CN108062632A - Methods of risk assessment and device, equipment and storage medium - Google Patents
Methods of risk assessment and device, equipment and storage medium Download PDFInfo
- Publication number
- CN108062632A CN108062632A CN201810002544.XA CN201810002544A CN108062632A CN 108062632 A CN108062632 A CN 108062632A CN 201810002544 A CN201810002544 A CN 201810002544A CN 108062632 A CN108062632 A CN 108062632A
- Authority
- CN
- China
- Prior art keywords
- information
- assessment
- expert
- risk
- operation data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of methods of risk assessment and device, equipment and storage medium, and this method includes：Obtain operation data information；Operation data information is converted to the semantic information of structuring by semantic pessimistic concurrency control；Semantic information is pre-processed, generates rough sets for information；Indexes Reduction carries out rough sets for information by Rough Set Reduction algorithm, generation includes the assessment benchmark rule of several risk indicators；Information is assessed to rough sets for information and the expert being pre-configured to screen, generate operation state information and reference state information respectively according to assessment benchmark rule；Operation state information and the similarity of reference state information are calculated, risk evaluation result is generated according to similarity calculation result and is exported.The present invention converts operation data information by semantic pessimistic concurrency control, carries out risk assessment with operation data on a large scale, improves the accuracy of assessment；Simultaneously using Rough Set Reduction algorithm generation assessment benchmark rule, assessment efficiency is promoted while accuracy is ensured.
Description
Technical field
This application involves risk assessment technology fields, and in particular to a kind of methods of risk assessment and device, equipment and storage
Medium.
Background technology
With the raising of enterprise development speedup, the expansion of development scale, it will usually huge operation data is accumulated, in order to fast
The operation state of fast understanding business, enterprise reasonably runs under the system of internal controlling management of enterprise, how to utilize the operation accumulated
Data carry out risk assessment and management and control becomes more and more important.
By taking the procurement business of supply chain as an example, procurement business is one of most link of risk in supply chain, is had numerous
Factor, which can become, causes the origin cause of formation that procurement business is caused danger.
Meet Material Requirements Planning for example, it is desired to consider to have whether to have, if having the corresponding legal procurement contract for closing rule,
Whether inventory information can effectively distribute buying object amount, and whether issue purchase order is accurate, and so as to not influence procurement plan, tracking is ordered
Whether single to perform in place, whether coordination problem processing is proper, and whether the buying time of payment is very long, etc..In another example, it is also necessary to consider
It arrives, when every next purchase order, it is necessary to the production schedule, the improvement plan of production-sales-stock of secondary month is held, and will be to meter
Draw involved in inventory information, sequence information is not handed over to be confirmed, and then determine buying object amount, ultimately generate purchase order；
It also needs to consider delivery ability of supplier, etc..It is potential huge that these situations can all cause enterprise to be faced in procurement business
Risks.
On the one hand existing risk assessment scheme does not make full use of operation data, cause appraisal procedure relatively simple, wind
The accuracy nearly assessed is not high, and management and control is ineffective；On the other hand in the magnitude increase of the operation data in face of being utilized, comment
It is bad to estimate efficiency.
The content of the invention
In view of drawbacks described above of the prior art or deficiency, are intended to provide one kind and make full use of operation data to improve risk
Accuracy is assessed, while promotes methods of risk assessment and device, the equipment and storage medium of assessment efficiency.
In a first aspect, the present invention provides a kind of methods of risk assessment, including：
Obtain operation data information；
Operation data information is converted to the semantic information of structuring by semantic pessimistic concurrency control；
Semantic information is pre-processed, generates rough sets for information；
Indexes Reduction carries out rough sets for information by Rough Set Reduction algorithm, generation includes the assessment of several risk indicators
Benchmark rule；
Information is assessed according to assessment benchmark rule to rough sets for information and the expert being pre-configured respectively to screen, generation fortune
Seek status information and reference state information；
Operation state information and the similarity of reference state information are calculated, risk assessment is generated according to similarity calculation result
As a result and export.
Second aspect, the present invention provide a kind of risk assessment device, including data capture unit, semantization unit, pre- place
Manage unit, evaluation profile determination unit, data screening unit and risk assessment unit.
Data capture unit is configured to obtain operation data information；
Semantization unit is configured to the semantic information that operation data information is converted to structuring by semantic pessimistic concurrency control；
Pretreatment unit is configured to pre-process semantic information, generates rough sets for information；
Evaluation profile determination unit is configured to Rough Set Reduction algorithm and Indexes Reduction is carried out to rough sets for information, raw
Into the assessment benchmark rule including several risk indicators；
Data screening unit is configured to respectively comment rough sets for information and the expert being pre-configured according to assessment benchmark rule
Estimate information to be screened, generate operation state information and reference state information；
Risk assessment unit is configured to calculate operation state information and the similarity of reference state information, according to similarity
Result of calculation generates risk evaluation result and exports.
