01 | Kent Dicks | Systems and methods for medical data interchange activation |
| CN102090930B (en) * | 2009-12-10 | 2013-01-09 | 中兴保全股份有限公司 | Home healthcare service management device |
| US20150157278A1 (en) * | 2013-12-10 | 2015-06-11 | Kabushiki Kaisha Toshiba | Electronic device, method, and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| HAIJUN GU ET AL.: "The Knowledge representation and Reasoning for Agents Based On the Elderly Monitoring,", 《APPLIED MECHANICS AND MATERIALS》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885010A (en) * | 2019-03-20 | 2019-06-14 | 中南大学 | The health combined based on multi-Agent and Internet of Things sees maintaining method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105725991B (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3170111B1 (en) | M2m ontology management and semantics interoperability | |
| Rahman et al. | A comprehensive survey on semantic interoperability for Internet of Things: State‐of‐the‐art and research challenges | |
| De Maio et al. | A knowledge-based framework for emergency DSS | |
| Stoilos et al. | Reasoning with the fuzzy description logic f-: Theory, practice and applications | |
| CN110266677A (en) | A kind of edge calculations intelligent gateway and implementation method towards industry manufacture | |
| Chen et al. | Semantic smart homes: towards knowledge rich assisted living environments | |
| Cristea et al. | Context-aware environments for the internet of things | |
| CN106446256A (en) | Real-time industrial production information sensation system based on context calculation | |
| Lasierra et al. | An autonomic ontology-based approach to manage information in home-based scenarios: From theory to practice | |
| KR20200124267A (en) | Semantic actions and inference support through distributed semantic data | |
| Aly et al. | Big data on internet of things: applications, architecture, technologies, techniques, and future directions | |
| CN108804679A (en) | A kind of operation system user's operation monitoring data method for visualizing | |
| Vandana et al. | Semantic ontology based IoT-resource description | |
| Zhong-Jun et al. | A method of meta-context ontology modeling and uncertainty reasoning in swot | |
| Fouchal et al. | Distributed backtracking algorithm based on tree decomposition over wireless sensor networks | |
| CN113678121A (en) | Automatic generation of tagged data in IOT systems | |
| Achouri et al. | Smart fog computing for efficient situations management in smart health environments | |
| CN105725991A (en) | Health monitoring system based on intelligent agent | |
| Ali | A social Internet of Things application architecture: applying semantic web technologies for achieving interoperability and automation between the cyber, physical and social worlds | |
| Triboan et al. | Fuzzy-based fine-grained human activity recognition within smart environments | |
| Krishnamoorthy et al. | Representing and managing the context of a situation | |
| CN115250237B (en) | Rule engine method and device for Internet of things | |
| Akanbi et al. | Semantic interoperability middleware architecture for heterogeneous environmental data sources | |
| Hu et al. | A Novel Context-aware Modeling and Reasoning Method based on OWL. | |
| Amja et al. | Modeling and reasoning in context-aware systems based on relational concept analysis and description logic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190101 Termination date: 20210127 |