Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, right below with reference to embodiment and attached drawingThe present invention is described in further details.Here, exemplary embodiment and its explanation of the invention is used to explain the present invention, but simultaneouslyIt is not as a limitation of the invention.
With the development of big data era, risk assessment can be carried out to personal or enterprise by big data analysis, be based onAssessment result is with the development of decision follow-up business.
Some embodiments provide a kind of Risk Identification Methods for this specification, and knowledge mapping and reason map are combined, obtainedRisk identification map is obtained, by carrying out clustering to the event in risk identification map, and determines each classification after clusterEvent risk class.The risk class and other attributes in risk identification map of binding events, utilize risk identificationModel carries out risk identification, determines the risks and assumptions of the target to be identified in risk identification map.Event biography is fully consideredThe important function in business risk identification is led, while having comprehensively considered the influence for the event that may occur, is known for business riskNew approaches are not provided, improve the accuracy of business risk recognition result.
The recognition methods of this specification risk can apply in client or server, and client can be intelligent handMachine, tablet computer, intelligent wearable device (smartwatch, virtual reality glasses, virtual implementing helmet etc.), intelligent vehicle-carried equipmentEqual electronic equipments.
Specifically, Fig. 1 is the flow diagram of this specification one embodiment risk recognition methods, as shown in Figure 1, thisThe Risk Identification Method provided in specification one embodiment may comprise steps of:
Step 102 obtains risk identification map, and the risk identification map includes be mutually related reason map and knowledgeMap.
Risk Identification Method in this specification embodiment can be applied in the scene for carrying out risk identification to enterprise,Such as: applying in enterprise's credit operation, financial institution can be by carrying out risk identification to enterprise, it is determined whether closes with the enterpriseMake.
In the specific implementation process, the risk identification map of acquisition can be the corresponding map of enterprise to be identified, such as: canTo obtain comprising in basic informations and the event relations such as top managers relationship, loan information, investing tip such as the listing of a company, share priceThe reason map for the events such as rise.In addition, the risk identification map in this specification embodiment may include reason map and knowledgeMap, wherein reason map and knowledge mapping are interrelated.Knowledge mapping is normally based on existing knowledge and carries out static integration, thingManage map using the relationship between event and event as entity and side, describe the Evolution between event, embody event itBetween dynamically associate.
The static knowledge of target to be identified enterprise i.e. to be identified can be obtained in this specification embodiment from databaseMap, then the reason map of enterprise to be identified is obtained, knowledge mapping and reason map are passed through into the relationship between enterprise and eventIt is associated, obtains risk identification map.
Fig. 2 is the structural schematic diagram of this specification one embodiment risk identification map, as shown in Fig. 2, upper half in figurePart is reason map, and by taking " senior executive scandal -83%- declination of profits " this relationship as an example, which can be described as a triple,May be interpreted as " senior executive's scandal " causes the confidence level of " declination of profits " to be 83%.Lower half portion is knowledge mapping, knowledge graph in Fig. 2Spectrum is associated by " A enterprise -- declination of profits " with reason map, and " investment " and " senior executive " two sides of A enterprise illustrateThe static data stored in knowledge mapping.
Step 104 carries out cluster and risk class division to the event in the risk identification map, obtains different classes ofEvent and the corresponding risk class of different classes of event.
In the specific implementation process, it can use clustering algorithm and clustering carried out to the event in knowledge mapping, it willEvent in risk identification map is divided into different classifications, and determines the risk class of different classes of event.Wherein, cluster is calculatedIt includes but is not limited to EM (Expectation Maximization that method, which can select common machine learning algorithm,Algorithm, it is expected that very big algorithm), DBSCAN (Density-Based Spatial Clustering ofApplications with Noise has noisy density clustering method), the K-Means (cluster based on distanceAlgorithm) cluster etc..After event in risk identification map is clustered, it can use Expert Rules according to cluster result, it is rightEvery class event carries out risk class division.Such as: can preset risk class is 0~10, by business analysis expert or in advanceThe modes such as risk class rule are first set, determine the corresponding risk class of event of each classification after cluster.
K-Means cluster, the clustering algorithm relative efficiency, algorithm input can be used in some embodiments of this specificationFor the event word after vectorization and it is expected obtained classification number, exports the event for including by classification and every class.Vectorization isRefer to the mathematical space that the event of text class is mapped to vectorization by model, for Clustering Model training.Common term vectorChange method includes but is not limited to bag of words, word2vec, n-gram (Chinese language model) etc..