The third aspect, the present invention also provides a kind of equipment, including one or more processors and memory, wherein memory
Comprising can by instruction that the one or more processors perform so that the one or more processors perform it is each according to the present invention
The methods of risk assessment that embodiment provides.
Fourth aspect, the present invention also provides a kind of computer readable storage medium for being stored with computer program, the calculating
Machine program makes computer perform the methods of risk assessment that each embodiment provides according to the present invention.
Methods of risk assessment and device, the equipment and storage medium that many embodiments of the present invention provide pass through semantic pessimistic concurrency control
Operation data information is converted, it, can be on a large scale fully with operation number without manually marking operation data information
It is believed that ceasing to carry out risk assessment, the accuracy of assessment is improved；Assessment base is also generated using Rough Set Reduction algorithm simultaneously
Quasi-regular, it is achieved thereby that promoting assessment efficiency while accuracy is ensured.
Description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is a kind of flow chart for methods of risk assessment that one embodiment of the invention provides.
Fig. 2 be method shown in Fig. 1 a kind of embodiment in step S40 flow chart.
Fig. 3 be method shown in Fig. 1 a kind of embodiment in step S50 flow chart.
Fig. 4 is a kind of flow chart of preferred embodiment of method shown in Fig. 1.
Fig. 5 be method shown in Fig. 4 a kind of embodiment in step S10 flow chart.
Fig. 6 is a kind of structure diagram for risk assessment device that one embodiment of the invention provides.
Fig. 7 is a kind of structure diagram of preferred embodiment of Fig. 6 shown devices.
Fig. 8 is a kind of structure diagram of preferred embodiment of Fig. 6 shown devices.
Fig. 9 is a kind of structure diagram for equipment that one embodiment of the invention provides.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, illustrated only in attached drawing with inventing relevant part.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is a kind of flow chart for methods of risk assessment that one embodiment of the invention provides.
As shown in Figure 1, in the present embodiment, the present invention provides a kind of methods of risk assessment, including：
S20：Obtain operation data information；
S30：Operation data information is converted to the semantic information of structuring by semantic pessimistic concurrency control；
S40：Semantic information is pre-processed, generates rough sets for information；
S50：Indexes Reduction carries out rough sets for information by Rough Set Reduction algorithm, generation includes several risk indicators
Assess benchmark rule；
S60：Information is assessed according to assessment benchmark rule to rough sets for information and the expert being pre-configured respectively to screen, it is raw
Into operation state information and reference state information；
S70：Operation state information and the similarity of reference state information are calculated, risk is generated according to similarity calculation result
Assessment result simultaneously exports.
Specifically, the above method can carry out risk assessment to enterprise, can also simultaneously to multiple enterprises respectively into
Row risk assessment is described in detail exemplified by carrying out risk assessment to the supply chain procurement business of enterprise A below.
In step S20, docked by the items with enterprise A with the relevant information system of supply chain procurement business, such as
Enterprise resource planning (ERP system), purchasing system, financial system etc. get the operation number of enterprise A items systems
According to.
In the present embodiment, operation data information is T1The operation data set D for each system that moment gets1, that is, run
Data message D=(D1)。
It preferably, can be with the operation data of each system of timing acquisition, and by (T in a period of time in step S201-Tn)
The each group operation data set (D that timing acquisition arrives1-Dn) as operation data information, i.e. operation data information D=(D1,
D2..., Dn)。
In step s 30, the operation data information that step S20 is got is turned by the semantic pessimistic concurrency control of pre-configuration
It changes, the purpose of conversion is uniformly to be converted to the data of all kinds of different-formats of each system convenient for identification (semanteme), convenient for place
Manage the information of (structuring).
Specific conversion regime is, by the semanteme of every operation data in semantic net Model Identification operation data information,
It is converted using the framework of several risk indicators as the semantic information of pre-configuration.
For example, with 40 risk indicator (M1-M40) combination converted as framework, can be by operation data set D1
Be converted to { (M1, D101), (M2, D102) ..., (M40, D140)}；It, can when operation data information includes multigroup operation data set
Each group operation data set is converted in the same fashion.Wherein, D101-D140For the semantic number of each risk indicator after conversion
According to.Reference of the above-mentioned example only as transfer principle, and the restriction not for conversion regime, based on the transfer principle, ability
Field technique personnel can carry out above-mentioned conversion by all kinds of different combo architectures.
