CN109345399A - Claims Resolution methods of risk assessment, device, computer equipment and storage medium - Google Patents
Claims Resolution methods of risk assessment, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109345399A CN109345399A CN201811238812.4A CN201811238812A CN109345399A CN 109345399 A CN109345399 A CN 109345399A CN 201811238812 A CN201811238812 A CN 201811238812A CN 109345399 A CN109345399 A CN 109345399A
- Authority
- CN
- China
- Prior art keywords
- resolution
- entity
- data
- knowledge
- history
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012502 risk assessment Methods 0.000 title claims abstract description 40
- 238000013507 mapping Methods 0.000 claims abstract description 35
- 239000013598 vector Substances 0.000 claims description 62
- 238000000605 extraction Methods 0.000 claims description 51
- 238000012545 processing Methods 0.000 claims description 47
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 7
- 238000013441 quality evaluation Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000001568 sexual effect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008676 import Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005086 pumping Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses Claims Resolution methods of risk assessment, device, computer equipment and storage mediums.This method comprises: obtaining history Claims Resolution data, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map；It receives and currently reports Claims Resolution data, parsing currently reports the Claims Resolution factor for including in Claims Resolution data；The Claims Resolution factor is imported into initial knowledge map, calculate the relevance values in the Claims Resolution factor and the initial knowledge map between each entity, if there are the relevance values between entity and the Claims Resolution factor to be greater than preset relevance threshold, corresponding related entities are shown.This method is realized using knowledge mapping technology in conjunction with knowledge mapping data correlation sexual clorminance, finds new association factor.
Description
Technical field
The present invention relates to Claims Resolution technical field of risk control more particularly to a kind of Claims Resolution methods of risk assessment, device, calculating
Machine equipment and storage medium.
Background technique
Currently, by data finiteness and large-scale calculations platform lack etc. reasons, traditional insurance enterprise can only be based on
Limited feature (such as age, gender, situation of being in danger) extract the core that some simple rules go auxiliary insurance person in conjunction with experience
It protects, core pays for work.And with social development, new Insurance Fraud type continues to bring out, and air control function rule of thumb sets correlation
Parameter, it is insensitive for new fraud type；Claims Resolution risks and assumptions are manually summarized with regular relative dependencies of settling a claim, order of accuarcy
It is difficult to control.
Summary of the invention
The embodiment of the invention provides a kind of Claims Resolution methods of risk assessment, device, computer equipment and storage mediums, it is intended to
It solves Claims Resolution risks and assumptions in the prior art manually to summarize with regular relative dependencies of settling a claim, what order of accuarcy was difficult to control asks
Topic.
In a first aspect, the embodiment of the invention provides a kind of Claims Resolution methods of risk assessment comprising:
History Claims Resolution data are obtained, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map；
It receives and currently reports Claims Resolution data, parsing currently reports the Claims Resolution factor for including in Claims Resolution data；
The Claims Resolution factor is imported into initial knowledge map, is calculated every in the Claims Resolution factor and the initial knowledge map
Relevance values between one entity, if there is the relevance values between entity and the Claims Resolution factor to be greater than preset correlation threshold
Value, corresponding related entities are shown.
Second aspect, the embodiment of the invention provides a kind of Claims Resolution risk assessment devices comprising:
Initial knowledge map construction unit carries out knowledge graph according to history Claims Resolution data for obtaining history Claims Resolution data
The building of spectrum obtains initial knowledge map；
Claims Resolution factor resolution unit currently reports Claims Resolution data for receiving, and parsing, which currently reports in Claims Resolution data, includes
The Claims Resolution factor；
Related entities acquiring unit calculates the Claims Resolution factor for the Claims Resolution factor to be imported initial knowledge map
With the relevance values in the initial knowledge map between each entity, if having entity and it is described Claims Resolution the factor between correlation
Value is greater than preset relevance threshold, and corresponding related entities are shown.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
Claims Resolution methods of risk assessment described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of storage mediums, wherein the storage medium is stored with calculating
Machine program, the computer program make the processor execute Claims Resolution wind described in above-mentioned first aspect when being executed by a processor
Dangerous appraisal procedure.
The embodiment of the invention provides a kind of Claims Resolution methods of risk assessment, device, computer equipment and storage mediums.The party
Method will currently report the Claims Resolution factor for including in Claims Resolution data to import initial knowledge map, calculate the Claims Resolution factor and described first
Relevance values in beginning knowledge mapping between each entity, if there have the relevance values between entity and the Claims Resolution factor to be greater than to be pre-
If relevance threshold, corresponding related entities are shown.The method achieve combine knowledge mapping data correlation excellent
Gesture finds new association factor.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention；
Fig. 2 is the sub-process schematic diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention；
Fig. 3 is another sub-process schematic diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention；
Fig. 5 is another sub-process schematic diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of Claims Resolution risk assessment device provided in an embodiment of the present invention；
Fig. 7 is the subelement schematic block diagram of Claims Resolution risk assessment device provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of Claims Resolution risk assessment device provided in an embodiment of the present invention；
Fig. 9 is another subelement schematic block diagram of Claims Resolution risk assessment device provided in an embodiment of the present invention；
Figure 10 is another subelement schematic block diagram of Claims Resolution risk assessment device provided in an embodiment of the present invention；
Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is the flow diagram of Claims Resolution methods of risk assessment provided in an embodiment of the present invention, the Claims Resolution
Methods of risk assessment is applied in management server, and this method is held by the application software being installed in management server
Row, management server are the enterprise terminal for carrying out Claims Resolution risk assessment.
As shown in Figure 1, the method comprising the steps of S101~S103.
S101, history Claims Resolution data are obtained, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge
Map.
In the present embodiment, number of policy is included at least in history Claims Resolution data, insurer, insured amount, type of insuring, is thrown
Protect the data such as validity period, insurer address, insurer's contact number, insurer's passport NO.；These data can act as and manage
Pay for relevant risks and assumptions.After the history for obtaining magnanimity settles a claim data, so that it may be known according to history Claims Resolution data building
Know map.
Wherein, the logical construction of knowledge mapping is divided into two levels: data Layer and mode layer.
In the data Layer of knowledge mapping, knowledge is that unit is stored in chart database with true (fact).If with [entity-
Relation-entity] or [entity-attribute-value] triple as true primary expression mode, then be stored in chart database
All data will constitute huge entity relationship network, form the map of knowledge.
Mode layer is the core of knowledge mapping on data Layer, and what it is in mode layer storage is knowledge by refinement, is led to
The mode layer for carrying out managerial knowledge map frequently with ontology library, by ontology library to the tenability of axiom, rule and constraint condition
Carry out the connection between the objects such as type and the attribute of Specification entity, relationship and entity.Status of the ontology library in knowledge mapping
It is equivalent to the mold of knowledge base, the knowledge base redundancy knowledge for possessing ontology library is less.
The building process of knowledge mapping be from initial data, using a series of technological means automatically or semi-automatically,
Knowledge element (i.e. true) is extracted from initial data, and is deposited into the data Layer of knowledge base and the process of mode layer.This
It is the process that an iteration updates, according to the logic of knowledge acquisition, each round iteration includes three phases: information extraction, knowledge
Fusion and knowledge processing.
By the way that the entity of history Claims Resolution data mining and relationship are constructed knowledge mapping, the knowledge mapping risk factor is not
Can only be associated with other risks and assumptions, can be also associated with other data, by figure mining algorithm can extract with it is current on
The maximally related data neighborhood of report Claims Resolution data or Neighbourhood set, i.e., find new correlation factor from associated data.
In one embodiment, as shown in Fig. 2, step S101 includes:
The correlation between entity, attribute and entity for including described in S1011, extraction history Claims Resolution data, obtains
Knowledge representation information after to extraction；
S1012, successively entity link and knowledge are carried out to the knowledge representation information after extraction merge, obtain fused knowing
Know expressing information；
S1013, ontological construction, knowledge reasoning and quality evaluation are successively carried out to fused knowledge representation information, obtained
Initial knowledge map.
Wherein, knowledge mapping has both bottom-up and top-down building modes.Wherein, top-down building is to borrow
The structured data sources such as encyclopaedia class internet site are helped, ontology and pattern information are extracted from quality data, is added to knowledge
In library；Bottom-up building is then to extract resources mode by certain technological means from the data of open acquisition, select
The higher new model of wherein confidence level is selected to be added in knowledge base after manual examination and verification.
Knowledge mapping mostly uses greatly bottom-up mode to construct at present, also main in embodiments herein to use the bottom of from
Upward knowledge mapping constructing technology is divided into 3 levels according to the process of knowledge acquisition: information extraction, knowledge fusion and knowing
Know processing.By carrying out above-mentioned 3 treatment processes to history Claims Resolution data, initial knowledge map can be obtained.
It is the process that an iteration updates using the process that bottom-up mode constructs knowledge mapping, each round updates packet
Include 3 steps:
A1) information extraction, i.e., from being extracted in various types of data sources between entity (concept), attribute and entity
Correlation forms the knowledge representation of ontological on this basis；
A2) knowledge fusion needs to integrate it after obtaining new knowledge, to eliminate contradiction and ambiguity, such as it is certain
Entity may there are many expression, some specific appellation perhaps to correspond to multiple and different entities etc.；
A3) knowledge is processed, and for the new knowledge by fusion, needs after quality evaluation (the artificial ginseng of part needs
With examination), qualified part could be added in knowledge base, to ensure the quality of knowledge base, after increasing data newly, Ke Yijin
Row knowledge reasoning expands existing knowledge, acquires new knowledge.
In one embodiment, as shown in figure 3, step S1011 includes:
S10111, name entity is extracted from history Claims Resolution data by condition random field, obtains the first processing data；
S10112, entity attribute extraction is carried out to the first processing data, obtains second processing data；
S10113, attribute extraction is carried out to second processing data, the knowledge representation information after being extracted.
In the present embodiment, when carrying out information extraction, critical issue therein is how to take out automatically from heterogeneous data source
Breath of winning the confidence obtains candidate blocks of knowledge.Information extraction be it is a kind of automatically from it is semi-structured and without being extracted in structured data it is real
The technology of the structured messages such as body, relationship and entity attribute.Related key technology includes: name Entity recognition, relationship
Extraction and attribute extraction.
Name Entity recognition (named entity recognition, NER) is also referred to as entity extraction, refers to from text data
Concentration automatically identifies name entity, frequently with method be and be based on condition random field carry out entity Boundary Recognition.Wherein item
Part random field (conditional random fields, abbreviation CRF or CRFs), is a kind of discriminate probabilistic model, be with
The one kind on airport is usually used in mark or analytical sequence data, such as natural language text or biological sequence.Condition random field is tool
There is undirected graph model, the vertex in figure represents stochastic variable, and the line between vertex represents the dependence relation between stochastic variable,
In condition random field, stochastic variable Y's is distributed as conditional probability, and given observed value is then stochastic variable X.