Step 106 is stored in the risk stratification as the attribute of corresponding event in the risk identification map.
In the specific implementation process, wind can be stored in using the risk class of definite event as the attribute of eventIn danger identification map, one of the feature as downstream industry's risk identification.Event attribute refers to the build-in attribute of event itself, such asIn Fig. 2 shown in event " senior executive's scandal ", " risk class " attribute is only related with event itself.
The risk identification map is converted to risk identification figure vector using figure embedded mobile GIS by step 108.
In the specific implementation process, risk identification map can be included into event, the risk class of event, degree letterBreath etc. generates risk identification figure vector with figure embedded mobile GIS.Figure embedded mobile GIS includes but is not limited to existing frame such as TransE(Translating Embedding), LINE (Large-scale information network embedding),Node2vec (a kind of feature learning optimization algorithm retained based on neighbours) etc..
Figure embedded mobile GIS used in some embodiments of this specification can be GNN (Graph Neural Network, figureNeural network algorithm), the input of GNN algorithm can be whole isomery figure, that is, risk identification map, isomery figure include all entities,Relationship, entity attribute, that is, risk class, the information such as side attribute, that is, confidence level export the insertion vector for each business entity.BenefitIt may be implemented that risk identification map is fast and accurately converted into risk identification figure vector with GNN algorithm, be subsequent risk identificationData basis is established.
The risk identification image volume is input to risk identification model by step 110, is obtained in the risk identification mapTarget to be identified risks and assumptions.
In the specific implementation process, historical data building risk identification model can be advanced with, as: known to useWhether the information of break is as sample data for enterprise, and bankrupt enterprise can be labeled as 1, remaining enterprise is labeled as 0 sideFormula is labeled, and is carried out model training using the sample data after mark, is constructed risk identification model.Risk identification modelConcrete form and training method, can be selected according to actual needs such as: risk identification model can choose sorting algorithm,Such as: logistic regression, CNN (Convolutional Neural Network, convolutional neural networks model), RNN (RecurrentNeural Network, Recognition with Recurrent Neural Network model) etc., this specification embodiment is not especially limited.
In some embodiments of this specification, risk identification model is a kind of convolutional neural networks MODEL C NN (machine learning mouldType), the last layer of convolutional neural networks model can be normalization exponential function softmax.CNN model the last layer is selected0,1 classification belonging to the vector of enterprise to be identified in the available target to be identified, that is, risk identification map of softmax functionProbability.When model training, inputs and convert the vector generated for the markup information of known business and known map, by CNN modelTraining obtains the parameter of model.When prediction, the vector that new risk identification map generates is put into CNN model, enterprise is obtainedIn the probability value of 0,1 two classification.When the probability value of 1 classification is greater than threshold value, whether which will make loans as credit departmentEnterprise to be investigated.Such as: the risks and assumptions of enterprise, that is, target to be identified to be identified in available risk identification map, risk becauseSon can indicate target to be identified there are the probability of risk, or there is no the probability of risk, exported according to risk identification modelProbability score, can determine whether target to be identified there are the degree of risk, carries out subsequent cooperation and provide data to be subsequentBasis.
Some embodiments provide a kind of Risk Identification Methods for this specification, and knowledge mapping and reason map are combined, obtainedRisk identification map is obtained, by carrying out clustering to the event in risk identification map, and determines each classification after clusterEvent risk class.The risk class and other attributes in risk identification map of binding events, utilize risk identificationModel carries out risk identification, determines the risks and assumptions of the target to be identified in risk identification map.By reason map and knowledgeMap combines, and has fully considered important function of the event conduction in business risk identification, has provided for business risk identificationNew approaches improve the accuracy of business risk recognition result.
Fig. 3 is the flow diagram of another embodiment risk recognition methods of this specification, as shown in figure 3, above-mentionedOn the basis of embodiment, in some embodiments of this specification, the method also includes:
After getting the risk identification map, using probability soft logic model to the event in the risk identification mapAnd/or entity carries out the completion of frontier juncture system.