Preferably for different type, the enterprise of different application scene is faced, it is necessary to which the risk of various combination is respectively configured
Index.For example, outer pin-type enterprise is with the market rate is wavy, product supplier's development degree is relatively slow, with certain monopolization
Advantage, customer demand have the supply chains feature such as large variation, should configure relevant risk indicator of the corresponding exchange rate etc.；It is and domestic
Type enterprise has the characteristics that the market supply chains such as based on the country, then need not configure the relevant risk indicator of the exchange rate, and answers configuration pin
To the risk indicator of domestic market.
Wherein, which builds and to be formed according to history operation data information and expertise data message, if not
The semanteme pessimistic concurrency control is configured, then needs to build the semanteme pessimistic concurrency control in advance before being assessed, it below will be by shown in Fig. 4-5
Preferred embodiment describes in detail.
In step S40-S50, by generate rough sets for information go forward side by side row index yojan generate assessment benchmark rule, with
Lower combination Fig. 2-3 is described in detail.
Fig. 2 be method shown in Fig. 1 a kind of embodiment in step S40 flow chart.As shown in Fig. 2, in the present embodiment
In, step S40 includes：
S41：Semantic information is carried out without guiding principle quantification treatment, generate quantitative information；
S43：Storehouse is assessed according to quantitative information and the expert being pre-configured and obtains the first expert assessment information；
S45：The risk class of information is assessed as determining using the risk indicator of quantitative information as conditional attribute, the first expert
Plan attribute generates rough sets for information.
Specifically, in step S41, no guiding principle quantification treatment is that the semantic information of step S30 generations is quantified, example
Such as：
In step S43, the expert of pre-configuration, which assesses, is configured with one or more sets assessment rules in storehouse.When expert assesses storehouse
It is middle configuration it is a set of assessment rule when, by quantitative information input the assessment rule, get the first expert assess information, such as：
| D1 | D2 | D3 | |
| First expert assesses information | Excessive risk | Risk | Risk |
When expert assesses, and more set assessment rules are configured in storehouse, quantitative information is inputted to often set assessment rule respectively, is obtained
Information is assessed to the first expert, such as：
In step S45, risk of information etc. is assessed using the risk indicator of quantitative information as conditional attribute, the first expert
Grade is used as decision attribute, generates rough sets for information, such as：
In the present embodiment, the assessment rule in expert's assessment storehouse is assessed based on quantitative information, in other embodiments
In, the assessment rule in expert's assessment storehouse is also based on semantic information and is assessed, then needs first according to semanteme to be believed in step S40
Breath and expert assess storehouse and obtain the first expert assessment information, then semantic information is carried out without guiding principle quantification treatment, ultimately produce coarse
Collect information.For two kinds of embodiments difference lies in the assessment rule of first way is relatively simple, data-handling efficiency is higher；And
The assessment rule of the second way is complex, and data processing is relatively complicated, but more rich data message can be commented
Estimate, can realize the assessment more refined.
Fig. 3 be method shown in Fig. 1 a kind of embodiment in step S50 flow chart.As shown in figure 3, in the present embodiment
In, step S50 includes：
S51：Traversal removes any risk indicator in conditional attribute, and assesses storehouse according to expert and reacquire the second expert
Information is assessed, judges that the first expert assesses information and whether the second expert assessment information is identical：It is then about to remove removed risk
Index；It is no, then retain removed risk indicator；
S53：Traversal removes any risk indicator combination in conditional attribute, and assesses storehouse according to expert and reacquire the 3rd
Expert assesses information, judges that the first expert assesses information and whether the 3rd expert assessment information is identical：It is then about to remove what is removed
Risk indicator combines；It is no, then retain removed risk indicator combination；
S55：Assessment benchmark rule is generated according to traversing result twice.
For example, for 40 risk indicator (M as conditional attribute1-M40), in step s 51 to removing each single item wind
Dangerous index is traveled through：
Remove M1, according to (M2-M40) quantitative information and expert assess storehouse obtain the second expert assess information, judge first
Expert assesses information and whether the second expert assessment information is identical：It is then about to remove M1；It is no, then retain M1；
Remove M2, according to (M1、M3-M40) quantitative information and expert assess storehouse and obtain the second expert and assess information, judge the
One expert assesses information and whether the second expert assessment information is identical：It is then about to remove M2；It is no, then retain M2；
……
Remove M40, according to (M1-M39) quantitative information and expert assess storehouse obtain the second expert assess information, judge first
Expert assesses information and whether the second expert assessment information is identical：It is then about to remove M40；It is no, then retain M40。
In step S53, to removing 40 risk indicator (M1-M40) in arbitrary 2,3 ..., the combination of 39 into
Row traversal, method are identical with step S51.