History settles a claim data by entity extraction, and what is obtained is the name entity of series of discrete, in order to obtain semantic letter
Breath, it is also necessary to extract the incidence relation between entity from relevant corpus, be contacted entity (concept) by incidence relation
Get up, it can the webbed structure of knowledge of shape.At this point, can be by being based on self-supervisory (self- in embodiments herein
Supervised) opening imformation of mode of learning extracts prototype system (TextRunner), which uses a small amount of handmarking
Data obtain an entity relationship disaggregated model as training set accordingly, then according to the entity relationship disaggregated model to open number
According to classifying, [entity-relationship-entity] triple is identified according to classification results training model-naive Bayesian, to realize
Entity attribute extraction is carried out to the first processing data, obtains second processing data.
The target of attribute extraction is the attribute information that special entity is acquired from different aforementioned sources.Such as some public
Personage can obtain the information such as its pet name, birthday, nationality, education background from network public information.Attribute extraction technology can
Collect these information from a variety of data sources, realizes completely delineating to entity attribute.Due to that entity attributes can be regarded
A kind of noun sexual intercourse between entity and attribute value, therefore attribute extraction problem can also be considered as to Relation extraction problem.
It can be used for based on the semi-structured data of encyclopaedia class website by extracting generation training corpus automatically in embodiments herein
Then training entity attribute marking model is applied to the entity attribute pumping to unstructured data.
In one embodiment, as shown in figure 4, step S10111 includes:
The entity class that S10111a, acquisition have been concluded；
S10111b, history data of settling a claim are compared and entity with the entity class concluded by condition random field
Boundary Recognition obtains the first processing data.
In the present embodiment, when carrying out entity extraction, existing 112 concluded kind entity class can be used, and be based on
Condition random field carries out entity Boundary Recognition, finally realizes the automatic classification to entity using adaptive perceptron, to realize
History data of settling a claim are compared and entity Boundary Recognition with the entity class concluded by condition random field, obtain first
Handle data.
S102, reception currently report Claims Resolution data, and parsing currently reports the Claims Resolution factor for including in Claims Resolution data.
In the present embodiment, user generally comprises insurance class by current report in Claims Resolution data that intelligent terminal is reported
Type (such as vehicle insurance produces danger, life insurance) reports the data such as dangerous time, report strategical vantage point location, the report danger type in data of reporting a case to the security authorities, report strategical vantage point location
Etc. information all can be considered the Claims Resolution factor.According to the Claims Resolution factor and obtained initial knowledge figure currently reported in Claims Resolution data
Spectrum can calculate the correlation factor for exceeding preset relevance threshold in initial knowledge map with Claims Resolution factor correlativity value.
S103, the Claims Resolution factor is imported into initial knowledge map, calculates the Claims Resolution factor and the initial knowledge figure
Relevance values in spectrum between each entity, if there have the relevance values between entity and the Claims Resolution factor to be greater than to be preset related
Property threshold value, corresponding related entities are shown.
In the present embodiment, the related entities for exceeding preset relevance threshold with Claims Resolution factor correlativity value are being calculated
When, the model based on distance can be used calculated (calculate the Claims Resolution factor with it is each in the initial knowledge map
The distance between entity is using as relevance values).Because each entity in initial knowledge map and other entities can be into
Then row vector calculates after each entity vectorization in corresponding term vector and the Claims Resolution factor between corresponding semantic vector
The Pearson came degree of correlation can obtain the relevance values of the entity factor and the factor of settling a claim.Later, calculate the Claims Resolution factor with it is described
Relevance values in initial knowledge map between each entity, if there is the relevance values between entity and the Claims Resolution factor to be greater than
Preset relevance threshold shows corresponding related entities, can recommend to choose which related entities to construct Claims Resolution
Then.
In one embodiment, as shown in figure 5, step S103 includes:
S1031, corresponding semantic vector in the Claims Resolution factor is obtained；
S1032, the corresponding term vector of each entity in included entity is obtained in initial knowledge map；
S1033, the Pearson came degree of correlation for obtaining corresponding semantic vector and each term vector in the Claims Resolution factor；
The Pearson came degree of correlation between the term vector of S1034, if it exists entity and the semantic vector exceeds preset phase
Closing property threshold value, obtains the term vector of correspondent entity, and related entities corresponding with term vector.
It include multiple keywords in the Claims Resolution factor in embodiments herein, each keyword is again one corresponding
Term vector obtains corresponding in the Claims Resolution factor by the term vector of multiple keywords respectively multiplied by summing after respective weights value
Semantic vector.Semantic vector term vector corresponding with entity each in included entity in initial knowledge map is sought into skin later
Your inferior degree of correlation, with obtain word of the Pearson came degree of correlation between the semantic vector beyond preset relevance threshold to
Amount, and the corresponding related entities of term vector are obtained, these related entities can be as the candidate Claims Resolution factor of building Claims Resolution then.Its
In, the Pearson came degree of correlation between two vectors is defined as the quotient of covariance and standard deviation between two variables.
This method will currently report the Claims Resolution factor for including in Claims Resolution data to import initial knowledge map, calculate the Claims Resolution
Relevance values in the factor and the initial knowledge map between each entity, if there is the phase between entity and the Claims Resolution factor
Closing property value is greater than preset relevance threshold, and corresponding related entities are shown.The method achieve combine knowledge mapping
Data correlation sexual clorminance finds new association factor.
The embodiment of the present invention also provides a kind of Claims Resolution risk assessment device, and the Claims Resolution risk assessment device is aforementioned for executing
Any embodiment of Claims Resolution methods of risk assessment.Specifically, referring to Fig. 6, Fig. 6 is Claims Resolution risk provided in an embodiment of the present invention
Assess the schematic block diagram of device.The Claims Resolution risk assessment device 100 can be configured in management server.
As shown in fig. 6, Claims Resolution risk assessment device 100 includes initial knowledge map construction unit 101, Claims Resolution factor parsing
Unit 102 and related entities acquiring unit 103.
Wherein, initial knowledge map construction unit 101, for obtain history Claims Resolution data, according to history settle a claim data into
The building of row knowledge mapping obtains initial knowledge map.
In the present embodiment, number of policy is included at least in history Claims Resolution data, insurer, insured amount, type of insuring, is thrown
Protect the data such as validity period, insurer address, insurer's contact number, insurer's passport NO.；These data can act as and manage
Pay for relevant risks and assumptions.After the history for obtaining magnanimity settles a claim data, so that it may be known according to history Claims Resolution data building
Know map.
By the way that the entity of history Claims Resolution data mining and relationship are constructed knowledge mapping, the knowledge mapping risk factor is not
Can only be associated with other risks and assumptions, can be also associated with other data, by figure mining algorithm can extract with it is current on
The maximally related data neighborhood of report Claims Resolution data or Neighbourhood set, i.e., find new correlation factor from associated data.
In one embodiment, as shown in fig. 7, initial knowledge map construction unit 101 includes:
Entity extracting unit 1011, for extract history Claims Resolution data described in include entity, attribute and entity it
Between correlation, the knowledge representation information after being extracted；
Knowledge fusion unit 1012, for carrying out successively entity link and knowledge conjunction to the knowledge representation information after extraction
And obtain fused knowledge representation information；
Knowledge processes unit 1013, for successively carrying out ontological construction, knowledge reasoning to fused knowledge representation information
And quality evaluation, obtain initial knowledge map.
Knowledge mapping mostly uses greatly bottom-up mode to construct at present, also main in embodiments herein to use the bottom of from
Upward knowledge mapping constructing technology is divided into 3 levels according to the process of knowledge acquisition: information extraction, knowledge fusion and knowing
Know processing.By carrying out above-mentioned 3 treatment processes to history Claims Resolution data, initial knowledge map can be obtained.
In one embodiment, as shown in figure 8, entity extracting unit 1011, comprising:
First data processing unit 10111, it is real for extracting name from history Claims Resolution data by condition random field
Body obtains the first processing data；
Second data processing unit 10112 obtains second processing for carrying out entity attribute extraction to the first processing data
Data；
Attribute extraction unit 10113, for carrying out attribute extraction to second processing data, the knowledge representation after being extracted
Information.
In the present embodiment, when carrying out information extraction, critical issue therein is how to take out automatically from heterogeneous data source
Breath of winning the confidence obtains candidate blocks of knowledge.Information extraction be it is a kind of automatically from it is semi-structured and without being extracted in structured data it is real
The technology of the structured messages such as body, relationship and entity attribute.Related key technology includes: name Entity recognition, relationship
Extraction and attribute extraction.
Name Entity recognition (named entity recognition, NER) is also referred to as entity extraction, refers to from text data
Concentration automatically identifies name entity, frequently with method be and be based on condition random field carry out entity Boundary Recognition.Wherein item
Part random field (conditional random fields, abbreviation CRF or CRFs), is a kind of discriminate probabilistic model, be with
The one kind on airport is usually used in mark or analytical sequence data, such as natural language text or biological sequence.Condition random field is tool
There is undirected graph model, the vertex in figure represents stochastic variable, and the line between vertex represents the dependence relation between stochastic variable,
In condition random field, stochastic variable Y's is distributed as conditional probability, and given observed value is then stochastic variable X.
History settles a claim data by entity extraction, and what is obtained is the name entity of series of discrete, in order to obtain semantic letter
Breath, it is also necessary to extract the incidence relation between entity from relevant corpus, be contacted entity (concept) by incidence relation
Get up, it can the webbed structure of knowledge of shape.At this point, can be by being based on self-supervisory (self- in embodiments herein
Supervised) opening imformation of mode of learning extracts prototype system (TextRunner), which uses a small amount of handmarking
Data obtain an entity relationship disaggregated model as training set accordingly, then according to the entity relationship disaggregated model to open number
According to classifying, [entity-relationship-entity] triple is identified according to classification results training model-naive Bayesian, to realize
Entity attribute extraction is carried out to the first processing data, obtains second processing data.
The target of attribute extraction is the attribute information that special entity is acquired from different aforementioned sources.Such as some public
Personage can obtain the information such as its pet name, birthday, nationality, education background from network public information.Attribute extraction technology can
Collect these information from a variety of data sources, realizes completely delineating to entity attribute.Due to that entity attributes can be regarded
A kind of noun sexual intercourse between entity and attribute value, therefore attribute extraction problem can also be considered as to Relation extraction problem.
It can be used for based on the semi-structured data of encyclopaedia class website by extracting generation training corpus automatically in embodiments herein
Then training entity attribute marking model is applied to the entity attribute pumping to unstructured data.
In one embodiment, as shown in figure 9, the first data processing unit 10111 includes:
History entity class acquiring unit 10111a, for obtaining the entity class concluded；
Entity boundary recognition unit 10111b, for passing through condition random field to entity history Claims Resolution data and concluded
Classification be compared with entity Boundary Recognition, obtain the first processing data.
In the present embodiment, when carrying out entity extraction, existing 112 concluded kind entity class can be used, and be based on
Condition random field carries out entity Boundary Recognition, finally realizes the automatic classification to entity using adaptive perceptron, to realize
History data of settling a claim are compared and entity Boundary Recognition with the entity class concluded by condition random field, obtain first
Handle data.
Claims Resolution factor resolution unit 102 currently reports Claims Resolution data for receiving, and parsing currently reports wraps in Claims Resolution data
The Claims Resolution factor included.