In the specific implementation process, as shown in figure 3, after getting risk identification map, it can use that probability is soft to patrolIt collects model (PSL, Probabilistic soft logic) and the completion of frontier juncture system is carried out to risk identification map.Probability soft logic canTo indicate the machine learning frame for developing probabilistic model, it can be used simple logical grammar and removes Definition Model, passes throughRapid Optimum carries out operation.The part lacked in the triple of risk identification map can be filled up up using PSL model, fromAnd map is made to become more complete.Map side completion in this specification embodiment is it can be appreciated that relationship between eventA kind of prediction, certainly, map completion algorithm can also include TransE, PRA (Path ranking algorithms, path rowSequence method) etc..PSL used in some embodiments of this specification (probability soft logic model) needs to predefine some knownRule, such as " A enterprise " are controlled interest " B enterprise ", A enterprise " declination of profits ", then B enterprise " declination of profits " etc., pre- based on these rulesThe relationship between each event and/or entity is surveyed, supplements a line between event unallied in former data.Wherein, entityIt can indicate the enterprise in risk identification map.
It can carry out affair clustering analysis and event class to the risk identification map after completion to divide, then by all kinds of thingsThe grade of part is stored in the risk identification map after completion as the attribute of event.Again to the risk identification map after completion intoRow vector conversion and risk identification.
This specification embodiment carries out the completion of frontier juncture system to risk identification map using PSL model, so that risk identification figureSpectrum is more abundant, has established data basis for subsequent risk identification.
In some embodiments of this specification, it is described using probability soft logic model to the event in the risk identification mapAnd/or entity carries out the completion of frontier juncture system, comprising:
The event in the risk identification map and/or relationship and institute between entity are determined using probability soft logic modelState the corresponding confidence level of relationship；
Using the relationship as the side of the risk identification map, the confidence level exists as the confidence level, additionIn the risk identification map.
In the specific implementation process, it can use PSL model prediction and determine each event or reality in risk identification mapRelationship between body, and there are the confidence levels of relationship.Using the relationship between event and/or entity as event and/or entityBetween side, using the confidence level of relationship as the confidence level on side.The output of PSL model be generate while and while confidence level.ExampleSuch as: referring to the record of above-described embodiment, PSL model pre-sets some rules, and based on these rules: " A enterprise " control interest " BEnterprise ", A enterprise " declination of profits ", by PSL model may can completion one " B enterprise -67%- declination of profits " ternaryGroup.As shown in Fig. 2, the corresponding confidence level when upper numerical value can indicate in Fig. 2 between each event, event and thing in Fig. 2The arrow direction on the side between part can indicate the conduction orientation of event.
This specification embodiment carries out the relationship in risk identification map between event and entity using PSL modelPrediction carries out the completion of map frontier juncture system, so that risk identification map is more abundant, has comprehensively considered the event that may occur to enterpriseThe influence of industry risk identification has established data basis for subsequent risk identification.
On the basis of the above embodiments, in some embodiments of this specification, the method also includes:
If the risks and assumptions of the target to be identified are greater than risk threshold value, using described in risk identification map inquiryThe event conduct the relation of target to be identified determines the risk origin cause of formation of the target to be identified.
In the specific implementation process, the query interface that encapsulation chart database can provide, can be used diagram data and is mentionedThe query language of confession, such as Gremlin, Cypher etc. inquire risk identification map.User can in this specification embodimentTo inquire interested company information in risk identification map, such as: user can be greater than the risk identification result risk factorThe enterprise of risk threshold value is further inquired.Such as: conducting path can be inquired by enterprise name, if A in risk identification resultThe risks and assumptions of enterprise be 0.8, be greater than risk threshold value 0.5, user can to A enterprise in risk identification map event conduct the relationPath is detected, to be better understood by the origin cause of formation for the risks and assumptions that A corporate earning arrives.It can be according to query result, into oneThe accuracy of step confirmation risk identification result.
This specification embodiment, by inquiring specified target to be identified in risk identification map, inquiry withThe conduct the relation of the related event of target to be identified further confirms that risk to determine the risk origin cause of formation of target to be identifiedThe accuracy of recognition result.
The risk identification process in this specification embodiment is specifically introduced below with reference to Fig. 3:
Step 1: obtaining existing map.
This specification embodiment it is available include top managers relationship, loan information, the basic informations such as investing tip andThe event relation such as listing of a company, the reason map of the events such as share price rise, reason map and knowledge mapping are blended, wind is formedDanger identification map.