In step S55, if the traversing result of step S51 removes wherein 15 risk indicators, the traversal of step S53 for offer
As a result wherein 20 risk indicators are removed for offer, and this 15 are Chong Die with there is 10 in this 20, then take its intersection, it is necessary to about remove
(15+20-10), totally 25 risk indicators, ultimately produce the assessment benchmark rule being made of remaining 15 risk indicators.
It preferably, can be further to offer except the item number given threshold of combination, for example, only to being no more than the combination of 10
It is traveled through.
In step S60, rough sets for information and the expert being pre-configured are commented according to the assessment benchmark rule that step S50 is generated
Estimate information to be screened, i.e., only retain every risk indicator in assessment benchmark rule, so that step S70 carries out similarity meter
It calculates.
In step S70, include 15 risk indicator (M to assess benchmark rule1-M15) exemplified by, when operation data information
Only include one group of operation data set D1, when corresponding to one group of operation state information of generation：
| Operation state information | Reference state information | |
| M1 | N11 | N10 |
| M2 | N21 | N20 |
| M3 | N31 | N30 |
| M4 | N41 | N40 |
| M5 | N51 | N50 |
| M6 | N61 | N60 |
| …… | …… | …… |
| M15 | N151 | N150 |
First, the difference for each risk indicator, operation state information and reference state information is calculated：Δ T (i)=
|Ni1-Ni0|, wherein i=1,2 ..., 15.
Secondly, the similarity G of operation state information and reference state information is calculated：
G=(min (Δ T (i))+a*max (Δ T (i)))/(Δ T (i)+a*max (Δ T (i)))
Wherein, a is the proportionality coefficient being pre-configured, and takes 0.7 in the present embodiment, can be according to reality in more embodiments
Demand is configured to different values, it can be achieved that identical technique effect.
When operation data information includes several groups of operation data set, corresponds to several groups of operation state information of generation, with 3
Exemplified by group：
Then have：
Equally calculate the difference for each risk indicator, operation state information and reference state information：
Δ T (i, j)=| Nij-Ni0|, wherein i=1,2 ..., 15；J=1,2,3.
The similarity G of operation state information and reference state information is calculated again：
G=∑s (min (Δ T (i, j))+a*max (Δ T (i, j)))/b (Δ T (i, j)+a*max (Δ T (i, j)))；
Wherein, b is the group number of operation data set.
It calculates similarity G and then according to the similarity of pre-configuration and the relation of risk evaluation result, generates final
Risk evaluation result simultaneously exports.Specifically, in the present embodiment, similarity is higher, then risk is higher.
Preferably, when being configured with more set assessment rules in system, when being corresponding with multigroup reference state information, then basis respectively
Every group of reference state information calculates the similarity compared with each group of reference state information by the above method, then to compared with
The similarity configuration weight of each group of reference state information, calculates last similarity result.
The various embodiments described above convert operation data information by semantic pessimistic concurrency control, without manually marking operation
Data message fully can carry out risk assessment with operation data information on a large scale, improve the accuracy of assessment；Simultaneously
Assessment benchmark rule is also generated using Rough Set Reduction algorithm, it is achieved thereby that promoting assessment effect while accuracy is ensured
Rate.
Fig. 4 is a kind of flow chart of preferred embodiment of method shown in Fig. 1.As shown in figure 4, in a preferred embodiment
In, the above method further comprises：
S10：The semantic pessimistic concurrency control of structure.
Fig. 5 be method shown in Fig. 4 a kind of embodiment in step S10 flow chart.
As shown in figure 5, in the present embodiment, step S10 is specifically included：
S11：Obtain operation data information, history operation data information and expertise data message；
S13：By the way that extension language (XML) can be marked to operation data information, history operation data information and expertise
Data message is marked, and generates label information；
S15：Classified according to application scenarios to label information, obtain several key words sorting information；
S17：Structuring conversion is carried out to each key words sorting information according to the risk indicator of each application scenarios respectively, if obtaining
Dry taxonomic structure information；
S19：According to each taxonomic structure information generative semantics pessimistic concurrency control.
Specifically, the structure principle of semantic pessimistic concurrency control can be known by those skilled in the art, no longer be described in detail herein.Its
In, step S15 is option, may not need and classifies for the more single enterprise of application scenarios.
Fig. 6 is a kind of structure diagram for risk assessment device that one embodiment of the invention provides.Fig. 6 shown devices can be right
Method shown in FIG. 1 should be performed.
As shown in fig. 6, in the present embodiment, the present invention provides a kind of risk assessment device, including data capture unit 20,
Semantization unit 30, pretreatment unit 40, evaluation profile determination unit 50, data screening unit 60 and risk assessment unit 70.
