CN108320798A - Illness result generation method and device - Google Patents
Illness result generation method and device Download PDFInfo
- Publication number
- CN108320798A CN108320798A CN201810110202.XA CN201810110202A CN108320798A CN 108320798 A CN108320798 A CN 108320798A CN 201810110202 A CN201810110202 A CN 201810110202A CN 108320798 A CN108320798 A CN 108320798A
- Authority
- CN
- China
- Prior art keywords
- illness
- doubtful
- state
- result
- keywords
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention provides a kind of illness result generation method and devices, are related to medical field.The illness result generation method finds out multiple doubtful illness results by more associated history illness results of set state of an illness keyword sample that the non-linear illness result trained according to multiple state of an illness keywords, in advance searches model, multiple state of an illness keyword training samples that pre-established history illness library includes and multiple state of an illness keyword training samples are respectively formed first with device；Then multiple state of an illness keywords according to each corresponding presetting score weight rule of doubtful illness result, input calculate multiple doubtful degree score values；The highest doubtful illness result of doubtful degree score value is finally extracted as current illness result.The illness result generation method with device is easy to operate, rate of correct diagnosis is high, saves the time and cost of labor, user experience is high.
Description
Technical field
The present invention relates to medical fields, in particular to a kind of illness result generation method and device.
Background technology
Treatment typically refers to the process for intervening or changing specific health state, to release the ailing activity carried out.Currently
In life, people usually require to reach in illness that then specified hospital stands in the queue to register and then doctor inquires and examines
It is disconnected, however the time energy of doctor is limited, single doctor can not understand thoroughly the knowledge and experience of all diseases；First-class doctor's door
The mistaken diagnosis examined and it is plain examine rate 60% or more, rate of correct diagnosis is relatively low；Even many doctors to the understanding of single disease even
The patient of the disease might as well be suffered from, and change the place of examination during actual therapeutic, hospital guide, the consultation of doctors are intended to professional's participation, consumption
When, it is of high cost, take a lot of trouble.
Invention content
In view of this, the embodiment of the present invention is designed to provide a kind of illness result generation method and device, to improve
Above-mentioned problem.
In a first aspect, an embodiment of the present invention provides a kind of illness result generation method, the illness result generation method
Including：
Multiple state of an illness keywords of the characterization disease symptoms information of input are obtained in response to the operation of user；
The non-linear illness result trained according to multiple state of an illness keywords, in advance searches model, pre-established history illness
More set state of an illness that the multiple state of an illness keyword training samples and multiple state of an illness keyword training samples that library includes are respectively formed are closed
The associated history illness result of keyword sample finds out multiple doubtful illness results；
According to the corresponding presetting score weight rule of each doubtful illness result, multiple state of an illness keyword meters of input
Calculate multiple doubtful degree score values；
The highest doubtful illness result of doubtful degree score value is extracted as current illness result.
Second aspect, the embodiment of the present invention additionally provide a kind of illness result generating means, and the illness result generates dress
Set including：
Information receiving unit obtains multiple state of an illness of the characterization disease symptoms information of input for the operation in response to user
Keyword；
Searching unit, the non-linear illness result for training according to multiple state of an illness keywords, in advance search model, built in advance
The multiple state of an illness keyword training samples and multiple state of an illness keyword training samples that vertical history illness library includes are respectively formed
More associated history illness results of set state of an illness keyword sample find out multiple doubtful illness results；
Computing unit, for according to the corresponding presetting score weight rule of each doubtful illness result, input it is more
A state of an illness keyword calculates multiple doubtful degree score values；
As a result generation unit, for extracting the highest doubtful illness result of doubtful degree score value as current illness result.
Compared with prior art, illness result generation method provided by the invention and device, first by according to multiple diseases
Multiple state of an illness that feelings keyword, the non-linear illness result lookup model of training in advance, pre-established history illness library include are closed
The associated history of more set state of an illness keyword samples that keyword training sample and multiple state of an illness keyword training samples are respectively formed
Illness result finds out multiple doubtful illness results；Then according to each corresponding presetting score weight of doubtful illness result
Rule, the multiple state of an illness keywords inputted calculate multiple doubtful degree score values；It is highest doubtful finally to extract doubtful degree score value
Like illness result as current illness result.The illness result generation method with device is easy to operate, rate of correct diagnosis is high, save
Time and cost of labor, user experience are high.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.Therefore, below to the reality of the present invention provided in the accompanying drawings
The detailed description for applying example is not intended to limit the range of claimed invention, but is merely representative of the selected implementation of the present invention
Example.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Fig. 1 is the interaction schematic diagram of server provided in an embodiment of the present invention and client；
Fig. 2 is the structure diagram of server provided in an embodiment of the present invention；
Fig. 3 is the flow chart of illness result generation method provided in an embodiment of the present invention；
Fig. 4 is the high-level schematic functional block diagram of illness result generating means provided in an embodiment of the present invention.
