CN109509102A - Claims Resolution decision-making technique, device, computer equipment and storage medium - Google Patents
Claims Resolution decision-making technique, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109509102A CN109509102A CN201810924549.8A CN201810924549A CN109509102A CN 109509102 A CN109509102 A CN 109509102A CN 201810924549 A CN201810924549 A CN 201810924549A CN 109509102 A CN109509102 A CN 109509102A
- Authority
- CN
- China
- Prior art keywords
- data
- corpus
- anatomy
- region
- information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This application involves data processing technique, a kind of Claims Resolution decision-making technique, device, computer equipment and storage medium are provided.Method includes: to obtain the condition of the injury data of the wounded to be settled a claim, obtains corresponding region of anatomy information according to condition of the injury data;Disease damage corpus set associated with region of anatomy information is obtained from the semantic network pre-established, and the first option information set is sent to terminal according to disease damage corpus set;The first choice that terminal is sent is received as a result, searching corresponding seriously injured degree corpus set from semantic network according to first choice result, the second option information set is sent to terminal according to seriously injured degree corpus set;Receive terminal return the second selection result, according to region of anatomy information, first choice result, the second selection result from obtain object matching data;The corresponding default Claims Resolution data of object matching data are obtained, objective decision data is obtained according to default Claims Resolution data, objective decision data is sent to terminal.
Description
Technical field
This application involves business insurance Claims Resolution technical fields, more particularly to a kind of Claims Resolution decision-making technique, device, computer
Equipment and storage medium.
Background technique
With the continuous improvement of business insurance IT application of service degree, raising settlement of insurance claim business is professional and compensates accurate
The demand of property is more more and more urgent.
In traditional technology, quotient's factoring is paid for, and people when such as traffic accident hurts Claims Resolution, generally requires largely have medical speciality background or non-
Medical professional reaches scene of an automobile accident and carries out the work such as field reconnaissance, underwriting after professional training to a certain degree.So
And before this mode requires height, Shang Bao company to need that a large amount of manpower and material resources is spent to carry out due to the medicine attainment to claims personnel
The related training of phase, causes Business to be settled a claim at high cost;On the other hand, by the judgement manually settled a claim, Insurance Actuary's needs pair
The wounded carries out condition of the injury judgement and then selects Claims Resolution scheme according to the condition of the injury, and whole process will take a significant amount of time, and lead to low efficiency
Under.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide it is a kind of can reduce business insurance Claims Resolution cost simultaneously
Improve Claims Resolution decision-making technique, device, computer equipment and the storage medium of Claims Resolution efficiency.
A kind of Claims Resolution decision-making technique, which comprises the condition of the injury data for obtaining the wounded to be settled a claim, according to the condition of the injury number
According to obtaining corresponding region of anatomy information;It is obtained from the semantic network pre-established associated with the region of anatomy information
Disease damage corpus set sends the first option information set to terminal according to the disease damage corpus set;Receive the terminal according to
The first choice that the first option information set returns according to the first choice result from the semantic network as a result, look into
Corresponding seriously injured degree corpus set is looked for, the second choosing is sent to the terminal according to the seriously injured degree corpus set
Item information aggregate;The second selection result that the terminal is returned according to the second option information set is received, according to the solution
Cut open location information, the first choice result, second selection result obtained from preset matched data set it is described to
The corresponding object matching data of Claims Resolution the wounded;The corresponding default Claims Resolution data of the object matching data are obtained, according to described pre-
If Claims Resolution data obtain objective decision data, the objective decision data are sent to the terminal.
The condition of the injury data for obtaining the wounded to be settled a claim in one of the embodiments, obtain according to the condition of the injury data
Corresponding region of anatomy information, comprising: receive the condition of the injury picture for described the wounded to be settled a claim that the terminal is sent;By the condition of the injury
Picture is input in the convolutional neural networks trained, and obtains the corresponding region of anatomy information of the condition of the injury picture.
It is described in one of the embodiments, to be obtained and the region of anatomy information phase from the semantic network pre-established
Before associated disease damage corpus set, comprising: obtain the semantic tree of default dimension, the default dimension includes at least anatomy portion
Position, disease damage and seriously injured degree;Calculate the semantic tree pair of the semantic tree corresponding node and other dimensions of each dimension
The co-occurrence frequency of the node answered between any two;Two nodes that the co-occurrence frequency is greater than preset threshold are established into incidence relation,
Generative semantics network.
It is described according to the region of anatomy information, the first choice result, described second in one of the embodiments,
Selection result obtains the corresponding object matching data of described the wounded to be settled a claim from preset matched data set, comprising: respectively
Obtain the region of anatomy information, the first choice result, the corresponding weight of second selection result;It calculates separately described
Region of anatomy information, the first choice result, the matching degree of second selection result and each matched data;According to institute
It states weight and the matching degree calculates the corresponding matching score value of each matched data, obtain the matching maximum matched data of score value
As object matching data.
It is described in one of the embodiments, that the first option information collection is sent to terminal according to the disease damage corpus set
It closes, comprising: to each of disease damage corpus set disease damage corpus, its corresponding description is searched from description information set
Information;The first option information set is obtained according to each corresponding description information of disease damage corpus.
It is described in one of the embodiments, to obtain objective decision data according to the default Claims Resolution data, comprising: to work as institute
When the quantity for stating default Claims Resolution data is preset quantity, the corresponding label information of the default Claims Resolution data of each is obtained;Obtain institute
State the corresponding personal information of user identifier;Objective decision data are obtained according to the label information and the personal information.