Wherein, data capture unit 20 is configured to obtain operation data information；
Semantization unit 30 is configured to the semantic letter that operation data information is converted to structuring by semantic pessimistic concurrency control
Breath；
Pretreatment unit 40 is configured to pre-process semantic information, generates rough sets for information；
Evaluation profile determination unit 50 is configured to Rough Set Reduction algorithm and carries out Indexes Reduction to rough sets for information,
Generation includes the assessment benchmark rule of several risk indicators；
Data screening unit 60 is configured to according to assessment benchmark rule respectively to rough sets for information and the expert being pre-configured
Assessment information is screened, and generates operation state information and reference state information；
Risk assessment unit 70 is configured to calculate operation state information and the similarity of reference state information, according to similar
Degree result of calculation generation risk evaluation result simultaneously exports.
The risk assessment principle of above device can refer to method shown in FIG. 1, and details are not described herein again.
Fig. 7 is a kind of structure diagram of preferred embodiment of Fig. 6 shown devices.Fig. 7 shown devices can correspond to execution
Method shown in Fig. 2-3.
As shown in fig. 7, in a preferred embodiment, pretreatment unit 40 quantifies subelement 41, acquisition of information including no guiding principle
Subelement 43 and rough set generation subelement 45.
Wherein, no guiding principle quantization subelement 41 is configured to that semantic information is carried out, without guiding principle quantification treatment, to generate quantitative information；
Acquisition of information subelement 43 is configured to assess the first expert of storehouse acquisition according to quantitative information and the expert being pre-configured
Assess information；
Rough set generation subelement 45 is configured to comment using the risk indicator of quantitative information as conditional attribute, the first expert
The risk class of information is estimated as decision attribute, generates rough sets for information.
It is also shown in FIG. 7, it is preferable that evaluation profile determination unit 50 includes first about except subelement 51, second about removes
Subelement 53 and pattern determination subelement 55.
Wherein, first about except subelement 51 be configured to traversal remove conditional attribute in any risk indicator, and according to
Expert assesses storehouse and reacquires the second expert assessment information, judges that the first expert assesses information and whether the second expert assesses information
It is identical：It is then about to remove removed risk indicator；It is no, then retain removed risk indicator；
Second about except subelement 53 is configured to any risk indicator combination in traversal removal conditional attribute, and according to special
Family assessment storehouse reacquire the 3rd expert assess information, judge the first expert assess information and the 3rd expert assessment information whether phase
Together：It is, then about except removed risk indicator combines；It is no, then retain removed risk indicator combination；
Pattern determination subelement 55 is configured to according to the generation assessment benchmark rule of traversing result twice.
The risk assessment principle of Fig. 7 shown devices can refer to the method shown in Fig. 2-3, and details are not described herein again.
Fig. 8 is a kind of structure diagram of preferred embodiment of Fig. 6 shown devices.Fig. 8 shown devices can correspond to execution
Method shown in Fig. 4-5.
As shown in figure 8, in a preferred embodiment, above device further includes model construction unit 10, it is configured to build
Semantic pessimistic concurrency control.
Specifically, data capture unit 20 is further configured to obtain operation data information, history operation data information
With expertise data message.
Model construction unit 10 includes mark subelement 11, classification subelement 13, structuring subelement 15 and model generation
Subelement 17.
Mark subelement 11 is configured to that extension language (XML) can be marked to run number to operation data information, history
It is believed that breath and expertise data message are marked, label information is generated；
Classification subelement 13 is configured to classify to label information according to application scenarios, obtains several key words sorting letters
Breath；
Structuring subelement 15 be configured to according to the risk indicators of each application scenarios respectively to each key words sorting information into
Row structuring is converted, and obtains several taxonomic structure information；
Model generation subelement 17 is configured to according to each taxonomic structure information generative semantics pessimistic concurrency control.
Fig. 9 is a kind of structure diagram for equipment that one embodiment of the invention provides.
As shown in figure 9, as another aspect, present invention also provides a kind of equipment 900, including one or more centres
Unit (CPU) 901 is managed, can be added according to the program being stored in read-only memory (ROM) 902 or from storage part 908
The program that is downloaded in random access storage device (RAM) 903 and perform various appropriate actions and processing.In RAM903, also deposit
It contains equipment 900 and operates required various programs and data.CPU901, ROM902 and RAM903 pass through the phase each other of bus 904
Even.Input/output (I/O) interface 905 is also connected to bus 904.
I/O interfaces 905 are connected to lower component：Importation 906 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 907 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage part 908 including hard disk etc.；
And the communications portion 909 of the network interface card including LAN card, modem etc..Communications portion 909 via such as because
The network of spy's net performs communication process.Driver 910 is also according to needing to be connected to I/O interfaces 905.Detachable media 911, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 910, as needed in order to read from it
Computer program be mounted into as needed storage part 908.