Icon：100- clients；200- servers；400- illness result generating means；101- processors；102- is stored
Device；103- storage controls；104- Peripheral Interfaces；301- information receiving units；302- searching units；303- computing units；
304- judging units；305- information transmitting units；306- result generation units.
Specific implementation mode
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, the detailed description of the embodiment of the present invention to providing in the accompanying drawings is not intended to limit claimed invention below
Range, but it is merely representative of the selected embodiment of the present invention.Based on the embodiment of the present invention, those skilled in the art are not doing
The every other embodiment obtained under the premise of going out creative work, shall fall within the protection scope of the present invention.
The illness result generation method that present pre-ferred embodiments are provided can be applied to application as shown in Figure 1 with device
In environment.As shown in Figure 1, client 100, server 200 are located in network, and by the network, client 100 and server
200 carry out data interaction.In the embodiment of the present invention, at least one application program is installed in client 100
(Application, APP), it is corresponding with server 200, provide service to the user.The server 200 can be, but unlimited
In network server, database server, cloud server etc..The client 100 may be, but not limited to, smart mobile phone,
PC (personal computer, PC), tablet computer, personal digital assistant (personal digital
Assistant, PDA), mobile internet surfing equipment (mobile Internet device, MID) etc..The operating system of client 100
It may be, but not limited to, Android (Android) system, IOS (iPhone operating system) system, Windows
Phone systems, Windows systems etc..
Fig. 2 shows a kind of structure diagrams for the server 200 that can be applied in the embodiment of the present invention.Server 200 wraps
Include illness result generating means 400, memory 102, storage control 103, processor 101 and Peripheral Interface 104.
Memory 102, storage control 103 and processor 101, each element directly or indirectly electrically connect between each other
It connects, to realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or signal between each other
Line, which is realized, to be electrically connected.Illness result generating means 400 include it is at least one can be in the form of software or firmware (firmware)
The software function for being stored in memory 102 or being solidificated in the operating system (operating system, OS) of client 100
Module.Processor 101 is for executing the executable module stored in memory 102, for example, illness result generating means 400 are wrapped
The software function module or computer program included.
Wherein, memory 102 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory 102Read Only Memory, ROM), programmable read only memory (Programmable Read-
Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory,
EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory,
EEPROM) etc..Wherein, memory 102 is for storing program, and processor 101 executes program after receiving and executing instruction, preceding
It states the method performed by the server-side that the stream process that any embodiment of the embodiment of the present invention discloses defines and can be applied to processor
In 101, or realized by processor 101.
Processor 101 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 101 can
To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), application-specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
Can be microprocessor or the processor 101 can also be any conventional processor 101 etc..
Peripheral Interface 104 couples various input/output devices to processor 101 and memory 102.In some implementations
In example, Peripheral Interface 104, processor 101 and storage control 103 can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
It is appreciated that structure shown in Fig. 2 is only to illustrate, server 200 may also include than shown in Fig. 2 more or more
Few component, or with the configuration different from shown in Fig. 2.Hardware, software or its group may be used in each component shown in Fig. 2
It closes and realizes.
Referring to Fig. 3, the embodiment of the present invention additionally provides a kind of illness result generation method, it is applied to server 200, disease
Crux fruit generation method includes：
Step S301：Receive the multiple state of an illness keywords for the characterization disease symptoms information that client 100 is sent.
Specifically, patient can input multiple state of an illness keywords in the Application Program Interface of client 100, then click
" confirmation " button, to which multiple state of an illness keywords are sent to client 100.Wherein, in the present embodiment, state of an illness keyword can be with
Judge related word for " cough ", " contact history ", " epidemic-stricken area " " age ", " gender ", " bradycardia " etc. and illness, herein
It is merely illustrative.It should be noted that due to being interacted just with word and patient in client 100, efficiency is very
It is low, and often there is deviation and invalid interaction, therefore audio, video or picture etc. can be embedded in the application program of client 100
Multimedia Attachments allow patient to be easy to compare, so that patient more accurately enters state of an illness keyword.