A kind of Claims Resolution decision making device, described device include:
Condition of the injury data acquisition module obtains pair for obtaining the condition of the injury data of the wounded to be settled a claim according to the condition of the injury data
The region of anatomy information answered;
First option information set sending module, for being obtained and the region of anatomy from the semantic network pre-established
The associated disease damage corpus set of information sends the first option information set to terminal according to the disease damage corpus set;
Second option information set sending module is returned for receiving the terminal according to the first option information set
First choice as a result, searching corresponding seriously injured degree corpus from the semantic network according to the first choice result
Set sends the second option information set to the terminal according to the seriously injured degree corpus set;
Object matching data acquisition module, returned for receiving the terminal according to the second option information set
Two selection results, according to the region of anatomy information, the first choice result, second selection result from preset matching
The corresponding object matching data of described the wounded to be settled a claim are obtained in data acquisition system;
Objective decision data transmission blocks, for obtaining the corresponding default Claims Resolution data of the object matching data, according to
The default Claims Resolution data obtain objective decision data, and the objective decision data are sent to the terminal.
Described device further includes semantic network generation module in one of the embodiments, and the semantic network generates mould
Block is used to obtain the semantic tree of default dimension, and the default dimension includes at least the region of anatomy, disease damage and seriously injured degree;
Calculate the co-occurrence frequency of the corresponding node of the semantic tree node corresponding with the semantic tree of other dimensions of each dimension between any two
Rate;Two nodes that the co-occurrence frequency is greater than preset threshold are established into incidence relation, generative semantics network.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes step described in above-mentioned Claims Resolution decision-making technique when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Step described in above-mentioned Claims Resolution decision-making technique is realized when row.
Above-mentioned Claims Resolution decision-making technique, device, computer equipment and storage medium get the condition of the injury data of the wounded to be settled a claim
Afterwards, the region of anatomy corresponding to the condition of the injury to patient judges, then finds disease damage corpus from semantic network, and to terminal
Delivery option information, then server further searches severity language according to the selection result that terminal returns from semantic network
Material, and again to terminal delivery option information, and after the selection result for receiving terminal return again, it can be according to acquisition
All data carry out Claims Resolution decision, the limited option data for only needing to be shown according to terminal in the whole process due to Insurance Actuary
It is selected, the final Claims Resolution result of decision can be obtained, the requirement to the professional knowledge of Insurance Actuary is substantially reduced, not only saved
The cost that Insurance Actuary is giveed training, and need to carry out condition of the injury judgement then to the wounded relative to Insurance Actuary in traditional technology
Claims Resolution scheme is selected according to the condition of the injury, saves the plenty of time, to improve Claims Resolution efficiency.
Detailed description of the invention
Fig. 1 is the application scenario diagram of Claims Resolution decision-making technique in one embodiment;
Fig. 2 is the flow diagram of Claims Resolution decision-making technique in one embodiment;
Fig. 3 is the step flow diagram of generative semantics network in one embodiment;
Fig. 4 is the structural block diagram of Claims Resolution decision making device in one embodiment;
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Claims Resolution decision-making technique provided by the present application, can be applied in application environment as shown in Figure 1, including terminal 102,
Server 104, wherein terminal 102 is the terminal that Insurance Actuary is used to carry out Claims Resolution decision, and terminal 102 passes through network and server
104 are communicated.Server 104 gets the condition of the injury data of the wounded to be settled a claim, and the condition of the injury of patient is judged according to the condition of the injury data
Then the corresponding region of anatomy obtains disease damage corpus associated with the region of anatomy from the semantic network pre-established
It closes, the first option information set is sent to terminal according to disease damage corpus set, Insurance Actuary can be selected by terminal 102 with patient's
Then selection result is sent to server 104 by terminal by the option that the condition of the injury is best suitable for, server 104 arrives the selection result
Afterwards, corresponding degree corpus set is searched from semantic network according to the selection result, is sent out according to degree corpus set to terminal
The second option information set is sent, then the option that Insurance Actuary is best suitable for again by the condition of the injury of the selection of terminal 102 and patient passes through
Selection result is sent to server 104 by terminal, after server 104 receives the selection result, according to the region of anatomy and two
Secondary selection result obtains object matching data from preset matched data set, corresponding default according to matched data inquiry
Claims Resolution data, obtain objective decision data according to default Claims Resolution data, objective decision data are sent to terminal 102.
Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, smart phone, plate electricity
Brain, server 104 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, providing a kind of Claims Resolution decision-making technique, it is applied in Fig. 1 in this way
It is illustrated for server, comprising the following steps:
Step S202 obtains the condition of the injury data of the wounded to be settled a claim, obtains corresponding region of anatomy information according to condition of the injury data.
Specifically, condition of the injury data refer to data relevant to the condition of the injury situation of patient, including but not limited to picture, text
Or voice.The region of anatomy refers to describing the medicine at each position of human body in human anatomy.
In the present embodiment, Insurance Actuary is known after the substantially condition of the injury situation for the wounded that settles a claim, and can pass through terminal to server
Send condition of the injury data.The condition of the injury data can be the text that the wounded's injury is described or voice or the wounded by
The picture of traumatic part position.After server receives condition of the injury data, it can be judged corresponding to the injury of patient according to condition of the injury data
The region of anatomy.
In one embodiment, when condition of the injury data are the verbal description to injury, which can be extracted
Keyword matches the keyword of extraction keyword set corresponding with each region of anatomy, by the key of successful match
The corresponding region of anatomy of word is as the corresponding region of anatomy of condition of the injury data;It, can be to voice when condition of the injury data are voice data
Data carry out text conversion, keyword are then extracted, by the keyword of extraction keyword set corresponding with each region of anatomy
It is matched, using the corresponding region of anatomy of the keyword of successful match as the corresponding region of anatomy of condition of the injury data.