In the present embodiment, user generally comprises insurance class by current report in Claims Resolution data that intelligent terminal is reported
Type (such as vehicle insurance produces danger, life insurance) reports the data such as dangerous time, report strategical vantage point location, the report danger type in data of reporting a case to the security authorities, report strategical vantage point location
Etc. information all can be considered the Claims Resolution factor.According to the Claims Resolution factor and obtained initial knowledge figure currently reported in Claims Resolution data
Spectrum can calculate the correlation factor for exceeding preset relevance threshold in initial knowledge map with Claims Resolution factor correlativity value.
Related entities acquiring unit 103, for by the Claims Resolution factor importing initial knowledge map, calculate the Claims Resolution because
The sub relevance values between each entity in the initial knowledge map, if having related between entity and the Claims Resolution factor
Property value be greater than preset relevance threshold, corresponding related entities are shown.
In the present embodiment, the related entities for exceeding preset relevance threshold with Claims Resolution factor correlativity value are being calculated
When, the model based on distance can be used to be calculated.Because of each entity and other entities in initial knowledge map
To carry out vectorization, then calculate after each entity vectorization corresponding term vector and corresponding semantic vector in the Claims Resolution factor it
Between the Pearson came degree of correlation, can obtain the entity factor and settle a claim the factor relevance values.Later, calculate the Claims Resolution factor and
Relevance values in the initial knowledge map between each entity, if there is the relevance values between entity and the Claims Resolution factor
Greater than preset relevance threshold, corresponding related entities are shown, can recommend to choose which related entities to construct
Claims Resolution is then.
In one embodiment, as shown in Figure 10, related entities acquiring unit 103 includes:
Semantic vector acquiring unit 1031, for obtaining corresponding semantic vector in the Claims Resolution factor；
Term vector acquiring unit 1032, for obtaining in initial knowledge map the corresponding word of each entity in included entity
Vector；
Pearson came correlation calculating unit 1033, for obtaining corresponding semantic vector and each word in the Claims Resolution factor
The Pearson came degree of correlation of vector；
Related entities judging unit 1034, for the Pearson came between the term vector and the semantic vector of entity if it exists
The degree of correlation exceeds preset relevance threshold, obtains the term vector of correspondent entity, and related entities corresponding with term vector.
It include multiple keywords in the Claims Resolution factor in embodiments herein, each keyword is again one corresponding
Term vector obtains corresponding in the Claims Resolution factor by the term vector of multiple keywords respectively multiplied by summing after respective weights value
Semantic vector.Semantic vector term vector corresponding with entity each in included entity in initial knowledge map is sought into skin later
Your inferior degree of correlation, with obtain word of the Pearson came degree of correlation between the semantic vector beyond preset relevance threshold to
Amount, and the corresponding related entities of term vector are obtained, these related entities can be as the candidate Claims Resolution factor of building Claims Resolution then.
The device will currently report the Claims Resolution factor for including in Claims Resolution data to import initial knowledge map, calculate the Claims Resolution
Relevance values in the factor and the initial knowledge map between each entity, if there is the phase between entity and the Claims Resolution factor
Closing property value is greater than preset relevance threshold, and corresponding related entities are shown.The method achieve combine knowledge mapping
Data correlation sexual clorminance finds new association factor.
Above-mentioned Claims Resolution risk assessment device can be implemented as the form of computer program, which can such as scheme
It is run in computer equipment shown in 11.
Figure 11 is please referred to, Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Refering to fig. 11, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute Claims Resolution methods of risk assessment.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute Claims Resolution methods of risk assessment.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Figure 11, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: history Claims Resolution data are obtained, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map；It receives
Claims Resolution data are currently reported, parsing currently reports the Claims Resolution factor for including in Claims Resolution data；The Claims Resolution factor is imported initial
Knowledge mapping calculates the relevance values in the Claims Resolution factor and the initial knowledge map between each entity, if there is entity
Relevance values between the Claims Resolution factor are greater than preset relevance threshold, and corresponding related entities are shown.
In one embodiment, processor 502 is executing the building that knowledge mapping is carried out according to history Claims Resolution data, obtains just
It when the step of beginning knowledge mapping, performs the following operations: extracting entity, attribute and the entity for including described in history Claims Resolution data
Between correlation, the knowledge representation information after being extracted；Successively chain of entities is carried out to the knowledge representation information after extraction
It connects and merges with knowledge, obtain fused knowledge representation information；To fused knowledge representation information successively carry out ontological construction,
Knowledge reasoning and quality evaluation obtain initial knowledge map.
In one embodiment, processor 502 execute know extract history Claims Resolution data described in include entity, attribute with
And the correlation between entity, when the step of the knowledge representation information after being extracted, perform the following operations: by condition with
Airport extracts name entity from history Claims Resolution data, obtains the first processing data；Entity category is carried out to the first processing data
Property extract, obtain second processing data；Attribute extraction is carried out to second processing data, the knowledge representation information after being extracted.
In one embodiment, processor 502 extracts name from history Claims Resolution data by condition random field in execution
Entity performs the following operations when obtaining the step of the first processing data: obtaining the entity class concluded；Pass through condition random
History Claims Resolution data are compared with the entity class concluded for field and entity Boundary Recognition, obtains the first processing data.