Specifically executive mode can be receive the characterization disease symptoms information that client 100 is sent one to step S301
Or multiple state of an illness keywords；It searches and the associated doubtful state of an illness keyword of one or more state of an illness keywords；It will be one or more
The associated doubtful state of an illness keyword of state of an illness keyword is sent to client 100；Being doubted from multiple for the transmission of client 100 is received again
Like the multiple state of an illness keywords selected in state of an illness keyword.
Step S302：According to multiple state of an illness keywords, the non-linear illness result of training in advance search model, pre-established
The multiple state of an illness keyword training samples and multiple state of an illness keyword training samples that history illness library includes are respectively formed more
The set associated history illness result of state of an illness keyword sample finds out multiple doubtful illness results.
Wherein, it is decision Tree algorithms model or neural network algorithm mould that the non-linear illness result of training, which searches model, in advance
Type or algorithm of support vector machine model or Genetic Algorithm Model or clustering algorithm model.
Wherein, it is a kind of method for approaching discrete function value that decision Tree algorithms model, which is decision Tree algorithms,.It is a kind of allusion quotation
The sorting technique of type, is first handled data, and readable rule and decision tree are generated using inductive algorithm, then using determining
Plan analyzes new data.Substantially decision tree is the process classified to data by series of rules.Decision tree structure
Making can be carried out in two steps, the first step, the generation of decision tree：The process of decision tree is generated by training sample set.Under normal circumstances,
Training sample data collection be according to actual needs it is historied, have certain degree of integration, be used for Data Analysis Services data
Collection.Second step, the beta pruning of decision tree：The beta pruning of decision tree is that the decision tree generated on last stage is tested, corrects and repaiied
Under process, mainly produced in the data check Decision Tree Construction in new sample data set (being known as test data set)
Raw preliminary rule wipes out the branch of the pre- weighing apparatus accuracy of those influences.Neural network algorithm model have adaptively with from group
Ability is knitted, is classified or is imitated using given sample canonical, is changed in carrying out study or training process according to training sample
Become synaptic weight value, to adapt to the requirement of ambient enviroment.Algorithm of support vector machine model is related with relevant learning algorithm
Supervised learning model, can analyze data, and recognition mode gives one group of training sample, Mei Gebiao for classification and regression analysis
Be denoted as and belong to two classes, a SVM training algorithm establishes a model, and it is a kind of or other classes to distribute new example, make its at
Classify for non-probability binary linearity.
Wherein, multiple doubtful illness results can be " pertussis ", " lung-kidney deficiency cough ", " phlegm-heat cough " etc. with it is more
The doubtful illness result of a state of an illness keyword.
Step S303：According to the corresponding presetting score weight rule of each doubtful illness result, multiple diseases of input
Feelings keyword calculates multiple doubtful degree score values.
Wherein, presetting score weight rule can be for example, doubtful illness result be " pertussis " when, if the state of an illness close
Keyword includes -5 points of " having contact history ", -40 points of " spastic paroxysmal cough "；" course of disease be more than 14 days " -40 is graded, specifically according to
Depending on actual case.
Preferably, the specific implementation procedure of step S303 can be：
Step S3031：State of an illness attributive classification is carried out to multiple state of an illness keywords of input according to each doubtful illness result.
Wherein, state of an illness attribute may include " epidemiological history ", " typical or atypical features ", " experimental test data " etc.
Deng.For example, " epidemiological history " includes the state of an illness keywords such as " morbidity season ", " epidemic-stricken area ", " contact history ", " preventing contact history "；
" typical or atypical features " include " apnea ", " asphyxia ", " livid purple ", " bradycardia ".
Step S3032：According to the corresponding score weight rule of each state of an illness attributive classification to different classes of multiple state of an illness
Keyword is scored.
The corresponding score weight rule of each state of an illness attributive classification can be morbidity season -5 points when being spring and autumn, in pertussis
- 5 points when popular epidemic-stricken area, there is -5 points of contact history, has -5 points of prevention contact history；- 5 points of apnea, asphyxia -5 points, it is -5 points livid purple,
- 5 points of bradycardia.
Step S3033：Each multiple scoring value being calculated are added to obtain each doubtful illness result correspondence
Doubtful degree score value.
Step S304：The highest doubtful illness result of doubtful degree score value is extracted as current illness result.
