CN117350547B - Method, device, equipment and storage medium for determining risk processing scheme of order - Google Patents
Method, device, equipment and storage medium for determining risk processing scheme of order Download PDFInfo
- Publication number
- CN117350547B CN117350547B CN202311513138.7A CN202311513138A CN117350547B CN 117350547 B CN117350547 B CN 117350547B CN 202311513138 A CN202311513138 A CN 202311513138A CN 117350547 B CN117350547 B CN 117350547B
- Authority
- CN
- China
- Prior art keywords
- target
- risk
- order
- processing scheme
- prediction
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 276
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 71
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000012216 screening Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012954 risk control Methods 0.000 abstract description 16
- 238000012549 training Methods 0.000 description 10
- 238000013145 classification model Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for determining a risk processing scheme of an order, wherein the method comprises the following steps: if the target early warning signal set of the target order in the current evaluation period is not empty, carrying out order risk classification prediction according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result; if the risk prediction result is that the risk exists, carrying out classified prediction on the risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set; and determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set. The overall risk control of the order is fully considered, and the accuracy of the target risk processing scheme is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and risk control, in particular to a method, a device, equipment and a storage medium for determining a risk processing scheme of an order.
Background
In the field of risk control, a risk processing scheme is generally generated for each early warning signal generated by each monitoring index corresponding to an order, and the timeliness of risk control is improved, but the overall risk control of the order is ignored. In addition, at present, data corresponding to the early warning signals are input into a classification model to conduct classification prediction of a risk processing scheme, and the accuracy of the classification model is limited due to the difficulty in acquiring training samples and the control of training cost, so that the accuracy of the risk processing scheme determined by the classification model is not high.
Disclosure of Invention
Based on this, it is necessary to propose a method, a device, equipment and a storage medium for determining a risk processing scheme of an order, aiming at the technical problems that in the field of risk control in the prior art, overall risk control of the order is omitted and accuracy of the risk processing scheme determined by adopting a classification model is not high.
In a first aspect, a method for determining a risk processing scheme of an order is provided, the method comprising:
Acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
if the target early warning signal set is not empty, carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result;
if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set;
and determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
In a second aspect, there is provided a risk processing scheme determining apparatus for an order, the apparatus comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
the order risk prediction module is used for carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set if the target early warning signal set is not empty, so as to obtain a risk prediction result;
the scheme prediction module is used for carrying out classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order if the risk prediction result is that the risk exists, so as to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set so as to obtain a second risk processing scheme set;
And the target risk processing scheme determining module is used for determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
In a third aspect, a computer device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the risk processing scheme determination method of an order as described above when the computer program is executed.
In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the risk treatment plan determination method of an order described above.
According to the method, the device, the equipment and the storage medium for determining the risk processing scheme of the order, if a target early-warning signal set of a target order in a current evaluation period is not empty, order risk classification prediction in a target order stage corresponding to the current evaluation period is carried out according to the target early-warning signal set and target monitoring data corresponding to the target early-warning signal set, so that a risk prediction result is obtained; if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set; and determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set. The whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on a target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is an application environment diagram of a method of determining a risk processing scheme for an order in one embodiment;
FIG. 2 is a flow diagram of a method of determining a risk processing scheme for an order in one embodiment;
FIG. 3 is a block diagram of a risk processing scheme determination device for an order in one embodiment;
FIG. 4 is a block diagram of a computer device in one embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method for determining the risk processing scheme of the order provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, wherein a client 110 communicates with a server 120 through a network.
The server 120 may obtain, through the client 110, a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, where the target order has a plurality of order phases, each order phase is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period. And the server 120 is configured to, if the target early-warning signal set is not empty, perform order risk classification prediction under a target order stage corresponding to a current evaluation period according to the target early-warning signal set and target monitoring data corresponding to the target early-warning signal set to obtain a risk prediction result, if the risk prediction result is that there is a risk, perform classification prediction of a risk processing scheme according to the target early-warning signal set, the target monitoring data and target basic information of the target order to obtain a first risk processing scheme set, determine a risk processing scheme from a preset processing scheme knowledge graph according to the target early-warning signal set, obtain a second risk processing scheme set, and determine a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set. The whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on a target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
Among other things, the client 110 may be, but is not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices. The server 120 may be implemented by a stand-alone server or a server cluster formed by a plurality of servers. The present invention will be described in detail with reference to specific examples.
Referring to fig. 2, fig. 2 is a flowchart of a method for determining a risk processing scheme of an order according to an embodiment of the present invention, including the following steps:
s1: acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
specifically, a target early warning signal set of a target order input by a user in a current evaluation period can be obtained, a target early warning signal set formed by all early warning signals of the target order in the current evaluation period can also be obtained from a preset storage space, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, the target early warning signal set is generated at the end of each evaluation period, the target early warning signal set formed by all early warning signals of the target order in the current evaluation period can also be obtained from a third party application, the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, the target early warning signal set is generated at the end of each evaluation period, and the target signal set formed by all early warning signals of the target order in the current evaluation period can also be obtained from a client, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period.
The target order is an order requiring overall risk control of the order. The order may be a purchase order, a production order, or a service order.
Each target order is divided into a plurality of order phases, and each order phase is provided with at least one evaluation period. And at the end of the evaluation period, acquiring all early warning signals obtained by inspection in the evaluation period to form an early warning signal set, and taking the early warning signal set as a basis for determining a risk processing scheme of a target order for the order in the evaluation period.
The early warning signal set contains at least 0 early warning signals.
Optionally, at least one early warning signal is generated at the end of each evaluation period, so that the target early warning signal set is not empty, and thus the evaluation of the order risk is performed once at the end of each evaluation period.
Optionally, the early warning signal is based on the monitoring index, the monitoring data corresponding to the target order is inspected, if the inspection result is the early warning requirement meeting the monitoring index, the early warning signal is generated, and if the inspection result is the early warning requirement not meeting the monitoring index, the early warning signal is not generated.
The monitoring data includes: one or more of device monitoring data, internet data, and enterprise-internal data. Device monitoring data includes, but is not limited to: one or more of voice data, video data, text data. Internet data includes, but is not limited to: news information, transaction data. The enterprise internal data includes, but is not limited to: production data, sales data, financial data, and human data.
The current evaluation period is the evaluation period in which the overall risk control of the order is required currently.
And taking the early warning signal set corresponding to the current evaluation period as a target early warning signal set. That is, the target early warning signal set is a set of all early warning signals corresponding to the target order in the current evaluation period.
S2: if the target early warning signal set is not empty, carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result;
and taking the current evaluation period of the target order in the order stage corresponding to the target order as a target order stage.
And the target monitoring data corresponding to the target early warning signal set, namely all the monitoring data of the target order in the current evaluation period.
Specifically, if the target early-warning signal set is not empty, this means that the target order is at risk for the monitoring index in the current evaluation period, and further order risk prediction is needed, so that the target early-warning signal set and the target monitoring data corresponding to the target early-warning signal set are input into a model obtained based on artificial intelligence training, thereby realizing order risk classification prediction under the target order stage corresponding to the current evaluation period, and generating a risk prediction result according to the vector obtained by prediction. By adopting order risk classification prediction based on target order stage, different prediction methods are adopted for different order stages, and the prediction accuracy is improved.
The value of the risk prediction result is risky or risky.
Optionally, order types are set for orders, and models can be trained for different order stages corresponding to different order types to realize order risk classification prediction.
Optionally, the target order stage, the target early-warning signal set and the target monitoring data corresponding to the target early-warning signal set are spliced, and the spliced data are input into a model obtained based on artificial intelligence training, so that order risk classification prediction under the target order stage corresponding to the current evaluation period is realized.
S3: if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set;
the target basic information of the target order is basic information describing the target order. The basic information includes: order identification, name or business name of the relevant party to the order (e.g., buyer, seller), order object, and order details. The order identification may be data uniquely identifying an order, such as an order name, an order ID, etc.
Specifically, if the risk prediction result is that there is a risk, this means that there is an order risk of the target order, and a risk processing scheme needs to be determined to solve the order risk, so that the target early warning signal set, the target monitoring data and the target basic information of the target order are input into a model obtained based on artificial intelligence training to implement classification prediction of the risk processing scheme, and a first risk processing scheme set is determined according to the vector obtained by prediction; and matching each early warning signal in the target early warning signal set with a risk processing scheme from a processing scheme knowledge graph, and taking all risk processing schemes matched with the target early warning signal set as a second risk processing scheme set.
Optionally, the target early warning signal set, the target monitoring data and the target basic information of the target order are spliced, and the spliced data are input into a model obtained based on artificial intelligence training, so that classified prediction of a risk processing scheme is realized.
The processing scheme knowledge graph comprises nodes and edges, the nodes are entities, the edges between the two nodes describe the relationship of the two nodes, wherein the entities are early warning signals or risk processing schemes, the two nodes comprise a node corresponding to an early warning signal and a node corresponding to a risk processing scheme, and the risk processing scheme can be adopted for risk control when the early warning signal is expressed.
S4: and determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
Specifically, based on a preset screening rule, screening risk processing schemes from the first risk processing scheme set and the second risk processing scheme set, and taking the screened risk processing schemes as target risk processing schemes corresponding to the target orders.
Optionally, the preset screening rule is a risk processing scheme existing in both the first risk processing scheme set and the second risk processing scheme set, and the risk processing scheme with the highest success rate is used, where the success rate refers to a success rate of executing the risk processing scheme to solve the risk of the order.
According to the method, the whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on the target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
In one embodiment, the step of performing classified prediction of the risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set includes:
s31: inputting the target early warning signal set, the target monitoring data and the target basic information into a preset scheme prediction model to conduct classified prediction of a risk processing scheme, so as to obtain a first prediction vector;
specifically, the target early warning signal set, the target monitoring data and the target basic information are input into a preset scheme prediction model to conduct classified prediction of a risk processing scheme, and data obtained through classified prediction are used as a first prediction vector.
The preset scheme prediction model is a classification model obtained based on neural network training, and the model structure and the specific training method of the preset scheme prediction model can be selected from the prior art, and are not described in detail herein.
The value of each vector element in the first predictive vector is a probability value and each vector element in the first predictive vector corresponds to a risk handling scheme.
S32: extracting individual characteristics of the order according to the target early warning signal set, the target monitoring data and the target basic information;
Specifically, the target early warning signal set, the target monitoring data and the target basic information are input into a preset feature extraction model, and the feature extraction model outputs individual features of an order.
The order personality characteristic is a characteristic of an order.
The feature extraction model is a model obtained based on neural network training, and will not be described in detail herein.
S33: acquiring the corresponding successful order commonality characteristics of each risk processing scheme;
specifically, the successful order commonality feature corresponding to each risk processing scheme input by the user may be obtained, the successful order commonality feature corresponding to each risk processing scheme may be obtained from a preset storage space, the successful order commonality feature corresponding to each risk processing scheme may be obtained from a third party application, and the successful order commonality feature corresponding to each risk processing scheme may be obtained from a client.
Each of the risk processing schemes corresponds to a successful order commonality feature. The successful order commonality is that of all orders for which the risk handling scheme successfully addresses the order risk.
S34: performing similarity calculation on the individual features of the orders and the common features of each successful order to obtain a similarity set;
Specifically, a cosine similarity-based calculation algorithm is used for calculating the similarity between the individual characteristics of the order and the commonality characteristics of each successful order, and all the calculated similarities are used as a similarity set.
S35: and determining the first risk treatment scheme set according to the similarity set and the first prediction vector.
Specifically, according to the similarity set and the first prediction vector, risk processing schemes are screened from all risk processing schemes corresponding to the first prediction vector, and all risk processing schemes screened are used as the first risk processing scheme set.
Compared with the existing mode of only adopting a classification model, the method and the device for classifying the individual features of the orders in the first risk processing scheme set based on the similarity and the result of classification prediction of the risk processing scheme determine the first risk processing scheme set, achieve the purpose of considering the similarity between the common features of all orders of which the risk processing scheme can successfully solve the risks of the orders and the individual features of the target orders, improve the probability that the risk processing scheme in the first risk processing scheme set solves the risks of the orders of the target orders, and further improve the accuracy of the target risk processing scheme.
In one embodiment, the step of determining the first set of risk treatment plans based on the set of similarities and the first prediction vector includes:
s351: carrying out classified prediction of a risk processing scheme according to each monitoring data, each early warning signal set and the target basic information of the target order to obtain a second prediction vector;
and each monitoring data of the target order is all monitoring data corresponding to the target order. And each early warning signal set of the target order is all the early warning signal sets corresponding to the target order.
Specifically, each monitoring data, each early warning signal set and the target basic information of the target order are input into a model obtained based on artificial intelligence training to conduct classified prediction of a risk processing scheme, and the predicted data are used as a second prediction vector.
The value of each vector element in the second predictive vector is a probability value and each vector element in the second predictive vector corresponds to a risk handling scheme.
S352: fusing the first prediction vector and the second prediction vector to obtain the target prediction vector;
specifically, the first prediction vector and the second prediction vector are subjected to weighted summation of values of corresponding vector elements of the same risk processing scheme, and data obtained by the weighted summation is used as the target prediction vector.
For example, the vector elements of the ith row and the jth column in the first prediction vector and the vector elements of the ith row and the jth column in the second prediction vector correspond to the same risk processing scheme, so that the value of the vector element of the ith row and the jth column in the first prediction vector and the value of the vector element of the ith row and the jth column in the second prediction vector are weighted and summed, and a probability value obtained by the weighted and summed is used as the value of the vector element of the ith row and the jth column in the target prediction vector.
S353: and determining the first risk treatment scheme set according to the similarity set and the target prediction vector.
Specifically, according to the similarity set and the first prediction vector, risk processing schemes are screened from all risk processing schemes corresponding to the first prediction vector, and all risk processing schemes screened are used as the first risk processing scheme set.
Compared with the existing mode of only adopting a classification model, the method and the device for classifying the individual features of the orders in the first risk processing scheme set have the advantages that the similarity among the common features of the successful orders of the individual features of the orders is calculated firstly, the first risk processing scheme set is determined based on the similarity and the classification prediction result of the risk processing scheme, the similarity between the common features of all orders of which the risk of the orders can be successfully solved by each risk processing scheme and the individual features of the target orders is considered, the probability that the risk processing scheme in the first risk processing scheme set solves the risk of the orders of the target orders is improved, and the accuracy of the target risk processing scheme is further improved; and the first prediction vector obtained by carrying out classified prediction on the data of the target order in the current evaluation period by the risk processing scheme is fused with the second prediction vector obtained by carrying out classified prediction on all the data of the target order by the risk processing scheme to serve as the target prediction vector, so that the global influence (namely the second prediction vector) of long-term data and the local influence (namely the first prediction vector) of short-term data are fully considered, the accuracy of the determined target prediction vector is improved, and the accuracy of the target risk processing scheme is further improved.
In one embodiment, the step of determining the first set of risk treatment plans based on the set of similarities and the target prediction vector includes:
s35311: correcting the target prediction vector by adopting the similarity set;
optionally, a weighted sum of two values of the same risk processing scheme (one value is from the similarity set and the other value is from the target prediction vector) is performed according to the similarity set and the target prediction vector to achieve correction, and the data obtained by correction is taken as the target prediction vector.
It will be appreciated that, using the set of similarities, other algorithms may be used to correct the target prediction vector, for example, setting the value of the risk processing scheme corresponding to the similarity in the set of similarities smaller than the probability threshold to 0.
It will be appreciated that the greater the value in the target prediction vector, the greater the likelihood that the risk handling scheme to which the value corresponds will address the order risk of the target order.
S35312: and respectively corresponding risk processing schemes of vector elements with values larger than a first threshold in the corrected target prediction vector are used as the first risk processing scheme set.
Specifically, the risk processing scheme corresponding to the vector element with the value larger than the first threshold value in the target prediction vector after correction is a scheme with relatively high possibility of solving the order risk of the target order.
Compared with the existing mode of only adopting a classification model, the method and the device for classifying the individual features of the orders in the first risk processing scheme set based on the similarity and the result of classification prediction of the risk processing scheme determine the first risk processing scheme set, achieve the purpose of considering the similarity between the common features of all orders of which the risk of the orders can be successfully solved by each risk processing scheme and the individual features of the target orders, improve the probability that the risk processing scheme in the first risk processing scheme set solves the risk of the orders of the target orders, and further improve the accuracy of the target risk processing scheme.
In one embodiment, the step of determining the first set of risk treatment plans based on the set of similarities and the target prediction vector further comprises:
s35321: the risk processing schemes respectively corresponding to the vector elements with the values larger than a second threshold value in the target prediction vector are used as a prediction scheme set;
Optionally, the second threshold is smaller than the first threshold.
Specifically, the risk processing schemes respectively corresponding to the vector elements with the values larger than the second threshold value in the target prediction vector realize that candidate risk processing schemes are selected from the classification prediction perspective.
S35322: the risk processing schemes respectively corresponding to the similarities with the values larger than a third threshold value in the similarity set are used as a similarity scheme set;
specifically, the risk processing schemes corresponding to the respective similarities with the values larger than the third threshold in the similarity set are selected from the aspect of feature similarity.
S35323: and performing intersection calculation on the prediction scheme set and the similar scheme set to obtain the first risk processing scheme set.
Specifically, the prediction scheme set and the similar scheme set are subjected to intersection calculation, so that the risk processing scheme in the intersection has high possibility of solving the order risk of the target order, and the possibility of classifying and predicting the order risk as the solution target order is high.
According to the method, the intersection of the prediction scheme set determined based on the target prediction vector and the similarity scheme set determined based on the similarity set is used as the first risk processing scheme set, and the accuracy of the risk processing scheme in the first risk processing scheme set is improved through the double consideration angle, so that the success rate of solving the order risk of the target order by the target risk processing scheme is improved.
In one embodiment, the step of determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set includes:
s411: screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set based on preset screening rules to serve as initial risk treatment schemes;
specifically, based on a preset screening rule, screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set, and taking the screened risk treatment schemes as initial risk treatment schemes.
S412: carrying out future trend prediction of order risk according to the monitoring data, the early warning signal sets and the target basic information of the target order to obtain a trend prediction result;
specifically, each monitoring data, each early warning signal set and the target basic information of the target order are input into a preset trend prediction model to predict future trend of the order risk, and the predicted data is used as a trend prediction result.
The trend prediction model is a model trained based on an ARIMA model. ARIMA model, known as auto-regressive integral moving average model (Autoregressive Integrated Moving Average Model).
Optionally, the trend prediction result describes a correspondence between time and order risk result.
S413: judging whether order risks exist in a target time window according to the trend prediction result, wherein the starting time of the target time window is the ending time of the current evaluation period;
specifically, in the target time window, if any one of the order risk results of the trend prediction results is a risk, determining that the order risk exists in the target time window; and in the target time window, if the order risk results of the trend prediction results are all risk-free, determining that the order risk does not exist in the target time window.
S414: if yes, correcting the initial risk treatment scheme to obtain the target risk treatment scheme;
specifically, if there is an order risk, that is, there is a target time window, in which risk processing needs to be enhanced, a preset correction method is adopted to correct the initial risk processing scheme, and a default setting in the initial risk processing scheme is used to correct the initial risk processing scheme to be an alternative setting, so that the corrected initial risk processing scheme can perform order risk processing more strictly, and the corrected initial risk processing scheme is used as the target risk processing scheme, wherein the requirement of the default setting is less than that of the alternative setting.
S415: and if the target risk treatment scheme does not exist, the initial risk treatment scheme is used as the target risk treatment scheme.
Specifically, if the initial risk processing scheme is not present, that is, there is no order risk in the target time window, the initial risk processing scheme is directly used as the target risk processing scheme, and at this time, default settings are adopted in the target risk processing scheme.
In this embodiment, when there is an order risk in the target time window after the current evaluation period, the initial risk processing scheme is modified and then used as the target risk processing scheme, so that future trends of the order risk are considered, the accuracy of the target risk processing scheme is improved, and the success rate of the target risk processing scheme for solving the order risk of the target order is further improved.
In one embodiment, the step of determining the target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set further includes:
s421: based on a preset screening rule, screening the risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set to obtain a scheme to be treated;
Specifically, based on a preset screening rule, screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set, and taking the screened risk treatment schemes as schemes to be treated.
S422: acquiring order portrait data of the target order;
specifically, the order portrait data of the target order input by the user can be obtained, the order portrait data of the target order can be obtained from a preset storage space, the order portrait data of the target order can be obtained from a third party application, and the order portrait data of the target order can be obtained from a client.
The order portraits data is used to describe the correspondence between portraits indicators and index values.
S423: and carrying out parameter item configuration on the scheme to be processed according to the order portrait data to obtain the target risk processing scheme corresponding to the target order.
Specifically, according to the order portrait data, a table look-up method is adopted to determine the value of each parameter item in the to-be-processed scheme, the determined value is added into the to-be-processed scheme, and the to-be-processed scheme with the configured parameter items is used as the target risk processing scheme corresponding to the target order.
According to the embodiment, parameter item configuration is carried out on the scheme to be processed according to the order portrait data, personalized configuration of the scheme to be processed is automatically carried out, the scheme to be processed completing parameter item configuration is enabled to be more in line with actual requirements of a target order, and then the success rate of the target risk processing scheme for solving the order risk of the target order is improved.
Referring to fig. 3, in one embodiment, a risk processing scheme determining apparatus for an order is provided, the apparatus including:
the data acquisition module 801 is configured to acquire a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, where the target order has a plurality of order phases, each order phase is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
the order risk prediction module 802 is configured to, if the target early-warning signal set is not empty, perform order risk classification prediction under a target order stage corresponding to a current evaluation period according to the target early-warning signal set and target monitoring data corresponding to the target early-warning signal set, so as to obtain a risk prediction result;
The scheme prediction module 803 is configured to, if the risk prediction result is that there is a risk, perform classification prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data, and target basic information of the target order, obtain a first risk processing scheme set, determine a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set, and obtain a second risk processing scheme set;
the target risk processing scheme determining module 804 is configured to determine a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
According to the method, the whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on the target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
In one embodiment, the step of performing, by the solution prediction module 803, classification prediction of a risk processing solution according to the target early warning signal set, the target monitoring data, and the target basic information of the target order, to obtain a first risk processing solution set includes:
inputting the target early warning signal set, the target monitoring data and the target basic information into a preset scheme prediction model to conduct classified prediction of a risk processing scheme, so as to obtain a first prediction vector;
extracting individual characteristics of the order according to the target early warning signal set, the target monitoring data and the target basic information;
acquiring the corresponding successful order commonality characteristics of each risk processing scheme;
performing similarity calculation on the individual features of the orders and the common features of each successful order to obtain a similarity set;
and determining the first risk treatment scheme set according to the similarity set and the first prediction vector.
In one embodiment, the step of determining the first risk treatment plan set by the plan prediction module 803 according to the similarity set and the first prediction vector includes:
Carrying out classified prediction of a risk processing scheme according to each monitoring data, each early warning signal set and the target basic information of the target order to obtain a second prediction vector;
fusing the first prediction vector and the second prediction vector to obtain the target prediction vector;
and determining the first risk treatment scheme set according to the similarity set and the target prediction vector.
In one embodiment, the step of determining the first risk treatment plan set by the plan prediction module 803 according to the similarity set and the target prediction vector includes:
correcting the target prediction vector by adopting the similarity set;
and respectively corresponding risk processing schemes of vector elements with values larger than a first threshold in the corrected target prediction vector are used as the first risk processing scheme set.
In one embodiment, the step of determining the first risk treatment plan set by the plan prediction module 803 according to the similarity set and the target prediction vector further includes:
the risk processing schemes respectively corresponding to the vector elements with the values larger than a second threshold value in the target prediction vector are used as a prediction scheme set;
The risk processing schemes respectively corresponding to the similarities with the values larger than a third threshold value in the similarity set are used as a similarity scheme set;
and performing intersection calculation on the prediction scheme set and the similar scheme set to obtain the first risk processing scheme set.
In one embodiment, the step of determining, by the target risk processing scheme determining module 804, a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set includes:
screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set based on preset screening rules to serve as initial risk treatment schemes;
carrying out future trend prediction of order risk according to the monitoring data, the early warning signal sets and the target basic information of the target order to obtain a trend prediction result;
judging whether order risks exist in a target time window according to the trend prediction result, wherein the starting time of the target time window is the ending time of the current evaluation period;
if yes, correcting the initial risk treatment scheme to obtain the target risk treatment scheme;
And if the target risk treatment scheme does not exist, the initial risk treatment scheme is used as the target risk treatment scheme.
In one embodiment, the step of determining, by the target risk processing scheme determining module 804, a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set further includes:
based on a preset screening rule, screening the risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set to obtain a scheme to be treated;
acquiring order portrait data of the target order;
and carrying out parameter item configuration on the scheme to be processed according to the order portrait data to obtain the target risk processing scheme corresponding to the target order.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes non-volatile and/or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is for communicating with an external client via a network connection. The computer program, when executed by a processor, performs the functions or steps of a method server side for determining a risk processing scheme for an order.
In one embodiment, a computer device is presented comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
if the target early warning signal set is not empty, carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result;
if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set;
And determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
According to the method, the whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on the target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
In one embodiment, a computer readable storage medium is presented, the computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of:
acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
If the target early warning signal set is not empty, carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result;
if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set;
and determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set.
According to the method, the whole risk control of the order is fully considered by carrying out order risk prediction and generation of a target risk processing scheme based on the target early warning signal set of the order in one period; and the target risk treatment scheme is determined according to the first risk treatment scheme set obtained by classification prediction of the risk treatment scheme and the second risk treatment scheme set obtained by the treatment scheme knowledge graph, and meanwhile, the risk treatment schemes which can be used by the classification prediction and the target early warning signal set are considered, so that the accuracy of the target risk treatment scheme is improved.
It should be noted that, the functions or steps implemented by the computer readable storage medium or the computer device may correspond to the relevant descriptions of the server side and the client side in the foregoing method embodiments, and are not described herein for avoiding repetition.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (6)
1. A method of determining a risk processing scheme for an order, the method comprising:
acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, wherein the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
If the target early warning signal set is not empty, carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set to obtain a risk prediction result;
if the risk prediction result is that the risk exists, performing classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set to obtain a second risk processing scheme set;
determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set;
the step of performing classified prediction of the risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set includes:
inputting the target early warning signal set, the target monitoring data and the target basic information into a preset scheme prediction model to conduct classified prediction of a risk processing scheme, so as to obtain a first prediction vector;
Extracting individual characteristics of the order according to the target early warning signal set, the target monitoring data and the target basic information;
acquiring the corresponding successful order commonality characteristics of each risk processing scheme;
performing similarity calculation on the individual features of the orders and the common features of each successful order to obtain a similarity set;
determining the first risk treatment scheme set according to the similarity set and the first prediction vector;
the step of determining the first risk treatment plan set according to the similarity set and the first prediction vector includes:
carrying out classified prediction of a risk processing scheme according to each monitoring data, each early warning signal set and the target basic information of the target order to obtain a second prediction vector;
fusing the first prediction vector and the second prediction vector to obtain a target prediction vector;
determining the first risk treatment scheme set according to the similarity set and the target prediction vector;
the step of determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set includes:
Screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set based on preset screening rules to serve as initial risk treatment schemes;
carrying out future trend prediction of order risk according to the monitoring data, the early warning signal sets and the target basic information of the target order to obtain a trend prediction result;
judging whether order risks exist in a target time window according to the trend prediction result, wherein the starting time of the target time window is the ending time of the current evaluation period;
if yes, correcting the initial risk treatment scheme to obtain the target risk treatment scheme;
if not, the initial risk treatment scheme is used as the target risk treatment scheme;
the step of fusing the first prediction vector and the second prediction vector to obtain a target prediction vector includes:
and carrying out weighted summation on the values of corresponding vector elements of the same risk processing scheme on the first prediction vector and the second prediction vector, and taking the data obtained by the weighted summation as the target prediction vector.
2. The method of claim 1, wherein the step of determining the first set of risk treatment plans based on the set of similarities and the target prediction vector comprises:
Correcting the target prediction vector by adopting the similarity set;
and respectively corresponding risk processing schemes of vector elements with values larger than a first threshold in the corrected target prediction vector are used as the first risk processing scheme set.
3. The method of determining a risk treatment plan for an order of claim 1, wherein said step of determining said first set of risk treatment plans based on said set of similarities and said target prediction vector further comprises:
the risk processing schemes respectively corresponding to the vector elements with the values larger than a second threshold value in the target prediction vector are used as a prediction scheme set;
the risk processing schemes respectively corresponding to the similarities with the values larger than a third threshold value in the similarity set are used as a similarity scheme set;
and performing intersection calculation on the prediction scheme set and the similar scheme set to obtain the first risk processing scheme set.
4. A risk processing scheme determining apparatus for an order, the apparatus comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a target early warning signal set formed by all early warning signals of a target order in a current evaluation period, the target order is provided with a plurality of order stages, each order stage is provided with at least one evaluation period, and the target early warning signal set is generated at the end of each evaluation period;
The order risk prediction module is used for carrying out order risk classification prediction under a target order stage corresponding to the current evaluation period according to the target early warning signal set and target monitoring data corresponding to the target early warning signal set if the target early warning signal set is not empty, so as to obtain a risk prediction result;
the scheme prediction module is used for carrying out classified prediction of a risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order if the risk prediction result is that the risk exists, so as to obtain a first risk processing scheme set, and determining a risk processing scheme from a preset processing scheme knowledge graph according to the target early warning signal set so as to obtain a second risk processing scheme set;
the target risk processing scheme determining module is used for determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set;
the step of performing classified prediction of the risk processing scheme according to the target early warning signal set, the target monitoring data and the target basic information of the target order to obtain a first risk processing scheme set includes:
Inputting the target early warning signal set, the target monitoring data and the target basic information into a preset scheme prediction model to conduct classified prediction of a risk processing scheme, so as to obtain a first prediction vector;
extracting individual characteristics of the order according to the target early warning signal set, the target monitoring data and the target basic information;
acquiring the corresponding successful order commonality characteristics of each risk processing scheme;
performing similarity calculation on the individual features of the orders and the common features of each successful order to obtain a similarity set;
determining the first risk treatment scheme set according to the similarity set and the first prediction vector;
the step of determining the first risk treatment plan set according to the similarity set and the first prediction vector includes:
carrying out classified prediction of a risk processing scheme according to each monitoring data, each early warning signal set and the target basic information of the target order to obtain a second prediction vector;
fusing the first prediction vector and the second prediction vector to obtain a target prediction vector;
determining the first risk treatment scheme set according to the similarity set and the target prediction vector;
The step of determining a target risk processing scheme corresponding to the target order according to the first risk processing scheme set and the second risk processing scheme set includes:
screening risk treatment schemes from the first risk treatment scheme set and the second risk treatment scheme set based on preset screening rules to serve as initial risk treatment schemes;
carrying out future trend prediction of order risk according to the monitoring data, the early warning signal sets and the target basic information of the target order to obtain a trend prediction result;
judging whether order risks exist in a target time window according to the trend prediction result, wherein the starting time of the target time window is the ending time of the current evaluation period;
if yes, correcting the initial risk treatment scheme to obtain the target risk treatment scheme;
if not, the initial risk treatment scheme is used as the target risk treatment scheme;
the step of fusing the first prediction vector and the second prediction vector to obtain a target prediction vector includes:
and carrying out weighted summation on the values of corresponding vector elements of the same risk processing scheme on the first prediction vector and the second prediction vector, and taking the data obtained by the weighted summation as the target prediction vector.
5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the risk handling scheme determination method of an order according to any of claims 1 to 3.
6. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the risk treatment plan determination method of an order according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311513138.7A CN117350547B (en) | 2023-11-14 | 2023-11-14 | Method, device, equipment and storage medium for determining risk processing scheme of order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311513138.7A CN117350547B (en) | 2023-11-14 | 2023-11-14 | Method, device, equipment and storage medium for determining risk processing scheme of order |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117350547A CN117350547A (en) | 2024-01-05 |
| CN117350547B true CN117350547B (en) | 2024-03-26 |
Family
ID=89371115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311513138.7A Active CN117350547B (en) | 2023-11-14 | 2023-11-14 | Method, device, equipment and storage medium for determining risk processing scheme of order |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117350547B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| CN113610627A (en) * | 2021-07-27 | 2021-11-05 | 浙江惠瀜网络科技有限公司 | Data processing method and device for risk early warning |
| CN114066242A (en) * | 2021-11-11 | 2022-02-18 | 北京道口金科科技有限公司 | Enterprise risk early warning method and device |
| CN115082209A (en) * | 2022-06-28 | 2022-09-20 | 平安银行股份有限公司 | Business data risk early warning method and device, computer equipment and storage medium |
| CN115345533A (en) * | 2022-10-20 | 2022-11-15 | 阿里健康科技(杭州)有限公司 | Order data processing method, device, equipment and storage medium |
| WO2023065545A1 (en) * | 2021-10-19 | 2023-04-27 | 平安科技（深圳）有限公司 | Risk prediction method and apparatus, and device and storage medium |
| CN116739759A (en) * | 2023-07-14 | 2023-09-12 | 深圳乐信软件技术有限公司 | Asset and fund matching method, device and equipment based on order risk identification |
-
2023
- 2023-11-14 CN CN202311513138.7A patent/CN117350547B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| CN113610627A (en) * | 2021-07-27 | 2021-11-05 | 浙江惠瀜网络科技有限公司 | Data processing method and device for risk early warning |
| WO2023065545A1 (en) * | 2021-10-19 | 2023-04-27 | 平安科技（深圳）有限公司 | Risk prediction method and apparatus, and device and storage medium |
| CN114066242A (en) * | 2021-11-11 | 2022-02-18 | 北京道口金科科技有限公司 | Enterprise risk early warning method and device |
| CN115082209A (en) * | 2022-06-28 | 2022-09-20 | 平安银行股份有限公司 | Business data risk early warning method and device, computer equipment and storage medium |
| CN115345533A (en) * | 2022-10-20 | 2022-11-15 | 阿里健康科技(杭州)有限公司 | Order data processing method, device, equipment and storage medium |
| CN116739759A (en) * | 2023-07-14 | 2023-09-12 | 深圳乐信软件技术有限公司 | Asset and fund matching method, device and equipment based on order risk identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117350547A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| Benchaji et al. | Enhanced credit card fraud detection based on attention mechanism and LSTM deep model | |
| CN108564386B (en) | Merchant identification method and device, computer equipment and storage medium | |
| CN111400560A (en) | Method and system for predicting based on heterogeneous graph neural network model | |
| CN108491511B (en) | Data mining method and device based on graph data and model training method and device | |
| CN110135943B (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN111737546B (en) | Method and device for determining entity service attribute | |
| US20220253856A1 (en) | System and method for machine learning based detection of fraud | |
| CN111291264A (en) | Access object prediction method and device based on machine learning and computer equipment | |
| CN110609954A (en) | Data acquisition method and device, computer equipment and storage medium | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN112905876A (en) | Information pushing method and device based on deep learning and computer equipment | |
| US11645716B2 (en) | System and method for implementing a trust discretionary distribution tool | |
| CN117196322B (en) | Intelligent wind control method, intelligent wind control device, computer equipment and storage medium | |
| CN117350547B (en) | Method, device, equipment and storage medium for determining risk processing scheme of order | |
| CN114692785B (en) | Behavior classification method, device, equipment and storage medium | |
| CN115424001A (en) | Scene similarity estimation method and device, computer equipment and storage medium | |
| CN114529399A (en) | User data processing method, device, computer equipment and storage medium | |
| CN114418743A (en) | Account information detection method, device, equipment, storage medium and program product | |
| CN109034207B (en) | Data classification method and device and computer equipment | |
| US20230377004A1 (en) | Systems and methods for request validation | |
| CN117455664A (en) | Method and device for processing resource data, computer equipment and storage medium | |
| CN113436020B (en) | Illegal account identification method and device, computer equipment and storage medium | |
| US20230334362A1 (en) | Self-adaptive multi-model approach in representation feature space for propensity to action | |
| CN118037458A (en) | Service request processing method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |