CN112700322A - Order sampling detection method and device, electronic equipment and storage medium - Google Patents
Order sampling detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112700322A CN112700322A CN202011635336.7A CN202011635336A CN112700322A CN 112700322 A CN112700322 A CN 112700322A CN 202011635336 A CN202011635336 A CN 202011635336A CN 112700322 A CN112700322 A CN 112700322A
- Authority
- CN
- China
- Prior art keywords
- order
- orders
- batch
- sampling
- false
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 170
- 238000005070 sampling Methods 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 claims description 31
- 238000007689 inspection Methods 0.000 claims description 26
- 238000012795 verification Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 238000012954 risk control Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an order sampling detection method, an order sampling detection device, electronic equipment and a storage medium. The order sampling detection method comprises the following steps: acquiring an order sample group of a merchant to be detected; randomly extracting a preset number of sampling orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants; and determining the authenticity of the order sample group according to the detection result of the sampling order. The embodiment of the invention reduces the detection cost of the order sample group sampling detection, ensures the accuracy of the order sample group sampling detection, and further improves the accuracy of the loan admission result of the merchant to be detected according to the authenticity of the order sample group.
Description
Technical Field
The embodiment of the invention relates to the technical field of internet, in particular to an order sampling detection method, an order sampling detection device, electronic equipment and a storage medium.
Background
In supply chain financial loan transactions, it is necessary to determine the admittance and payment of a loan with reference to the authenticity of the actual order of the loan merchant. Different merchants have different scale order services, so the number of orders in a unit period is different. For the purpose of risk control, the authenticity of the order is determined according to the order data of the merchant, the order is falsified and truthful, and the valid real order is included in the reference range of loan.
If the authenticity detection is performed on all the orders of the lending merchant, a huge amount of work is brought, so that the common method is to randomly extract a plurality of orders from all the orders of the lending merchant for detection, and determine the authenticity of the whole order according to the detection results of the extracted plurality of orders. The number of orders drawn at random therefore determines the accuracy and efficiency of the overall drawing of the order.
However, since the orders of different loan merchants have different scales, if the same standard is adopted to randomly draw different loan merchants, the detection of the orders of the merchants is inaccurate, and the correctness of the final loan admission decision is affected.
Disclosure of Invention
The embodiment of the invention provides an order sample detection method, an order sample detection device, electronic equipment and a storage medium, which can reduce the detection cost of the order sample group sample detection and ensure the accuracy of the order sample group sample detection.
In a first aspect, an embodiment of the present invention provides an order sampling detection method, including:
acquiring an order sample group of a merchant to be detected;
randomly extracting a preset number of sampling orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and determining the authenticity of the order sample group according to the detection result of the sampling order.
In a second aspect, an embodiment of the present invention further provides an order sampling detection apparatus, including:
the order acquisition module is used for acquiring an order sample group of the merchant to be detected;
the sampling order extraction module is used for randomly extracting a preset number of sampling orders from the order sample group to detect; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and the order authenticity determining module is used for determining the authenticity of the order sample group according to the detection result of the sampling order.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of sample order detection as in any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the order sampling detection method according to any embodiment of the present invention.
The method and the device are based on the obtained order sample group of the merchant to be detected; randomly extracting a preset number of sampling orders from the order sample group for detection; and determining the authenticity of the order sample group according to the detection result of the sampling order, wherein the preset quantity value of the sampling order is determined through a sampling detection model, and the sampling detection model is determined based on the historical order of the merchant. Therefore, the accuracy of sampling detection of the order sample group is guaranteed while the detection cost of sampling detection of the order sample group is reduced, the accuracy of determining the authenticity of the whole order sample group according to the authenticity of the sampled order is guaranteed under the condition that the preset number of sampling detections is minimum, and the accuracy of determining the loan admission result of a merchant to be detected according to the authenticity of the order sample group is improved.
Drawings
FIG. 1 is a flow chart of an order sampling inspection method according to an embodiment of the present invention;
FIG. 2 is a flowchart of an order sampling inspection method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an order sampling inspection system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an order sampling detection apparatus in a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device in a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an order sample inspection method according to a first embodiment of the present invention, which can be applied to randomly extract a part of sample orders from an order sample group for inspection, and determine an inspection result of the whole order sample group according to the inspection result of the sample orders. The method can be executed by an order sampling detection device, which can be implemented in software and/or hardware and can be configured in an electronic device, for example, the electronic device can be a device with communication and computing capabilities, such as a background server. As shown in fig. 1, the method specifically includes:
The merchant to be detected refers to a merchant submitting a loan application, and in order to perform loan admission judgment on the merchant, the authenticity of an order sold by the merchant needs to be detected. The order sample group refers to information of orders that the to-be-detected merchants have completed on all sales platforms within a preset time range, wherein the preset time range is generally set to be recent, such as one month, three months, or half a year. The closer the preset time range is, the more the current business condition of the merchant can be reflected, and the authenticity and the timeliness are realized.