Step 2: the completion of map frontier juncture system.
PSL soft probabilistic logic can be used, the completion of map side is carried out to the existing map in step 1.Specific complementing method canWith the record with reference to above-described embodiment, details are not described herein again.
Step 3: affair clustering.
K-means algorithm can be used to cluster all events in the map after completion in step 2, clusteredAs a result.
Step 4: event risk grade classification.
Business expert can be asked to carry out risk equivalent definition to the event category generated in step 3, as risk class can be determinedJustice is the integer within 1 to 10.Or it presets risk stratification and determines rule, the risk etc. of rule-based all kinds of events of determinationGrade.
Step 5: the insertion of knowledge graph spectrogram.
GNN model can be used, figure insertion is carried out to information required in map, as: event risk grade, completionEvent relation and confidence level, degree information etc. generate risk identification figure vector with figure embedded mobile GIS.
Step 6: calculating business risk index.
Step 5 figure can be embedded in the risk identification figure vector generated and be put into the CNN network that the last layer is softmaxIn, obtain the risks and assumptions of enterprise.
The present invention provides a kind of credit risk recognition methods based on reason map, fully consider that event conduction is being looked forward toImportant function in industry risk identification, while having comprehensively considered the influence for the event that may occur, it is bank credit to public riskIdentification provides new approaches, the accuracy of recognition result when improving risk.
Fig. 4 is a kind of structural schematic diagram of the risk recognition system provided in this specification embodiment, as shown in figure 4, thisSpecification embodiment additionally provides a kind of risk recognition system, which may include: map storage unit 1, map completion listFirst 2, event risk grade classification unit 3, risks and assumptions generation unit 4, knowledge query unit 5, in which:
Map storage unit 1 can be used for storing the fused knowledge mapping and reason map for having constructed completion, knowledgeMap and reason map blend to form risk identification map.
Map completion unit 2 can be used for filling up the part lacked in the map triple in map storage unit 1It goes, so that map be made to become more complete.
Event risk grade classification unit 3 can be used for all events existing for reason map in map completion unit 2Clustered, business expert carries out event risk grade classification according to cluster result, to every class event, and using division result asEvent attribute is stored into map.
Risks and assumptions generation unit 4 can be used for the feature according to present in map and carry out conformity calculation, obtains one and takeIt is worth risks and assumptions of the range between [0,1], for supporting decision.Fig. 5 is that this specification one embodiment risk factor is rawAt the structural schematic diagram of unit, risks and assumptions generation unit 4 as shown in Figure 5 may include mark unit 51, figure embedded unit 52,Risks and assumptions computing unit 53.Wherein, data mark unit 51 can using known enterprise whether break data or itsHis business high risk behavioral data carries out label for labelling as sample data, to sample data, and such as: bankrupt enterprise is labeled as 1,Remaining enterprise is labeled as 0.Data after mark can be used for the model training of risks and assumptions computing unit 53.Figure embedded unit 52Existing map can be embedded in comprising event risk grade, the event relation of completion and confidence level, degree information etc. with figureAlgorithm generates figure vector, imports final risks and assumptions computing unit 53, obtains the risks and assumptions of enterprise to be identified.Business simultaneouslyPersonnel can confirm risk threshold value according to business demand, will be greater than the enterprise of threshold value as high spot reviews object, risks and assumptions canTo be set as 0.5.Wherein, risks and assumptions, which are calculated, can specifically refer to above-mentioned reality using machine learning models such as CNN modelsThe record of example is applied, details are not described herein again.
Knowledge query unit 5 can be used for inquiring the event conduct the relation of target to be identified in risk identification map, determineThe risk origin cause of formation of the target to be identified.Such as: when the risks and assumptions of target to be identified are greater than risk threshold value, knowledge can be passed throughQuery unit 5 inquires risk identification map, inquires the event conducting path of the target to be identified, and analyze the target to be identifiedThe risk origin cause of formation.The map of inquiry can be the risk identification map obtained after map completion element sides relationship completion.