In another embodiment, condition of the injury data can be image data corresponding to the wounded's injury, and server can
The image data to be input in the machine learning model that can be used for classifying that one has been trained, condition of the injury data pair are finally obtained
The region of anatomy answered.
Step S204 obtains disease damage corpus associated with region of anatomy information from the semantic network pre-established
It closes, the first option information set is sent to terminal according to disease damage corpus set.
Specifically, semantic network (semantic network) is a kind of shape with network format expression medical knowledge construction
Formula includes at least region of anatomy corpus, condition of the injury severity corpus and disease damage corpus in the semantic network of the present embodiment, various
Certain incidence relation is set up between corpus according to preset rule, two corpus with incidence relation are in semantic net
It is attached in network by one " side " in network.In the semantic network, any one language can be found by these " sides "
The association corpus of material.Wherein, region of anatomy corpus refers to the description to the region of anatomy each in human anatomy, as hip,
Coccyx etc.;Disease damage corpus refers to that the condition of the injury describes the medicine of damage caused by the region of anatomy, such as fracture, bleeding, dislocation
Deng;Severity refers to the medicine description of severity corresponding to the condition of the injury, for example, it is comminuted, open, half etc..
In the present embodiment, server can traverse semantic tree after getting the corresponding region of anatomy information of condition of the injury data
In all region of anatomy corpus, then the region of anatomy corpus is positioned, after navigating to the region of anatomy information,
All disease damage corpus being associated are searched in semantic network, these disease damage corpus form disease damage corpus set, and then basis should
Disease damage corpus set sends the first option information set to terminal.Wherein, the first option information set refers to being supplied to terminal
Carry out the option information relevant to disease damage corpus of selection.
In one embodiment, the first option information set can be directly for by each disease damage corpus group in disease damage corpus set
At set.
Step S206, the first choice that reception terminal is returned according to the first option information set is as a result, according to first choice
As a result corresponding seriously injured degree corpus set is searched from semantic network, according to seriously injured degree corpus set to terminal
Send the second option information set.
Specifically, after the first option information set is sent to terminal by server, terminal shows these option informations
Show, Insurance Actuary can select at the terminal according to the practical condition of the injury of patient, the option information that then terminal selects Insurance Actuary
Alternatively result is sent to server.Since the respective option in the first option information is all with the disease in disease damage corpus set
It is relevant to damage corpus, after server receives the selection result of terminal, the corresponding disease damage corpus of the selection result can be obtained, so
The disease damage corpus is positioned in semantic network afterwards, and obtains all severity corpus corresponding with the disease damage corpus, then
The second option information set is sent to terminal according to these severity corpus;Wherein, the second option information set refers to mentioning
Supply terminal carries out the option information relevant to seriously injured degree corpus of selection.
In one embodiment, the second option information set can be directly for by each wound in seriously injured degree corpus set
The set of gesture severity corpus composition.
Step S208 receives the second selection result that terminal is returned according to the second option information set, according to the region of anatomy
Information, first choice result, the second selection result obtain the corresponding target of the wounded to be settled a claim from preset matched data set
Matched data.
Specifically, after the second option information set is sent to terminal by server, terminal shows these option informations
Show, Insurance Actuary can select at the terminal according to the practical condition of the injury of patient, the option information that then terminal selects Insurance Actuary
Alternatively result is sent to server.Since the respective option in the second option information is all with seriously injured degree corpus
Seriously injured degree corpus in conjunction is related, after server receives the selection result of terminal, can obtain the selection knot
The corresponding seriously injured degree corpus of fruit.
Preset matched data set refers to the set as composed by preset matched data, wherein coupling number
The number of the condition of the injury situation of the wounded is described according to one or several dimensions in the slave region of anatomy of finger, disease damage, seriously injured degree
According to such as " left side index finger comminuted fracture ", " open cerebellar hemorrhage ", " right hips subluxation ", therefore, server is obtaining
After getting the region of anatomy, disease damage corpus, seriously injured degree corpus corresponding to the condition of the injury for the wounded that settles a claim, these languages can be calculated
Material with matched data set in each matched data matching degree, selected according to matching degree calculated result matched data as
The corresponding object matching data of the wounded to be settled a claim, for example, the matching point of each matched data and above-mentioned several corpus can be calculated
Then value selects the matching highest matched data of score value as object matching data.
Step S210 obtains the corresponding default Claims Resolution data of object matching data, obtains target according to default Claims Resolution data
Objective decision data are sent to terminal by decision data.
Specifically, preset Claims Resolution data include but is not limited to amount for which loss settled, Claims Resolution the time limit, preset Claims Resolution data by manually into
Row is previously set.
In the present embodiment, for each matched data in matched data set, it is provided with corresponding default Claims Resolution number
According to.Server inquires the corresponding default Claims Resolution data of the object matching data, then basis after getting object matching data
The default Claims Resolution data inquired obtain objective decision data, wherein the server that objective decision data refer to is from default Claims Resolution number
According to the final decision data of middle acquisition treating Claims Resolution patient and settling a claim.Further, server sends objective decision data
To terminal.
It is appreciated that the corresponding default Claims Resolution data of each matched data have been likely to one or more, work as Claims Resolution
Data only one when, directly using the default Claims Resolution data as objective decision data;When default Claims Resolution data have multiple, clothes
Business device from these Claims Resolution data in select one as objective decision data.