In one embodiment, processor 502 is executing the relevance values between acquisition and the Claims Resolution factor beyond default
Relevance threshold related entities step when, perform the following operations: obtaining corresponding semantic vector in the Claims Resolution factor；
Obtain in initial knowledge map the corresponding term vector of each entity in included entity；Obtain corresponding language in the Claims Resolution factor
The Pearson came degree of correlation of adopted vector and each term vector；Pearson came between the term vector of entity and the semantic vector if it exists
The degree of correlation exceeds preset relevance threshold, obtains the term vector of correspondent entity, and related entities corresponding with term vector.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Figure 11 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 11,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Storage medium is provided in another embodiment of the invention.The storage medium can be that non-volatile computer can
Read storage medium.The storage medium is stored with computer program, and following step is realized when wherein computer program is executed by processor
It is rapid: to obtain history Claims Resolution data, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map；It receives
Claims Resolution data are currently reported, parsing currently reports the Claims Resolution factor for including in Claims Resolution data；The Claims Resolution factor is imported initial
Knowledge mapping calculates the relevance values in the Claims Resolution factor and the initial knowledge map between each entity, if there is entity
Relevance values between the Claims Resolution factor are greater than preset relevance threshold, and corresponding related entities are shown.
In one embodiment, the building that knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map
The step of, comprising: the correlation between entity, attribute and the entity for including described in history Claims Resolution data is extracted, is obtained
Knowledge representation information after extraction；Successively entity link is carried out to the knowledge representation information after extraction and knowledge merges, is melted
Knowledge representation information after conjunction；Ontological construction, knowledge reasoning and quality evaluation are successively carried out to fused knowledge representation information,
Obtain initial knowledge map.
In one embodiment, described to extract between entity, attribute and the entity for including described in history Claims Resolution data
The step of correlation, knowledge representation information after being extracted, comprising: settled a claim by condition random field from history and mentioned in data
Name entity is taken out, the first processing data are obtained；Entity attribute extraction is carried out to the first processing data, obtains second processing number
According to；Attribute extraction is carried out to second processing data, the knowledge representation information after being extracted.
In one embodiment, described settled a claim by condition random field from history extracts name entity in data, obtains the
The step of one processing data, comprising: obtain the entity class concluded；By condition random field to history settle a claim data with returned
The entity class received be compared with entity Boundary Recognition, obtain the first processing data.
In one embodiment, the relevance values between the acquisition and the Claims Resolution factor exceed preset relevance threshold
Related entities the step of, comprising: obtain corresponding semantic vector in the Claims Resolution factor；It obtains and is wrapped in initial knowledge map
Include the corresponding term vector of each entity in entity；Obtain the skin of corresponding semantic vector and each term vector in the Claims Resolution factor
The inferior degree of correlation of that；The Pearson came degree of correlation between the term vector of entity and the semantic vector exceeds preset correlation if it exists
Threshold value obtains the term vector of correspondent entity, and related entities corresponding with term vector.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The all or part of part or the technical solution that technology contributes can be embodied in the form of software products, should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or
The various media that can store program code such as person's CD.
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 readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of Claims Resolution methods of risk assessment characterized by comprising
History Claims Resolution data are obtained, the building of knowledge mapping is carried out according to history Claims Resolution data, obtains initial knowledge map；
It receives and currently reports Claims Resolution data, parsing currently reports the Claims Resolution factor for including in Claims Resolution data；
The Claims Resolution factor is imported into initial knowledge map, calculates each reality in the Claims Resolution factor and the initial knowledge map
Relevance values between body will if there is the relevance values between entity and the Claims Resolution factor to be greater than preset relevance threshold
Corresponding related entities are shown.
2. Claims Resolution methods of risk assessment according to claim 1, which is characterized in that described to be carried out according to history Claims Resolution data
The building of knowledge mapping obtains initial knowledge map, comprising:
The correlation between entity, attribute and the entity for including described in history Claims Resolution data is extracted, after being extracted
Knowledge representation information；
Successively entity link is carried out to the knowledge representation information after extraction and knowledge merges, obtains fused knowledge representation letter
Breath；
Ontological construction, knowledge reasoning and quality evaluation are successively carried out to fused knowledge representation information, obtain initial knowledge figure
Spectrum.
3. Claims Resolution methods of risk assessment according to claim 2, which is characterized in that institute in the extraction history Claims Resolution data
State including entity, the correlation between attribute and entity, knowledge representation information after being extracted, comprising:
Name entity is extracted from history Claims Resolution data by condition random field, obtains the first processing data；
Entity attribute extraction is carried out to the first processing data, obtains second processing data；
Attribute extraction is carried out to second processing data, the knowledge representation information after being extracted.
4. Claims Resolution methods of risk assessment according to claim 3, which is characterized in that it is described by condition random field from history
Name entity is extracted in Claims Resolution data, obtains the first processing data, comprising:
Obtain the entity class concluded；
History data of settling a claim are compared and entity Boundary Recognition with the entity class concluded by condition random field, are obtained
First processing data.
5. Claims Resolution methods of risk assessment according to claim 1, which is characterized in that it is described acquisition with the Claims Resolution factor it
Between relevance values exceed preset relevance threshold related entities, comprising:
Obtain corresponding semantic vector in the Claims Resolution factor；
Obtain in initial knowledge map the corresponding term vector of each entity in included entity；
Obtain the Pearson came degree of correlation of corresponding semantic vector and each term vector in the Claims Resolution factor；
The Pearson came degree of correlation between the term vector of entity and the semantic vector exceeds preset relevance threshold if it exists, obtains
Take the term vector of correspondent entity, and related entities corresponding with term vector.
6. a kind of Claims Resolution risk assessment device characterized by comprising
Initial knowledge map construction unit carries out knowledge mapping according to history Claims Resolution data for obtaining history Claims Resolution data
Building, obtains initial knowledge map；
Claims Resolution factor resolution unit currently reports Claims Resolution data for receiving, and parsing currently reports the reason for including in Claims Resolution data
Pay for the factor；
Related entities acquiring unit calculates the Claims Resolution factor and institute for the Claims Resolution factor to be imported initial knowledge map
The relevance values in initial knowledge map between each entity are stated, if there are the relevance values between entity and the Claims Resolution factor big
In preset relevance threshold, corresponding related entities are shown.
7. Claims Resolution risk assessment device according to claim 6, which is characterized in that the initial knowledge map construction list
Member, comprising:
Entity extracting unit, it is mutual between the entity, attribute and the entity that include described in history Claims Resolution data for extracting
Relationship, the knowledge representation information after being extracted；
Knowledge fusion unit is melted for carrying out successively entity link and knowledge merging to the knowledge representation information after extraction
Knowledge representation information after conjunction；
Knowledge processes unit, comments for successively carrying out ontological construction, knowledge reasoning and quality to fused knowledge representation information
Estimate, obtains initial knowledge map.
8. Claims Resolution risk assessment device according to claim 7, which is characterized in that the entity extracting unit, comprising:
First data processing unit extracts name entity in data for settling a claim by condition random field from history, obtains the
One processing data；
Second data processing unit obtains second processing data for carrying out entity attribute extraction to the first processing data；
Attribute extraction unit, for carrying out attribute extraction to second processing data, the knowledge representation information after being extracted.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in Claims Resolution methods of risk assessment.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, and the computer program is worked as
The processor is set to execute such as Claims Resolution methods of risk assessment described in any one of claim 1 to 5 when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811238812.4A CN109345399B (en) | 2018-10-23 | 2018-10-23 | Method, device, computer equipment and storage medium for evaluating risk of claim settlement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811238812.4A CN109345399B (en) | 2018-10-23 | 2018-10-23 | Method, device, computer equipment and storage medium for evaluating risk of claim settlement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109345399A true CN109345399A (en) | 2019-02-15 |
| CN109345399B CN109345399B (en) | 2024-03-26 |
Family
ID=65311336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811238812.4A Active CN109345399B (en) | 2018-10-23 | 2018-10-23 | Method, device, computer equipment and storage medium for evaluating risk of claim settlement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109345399B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060166A (en) * | 2019-03-13 | 2019-07-26 | 平安科技（深圳）有限公司 | Intelligence Claims Resolution method, apparatus, computer equipment and storage medium |
| CN110322216A (en) * | 2019-05-30 | 2019-10-11 | 阿里巴巴集团控股有限公司 | The case checking method and device of knowledge based map |
| CN110503236A (en) * | 2019-07-08 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk Forecast Method, device, equipment and the storage medium of knowledge based map |
| CN110689322A (en) * | 2019-09-27 | 2020-01-14 | 成都知识视觉科技有限公司 | Artificial intelligence auxiliary claims checking system suitable for insurance claims settlement process |
| CN110866836A (en) * | 2019-11-14 | 2020-03-06 | 支付宝(杭州)信息技术有限公司 | Computer-implemented medical insurance scheme auditing method and device |
| CN111652704A (en) * | 2020-06-09 | 2020-09-11 | 唐松 | Financial credit risk assessment method based on knowledge graph and graph deep learning |
| CN111797406A (en) * | 2020-07-15 | 2020-10-20 | 智博云信息科技(广州)有限公司 | Medical fund data analysis processing method and device and readable storage medium |
| CN111915444A (en) * | 2019-05-08 | 2020-11-10 | 国际商业机器公司 | Intelligent learning and application of operational rules |
| CN112069808A (en) * | 2020-09-28 | 2020-12-11 | 深圳壹账通智能科技有限公司 | Financing wind control method and device, computer equipment and storage medium |
| CN112215711A (en) * | 2020-10-13 | 2021-01-12 | 中国银行股份有限公司 | Product risk assessment method and device |
| CN112508745A (en) * | 2021-02-05 | 2021-03-16 | 北京肇祺信息科技有限公司 | Document evaluation method and device |
| WO2021135290A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳Tcl新技术有限公司 | Information visualization method, apparatus and device based on knowledge graph, and storage medium |
| CN113379053A (en) * | 2020-12-17 | 2021-09-10 | 中国人民公安大学 | Emergency response decision-making method and device and electronic equipment |
| CN113434627A (en) * | 2020-03-18 | 2021-09-24 | 中国电信股份有限公司 | Work order processing method and device and computer readable storage medium |
| CN113469577A (en) * | 2021-07-27 | 2021-10-01 | 中国银行股份有限公司 | Pre-allocation method and device for audit project personnel |
| CN113643141A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Method, device and equipment for generating explanatory conclusion report and storage medium |
| CN113643141B (en) * | 2021-08-30 | 2024-06-21 | 深圳平安医疗健康科技服务有限公司 | Method, device, equipment and storage medium for generating interpretation conclusion report |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012133735A (en) * | 2010-12-24 | 2012-07-12 | Kddi Corp | Social graph updating system, social graph updating method, and program |
| CN105373590A (en) * | 2015-10-22 | 2016-03-02 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and knowledge data processing device |
| WO2017212268A1 (en) * | 2016-06-08 | 2017-12-14 | Blippar.Com Limited | Data processing system and data processing method |
| CN108305175A (en) * | 2017-12-30 | 2018-07-20 | 上海栈略数据技术有限公司 | Settlement of insurance claim air control assisted verification system based on intellectual medical knowledge mapping |
-
2018
- 2018-10-23 CN CN201811238812.4A patent/CN109345399B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012133735A (en) * | 2010-12-24 | 2012-07-12 | Kddi Corp | Social graph updating system, social graph updating method, and program |
| CN105373590A (en) * | 2015-10-22 | 2016-03-02 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and knowledge data processing device |