If the score of multiple doubtful illness results is respectively -90 points of " pertussis "；- 75 points of " lung-kidney deficiency cough "；" phlegm heat
Cough " -60 points, then will " pertussis " current illness of conduct as a result, and current illness result be transmitted to client 100 showing
Show.
Furthermore it is also possible to which multiple doubtful degree score values are carried out descending arrangement；When obtaining user within the presetting time
When the score value selection instruction of input, the doubtful degree score value that user is selected is as current illness result；When presetting
In when not obtaining score value selection instruction input by user, extract the highest doubtful illness result of doubtful degree score value as current
Illness result.
In order to further enhance the reliability of current illness result, which further includes：
Step S305：When judging whether highest doubtful degree score value is less than presetting score threshold, if it is, holding
Row step S306.
Step S306：Receive the multiple disease examination data critical words for the characterization disease symptoms information that client 100 is sent.
For example, presetting score threshold can be 80 points, concrete foundation actual conditions and set.Disease examination data are closed
Keyword may include " peripheral white blood cell amount ", " peripheral blood lymphocytes ", " have from phlegm, nasopharynx secretions and be separated to
Bordetella pertussis ", " increased times of the convalescent serum specific antibody than acute stage ".
Step S307：According to the presetting inspection data corresponding score weight rule of classification and multiple disease examination numbers
It scores according to keyword, to obtain disease examination data score value.
Wherein, check that the corresponding score weight rule of data classification can be that " peripheral white blood cell amount " be more than>
10000/DL-5 points；" peripheral blood lymphocytes " is more than 30%-5 points, " has the pertussis being separated to from phlegm, nasopharynx secretions
- 5 points of Bao Te bacterium ", " increased times of the convalescent serum specific antibody than acute stage " are more than 4 times -5 points.
Step S308：The doubtful degree score value previously obtained is added to doubt to which acquisition is new with disease examination data score value
Like degree score value.
For example, disease examination data score value is 10 points, the doubtful degree score value previously obtained is 70 points, then new doubtful journey
It is 80 points to spend score value, and the new doubtful degree fractional value 80 of acquisition divides can be as the reference data of current illness result.
It is only to illustrate herein it should be noted that depending on above-mentioned score weight rule can be according to actual demand
It is bright, depending on above-mentioned state of an illness keyword, state of an illness attributive classification, disease examination data critical word can also be according to actual demands,
This is merely illustrative.
Referring to Fig. 4, the embodiment of the present invention additionally provides a kind of illness result generating means 400, it should be noted that this
The technique effect of the illness result generating means 400 that embodiment is provided, basic principle and generation is identical with above-described embodiment,
To briefly describe, the present embodiment part does not refer to place, can refer to corresponding contents in the above embodiments.Illness result generates dress
It includes that information receiving unit 301, searching unit 302, computing unit 303, information transmitting unit 305 and result generate to set 400
Unit 306.
Multiple state of an illness that information receiving unit 301 is used to receive the characterization disease symptoms information of the transmission of client 100 are crucial
Word.
Specifically, information receiving unit 301 is additionally operable to receive the multiple of the characterization disease symptoms information of the transmission of client 100
State of an illness keyword；Searching unit 302 is for searching and the associated doubtful state of an illness keyword of one or more state of an illness keywords；Information
Transmission unit 305 is used to the associated doubtful state of an illness keyword of one or more state of an illness keywords being sent to client 100；Information
What receiving unit 301 was additionally operable to receive the transmission of client 100 again selects multiple state of an illness from multiple doubtful state of an illness keywords
Keyword.
Specifically, step S301 can be executed using information receiving unit 301.
Searching unit 302 is additionally operable to according to multiple state of an illness keywords, the non-linear illness result of training in advance searches model,
The multiple state of an illness keyword training samples and multiple state of an illness keyword training samples difference that pre-established history illness library includes
The more associated history illness results of set state of an illness keyword sample formed find out multiple doubtful illness results.
Wherein, the non-linear illness result lookup model of training in advance can be but be not limited to decision Tree algorithms model or god
Through network algorithm model or algorithm of support vector machine model or Genetic Algorithm Model or clustering algorithm model.
Specifically, step S302 can be executed using searching unit 302.
Computing unit 303 is used for according to each doubtful illness result corresponding presetting score weight rule, input
Multiple state of an illness keywords calculate multiple doubtful degree score values.