In above-mentioned Claims Resolution decision-making technique, server is being got after the condition of the injury data for the wounded that settles a claim, to the condition of the injury of patient
The corresponding region of anatomy is judged, disease damage corpus is then found from semantic network, and to terminal delivery option information, so
Server further searches severity corpus according to the selection result that terminal returns from semantic network afterwards, and again to terminal
Delivery option information, and after the selection result for receiving terminal return again, it can be managed according to all data of acquisition
Decision is paid for, since Insurance Actuary only needs the limited option data shown according to terminal to select in the whole process
Obtain the final Claims Resolution result of decision, the requirement to the professional knowledge of Insurance Actuary substantially reduces, not only save to Insurance Actuary into
The cost of row training, and need to carry out the wounded condition of the injury judgement relative to Insurance Actuary in traditional technology then to be selected according to the condition of the injury
Claims Resolution scheme is selected, the plenty of time is saved, to improve Claims Resolution efficiency.
In one embodiment, the condition of the injury data for obtaining the wounded to be settled a claim obtain corresponding anatomy portion according to condition of the injury data
Position information, comprising: receive the condition of the injury picture for the wounded to be settled a claim that terminal is sent;Condition of the injury picture is input to the convolution mind trained
In network, the corresponding region of anatomy information of condition of the injury picture is obtained.
Specifically, trained convolutional neural networks include convolutional layer, pond layer and full articulamentum;Condition of the injury picture is defeated
Enter into the convolutional neural networks trained, obtain the corresponding region of anatomy information of condition of the injury picture, specifically include: will suffer from wait settle a claim
Input of the condition of the injury picture of person as convolutional layer, convolutional layer carry out convolution algorithm for treating the corresponding image data of Claims Resolution patient
Obtain fisrt feature matrix;Using fisrt feature matrix as the input of pond layer, pond layer is used for will be in fisrt feature matrix
Maximum weight is projected to obtain normalized second characteristic matrix in each vector;Using second characteristic matrix as full connection
The input of layer, full articulamentum are used to carry out classified calculating according to second characteristic matrix to obtain region of anatomy information.
Wherein, convolutional neural networks can be trained in the following manner and be obtained: obtaining training sample set and training sample is concentrated
The corresponding region of anatomy information of each training sample;Each training sample is concentrated successively to be used as convolutional Neural training sample
The input of network carries out convolutional neural networks using its corresponding region of anatomy information as the desired output of convolutional neural networks
Training obtains current trained convolutional neural networks.Wherein, training sample refers to that region of anatomy information had determined goes through
History condition of the injury image data.
In one embodiment, it as shown in figure 3, further including the steps that generative semantics tree before step S204, specifically includes:
Step S302 obtains the semantic tree of default dimension, it is tight including at least the region of anatomy, disease damage and the condition of the injury to preset dimension
Weight degree.
It specifically, can be first against the corpus for extracting each default dimension in standardized medicine corpus, according to each
Semantic relation between the corresponding corpus of a dimension constructs semantic tree in advance, and each node is standardized medicine in semantic tree
Word, standardized medicine corpus such as can be ICD (International Classification of
Diseases, International Classification of Diseases) coding scheme, it presets dimension and includes at least the region of anatomy, disease damage and seriously injured degree.
As shown in table 1 below, it is illustrated with the part of semantic tree for position " ear ":
Table 1
As seen from the above table, semantic tree can have multi-level structure, and level is higher, then explanation is to the corresponding semanteme of root node
Node word " ear " more refines the medical terms of statement.
Step S304 calculates the corresponding node of the semantic tree node corresponding with the semantic tree of other dimensions of each dimension
Co-occurrence frequency between any two.
Specifically, for the semantic tree of each dimension, its each corresponding node, the semanteme with other dimensions are calculated
Set the co-occurrence frequency between corresponding node, wherein co-occurrence frequency refers to two words in preset context altogether
With the frequency occurred, co-occurrence frequency is bigger, indicates that the correlation degree of two words is bigger.Co-occurrence frequency is usually with co-occurrence matrix
Form is expressed, the pairs algorithm or stripes algorithm meter that co-occurrence matrix can for example be realized using MapReduce model
It obtains.
Two nodes that co-occurrence frequency is greater than preset threshold are established incidence relation, generative semantics network by step S306.
Specifically, preset threshold can according to in semantic network between two nodes that are mutually related correlation degree difference
It is required that carrying out different degrees of setting.Correlation degree requirement is higher between two nodes that are mutually related, then preset threshold is bigger.
In the present embodiment, two nodes of preset threshold are greater than for co-occurrence frequency, pass through one in semantic network
While being attached, i.e., the corresponding corpus of two nodes is established into incidence relation.When the incidence relation between each semantic tree is established
After good, semantic network is obtained.It in the semantic network, is scanned for, can be obtained associated therewith by any one corpus
All corpus.
The semantic network generated in the present embodiment, due to being that the cooccurrence relation between the semantic tree to each dimension carries out
It establishes, can quickly and accurately be used for corpus search, improve the efficiency of Claims Resolution decision.
In one embodiment, according to region of anatomy information, first choice result, the second selection result from preset matching
It includes: to obtain region of anatomy information, first choice respectively that the corresponding object matching data of the wounded to be settled a claim are obtained in data acquisition system
As a result, the corresponding weight of the second selection result;Calculate separately region of anatomy information, first choice result, the second selection result with
The matching degree of each matched data;The corresponding matching score value of each matched data is calculated according to weight and matching degree, is obtained
The maximum matched data of score value is matched as object matching data.
In the present embodiment, the corpus of three region of anatomy, disease damage, seriously injured degree dimensions is pre-set pair
The weight answered, and due to first choice the result is that being selected from the first option information set relevant to disease damage corpus set
It arrives, therefore, the weight of first choice result is identical as the weight of disease damage corpus, similarly, the weight and the condition of the injury of the second selection result
The weight of severity corpus is identical.