This specification embodiment combines reason map and knowledge mapping, not only allows for the static knowledge of enterprise, alsoThe influence that the Evolution between event identifies business risk is comprehensively considered.Fully consider event conduction in business riskImportant function in identification, while frontier juncture system supplement is carried out to map using PSL model, comprehensively consider the event that may occurInfluence, new approaches are provided to public risk identification for credit, improve the accuracy of risk identification result.
Various embodiments are described in a progressive manner for the above method in this specification, identical between each embodimentSimilar part may refer to each other, and each embodiment focuses on the differences from other embodiments.CorrelationPlace illustrates referring to the part of embodiment of the method.
Based on Risk Identification Method described above, this specification one or more embodiment also provides a kind of risk identificationSquare law device.The device may include system (including the distributed system for having used this specification embodiment the methodSystem), software (application), module, component, server, client etc. and the device for combining necessary implementation hardware.Based on same woundNew design, the device in one or more embodiments that this specification embodiment provides is as described in the following examples.Due to dressSet that the implementation solved the problems, such as is similar to method, thus the implementation of the specific device of this specification embodiment may refer to it is aforementionedThe implementation of method, overlaps will not be repeated.Used below, predetermined function may be implemented in term " unit " or " module "Software and/or hardware combination.Although device described in following embodiment is preferably realized with software, hardware,Or the realization of the combination of software and hardware is also that may and be contemplated.
Specifically, Fig. 6 is the structural schematic diagram of this specification one embodiment risk identification device, and this specification is implementedRisk identification device in example, which can be, to be arranged in the terminal that can be engaged in the dialogue with user or the equipment that can be realized its function,This specification embodiment is not especially limited.As shown in fig. 6, a kind of risk identification device can wrap in this specification embodimentIt includes: map acquiring unit 61, event class determination unit 62, event attribute storage unit 63, figure embedded unit 64, risk identificationUnit 65, in which:
Map acquiring unit 61 can be used for obtaining risk identification map, and the risk identification map includes interrelatedReason map and knowledge mapping；
Event class determination unit 62 can be used for carrying out the event in the risk identification map cluster and risk etc.Grade divides, and obtains different classes of event and the corresponding risk class of different classes of event；
Event attribute storage unit 63 can be used for being stored in using the risk stratification as the attribute of corresponding event describedIn risk identification map；
Figure embedded unit 64 can be used for that the risk identification map is converted to risk identification figure using figure embedded mobile GISVector；
Risk identification unit 65 can be used for for the risk identification image volume being input to risk identification model, obtain instituteState the risks and assumptions of the target to be identified in risk identification map.
The risk identification device that this specification embodiment provides combines knowledge mapping and reason map, obtains risk and knowsOther map, by carrying out clustering to the event in risk identification map, and determine the event of each classification after clusterRisk class.The risk class and other attributes in risk identification map of binding events are carried out using risk identification modelRisk identification determines the risks and assumptions of the target to be identified in risk identification map.Reason map is mutually tied with knowledge mappingIt closes, has fully considered important function of the event conduction in business risk identification, provide new approaches for business risk identification, mentionThe high accuracy of business risk recognition result.
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the methodFormula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
This specification embodiment also provides a kind of risk identification data processing equipment, comprising: at least one processor andFor the memory of storage processor executable instruction, the processor realizes the risk of above-described embodiment when executing described instructionRecognition methods, such as:
Risk identification map is obtained, the risk identification map includes be mutually related reason map and knowledge mapping；
To the event in the risk identification map carry out cluster and risk class divide, obtain different classes of event withAnd the corresponding risk class of different classes of event；
It is stored in the risk stratification as the attribute of corresponding event in the risk identification map；
The risk identification map is converted into risk identification figure vector using figure embedded mobile GIS；
The risk identification image volume is input to risk identification model, is obtained to be identified in the risk identification mapThe risks and assumptions of target.
It should be noted that terminal device described above can also include other implement according to the description of embodiment of the methodMode.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
On the basis of the above embodiments, a kind of computer-readable storage can also be provided in this specification one embodimentMedium is stored thereon with computer instruction, and described instruction, which is performed, realizes the recognition methods of above-described embodiment risk, such as:
Risk identification map is obtained, the risk identification map includes be mutually related reason map and knowledge mapping；
To the event in the risk identification map carry out cluster and risk class divide, obtain different classes of event withAnd the corresponding risk class of different classes of event；
It is stored in the risk stratification as the attribute of corresponding event in the risk identification map；
The risk identification map is converted into risk identification figure vector using figure embedded mobile GIS；
The risk identification image volume is input to risk identification model, is obtained to be identified in the risk identification mapThe risks and assumptions of target.
The storage medium may include the physical unit for storing information, usually by after information digitalization again with benefitThe media of the modes such as electricity consumption, magnetic or optics are stored.It may include: that letter is stored in the way of electric energy that the storage medium, which has,The device of breath such as, various memory, such as RAM, ROM；The device of information is stored in the way of magnetic energy such as, hard disk, floppy disk, magneticBand, core memory, magnetic bubble memory, USB flash disk；Using optical mode storage information device such as, CD or DVD.Certainly, there are also itReadable storage medium storing program for executing of his mode, such as quantum memory, graphene memory etc..
It should be noted that computer readable storage medium described above can also include according to the description of embodiment of the methodOther embodiments.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
The risk prevention system system that this specification provides can be individual risk recognition system, can also apply in a variety of numbersAccording in analysis process system.The system may include any one risk identification device in above-described embodiment.The systemIt can be individual server, also may include the one or more the methods or one or more real for having used this specificationApply server cluster, system (including distributed system), the software (application), practical operation device, logic gates of a deviceDevice, quantum computer etc. simultaneously combine the necessary terminal installation for implementing hardware.The detection system of the verification variance data canTo include at least one processor and store the memory of computer executable instructions, when the processor executes described instructionThe step of realizing method described in above-mentioned any one or multiple embodiments.
Embodiment of the method provided by this specification embodiment can mobile terminal, terminal, server orIt is executed in similar arithmetic unit.For running on the server, Fig. 7 is this specification embodiment risk identification serverHardware block diagram.As shown in fig. 7, server 10 may include one or more (only showing one in figure) processors 100(processing unit that processor 100 can include but is not limited to Micro-processor MCV or programmable logic device FPGA etc.), for depositingStore up the memory 200 of data and the transmission module 300 for communication function.This neighborhood those of ordinary skill is appreciated that figureStructure shown in 7 is only to illustrate, and does not cause to limit to the structure of above-mentioned electronic device.For example, server 10 may also includeThe more or less component than shown in Fig. 7, such as can also include other processing hardware, as database or multistage are slowIt deposits, GPU, or with the configuration different from shown in Fig. 7.
Memory 200 can be used for storing the software program and module of application software, such as the wind in this specification embodimentCorresponding program instruction/the module of dangerous preventing control method, processor 100 by software program that operation is stored in memory 200 withAnd module, thereby executing various function application and data processing.Memory 200 may include high speed random access memory, can also wrapNonvolatile memory is included, such as one or more magnetic storage device, flash memory or other non-volatile solid state memories.In some instances, memory 200 can further comprise the memory remotely located relative to processor 100, these are remotely depositedReservoir can pass through network connection to terminal.The example of above-mentioned network include but is not limited to internet, intranet,Local area network, mobile radio communication and combinations thereof.
Transmission module 300 is used to that data to be received or sent via a network.Above-mentioned network specific example may includeThe wireless network that the communication providers of terminal provide.In an example, transmission module 300 includes a Network adaptationDevice (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to it is mutualNetworking is communicated.In an example, transmission module 300 can be radio frequency (Radio Frequency, RF) module, useIn wirelessly being communicated with internet.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claimsIt is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodimentIt executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitableSequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also canWith or may be advantageous.
Method or apparatus described in above-described embodiment that this specification provides can realize that business is patrolled by computer programIt collects and records on a storage medium, the storage medium can be read and be executed with computer, realize this specification embodiment instituteThe effect of description scheme.
The above-mentioned risk prevention system method or apparatus that this specification embodiment provides can be executed by processor in a computerCorresponding program instruction realizes, such as using the c++ language of windows operating system the end PC is realized, Linux system is realized,Or other are for example realized using android, iOS system programming language in intelligent terminal, and based on quantum computerHandle logic realization etc..
It should be noted that specification device described above, processing equipment, computer storage medium, system are according to correlationThe description of embodiment of the method can also include other embodiments, and concrete implementation mode is referred to corresponding method embodimentDescription, do not repeat one by one herein.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodimentDividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for hardware+For program class embodiment, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to sideThe part of method embodiment illustrates.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claimsIt is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodimentIt executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitableSequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also canWith or may be advantageous.
Although this application provides the method operating procedure as described in embodiment or flow chart, based on conventional or noninvasiveThe labour for the property made may include more or less operating procedure.The step of enumerating in embodiment sequence is only numerous stepsOne of execution sequence mode, does not represent and unique executes sequence.It, can when device or client production in practice executesTo execute or parallel execute (such as at parallel processor or multithreading according to embodiment or method shown in the drawings sequenceThe environment of reason).
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be usedThink personal computer, laptop computer, vehicle-mounted human-computer interaction device, cellular phone, camera phone, smart phone, individualDigital assistants, media player, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device orThe combination of any equipment in these equipment of person.
Although this specification embodiment provides the method operating procedure as described in embodiment or flow chart, based on conventionalIt may include either more or less operating procedure without creative means.The step of being enumerated in embodiment sequence be onlyOne of numerous step execution sequence mode does not represent and unique executes sequence.Device or end product in practice is heldWhen row, can be executed according to embodiment or method shown in the drawings sequence or it is parallel execute (such as parallel processor orThe environment of multiple threads, even distributed data processing environment).The terms "include", "comprise" or its any other changeBody is intended to non-exclusive inclusion, so that process, method, product or equipment including a series of elements are not only wrappedThose elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, productOr the element that equipment is intrinsic.In the absence of more restrictions, being not precluded is including process, the side of the elementThere is also other identical or equivalent elements in method, product or equipment.
For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.Certainly, implementing thisThe function of each module can be realized in the same or multiple software and or hardware when specification embodiment, it can also be by realityShow the module of same function by the combination realization etc. of multiple submodule or subelement.Installation practice described above is onlySchematically, for example, the division of the unit, only a kind of logical function partition, can there is other draw in actual implementationThe mode of dividing, such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored,Or it does not execute.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be by oneThe indirect coupling or communication connection of a little interfaces, device or unit can be electrical property, mechanical or other forms.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is completeEntirely can by by method and step carry out programming in logic come so that controller with logic gate, switch, specific integrated circuit, programmableLogic controller realizes identical function with the form for being embedded in microcontroller etc..Therefore this controller is considered one kindHardware component, and the structure that the device for realizing various functions that its inside includes can also be considered as in hardware component.OrPerson even, can will be considered as realizing the device of various functions either the software module of implementation method can be hardware againStructure in component.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program productFigure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructionsThe combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programsInstruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produceA raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for realThe device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spyDetermine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram orThe function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that countingSeries of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer orThe instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram oneThe step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, netNetwork interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/orThe forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable mediumExample.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any methodOr technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), movesState random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasableProgrammable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devicesOr any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculatesMachine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It will be understood by those skilled in the art that the embodiment of this specification can provide as the production of method, system or computer programProduct.Therefore, in terms of this specification embodiment can be used complete hardware embodiment, complete software embodiment or combine software and hardwareEmbodiment form.Moreover, it wherein includes computer available programs that this specification embodiment, which can be used in one or more,Implement in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of codeThe form of computer program product.
This specification embodiment can describe in the general context of computer-executable instructions executed by a computer,Such as program module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, journeySequence, object, component, data structure etc..This specification embodiment can also be practiced in a distributed computing environment, in these pointsCloth calculates in environment, by executing task by the connected remote processing devices of communication network.In distributed computing ringIn border, program module can be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodimentDividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system realityFor applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the methodPart explanation.In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ",The description of " specific example " or " some examples " etc. means specific features described in conjunction with this embodiment or example, structure, materialOr feature is contained at least one embodiment or example of this specification embodiment.In the present specification, to above-mentioned termSchematic representation be necessarily directed to identical embodiment or example.Moreover, description specific features, structure, material orPerson's feature may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, in not conflicting feelingsUnder condition, those skilled in the art by different embodiments or examples described in this specification and different embodiment or can showThe feature of example is combined.
The foregoing is merely the embodiments of this specification embodiment, are not limited to this specification embodiment.It is rightFor those skilled in the art, this specification embodiment can have various modifications and variations.It is all in this specification embodimentAny modification, equivalent replacement, improvement and so within spirit and principle, the right that should be included in this specification embodiment are wantedWithin the scope of asking.