Specifically, computing unit 303 includes：Classification submodule, for each doubtful illness result of foundation to the more of input
A state of an illness keyword carries out state of an illness attributive classification；Score submodule, for according to the corresponding score power of each state of an illness attributive classification
Weight-normality then scores to different classes of multiple state of an illness keywords；Computational submodule, for by it is each be calculated it is multiple
Scoring value is added to obtain the corresponding doubtful degree score value of each doubtful illness result.
Specifically, step S303 can be executed using computing unit 303.
As a result generation unit 306 is for extracting the highest doubtful illness result of doubtful degree score value as current illness knot
Fruit.
It is to be appreciated that step S304 can be executed using result generation unit 306.
Judging unit 304 is for judging that highest doubtful degree score value is less than presetting score threshold.
It is to be appreciated that step S305 can be executed using judging unit 304.
In addition, information receiving unit 301 is additionally operable to when highest doubtful degree score value is less than presetting score threshold,
Receive the multiple disease examination data critical words for the characterization disease symptoms information that client 100 is sent；Score submodule is additionally operable to
It scores according to the presetting inspection data corresponding score weight rule of classification and multiple disease examination data critical words,
To obtain disease examination data score value；Computational submodule is additionally operable to the doubtful degree score value that will have previously obtained and disease examination number
It is added to obtain new doubtful degree score value according to score value.
It is to be appreciated that step S306 can also be performed using information receiving unit 301, may be used also using computing unit 303
To execute step S307, step S308.
To sum up, illness result generation method provided by the invention and device, first by according to multiple state of an illness keywords, pre-
Multiple state of an illness keyword training samples that first the non-linear illness result of training searches model, pre-established history illness library includes
And the associated history illness result of more set state of an illness keyword samples that multiple state of an illness keyword training samples are respectively formed is searched
Go out multiple doubtful illness results；Then according to each doubtful illness result corresponding presetting score weight rule, input
Multiple state of an illness keywords calculate multiple doubtful degree score values；The highest doubtful illness result of doubtful degree score value is finally extracted to make
For current illness result.The illness result generation method with device is easy to operate, rate of correct diagnosis is high, saves the time and artificial
Cost, user experience are high.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, the flow chart in attached drawing and block diagram
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part for the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that at some as in the realization method replaced, the function of being marked in box can also be to be different from
The sequence marked in attached drawing occurs.For example, two continuous boxes can essentially be basically executed in parallel, they are sometimes
It can execute in the opposite order, this is depended on the functions involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use function or the dedicated base of action as defined in executing
It realizes, or can be realized using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each function module in each embodiment of the present invention can integrate to form an independent portion
Point, can also be modules individualism, can also two or more modules be integrated to form an independent part.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic disc or CD.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should be noted that：Similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and is explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Claims (10)
1. a kind of illness result generation method, which is characterized in that the illness result generation method includes：
Receive the multiple state of an illness keywords for the characterization disease symptoms information that client is sent；
According to multiple state of an illness keywords, the non-linear illness result of training in advance searches model, pre-established history illness library is wrapped
More set state of an illness keywords that the multiple state of an illness keyword training samples and multiple state of an illness keyword training samples contained are respectively formed
The associated history illness result of sample finds out multiple doubtful illness results；
Multiple state of an illness keywords according to each corresponding presetting score weight rule of doubtful illness result, input calculate
Multiple doubtful degree score values；
The highest doubtful illness result of doubtful degree score value is extracted as current illness result.
2. illness result generation method according to claim 1, which is characterized in that each doubtful illness result of the foundation
Corresponding presetting score weight rule, input multiple state of an illness keywords the step of calculating multiple doubtful degree score values wrap
It includes：
State of an illness attributive classification is carried out to multiple state of an illness keywords of input according to each doubtful illness result；
Different classes of multiple state of an illness keywords are carried out according to the corresponding weight rule of scoring of each state of an illness attributive classification
Score；
Each multiple scoring value being calculated are added to obtain the corresponding doubtful degree score value of each doubtful illness result.
3. illness result generation method according to claim 2, which is characterized in that extract doubtful degree score value most described
Before the step of high doubtful illness result is as current illness result, the illness result generation method further includes：
When highest doubtful degree score value is less than presetting score threshold, the characterization disease symptoms letter that client is sent is received
Multiple disease examination data critical words of breath；
According to the presetting inspection data corresponding score weight rule of classification and the multiple disease examination data critical word
It scores, to obtain disease examination data score value；
The doubtful degree score value previously obtained is added with disease examination data score value to the new doubtful degree score value of acquisition.