In one embodiment, the region of anatomy, first choice result, the second selection result and each matched data are calculated
Matching degree when, matched data is segmented first, then carries out part-of-speech tagging, marks out the region of anatomy, disease damage and wound
The parts of speech such as gesture severity, the region of anatomy word progress of the region of anatomy information and matched data that then get server
Match, the first choice result that server is got matched with the disease damage word of matched data, by the second selection result with
Seriously injured degree word with data is matched.
Match the accumulated value that score value is each matching degree and the product of corresponding weight.For example, solution is such as set separately
Cut open position, disease damage, the weight of seriously injured degree be 0.6,0.4,0.2, for some diagnostic data, obtained according to the region of anatomy
To matching degree is 0.8, is 0.5 according to the matching degree that disease damage obtains, the matching degree obtained according to seriously injured degree is 0.6,
Then finally match score value are as follows: 0.6x0.8+0.4x0.5+0.2x0.6.
In one embodiment, step S204 includes: and is believed from description each of disease damage corpus set disease damage corpus
Its corresponding description information is searched in breath set;The first option information is obtained according to each corresponding description information of disease damage corpus
Set.
Specifically, description information refers to the corresponding popular description language of disease damage corpus.Due to each in semantic network
A corpus is all standardized medicine description, and for Insurance Actuary, the disease damage corpus that accurate understanding is all is needed, to medicine
Professional knowledge is more demanding, therefore, corresponding description information can be arranged to each disease damage corpus in advance, and establish description information
With the mapping relations between disease damage corpus, server is being got after the corresponding disease damage corpus set of the wounded that settles a claim, can basis
These description informations are finally alternatively obtained first to each corresponding description information of disease damage corpus by mapping relationship searching
Option information set.
In the present embodiment, the corresponding description information of disease damage corpus is obtained to obtain first choice information aggregate, due to retouching
Stating information is straightaway language description, the requirement to the medical knowledge of Insurance Actuary can be further decreased, thus into one
Step reduces the related training of early period, finally further decreases the cost of quotient's Claims Resolution.
It is appreciated that corresponding description information can equally be previously set and establish mapping for seriously injured degree corpus
Relationship is getting the corresponding seriously injured degree corpus set of the wounded to be settled a claim, equally can be according to mapping relationship searching to often
Then these description informations are alternatively obtained the second option information by the corresponding description information of one seriously injured degree corpus
Set.
In one embodiment, objective decision data are obtained according to default Claims Resolution data, comprising: when default Claims Resolution data
When quantity is preset quantity, the corresponding label information of the default Claims Resolution data of each is obtained, the corresponding individual of user identifier is obtained
Information obtains objective decision data according to label information and personal information.
Wherein, preset quantity refers to the quantity more than or equal to 2.The default corresponding label information of data of settling a claim refers to
Including gender, age section and city, e.g., label information of some default Claims Resolution data is " female ", " 30-50 ", " Beijing ",
" Shanghai ", " Guangzhou ";The corresponding personal information of user identifier includes gender, age and the city at place of patient to be settled a claim.
In the present embodiment, the personal information of patient is matched with the label information of Claims Resolution data, works as personal information
When with label information successful match, using the corresponding default Claims Resolution data of the label information as objective decision data.Such as, reason is preset
Pay for data A label information be " female ", " 30-50 ", " Beijing ", " Shanghai ", " Guangzhou ", preset Claims Resolution data B label information
For " male ", " 30-50 ", " Beijing ", " Shanghai ", " Guangzhou ";The personal information of some patient to be settled a claim includes: gender: female, year
Age: 38, address: Shanghai is then matched with the patient to be settled a claim for default Claims Resolution data A.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of Claims Resolution decision making device 400, comprising: condition of the injury data acquisition
Module 402, the first option information set sending module 404, the second option information set sending module 406, object matching data
Obtain module 408 and objective decision data transmission blocks 410, in which:
Condition of the injury data acquisition module 420 is used to obtain the condition of the injury data of the wounded to be settled a claim, is corresponded to according to condition of the injury data
Region of anatomy information;
First option information set sending module 404 is used to obtain from the semantic network pre-established to be believed with the region of anatomy
The associated disease damage corpus set of manner of breathing sends the first option information set to terminal according to disease damage corpus set;
Second option information set sending module 406 is for receiving terminal is returned according to the first option information set first
Selection result searches corresponding seriously injured degree corpus set according to first choice result, according to the condition of the injury from semantic network
Severity corpus set sends the second option information set to terminal;
Object matching data acquisition module 408 is used to receive the second selection that terminal is returned according to the second option information set
As a result, being obtained from preset matched data set wait manage according to region of anatomy information, first choice result, the second selection result
Pay for the corresponding object matching data of the wounded;
Objective decision data transmission blocks 410 are for obtaining the corresponding default Claims Resolution data of object matching data, according to pre-
If Claims Resolution data obtain objective decision data, objective decision data are sent to terminal.
In one embodiment, condition of the injury data acquisition module 420 is also used to receive the wound of the wounded to be settled a claim of terminal transmission
Feelings picture;Condition of the injury picture is input in the convolutional neural networks trained, the corresponding region of anatomy information of condition of the injury picture is obtained.
In one embodiment, above-mentioned apparatus further includes semantic network generation module, and semantic network generation module is for obtaining
The semantic tree of default dimension is taken, dimension is preset and includes at least the region of anatomy, disease damage and seriously injured degree;Calculate each dimension
The co-occurrence frequency of the corresponding node of the semantic tree of degree node corresponding with the semantic tree of other dimensions between any two;By co-occurrence frequency
Two nodes greater than preset threshold establish incidence relation, generative semantics network.
