A risk control method and related device for service orders

Abstract

The present application provides a risk management method and related devices for service orders, which can be applied to the field of data verification. In the technical solution of the present application, the historical service order data is first obtained, and then the association rule algorithm is used to obtain the relationship between the item sets in the historical service order data, and the association confidence between the item sets in the historical service order data is calculated. The pending service orders are monitored by the association confidence to determine whether the pending service orders have a risk of fraud. The technical solution of the present application can quickly screen out service orders that have a risk of fraud, which is conducive to the rapid implementation of service orders.

Description

Technical Field

[0001] The present application relates to the field of data verification, and in particular to a risk management method and related device for a service order. Background Art

[0002] Providing users with the required door-to-door services based on their service orders has been widely used. However, this type of door-to-door service has certain risks. For example, some service providers may pay people to perform some fake order behaviors on the service platform in order to obtain better service sales and evaluations. Therefore, it is necessary to supervise the service orders to ensure their implementation.

[0003] At present, the method for supervising service orders is as follows: first, based on the real-time uploaded photos, the actual service start time, service personnel, service objects, service locations and other service information are compared with the corresponding preset information respectively. When these service information and the corresponding preset information all match, the service is started; after the service is completed, the service end time is compared with the pre-set service end information, so as to realize the monitoring of service orders.

[0004] However, due to the large variety of service orders and the large number of service objects, this method requires comparing the service information involved in each service order with the pre-set information one by one, which is labor-intensive and cumbersome, resulting in a long time spent on screening risky orders, thus affecting the risk management efficiency of service orders. Summary of the invention

[0005] The present application provides a service order risk management method and related devices to solve the problem of low efficiency of service order risk management in the prior art.

[0006] In a first aspect, the present application provides a risk management method for a service order, including: a service order management device receives first information, wherein the first information is used to indicate a service object, a service type, a service item, a service time, a service fee, and service personnel information of a service provided to the service object; the service order management device generates service order data based on the first information; the service order management device sends the service order data to a service order monitoring device, and the service order monitoring device is used to monitor whether the service order data has a risk of fraud.

[0007] In this method, the service order management device can obtain a complete record of the service order by receiving the first information and generating service order data from the first information. Based on the complete record, the entire service process can be supervised, controlled and evaluated.

[0008] In combination with the method of the first aspect, the method further includes: the service order management device sends the service order to a first terminal device indicated by the service personnel information, and the first terminal device is used to display the information in the service order to the service personnel.

[0009] By sending the service order to the first terminal device, the service dispatch process can be completed, so that the service personnel can confirm the service object and the service type required by the service object according to the information in the service order, thereby completing the corresponding service task.

[0010] In combination with the method of the first aspect, the method further includes: the service order management device sends the service order and service verification code to a second terminal device, and the second terminal device is used to display the information in the service order and the service verification code to the service object.

[0011] By sending the service order to the second terminal device, the service recipient can confirm whether the order is correct based on the service order information. By sending the service verification code to the second terminal device, the service recipient can provide the service verification code to the service personnel, and then confirm whether the order service is valid based on the service verification code.

[0012] In addition, the method also includes: the service order management device receives the pending service verification code sent by the first terminal device for the service order; the service order management device verifies the pending service verification code based on the service verification code; the service order management device sends the verification result of the pending verification code to the first terminal device.

[0013] The pending service verification code is the service verification code provided by the service object to the service personnel. The first terminal inputs the pending service verification code and sends it to the service order management device. The service order management device verifies the service verification code and the pending service verification code. Only when the verification is successful, the service personnel starts to perform the service task.

[0014] In a second aspect, the present application provides a risk management method for a service order, comprising: obtaining a plurality of historical service order data, the plurality of historical service order data corresponding one-to-one to a plurality of services, each of the plurality of historical service order data including the value of each service feature of a plurality of service features of a corresponding service in the plurality of services; obtaining S items from the plurality of historical service order data, the S items corresponding one-to-one to S types of service feature values ​​in a service, each of the S items being used to represent a corresponding service feature value in the S types of service feature values, and S being a positive integer greater than 1; determining an association confidence between a first frequent item set and a second frequent item set based on the plurality of historical service order data, the association confidence being used to monitor whether there is a risk of fraud in the service order data to be processed, the first frequent item set including M items from the S items, the second frequent item set including N items from the S items, M and N being positive integers less than or equal to S, and the first frequent item set being different from the second frequent item set.

[0015] In the method, the multiple service features include one or more of the following service features: service object, service type of the service provided corresponding to the service, service item, service time, service fee and service personnel information.

[0016] In this method, multiple historical service order data are obtained, and the relationship between each item set in the multiple historical service order data is found according to the multiple historical service order data, so as to form an association rule and obtain the association confidence between each item set. According to the association confidence, the service order data to be processed can be monitored and it can be determined whether the service order data to be processed has a risk of fraud.

[0017] In a third aspect, the present application provides a risk management method for a service order, comprising: a service order monitoring device obtains service order data to be monitored, the service order data to be monitored including the value of each service feature of multiple service features of the service to be monitored; the service order monitoring device obtains the correlation between a first item set and a second item set in the service order data to be monitored; the service order monitoring device determines whether the service order data to be monitored has a risk of fraud based on a target association confidence and the correlation, wherein the target association confidence includes an association confidence determined using the method of the second aspect, the first item set is the same as the first frequent item set, and the second item set is the same as the second frequent item set.

[0018] In this method, a minimum correlation confidence and a preset value can be set in advance. When the correlation in the service order data to be monitored is greater than or equal to the minimum correlation confidence, the relationship between the difference between the correlation and the target correlation confidence and the preset value is judged. If the difference between the correlation and the target correlation confidence is greater than or equal to the preset value, it is determined that the service order data to be monitored has a risk of falsification.

[0019] In a fourth aspect, the present application provides a risk management device for a service order, including: the device may include various functional modules for implementing the method in the first aspect. Any functional module may be implemented in software and / or hardware. For example, the device may include a receiving module, a generating module, and a sending module.

[0020] The receiving module is used for the service order management device to receive first information, where the first information is used to indicate the service object, the service type, service items, service time, service fees and service personnel information of the service provided to the service object.

[0021] The generating module is used by the service order management device to generate service order data according to the first information.

[0022] The sending module is used for the service order management device to send the service order data to the service order monitoring device, and the service order monitoring device is used to monitor whether there is a risk of fraud in the service order data.

[0023] In a fifth aspect, the present application provides a risk management device for a service order, which may include various functional modules for implementing the method in the second aspect. Any functional module may be implemented in software and / or hardware. For example, the device may include an acquisition module and a determination module.

[0024] The acquisition module is used to acquire multiple historical service order data, which correspond one-to-one to multiple services. Each historical service order data in the multiple historical service order data includes the value of each service feature in multiple service features corresponding to the multiple services.

[0025] The acquisition module is also used to obtain S items, the S items corresponding one-to-one to S service characteristic values ​​in the service, each of the S items is used to represent a corresponding service characteristic value in the S service characteristic values, and S is a positive integer greater than 1.

[0026] A determination module is used to determine the association confidence between the first frequent itemset and the second frequent itemset according to the plurality of historical service order data.

[0027] In a sixth aspect, the present application provides a risk management device for a service order, which may include various functional modules for implementing the method in the third aspect. Any functional module may be implemented in software and / or hardware. For example, the device may include an acquisition module and a judgment module.

[0028] The acquisition module is used by the service order monitoring device to acquire the service order data to be monitored, and the service order data to be monitored includes the value of each service feature of multiple service features of the service to be monitored.

[0029] The acquisition module is also used by the service order monitoring device to acquire the correlation between the first item set and the second item set in the service order data to be monitored.

[0030] The judgment module is used by the service order monitoring device to judge whether the service order data to be monitored has a risk of fraud based on the target association confidence and the association degree.

[0031] In a seventh aspect, the present application provides a risk management device for a service order, which may include various functional modules for implementing the methods in the first aspect, the second aspect, and the third aspect. For example, the device may include a memory and a processor coupled to the memory.

[0032] The processor is used to execute program instructions to implement the instructions executed by the methods in the first aspect, the second aspect and the third aspect; the memory is used to store the instructions executed by the processor or the input data required for the processor to run the instructions or the data generated after the processor runs the instructions.

[0033] In an eighth aspect, the present application provides a computer-readable storage medium storing a program code for execution by a processor, wherein the program code includes instructions for implementing the methods in the first aspect, the second aspect, and the third aspect.

[0034] In a ninth aspect, the present application provides a computer program product, which, when executed on a processor, enables a risk management device for a service order to implement the methods in the first, second and third aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] Figure 1 A schematic diagram of the architecture of a service order management system applicable to an embodiment of the present application;

[0037] Figure 2 A flow chart of a risk management method for a service order provided in one embodiment of the present application;

[0038] Figure 3 A schematic flow chart of a method for obtaining association confidences between item sets in a plurality of historical service order data by using an association rule algorithm provided in one embodiment of the present application;

[0039] Figure 4 A schematic diagram of using the Apriori algorithm to obtain the association confidence between a first frequent item set and a second frequent item set in multiple historical service order data provided by an embodiment of the present application;

[0040] Figure 5 A flowchart of a method for determining service order data to be processed provided in one embodiment of the present application;

[0041] Figure 6 A schematic diagram of the structure of a risk management and control device for a service order provided in one embodiment of the present application;

[0042] Figure 7 A schematic diagram of the structure of a risk management and control device for a service order provided in another embodiment of the present application;

[0043] Figure 8 A schematic diagram of the structure of a risk control device for a service order of a service provided by another embodiment of the present application;

[0044] Fig. 9 A schematic diagram of the structure of a risk management device for a service order of a service provided in yet another embodiment of the present application.

[0045] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0047] First, the terms involved in this application are explained:

[0048] Home service: refers to the service personnel providing some services to users according to the service orders of users, so that users can enjoy these services without going out or traveling far. It can be understood that users here can include users of all ages, and home services can include food delivery services, taxi services, and home-based elderly care services.

[0049] Home-based elderly care services: refers to the government and social forces relying on the community to provide a variety of door-to-door services such as life care, housekeeping services, rehabilitation care and spiritual comfort for the elderly at home.

[0050] Association rules: They reflect the interdependence and correlation between one thing and other things. They are an important technology in data mining and are used to mine the correlation between valuable data items from large amounts of data.

[0051] Association rules include two subtasks: frequent pattern discovery and association rule generation. Frequent pattern discovery is also called frequent pattern mining, frequent item mining, etc. It refers to selecting frequent items from a series of candidate items. The degree of frequency can usually be measured by the frequency of occurrence of each item. When it exceeds a certain threshold, the task item is frequent. Generating association rules means finding association rules whose confidence is not less than the minimum confidence given by the user in the largest frequent item set that has been discovered.

[0052] Classic association rule algorithms include association rule mining (Apriori) algorithm and frequent pattern tree (FP-growth) algorithm.

[0053] The basic idea of ​​the Apriori algorithm is: first, through iteration, retrieve all frequent item sets in the transaction database, that is, item sets whose support is not less than the threshold set by the user; second, use the frequent item sets to construct rules that meet the user's minimum trust. Among them, mining or identifying all frequent item sets is the core part of the algorithm. The algorithm is simple and easy to implement, and the algorithm has good scalability and can be used in fields such as parallel computing.

[0054] The FP-growth algorithm stores the data set in a specific structure called a frequent pattern (FP) tree and then discovers frequent item sets or frequent item pairs, that is, a set of element items that often appear together. This algorithm is more efficient than the Apriori algorithm. During the entire algorithm execution process, it only needs to traverse the data set twice to complete the frequent pattern discovery. The basic process of discovering frequent item sets includes: building an FP tree and mining frequent item sets from the FP tree.

[0055] Support represents the probability of a certain item set appearing in a data set, where an item set represents any combination of data items, so an item set can include one data item or multiple data items. For example, if the item set is item set A, and item set A includes data item a, then the probability of item set A appearing is the probability of data item a occurring. For another example, if the item set is item set B, and item set B includes data item b and data item c, then the probability of item set B appearing is the probability of data item b and data item c occurring at the same time. The minimum support is a threshold artificially defined according to practical significance, indicating the lowest importance of an item set in a statistical sense.

[0056] Confidence indicates the probability that the second item set will also appear when the first item set appears. For example, when the first item set is item set A and the second item set is item set B, where item set A includes data item a and item set B includes data item b and data item c, then the confidence at this time indicates the probability that item set B will also appear when item set A appears, that is, the probability that data item b and data item c will occur at the same time when data item a occurs. The minimum confidence is also a threshold artificially defined according to practical significance, indicating the minimum reliability of the association relationship.

[0057] Frequent itemsets: refers to the itemsets, sequences or substructures that appear frequently in the data set. Frequent itemsets refer to the itemsets whose support is greater than or equal to the minimum support.

[0058] At present, the methods for supervising service orders include: first, comparing the actual service start time, service personnel, service objects, and service locations and other service information with the corresponding preset information based on the photos uploaded by the service personnel in real time, and starting the service when all these service information match the corresponding preset information; after the service is completed, the service end time and service object satisfaction are compared with the pre-set service end information, so that the quality of the service personnel's door-to-door service can be strictly monitored. However, due to the large number of service order types and service objects, this method requires that the service information involved in each service order be compared with the pre-set information one by one, which is a large workload and relatively cumbersome, resulting in a long time for troubleshooting risky orders. Therefore, how to improve the risk management efficiency of service orders is a technical problem that needs to be solved in this application.

[0059] Figure 1 This is a schematic diagram of a service order management system architecture applicable to the embodiment of this application. Figure 1 As shown, the service order management system includes multiple devices, which may include a service order management device, a first terminal device, a second terminal device and a service order supervision device. The service order management device can communicate with the first terminal device, the second terminal device and the service order supervision device.

[0060] The service order management device can be used to receive information and generate service order data based on the information, and the information is used to indicate the service object, the service type, service item, service time, service fee and service personnel information of the service provided to the service object. The service order management device can also send a service order to the first terminal device, send a service order and a service verification code to the second terminal device, and send service order data to the service order monitoring device. In addition, the service order management device can also receive a pending service verification code sent by the first terminal device for the service order, and verify the verification code.

[0061] The first terminal device may include at least one service personnel terminal device, which may receive a service order from the service order management device and display the service order to the service personnel, so that the service personnel may perform the corresponding service task according to the service order. In addition, the service personnel may also send the input verification code to the service order management device through the service personnel terminal device, thereby completing the verification process. It is understandable that each service personnel may correspond to at least one service personnel terminal device.

[0062] The second terminal device may include at least one service object terminal device, which may receive a service order and a service verification code from the service order management device, and display the service order and service verification code to the service object, so that the service object may confirm whether the order information is correct, and provide the service verification code to the service personnel. It is understandable that each service object may correspond to at least one service object terminal device.

[0063] The service order monitoring device is used to obtain the service order data to be monitored and the correlation between each data item set in the service order data to be monitored, and determine whether the service order data to be monitored has a risk of fraud. Optionally, the service order monitoring device can also obtain historical service order data, and determine the correlation confidence between the first frequent item set and the second frequent item set based on the historical service order data.

[0064] It is understood that the first terminal device and the second terminal device may be wireless terminals, and the wireless terminal may be a device that provides voice and / or other business data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. The wireless terminal may be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal. Alternatively, the wireless terminal device may also be a smart watch, a tablet computer, or other devices.

[0065] This application will be explained later using home-based elderly care services as an example.

[0066] Figure 2A flow chart of a risk management method for a service order provided in one embodiment of the present application is as follows: Figure 2 As shown, the risk management method of the service order includes steps 201, 202 and 203. The method can be performed by Figure 1 The service order management device in the system shown is executed.

[0067] Step 201, receiving first information, where the first information is used to indicate a service object, a service type, service items, service time, service fees, and service personnel information of a service provided to the service object.

[0068] In this embodiment, the service may be any one of door-to-door services such as home-based elderly care services, taxi services, and food delivery services.

[0069] Taking home-based elderly care services as an example, the service type of home-based elderly care services can be any one of multiple types such as meal assistance, bathing assistance, cleaning assistance, emergency assistance, medical assistance, and nursing. Each of these multiple service types can include at least one specific item. For example, when the service type is meal assistance, the service type can include two items: whether to add meals, so the service item can be any type of multiple specific items included in the multiple service types. The service time indicates the specific time to perform the home-based elderly care service. The service fee indicates that the service recipient needs to pay the fee for the home-based elderly care service. The service personnel information includes information about the service personnel who perform the home-based elderly care service and the service personnel equipment corresponding to the service personnel.

[0070] In one possible implementation method, the service recipient can order home-based elderly care services by calling a home-based elderly care service order manager. The service order manager inputs the service recipient's information and the service recipient's instruction information into a home-based elderly care service order management device through the service recipient's instruction information. The home-based elderly care service order management device receives the service recipient's information and the service recipient's instruction information.

[0071] Among them, the indication information of the service object is used to indicate the service information of the home-based elderly care service required by the service object. The indication information of the service object may include various information such as the service type, service items, service time, service fee and service personnel information required by the service object.

[0072] In another possible implementation method, the service object can select the first information through the service object terminal device, and send the first information to the home-based elderly care service order management device through the service object terminal device, and the home-based elderly care service order management device receives the first information.

[0073] In this embodiment, after the home-based elderly care service order management device receives the first information, it can send the home-based elderly care service order to the first terminal device indicated by the service personnel information in the first information, and the first terminal device is used to display the information in the home-based elderly care service order to the service personnel.

[0074] The first terminal device indicated by the service personnel information may be a service personnel terminal device used by the service personnel who perform the home-based elderly care service.

[0075] In this embodiment, after receiving the first information, the home-based elderly care service order management device can also send the home-based elderly care service order and the service verification code to the second terminal device indicated by the service object information according to the service object information in the first information. The second terminal device is used to display the information in the home-based elderly care service order and the service verification code to the service object.

[0076] The second terminal device indicated by the service object information may be a service object terminal device used by the service object initiating the home-based elderly care service.

[0077] The verification code is used to confirm whether the home-based elderly care service is valid. The specific method includes: the service object can provide the service personnel with a pending service verification code, the service personnel inputs the pending service verification code into the service personnel terminal device, and the service personnel terminal device can send the pending service verification code to the home-based elderly care service order management device. When the home-based elderly care service order management device receives the pending service verification code, it verifies the pending service verification code based on the service verification code. If the pending service verification code is consistent with the service verification code, the verification is successful; if the pending service verification code is inconsistent with the service verification code, the verification fails. After the home-based elderly care service order management device verifies the pending service verification code, it sends the verification result of the pending verification code to the first terminal device. When the first terminal device displays that the verification result is successful, the service personnel begins to provide corresponding services to the service object.

[0078] Step 202: Generate service order data according to the first information.

[0079] When the service order is executed, the first information corresponding to the service order is generated into service order data.

[0080] Generating service order data according to the first information means generating the service order data corresponding to the first information according to the service object indicated by the first information and the service type, service items, service time, service fees and service personnel information of the service provided for the service object.

[0081] Step 203: Send the service order data to a service order monitoring device, which is used to monitor whether the service order data has a risk of fraud.

[0082] The method for a service order monitoring device to monitor whether service order data has a risk of fraud includes: obtaining multiple historical service order data, using an association rule algorithm to obtain the association confidence between each item set in the multiple historical service order data; and judging whether the service order data to be processed has a risk of fraud based on the association confidence.

[0083] Figure 3 A flow chart of a method for obtaining association confidences between item sets in multiple historical service order data using an association rule algorithm provided in one embodiment of the present application. Figure 3 As shown, the method includes: step 301, step 302 and step 303. The method can be Figure 1 Service order monitoring equipment execution in the system shown.

[0084] Step 301, obtaining a plurality of historical service order data, wherein the plurality of historical service order data correspond one to one with the plurality of services, and each of the plurality of historical service order data comprises a value of each service feature of a plurality of service features corresponding to the plurality of services.

[0085] In this embodiment, the service order management device sends service order data to the service order monitoring device. Each time the service order monitoring device receives a piece of service order data, it records the service order data or stores the service order data in a database. Therefore, obtaining historical service order data refers to calling the historical service order data recorded by the service order monitoring device or calling the historical service order data from the database.

[0086] Step 302, obtaining S items from multiple historical service order data, the S items corresponding one-to-one to S types of service feature values ​​in the service, each of the S items is used to represent a corresponding service feature value in the S types of service feature values, and S is a positive integer greater than 1.

[0087] An implementation method for obtaining S items from a plurality of historical service order data includes: setting a data processing standard, and converting the S items from the plurality of historical service order data into standard service feature values ​​according to the processing standard.

[0088] Step 303: determining the association confidence between the first frequent itemset and the second frequent itemset according to the plurality of historical service order data, wherein the association confidence is used to monitor whether the service order data to be processed has a fraud risk.

[0089] In this embodiment, the first frequent itemset includes M items out of S items, the second frequent itemset includes N items out of S items, M and N are positive integers less than or equal to S, and the first frequent itemset is different from the second frequent itemset.

[0090] In this method, the multiple service characteristics include one or more of the following service characteristics: service object, service type of the service provided corresponding to the service, service item, service time, service fee and service personnel information.

[0091] It can be understood that the multiple historical service order data can be used as a data set, and the S items in the multiple historical service order data represent the S item sets contained in the data set composed of the multiple historical service order data. When the item set includes a service feature, the item set that meets the minimum support in the item set is called the first frequent item set; when the item set includes multiple service features, the item set that meets the minimum support in the item set is called the second frequent item set.

[0092] It is understandable that this method constructs the association confidence between the first frequent itemset and the second frequent itemset based on the Apriori algorithm, and can also construct rules based on other association rule algorithms. This application does not impose any limitation on the type of association rule algorithms.

[0093] Figure 4 A schematic diagram of using the Apriori algorithm to obtain the association confidence between a first frequent item set and a second frequent item set in multiple historical service order data is provided in one embodiment of the present application. Figure 4 As shown in (1), it is assumed that there are five historical service order data, and these five historical service order data correspond to five services one by one. Each of the five historical service order data includes three service features. It is assumed that the three service features are: order time, order additional meal status and service personnel. Then each of the five historical service order data includes the value of each service feature corresponding to the three service features.

[0094] In order to facilitate the association of service features in historical service order data, the service feature values ​​in the historical service order data are first standardized. Here, orders with an order duration of no more than one hour are set to a, orders with an order duration of more than one hour are set to b, orders with additional meals are set to c, orders with service personnel Xiao Wang are set to e, and orders with service personnel Xiao Li are set to f. The historical service order data can be converted from (1) to (2). Based on the standardized data in (2), multiple item sets corresponding to the historical service order data can be obtained. Each item set in the multiple item sets has a corresponding service feature value, and the service features in each item set can contain one or more service features.

[0095] In this embodiment, the candidate item set C1 can be obtained according to the types of service features in (2). As shown in (3), the candidate item set C1 can include five candidate item sets {a}, {b}, {c}, {e} and {f}. Each candidate item set in the candidate item set C1 includes a feature value. Then, according to the number of times each candidate item set appears in the historical service orders, the support of each candidate item set in the five candidate item sets is calculated. For example, in the historical service orders, a appears 3 times, and there are 5 services in the historical services, so the support of the candidate item set {a} is: 3 / 5=0.6. Similarly, the support of each candidate item set in the candidate item set C1 can be obtained.

[0096] Select the candidate item set with support greater than the minimum support from the candidate item set C1 as the frequent item set L1, and the frequent item set L1 and the support of the frequent item set L1 can be obtained. The obtained frequent item set L1 is shown in (4). It can be understood that the number of item sets L1 in the frequent item set is less than or equal to the number of candidate item sets C1, and the minimum support is pre-set, which is set to 0.2 here.

[0097] Then, the candidate item set C2 can be obtained from the frequent item set L1. As shown in (5), the candidate item set C2 may include multiple candidate item sets such as {a, b}, {a, c}, {a, e}, ..., {e, f}, and each candidate item set in the candidate item set C2 includes two eigenvalues. Then, according to the number of times each candidate item set appears in the historical service orders, the support of each candidate item set in the multiple candidate item sets is calculated. For example, in the historical service orders, the number of times a and b appear at the same time is 0, and there are 5 services in the historical services, so the support of the candidate item set {a, b} is 0. For another example, in the historical service orders, the number of times a and c appear at the same time is 2 times, and there are 5 services in the historical services, so the support of the candidate item set {a, c} is 2 / 5=0.4. Similarly, the support of each candidate item set in the candidate item set C2 can be obtained.

[0098] Select the candidate item set with support greater than the minimum support from the candidate item set C2 as the frequent item set L2, and you can get the frequent item set L2 and the support of the frequent item set L2. The obtained frequent item set L2 is shown in (6). It can be understood that the number of item sets L2 in the frequent item set is less than or equal to the number of candidate item sets C2.

[0099] Then, the candidate item set C3 can be obtained from the frequent item set L2. As shown in (7), the candidate item set C3 can include multiple candidate item sets such as {a, c, e}, {b, c, e}, {b, c, f} and {b, e, f}. Each candidate item set in the candidate item set C3 includes three eigenvalues. Then, according to the number of times each candidate item set appears in the historical service orders, the support of each candidate item set in the multiple candidate item sets is calculated. For example, in the historical service orders, the number of times a, c and e appear at the same time is 2 times, and there are 5 services in the historical services, so the support of the candidate item set {a, c, e} is 2 / 5=0.4. For another example, in the historical service orders, the number of times b, c and e appear at the same time is 1 time, and there are 5 services in the historical services, so the support of the candidate item set {b, c, e} is 1 / 5=0.2. Similarly, the support of each candidate item set in the candidate item set C3 can be obtained.

[0100] Select the candidate item set with support greater than the minimum support from the candidate item set C3 as the frequent item set L3, and the frequent item set L3 and the support of the frequent item set L3 can be obtained. The obtained frequent item set L3 is shown in (8). It can be understood that the number of item sets L3 in the frequent item set is less than or equal to the number of candidate item sets C3.

[0101] Finally, the frequent item sets are associated with each other, and the association confidence between the frequent item sets is calculated. In this embodiment, the method for associating the frequent item sets and the calculated association confidence are shown in (9). For example, the association between the item set {a} and the item set {c} can be recorded as {a}→{c}, where {a}→{c} means that the item set {c} occurs when the item set {a} occurs, and the association confidence of {a}→{c} refers to the probability of the item set {c} occurring when the item set {a} occurs.

[0102] Methods for calculating the association confidence of {a}→{c} may include the following two methods. In the first possible implementation method, the number of times that item set {a} and item set {c} occur simultaneously is divided by the number of times item set {a} occurs. In this embodiment, the number of times item set {a} and item set {c} occur simultaneously is 2 times, and the number of times item set {a} occurs is 3 times, and the association confidence of {a}→{c} is 2 / 3≈66.7%.

[0103] In a second possible implementation method, the support of the item set {a, c} is divided by the support of the item set {a}. In this embodiment, the support of the item set {a, c} is 0.4, and the support of the item set {a} is 0.6, and the obtained association confidence of {a}→{c} is 0.4 / 0.6≈66.7%.

[0104] It can be understood that the first candidate item set is an item set containing a service feature, and the first frequent item set is the first candidate item set that satisfies the support. Therefore, the candidate item set C1 is the first candidate item set, and the frequent item set L1 is the first frequent item set.

[0105] It can be understood that the second candidate item set is an item set containing multiple service features, and the second frequent item set is a second candidate item set that satisfies the support. Therefore, candidate item set C2 and candidate item set C3 are the second candidate item sets, and frequent item set L2 and frequent item set L3 are the second frequent item sets.

[0106] Figure 5 A flow chart of a method for determining service order data to be processed provided in one embodiment of the present application. Figure 5 As shown, the method includes steps 501, 502 and 503. The method can be Figure 1 Service order monitoring equipment execution in the system shown.

[0107] Step 501: Acquire order data of a service to be monitored, where the order data of the service to be monitored includes a value of each service feature of a plurality of service features of the service to be monitored.

[0108] In this method, the method of obtaining the service order data to be monitored is the same as the method of obtaining the historical service order data in step 301, so it will not be repeated here.

[0109] Step 502: Obtain the correlation between the first item set and the second item set in the service order data to be monitored.

[0110] The first item set is the same as the first frequent item set in step 303, and the second item set is the same as the second frequent item set in step 303. The association degree between the first item set and the second item set refers to the probability of the second item set occurring when the first item set occurs, which is consistent with the method of calculating the association confidence of frequent item sets described above, so it will not be repeated.

[0111] Step 503: determine whether the service order data to be monitored has a risk of fraud based on the target association confidence and the association.

[0112] In this embodiment, the target association confidence includes the association confidence determined in step 303 .

[0113] The method for judging whether the service order data to be monitored has a risk of fraud based on the target association confidence and the association may include: setting a minimum confidence and a preset value based on the target association confidence, the minimum confidence is used to represent the minimum reliability of association between each item set; if the correlation between the first item set and the second item set in the service order data to be monitored is lower than the minimum confidence, then directly determining that the service order data to be monitored has a risk of fraud; if the correlation between the first item set and the second item set in the service order data to be monitored is higher than the minimum confidence, then judging the difference between the correlation and the target association confidence; if the difference between the correlation and the target association confidence is greater than or equal to the preset value, determining that the service order data to be monitored has a risk of fraud.

[0114] If the service order data to be monitored has a risk of falsification, the service order monitoring device will check the service order and call the data of the service order to determine its authenticity.

[0115] In the technical solution proposed in this application, historical service order data is first obtained, and then the association relationship between the item sets in the historical service order data is constructed by using the association rule algorithm to form an association rule, and then the association confidence of the association rule is calculated. According to the association confidence, the service order can be checked to determine whether the service order has a risk of fraud. Only when the service order has a risk of fraud, the data of the service order is called for authenticity determination. In this method, there is no need to compare the service information involved in each service order with the pre-set information one by one, and false orders and risky orders can be quickly screened out, thereby improving the risk management efficiency of service orders, thereby ensuring the implementation of service order services.

[0116] Figure 6 A schematic diagram of the structure of a risk control device for a service order provided by an embodiment of the present application. Figure 6 As shown, the risk management and control device 600 for the service order includes a receiving module 601 , a generating module 602 and a sending module 603 .

[0117] The risk control device 600 for service orders can be used to implement Figure 2 The schematic diagram of the risk control method flow of the service order of the embodiment shown in FIG. 6 shows that the receiving module 601 can be used to execute the step S201, the generating module 602 can be used to execute the step S202, and the sending module 603 can be used to execute the step S203.

[0118] Figure 7 This is a schematic diagram of the structure of a risk control device for a service order provided by another embodiment of the present application. Figure 7 As shown, the risk management and control device 700 for the service order includes an acquisition module 701 and a determination module 702 .

[0119] The risk control device 700 of the service order can be used to implement Figure 3 The schematic diagram of the risk control method flow of the service order of the embodiment shown in FIG. 7 shows that the acquisition module 701 can be used to execute the step S301, the acquisition module 701 can also be used to execute the step S302, and the determination module 702 can be used to execute the step S303.

[0120] Figure 8 This is a schematic diagram of the structure of a risk control device for a service order provided by another embodiment of the present application. Figure 8 As shown, the risk management and control device 800 for the service order includes an acquisition module 801 and a judgment module 802 .

[0121] The risk control device 800 of the service order can be used to implement Figure 5 The schematic diagram of the risk control method flow of the service order of the embodiment shown in FIG. 8 shows that the acquisition module 801 can be used to execute the step S501, the acquisition module 801 can also be used to execute the step S502, and the judgment module 802 can be used to execute the step S503.

[0122] Fig. 9 This is a schematic diagram of the structure of a risk control device for a service order provided by another embodiment of the present application. Fig. 9 As shown, the risk control device 900 of the service order includes: a processor 901 and an interface circuit 902. The processor 901 and the interface circuit 902 are coupled to each other. It can be understood that the interface circuit 902 can be a transceiver or an input-output interface. Optionally, the service information reminder device 900 can also include a memory 903 for storing instructions executed by the processor 901 or storing input data required by the processor 901 to run the instructions or storing data generated after the processor 901 runs the instructions.

[0123] As an example, the processor 901 may be used to implement the functions of the above-mentioned generating module 602 , and the interface circuit 902 may be used to implement the functions of the above-mentioned receiving module 601 and sending module 603 .

[0124] As another example, the processor 901 may be used to implement the function of the above-mentioned determination module 702 , and the interface circuit 902 may be used to implement the function of the above-mentioned acquisition module 701 .

[0125] As another example, the processor 901 may be used to implement the function of the above-mentioned determination module 802 , and the interface circuit 902 may be used to implement the function of the above-mentioned acquisition module 801 .

[0126] It is understood that the processor in the embodiments of the present application may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0127] The method steps in the embodiments of the present application can be implemented by hardware, or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, register, hard disk, mobile hard disk, read-only compact disk (CD-ROM) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuit, ASIC). In addition, the application specific integrated circuit can be located in a network device or a terminal device. Of course, the processor and the storage medium can also be present in a network device or a terminal device as discrete components.

[0128] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, a tape; it may also be an optical medium, for example, a digital video disc; it may also be a semiconductor medium, for example, a solid-state hard disk.

[0129] In each embodiment of the present application, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships. The term "multiple" in this article refers to two or more. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and next associated objects are in an "or" relationship; in a formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship.

[0130] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0131] It is to be understood that, in the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the order of execution of each process should be determined by its function and inherent logic, and the implementation process of the embodiments of the present application should not be limited in any way. Those skilled in the art will easily think of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptive change of the present application, which follows the general principles of the present application and includes the common knowledge or customary technical means in the art that are not disclosed in the present application. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present application are indicated by the following claims.

[0132] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A risk management method for a service order, characterized in that: include: The service order management device receives first information, where the first information is used to indicate a service object, a service type, a service item, a service time, a service fee, and service personnel information of a service provided to the service object; The service order management device sends the service order to the first terminal device indicated by the service personnel information, and the first terminal device is used to display the information in the service order to the service personnel; The service order management device sends the service order and service verification code to the second terminal device, and the second terminal device is used to display the information in the service order and the service verification code to the service object; When the service order is executed, the service order management device generates service order data according to the first information; The service order management device sends the service order data to a service order monitoring device, and the service order monitoring device is used to monitor whether the service order data has a risk of fraud according to the association confidence between each item set in a plurality of historical service order data; Acquire a plurality of historical service order data, wherein the plurality of historical service order data correspond one to one with the plurality of services, and each of the plurality of historical service order data includes a value of each service feature of a plurality of service features corresponding to the secondary service in the plurality of services; Acquire S items from the plurality of historical service order data, the S items corresponding one-to-one to S types of service feature values ​​in the service, each item in the S items is used to represent a corresponding service feature value in the S types of service feature values, and S is a positive integer greater than 1; An association confidence between a first frequent item set and a second frequent item set is determined according to the multiple historical service order data and an association rule algorithm, wherein the association confidence is used to monitor whether the service order data to be processed has a risk of fraud, wherein the first frequent item set includes M items of the S items, and the second frequent item set includes N items of the S items, wherein M and N are positive integers less than or equal to S, and the first frequent item set is different from the second frequent item set.

2. The method according to claim 1, characterized in that: The method further comprises: The service order management device receives a to-be-processed service verification code sent by the first terminal device for the service order; The service order management device verifies the to-be-processed service verification code based on the service verification code; The service order management device sends the verification result of the verification code to be processed to the first terminal device.

3. The method according to claim 1, characterized in that The multiple service features include one or more of the following service features: service object, service type of service provided corresponding to the service, service item, service time, service fee and service personnel information.

4. A risk management method for a service order, characterized in that: include: The service order monitoring device obtains service order data to be monitored, wherein the service order data to be monitored includes the value of each service feature of multiple service features of the service to be monitored; wherein the service order data to be monitored is generated by the service order management device after the service order is executed; The service order monitoring device obtains the correlation between the first item set and the second item set in the service order data to be monitored; The service order monitoring device determines whether the service order data to be monitored has a risk of falsification based on the target association confidence and the association, wherein the target association confidence includes the association confidence determined using the method described in claim 2 or 3, the first item set is the same as the first frequent item set, and the second item set is the same as the second frequent item set.

5. The method according to claim 4, characterized in that The determining whether the service order data to be monitored has a risk of fraud according to the target association confidence and the association degree includes: When the difference between the correlation degree and the target correlation confidence degree is greater than or equal to a preset value, it is determined that the service order data to be monitored has a risk of falsification.

6. A risk control device for a service order, characterized in that: include: A receiving module, configured for the service order management device to receive first information, wherein the first information is used to indicate a service object, a service type, a service item, a service time, a service fee, and service personnel information of a service provided to the service object; A sending module, used for the service order management device to send the service order to the first terminal device indicated by the service personnel information, and the first terminal device is used to display the information in the service order to the service personnel; The sending module is further used for the service order management device to send the service order and service verification code to the second terminal device, and the second terminal device is used to display the information in the service order and the service verification code to the service object; A generating module, configured to generate service order data according to the first information by the service order management device after the service order is executed; The sending module is further used for the service order management device to send the service order data to the service order monitoring device, and the service order monitoring device is used to monitor whether the service order data has a risk of fraud according to the association confidence between each item set in the plurality of historical service order data; an acquisition module, configured to acquire a plurality of historical service order data, wherein the plurality of historical service order data correspond one to one with multiple services, and each of the plurality of historical service order data comprises a value of each service feature of a plurality of service features corresponding to a secondary service in the plurality of services; The acquisition module is further used to acquire S items, the S items corresponding one-to-one to S service characteristic values ​​in the service, each item in the S items is used to represent a corresponding service characteristic value in the S service characteristic values, and S is a positive integer greater than 1; A determination module is used to determine the association confidence between the first frequent item set and the second frequent item set according to the multiple historical service order data and the association rule algorithm, wherein the association confidence is used to monitor whether the service order data to be processed has a risk of fraud, the first frequent item set includes M items of the S items, the second frequent item set includes N items of the S items, M and N are positive integers less than or equal to S, and the first frequent item set is different from the second frequent item set.

7. A risk control device for a service order, characterized in that: include: An acquisition module, used for the service order monitoring device to acquire service order data to be monitored, wherein the service order data to be monitored includes the value of each service feature of multiple service features of the service to be monitored; wherein the service order data to be monitored is generated by the service order management device after the service order is executed; The acquisition module is further used by the service order monitoring device to acquire the correlation between the first item set and the second item set in the service order data to be monitored; A judgment module, used for the service order monitoring device to judge whether the service order data to be monitored has a risk of fraud based on the target association confidence and the association, wherein the target association confidence includes the association confidence determined using the method according to claim 2 or 3, the first item set is the same as the first frequent item set, and the second item set is the same as the second frequent item set.

8. A risk control device for a service order, characterized in that: including a memory, and a processor coupled to the memory; The memory is used to store program instructions; The processor is configured to execute the program instructions to implement the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program code for computer execution, wherein the program code includes a program for implementing the method according to any one of claims 1 to 5.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when being executed by a processor.

Images