4. illness result generation method according to claim 1, which is characterized in that the characterization for receiving client and sending
The step of multiple state of an illness keywords of disease symptoms information includes：
Receive the one or more state of an illness keywords for the characterization disease symptoms information that client is sent；
It searches and the associated doubtful state of an illness keyword of one or more state of an illness keywords；
The associated doubtful state of an illness keyword of one or more state of an illness keywords is sent to the client；
The multiple state of an illness keywords selected from multiple doubtful state of an illness keywords that client is sent are received again.
5. illness result generation method according to claim 1, which is characterized in that the non-linear illness of the training in advance
As a result it is decision Tree algorithms model or neural network algorithm model or algorithm of support vector machine model or genetic algorithm to search model
Model or clustering algorithm model.
6. a kind of illness result generating means, which is characterized in that the illness result generating means include：
Information receiving unit, multiple state of an illness keywords of the characterization disease symptoms information for receiving client transmission；
Searching unit is used for according to multiple state of an illness keywords, the non-linear illness result of training in advance searches model, pre-established
The multiple state of an illness keyword training samples and multiple state of an illness keyword training samples that history illness library includes are respectively formed more
The set associated history illness result of state of an illness keyword sample finds out multiple doubtful illness results；
Computing unit, for multiple diseases according to the corresponding presetting score weight rule of each doubtful illness result, input
Feelings keyword calculates multiple doubtful degree score values；
As a result generation unit, for extracting the highest doubtful illness result of doubtful degree score value as current illness result.
7. illness result generating means according to claim 6, which is characterized in that the computing unit includes：
Classification submodule divides for carrying out state of an illness attribute to multiple state of an illness keywords of input according to each doubtful illness result
Class；
Score submodule, for according to the corresponding score weight rule of each state of an illness attributive classification to different classes of multiple
State of an illness keyword is scored；
Computational submodule obtains each doubtful illness result correspondence for being added each multiple scoring value being calculated
Doubtful degree score value.
8. illness result generating means according to claim 7, which is characterized in that
Described information receiving unit is additionally operable to, when highest doubtful degree score value is less than presetting score threshold, receive client
The multiple disease examination data critical words for the characterization disease symptoms information that end is sent；
The score submodule is additionally operable to classify corresponding score weight rule and described more according to presetting inspection data
A disease examination data critical word is scored, to obtain disease examination data score value；
The doubtful degree score value that the computational submodule is additionally operable to previously to have obtained is added to obtain with disease examination data score value
Obtain doubtful degree score value newly.
9. illness result generating means according to claim 6, which is characterized in that the illness result generating means are also wrapped
Information transmitting unit is included,
Described information receiving unit is additionally operable to receive the multiple state of an illness keywords for the characterization disease symptoms information that client is sent；
The searching unit is additionally operable to search and the associated doubtful state of an illness keyword of one or more state of an illness keywords；
Described information transmission unit is used to the associated doubtful state of an illness keyword of one or more state of an illness keywords being sent to described
Client；
Described information receiving unit is additionally operable to receive selecting from multiple doubtful state of an illness keywords for the client transmission again
Go out multiple state of an illness keywords.