Particularly, in accordance with an embodiment of the present disclosure, the methods of risk assessment of any of the above-described embodiment description can be implemented
For computer software programs.For example, embodiment of the disclosure includes a kind of computer program product, including being tangibly embodied in
Computer program on machine readable media, the computer program include to perform the program code of methods of risk assessment.
In such embodiments, the computer program can be downloaded and installed by communications portion 909 from network and/or from
Detachable media 911 is mounted.
As another aspect, present invention also provides a kind of computer readable storage medium, the computer-readable storage mediums
Matter can be computer readable storage medium included in the device of above-described embodiment；Can also be individualism, it is unassembled
Enter the computer readable storage medium in equipment.There are one computer-readable recording medium storages or more than one program, should
Program is used for performing the methods of risk assessment for being described in the application by one or more than one processor.
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of various embodiments of the invention, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.In this regard, each box in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that it is marked at some as in the realization replaced in box
The function of note can also be occurred with being different from the order marked in attached drawing.For example, two boxes succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also
It is noted that the combination of each box in block diagram and/or flow chart and the box in block diagram and/or flow chart, Ke Yitong
Cross perform as defined in functions or operations dedicated hardware based system come realize or can by specialized hardware with calculate
The combination of machine instruction is realized.
Being described in unit or module involved in the embodiment of the present application can be realized by way of software, can also
It is realized by way of hardware.Described unit or module can also be set in the processor, for example, each unit can
With the software program being provided in computer or intelligent movable equipment or the hardware unit being separately configured.Wherein, this
The title of a little units or module does not form the restriction to the unit or module in itself under certain conditions.
The preferred embodiment and the explanation to institute's application technology principle that above description is only the application.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from the application design, appointed by above-mentioned technical characteristic or its equivalent feature
Other technical solutions that meaning is combined and formed.Such as features described above has similar functions with (but not limited to) disclosed herein
The technical characteristic technical solution being replaced mutually and formed.
Claims (10)
1. a kind of methods of risk assessment, which is characterized in that including：
Obtain operation data information；
The operation data information is converted to the semantic information of structuring by semantic pessimistic concurrency control；
Institute's semantic information is pre-processed, generates rough sets for information；
Indexes Reduction carries out the rough sets for information by Rough Set Reduction algorithm, generation includes the assessment of several risk indicators
Benchmark rule；
Information is assessed according to the assessment benchmark rule to the rough sets for information and the expert being pre-configured respectively to screen, it is raw
Into operation state information and reference state information；
The operation state information and the similarity of the reference state information are calculated, risk is generated according to similarity calculation result
Assessment result simultaneously exports.
2. according to the method described in claim 1, it is characterized in that, described pre-process institute's semantic information, generation is thick
Rough collection information includes：
Institute's semantic information is carried out without guiding principle quantification treatment, generate quantitative information；
Storehouse is assessed according to the quantitative information and the expert being pre-configured and obtains the first expert assessment information；
The risk class of information is assessed as determining using the risk indicator of the quantitative information as conditional attribute, first expert
Plan attribute generates rough sets for information.
3. according to the method described in claim 2, it is characterized in that, described believe the rough set by Rough Set Reduction algorithm
Breath carries out Indexes Reduction, and the assessment benchmark rule that generation includes several risk indicators includes：
Traversal removes any risk indicator in the conditional attribute, and assesses storehouse according to the expert and reacquire the second expert
Information is assessed, judges that first expert assesses information and whether second expert assessment information is identical：It is then about to remove and moved
The risk indicator removed；It is no, then retain removed risk indicator；
Traversal removes any risk indicator combination in the conditional attribute, and assesses storehouse according to the expert and reacquire the 3rd
Expert assesses information, judges that first expert assesses information and whether the 3rd expert assessment information is identical：It is then about to remove
The risk indicator combination removed；It is no, then retain removed risk indicator combination；
Assessment benchmark rule is generated according to traversing result twice.
4. according to claim 1-3 any one of them methods, which is characterized in that further include：The semantic pessimistic concurrency control of structure.
5. according to the method described in claim 4, it is characterized in that, the semantic pessimistic concurrency control of the structure includes：
Obtain operation data information, history operation data information and expertise data message；
By the way that extension language (XML) can be marked to the operation data information, history operation data information and expertise data
Information is marked, and generates label information；
Classified according to application scenarios to the label information, obtain several key words sorting information；
Structuring conversion is carried out to each key words sorting information according to the risk indicator of each application scenarios respectively, if obtaining
Dry taxonomic structure information；
According to each taxonomic structure information generative semantics pessimistic concurrency control.