Specifically, the sales order information of the merchant in all E-commerce platforms is determined according to the information of the merchant to be detected, and target order data in the time period is screened out according to the preset time period condition to serve as an order sample group. Illustratively, after the order sample groups of the merchants to be detected on the platforms are obtained, the cleaning and collecting operations of the order sample groups are executed. For example, the important attention information of each order in the order sample group is extracted and stored according to a preset format. The key attention information comprises recipient information, sender information, a recipient address, a sender address, a logistics company name, a logistics list number, delivery time and the like. Illustratively, cleaning source order data is performed according to the requirement of providing the logistics list verification service platform, and the cleaned order data is used as an order sample group to be detected by the merchant.
Because the operation condition of each merchant is different, part of merchants operate really, the orders of the merchants are all real orders, and part of merchants counterfeit the order sales data in order to improve the trust of users, so that a large amount of false orders are manufactured, such as order refreshing and the like. If each order of the merchant to be detected is detected one by one, a large amount of detection manpower, material resources and time are consumed, and for the merchant needing lending, the problems of overlong waiting time and the like occur, so that the operating condition is influenced.
Therefore, a sampling inspection model is established, a time range is set, the time is earlier than the time of the order to be inspected, and the sampling inspection model is determined according to historical order data according with the time. The preset number of samples to be sampled and detected in the order sample group of the merchant to be detected can be determined according to the sampling detection model, so that the detection result of the whole order sample group can be determined according to the detection results of the sampling orders with the preset number.
Specifically, the preset number of the random sampling orders required by the merchant to be detected is determined according to the sampling detection model, and the orders with the preset number are randomly extracted from the order sample group to be detected and detected. The preset number of the sampling orders is determined through the sampling detection model, on one hand, the number of samples needing to be detected is greatly reduced, so that the detection manpower and time expenditure is reduced, the processing speed and the working efficiency of borrowing and lending requests of enterprises to merchants are improved, and on the other hand, the accuracy of the detection results of order sample groups determined according to the detection results of the sampling orders is ensured.
The sampling order is detected according to the logistics authenticity in the order. For merchants conducting order data counterfeiting, the method generally adopts a billing technology, and the authenticity of logistics in billing orders is difficult to guarantee. Specifically, the sampled orders are detected to be authentic, the sampled orders can be communicated with a third-party logistics list verification service platform, information of the orders needing to be verified is input to the logistics list verification service platform and comprises information of a receiver, information of a sender, an address of the receiver, an address of the sender, a name of a logistics company, a number of the logistics list, delivery time and delivery time, the information of the orders needing to be verified is inquired and compared, and if the order information is consistent with the information searched on the third-party logistics list verification service platform, the orders are considered to be real orders.
And 103, determining the authenticity of the order sample group according to the detection result of the sampling order.
And after all the sampling orders are detected, determining the authenticity of the order sample group according to the detection result of the sampling orders. If the detection results of the sampled orders are all true, determining the order sample group as a true order sample group; if the detection result of any sample order is a false order in the detection process of the sample order, immediately stopping the detection of the subsequent sample order, and determining that the order sample group is the false order sample group.
In one possible embodiment, step 103 includes:
and if the detection results of the sampled orders are all true, determining the order sample group as a true order sample group.
After the randomly extracted sample orders are detected, counting the detection results of the sample orders, and if the detection results of the sample orders are all real orders, determining that the order sample group is a real order sample group. This is determined based on the principle that the sample detection model determines the preset number.
For example, a certain merchant to be detected for loan determines that the preset number of sample orders is 100 according to a sample detection model, detects the 100 sample orders one by one, and determines that the order sample group is a real order sample group if all the 100 sample orders are detected as real orders. If a false order appears in the 100 sample orders, the order sample group is directly determined as the false order sample group.
In a possible embodiment, before step 102, the method further includes:
dividing the order sample group according to the preset order quantity in a single batch to obtain at least two batch orders;
correspondingly, randomly extracting a preset number of sampling orders from the order sample group for detection, and determining the authenticity of the order sample group according to the detection result of the sampling orders, wherein the method comprises the following steps:
and randomly extracting a preset number of sampling orders from the orders of each batch in sequence for detection, and determining the authenticity of the orders of each batch according to the detection result of the sampling orders to obtain a real order sample group.
If the preset number of sample orders are directly randomly extracted from all the order sample groups of the detection merchant, when a detection error occurs, the whole order sample group needs to be detected again, and human resources are wasted. Therefore, in the embodiment of the present invention, the order sample group is divided to obtain at least two batch orders, wherein the number in each batch order is the preset number of orders in a single batch, and the number can be determined according to the actual order sample group and the setting in the sampling inspection model, which is not limited herein. For example, the order sample group is divided into N/M batches by taking the order quantity M in a preset single batch as a unit, and the last batch may be less than M. And each batch of orders are extracted and detected respectively, and even if a detection error occurs in a certain batch of orders, the batch of orders only needs to be detected again, so that the workload of rework is greatly reduced.
Specifically, the order sample group is divided into a plurality of small batch orders in batches, each divided batch order is subjected to independent order extraction and detection, the authenticity of each batch order is determined according to the detection result of the sampled order in each batch order, and the real batch order result and the false batch order result are counted.
In a possible embodiment, after step 103, the method further includes:
and determining the wind control result of the merchant to be detected according to the authenticity result of the order sample group of the merchant to be detected based on a preset wind control model so as to determine the loan admission result of the merchant to be detected according to the wind control result.
The wind control model refers to a risk assessment system model for loan admission to a merchant, and can be constructed according to the requirements of a fund provider, which is not limited herein. Firstly, according to a sampling detection model, detecting a sampling order to be detected of a merchant to be detected to obtain an authenticity result of an order sample group, inputting the detected authenticity result into a wind control model, carrying out statistics and calculation by the wind control model according to the result of detecting authenticity of the order sample group, evaluating the current operating condition, integrity degree and the like of the merchant to be detected, calculating a loan result of the merchant to be detected, including loanable amount, risk degree and other parameters, according to a preset risk control model, and particularly taking actual requirements as a reference, wherein the actual requirements are not limited.
The method and the device are based on the obtained order sample group of the merchant to be detected; randomly extracting a preset number of sampling orders from the order sample group for detection; and determining the authenticity of the order sample group according to the detection result of the sampling order, wherein the preset quantity value of the sampling order is determined through a sampling detection model, and the sampling detection model is determined based on the historical order of the merchant. Therefore, the accuracy of sampling detection of the order sample group is guaranteed while the detection cost of sampling detection of the order sample group is reduced, the accuracy of determining the authenticity of the whole order sample group according to the authenticity of the sampled order is guaranteed under the condition that the preset number of sampling detections is minimum, and the accuracy of determining the loan admission result of a merchant to be detected according to the authenticity of the order sample group is improved.
Example two
Fig. 2 is a flowchart of a method for constructing a sampling inspection model in a second embodiment of the present invention, which is applicable to a case where the number of sample orders to be inspected is determined by randomly extracting a part of sample orders from an order sample group. As shown in fig. 2, the method includes:
Historical order validation data refers to order data that occurs within a period of time before the order to be detected is generated. The historical order verification data is closer to the generation time of the order data to be detected, the current business condition of the merchant can be effectively reflected, and certain timeliness and accuracy are achieved. The time is not limited, and can be determined according to actual business time, business volume, historical factors and the like of the merchant.
Specifically, a screening time period of the historical order verification data is set, and all historical order verification data of the merchant in the time period are derived from the e-commerce platform database where the merchant is located. The merchant may be the merchant to be detected, or the merchant of the same grade and type as the merchant to be detected.
The historical order verification data is subjected to batch detection, the order quantity of each batch can be preset without limitation, and authenticity detection is performed on each order in each batchAnd obtaining the final detection result of each batch, namely the batch is a real batch or a false batch. Wherein the proportion of the number of the real batches to the total number of the batches is the real batch order probability, which is set as P1(ii) a The proportion of the number of the false batches to the total number of the batches is a false batch order rate which is set as P2(ii) a In a real batch order, the ratio of the number of dummy orders to the total number of orders in the real batch order is set to p1The ratio of the real order quantity to the total order quantity in the real batch order is 1-p1(ii) a In a dummy batch, the ratio of the number of dummy orders to the total number of orders in the dummy batch order is p2The ratio of the real order quantity to the total order quantity in the dummy batch order is 1-p2. As the detection result of the order batch only comprises a real batch and a false batch, the relation between the order rate of the real batch and the order rate of the false batch is P2＝1-P1。
According to historical order verification data of a merchant, the true batch order probability, the false batch order probability, the proportion of false orders in true batch orders and the proportion of false orders in false batch orders of the sampling detection model are obtained and used as priori knowledge for evaluating the merchant sampling detection model, the order sample to be detected is detected, and the merchant sampling detection model has certain rationality and accuracy.
And step 203, determining that the probability that the batch order to be detected is the real batch order is greater than the number of the sample orders under the condition of the sampling detection confidence coefficient when a preset event occurs and the number is the preset number according to the real batch order probability, the false batch order probability, the proportion of the false orders in the real batch order and the proportion of the false orders in the false batch order.
The preset event is that partial sampling orders are randomly extracted from the to-be-detected batch orders, and the partial sampling orders are real orders.
According to the historical transaction order information of a merchant and the specific requirements of a risk control model, the order quantity of a single batch and the sampling detection confidence coefficient are reasonably set, wherein the sampling detection confidence coefficient is the lowest probability that the set current batch of order samples are real batch of order samples under the condition that a certain number of orders are extracted from the current batch of order samples.
Illustratively, the order quantity of a single batch is set to be M, which is set to be 200 here, the sampling detection confidence is 90%, and the true batch order probability, the false batch order probability, the proportion of false orders in true batch orders and the proportion of false orders in false batch orders are obtained according to the historical order verification data of the merchant.
Randomly sampling 200 orders of each batch, and sequentially verifying the samples; in the extraction process, when one extraction sample is added, namely according to a Bayesian formula, the probability that the current batch of orders is real batch orders is solved under the condition that all the samples of the orders to be detected extracted in the current batch are real order samples; and if the probability is determined to be greater than or equal to the confidence of the sampling detection, determining that the number of the extracted samples corresponding to the probability is the preset number to be solved. And if false orders appear in the sampled orders in the process of random sampling detection when the probability that the current batch orders are real batch orders does not reach the sampling detection confidence coefficient under the condition that the order samples to be detected extracted in the current batch are all real order samples in the process of random sampling detection, stopping detection.
In one possible embodiment, step 203 includes:
based on the traversal algorithm, a preset number in the following formula is determined:
k represents the order quantity of randomly extracting partial sampling orders from the to-be-detected batch orders; p (real batch | A) represents the probability that the batch order to be detected is a real batch order when a preset event occurs; a (K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are real batch orders, wherein the K orders are all real ordersProbability, i.e.
(K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are placed in the false batch orders, wherein the K orders are all the probability of true orders, namely
P1Probability of order for real batch, P2Probability of order for a false batch, p1Is the proportion of false orders in a real batch order, p2Is the proportion of false orders in false batch orders.
Specifically, assume that the order quantity of the randomly extracted partial sample order in the to-be-detected batch order is K, and a (K) is that K orders are randomly extracted from the to-be-detected batch order when the to-be-detected batch order is a real batch order, where the K orders are all the probability of occurrence of the real order,
that is, the real order number M (1-p) in the real batch with the order number M1) I.e. a (K) equals M (1-p) in the real batch1) Dividing the combined number of the randomly extracted K real orders in the real orders by the combined number of the randomly extracted K real orders in all the M orders in the real batch; (K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are placed in the false batch orders, wherein the K orders are the probability of occurrence of real orders,
that is, the number of real orders existing in the dummy batch order with the order number M is M (1-p)2) Then b (K) equals the number M (1-p) in the dummy lot with order number M2) The combined number of the randomly drawn K real orders in the real order is divided by the combined number of the randomly drawn K real orders in all orders in the dummy batch. Using traversal when P (true Lot | A) is required to meet acceptable sample detection confidenceThe most suitable K value is found by searching, that is, the first K value satisfying that P (real batch | a) is greater than or equal to the confidence of sample detection is found by programming and traversing K ═ 1,2, 3. The significance of the value of K is that if all of the sampled K samples are true orders, then at the sample detection confidence level, the batch order belongs to a true order batch. If an unreal order appears in the K samples, the batch order is considered to belong to an unreal order batch.
In a possible embodiment, on the basis that the sampling inspection model constructed according to the first embodiment determines the preset quantity, after determining the authenticity of the order sample group according to the inspection result of the sampling order, the method further includes:
and updating the probability of the real batch orders, the probability of the false batch orders, the proportion of the false orders in the real batch orders and the proportion of the false orders in the false batch orders according to the authenticity of the order sample group so as to update the sampling detection model.
The sampling detection model is determined according to historical order verification data, so that after the authenticity of the order sample group is determined according to the detection result of the sampling order, the authenticity result of the order sample group also belongs to the historical order verification data, and the authenticity result of the order sample group is used for updating the real batch order probability, the false batch order probability, the proportion of false orders in the real batch orders and the proportion of false orders in the false batch orders of the determination sampling detection model so as to ensure the accuracy and timeliness of the priori knowledge. So as to avoid inaccurate results caused by the change of business conditions of the merchants. For example, a certain merchant submits the loan demand in the last year, the merchant operates in good faith all the time in the operation process, all orders are real orders, false orders do not exist, the system evaluates and judges according to the previous historical orders and the orders to be detected to obtain that the merchant has good operation condition and certain credit, and therefore the merchant is borrowed and credited through the risk evaluation system. In order to further enhance the product competitiveness, the merchant makes false orders and makes lots of false orders to fill, and also puts forward the demand of loan, if the system judges according to the previous data, the result judgment is wrong, and then loan is carried out, so that the risk is higher.
Therefore, the probability of real batch orders, the probability of false batch orders, the proportion of false orders in the real batch orders and the proportion of false orders in the false batch orders are updated according to the authenticity of the order sample group, so that the sampling detection model is updated, and the timeliness and the accuracy of the evaluation information of the merchant are guaranteed.
The embodiment of the invention realizes the determination of the number of the sampling orders from the order sample group based on the construction of the sampling detection model. Therefore, the accuracy of sampling detection of the order sample group is guaranteed while the detection cost of sampling detection of the order sample group is reduced, the accuracy of determining the authenticity of the whole order sample group according to the authenticity of the sampled order is guaranteed under the condition that the preset number of sampling detections is minimum, and the accuracy of determining the loan admission result of a merchant to be detected according to the authenticity of the order sample group is improved.
Fig. 3 is a schematic structural diagram of an order sampling inspection system according to an embodiment of the present invention, and as shown in fig. 3, the order sampling inspection system includes a source data access module, a big data platform processing module, a sampling algorithm solving module, an order verification module, and a wind control flow module. In the source data access module, the obtained e-commerce platform order data of the merchant and the order data of an EPR (electronic public relationship system) are synchronized to a data storage platform in a big data platform processing module, the order source data in the data storage platform are cleaned, target order data are collected, and then the cleaned and collected order sample groups are randomly sampled in batches. And determining the size of the randomly extracted preset number K in each batch according to a preset sampling detection model in a sampling algorithm solving module, wherein the sampling detection model is constructed based on the historical verification record.
Calling logistics list verification services in an order verification module to verify K randomly extracted sampling orders in each batch, marking results after obtaining authenticity verification results, and storing the results into a historical verification record, wherein the historical verification record can be used for determining calculation results of a wind control model in a wind control flow module on one hand so as to determine loan admission results of the merchant; on the other hand, the historical verification records in the sampling algorithm solution can be updated, so that the statistical parameters are updated, and the sampling detection model is updated. When the authenticity result of each sampling order in the batch of orders is determined, if any false order appears, the detection of the batch of orders is finished, namely the batch of orders is determined to be the false batch order; and if the K randomly extracted sample orders in the batch are all real orders, determining that the batch of orders are real batch orders.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an order sampling inspection apparatus according to a third embodiment of the present invention, which is applicable to a case where a part of the order samples is randomly extracted from the order sample group for inspection, and the inspection result of the whole order sample group is determined according to the inspection result of the sample order. As shown in fig. 4, the apparatus includes:
the order obtaining module 310 is configured to obtain an order sample group of the merchant to be detected;
a sample order extracting module 320, configured to randomly extract a preset number of sample orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
the order authenticity determining module 330 is configured to determine authenticity of the order sample group according to a detection result of the sample order.
The method and the device are based on the obtained order sample group of the merchant to be detected; randomly extracting a preset number of sampling orders from the order sample group for detection; and determining the authenticity of the order sample group according to the detection result of the sampling order, wherein the preset quantity value of the sampling order is determined through a sampling detection model, and the sampling detection model is determined based on the historical order of the merchant. Therefore, the accuracy of sampling detection of the order sample group is guaranteed while the detection cost of sampling detection of the order sample group is reduced, the accuracy of determining the authenticity of the whole order sample group according to the authenticity of the sampled order is guaranteed under the condition that the preset number of sampling detections is minimum, and the accuracy of determining the loan admission result of a merchant to be detected according to the authenticity of the order sample group is improved.
Optionally, the apparatus further includes a sampling detection model building module, including:
the historical order acquisition unit is used for acquiring historical order verification data of the merchant;
the history probability determining unit is used for determining the real batch order probability, the false batch order probability, the proportion of false orders in the real batch orders and the proportion of false orders in the false batch orders according to the history order verification data; wherein the sum of the true batch order probability and the false batch order probability is 1;
the preset quantity determining unit is used for determining that the probability that the batch order to be detected is the real batch order is greater than the quantity of the sample orders under the condition of the sampling detection confidence coefficient when a preset event occurs and the quantity is the preset quantity according to the real batch order probability, the false batch order probability, the proportion of the false orders in the real batch order and the proportion of the false orders in the false batch order;
the preset event is that partial sampling orders are randomly extracted from the to-be-detected batch orders, and all the partial sampling orders are real orders.
Optionally, the preset number determining unit is specifically configured to:
based on the traversal algorithm, a preset number in the following formula is determined:
k represents the order quantity of randomly extracting partial sampling orders from the to-be-detected batch orders; p (real lot | A) represents at a preset timeProbability that the batch order to be detected is a real batch order when the piece occurs; a (K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are real batch orders, wherein the K orders are all the probability of occurrence of the real orders, namely
(K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are placed in the false batch orders, wherein the K orders are all the probability of true orders, namely
P1Probability of order for said real batch, P2Probability of order for a false batch, p1Is the proportion of false orders in a real batch order, p2Is the proportion of false orders in false batch orders.
Optionally, the apparatus further comprises a model updating module for determining the authenticity of the order sample group according to the detection result of the sampling order,
and updating the probability of the real batch orders, the probability of the false batch orders, the proportion of the false orders in the real batch orders and the proportion of the false orders in the false batch orders according to the authenticity of the order sample group so as to update the sampling detection model.
Optionally, the order authenticity determining module is specifically configured to:
and if the detection results of the sampling orders are all true, determining that the order sample group is a true order sample group.
Optionally, the apparatus further includes an order dividing module, configured to divide the order sample group according to a preset order quantity in a single batch before randomly extracting a preset number of sample orders from the order sample group for detection, so as to obtain at least two batches of orders;
correspondingly, the sampling order extraction module and the order authenticity determination module are specifically used for:
randomly extracting a preset number of sampling orders from each batch of orders in sequence for detection;
and determining the authenticity of each batch of orders according to the detection result of the sampling orders so as to obtain a real order sample group.
Optionally, the apparatus further includes a wind control result determining module, configured to determine, based on a preset wind control model, a wind control result of the merchant to be detected according to the authenticity result of the order sample group of the merchant to be detected after determining the authenticity of the order sample group according to the detection result of the sample order, so as to determine a loan admission result of the merchant to be detected according to the wind control result.
The order sampling detection device provided by the embodiment of the invention can execute the order sampling detection method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the order sampling detection method.
Example four
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 5, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory device 28, and a bus 18 that couples various system components including the system memory device 28 and the processing unit 16.
The system storage 28 may include computer system readable media in the form of volatile storage, such as Random Access Memory (RAM)30 and/or cache storage 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Storage 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in storage 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system storage device 28, for example, implementing the order sampling detection method provided by the embodiment of the present invention, including:
acquiring an order sample group of a merchant to be detected;
randomly extracting a preset number of sampling orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and determining the authenticity of the order sample group according to the detection result of the sampling order.
EXAMPLE five
The fifth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the order sampling detection method provided in the fifth embodiment of the present invention, and the method includes:
acquiring an order sample group of a merchant to be detected;
randomly extracting a preset number of sampling orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and determining the authenticity of the order sample group according to the detection result of the sampling order.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An order sampling detection method is characterized by comprising the following steps:
acquiring an order sample group of a merchant to be detected;
randomly extracting a preset number of sampling orders from the order sample group for detection; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and determining the authenticity of the order sample group according to the detection result of the sampling order.
2. The method of claim 1, wherein the sampling test model is constructed by:
acquiring historical order verification data of a merchant;
determining the probability of real batch orders, the probability of false batch orders, the proportion of false orders in the real batch orders and the proportion of false orders in the false batch orders according to the historical order verification data; wherein the sum of the true batch order probability and the false batch order probability is 1;
based on the preset order quantity in a single batch and the sampling detection confidence coefficient, determining that the probability that the batch order to be detected is the real batch order is greater than the quantity of the sampling orders under the condition of the sampling detection confidence coefficient when a preset event occurs and the quantity is the preset quantity according to the real batch order probability, the false batch order probability, the proportion of the false orders in the real batch order and the proportion of the false orders in the false batch order;
the preset event is that partial sampling orders are randomly extracted from the to-be-detected batch orders, and all the partial sampling orders are real orders.
3. The method of claim 2, wherein determining that the probability that the batch order to be detected is the real batch order is greater than the number of the sample orders under the condition of the sampling detection confidence coefficient when a preset event occurs is determined to be a preset number according to the real batch order probability, the false batch order probability, the proportion of the false orders in the real batch orders and the proportion of the false orders in the false batch orders based on the preset order quantity in a single batch and the sampling detection confidence coefficient comprises:
based on the traversal algorithm, a preset number in the following formula is determined:
k represents the order quantity of randomly extracting partial sampling orders from the to-be-detected batch orders; p (real batch | A) represents the probability that the batch order to be detected is a real batch order when a preset event occurs; a (K) randomly selecting K orders from the batch orders to be detected when the batch orders to be detected are real batch ordersThe probability that all K orders are true orders, i.e.
(K) randomly extracting K orders from the batch orders to be detected when the batch orders to be detected are placed in the false batch orders, wherein the K orders are all the probability of true orders, namely
P1Probability of order for said real batch, P2Probability of order for a false batch, p1Is the proportion of false orders in a real batch order, p2Is the proportion of false orders in false batch orders.
4. The method of claim 2, further comprising, after determining the authenticity of the sample group of orders based on the inspection of the sample order:
and updating the probability of the real batch orders, the probability of the false batch orders, the proportion of the false orders in the real batch orders and the proportion of the false orders in the false batch orders according to the authenticity of the order sample group so as to update the sampling detection model.
5. The method of claim 1, wherein determining the authenticity of the sample group of orders based on the inspection of the sample order comprises:
and if the detection results of the sampling orders are all true, determining that the order sample group is a true order sample group.
6. The method of claim 1, further comprising, prior to randomly drawing a preset number of sample orders from the group of order samples for inspection:
dividing the order sample group according to a preset order quantity in a single batch to obtain at least two batch orders;
correspondingly, randomly extracting a preset number of sampling orders from the order sample group for detection, and determining the authenticity of the order sample group according to the detection result of the sampling orders, including:
and randomly extracting a preset number of sampling orders from the orders of each batch in sequence for detection, and determining the authenticity of the orders of each batch according to the detection result of the sampling orders so as to obtain a real order sample group.
7. The method of claim 1, further comprising, after determining the authenticity of the sample group of orders based on the inspection of the sample order:
and determining the wind control result of the merchant to be detected according to the authenticity result of the order sample group of the merchant to be detected based on a preset wind control model so as to determine the loan admission result of the merchant to be detected according to the wind control result.
8. An order sampling inspection device, comprising:
the order acquisition module is used for acquiring an order sample group of the merchant to be detected;
the sampling order extraction module is used for randomly extracting a preset number of sampling orders from the order sample group to detect; the preset number is determined by adopting a sampling detection model, and the sampling detection model is determined based on historical orders of merchants;
and the order authenticity determining module is used for determining the authenticity of the order sample group according to the detection result of the sampling order.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the order sampling inspection method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the order sampling inspection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011635336.7A CN112700322B (en) | 2020-12-31 | 2020-12-31 | Order sampling detection method, order sampling detection device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011635336.7A CN112700322B (en) | 2020-12-31 | 2020-12-31 | Order sampling detection method, order sampling detection device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112700322A true CN112700322A (en) | 2021-04-23 |
| CN112700322B CN112700322B (en) | 2023-12-19 |
Family
ID=75513790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011635336.7A Active CN112700322B (en) | 2020-12-31 | 2020-12-31 | Order sampling detection method, order sampling detection device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112700322B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078323A1 (en) * | 2002-10-10 | 2004-04-22 | Household International, Inc. | Quality control for loan processing |
| CN101661596A (en) * | 2009-09-24 | 2010-03-03 | 北京英思沃工业科技有限公司 | Network financing service system |
| US20120005064A1 (en) * | 2008-07-15 | 2012-01-05 | The Bank Of New York Mellon Corporation | Outlier trade detection for financial asset transactions |
| US20140379387A1 (en) * | 2012-03-01 | 2014-12-25 | Su-Cc Corporation Limited | System and method for life cycle operation of supply chain business transaction |
| US20160125533A1 (en) * | 2014-10-30 | 2016-05-05 | Gordian Innovative Technologies, Limited | System and method for simulating a live trading market |
| AU2018274992A1 (en) * | 2017-12-12 | 2019-02-21 | Xiaomin YUAN | Unit trading system |
| CN109767313A (en) * | 2018-12-13 | 2019-05-17 | 平安普惠企业管理有限公司 | Method and Related product based on resource distribution |
| WO2020119272A1 (en) * | 2018-12-13 | 2020-06-18 | 阿里巴巴集团控股有限公司 | Risk identification model training method and apparatus, and server |
-
2020
- 2020-12-31 CN CN202011635336.7A patent/CN112700322B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078323A1 (en) * | 2002-10-10 | 2004-04-22 | Household International, Inc. | Quality control for loan processing |
| US20120005064A1 (en) * | 2008-07-15 | 2012-01-05 | The Bank Of New York Mellon Corporation | Outlier trade detection for financial asset transactions |
| CN101661596A (en) * | 2009-09-24 | 2010-03-03 | 北京英思沃工业科技有限公司 | Network financing service system |
| US20140379387A1 (en) * | 2012-03-01 | 2014-12-25 | Su-Cc Corporation Limited | System and method for life cycle operation of supply chain business transaction |
| US20160125533A1 (en) * | 2014-10-30 | 2016-05-05 | Gordian Innovative Technologies, Limited | System and method for simulating a live trading market |
| AU2018274992A1 (en) * | 2017-12-12 | 2019-02-21 | Xiaomin YUAN | Unit trading system |
| CN109767313A (en) * | 2018-12-13 | 2019-05-17 | 平安普惠企业管理有限公司 | Method and Related product based on resource distribution |
| WO2020119272A1 (en) * | 2018-12-13 | 2020-06-18 | 阿里巴巴集团控股有限公司 | Risk identification model training method and apparatus, and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112700322B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242261B (en) | Method for evaluating security risk based on big data and terminal equipment | |
| WO2021254027A1 (en) | Method and apparatus for identifying suspicious community, and storage medium and computer device | |
| CN109637000B (en) | Invoice detection method and device, storage medium and electronic terminal | |
| CN111612040B (en) | Financial data anomaly detection method and related device based on isolated forest algorithm | |
| CN111144697A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN111125266A (en) | Data processing method, device, equipment and storage medium | |
| CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
| CN113034046A (en) | Data risk metering method and device, electronic equipment and storage medium | |
| CN111046184A (en) | Text risk identification method, device, server and storage medium | |
| CN112184304A (en) | Method, system, server and storage medium for assisting decision | |
| CN111914729A (en) | Voucher association method and device, computer equipment and storage medium | |
| CN112184003A (en) | Bank counter workload assessment method and device, storage medium and electronic equipment | |
| CN111738290B (en) | Image detection method, model construction and training method, device, equipment and medium | |
| CN111861757A (en) | Financing matching method, system, equipment and storage medium | |
| CN109829769B (en) | Electronic invoice duplicate checking method and system | |
| CN111680083A (en) | Intelligent multi-stage government financial data acquisition system and data acquisition method | |
| CN111681050A (en) | Advertisement pushing method, device, equipment and storage medium | |
| CN112700322B (en) | Order sampling detection method, order sampling detection device, electronic equipment and storage medium | |
| CN110766547A (en) | Method, device, equipment and storage medium for determining credibility grade | |
| CN111242779A (en) | Financial data characteristic selection and prediction method, device, equipment and storage medium | |
| CN116245630A (en) | Anti-fraud detection method and device, electronic equipment and medium | |
| CN115033650A (en) | Data processing method and device based on relational data | |
| CN111489101A (en) | Order auditing method, device, equipment and medium based on big data | |
| CN111506615A (en) | Method and device for determining occupation degree of invalid user | |
| JP2010079555A (en) | Credit determination system and document falsification determination method |
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 |