10. illness result generating means according to claim 6, which is characterized in that the non-thread venereal disease of the training in advance
It is that decision Tree algorithms model or neural network algorithm model or algorithm of support vector machine model or heredity are calculated that crux fruit, which searches model,
Method model or clustering algorithm model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810110202.XA CN108320798A (en) | 2018-02-05 | 2018-02-05 | Illness result generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810110202.XA CN108320798A (en) | 2018-02-05 | 2018-02-05 | Illness result generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108320798A true CN108320798A (en) | 2018-07-24 |
Family
ID=62902743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810110202.XA Pending CN108320798A (en) | 2018-02-05 | 2018-02-05 | Illness result generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108320798A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360658A (en) * | 2018-11-01 | 2019-02-19 | 北京航空航天大学 | A kind of the disease pattern method for digging and device of word-based vector model |
| CN109545384A (en) * | 2018-11-21 | 2019-03-29 | 上海依智医疗技术有限公司 | A kind of medical diagnostic method and device |
| CN110782996A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Construction method and device of medical database, computer equipment and storage medium |
| CN111180081A (en) * | 2019-12-30 | 2020-05-19 | 众安信息技术服务有限公司 | Intelligent inquiry method and device |
| WO2020113544A1 (en) * | 2018-12-07 | 2020-06-11 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence medical symptom recognition system based on end-to-end learning |
| CN112102954A (en) * | 2020-09-02 | 2020-12-18 | 南京江北新区科技投资集团有限公司 | Big data analysis cloud platform system capable of providing intelligent medical service |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423789A (en) * | 2000-02-14 | 2003-06-11 | 第一咨询公司 | Automated diagnostic system and method |
-
2018
- 2018-02-05 CN CN201810110202.XA patent/CN108320798A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423789A (en) * | 2000-02-14 | 2003-06-11 | 第一咨询公司 | Automated diagnostic system and method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360658A (en) * | 2018-11-01 | 2019-02-19 | 北京航空航天大学 | A kind of the disease pattern method for digging and device of word-based vector model |
| CN109360658B (en) * | 2018-11-01 | 2021-06-08 | 北京航空航天大学 | Disease pattern mining method and device based on word vector model |
| CN109545384A (en) * | 2018-11-21 | 2019-03-29 | 上海依智医疗技术有限公司 | A kind of medical diagnostic method and device |
| WO2020113544A1 (en) * | 2018-12-07 | 2020-06-11 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence medical symptom recognition system based on end-to-end learning |
| CN112655054A (en) * | 2018-12-07 | 2021-04-13 | 北京嘀嘀无限科技发展有限公司 | Artificial intelligence medical symptom identification system based on end-to-end learning |
| CN110782996A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Construction method and device of medical database, computer equipment and storage medium |
| CN111180081A (en) * | 2019-12-30 | 2020-05-19 | 众安信息技术服务有限公司 | Intelligent inquiry method and device |
| CN111180081B (en) * | 2019-12-30 | 2023-11-03 | 众安信息技术服务有限公司 | Intelligent inquiry method and device |
| CN112102954A (en) * | 2020-09-02 | 2020-12-18 | 南京江北新区科技投资集团有限公司 | Big data analysis cloud platform system capable of providing intelligent medical service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320798A (en) | Illness result generation method and device | |
| CN109783632B (en) | Customer service information pushing method and device, computer equipment and storage medium | |
| WO2020125445A1 (en) | Classification model training method, classification method, device and medium | |
| CN104765733B (en) | A kind of method and apparatus of social networks event analysis | |
| Khalilia et al. | Predicting disease risks from highly imbalanced data using random forest | |
| CN108198631A (en) | Evidence-based medical outcome generation method and device | |
| Duggal et al. | Predictive risk modelling for early hospital readmission of patients with diabetes in India | |
| Pathan et al. | Identifying stroke indicators using rough sets | |
| CN110377727B (en) | Multi-label text classification method and device based on multi-task learning | |
| CN109036577A (en) | Diabetic complication analysis method and device | |
| WO2023011382A1 (en) | Recommendation method, recommendation model training method, and related product | |
| Duggal et al. | Impact of selected pre-processing techniques on prediction of risk of early readmission for diabetic patients in India | |
| US20200303071A1 (en) | Implementation of machine-learning based query construction and pattern identification through visualization in user interfaces | |
| Miyazawa et al. | Artificial intelligence in food science and nutrition: A narrative review | |
| CN112562863A (en) | Epidemic disease monitoring and early warning method and device and electronic equipment | |
| Baechle et al. | A framework for the estimation and reduction of hospital readmission penalties using predictive analytics | |
| Pal et al. | Survey of fake news detection using machine intelligence approach | |
| Iddrisu et al. | A sentiment analysis framework to classify instances of sarcastic sentiments within the aviation sector | |
| Syed Mustapha | Predictive analysis of students’ learning performance using data mining techniques: A comparative study of feature selection methods | |
| Tiwari et al. | Symptoms are known by their companies: towards association guided disease diagnosis assistant | |
| CN111627566A (en) | Indication information processing method and device, storage medium and electronic equipment | |
| US11100425B2 (en) | Facilitating data-driven mapping discovery | |
| CN114664421A (en) | Doctor-patient matching method and device, electronic equipment, medium and product | |
| CN114219663A (en) | Product recommendation method and device, computer equipment and storage medium | |
| Al-Hameli et al. | Prediction of diabetes using hidden Naïve Bayes: comparative study |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180724 |
|
| RJ01 | Rejection of invention patent application after publication |