In one embodiment, object matching data acquisition module 408 is also used to obtain region of anatomy information, first respectively
Selection result, the corresponding weight of the second selection result;Calculate separately region of anatomy information, first choice result, the second selection knot
The matching degree of fruit and each matched data;The corresponding matching score value of each matched data is calculated according to weight and matching degree,
The matching maximum matched data of score value is obtained as object matching data.
In one embodiment, the first option information set sending module 404 is also used to every in disease damage corpus set
One disease damage corpus searches its corresponding description information from description information set;
The first option information set is obtained according to each corresponding description information of disease damage corpus.
In one embodiment, objective decision data transmission blocks 410 are also used to when the quantity of default Claims Resolution data be pre-
If when quantity, obtaining the corresponding label information of the default Claims Resolution data of each;Obtain the corresponding personal information of user identifier;According to
Label information and personal information obtain objective decision data.
Specific about Claims Resolution decision making device limits the restriction that may refer to above for Claims Resolution decision-making technique, herein not
It repeats again.Modules in above-mentioned Claims Resolution decision making device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as matched data, default Claims Resolution data.The network interface of the computer equipment is used for
It is communicated with external terminal by network connection.To realize a kind of Claims Resolution decision-making party when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of the condition of the injury data for obtaining the wounded to be settled a claim when executing computer program, according to
Condition of the injury data obtain corresponding region of anatomy information;It is obtained from the semantic network pre-established associated with region of anatomy information
Disease damage corpus set, according to disease damage corpus set to terminal send the first option information set;Terminal is received according to the first choosing
The first choice that item information aggregate returns from semantic network as a result, search corresponding seriously injured journey according to first choice result
Corpus set is spent, the second option information set is sent to terminal according to seriously injured degree corpus set;Terminal is received according to the
Two option information set return the second selection result, according to region of anatomy information, first choice result, the second selection result from
The corresponding object matching data of the wounded to be settled a claim are obtained in preset matched data set;It is corresponding pre- to obtain object matching data
If settling a claim data, objective decision data are obtained according to default Claims Resolution data, objective decision data are sent to terminal.
In one embodiment, the condition of the injury data for obtaining the wounded to be settled a claim obtain corresponding anatomy portion according to condition of the injury data
Position information, comprising: receive the condition of the injury picture for the wounded to be settled a claim that terminal is sent;Condition of the injury picture is input to the convolution mind trained
In network, the corresponding region of anatomy information of condition of the injury picture is obtained.
In one embodiment, disease damage language associated with region of anatomy information is obtained from the semantic network pre-established
Before material set, processor also performs the steps of the semantic tree for obtaining default dimension when executing computer program, presets dimension
Including at least the region of anatomy, disease damage and seriously injured degree;Calculate each dimension the corresponding node of semantic tree and other
The co-occurrence frequency of the corresponding node of the semantic tree of dimension between any two;Two nodes that co-occurrence frequency is greater than preset threshold are established
Incidence relation, generative semantics network.
In one embodiment, according to region of anatomy information, first choice result, the second selection result from preset matching
The corresponding object matching data of the wounded to be settled a claim are obtained in data acquisition system, comprising: obtain region of anatomy information, first choice respectively
As a result, the corresponding weight of the second selection result;Calculate separately region of anatomy information, first choice result, the second selection result with
The matching degree of each matched data;The corresponding matching score value of each matched data is calculated according to weight and matching degree, is obtained
The maximum matched data of score value is matched as object matching data.
In one embodiment, the first option information set is sent to terminal according to disease damage corpus set, comprising: to disease damage
Each of corpus set disease damage corpus searches its corresponding description information from description information set;According to each disease
The corresponding description information of damage corpus obtains the first option information set.
In one embodiment, objective decision data are obtained according to default Claims Resolution data, comprising: when default Claims Resolution data
When quantity is preset quantity, the corresponding label information of the default Claims Resolution data of each is obtained;Obtain the corresponding individual of user identifier
Information;Objective decision data are obtained according to label information and personal information.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of the condition of the injury data for obtaining the wounded to be settled a claim when being executed by processor, obtained pair according to condition of the injury data
The region of anatomy information answered;Disease damage corpus associated with region of anatomy information is obtained from the semantic network pre-established
It closes, the first option information set is sent to terminal according to disease damage corpus set;Terminal is received to be returned according to the first option information set
The first choice returned as a result, search corresponding seriously injured degree corpus set from semantic network according to first choice result,
The second option information set is sent to terminal according to seriously injured degree corpus set;Terminal is received according to the second option information collection
The second selection result returned is closed, according to region of anatomy information, first choice result, the second selection result from preset coupling number
According to obtaining the corresponding object matching data of the wounded to be settled a claim in set;The corresponding default Claims Resolution data of object matching data are obtained,
Objective decision data are obtained according to default Claims Resolution data, objective decision data are sent to terminal.
In one embodiment, the condition of the injury data for obtaining the wounded to be settled a claim obtain corresponding anatomy portion according to condition of the injury data
Position information, comprising: receive the condition of the injury picture for the wounded to be settled a claim that terminal is sent;Condition of the injury picture is input to the convolution mind trained
In network, the corresponding region of anatomy information of condition of the injury picture is obtained.
In one embodiment, disease damage language associated with region of anatomy information is obtained from the semantic network pre-established
Before material set, the semantic tree for obtaining default dimension is also performed the steps of when computer program is executed by processor, and presets dimension
Degree includes at least the region of anatomy, disease damage and seriously injured degree;Calculate each dimension the corresponding node of semantic tree and its
The co-occurrence frequency of the corresponding node of the semantic tree of his dimension between any two;Two nodes that co-occurrence frequency is greater than preset threshold are built
Vertical incidence relation, generative semantics network.
In one embodiment, according to region of anatomy information, first choice result, the second selection result from preset matching
The corresponding object matching data of the wounded to be settled a claim are obtained in data acquisition system, comprising: obtain region of anatomy information, first choice respectively
As a result, the corresponding weight of the second selection result;Calculate separately region of anatomy information, first choice result, the second selection result with
The matching degree of each matched data;The corresponding matching score value of each matched data is calculated according to weight and matching degree, is obtained
The maximum matched data of score value is matched as object matching data.
In one embodiment, the first option information set is sent to terminal according to disease damage corpus set, comprising: to disease damage
Each of corpus set disease damage corpus searches its corresponding description information from description information set;According to each disease
The corresponding description information of damage corpus obtains the first option information set.
In one embodiment, objective decision data are obtained according to default Claims Resolution data, comprising: when default Claims Resolution data
When quantity is preset quantity, the corresponding label information of the default Claims Resolution data of each is obtained;Obtain the corresponding individual of user identifier
Information;Objective decision data are obtained according to label information and personal information.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of Claims Resolution decision-making technique, which comprises
The condition of the injury data for obtaining the wounded to be settled a claim obtain corresponding region of anatomy information according to the condition of the injury data;
Disease damage corpus set associated with the region of anatomy information is obtained from the semantic network pre-established, according to described
Disease damage corpus set sends the first option information set to terminal;
The first choice that the terminal is returned according to the first option information set is received as a result, according to the first choice knot
Fruit searches corresponding seriously injured degree corpus set from the semantic network, according to the seriously injured degree corpus set
The second option information set is sent to the terminal;
The second selection result that the terminal is returned according to the second option information set is received, is believed according to the region of anatomy
Breath, the first choice result, second selection result obtain described the wounded to be settled a claim from preset matched data set
Corresponding object matching data;
The corresponding default Claims Resolution data of the object matching data are obtained, obtain objective decision number according to the default Claims Resolution data
According to the objective decision data are sent to the terminal.
2. the method according to claim 1, wherein the condition of the injury data for obtaining the wounded to be settled a claim, according to institute
It states condition of the injury data and obtains corresponding region of anatomy information, comprising:
Receive the condition of the injury picture for described the wounded to be settled a claim that the terminal is sent;
The condition of the injury picture is input in the convolutional neural networks trained, the corresponding region of anatomy of the condition of the injury picture is obtained
Information.
3. the method according to claim 1, wherein it is described from the semantic network pre-established obtain with it is described
Before the associated disease damage corpus set of region of anatomy information, comprising:
The semantic tree of default dimension is obtained, the default dimension includes at least the region of anatomy, disease damage and seriously injured degree;
Calculate the corresponding node of the semantic tree node corresponding with the semantic tree of other dimensions of each dimension being total between any two
Existing frequency;
Two nodes that the co-occurrence frequency is greater than preset threshold are established into incidence relation, generative semantics network.
4. the method according to claim 1, wherein it is described according to the region of anatomy information, it is described first choosing
It selects result, second selection result and obtains the corresponding object matching of described the wounded to be settled a claim from preset matched data set
Data, comprising:
The region of anatomy information, the first choice result, the corresponding weight of second selection result are obtained respectively;
Calculate separately the region of anatomy information, the first choice result, second selection result and each coupling number
According to matching degree;
The corresponding matching score value of each matched data is calculated according to the weight and the matching degree, it is maximum to obtain matching score value
Matched data as object matching data.
5. the method according to claim 1, wherein described send the to terminal according to the disease damage corpus set
One option information set, comprising:
To each of disease damage corpus set disease damage corpus, its corresponding description letter is searched from description information set
Breath;
The first option information set is obtained according to each corresponding description information of disease damage corpus.
6. according to claim 1 to method described in 5 any one, which is characterized in that described according to the default Claims Resolution data
Obtain objective decision data, comprising:
When the quantity of the default Claims Resolution data is preset quantity, the corresponding label letter of the default Claims Resolution data of each is obtained
Breath;
Obtain the corresponding personal information of the user identifier;
Objective decision data are obtained according to the label information and the personal information.
7. a kind of Claims Resolution decision making device, which is characterized in that described device includes:
Condition of the injury data acquisition module obtains corresponding for obtaining the condition of the injury data of the wounded to be settled a claim according to the condition of the injury data
Region of anatomy information;
First option information set sending module, for being obtained and the region of anatomy information from the semantic network pre-established
Associated disease damage corpus set sends the first option information set to terminal according to the disease damage corpus set;
Second option information set sending module, returned for receiving the terminal according to the first option information set
One selection result searches corresponding seriously injured degree corpus according to the first choice result from the semantic network
It closes, the second option information set is sent to the terminal according to the seriously injured degree corpus set;
Object matching data acquisition module, the second choosing returned for receiving the terminal according to the second option information set
It selects as a result, according to the region of anatomy information, the first choice result, second selection result from preset matched data
The corresponding object matching data of described the wounded to be settled a claim are obtained in set;
Objective decision data transmission blocks, for obtaining the corresponding default Claims Resolution data of the object matching data, according to described
Default Claims Resolution data obtain objective decision data, and the objective decision data are sent to the terminal.
