Risk control analysis method and device

Abstract

The embodiment of the invention discloses a risk control analysis method and device. According to one specific embodiment, the method comprises the steps that a risk control element combination set is acquired, and risk control elements are attribute values of receipts; for risk control element combinations in the risk control element combination set, obtaining statistical data of the risk control element combinations, and determining recommendation values of the risk control element combinations according to the statistical data by using a pre-trained risk control element analysis model, the recommendation values being used for representing importance of the risk control element combinations for risk control analysis of the receipts; and selecting a risk control element combination from the risk control element combination set as a target risk control element combination according to the corresponding recommendation value, and determining risk control receipts in the to-be-analyzed receipt set according to the target risk control element combination. According to the embodiment, automatic risk control analysis of the receipts can be realized.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a risk control analysis method and device. Background Art

[0002] In many fields such as e-commerce, logistics, and transportation, a large number of documents may be generated at any time (such as transportation documents of transportation platforms, etc.). Especially for some larger platforms or enterprises, the number of documents to be processed is very large, and it is also difficult to manage the risk control of a large number of documents. Usually, a large amount of manpower is required to conduct corresponding risk control analysis according to different scenarios, and then take corresponding sub-control and audit actions.

[0003] Specifically, it is usually necessary to query and analyze the specified risk control scenarios to compare the risk control elements of the corresponding business horizontally to find risk control problems. For example, for the same route and the same cargo volume, due to the high cost caused by the problem of the vehicle model used, the existing technology usually needs to set the query and analysis conditions according to the scenario of the vehicle model problem to export relevant data for horizontal comparison, and then analyze the transportation documents with risk control problems. Obviously, the existing technology requires artificial definition of risk control scenarios as a prerequisite, and then set the risk control elements that need to be analyzed through expert analysis, and then determine the documents with risk control problems through data comparison. Summary of the invention

[0004] The embodiments of the present disclosure provide a risk control analysis method and device.

[0005] In a first aspect, an embodiment of the present disclosure provides a risk control analysis method, the method comprising: obtaining a risk control factor combination set, wherein the risk control factor is an attribute value of a document; for a risk control factor combination in the risk control factor combination set, obtaining statistical data of the risk control factor combination, and using a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination based on the statistical data, the recommended value being used to characterize the importance of the risk control factor combination for the risk control analysis of the document; selecting a risk control factor combination from the risk control factor combination set as a target risk control factor combination based on the corresponding recommended value, and determining the risk control documents in the document set to be analyzed based on the target risk control factor combination.

[0006] In a second aspect, an embodiment of the present disclosure provides a risk control analysis device, comprising: an acquisition unit, configured to acquire a risk control factor combination set, wherein the risk control factor is an attribute value of a document; a determination unit, configured to acquire statistical data of the risk control factor combination in the risk control factor combination set, and determine a recommended value of the risk control factor combination according to the statistical data using a pre-trained risk control factor analysis model, wherein the recommended value is used to characterize the importance of the risk control factor combination for the risk control analysis of the document; the risk control unit, configured to select a risk control factor combination from the risk control factor combination set as a target risk control factor combination according to the corresponding recommended value, and determine the risk control documents in the document set to be analyzed according to the target risk control factor combination.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0009] The risk control analysis method and device provided by the embodiments of the present disclosure, for each risk control factor combination, determine the importance of the risk control factor combination to the risk control analysis of the document based on the statistical data of the risk control factor combination by using a pre-trained risk control factor analysis model, and then select the risk control factor combination based on the importance to determine the risk control documents in the document set to be analyzed. There is no need for manual operations such as manually specifying risk control scenarios and setting risk control factors, which helps to improve the degree of automation of risk control analysis of documents. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0011] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0012] Figure 2 is a flow chart of an embodiment of the risk control analysis method according to the present disclosure;

[0013] Figure 3 is a schematic principle block diagram of the risk control analysis method according to the present disclosure;

[0014] Figure 4is a schematic data architecture diagram of the risk control analysis method according to the present disclosure;

[0015] Figure 5 is a schematic structural diagram of an embodiment of a risk control analysis device according to the present disclosure;

[0016] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0018] It should be noted that in the technical solution of the present invention, the collection / collection, update, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken for user personal information to selectively block the use or access to personal information data to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. In addition, once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0019] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] Figure 1 An exemplary architecture 100 is shown to which an embodiment of the risk control analysis method or risk control analysis device of the present disclosure can be applied.