| WO2017212268A1 (en) * | 2016-06-08 | 2017-12-14 | Blippar.Com Limited | Data processing system and data processing method |
| CN108305175A (en) * | 2017-12-30 | 2018-07-20 | 上海栈略数据技术有限公司 | Settlement of insurance claim air control assisted verification system based on intellectual medical knowledge mapping |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060166A (en) * | 2019-03-13 | 2019-07-26 | 平安科技（深圳）有限公司 | Intelligence Claims Resolution method, apparatus, computer equipment and storage medium |
| CN111915444A (en) * | 2019-05-08 | 2020-11-10 | 国际商业机器公司 | Intelligent learning and application of operational rules |
| US11966928B2 (en) | 2019-05-08 | 2024-04-23 | International Business Machines Corporation | Intelligent learning and application of operational rules |
| CN110322216A (en) * | 2019-05-30 | 2019-10-11 | 阿里巴巴集团控股有限公司 | The case checking method and device of knowledge based map |
| CN110503236A (en) * | 2019-07-08 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk Forecast Method, device, equipment and the storage medium of knowledge based map |
| CN110689322A (en) * | 2019-09-27 | 2020-01-14 | 成都知识视觉科技有限公司 | Artificial intelligence auxiliary claims checking system suitable for insurance claims settlement process |
| CN110866836A (en) * | 2019-11-14 | 2020-03-06 | 支付宝(杭州)信息技术有限公司 | Computer-implemented medical insurance scheme auditing method and device |
| CN110866836B (en) * | 2019-11-14 | 2022-12-06 | 支付宝(杭州)信息技术有限公司 | Computer-implemented medical insurance scheme auditing method and device |
| WO2021135290A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳Tcl新技术有限公司 | Information visualization method, apparatus and device based on knowledge graph, and storage medium |
| CN113434627A (en) * | 2020-03-18 | 2021-09-24 | 中国电信股份有限公司 | Work order processing method and device and computer readable storage medium |
| CN111652704A (en) * | 2020-06-09 | 2020-09-11 | 唐松 | Financial credit risk assessment method based on knowledge graph and graph deep learning |
| CN111797406A (en) * | 2020-07-15 | 2020-10-20 | 智博云信息科技(广州)有限公司 | Medical fund data analysis processing method and device and readable storage medium |
| CN112069808A (en) * | 2020-09-28 | 2020-12-11 | 深圳壹账通智能科技有限公司 | Financing wind control method and device, computer equipment and storage medium |
| CN112215711A (en) * | 2020-10-13 | 2021-01-12 | 中国银行股份有限公司 | Product risk assessment method and device |
| CN112215711B (en) * | 2020-10-13 | 2023-09-19 | 中国银行股份有限公司 | Product risk assessment method and device |
| CN113379053A (en) * | 2020-12-17 | 2021-09-10 | 中国人民公安大学 | Emergency response decision-making method and device and electronic equipment |
| CN112508745A (en) * | 2021-02-05 | 2021-03-16 | 北京肇祺信息科技有限公司 | Document evaluation method and device |
| CN112508745B (en) * | 2021-02-05 | 2021-08-27 | 北京肇祺信息科技有限公司 | Document evaluation method and device |
| CN113469577A (en) * | 2021-07-27 | 2021-10-01 | 中国银行股份有限公司 | Pre-allocation method and device for audit project personnel |
| CN113643141A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Method, device and equipment for generating explanatory conclusion report and storage medium |
| CN113643141B (en) * | 2021-08-30 | 2024-06-21 | 深圳平安医疗健康科技服务有限公司 | Method, device, equipment and storage medium for generating interpretation conclusion report |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109345399B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109345399A (en) | Claims Resolution methods of risk assessment, device, computer equipment and storage medium | |
| CN112084383B (en) | Knowledge graph-based information recommendation method, device, equipment and storage medium | |
| US10824949B2 (en) | Method and system for extracting information from graphs | |
| US9361587B2 (en) | Authoring system for bayesian networks automatically extracted from text | |
| CN110032632A (en) | Intelligent customer service answering method, device and storage medium based on text similarity | |
| US20200104409A1 (en) | Method and system for extracting information from graphs | |
| CN110516910A (en) | Declaration form core based on big data protects model training method and core protects methods of risk assessment | |
| CN112148987A (en) | Message pushing method based on target object activity and related equipment | |
| CN104714931A (en) | Method and system for selecting a structure to represent tabular information | |
| CN110020002A (en) | Querying method, device, equipment and the computer storage medium of event handling scheme | |
| CN107357874A (en) | User classification method and device, electronic equipment, storage medium | |
| CN111177367B (en) | Case classification method, classification model training method and related products | |
| CN112256886B (en) | Probability calculation method and device in atlas, computer equipment and storage medium | |
| WO2020102220A1 (en) | Adherence monitoring through machine learning and computing model application | |
| CN113254833A (en) | Information pushing method and service system based on birth teaching fusion | |
| CN108885631A (en) | Method and system for the contract management in Data Market | |
| CN110941644B (en) | Policy data generation method, device, equipment and storage medium | |
| CN106844550A (en) | Method and device is recommended in a kind of virtual platform operation | |
| CN116703682B (en) | Government affair data platform based on deep learning | |
| CN117291722A (en) | Object management method, related device and computer readable medium | |
| CN116702736A (en) | Safe call generation method and device, electronic equipment and storage medium | |
| CN112182253B (en) | Data processing method, data processing equipment and computer readable storage medium | |
| CN110059480A (en) | Attack monitoring method, device, computer equipment and storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113868481A (en) | Component acquisition method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |