Financial risk identification method, device, equipment, medium and program product

Abstract

The invention discloses a financial risk identification method, device and equipment, a medium and a program product, and relates to the technical field of financial science and technology. The method comprises the following steps: acquiring historical financial risk event data; based on the user dimension and the equipment dimension, performing data classification on the historical financial risk event data to obtain to-be-marked user sample data and to-be-marked equipment sample data; according to the to-be-marked user sample data and the to-be-marked equipment sample data, determining a user equipment joint label and a target sample feature; and training a financial service scene pre-training model by using the user equipment joint tag and the target sample features to obtain a target financial risk identification model, and performing financial risk identification through the target financial risk identification model. According to the technical scheme of the embodiment of the invention, the financial risk identification effect can be improved, so that the account fund security is effectively protected.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a financial risk identification method, device, equipment, medium and program product. Background Art

[0002] With the development of technology, mobile terminals have become an important carrier for daily consumption, transfer and other financial behaviors of the public. While bringing convenience, they have also caused more and more fraud incidents. Many criminals steal user information through Trojan viruses, phishing websites, and disguised administrators, and conduct transactions through stolen information, causing property losses to account owners.

[0003] At present, banks' account security control is still limited to verifying the real identity of customers, and they have only deployed some simple control measures to identify financial risks. This was feasible when handling business at the counter in the past, but in online channels such as online banking and mobile banking, these control measures can be easily cracked, causing serious losses. Summary of the invention

[0004] The present invention provides a financial risk identification method, device, equipment, medium and program product to solve the problem that the current financial risk identification effect is poor, resulting in the inability to further effectively protect the security of user accounts.

[0005] According to one aspect of the present invention, there is provided a financial risk identification method, comprising:

[0006] Obtain historical financial risk event data;

[0007] Based on the user dimension and the device dimension, the historical financial risk event data is classified to obtain the user sample data to be marked and the device sample data to be marked;

[0008] Determine the user device joint label and target sample features based on the user sample data to be labeled and the device sample data to be labeled;

[0009] The financial business scenario pre-training model is trained by utilizing the joint labels of user devices and target sample features to obtain a target financial risk identification model, so as to identify financial risks through the target financial risk identification model.

[0010] According to another aspect of the present invention, there is provided a financial risk identification device, comprising:

[0011] The completed risk event data acquisition module is used to obtain historical financial risk event data;

[0012] A data classification module is used to classify historical financial risk event data based on user dimensions and device dimensions to obtain user sample data to be marked and device sample data to be marked;

[0013] A training sample preparation module is used to determine the user device joint label and the target sample characteristics according to the user sample data to be marked and the device sample data to be marked;

[0014] The model training module is used to train the financial business scenario pre-training model using the user device joint label and the target sample features to obtain the target financial risk identification model so as to identify financial risks through the target financial risk identification model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial risk identification method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial risk identification method described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided, characterized in that the computer program product includes a computer program, and when the computer program is executed by a processor, the financial risk identification method described in any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention obtains historical financial risk event data, and then classifies the historical financial risk event data based on the user dimension and the device dimension to obtain user sample data to be labeled and device sample data to be labeled, and then determines the user device joint label and the target sample feature according to the user sample data to be labeled and the device sample data to be labeled, and uses the user device joint label and the target sample feature to train the financial business scenario pre-training model to obtain the target financial risk identification model. In this solution, historical financial risk event data is classified and labeled from different dimensions, and the user device joint label is used to train the model with the corresponding target sample feature, and financial risks are identified from the dual dimensions of user and device, which greatly improves the quality of training samples, so as to effectively improve the prediction effect of the model, solves the problem that the current financial risk identification effect is poor, resulting in the inability to further effectively protect the security of user accounts, and can improve the financial risk identification effect, thereby effectively protecting the security of account funds.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a financial risk identification method provided in Embodiment 1 of the present invention;

[0025] Figure 2 A flowchart of a financial risk identification method provided in Embodiment 2 of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a financial risk identification device provided in Embodiment 3 of the present invention;

[0027] Figure 4 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flowchart of a financial risk identification method provided in the first embodiment of the present invention. This embodiment is applicable to the case of accurate financial risk identification. The method can be executed by a financial risk identification device. The financial risk identification device can be implemented in the form of hardware and / or software. The financial risk identification device can be configured in an electronic device. The electronic device may include but is not limited to a computer or a server. Figure 1 As shown, the method includes:

[0032] Step 110: Obtain historical financial risk event data.

[0033] Among them, historical financial risk event data may be relevant data of completed financial risk events.

[0034] In an embodiment of the present invention, based on the identification needs of specific financial risk scenarios, historical financial risk event data under corresponding scenarios can be obtained.

[0035] Step 120: Based on the user dimension and the device dimension, the historical financial risk event data is classified to obtain user sample data to be marked and device sample data to be marked.

[0036] The user sample data to be marked may be the user dimension data in the historical financial risk event data, and the device sample data to be marked may be the device dimension data in the historical financial risk event data.

[0037] In an embodiment of the present invention, historical financial risk event data can be classified according to user dimension and device dimension, so that the data of user dimension in the historical financial risk event data can be used as user sample data to be labeled, and the data of device dimension in the historical financial risk event data can be used as device sample data to be labeled.

[0038] Step 130: Determine the user device joint label and the target sample characteristics according to the user sample data to be labeled and the device sample data to be labeled.

[0039] The user device joint label can be a joint label obtained by combining the label corresponding to the user sample data to be labeled and the label corresponding to the device sample data to be labeled. The target sample feature can be a sample feature determined based on the user sample data to be labeled and the device sample data to be labeled, and is used for joint user device joint label pair model training.

[0040] In an embodiment of the present invention, the user sample data to be marked and the device sample data to be marked can be analyzed according to the preset rules for sample labeling, and the labels corresponding to the user sample data to be marked and the device sample data to be marked can be determined, and then the labels under the two dimensions can be associated and combined to obtain a user-device joint label, and the characteristics of the user sample data to be marked and the device sample data to be marked can be further analyzed to determine the target sample characteristics.

[0041] Step 140: Use the user device joint label and the target sample characteristics to train the financial business scenario pre-training model to obtain a target financial risk identification model, so as to perform financial risk identification through the target financial risk identification model.

[0042] The financial business scenario pre-training model may be a machine learning model with data processing and prediction capabilities. The target financial risk identification model may be a model obtained after the financial business scenario pre-training model is trained, and is used for financial risk identification and prediction.

[0043] In an embodiment of the present invention, the user device joint label and the corresponding target sample features can be used as training samples and input into a financial business scenario pre-training model to train the financial business scenario pre-training model to obtain a target financial risk identification model. The financial event data to be analyzed is then analyzed and predicted based on the target financial risk identification model to provide financial risk warnings and ensure the security of user funds.

[0044] The technical solution of the embodiment of the present invention obtains historical financial risk event data, and then classifies the historical financial risk event data based on the user dimension and the device dimension to obtain user sample data to be labeled and device sample data to be labeled, and then determines the user device joint label and the target sample feature according to the user sample data to be labeled and the device sample data to be labeled, and uses the user device joint label and the target sample feature to train the financial business scenario pre-training model to obtain the target financial risk identification model. In this solution, historical financial risk event data is classified and labeled from different dimensions, and the user device joint label is used to train the model with the corresponding target sample feature, and financial risks are identified from the dual dimensions of user and device, which greatly improves the quality of training samples, so as to effectively improve the prediction effect of the model, solves the problem that the current financial risk identification effect is poor, resulting in the inability to further effectively protect the security of user accounts, and can improve the financial risk identification effect, thereby effectively protecting the security of account funds.

[0045] Embodiment 2

[0046] Figure 2 This is a flowchart of a financial risk identification method provided in the second embodiment of the present invention. This embodiment is specific based on the above embodiment and provides a specific optional implementation method for determining the user device joint label and the target sample characteristics based on the user sample data to be marked and the device sample data to be marked. Figure 2 As shown, the method includes:

[0047] Step 210: Obtain historical financial risk event data.

[0048] Step 220: Based on the user dimension and the device dimension, the historical financial risk event data is classified to obtain user sample data to be marked and device sample data to be marked.

[0049] Step 230: Determine the user dimension label of each sample data in the user sample data to be labeled, and the device dimension label of each sample data in the device sample data to be labeled.

[0050] The user dimension tag may be a tag determined for user behavior in a financial scenario, and the device dimension tag may be a tag determined for device behavior in a financial scenario.

[0051] In an embodiment of the present invention, each sample data in the user sample data to be labeled can be parsed to determine the user dimension label that is respectively adapted to each sample in the preset user dimension label set, and each sample data in the device sample data to be labeled can be parsed to determine the device dimension label that is respectively adapted to each sample in the preset device dimension label set.

[0052] In an optional embodiment of the present invention, determining the user dimension label of each sample data in the user sample data to be labeled, and the device dimension label of each sample data in the device sample data to be labeled, may include: determining the user behavior feature mapping label and the device behavior feature mapping label; parsing the user sample data to be labeled, and determining the user dimension label of each sample data in the user sample data to be labeled based on the user behavior feature mapping label; parsing the device sample data to be labeled, and determining the device dimension label of each sample data in the device sample data to be labeled based on the device behavior feature mapping label.

[0053] The user behavior feature mapping tag may be a preset full user dimension tag mapped with the user behavior feature, and the device behavior feature mapping tag may be a preset full device dimension tag mapped with the device behavior feature.

[0054] In an embodiment of the present invention, a pre-configured label corresponding to user behavior in a financial scenario, i.e., a user behavior feature mapping label, and a pre-configured label corresponding to device behavior in a financial scenario, i.e., a device behavior feature mapping label, can be obtained, so as to parse the user sample data to be labeled, and determine the user dimension label of each sample data in the user sample data to be labeled according to the parsing result of the user sample data to be labeled and the user behavior feature mapping label, and further parse the device sample data to be labeled, and determine the user dimension label of each sample data in the user sample data to be labeled according to the parsing result of the user sample data to be labeled and the device behavior feature mapping label. Without manual intervention, the label of each sample can be automatically adapted based on the user behavior feature mapping label and the device behavior feature mapping label.

[0055] In an optional embodiment of the present invention, parsing the user sample data to be labeled, and determining the user dimension label of each sample data in the user sample data to be labeled according to the user behavior feature mapping label, may include: parsing the user behavior feature of each sample data in the user sample data to be labeled; mapping the user behavior feature of each sample data in the user sample data to be labeled with the user behavior feature mapping label to obtain the user dimension label of each sample data in the user sample data to be labeled.

[0056] Among them, the user dimension label may include at least one of a one-person-multiple-device label, a user business processing time period label, and a user business processing type label. The one-person-multiple-device label may be a label that represents a user logging into multiple devices. Exemplarily, the one-person-multiple-device label may be refined according to different financial business types based on the number of devices logged into by a user, and the specific level may be set by the user. The user business processing time period label may be a label set for the user's daily or current business processing time. For example, different time periods correspond to early morning, morning, and noon, etc., and / or different user business processing time labels such as weekends and weekdays. The user business processing type label can be used to characterize the user's daily or current business processing type, which may specifically include transfers, balance inquiries, and fund purchases, etc.

[0057] In an embodiment of the present invention, each sample data in the user sample data to be labeled can be parsed, the user behavior characteristics of each sample data in the user sample data to be labeled can be extracted, and each sample data in the user sample data to be labeled can be matched and mapped with the user behavior characteristic mapping label according to the user behavior characteristics to obtain the user dimension label of each sample data in the user sample data to be labeled. From the user dimension, each sample data in the user sample data to be labeled can be labeled according to the user behavior, and the specific labeling label can better fit the financial scenario, which can improve the training effect of the model for the specific financial scenario.

[0058] In an optional embodiment of the present invention, parsing the sample data of the device to be marked, and determining the device dimension label of each sample data in the sample data of the device to be marked according to the device behavior feature mapping label, can include: parsing the device behavior feature of each sample data in the sample data of the device to be marked; mapping the device behavior feature of each sample data in the sample data of the device to be marked with the device behavior feature mapping label to obtain the device dimension label of each sample data in the sample data of the device to be marked.

[0059] Among them, the device dimension label may include at least one of a one-machine-multiple-person label, a device-frequent-start label, a device-simulator label, a device-parameter-tampered label, a remote-operation label, and a cloud-communication label. A one-machine-multiple-person label may be a label for a device to log in to multiple users. Exemplarily, a one-machine-multiple-person label may be refined according to different financial service types based on the number of logged-in customers, and the specific level may be set by the user. A device-frequent-start label may be a label set when the number of times a device starts an APP (Application, mobile application software) exceeds a set threshold within a period of time. A device-simulator label may be a label set when the device installed by the APP is abnormal and is a simulator. A device-parameter-tampered label may be a label set when a parameter of a device installed by the APP is inconsistent with the previous one. A remote-operation label may be a label set when the device has screen sharing and / or remote control. A cloud-communication label may be a label for communicating with the cloud.

[0060] In an embodiment of the present invention, each sample data in the device sample data to be marked can be parsed, and the device behavior characteristics of each sample data in the device sample data to be marked can be extracted. Each sample data in the device sample data to be marked can be matched and mapped with the device behavior characteristic mapping label according to the device behavior characteristics to obtain the device dimension label of each sample data in the device sample data to be marked. From the device dimension, each sample data in the device sample data to be marked can be labeled according to the device behavior, and the specific labeling label can better fit the financial scenario, which can improve the training effect of the model for the specific financial scenario.

[0061] Step 240: Associating the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled based on the financial risk event to obtain a user-device joint label.

[0062] In an optional embodiment of the present invention, the user dimension label of each sample data in the user sample data to be labeled and the device dimension label of each sample data in the device sample data to be labeled are associated based on financial risk events to obtain a user-device joint label, which may include: directly associating the user dimension label of each sample data in the user sample data to be labeled and the device dimension label of each sample data in the device sample data to be labeled according to financial risk events to obtain a first joint label, and using the first joint label as the user-device joint label; or, parsing user-device trusted relationship data based on the user sample data to be labeled and the device sample data to be labeled, and determining a second joint label based on the user-device trusted relationship data; and using the first joint label and the second joint label as the user-device joint label.

[0063] Among them, the first joint label can be a joint label composed of a user dimension label and a device dimension label of the same financial risk event. The user-device trusted relationship data can be used to describe the trustworthiness of the user and the device he operates. Exemplarily, at least one user dimension label of a sample in the user sample data to be labeled under the same financial risk event can be combined with at least one device dimension label of the sample data in the device sample data to be labeled to obtain the first joint label.

[0064] The second joint tag may be used to identify the trust level of the user and the device determined based on the user device trust relationship data. The second joint tag may include but is not limited to high trust, medium trust, low trust and untrust.

[0065] In an embodiment of the present invention, the user dimension label of each sample data in the user sample data to be labeled and the device dimension label of each sample data in the device sample data to be labeled can be associated and combined for the same financial risk event to obtain a first joint label. Alternatively, the user sample data to be labeled and the device sample data to be labeled are integrated to parse the user device trusted relationship data, and the first joint label and the second joint label are used as the user device joint label. This solution can not only directly utilize the user dimension label and the device dimension label that have been determined to freely combine them into the first joint label, but also extract new labels from the perspective of the credibility of the user and the device after the first joint label is determined, thereby enriching the diversity of the sample labels of the training model to improve the model prediction effect.

[0066] Step 250: Determine target sample characteristics based on the user sample data to be marked and the device sample data to be marked.

[0067] Step 260: Use the user device joint label and the target sample characteristics to train the financial business scenario pre-training model to obtain a target financial risk identification model, so as to perform financial risk identification through the target financial risk identification model.

[0068] In this solution, the target financial risk identification model can use the two-dimensional relationship between equipment and customers to predict the financial risks of different business scenarios. For specific business scenarios such as money laundering and account calls, it can describe the potential financial risks of the customer from the equipment dimension and predict the potential financial risks of the customer.

[0069] The technical solution of the embodiment of the present invention obtains historical financial risk event data, and then classifies the historical financial risk event data based on user dimensions and device dimensions to obtain user sample data to be labeled and device sample data to be labeled, and then determines the user dimension label of each sample data in the user sample data to be labeled, and the device dimension label of each sample data in the device sample data to be labeled, and further associates the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled based on financial risk events to obtain a user-device joint label, and then determines the target sample characteristics based on the user sample data to be labeled and the device sample data to be labeled, and uses the user-device joint label and the target sample characteristics to train a financial business scenario pre-training model to obtain a target financial risk identification model, so as to perform financial risk identification through the target financial risk identification model. In this solution, after classifying and labeling the historical financial risk event data, the labels are combined into joint labels from the user dimension and the device dimension, and the model is trained with the corresponding target sample features. Financial risks are identified from the dual dimensions of user and device, which greatly improves the quality of training samples and effectively improves the prediction effect of the model. This solves the current problem of poor financial risk identification, which makes it impossible to further effectively protect user account security. It can improve the financial risk identification effect and thus effectively protect the security of account funds.

[0070] In the technical solution of the embodiment of the present invention, the collection, storage, use, processing, transmission, provision, disclosure and application of user-related data in the historical financial risk event data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0071] Embodiment 3

[0072] Figure 3 This is a structural diagram of a financial risk identification device provided in Example 3 of the present invention.

[0073] like Figure 3 As shown, the device comprises:

[0074] The completed risk event data acquisition module 310 is used to acquire historical financial risk event data;

[0075] The data classification module 320 is used to classify the historical financial risk event data based on the user dimension and the device dimension to obtain the user sample data to be marked and the device sample data to be marked;

[0076] The training sample preparation module 330 is used to determine the user device joint label and the target sample feature according to the user sample data to be labeled and the device sample data to be labeled;

[0077] The model training module 340 is used to train the financial business scenario pre-training model using the user device joint label and the target sample characteristics to obtain a target financial risk identification model so as to perform financial risk identification through the target financial risk identification model.

[0078] The technical solution of the embodiment of the present invention obtains historical financial risk event data, and then classifies the historical financial risk event data based on the user dimension and the device dimension to obtain user sample data to be labeled and device sample data to be labeled, and then determines the user device joint label and the target sample feature according to the user sample data to be labeled and the device sample data to be labeled, and uses the user device joint label and the target sample feature to train the financial business scenario pre-training model to obtain the target financial risk identification model. In this solution, historical financial risk event data is classified and labeled from different dimensions, and the user device joint label is used to train the model with the corresponding target sample feature, and financial risks are identified from the dual dimensions of user and device, which greatly improves the quality of training samples, so as to effectively improve the prediction effect of the model, solves the problem that the current financial risk identification effect is poor, resulting in the inability to further effectively protect the security of user accounts, and can improve the financial risk identification effect, thereby effectively protecting the security of account funds.

[0079] Optionally, the training sample preparation module 330 includes a preliminary label determination unit, a joint label determination unit and a sample feature determination unit. The preliminary label determination unit is used to determine the user dimension label of each sample data in the user sample data to be labeled, and the device dimension label of each sample data in the device sample data to be labeled. The joint label determination unit is used to associate the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled based on financial risk events to obtain the user device joint label. The sample feature determination unit is used to determine the target sample feature based on the user sample data to be labeled and the device sample data to be labeled.

[0080] Optionally, a preliminary label determination unit is specifically used to determine user behavior feature mapping labels and device behavior feature mapping labels; parse the user sample data to be labeled, and determine the user dimension label of each sample data in the user sample data to be labeled based on the user behavior feature mapping labels; parse the device sample data to be labeled, and determine the device dimension label of each sample data in the device sample data to be labeled based on the device behavior feature mapping labels.

[0081] Optionally, a preliminary label determination unit is specifically used to analyze user behavior characteristics of each sample data in the user sample data to be labeled; map the user behavior characteristics of each sample data in the user sample data to be labeled with the user behavior characteristic mapping label to obtain a user dimension label for each sample data in the user sample data to be labeled; wherein the user dimension label includes at least one of a one-person-multiple-machine label, a user business processing time period label, and a user business processing type label.

[0082] Optionally, a preliminary label determination unit is specifically used to parse the device behavior characteristics of each sample data in the device sample data to be marked; map the device behavior characteristics of each sample data in the device sample data to be marked with the device behavior characteristic mapping label to obtain the device dimension label of each sample data in the device sample data to be marked; wherein the device dimension label includes at least one of a one-machine-multiple-person label, a device frequency-start label, a device simulator label, a device parameter tampering label, a remote operation label, and a cloud communication label.

[0083] Optionally, a joint label determination unit is specifically used to directly associate the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled according to financial risk events to obtain a first joint label, and use the first joint label as the user device joint label; or, based on the user sample data to be labeled and the device sample data to be labeled, parse the user device trusted relationship data, and determine the second joint label based on the user device trusted relationship data; use the first joint label and the second joint label as the user device joint label.

[0084] The financial risk identification device provided in the embodiment of the present invention can execute the financial risk identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0085] Embodiment 4

[0086] Figure 4A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0087] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0088] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0089] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the financial risk identification method.

[0090] In some embodiments, the financial risk identification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the financial risk identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the financial risk identification method in any other appropriate manner (e.g., by means of firmware).

[0091] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0093] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0094] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0095] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0096] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of traditional physical hosts and VPS servers, which are difficult to manage and have weak business scalability.

[0097] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0098] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A financial risk identification method, characterized in that: include: Obtain historical financial risk event data; Based on the user dimension and the device dimension, the historical financial risk event data is classified to obtain user sample data to be marked and device sample data to be marked; Determine a user device joint label and a target sample feature according to the user sample data to be marked and the device sample data to be marked; The user device joint label and the target sample feature are used to train a financial business scenario pre-training model to obtain a target financial risk identification model, so as to perform financial risk identification through the target financial risk identification model.

2. The method according to claim 1, characterized in that: The determining of the user device joint label and the target sample feature according to the user sample data to be marked and the device sample data to be marked includes: Determine a user dimension label for each sample data in the user sample data to be labeled, and a device dimension label for each sample data in the device sample data to be labeled; Associating the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled based on the financial risk event to obtain the user device joint label; The target sample feature is determined based on the user sample data to be marked and the device sample data to be marked.

3. The method according to claim 2, characterized in that The determining of the user dimension label of each sample data in the user sample data to be labeled and the device dimension label of each sample data in the device sample data to be labeled includes: Determine user behavior feature mapping labels and device behavior feature mapping labels; Parsing the user sample data to be labeled, and determining a user dimension label for each sample data in the user sample data to be labeled according to the user behavior feature mapping label; The sample data of the device to be marked is parsed, and the device dimension label of each sample data in the sample data of the device to be marked is determined according to the device behavior feature mapping label.

4. The method according to claim 3, characterized in that The parsing of the user sample data to be labeled and determining the user dimension label of each sample data in the user sample data to be labeled according to the user behavior feature mapping label includes: Analyzing the user behavior characteristics of each sample data in the user sample data to be marked; Mapping the user behavior feature of each sample data in the user sample data to be labeled with the user behavior feature mapping label to obtain a user dimension label for each sample data in the user sample data to be labeled; Among them, the user dimension label includes at least one of a one-person-multiple-machine label, a user business processing time period label, and a user business processing type label.

5. The method according to claim 3, characterized in that: The parsing of the sample data of the device to be marked and determining the device dimension label of each sample data in the sample data of the device to be marked according to the device behavior feature mapping label include: Analyzing the device behavior characteristics of each sample data in the sample data of the device to be marked; Mapping the device behavior feature of each sample data in the device sample data to be marked with the device behavior feature mapping label to obtain a device dimension label for each sample data in the device sample data to be marked; Among them, the device dimension label includes at least one of a one-machine-multiple-person label, a device frequency-start label, a device simulator label, a device parameter tampering label, a remote operation label and a cloud communication label.

6. The method according to claim 2, characterized in that The step of associating the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled based on financial risk events to obtain the user device joint label includes: Directly associate the user dimension label of each sample data in the user sample data to be labeled with the device dimension label of each sample data in the device sample data to be labeled according to the financial risk event to obtain a first joint label, and use the first joint label as the user device joint label; or Based on the user sample data to be marked and the device sample data to be marked, parsing the user device trusted relationship data, and determining a second joint tag according to the user device trusted relationship data; The first joint tag and the second joint tag are used as the user equipment joint tag.

7. A financial risk identification device, characterized in that: include: The completed risk event data acquisition module is used to obtain historical financial risk event data; A data classification module, used to classify the historical financial risk event data based on user dimensions and device dimensions to obtain user sample data to be marked and device sample data to be marked; A training sample preparation module, used to determine a user device joint label and a target sample feature according to the user sample data to be marked and the device sample data to be marked; The model training module is used to train a financial business scenario pre-training model using the user device joint label and the target sample characteristics to obtain a target financial risk identification model so as to perform financial risk identification through the target financial risk identification model.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial risk identification method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial risk identification method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the financial risk identification method according to any one of claims 1 to 6.

Images