[0021] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0022] The terminal devices 101, 102, 103 interact with the server 105 through the network 104 to receive or send messages, etc. Various client applications may be installed on the terminal devices 101, 102, 103, such as browser applications, search applications, shopping applications, instant messaging tools, risk control analysis applications, etc.

[0023] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers and desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, multiple software or software modules for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0024] The server 105 may be a server that provides various services, such as a backend server that provides various services for client applications installed on the terminal devices 101, 102, and 103. The server 105 may obtain a risk control factor combination set from the terminal devices 101, 102, and 103, and then use a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination according to the statistical data of the risk control factor combination, and select a risk control factor combination according to the recommended value to determine the risk control document in the document set to be analyzed.

[0025] It should be noted that the above-mentioned risk control factor combination set can also be directly stored locally on the server 105. The server 105 can directly extract the locally stored risk control factor combination set and process it. At this time, the terminal devices 101, 102, 103 and the network 104 may not exist.

[0026] It should be noted that the risk control analysis method provided in the embodiments of the present disclosure is generally executed by the server 105 , and accordingly, the risk control analysis device is generally disposed in the server 105 .

[0027] It should also be noted that risk control analysis applications may also be installed in the terminal devices 101, 102, and 103, and the terminal devices 101, 102, and 103 may also perform risk control analysis based on risk control analysis applications. In this case, the risk control analysis method may also be executed by the terminal devices 101, 102, and 103, and accordingly, the risk control analysis method device may also be set in the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may not have the server 105 and the network 104.

[0028] It should be noted that the server 105 can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, multiple software or software modules for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0029] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0030] Continue to refer Figure 2 , which shows a process 200 of an embodiment of a risk control analysis method according to the present disclosure. The risk control analysis method comprises the following steps:

[0031] Step 201: Obtain a risk control factor combination set.

[0032] In this embodiment, the risk control factor may be an attribute value of a document. The document may be any type of document. For example, the document may be a transaction document, a transport document, etc. The attribute value of a document may refer to the attribute values ​​of various attributes related to the content of the document. Taking a transport document as an example, the attribute value of a transport document may represent the transport route, cargo volume, timeliness, mileage, vehicle type used, etc.

[0033] A risk control factor combination can be composed of several risk control factors. A risk control factor combination set can be composed of several risk control factor combinations. Figure 1 The server 105 shown in the figure, etc.) can obtain a risk control factor combination set from a local or other data source. The risk control factor combination set can be determined based on historically determined risk control documents. A risk control document can refer to a document with risk control issues. Taking a transport document as an example, a transport document with risk control issues can refer to a transport document with excessively high transport costs (such as transport fees, etc.). For example, the transport cost is greater than a preset threshold. The preset threshold can be specifically set by a technician based on the actual application scenario.

[0034] Step 202: For a risk control factor combination in the risk control factor combination set, obtain statistical data of the risk control factor combination, and use a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination based on the statistical data.

[0035] In this embodiment, the statistical data of the risk control factor combination may refer to the statistical data of various attributes related to the risk control factor combination. For example, the statistical data may include the hit rate of the risk control factor combination in the specified document set. The hit rate may represent the ratio of the total amount of risk control documents corresponding to the risk control factor combination to the total amount of documents corresponding to the sub-control factor combination. Generally, the statistical data of the risk control factor combination may be obtained through data statistics.

[0036] Optionally, the statistical data of the above-mentioned risk control factor combination includes at least one of the following: cumulative weight, total data, and adoption ratio. Among them, the cumulative weight can represent the product of the weight of the risk control level of the risk control factor combination and the number of documents corresponding to the risk control level. The risk control level can be set by technical personnel according to the actual application scenario. The total data can represent the total amount of risk control documents. The adoption ratio can represent the hit rate of the risk control factor combination. The importance of the risk control factor combination for risk control analysis can be more accurately judged by the cumulative weight, total data, and adoption ratio.

[0037] The risk control factor analysis model can determine the recommended value of the risk control factor combination based on the statistical data of the risk control factor combination, that is, the corresponding relationship between the statistical data of the risk control factor combination and the recommended value. Among them, the recommended value can represent the importance of the risk control factor combination to the risk control analysis of the document. Generally, the larger the recommended value, the higher the corresponding importance.

[0038] The risk control factor analysis model can be trained using machine learning methods based on historically annotated training samples. The network structure of the risk control factor analysis model can be flexibly set by technical personnel according to needs.

[0039] Step 203: Select a risk control factor combination from the risk control factor combination set as a target risk control factor combination according to the corresponding recommended value, and determine the risk control document in the document set to be analyzed according to the target risk control factor combination.

[0040] In this step, several risk control factor combinations may be selected from the risk control factor combination set in descending order of the corresponding recommended values ​​as the target risk control factor combination. For example, a preset number of risk control factor combinations may be selected from the risk control factor combination set as the target risk control factor combination. For another example, a risk control factor combination whose corresponding recommended value is greater than a preset threshold may be selected from the risk control factor combination set as the target risk control factor combination.

[0041] For each target risk control factor combination, the risk control documents in the document set to be analyzed can be further determined according to the target risk control factor combination. The document set to be analyzed can be composed of several documents that need to be analyzed for risk control. Specifically, various methods can be used to determine the risk control documents in the document set to be analyzed according to the target risk control factor combination.

[0042] For example, for each risk control factor combination, the documents corresponding to the risk control factor combination can be first screened from the set of documents to be analyzed. Among them, the document corresponding to the risk control factor combination can refer to the document whose corresponding attribute value includes the risk control factor combination. Then, it can be determined whether the document is a risk control document according to the preset risk control analysis rules. Among them, the risk control analysis rules can be pre-set by technical personnel. Taking the transport document as an example, the risk control analysis rules may include that the transportation cost is greater than a preset threshold. At this time, the transportation cost of the document (such as transportation fee) can be obtained from the local or other data sources first, and it can be determined whether the transportation cost of the document is greater than the preset threshold. If the transportation cost of the document is greater than the preset threshold, the document can be considered to be a risk control document.

[0043] Through the pre-trained risk control factor analysis model, the importance of each risk control factor combination to the risk control analysis of the document is determined according to the statistical data of the risk control factor combination, and then the risk control factor combinations are selected in order of importance from large to small to perform risk control analysis on the document to determine the risk control document. This can improve the degree of automation of risk control analysis for the document and avoid excessive human participation.

[0044] In some optional implementations of this embodiment, for each target risk control factor combination, the risk control documents in the document set to be analyzed can be determined by the following steps:

[0045] Step 1: Select documents corresponding to the target risk control factor combination from the document set to be analyzed as candidate documents.

[0046] In this step, documents whose corresponding attribute values ​​include the target risk control factor combination can be selected from the document set to be analyzed as candidate documents. As an example, the target risk control factor combination includes vehicle type "A" and departure place "G". At this time, all documents whose vehicle type "A" and departure place "G" can be selected from the document set to be analyzed as candidate documents.

[0047] Step 2: Calculate the average value of the target attribute value of the documents in the document to be analyzed.

[0048] In this step, the average value of the target attribute value of all documents in the document to be analyzed can be counted. The attribute corresponding to the target attribute value can refer to the attribute that needs to be analyzed and controlled for risk control. Taking a transport document as an example, the target attribute value can refer to the transport cost of the transport document.

[0049] Step 3: For each candidate document, determine whether the candidate document is a risk control document by comparing the target attribute value of the candidate document with the average value.

[0050] In this step, for each candidate document, if the target attribute value of the candidate document meets the preset relationship with the above average value, the candidate document can be determined to be a risk control document. The preset relationship can be flexibly set according to the actual application scenario. Taking the transport document as an example, the preset relationship can mean that the target attribute value of the candidate document is greater than the average value.

[0051] After selecting the target risk control factor combination, risk control analysis is performed on the document by comparing the target attribute value of the corresponding document with the average attribute value of all documents. This can achieve automatic screening of the target risk control factor combination, thereby improving the convenience of risk control analysis for documents.

[0052] In some optional implementations of this embodiment, the above method may also include: obtaining real risk control documents in the document set to be analyzed, and generating risk control feedback data based on the real risk control documents; and updating the risk control factor analysis model based on the risk control feedback data.

[0053] The real risk control document is the real risk control document in the set of documents to be analyzed. For example, the risk control document determined in step 203 above can be used as the real risk control document. For another example, the risk control document determined in step 203 above can be combined with the risk control document determined by other risk control analysis methods to comprehensively determine the real risk control document.

[0054] The risk control feedback data may include risk control documents and corresponding risk control factor combinations, and may also include the total amount of risk control documents, the total amount of processed risk control documents, and the number of risk control documents at different risk control levels. The following table is an example of risk control feedback data:

[0055]

[0056] As shown in the table above, the attributes of the transport document corresponding to the risk control factor combination include departure city, vehicle type, destination district and county, and carrier method. The denominator in the column of total amount of sub-controlled documents represents the total amount of risk control documents, and the numerator represents the total amount of risk control documents that have been processed.

[0057] The risk control factor analysis model can be further trained and updated using the risk control feedback data, so that the updated risk control factor analysis model can be used to re-estimate the recommended values ​​corresponding to each risk control factor combination in the risk control factor combination set. When the next risk control analysis is performed on the document, several risk control factor combinations can be selected from the risk control factor combination set as the target risk control factor combination in the order of the new recommended values ​​corresponding to each risk control factor combination from large to small, and then the risk control documents in the document set to be analyzed are determined based on the target risk control factor combination. In this way, the risk control feedback data can be generated using real risk control documents, and the risk control factor analysis model can be continuously updated to continuously improve the accuracy and stability of the risk control analysis results.

[0058] Continue to see Figure 3 , Figure 3 FIG. 1 is a schematic principle block diagram of the risk control analysis method according to this embodiment. Figure 3 As shown, taking the transport documents obtained through TSM (Transportation System Management) as an example, the risk control factor analysis model can be used to first determine the recommended value of each risk control factor combination, and the target risk control factor combination can be screened according to the corresponding recommended value. Then, risk control analysis can be performed based on the target risk control factor combination to determine the risk control document. Then, the corresponding risk control feedback data can be generated by intercepting the risk control document to update the risk control factor analysis model, so as to utilize the continuously accumulated risk control data and continuously improve the analysis capability of the risk control factor analysis model to more accurately screen the target risk control factor combination.

[0059] Continue to see Figure 4 , Figure 4 A schematic data architecture diagram of the risk control analysis method according to this embodiment. Figure 4 As shown, TSM, network database and settlement database can be used as data sources. Then, the data source can be synchronized to the data warehouse of the data layer through the data acquisition layer according to the specified rules (such as summary processing rules, risk control data filtering rules, etc.). Among them, the summary processing rules can be used to obtain data from the data source and process it into business summary data, so as to compress data such as millions into data such as tens of thousands for storage. The risk control business data filtering rules can be used to extract business data that deviates from the mean by more than a threshold into the risk control business data. Business summary data and risk control business data, etc. can be stored in the data warehouse. The above-mentioned risk control analysis method can obtain the risk control factor combination set by calling the risk control data interface provided by the data interface layer to perform risk control analysis on the document.

[0060] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a risk control analysis device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0061] like Figure 5As shown, the risk control analysis device 500 provided in this embodiment includes an acquisition unit 501, a determination unit 502 and a risk control unit 503. The acquisition unit 501 is configured to acquire a risk control factor combination set, wherein the risk control factor is an attribute value of a document; the determination unit 502 is configured to acquire statistical data of the risk control factor combination in the risk control factor combination set, and to determine a recommended value of the risk control factor combination according to the statistical data using a pre-trained risk control factor analysis model, wherein the recommended value is used to characterize the importance of the risk control factor combination for the risk control analysis of the document; the risk control unit 503 is configured to select a risk control factor combination from the risk control factor combination set as a target risk control factor combination according to the corresponding recommended value, and to determine the risk control document in the document set to be analyzed according to the target risk control factor combination.

[0062] In this embodiment, in the risk control analysis device 500, the specific processing of the acquisition unit 501, the determination unit 502 and the risk control unit 503 and the technical effects thereof can be referred to in Figure 2 The relevant descriptions of step 201, step 202 and step 203 in the corresponding embodiment are not repeated here.

[0063] In some optional implementations of this embodiment, the risk control unit is further configured to: select documents corresponding to the target risk control factor combination from the document set to be analyzed as candidate documents; calculate the average value of the target attribute values ​​of the documents in the document set to be analyzed; for each candidate document, determine whether the candidate document is a risk control document by comparing the target attribute value of the candidate document with the average value. ;

[0064] In some optional implementations of this embodiment, the risk control documents include documents with transportation costs greater than a preset threshold.

[0065] In some optional implementations of the present embodiment, the risk control unit is further configured to: for each target risk control factor combination, select a document whose corresponding attribute value includes the risk control factor combination from the document set to be analyzed; obtain the transportation cost of the selected document, and determine whether the transportation cost is greater than a preset threshold; in response to determining that the transportation cost is greater than the preset threshold, determine that the selected document is a risk control document.

[0066] In some optional implementations of this embodiment, the above-mentioned statistical data includes at least one of the following: cumulative weight, total amount of data, and adoption ratio, wherein the cumulative weight is used to represent the product of the weight of the risk control level of the risk control factor combination and the number of documents corresponding to the risk control level, the total amount of data is used to represent the total amount of risk control documents, and the adoption ratio is used to represent the hit rate of the risk control factor combination.

[0067] In some optional implementations of the present embodiment, the above-mentioned risk control analysis device 500 also includes: an update unit (not shown in the figure) is configured to: obtain real risk control documents in the document set to be analyzed, and generate risk control feedback data based on the real risk control documents; and update the risk control factor analysis model based on the risk control feedback data.

[0068] In some optional implementations of this embodiment, the risk control feedback data includes: risk control documents, corresponding risk control factor combinations, the total number of risk control documents processed, and the number of risk control documents at different risk control levels.

[0069] The device provided by the above-mentioned embodiments of the present disclosure obtains a risk control factor combination set through an acquisition unit, wherein the risk control factor is an attribute value of a document; the determination unit obtains statistical data of the risk control factor combination for the risk control factor combination in the risk control factor combination set, and uses a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination according to the statistical data, and the recommended value is used to characterize the importance of the risk control factor combination for the risk control analysis of the document; the risk control unit 503 selects a risk control factor combination from the risk control factor combination set as a target risk control factor combination according to the corresponding recommended value, and determines the risk control document in the document set to be analyzed according to the target risk control factor combination, without the need for manual operations such as manually specifying risk control scenarios and setting risk control factors, which helps to improve the degree of automation of risk control analysis of documents.

[0070] Reference below Figure 6 , which shows an electronic device (eg, Figure 1 A schematic diagram of the structure of the server in FIG600. Figure 6 The server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0071] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0072] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0073] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0074] It should be noted that the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0075] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a risk control factor combination set, wherein the risk control factor is an attribute value of a document; obtains statistical data of the risk control factor combination in the risk control factor combination set, and uses a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination based on the statistical data, the recommended value being used to characterize the importance of the risk control factor combination for the risk control analysis of the document; selects a risk control factor combination from the risk control factor combination set as a target risk control factor combination based on the corresponding recommended value, and determines the risk control documents in the document set to be analyzed based on the target risk control factor combination.

[0076] Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0077] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a determination unit and a risk control unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the acquisition unit may also be described as "a unit for acquiring a combination set of risk control elements, wherein the risk control elements are attribute values ​​of documents".

[0079] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) to form a technical solution.

Claims

1. A risk control analysis method, comprising: Get the risk control factor combination set, where the risk control factor is the attribute value of the document; For a risk control factor combination in the risk control factor combination set, obtaining statistical data of the risk control factor combination, and using a pre-trained risk control factor analysis model to determine a recommended value of the risk control factor combination according to the statistical data, wherein the recommended value is used to characterize the importance of the risk control factor combination for the risk control analysis of the document; According to the corresponding recommended values, a risk control factor combination is selected from the risk control factor combination set as a target risk control factor combination, and according to the target risk control factor combination, a risk control document in the document set to be analyzed is determined.

2. The method according to claim 1, wherein: Determining the risk control documents in the set of documents to be analyzed according to the target risk control factor combination includes: Selecting documents corresponding to the target risk control factor combination from the set of documents to be analyzed as candidate documents; Counting the average value of the target attribute values ​​of the documents in the document set to be analyzed; For each candidate document, whether the candidate document is a risk control document is determined by comparing the target attribute value of the candidate document with the average value.

3. The method according to claim 2, wherein: The risk control documents include documents whose transportation costs are greater than a preset threshold.

4. The method according to claim 3, wherein: Determining the risk control documents in the set of documents to be analyzed according to the target risk control factor combination includes: For each target risk control factor combination, select a document whose corresponding attribute value includes the risk control factor combination from the document set to be analyzed; Obtaining the transportation cost of the selected document, and determining whether the transportation cost is greater than a preset threshold; In response to determining that the transportation cost is greater than a preset threshold, the selected document is determined to be a risk control document.

5. The method according to claim 1, wherein: The statistical data includes at least one of the following: cumulative weight, total data, and adoption ratio, wherein the cumulative weight is used to represent the product of the weight of the risk control level of the risk control factor combination and the number of documents corresponding to the risk control level, the total data is used to represent the total amount of risk control documents, and the adoption ratio is used to represent the hit rate of the risk control factor combination.

6. The method according to any one of claims 1 to 5, wherein: The method further comprises: Acquire the real risk control documents in the set of documents to be analyzed, and generate risk control feedback data according to the real risk control documents; The risk control factor analysis model is updated according to the risk control feedback data.

7. The method according to claim 6, wherein: The risk control feedback data includes: risk control documents, corresponding risk control factor combinations, the total amount of risk control documents processed, and the number of risk control documents at different risk control levels.

8. A risk control analysis device, wherein: The device comprises: An acquisition unit is configured to acquire a risk control factor combination set, wherein the risk control factor is an attribute value of a document; a determining unit configured to obtain statistical data of the risk control factor combination in the risk control factor combination set, and determine a recommended value of the risk control factor combination according to the statistical data by using a pre-trained risk control factor analysis model, wherein the recommended value is used to represent the importance of the risk control factor combination for the risk control analysis of the document; The risk control unit is configured to select a risk control factor combination from the risk control factor combination set as a target risk control factor combination according to the corresponding recommended value, and to determine the risk control document in the document set to be analyzed according to the target risk control factor combination.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images