6. a kind of risk assessment device, which is characterized in that including：
Data capture unit is configured to obtain operation data information；
Semantization unit is configured to the semantic letter that the operation data information is converted to structuring by semantic pessimistic concurrency control
Breath；
Pretreatment unit is configured to pre-process institute's semantic information, generates rough sets for information；
Evaluation profile determination unit is configured to Rough Set Reduction algorithm and carries out Indexes Reduction to the rough sets for information,
Generation includes the assessment benchmark rule of several risk indicators；
Data screening unit is configured to according to the assessment benchmark rule to the rough sets for information and to be pre-configured special respectively
Family's assessment information is screened, and generates operation state information and reference state information；
Risk assessment unit is configured to calculate the operation state information and the similarity of the reference state information, according to
Similarity calculation result generates risk evaluation result and exports.
7. device according to claim 6, which is characterized in that the pretreatment unit includes：
No guiding principle quantifies subelement, is configured to that institute's semantic information is carried out, without guiding principle quantification treatment, to generate quantitative information；
Acquisition of information subelement is configured to obtain the first expert according to the quantitative information and the expert being pre-configured assessment storehouse and comment
Estimate information；
Rough set generates subelement, is configured to using the risk indicator of the quantitative information as conditional attribute, described first specially
The risk class of family's assessment information generates rough sets for information as decision attribute；
The evaluation profile determination unit includes：
First about except subelement, any risk indicator being configured in the traversal removal conditional attribute, and according to described special
Family's assessment storehouse reacquires the second expert and assesses information, judges that first expert assesses information and second expert assesses letter
Whether breath is identical：It is then about to remove removed risk indicator；It is no, then retain removed risk indicator；
Second, about except subelement, is configured to any risk indicator that traversal is removed in the conditional attribute and combines, and according to institute
It states expert and assesses storehouse reacquisition the 3rd expert assessment information, judge that first expert assesses information and the 3rd expert comments
Whether identical estimate information：It is, then about except removed risk indicator combines；It is no, then retain removed risk indicator combination；
Pattern determination subelement is configured to according to the generation assessment benchmark rule of traversing result twice.
8. the device according to claim 6 or 7, which is characterized in that further include model construction unit, be configured to structure language
Adopted pessimistic concurrency control；
The data capture unit is further configured to obtain operation data information, history operation data information and expertise
Data message；
The model construction unit includes：
Subelement is marked, is configured to mark extension language (XML) to the operation data information, history operation data
Information and expertise data message are marked, and generate label information；
Classification subelement, is configured to classify to the label information according to application scenarios, obtains several key words sortings letters
Breath；
Structuring subelement is configured to the risk indicator according to each application scenarios respectively to each key words sorting information
Structuring conversion is carried out, obtains several taxonomic structure information；
Model generates subelement, is configured to according to each taxonomic structure information generative semantics pessimistic concurrency control.
9. a kind of equipment, which is characterized in that the equipment includes：
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors
Perform the method as any one of claim 1-5.
10. a kind of computer readable storage medium for being stored with computer program, which is characterized in that the program is executed by processor
Methods of the Shi Shixian as any one of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810002544.XA CN108062632A (en) | 2018-01-02 | 2018-01-02 | Methods of risk assessment and device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810002544.XA CN108062632A (en) | 2018-01-02 | 2018-01-02 | Methods of risk assessment and device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108062632A true CN108062632A (en) | 2018-05-22 |
Family
ID=62140915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810002544.XA Pending CN108062632A (en) | 2018-01-02 | 2018-01-02 | Methods of risk assessment and device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108062632A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325704A (en) * | 2018-10-11 | 2019-02-12 | 四川海纳仁东科技有限公司 | Dangerous waste disposal process risk evaluating method based on rough set-GRNN algorithm |
| CN109726923A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Institution of higher learning based on consultation information carry out legal risk appraisal procedure |
| CN109919471A (en) * | 2019-02-27 | 2019-06-21 | 河南鑫安利安全科技股份有限公司 | A kind of wisdom air control appraisal procedure and system |
| CN110619568A (en) * | 2019-09-17 | 2019-12-27 | 王文斌 | Risk assessment report generation method, device, equipment and storage medium |
| CN110990639A (en) * | 2019-10-29 | 2020-04-10 | 华中师范大学 | Data processing method and device for education informatization horizontal trend analysis |
| CN113435759A (en) * | 2021-07-01 | 2021-09-24 | 贵州电网有限责任公司 | Primary equipment risk intelligent evaluation method based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012174125A (en) * | 2011-02-23 | 2012-09-10 | Yamaguchi Univ | Disaster prevention plan support system and program of the same |
| CN103426123A (en) * | 2013-07-24 | 2013-12-04 | 国家电网公司 | Power grid fault risk evaluation method based on rough set theory |
| CN103744850A (en) * | 2013-10-14 | 2014-04-23 | 国家电网公司 | Power grid disaster real-time regulating and control device and method based on intuition fuzzy rough set |
| CN103914792A (en) * | 2014-03-17 | 2014-07-09 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Integrated risk assessment method for calculating operation uncertainty of electric transmission line |
-
2018
- 2018-01-02 CN CN201810002544.XA patent/CN108062632A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012174125A (en) * | 2011-02-23 | 2012-09-10 | Yamaguchi Univ | Disaster prevention plan support system and program of the same |
| CN103426123A (en) * | 2013-07-24 | 2013-12-04 | 国家电网公司 | Power grid fault risk evaluation method based on rough set theory |
| CN103744850A (en) * | 2013-10-14 | 2014-04-23 | 国家电网公司 | Power grid disaster real-time regulating and control device and method based on intuition fuzzy rough set |
| CN103914792A (en) * | 2014-03-17 | 2014-07-09 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Integrated risk assessment method for calculating operation uncertainty of electric transmission line |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325704A (en) * | 2018-10-11 | 2019-02-12 | 四川海纳仁东科技有限公司 | Dangerous waste disposal process risk evaluating method based on rough set-GRNN algorithm |
| CN109325704B (en) * | 2018-10-11 | 2022-04-01 | 四川海纳仁东科技有限公司 | Risk evaluation method for hazardous waste disposal process based on rough set-GRNN algorithm |
| CN109726923A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Institution of higher learning based on consultation information carry out legal risk appraisal procedure |
| CN109919471A (en) * | 2019-02-27 | 2019-06-21 | 河南鑫安利安全科技股份有限公司 | A kind of wisdom air control appraisal procedure and system |
| CN110619568A (en) * | 2019-09-17 | 2019-12-27 | 王文斌 | Risk assessment report generation method, device, equipment and storage medium |
| CN110990639A (en) * | 2019-10-29 | 2020-04-10 | 华中师范大学 | Data processing method and device for education informatization horizontal trend analysis |
| CN110990639B (en) * | 2019-10-29 | 2021-04-06 | 华中师范大学 | Data processing method and device for education informatization horizontal trend analysis |
| CN113435759A (en) * | 2021-07-01 | 2021-09-24 | 贵州电网有限责任公司 | Primary equipment risk intelligent evaluation method based on deep learning |
| CN113435759B (en) * | 2021-07-01 | 2023-07-04 | 贵州电网有限责任公司 | Primary equipment risk intelligent assessment method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062632A (en) | Methods of risk assessment and device, equipment and storage medium | |
| Guo et al. | Does digital transformation improve the firm’s performance? From the perspective of digitalization paradox and managerial myopia | |
| AU2022211812A1 (en) | Method and system of dynamic model selection for time series forecasting | |
| JP6134632B2 (en) | Funds flow analysis apparatus and method | |
| CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
| WO2021088499A1 (en) | False invoice issuing identification method and system based on dynamic network representation | |
| Ingvaldsen et al. | Industrial application of semantic process mining | |
| Lahann et al. | Utilizing machine learning techniques to reveal vat compliance violations in accounting data | |
| Lodhi et al. | Business process improvement framework and representational support | |
| CN109815480B (en) | Data processing method and device and storage medium | |
| Chávez et al. | Lean production management model for SME waste reduction in the processed food sector in Peru | |
| Park et al. | Analyzing process-aware information system updates using digital twins of organizations | |
| Yu | Data mining in library reader management | |
| CN110458581B (en) | Method and device for identifying business turnover abnormality of commercial tenant | |
| Chan et al. | Artificial intelligence in accounting and auditing | |
| CN117273968A (en) | Accounting document generation method of cross-business line product and related equipment thereof | |
| Yuan et al. | An evaluation index system for intellectual capital evaluation based on machine learning | |
| CN115907937A (en) | Supply chain financial risk monitoring method and system based on neural network | |
| Verevka et al. | Opportunities and barriers to using big data technologies in the metallurgical industry | |
| CN113837648B (en) | Enterprise relevance analysis method, associated enterprise recommendation method and device | |
| Badwan et al. | Financial Risk Management in the Supply Chain Using Business Intelligence and Big Data | |
| CN113379212A (en) | Block chain-based logistics information platform default risk assessment method, device, equipment and medium | |
| Iastremska et al. | Priority directions of investments into development of the systems of organizational knowledge of industrial business entities | |
| Yashin et al. | Evaluation of technological innovations of a company by the methods of chain repeat and equivalent annuity | |
| Wan et al. | Improvement of ERP Cost Accounting System with Big Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180522 |