8. device according to claim 7, which is characterized in that described device further includes semantic network generation module, described
Semantic network generation module is used to obtain the semantic tree of default dimension, the default dimension include at least the region of anatomy, disease damage with
And seriously injured degree;Calculate the corresponding node of the semantic tree node two corresponding with the semantic tree of other dimensions of each dimension
Co-occurrence frequency between two;Two nodes that the co-occurrence frequency is greater than preset threshold are established into incidence relation, generative semantics net
Network.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810924549.8A CN109509102B (en) | 2018-08-14 | 2018-08-14 | Claims settlement decision method, device, computer equipment and storage medium |
PCT/CN2019/096970 WO2020034808A1 (en) | 2018-08-14 | 2019-07-22 | Decision data acquisition method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810924549.8A CN109509102B (en) | 2018-08-14 | 2018-08-14 | Claims settlement decision method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109509102A true CN109509102A (en) | 2019-03-22 |
CN109509102B CN109509102B (en) | 2023-04-11 |
Family
ID=65745648
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810924549.8A Active CN109509102B (en) | 2018-08-14 | 2018-08-14 | Claims settlement decision method, device, computer equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109509102B (en) |
WO (1) | WO2020034808A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020034808A1 (en) * | 2018-08-14 | 2020-02-20 | 平安医疗健康管理股份有限公司 | Decision data acquisition method and apparatus, computer device, and storage medium |
CN112037235A (en) * | 2020-08-27 | 2020-12-04 | 平安科技(深圳)有限公司 | Injury picture automatic auditing method and device, electronic equipment and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113590839A (en) * | 2021-07-30 | 2021-11-02 | 支付宝(杭州)信息技术有限公司 | Knowledge graph construction method, target service execution method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002001460A2 (en) * | 2000-06-23 | 2002-01-03 | Computer Sciences Corporation | System and method for processing insurance claims |
CN107180389A (en) * | 2017-05-10 | 2017-09-19 | 平安科技(深圳)有限公司 | People's wound Claims Resolution setting loss fee calculating method, device, server and medium |
CN107798621A (en) * | 2017-08-30 | 2018-03-13 | 平安科技(深圳)有限公司 | Medical diagnosis on disease signal auditing method and device |
CN108153855A (en) * | 2017-12-22 | 2018-06-12 | 平安养老保险股份有限公司 | Method, apparatus, computer equipment and the storage medium of Claims Resolution image data storage |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109509102B (en) * | 2018-08-14 | 2023-04-11 | 深圳平安医疗健康科技服务有限公司 | Claims settlement decision method, device, computer equipment and storage medium |
-
2018
- 2018-08-14 CN CN201810924549.8A patent/CN109509102B/en active Active
-
2019
- 2019-07-22 WO PCT/CN2019/096970 patent/WO2020034808A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002001460A2 (en) * | 2000-06-23 | 2002-01-03 | Computer Sciences Corporation | System and method for processing insurance claims |
CN107180389A (en) * | 2017-05-10 | 2017-09-19 | 平安科技(深圳)有限公司 | People's wound Claims Resolution setting loss fee calculating method, device, server and medium |
CN107798621A (en) * | 2017-08-30 | 2018-03-13 | 平安科技(深圳)有限公司 | Medical diagnosis on disease signal auditing method and device |
CN108153855A (en) * | 2017-12-22 | 2018-06-12 | 平安养老保险股份有限公司 | Method, apparatus, computer equipment and the storage medium of Claims Resolution image data storage |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020034808A1 (en) * | 2018-08-14 | 2020-02-20 | 平安医疗健康管理股份有限公司 | Decision data acquisition method and apparatus, computer device, and storage medium |
CN112037235A (en) * | 2020-08-27 | 2020-12-04 | 平安科技(深圳)有限公司 | Injury picture automatic auditing method and device, electronic equipment and storage medium |
CN112037235B (en) * | 2020-08-27 | 2023-01-10 | 平安科技(深圳)有限公司 | Injury picture automatic auditing method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109509102B (en) | 2023-04-11 |
WO2020034808A1 (en) | 2020-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109255013A (en) | Claims Resolution decision-making technique, device, computer equipment and storage medium | |
CN109410071A (en) | Core protects data processing method, device, computer equipment and storage medium | |
CN109657246B (en) | Method for establishing extraction type machine reading understanding model based on deep learning | |
CN109509102A (en) | Claims Resolution decision-making technique, device, computer equipment and storage medium | |
CN109543516A (en) | Signing intention judgment method, device, computer equipment and storage medium | |
CN110021439A (en) | Medical data classification method, device and computer equipment based on machine learning | |
DE112017006166T5 (en) | METHOD AND SYSTEM FOR GENERATING A MULTI-RELEVANT LABEL | |
CN108153876A (en) | Intelligent answer method and system | |
CN109325041A (en) | Business data processing method, device, computer equipment and storage medium | |
CN104239440B (en) | Search result shows method and apparatus | |
CN109215796B (en) | Searching method, searching device, computer equipment and storage medium | |
CN110909145B (en) | Training method and device for multi-task model | |
CN109256216A (en) | Medical data processing method, device, computer equipment and storage medium | |
CN110688478B (en) | Answer sorting method, device and storage medium | |
CN110489951A (en) | Method, apparatus, computer equipment and the storage medium of risk identification | |
CN113742492B (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
CN109274845A (en) | Intelligent sound pays a return visit method, apparatus, computer equipment and storage medium automatically | |
CN107730485A (en) | Car damage identification method, electronic equipment and computer-readable recording medium | |
CN108804718A (en) | Data push method, device, electronic equipment and computer readable storage medium | |
CN110347776A (en) | Interest point name matching process, device, equipment and storage medium | |
WO2023134061A1 (en) | Artificial intelligence-based method and apparatus for determining drug feature information | |
CN110134761A (en) | Adjudicate document information retrieval method, device, computer equipment and storage medium | |
CN109377387A (en) | Medical insurance claims expense detection method, device, computer equipment and storage medium | |
CN108959529A (en) | Determination method, apparatus, equipment and the storage medium of problem answers type | |
CN113657343A (en) | Method and device for generating claim resource data based on machine learning |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220519 Address after: 518048 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |