Data evaluation method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a data evaluation method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining a target object set which comprises N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; n is a positive integer; in the risk assessment model, identifying risk degrees corresponding to the N target objects based on the transaction data, and determining first assessment values corresponding to the N target objects according to the risk degrees; according to the hit time difference corresponding to the N target objects, determining a target fitting function corresponding to the target object set, according to the target fitting function, determining the validity period of the N target objects in the limited state, and according to the validity period, determining second assessment values corresponding to the N target objects from a risk assessment level table; and according to the first assessment value and the second assessment value, determining target risk assessment levels corresponding to the N target objects from a risk assessment level table, so that the accuracy of risk assessment can be improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a data evaluation method, device, equipment and computer-readable storage medium. Background Art

[0002] With the rapid development of the global economy, people's lives have been greatly facilitated and improved, but the security issues that come with it have also received widespread attention. For example, malicious trading objects use abnormal means to obtain profits, and use various means to cover up and conceal the nature of malicious behavior to make it legal in form. In order to reduce the harm of abnormal means to the global economy, it is proposed to conduct risk assessment on malicious trading objects, determine the risk assessment level of malicious trading objects, and conduct risk management on malicious trading objects according to the risk assessment level.

[0003] In the prior art, a risk assessment is usually performed on a malicious transaction object based on its transaction data. However, the prediction of the validity period of the risk assessment level of the malicious transaction object is usually done manually, which has the disadvantages of being one-sided and having low prediction accuracy. Summary of the invention

[0004] The embodiments of the present application provide a data evaluation method, apparatus, device, and computer-readable storage medium, which can improve the accuracy of predicting risk assessment levels.

[0005] The present application provides a data evaluation method, which includes:

[0006] Obtain a target object set, the target object set including N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state;

[0007] In the risk assessment model, the risk levels corresponding to the N target objects are identified based on the transaction data, and the first assessment values ​​corresponding to the N target objects are determined according to the risk levels;

[0008] Determine the target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state;

[0009] According to the first evaluation value and the second evaluation value, target risk assessment levels corresponding to the N target objects are determined from the risk assessment level table.

[0010] An embodiment of the present application provides a data evaluation device, including:

[0011] An acquisition module is used to acquire a target object set, the target object set includes N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state;

[0012] A first evaluation module, configured to obtain risk levels corresponding to N target objects based on the transaction data, and determine first evaluation values ​​corresponding to the N target objects according to the risk levels;

[0013] The second evaluation module is used to determine the target fitting function corresponding to the target object set according to the hit time difference corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second evaluation value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state;

[0014] The rating module is used to determine the target risk assessment levels corresponding to N target objects from the risk assessment level table according to the first assessment value and the second assessment value.

[0015] The acquisition module includes:

[0016] an acquisition unit, configured to acquire first business data, the first business data including S first business objects, transaction data associated with the S first business objects, and first hit times corresponding to the S first business objects; the first hit time is a timestamp when the S first business objects are determined to be risk objects; S is a positive integer;

[0017] an acquisition unit, configured to acquire second business data associated with the enterprise to be evaluated, the second business data including M second business objects, transaction data associated with the M second business objects, and second hit times corresponding to the M second business objects; the second hit time is a timestamp when the M second business objects are determined to be in a restricted state; M is a positive integer;

[0018] The first processing unit is used to determine N target objects from the second business data according to the object information included in the transaction data associated with the S first business objects, and determine the hit time difference corresponding to the N target objects according to the first hit time and the second hit time corresponding to the N target objects; the S first business objects and the M second business objects include the N target objects; N is a positive integer less than or equal to S and less than or equal to M;

[0019] The first processing unit is used to generate a target object set according to N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects.

[0020] Wherein, the above-mentioned second evaluation module includes:

[0021] A second processing unit is used to determine the number of target objects corresponding to each hit time difference according to the N target objects and the hit time differences corresponding to the N target objects;

[0022] A target fitting function determination unit, used for determining a target fitting function corresponding to a target object set according to each hit time difference and the number of target objects corresponding to each hit time difference;

[0023] The first evaluation unit is used to derive the target fitting function to obtain the derivative of the target fitting function, determine the validity period of the N target objects in the restricted state according to the derivative of the target fitting function, and determine the second evaluation value corresponding to the N target objects from the risk assessment level table according to the validity period.

[0024] Wherein, the above-mentioned target fitting function determination unit includes:

[0025] A first processing subunit is used to determine a target fitting function type by taking each hit time difference as an independent variable and the number of target objects corresponding to each hit time difference as a dependent variable;

[0026] The target fitting function determination subunit is used to determine the function parameters of the target fitting function type in the least squares method according to each hit time difference and the number of target objects corresponding to each hit time difference, and determine the target fitting function type containing the function parameters as the target fitting function corresponding to the target object set.

[0027] Among them, the N target objects include the target object S i , i is a positive integer less than or equal to N; the first evaluation unit comprises:

[0028] The second processing subunit is used to determine the target object S from the risk assessment level table according to the validity period. i The corresponding baseline risk assessment level; the baseline risk assessment level is used to determine the target object S i The corresponding target risk assessment level is greater than or equal to the benchmark risk assessment level;

[0029] The first evaluation subunit is used to determine the evaluation value range associated with the baseline risk assessment level from the risk assessment level table according to the baseline risk assessment level, and determine the target object S according to the evaluation value range i The corresponding second evaluation value.

[0030] Among them, the above-mentioned rating modules include:

[0031] The third processing unit is used to process the target object S i The corresponding first evaluation value and target object S i The corresponding second evaluation values ​​are summed to obtain the target object S i a corresponding third evaluation value;

[0032] The third processing unit is used to compare the target object S i The corresponding third evaluation value and target object S i The size of the target object S corresponding to the minimum evaluation value i The corresponding third evaluation value and target object S i The larger value among the corresponding minimum evaluation values ​​is determined as the target object S i The corresponding fourth assessment value; the lowest assessment value is the minimum assessment value included in the assessment value range associated with the benchmark risk assessment level;

[0033] The third processing unit is used to compare the target object S i The corresponding highest evaluation value and target object S i The size of the corresponding fourth evaluation value is the target object S i The corresponding highest evaluation value and target object S i The smaller value among the corresponding fourth evaluation values ​​is determined as the target object S i The corresponding predicted evaluation value is used to determine the target object S from the risk assessment level table according to the predicted evaluation value i The corresponding target risk assessment level; the maximum assessment value is the maximum assessment value included in the assessment value range associated with the benchmark risk assessment level.

[0034] The above device further comprises:

[0035] A processing module is used to determine a scoring formula corresponding to the risk assessment grade table according to an initial ratio value and a target change value; the initial ratio value is the ratio of the number of risk objects to the number of non-risk objects used to train the risk assessment model; the target change value is the difference between the assessment value corresponding to the initial ratio value and the assessment value corresponding to the target ratio value when the initial ratio value changes to the target ratio value;

[0036] The above-mentioned first evaluation module is specifically used to determine the first evaluation values ​​corresponding to the N target objects according to the scoring formula and the risk levels corresponding to the N target objects.

[0037] An embodiment of the present application provides a computer device, including: a processor and a memory;

[0038] The above-mentioned processor is connected to the memory and the network interface, wherein the network interface is used to provide data communication function, the memory is used to store program code, and the processor is used to call the above-mentioned program code to execute the method provided in the first aspect of the embodiment of the present application.

[0039] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. The computer program is suitable for being loaded and executed by a processor so that a computer device having the processor executes the method provided by the embodiment of the present application.

[0040] In an embodiment of the present application, in a risk assessment model, the risk levels corresponding to the N target objects can be identified based on the transaction data associated with the N target objects included in the target object set, and the first assessment value corresponding to the target object can be determined according to the risk level. Further, the target fitting function corresponding to the target object set can be determined according to the hit time difference corresponding to the target object, and then the validity period of each target object in the target object set in the restricted state can be determined according to the target fitting function, and the second assessment value corresponding to each target object can be determined from the risk assessment level table according to the validity period. Among them, the hit time difference is the time difference between the timestamp when the target object is determined as a risk object and the timestamp when the target object is determined to be in a restricted state. Further, according to the first assessment value and the second assessment value corresponding to the target object, the risk assessment level corresponding to the target object is determined from the risk assessment level table. It should be understood that by introducing the hit time difference corresponding to the target object, the risk assessment of the target object from the time dimension is increased, and a multi-dimensional and comprehensive risk assessment level is obtained, which improves the accuracy of predicting the risk assessment level. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural diagram of a network architecture provided by an embodiment of the present application;

[0042] Figure 2 It is a flow chart of a data evaluation method provided in an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of a scenario of the data evaluation method provided in an embodiment of the present application;

[0044] Figure 4 is another flow chart of the data evaluation method provided in the embodiment of the present application;

[0045] Figure 5 is a data schematic diagram of the data evaluation method provided in an embodiment of the present application;

[0046] Figure 6 is a schematic diagram of the structure of a data evaluation device provided in an embodiment of the present application;

[0047] Figure 7 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The implementation of the technical solution of the present application is further described in detail below in conjunction with the accompanying drawings.

[0050] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning and other technologies.

[0051] Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0052] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0053] The implementation of the technical solution of the present application is further described in detail below in conjunction with the accompanying drawings.

[0054] See also Figure 1 , Figure 1Schematic diagram of a network architecture provided by an embodiment of the present application. Figure 1 As shown, the system architecture may include a business server 100 and a terminal cluster, and the terminal cluster may include: terminal devices 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n and the like. Among them, the above-mentioned business server 100 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud database, cloud service, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The terminal device (including terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n) may be a smart phone, tablet computer, laptop computer, desktop computer, PDA, wearable device (such as smart watch, smart bracelet, etc.), smart TV, smart car and other smart terminals. Among them, the business server 100 can establish a communication connection with each terminal device in the terminal cluster, and a communication connection can also be established between each terminal device in the terminal cluster. In other words, the business server 100 can establish a communication connection with each terminal device in the terminal device 200a, the terminal device 200b, the terminal device 200c, ..., the terminal device 200n. For example, a communication connection can be established between the terminal device 200a and the business server 100. A communication connection can be established between the terminal device 200a and the terminal device 200b, and a communication connection can also be established between the terminal device 200a and the terminal device 200c. Among them, the above-mentioned communication connection does not limit the connection method, and can be directly or indirectly connected through a wired communication method, or directly or indirectly connected through a wireless communication method, etc., which can be determined according to the actual application scenario, and this application does not limit it here.

[0055] It should be understood that Figure 1 Each terminal device in the terminal cluster shown may be installed with a data evaluation client, the business server 100 may include a data evaluation service, and the business server 100 may interact with each terminal device for data. The data evaluation client may be an independent client, an embedded sub-client integrated in a client (such as a financial client, a social client, etc.), or a web application accessed through a browser, which may be determined according to the actual application scenario and is not limited here.

[0056] After the terminal device establishes a communication connection with the business server 100, the business server 100 can interact with the terminal device for data. For example, the business server 100 can obtain the transaction data associated with the terminal operation object (i.e., the terminal user) through the data evaluation client loaded on the terminal device, and the terminal device can obtain the risk assessment level corresponding to the target object through the business server 100. For example, the business server 100 can obtain a target object set through the terminal device, etc. Among them, the target object set includes N target objects, transaction data associated with N target objects, and hit time differences corresponding to N target objects; N is a positive integer. Among them, the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state. It should be understood that the transaction data associated with the target object may include the identity information, transaction object, transaction amount, transaction area, and transaction time associated with the target object, etc., which can be determined according to the actual application scenario, and this application is not limited here. Further, in the risk assessment model, the business server 100 can identify the risk level corresponding to the N target objects based on the transaction data, and determine the first assessment value corresponding to the N target objects according to the risk level. It should be understood that the risk assessment model is used to perform risk assessment on transaction data associated with any input target object to obtain the risk level for the target object, and then determine the first assessment value of the target object according to the risk level. Among them, the risk level is used to indicate the probability that the target object is determined as a risk object. The higher the risk level, the higher the risk assessment level of the target object, and the lower the risk level, the lower the risk assessment level of the target object. The first assessment value is used to indicate the assessment value of the risk level of the target object in the risk assessment level table. Further, the business server 100 can determine the target fitting function corresponding to the target object set according to the hit time difference corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period. Among them, the validity period is the length of time that the N target objects are in the restricted state. The business server 100 can determine the target risk assessment level corresponding to the N target objects from the risk assessment level table according to the first assessment value and the second assessment value.

[0057] It should be understood that the data evaluation method provided in this application (which may be referred to as the data evaluation method or method for convenience of description) may include quantitative evaluation and qualitative evaluation in the risk assessment level. Among them, the quantitative evaluation is to identify the transaction data associated with the target object through the risk assessment model to obtain the risk level of the target object, and then determine the first evaluation value corresponding to the target object according to the risk level, and the risk assessment level of the target object can be predicted by the first evaluation value. Qualitative evaluation is to introduce the hit time difference, determine the target fitting function corresponding to the target object set according to the hit time difference corresponding to the target object, and then determine the second evaluation value corresponding to the target object through the target fitting function. Among them, the target fitting function can predict the duration of the target object in a restricted state from the time dimension. Further, according to the quantitative evaluation and qualitative evaluation, that is, according to the first evaluation value and the second evaluation value, the target risk assessment level corresponding to the target object can be determined from the risk assessment level table. By adopting the present application, a risk assessment can be conducted on the target object to obtain the corresponding risk assessment level of the target object. The duration that the target object is in a restricted state can also be predicted by introducing a hit time difference, thereby improving the accuracy of the predicted risk assessment level and avoiding the manual prediction of the validity period of the target object in a restricted state by technical personnel based on past experience, thereby reducing the waste of human resources and costs.

[0058] It is understandable that the data evaluation method provided in the embodiment of the present application can be implemented as follows: Figure 1 The service server 100 shown in the figure may also be executed by a terminal device (such as Figure 1 The terminal device 200a, the terminal device 200b, ..., the terminal device 200n shown in the figure can be executed by any one of them), and can also be executed by the terminal device and the service server together. The specific details can be determined according to the actual application scenario and are not limited here. For the convenience of subsequent understanding and explanation, the embodiment of the present application can be Figure 1 The service server 100 shown is taken as an example for description.

[0059] See also Figure 2 , Figure 2 Schematic diagram of a data evaluation method provided in the embodiment of the present application. For ease of understanding, the present application embodiment is described by taking a business server as an example. Figure 1 The business server 100 in the example is described. The embodiment of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, software development, etc. Figure 2 In the data evaluation method shown in FIG. 1 , each step of the data evaluation method can be performed by Figure 1 The business server 100 in the embodiment is used to execute, for example Figure 2 As shown, the data evaluation method may at least include the following steps S101 to S104.

[0060] Step S101, obtain a target object set, the target object set includes N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state.

[0061] In some feasible implementations, the business server may obtain the first business data through the terminal device. The first business data includes S first business objects, transaction data associated with the S first business objects, and the first hit time corresponding to the S first business objects. The first hit time is the timestamp when the S first business objects are determined as risk objects, and S is a positive integer. It should be understood that the first business object may be a business object determined as a risk object by the assessment agency, and the assessment agency may perform risk assessment on the business object and integrate the transaction data associated with the risk object. After obtaining the risk object, the assessment agency may generate a risk list based on the transaction data associated with the risk object, and synchronize the risk list to the data assessment client loaded on the terminal device, so that the business server can obtain the risk list through the data assessment client loaded on the terminal device. The business server can obtain the risk list synchronized by the assessment agency through the terminal device, and determine the timestamp of the risk list obtained as the first hit time, that is, the timestamp when the first business object is determined as a risk object. It should be understood that the business server may obtain the risk list from the assessment agency from time to time through the data assessment client loaded on the terminal device, and integrate the risk list to obtain the first business data. Exemplarily, the business server obtains the timestamp of account 1 as May 1, 2023 through the terminal device, that is, May 1, 2023 is the first hit time corresponding to account 1, and the timestamp of account 2 can also be obtained as May 2, 2023, that is, May 2, 2023 is the first hit time corresponding to account 2. The business server can determine the above account 1 as the first business object A, determine account 2 as the first business object B, and integrate the transaction data associated with the first business object A, the first hit time corresponding to the first business object A, the transaction data associated with the first business object B, and the first hit time corresponding to the first business object B to obtain the first business data.

[0062] Specifically, please refer to Table 1, which is a transaction data table of the first business data. As shown in Table 1, the first business data includes 7 first business objects and the first hit time corresponding to each first business object. As shown in Table 1, the first business data may include object information and the first hit time corresponding to the first business object A, the first business object B, the first business object C, the first business object D, the first business object E, the first business object F and the first business object G, respectively.

[0063] First Business Data First business object First hit time Object Information A 20230501 Object Information B 20230502 Object Information C 20230501 Object Information D 20230505 Object Information E 20230501 Object Information F 20230505 Object Information G 20230506

[0064] Table 1

[0065] Further, the business server can obtain the second business data associated with the enterprise to be evaluated, and the second business data includes M second business objects, transaction data associated with M second business objects, and the second hit time corresponding to the M second business objects. Among them, the second hit time is the timestamp when the M second business objects are determined to be in a restricted state, and M is a positive integer. It should be understood that the enterprise to be evaluated is an enterprise that needs to conduct risk assessment on the customers associated with the enterprise, that is, the transaction data of the customers associated with the above-mentioned enterprise can be obtained through the data evaluation client. It should be understood that the above-mentioned second business object can be the customer associated with the above-mentioned enterprise to be evaluated. The business object can be registered in the data evaluation client according to the identity information (such as object information) to obtain the account associated with the business object. The business object can complete the transaction task in the data evaluation client according to the account, and the data evaluation client can store the transaction data of the registered business object. It should be understood that in the specific implementation of the present application, it involves user information and other related data. When the embodiment of the present application is applied to a specific product or technology, it is necessary to obtain user permission or consent, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant region.

[0066] See also Figure 3 , Figure 3 Schematic diagram of a scenario of the data evaluation method provided in the embodiment of the present application. Figure 3 As shown, interface 1 and interface 2 may be interfaces of the terminal device at different times. As shown in interface 1, the business server may return a transaction list of business objects associated with the data evaluation client to the terminal device, so that the terminal device displays the above transaction list to the operation object. Among them, the above transaction list may include the accounts and transaction data of each business object. When the operation object needs to view the transaction data of any account, such as when the operation object needs to view the transaction data of account 2, the operation object may click on the expansion control 201a. When the business server detects the operation object's operation request for the expansion control 201a, the business server returns interface 2 to the operation object, so that the terminal device jumps to interface 2. As shown in interface 1, the business server may return a transaction list of business objects associated with the data evaluation client to the terminal device, so that the terminal device jumps to interface 2. Figure 3 As shown, the terminal device displays the transaction data associated with account 2 to the operation object through interface 2. For example, the transaction data associated with account 2 may include whether it is in a restricted state, the second hit time, the transaction amount, the transaction time, and the transaction location.

[0067] Furthermore, the business server can obtain M second business objects in a restricted state through a data evaluation client loaded on a terminal device, and the business server obtains the second business data based on the M second business objects, the transaction data associated with the M second business objects, and the second hit times corresponding to the M second business objects. It should be understood that the business object associated with the data evaluation client can be a business object in an unrestricted state, or a second business object in a restricted state. Specifically, please refer to Table 2, which is a transaction data table of the second business data. As shown in Table 2, the second business data may include object information and the second hit time corresponding to the second business object A, the second business object B, the second business object D, the second business object E, the second business object F, the second business object G, the second business object H, and the second business object I, respectively.

[0068] Second business data Second business object Second hit time Object Information A 20230502 Object Information B 20230502 Object Information D 20230507 Object Information E 20230505 Object Information F 20230505 Object Information G 20230506 Object Information H 20230506 Object Information I 20230507

[0069] Table 2

[0070] Further, the business server can determine N target objects from the second business data based on the object information included in the transaction data associated with the S first business objects, and determine the hit time difference corresponding to the N target objects based on the first hit time and the second hit time corresponding to the N target objects. Among them, the S first business objects and the M second business objects include N target objects. Among them, N is a positive integer less than or equal to S and less than or equal to M. It should be understood that the process in which the above-mentioned business server determines N target objects from the second business data based on the object information included in the transaction data associated with the S first business objects is that the business server determines the business object with the same object information from the first business data and the second business data, and determines the business object as the target object. For example, the business server can determine that the second business object A in the second business data is the target object based on the object information of the first business object A, and record the target object as target object A.

[0071] As shown in Table 1, the first business data includes 7 first business objects and a first hit time corresponding to each first business object. As shown in Table 2, the second business data includes 8 second business objects and a second hit time corresponding to each second business object. The business server can determine 6 target objects from the second business data according to the object information corresponding to the 7 first business objects in Table 1, that is, the business server determines the second business object A, the second business object B, the second business object D, the first business object E, the first business object F and the first business object G in the second business data as the target object A, the target object B, the target object D, the target object E, the target object F and the target object G respectively according to the object information corresponding to the first business object A, the first business object B, the first business object D, the first business object E, the first business object F and the first business object G respectively. It should be understood that the first business object A and the second business object A have the same object information, ..., and the first business object G and the second business object G have the same object information. Furthermore, the business server can determine the hit time difference corresponding to each target object according to the first hit time and the second hit time corresponding to the target object, that is, the difference between the first hit time and the second hit time corresponding to each target object. The second hit time of each target object is the same as the first hit time, or the second hit time is after the first hit time.

[0072] Furthermore, the business server can generate a target object set based on the N target objects, the transaction data associated with the N target objects, and the hit time differences corresponding to the N target objects. Exemplarily, the business server can generate a target object set based on the above-mentioned 6 target objects, the transaction data associated with the 6 target objects, and the hit time differences corresponding to the 6 target objects. Please refer to Table 3, which is a hit time difference data table for target objects. As shown in Table 3, the above-mentioned hit time difference data table includes target objects with the same object information obtained from the first business data and the second business data, as well as the first hit time corresponding to the target object in the first business data, the second hit time corresponding to the target object in the second business data, and the difference between the second hit time corresponding to the target object and the first hit time, that is, the hit time difference.

[0073] Target object collection Target audience First hit time Second hit time Hit time difference / day Object Information A 20230501 20230502 1 Object Information B 20230502 20230502 0 Object Information D 20230505 20230507 2 Object Information E 20230501 20230502 1 Object Information F 20230505 20230505 0 Object Information G 20230506 20230506 0

[0074] Table 3

[0075] Step S102: In the risk assessment model, the risk levels corresponding to the N target objects are identified based on the transaction data, and the first assessment values ​​corresponding to the N target objects are determined according to the risk levels.

[0076] In some feasible implementations, the business server can identify the risk levels corresponding to N target objects based on the transaction data in the risk assessment model, and determine the first assessment values ​​corresponding to the N target objects based on the risk levels. The risk assessment model is used to characterize the transaction data associated with the target object, and then perform risk assessment on the target object based on the transaction features obtained after the characterization process to identify the risk level corresponding to the target object. The risk level can be the probability value of the target object being determined as a risk object. It should be understood that the risk assessment model can be trained based on sample data containing transaction data associated with risk objects and transaction data associated with non-risk objects. The ratio of the number of risk objects to the number of non-risk objects is the initial ratio value.

[0077] Further, the business server can determine the first assessment value corresponding to the N target objects according to the risk level. Please refer to Table 4, which is a risk assessment level table provided in an embodiment of the present application. It should be understood that the present application does not limit the division of risk assessment levels, the first assessment value, the validity period, and the second assessment value in the risk assessment level table, that is, the division of risk assessment levels, the first assessment value, the validity period, and the second assessment value can be specifically determined according to the actual application scenario. As shown in Table 4, the risk assessment level table can include 5 risk assessment levels, namely high risk, relatively high risk, medium risk, relatively low risk, and low risk, and also includes the first assessment value interval, validity period, and second assessment value corresponding to each risk assessment level.

[0078] Risk Assessment Level The first evaluation value interval Validity period T / year Second evaluation value High risk (800，1000] T≥3 100 Higher risk (600，800] 3＞T≥2.5 80 Medium risk (400，600] 2.5＞T≥2 60 Lower risk (200，400] 1.5＞T≥1 40 Low risk (0，200] 1＞T≥0.5 20

[0079] Table 4

[0080] Specifically, after identifying the risk level p corresponding to the target object, the business server can determine the scoring formula corresponding to the risk assessment grade table according to the initial ratio value and the target change value. Among them, the initial ratio value is the ratio of the number of risk objects to the number of non-risk objects used to train the risk assessment model, and the target change value is the difference between the evaluation value corresponding to the initial ratio value and the evaluation value corresponding to the target ratio value when the initial ratio value changes to the target ratio value. It should be understood that the initial ratio value, the target change value and the scoring formula corresponding to the risk assessment grade table can be determined according to the actual application scenario, and the present application does not limit it here. For example, the scoring formula corresponding to the risk assessment grade table can be determined according to Formula 1, that is,

[0081] Score=A+B*log(Odds) (1)

[0082] Among them, Odds is the risk ratio corresponding to the target object, and Score is the evaluation value corresponding to the risk ratio of the target object when it is Odds. Odds can be determined according to Formula 2, that is,

[0083]

[0084] Among them, A and B are constants, and A and B can be determined by the initial ratio value and the target change value. The constants of A and B can be determined according to Formula 3 and Formula 4, that is,

[0085] Score1=A+B*log(X) (3)

[0086] Score2+PDO=A+B*log (2X) (4)

[0087] For example, if the initial ratio value X=0.25, that is, the ratio of the number of risk objects to the number of non-risk objects used to train the risk assessment model is 1:4, the expected initial ratio value is 0.25 and the corresponding evaluation value Score1=500, that is, the expected initial ratio value is 0.25 and the corresponding evaluation value is half of the first evaluation value in the risk assessment level table. If the initial ratio value X changes to the target ratio value 2X, such as when the initial ratio value changes from 0.25 to the target ratio value 0.5, the difference between the evaluation value corresponding to the target ratio value 0.5 and the evaluation value corresponding to the initial ratio value 0.25 is PDO=50, that is, Score2=Score1+PDO. Substituting formula 3 and formula 4 into formula 5 and formula 6, the parameters A and B contained in the scoring formula can be determined according to formula 5 and formula 6, that is,

[0088] 500=A+B*log (0.25) (5)

[0089] 500+50=A+B*log (0.5) (6)

[0090] Furthermore, after obtaining the scoring formula corresponding to the risk assessment level table, the business server may determine the first assessment value corresponding to the target object according to the risk level corresponding to the target object and the scoring formula.

[0091] Step S103, according to the hit time differences corresponding to the N target objects, determine the target fitting function corresponding to the target object set, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state.

[0092] In some feasible implementations, the business server can determine the number of target objects corresponding to each hit time difference based on the N target objects and the hit time differences corresponding to the N target objects. The business server can draw a bar chart based on the number of target objects corresponding to each hit time difference, that is, the business server can use each hit time difference as an independent variable and the number of target objects corresponding to each hit time difference as a dependent variable to determine the target fitting function type. Further, the business server can determine the function parameters of the target fitting function type in the least squares method based on each hit time difference and the number of target objects corresponding to each hit time difference, and determine the target fitting function type containing the function parameters as the target fitting function corresponding to the target object set. It should be understood that the above-mentioned target fitting function type can be a linear polynomial, a multi-time polynomial, an exponential function, a power function, etc., which can be specifically determined according to the actual application scenario, and this application is not limited here.

[0093] Furthermore, after the business server determines the target fitting function corresponding to the target object set, the target fitting function can be differentiated to obtain the derivative of the target fitting function, and the validity period of the N target objects in the restricted state can be determined according to the derivative of the target fitting function, and then the second evaluation value corresponding to the N target objects can be determined from the risk assessment level table according to the validity period. It should be understood that the target fitting function takes each hit time difference as an independent variable, and takes the number of target objects corresponding to each hit time difference as a dependent variable. Therefore, as the validity period is extended, the business objects that overlap in the first business data and the second business data will be completely in a restricted state. In other words, the validity period is determined when the target fitting function tends to be stable, that is, the validity period can be determined when the derivative of the target fitting function is 0 when the dependent variable is 0.

[0094] Furthermore, the business server determines the target object S from the risk assessment level table according to the validity period. i The corresponding benchmark risk assessment level. Among them, the N target objects include target object S i , i is a positive integer less than or equal to N, and the benchmark risk assessment level is used to determine the target object S i The corresponding target risk assessment level is greater than or equal to the benchmark risk assessment level. Further, the business server can determine the assessment value range associated with the benchmark risk assessment level from the risk assessment level table according to the benchmark risk assessment level, and determine the target object S according to the assessment value range. i Corresponding second evaluation value. For example, if the target object S i The corresponding validity period is 3 years, so the target object S can be determined according to Table 4 i The corresponding baseline risk assessment level is high risk. According to Table 4, when the baseline risk assessment level is high risk, the assessment value range associated with the baseline risk assessment level is (800, 1000], and the target object Si The corresponding second evaluation value is 100.

[0095] Step S104: determining target risk assessment levels corresponding to N target objects from a risk assessment level table according to the first assessment value and the second assessment value.

[0096] In some feasible implementations, the service server may i The corresponding first evaluation value and target object S i The corresponding second evaluation values ​​are summed to obtain the target object S i Corresponding third evaluation value. For example, please refer to Table 3. If the business server determines through step S102 that the first evaluation value corresponding to the target object A is 697, and further determines through step S103 that the validity period of the target fitting function corresponding to the target object set is 3 years, then through Table 4 it can be determined that the second evaluation value corresponding to the target object A is 100, and then it can be determined that the third evaluation value corresponding to the target object A is the sum of the first evaluation value and the second evaluation value, that is, the third evaluation value is 797.

[0097] Furthermore, the service server can compare the target object S i The corresponding third evaluation value and target object S i The size of the target object S corresponding to the minimum evaluation value i The corresponding third evaluation value and target object S i The larger value among the corresponding minimum evaluation values ​​is determined as the target object S i The corresponding fourth assessment value. Among them, the lowest assessment value is the minimum assessment value included in the assessment value range associated with the baseline risk assessment level. Exemplarily, if the validity period is 3 years, the business server can determine that the baseline risk assessment level corresponding to the target object A is high risk according to Table 4, and then determine that the assessment value range associated with the baseline risk assessment level is (800, 1000) according to the first assessment value interval corresponding to the high risk. Among them, the lowest assessment value is the minimum assessment value included in the assessment value range associated with the baseline risk assessment level, that is, the lowest assessment value is 800. Furthermore, the business server determines the minimum assessment value 800 corresponding to the target object A as the fourth assessment value by comparing the third assessment value 797 corresponding to the target object A with the minimum assessment value 800 corresponding to the target object A.

[0098] Furthermore, the service server can compare the target object S i The corresponding highest evaluation value and target object S i The size of the corresponding fourth evaluation value is the target object S i The corresponding highest evaluation value and target object S i The smaller value among the corresponding fourth evaluation values ​​is determined as the target object S iThe corresponding predicted evaluation value is used to determine the target object S from the risk assessment level table according to the predicted evaluation value i Corresponding target risk assessment level. Among them, the maximum assessment value is the maximum assessment value included in the assessment value range associated with the baseline risk assessment level. Exemplarily, if the validity period is 3 years, the business server can determine that the baseline risk assessment level corresponding to the target object A is high risk according to Table 4, and then determine that the assessment value range associated with the baseline risk assessment level is (800, 1000) according to the first assessment value interval corresponding to the high risk. Among them, the highest assessment value is the maximum assessment value included in the assessment value range associated with the baseline risk assessment level, that is, the highest assessment value is 1000. Further, the business server determines the fourth assessment value 800 corresponding to the target object A as the predicted assessment value corresponding to the target object A by comparing the fourth assessment value 800 corresponding to the target object A with the highest assessment value 1000 corresponding to the target object A. Further, the business server can determine from the risk assessment level table that the target risk assessment level corresponding to the target object A is high risk according to the predicted assessment value corresponding to the target object A being 800.

[0099] It is understandable that in the risk assessment model, the risk level corresponding to the target object can be identified based on the transaction data, and then the first assessment value corresponding to the target object can be determined according to the risk level. Further, according to the hit time difference corresponding to the target object, the target fitting function corresponding to the target object set is determined, the validity period of the target object in the restricted state is determined according to the target fitting function, and the second assessment value corresponding to the target object is determined from the risk assessment level table according to the validity period. Finally, according to the first assessment value and the second assessment value, the target risk assessment level corresponding to the target object is determined from the risk assessment level table. With the present application, risk assessment can be performed on each target object in the target object set, and the hit time difference of the target object can also be introduced, and the validity period of the target object in the restricted state is determined in combination with the hit time difference of the target object. On the basis of obtaining the first assessment value corresponding to the target object, the second assessment value corresponding to the target object determined in combination with the validity period is finally determined from the risk assessment level table according to the first assessment value and the second assessment value. The target object can be risk assessed from multiple angles and in all aspects, which improves the accuracy of predicting the risk assessment level, and can also avoid the technicians from manually predicting the validity period of the target object in the restricted state based on previous experience, reducing the waste of human resources and costs.

[0100] See also Figure 4 , Figure 4 is another flow chart of the data evaluation method provided in the embodiment of the present application. The data evaluation method can be executed by a computer device, and the computer device may include Figure 1The terminal device or service server 100, for the convenience of subsequent understanding and description, the embodiment of the present application may be Figure 1 The business server 100 shown in FIG. 1 is used as an example for explanation. The process of the business server determining the second evaluation values ​​corresponding to the N target objects is as follows: Figure 4 As shown, the data evaluation method may at least include the following steps S201 to S206.

[0101] Step S201, obtain a target object set, the target object set includes N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state.

[0102] Step S202: In the risk assessment model, the risk levels corresponding to the N target objects are identified based on the transaction data, and the first assessment values ​​corresponding to the N target objects are determined according to the risk levels.

[0103] The specific implementation of step S201 and step S202 can be found in the above Figure 2 The steps S101 and S102 in the corresponding embodiment will not be described in detail here.

[0104] Step S203, determining the number of target objects corresponding to each hit time difference according to the N target objects and the hit time differences corresponding to the N target objects.

[0105] In some feasible implementations, the business server may determine the number of target objects corresponding to each hit time difference based on the N target objects and the hit time differences corresponding to the N target objects. Exemplarily, as shown in Table 3, when the hit time difference is 0 days, the number of corresponding target objects is 3, namely target object B, target object F, and target object G; when the hit time difference is 1 day, the number of corresponding target objects is 2, namely target object A and target object E; when the hit time difference is 2 days, the number of corresponding target objects is 1, namely target object D.

[0106] Step S204: determining a target fitting function corresponding to the target object set according to each hit time difference and the number of target objects corresponding to each hit time difference.

[0107] In some feasible implementations, the business server can use each hit time difference as an independent variable and the number of target objects corresponding to each hit time difference as a dependent variable to determine the target fitting function type. In other words, the business server can convert the hit time difference and the number of target objects corresponding to the hit time difference into a bar graph to obtain the distribution of the target objects on the hit time difference. For example, the business server can convert the hit time difference and the number of target objects corresponding to each hit time difference shown in Table 3 into a bar graph. See Figure 5 , Figure 5 : is a data schematic diagram of the data evaluation method provided in the embodiment of the present application. The X-axis is the hit time difference (days), and the Y-axis is the number of target objects (pieces). Figure 5 As shown, according to the distribution of the target object in the hit time difference, an exponential function can be used as the target fitting function type of the curve fitting, that is, the target fitting function type can refer to Formula 7, that is,

[0108] y=a*e bx +c (7)

[0109] Among them, e is a natural constant, and its value is about 2.71828, and a, b and c are function parameters of the target fitting function type. The business server can determine the function parameters of the target fitting function type in the least squares method according to each hit time difference and the number of target objects corresponding to each hit time difference, that is, a, b and c in Formula 7. Further, the business server can determine the target fitting function type containing function parameters as the target fitting function corresponding to the target object set. Among them, the method used for curve fitting can refer to the least squares method, which will not be elaborated here. Exemplarily, the function parameters a, b and c in Formula 7 can be determined according to actual data, that is, the target fitting function can refer to Formula 8, that is

[0110] y=75.79455357325112*e -0.16067559041796947*x +2.377895856494774 (8)

[0111] Step S205, deriving the target fitting function to obtain the derivative of the target fitting function, determining the validity period of the N target objects in the restricted state according to the derivative of the target fitting function, and determining the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period.

[0112] In some feasible implementations, the service server may derive the target fitting function to obtain the derivative of the target fitting function. Figure 5As shown, as the validity period increases, the longer the hit duration is, the number of target objects corresponding to the hit duration gradually approaches 0, that is, the distribution of target objects on the hit time difference gradually tends to be stable, and at this time y=0 in Formula 7. Therefore, by deriving the target fitting function, it can be obtained that the time corresponding to when the number of target objects infinitely tends to 0 is the duration of the validity period. Exemplarily, according to the derivative of the target fitting function, that is, according to the derivative of Formula 8, it can be determined that the validity period corresponding to each target object in the data is 3 years.

[0113] Furthermore, the business server determines the target object S from the risk assessment level table according to the validity period. i The corresponding benchmark risk assessment level. Among them, the target object S i is the N target objects included in the target object set. For example, as shown in Table 3, the target object S i It can be any one of target object A, target object B, target object D, target object E, target object F and target object G. For example, the first evaluation value corresponding to target object A is 697, and the validity period corresponding to target object A is 3 years. According to Table 4, the benchmark risk assessment level corresponding to target object A is high risk. Further, the business server can determine the assessment strategy according to the benchmark risk assessment level, that is, the target risk assessment level corresponding to target object A shall not be lower than high risk, that is, the target risk assessment level corresponding to target object A is greater than or equal to high risk.

[0114] Furthermore, the business server may determine the evaluation value range associated with the benchmark risk assessment level from the risk assessment level table according to the benchmark risk assessment level, and determine the target object S according to the evaluation value range. i For example, if the baseline risk assessment level corresponding to target object A is high risk, then as shown in Table 4, the assessment value range associated with high risk is (800, 1000], and the second assessment value corresponding to target object A is 100.

[0115] Step S206: determining target risk assessment levels corresponding to the N target objects from the risk assessment level table according to the first assessment value and the second assessment value.

[0116] In some feasible implementations, the process of the business server determining the target risk assessment levels corresponding to N target objects from the risk assessment level table according to the first assessment value and the second assessment value can be seen in Formula 9, that is,

[0117] Prediction evaluation value = min (highest evaluation value, max (third evaluation value, lowest evaluation value)) (9)

[0118] Among them, the third evaluation value is the sum of the first evaluation value and the second evaluation value, the lowest evaluation value is the minimum evaluation value included in the evaluation value range associated with the benchmark risk assessment level, and the highest evaluation value is the maximum evaluation value included in the evaluation value range associated with the benchmark risk assessment level. For example, the first evaluation value corresponding to the target object A is 697, and the benchmark risk assessment level corresponding to the target object A is high risk. According to Table 4, the evaluation value range associated with the benchmark risk assessment level is (800, 1000], so the lowest evaluation value is 800 and the highest evaluation value is 1000. Therefore, it can be determined that the second evaluation value corresponding to the target object A is 100, and the third evaluation value = 697 + 100 = 797. Further, the third evaluation value and the lowest evaluation value corresponding to the target object A are compared, and the lowest evaluation value with a larger evaluation value is determined as the fourth evaluation value corresponding to the target object A, that is, the fourth evaluation value is 800. Further, the business server can compare the fourth evaluation value and the highest evaluation value corresponding to the target object A, and determine the fourth evaluation value with a smaller evaluation value as the predicted evaluation value corresponding to the target object A, that is, the predicted evaluation value is 800. The business server can determine from the risk assessment level table that the target risk assessment level corresponding to the target object A is high risk according to the predicted evaluation value corresponding to the target object A being 800.

[0119] In an embodiment of the present application, the hit time difference and the number corresponding to the hit time difference can be obtained from the target object set, and then a histogram is obtained according to the hit time difference and the number corresponding to the hit time difference, and a curve fitting is performed on the histogram to obtain a target fitting function corresponding to the target object set. Further, the validity period of the target object in a restricted state is determined according to the target fitting function, and the second evaluation value corresponding to the target object is determined from the risk assessment level table according to the validity period. By introducing the second evaluation value on the basis of the first evaluation value, the target risk assessment level corresponding to the target object is determined from the risk assessment level table according to the first evaluation value and the second evaluation value. With the present application, the hit time difference of the target object can be introduced, and the validity period of the target object in a restricted state can be determined in combination with the hit time difference of the target object. On the basis of obtaining the first evaluation value corresponding to the target object, the second evaluation value corresponding to the target object determined in combination with the validity period is determined, and finally the target risk assessment level corresponding to the target object is determined according to the first evaluation value and the second evaluation value. Therefore, the use of this application can conduct risk assessment on the target object from multiple angles and in all aspects, improve the accuracy of predicting risk assessment levels, and avoid technical personnel from manually predicting the validity period of the target object in a restricted state based on past experience, thereby reducing the waste of human resources and costs.

[0120] Based on the description of the embodiment of the above data evaluation method, the embodiment of the present application also discloses a data evaluation device 1. Figure 6 , Figure 6: is a schematic diagram of the structure of the data evaluation device provided in the embodiment of the present application. In the embodiment of the present application, the device can run the following modules:

[0121] The acquisition module 11 is used to acquire a target object set, the target object set includes N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state;

[0122] A first evaluation module 12, configured to obtain risk levels corresponding to N target objects based on the transaction data, and determine first evaluation values ​​corresponding to the N target objects according to the risk levels;

[0123] The second evaluation module 13 is used to determine the target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second evaluation value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state;

[0124] The rating module 14 is used to determine the target risk assessment levels corresponding to the N target objects from the risk assessment level table according to the first assessment value and the second assessment value.

[0125] The acquisition module 11 includes:

[0126] The acquisition unit 111 is used to acquire first business data, where the first business data includes S first business objects, transaction data associated with the S first business objects, and first hit times corresponding to the S first business objects; the first hit time is a timestamp when the S first business objects are determined to be risk objects; S is a positive integer;

[0127] The acquisition unit 111 is used to acquire second business data associated with the enterprise to be evaluated, where the second business data includes M second business objects, transaction data associated with the M second business objects, and second hit times corresponding to the M second business objects; the second hit time is a timestamp when the M second business objects are determined to be in a restricted state; M is a positive integer;

[0128] The first processing unit 112 is used to determine N target objects from the second business data according to the object information included in the transaction data associated with the S first business objects, and determine the hit time difference corresponding to the N target objects according to the first hit time and the second hit time corresponding to the N target objects; the S first business objects and the M second business objects include the N target objects; N is a positive integer less than or equal to S and less than or equal to M;

[0129] The first processing unit 112 is configured to generate a target object set according to the N target objects, the transaction data associated with the N target objects, and the hit time differences corresponding to the N target objects.

[0130] Wherein, the second evaluation module 13 includes:

[0131] The second processing unit 131 is used to determine the number of target objects corresponding to each hit time difference according to the N target objects and the hit time differences corresponding to the N target objects;

[0132] A target fitting function determining unit 132, configured to determine a target fitting function corresponding to a target object set according to each hit time difference and the number of target objects corresponding to each hit time difference;

[0133] The first evaluation unit 133 is used to derive the target fitting function to obtain the derivative of the target fitting function, determine the validity period of the N target objects in the restricted state according to the derivative of the target fitting function, and determine the second evaluation value corresponding to the N target objects from the risk assessment level table according to the validity period.

[0134] The target fitting function determining unit 132 includes:

[0135] The first processing subunit 1321 is used to determine the target fitting function type by taking each hit time difference as an independent variable and the number of target objects corresponding to each hit time difference as a dependent variable;

[0136] The target fitting function determination subunit 1322 is used to determine the function parameters of the target fitting function type in the least squares method according to each hit time difference and the number of target objects corresponding to each hit time difference, and determine the target fitting function type containing the function parameters as the target fitting function corresponding to the target object set.

[0137] Among them, the N target objects include the target object S i , i is a positive integer less than or equal to N; the first evaluation unit 133 includes:

[0138] The second processing subunit 1331 is used to determine the target object S from the risk assessment level table according to the validity period. i The corresponding baseline risk assessment level; the baseline risk assessment level is used to determine the target object S i The corresponding target risk assessment level is greater than or equal to the benchmark risk assessment level;

[0139] The first evaluation subunit 1332 is used to determine the evaluation value range associated with the baseline risk assessment level from the risk assessment level table according to the baseline risk assessment level, and determine the target object S according to the evaluation value range. i The corresponding second evaluation value.

[0140] The rating module 14 includes:

[0141] The third processing unit 141 is used to process the target object S i The corresponding first evaluation value and target object S i The corresponding second evaluation values ​​are summed to obtain the target object S i a corresponding third evaluation value;

[0142] The third processing unit 141 is used to compare the target object S i The corresponding third evaluation value and target object S i The size of the target object S corresponding to the minimum evaluation value i The corresponding third evaluation value and target object S i The larger value among the corresponding minimum evaluation values ​​is determined as the target object S i The corresponding fourth assessment value; the lowest assessment value is the minimum assessment value included in the assessment value range associated with the benchmark risk assessment level;

[0143] The third processing unit 141 is used to compare the target object S i The corresponding highest evaluation value and target object S i The size of the corresponding fourth evaluation value is the target object S i The corresponding highest evaluation value and target object S i The smaller value among the corresponding fourth evaluation values ​​is determined as the target object S i The corresponding predicted evaluation value is used to determine the target object S from the risk assessment level table according to the predicted evaluation value i The corresponding target risk assessment level; the maximum assessment value is the maximum assessment value included in the assessment value range associated with the benchmark risk assessment level.

[0144] The above device further comprises:

[0145] Processing module 15, used to determine the scoring formula corresponding to the risk assessment grade table according to the initial ratio value and the target change value; the initial ratio value is the ratio of the number of risk objects to the number of non-risk objects used to train the risk assessment model; the target change value is the difference between the evaluation value corresponding to the initial ratio value and the evaluation value corresponding to the target ratio value when the initial ratio value changes to the target ratio value;

[0146] The first evaluation module 12 is specifically configured to determine first evaluation values ​​corresponding to the N target objects according to a scoring formula and risk levels corresponding to the N target objects.

[0147] According to the above Figure 2 The corresponding embodiment, Figure 2The implementation method described in steps S101 to S104 of the data evaluation method shown in FIG. Figure 6 Each module of the device shown in the figure is executed. For example, the above Figure 2 The implementation method described in step S101 of the data evaluation method shown in FIG. Figure 6 In the device shown in FIG. 1 , the acquisition module 11 is used to perform the operation, the implementation method described in step S102 can be performed by the first evaluation module 12, the implementation method described in step S103 can be performed by the second evaluation module 13, and the implementation method described in step S104 can be performed by the rating module 14. The implementation methods performed by the acquisition module 11, the first evaluation module 12, the second evaluation module 13, and the rating module 14 can be referred to in the above Figure 2 The implementation methods provided in each step of the corresponding embodiment will not be repeated here.

[0148] In an embodiment of the present application, the risk level corresponding to the target object can be identified, and the first evaluation value corresponding to the target object can be determined according to the risk level. Furthermore, the target fitting function corresponding to the target object set can be determined according to the hit time difference corresponding to the target object, and then the validity period of each target object in the target object set in a restricted state can be determined according to the target fitting function, and the second evaluation value corresponding to each target object can be determined from the risk assessment level table according to the validity period. The risk assessment level corresponding to the target object can be determined by the first evaluation value and the second evaluation value, and the technician does not need to predict the validity period of the target object based on experience, which reduces labor costs and improves the accuracy of predicting the risk assessment level from the time dimension.

[0149] In an embodiment of the present application, each module in the device shown in the above figure can be separately or all merged into one or several other modules to constitute, or a certain module (or modules) thereof can also be split into multiple smaller modules in function to constitute, which can achieve the same operation without affecting the realization of the technical effect of the embodiment of the present application. The above modules are divided based on logical functions. In practical applications, the function of a module can also be realized by multiple modules, or the function of multiple modules is realized by one module. In other feasible implementations of the present application, the above device can also include other modules. In practical applications, these functions can also be implemented with the assistance of other modules, and can be implemented by the collaboration of multiple modules, which is not limited here.

[0150] See also Figure 7 , Figure 7: is a structural diagram of a computer device provided in an embodiment of the present application, and the computer device may be a terminal device or a server. The computer device 1000 may include: a processor 1001, a network interface 1004 and a memory 1005. In addition, the above-mentioned computer device 1000 may also include: a user interface 1003, and at least one communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Among them, in some embodiments, the user interface 1003 may include a display screen (Display), a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or it may be a non-volatile memory (non-volatile memory), such as at least one disk storage. Optionally, the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001. As Figure 7 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.

[0151] In such Figure 7 In the computer device 1000 shown, the network interface 1004 can provide a network communication function; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0152] Obtain a target object set, the target object set including N target objects, transaction data associated with the N target objects, and hit time differences corresponding to the N target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state;

[0153] In the risk assessment model, the risk levels corresponding to the N target objects are identified based on the transaction data, and the first assessment values ​​corresponding to the N target objects are determined according to the risk levels;

[0154] Determine the target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state;

[0155] According to the first evaluation value and the second evaluation value, target risk assessment levels corresponding to the N target objects are determined from the risk assessment level table.

[0156] It should be understood that the computer device 1000 described in the embodiment of the present application can execute the above Figure 2 , Figure 4 The description of the data evaluation method in the corresponding embodiment can also be performed as described above. Figure 6 The description of the data evaluation device in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of the same method will not be repeated here.

[0157] In addition, it should be pointed out here that: the embodiment of the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program executed by the data evaluation device mentioned above, and when the processor executes the computer program, it can execute the above-mentioned Figure 2 , Figure 4 The description of the data evaluation method in the corresponding embodiment will therefore not be repeated here. In addition, the description of the beneficial effects of the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in the present application, please refer to the description of the method embodiment of the present application. As an example, the computer program can be deployed on a computer device for execution, or executed on multiple computer devices located in one location, or, executed on multiple computer devices distributed in multiple locations and interconnected by a communication network, and multiple computer devices distributed in multiple locations and interconnected by a communication network can constitute a communication system.

[0158] In addition, it should be noted that: the embodiment of the present application also provides a computer program product, which may include a computer program, and the computer program may be stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor may execute the computer program, so that the computer device can execute the above Figure 2 , Figure 4 The description of the data evaluation method in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated here. For technical details not disclosed in the computer program product embodiment involved in this application, please refer to the description of the method embodiment of this application.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0160] The terms "first", "second", etc. in the description, claims, and drawings of the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other step units inherent to these processes, methods, devices, products, or equipment.

[0161] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0162] The method and related apparatus provided by the embodiment of the present application are described with reference to the method flow chart and / or structural diagram provided by the embodiment of the present application. Specifically, each process and / or box in the method flow chart and / or structural diagram, as well as the combination of the processes and / or boxes in the flow chart and / or block diagram, can be implemented by a computer program. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the process. Figure 1 A process or multiple processes and / or structures Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or structures Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.

[0163] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A data evaluation method, characterized in that: The method comprises: Obtain a target object set, the target object set including N target objects, N transaction data associated with the target objects, and N hit time differences corresponding to the target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state; In the risk assessment model, the risk levels corresponding to the N target objects are identified based on the transaction data, and the first assessment values ​​corresponding to the N target objects are determined according to the risk levels; Determine the target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second assessment value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state; According to the first evaluation value and the second evaluation value, target risk assessment levels corresponding to the N target objects are determined from the risk assessment level table.

2. The data evaluation method according to claim 1, characterized in that: The obtaining of the target object set includes: Acquire first business data, where the first business data includes S first business objects, S transaction data associated with the first business objects, and first hit times corresponding to the S first business objects; the first hit time is a timestamp when the S first business objects are determined to be the risk objects; S is a positive integer; Acquire second business data associated with the enterprise to be evaluated, where the second business data includes M second business objects, M transaction data associated with the second business objects, and second hit times corresponding to the M second business objects; the second hit time is a timestamp when the M second business objects are determined to be in a restricted state; M is a positive integer; According to the object information included in the transaction data associated with the S first business objects, N target objects are determined from the second business data, and the hit time differences corresponding to the N target objects are determined according to the first hit time and the second hit time corresponding to the N target objects; the S first business objects and the M second business objects include the N target objects; N is a positive integer less than or equal to S and less than or equal to M; The target object set is generated according to the N target objects, the transaction data associated with the N target objects, and the hit time differences corresponding to the N target objects.

3. The data evaluation method according to claim 1, characterized in that: The method of determining a target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determining a validity period during which the N target objects are in a restricted state according to the target fitting function, and determining a second assessment value corresponding to the N target objects from a risk assessment level table according to the validity period includes: According to the N target objects and the hit time differences corresponding to the N target objects, determine the number of the target objects corresponding to each hit time difference; Determine the target fitting function corresponding to the target object set according to each of the hit time differences and the number of the target objects corresponding to each of the hit time differences; The target fitting function is differentiated to obtain the derivative of the target fitting function, and the validity period of the N target objects in a restricted state is determined according to the derivative of the target fitting function; and the second assessment values ​​corresponding to the N target objects are determined from the risk assessment level table according to the validity period.

4. The data evaluation method according to claim 3, characterized in that: Determining the target fitting function corresponding to the target object set according to each of the hit time differences and the number of the target objects corresponding to each of the hit time differences includes: Taking each of the hit time differences as an independent variable and the number of the target objects corresponding to each of the hit time differences as a dependent variable, determining a target fitting function type; According to each hit time difference and the number of target objects corresponding to each hit time difference, the function parameters of the target fitting function type in the least squares method are determined, and the target fitting function type containing the function parameters is determined as the target fitting function corresponding to the target object set.

5. The data evaluation method according to claim 3, characterized in that: The N target objects include target object S i , i is a positive integer less than or equal to N; said deriving the target fitting function to obtain the derivative of the target fitting function, determining the validity period of the N target objects in the restricted state according to the derivative of the target fitting function, and determining the second assessment values ​​corresponding to the N target objects from the risk assessment level table according to the validity period, including: Determine the target object S from the risk assessment level table according to the validity period i The corresponding baseline risk assessment level; the baseline risk assessment level is used to determine the target object S i The corresponding target risk assessment level is greater than or equal to the baseline risk assessment level; According to the baseline risk assessment level, determine the assessment value range associated with the baseline risk assessment level from the risk assessment level table, and determine the target object S according to the assessment value range. i The corresponding second evaluation value.

6. The data evaluation method according to claim 5, characterized in that: The step of determining target risk assessment levels corresponding to the N target objects from the risk assessment level table according to the first assessment value and the second assessment value includes: For the target object S i The corresponding first evaluation value and the target object S i The corresponding second evaluation values ​​are summed to obtain the target object S i a corresponding third evaluation value; Compare the target object S i The corresponding third evaluation value and the target object S i The size of the target object S corresponding to the minimum evaluation value i The corresponding third evaluation value and the target object S i The larger value among the corresponding minimum evaluation values ​​is determined as the target object S i The corresponding fourth evaluation value; the lowest evaluation value is the minimum evaluation value included in the evaluation value range associated with the baseline risk evaluation level; Compare the target object S i The corresponding highest evaluation value and the target object S i The size of the corresponding fourth evaluation value is the target object S i The corresponding highest evaluation value and the target object S i The smaller value of the corresponding fourth evaluation value is determined as the target object S i The corresponding predicted evaluation value is used to determine the target object S from the risk assessment level table according to the predicted evaluation value. i The corresponding target risk assessment level; the maximum assessment value is the maximum assessment value included in the assessment value range associated with the benchmark risk assessment level.

7. The data evaluation method according to claim 1, characterized in that: In the risk assessment model, before identifying the risk levels corresponding to the N target objects based on the transaction data and determining the first assessment values ​​corresponding to the N target objects according to the risk levels, the method further includes: Determine the scoring formula corresponding to the risk assessment grade table according to the initial ratio value and the target change value; the initial ratio value is the ratio of the number of risk objects to the number of non-risk objects used to train the risk assessment model; the target change value is the difference between the evaluation value corresponding to the initial ratio value and the evaluation value corresponding to the target ratio value when the initial ratio value changes to the target ratio value; The step of obtaining risk levels corresponding to the N target objects based on the transaction data by using a risk assessment model, and determining first assessment values ​​corresponding to the N target objects according to the risk levels, includes: Determine first evaluation values ​​corresponding to the N target objects according to the scoring formula and the risk levels corresponding to the N target objects.

8. A risk assessment device, characterized in that: include: An acquisition module, used to acquire a target object set, the target object set including N target objects, N transaction data associated with the target objects, and N hit time differences corresponding to the target objects; N is a positive integer; the hit time difference is the time difference between the timestamp when the target object is determined to be a risk object and the timestamp when the target object is determined to be in a restricted state; A first evaluation module, configured to obtain risk levels corresponding to the N target objects based on the transaction data, and determine first evaluation values ​​corresponding to the N target objects according to the risk levels; A second evaluation module is used to determine the target fitting function corresponding to the target object set according to the hit time differences corresponding to the N target objects, determine the validity period of the N target objects in the restricted state according to the target fitting function, and determine the second evaluation value corresponding to the N target objects from the risk assessment level table according to the validity period; the validity period is the length of time that the N target objects are in the restricted state; A rating module is used to determine target risk assessment levels corresponding to the N target objects from a risk assessment level table according to the first assessment value and the second assessment value.

9. A computer device, characterized in that: include: Processors, transceivers, memory, and network interfaces; The processor is connected to the transceiver, the memory, and the network interface, wherein the network interface is used to provide a data communication function, the memory is used to store program code, and the processor and the transceiver are used to call the program code to execute the method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded and executed by a processor, so that a computer device having the processor executes the method according to any one of claims 1 to 7.

Images