Behavior detection method and device

Abstract

The embodiment of the invention provides a behavior detection method and device, and the method comprises the steps: obtaining a first credit score, N first sub-credit scores, a second credit score and N second sub-credit scores of a first user, the first credit score and the N first sub-credit scores are obtained through inputting M first feature domains into a credit score model, the second credit score and the N second sub-credit scores are obtained by inputting the M second feature domains into the credit score model. If the first credit score is different from the second credit score, S first sub-credit scores and S second sub-credit scores are determined according to the N first sub-credit scores and the N second sub-credit scores, and according to first feature data in a first feature domain corresponding to the S first sub-credit scores and second feature data in a second feature domain corresponding to the S second sub-credit scores, the S first sub-credit scores and the S second sub-credit scores are determined; at least one piece of target behavior information that causes the first credit score to change relative to the second credit score is determined. Through the method, the user behavior causing credit score change can be accurately determined.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a behavior detection method and device. Background Art

[0002] A user's credit score is an indicator for evaluating a user's credit status. Financial institutions often provide users with corresponding financial services based on their credit scores.

[0003] Currently, most financial companies only display credit scores to users. When the user's behavior information changes, the credit score displayed by the financial company will also change accordingly. However, the credit scores displayed by most financial companies are not interpretable, that is, the financial companies cannot determine which user's behavior information will cause the user's credit score to change. Therefore, when the credit score changes, how to determine the user behavior that caused the credit score change is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a behavior detection method and device for determining user behavior that causes a credit score change.

[0005] In the first aspect, the embodiment of the present application provides a behavior detection method, which can be executed by a processor of a computer device. The method specifically includes the following steps: the processor obtains a first credit score and N first sub-credit scores of a first user, wherein the first credit score and N first sub-credit scores are obtained by inputting M first feature domains of the first user obtained at the first moment into a credit score model, the first credit score is determined based on the N first sub-credit scores, each of the N first sub-credit scores corresponds to at least one first feature domain in the M first feature domains, and each first feature domain includes at least one first feature data; M is an integer greater than 1, and N is an integer greater than or equal to M; the credit score model is trained based on a first data set, and the first data set includes at least one group of M preset feature domains with credit score labels. The processor may also obtain the second credit score and N second sub-credit scores of the first user, wherein the second credit score and the N second sub-credit scores are obtained by inputting the M second feature domains of the first user obtained at the second moment into the credit score model, the second moment is before the first moment, the second credit score is determined based on the N second sub-credit scores, each second sub-credit score in the N second sub-credit scores corresponds to at least one second feature domain in the M second feature domains, and each second feature domain includes at least one second feature data. In the case where the first credit score is different from the second credit score, the processor compares the N first sub-credit scores with the N second sub-credit scores to determine S first sub-credit scores and S second sub-credit scores corresponding to the S first sub-credit scores, the S first sub-credit scores and the S second sub-credit scores are different, wherein S is a positive integer less than or equal to N. The processor then compares the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores to determine at least one target behavior information that causes the first credit score to change relative to the second credit score.

[0006] In the above method, when the credit score of a user changes, the user behavior that caused the credit score change can be accurately determined.

[0007] In one possible design, the processor obtains M first feature domains of the first user at a first moment, which may include: the processor obtains first user data of the first user at a first moment, wherein the first user data includes multiple first feature data; the processor then divides the multiple first feature data based on a preset division rule to obtain M first feature domains.

[0008] In a possible design, the M first feature domains of the first user are obtained by dividing a plurality of first feature data included in the first user data of the first user acquired at the first moment based on a preset division rule.

[0009] In one possible design, the credit score model may include a mapping module, a feature extraction module and a credit score output module; the first credit score and N first sub-credit scores are obtained in the following manner: the processor first inputs at least one first feature data of the M first feature domains into the mapping module to obtain the first feature domain vectors corresponding to the M first feature domains respectively, and the processor then inputs the obtained M first feature domain vectors into the feature extraction module to obtain N first cross vectors, and finally, the processor inputs the N first cross vectors into the credit score output module to obtain the first credit score and N first sub-credit scores.

[0010] In a possible design, the mapping module may include an embedding layer and a first concatenation layer; M first feature domain vectors are obtained in the following manner: for the jth first feature domain among the M first feature domains, where j is an integer that runs through [1, M], the following steps are performed: the processor inputs at least one first feature data in the jth first feature domain into the embedding layer, and determines that at least one first feature data in each first feature domain corresponds to a first feature vector. The processor then concatenates at least one first feature vector in the jth first feature domain based on the first concatenation layer to obtain the first feature domain vector corresponding to the jth first feature domain.

[0011] In one possible design, the feature extraction module may include a feature cross layer, L connection layers and a second splicing layer; wherein L is a non-negative integer; N first cross vectors are obtained in the following manner: the processor inputs M first feature domain vectors into the feature cross layer to obtain N second cross vectors, the processor then inputs the N second cross vectors into the L connection layers to obtain N third cross vectors, and then the processor inputs the N third cross vectors and the M first feature domain vectors into the second splicing layer to obtain N first cross vectors.

[0012] In a possible design, the processor inputs M first feature domain vectors into the feature cross layer to obtain N second cross vectors, which may include: for the jth first feature domain vector among the M first feature domain vectors, the processor performs matrix dot multiplication on the jth first feature domain vector and the jth first feature domain vector to obtain a first type vector corresponding to the jth first feature domain vector, where j is an integer that runs through [1, M], and the processor then determines at least one group of two associated first feature domain vectors based on a preset cross rule, performs matrix dot multiplication on each group of two associated first feature domain vectors, and obtains at least one second type vector. Finally, the first type vector and at least one second type vector corresponding to the jth first feature domain vector are used as N second cross vectors.

[0013] In one possible design, the processor inputs N third cross vectors and M first feature domain vectors into the second splicing layer to obtain N first cross vectors, which may include: for the pth third cross vector among the N third cross vectors, where p is an integer ranging from [1, N], performing the following steps: the processor determines at least one first feature domain vector corresponding to the pth third cross vector as the target feature vector, and then splices the pth third cross vector with at least one target feature domain vector to obtain a first cross vector corresponding to the pth third cross vector.

[0014] In one possible design, the processor compares the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores to determine at least one target behavior information that causes the first credit score to change relative to the second credit score, which may include: for the i-th first sub-credit score among the S first sub-credit scores and the i-th second sub-credit score among the S second sub-credit scores, the i-th first sub-credit score corresponds to the i-th second sub-credit score, and i is an integer ranging from [1, S], performing the following steps: the processor determines at least one first data to be compared, the at least one first data to be compared is the first feature data in at least one first feature domain corresponding to the i-th first sub-credit score, the processor may also determine at least one second data to be compared, the at least one second data to be compared is the second feature data in at least one second feature domain corresponding to the i-th second sub-credit score, and then, the processor determines at least one target behavior information that causes the i-th first sub-credit score to change relative to the i-th second sub-credit score based on the at least one first data to be compared and the at least one second data to be compared.

[0015] In one possible design, the above method may also include: outputting at least one target behavior information that causes the first credit score to change relative to the second credit score.

[0016] In a possible design, the above method may also include at least one of the following: outputting a change in the first credit score relative to the second credit score, or outputting the first credit score.

[0017] In one possible design, the change of the first credit score relative to the second credit score includes at least one of the following: the amount of change of the first credit score relative to the second credit score, or the sign of the change of the first credit score relative to the second credit score.

[0018] In a second aspect, an embodiment of the present application further provides a behavior detection device, which includes units or means for executing each step of the above first aspect.

[0019] In a third aspect, an embodiment of the present application further provides a computer device, comprising a memory and a processor, wherein the memory is used to store programs and data, and the processor is used to run the programs stored in the memory, and execute the method provided in the first aspect according to the data stored in the memory.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer storage medium, in which a computer program is stored. When the computer program is executed by a computer, the computer executes the method provided in the first aspect above.

[0021] In a fifth aspect, an embodiment of the present application further provides a chip, which is used to read a computer program stored in a memory to implement the method in the first aspect above.

[0022] In a sixth aspect, an embodiment of the present application provides a chip system, which includes a processor for supporting a computer device to implement the functions involved in the first aspect. In a possible design, the chip system also includes a memory, which is used to store the necessary programs and data for the computer device. The chip system can be composed of a chip, or it can include a chip and other discrete devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0024] Figure 2 A flow chart of a behavior detection method provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a flow chart of a method for determining M first feature domains provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of the structure of a credit score model provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of a credit score model provided in an embodiment of the present application;

[0028] Figure 6 A flowchart of a method for determining a first credit score and N first sub-credit scores provided in an embodiment of the present application;

[0029] Figure 7 A schematic diagram of a flow chart of a method for determining N first cross vectors provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram of a structure showing a first credit score provided in an embodiment of the present application;

[0031] Fig. 9 A schematic diagram of a structure showing a first credit score provided in an embodiment of the present application;

[0032] Fig.10 A schematic diagram of a structure showing a first credit score provided in an embodiment of the present application;

[0033] Fig.11 A schematic diagram of the structure of a first model provided in an embodiment of the present application;

[0034] Fig.12 A schematic diagram of the structure of a second model provided in an embodiment of the present application;

[0035] Fig.13 A schematic diagram of the structure of a third model provided in an embodiment of the present application;

[0036] Fig.14 A schematic diagram of the structure of a behavior detection device provided in an embodiment of the present application;

[0037] Fig.15 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present application more clear, the present application will be further described in detail below with reference to the accompanying drawings. The specific operation methods, functional descriptions, etc. in the method embodiments can also be applied to the device embodiments or system embodiments.

[0039] In order to better explain the embodiments of the present application, the relevant terms or technologies in the present application are first explained:

[0040] 1. Row Vector

[0041] A row vector is a 1×p matrix, where p is any positive integer, for example: x = [x 1 x 2 …x p ].

[0042] Column vectors

[0043] A column vector is a q×1 matrix, where q is any positive integer, for example:

[0044] Matrix size / scale

[0045] A p×q matrix is ​​a rectangular array of p rows and q columns. For example:

[0046]

[0047] Each number that makes up the matrix is ​​called an element of the matrix. 11 , A 12 , …, A pq etc. are all elements of matrix A. The subscript (or coordinate) of the element is used to indicate the position of the element in the matrix, which can be the row number (or row coordinate) or column number (or column coordinate) of the element in the matrix. 11 The subscript "11" indicates that the element is located in the first row and first column of matrix A. 21 Indicates that the element is located in the second row and first column of matrix A. In addition, the subscript of the element can also have different forms, such as A 11 It can also be written as A 1，1 , A 21 It can also be written as A 2，1 Etc. Similar details will not be repeated below.

[0048] It should be noted that the row number of the starting row of a matrix is ​​not limited to 1, but can also be other values, such as 0. Similarly, the column number of the starting column of the matrix is ​​not limited to 1, but can also be other data such as 0. For example, if the row number of the starting row and the column number of the starting column of the above matrix are 0 and 0 respectively, then the subscript of the first element in the matrix is ​​"00", indicating that the element is in the 0th row and 0th column of the matrix.

[0049] 4. Matrix dot product (element-wise product, entry-wise product)

[0050] Matrix dot product refers to the element-by-element multiplication of two matrices of the same scale (or size, that is, the two matrices have the same number of rows and columns). As shown below, both A and B are p×q matrices. The matrix C is obtained after the matrix dot product of matrix A and matrix B.

[0051]

[0052]

[0053] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0054] Figure 1 The structure diagram of a possible computer device applicable to the behavior detection method provided in the embodiment of the present application is shown. Figure 1 As shown, the computer device includes: a processor 110, a memory 120, a communication module 130, an input unit 140, a display unit 150, a power supply 160 and other components. Those skilled in the art can understand that Figure 1The structure of the computer device shown in the figure does not constitute a limitation on the computer device. The computer device provided in the embodiment of the present application may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0055] Combine the following Figure 1 A detailed introduction to the various components of a computer device:

[0056] The communication module 130 can be connected to other devices by wireless connection or physical connection to realize data transmission and reception of the computer device. Optionally, the communication module 130 can include any one or a combination of a radio frequency (RF) circuit, a wireless fidelity (WiFi) module, a communication interface, a Bluetooth module, etc., which is not limited in the embodiment of the present application.

[0057] The memory 120 may be used to store program instructions and data. The processor 110 executes various functional applications and data processing of the computer device by running the program instructions stored in the memory 120. Among them, the program instructions may enable the processor 110 to execute the behavior detection method provided in the following embodiments of the present application.

[0058] Optionally, the memory 120 may mainly include a program storage area and a data storage area. The program storage area may store an operating system, various application programs, and program instructions, etc.; the data storage area may store various data such as user data of users. In addition, the memory 110 may include a high-speed random access memory, and may also include a non-volatile memory, such as a disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0059] The input unit 140 may be used to receive information such as data or operation instructions input by a user. Optionally, the input unit 140 may include input devices such as a touch panel, function keys, a physical keyboard, a mouse, a camera, and a monitor.

[0060] The display unit 150 can realize human-computer interaction and is used to display information input by the user, information provided to the user, etc. through a user interface. The display unit 150 may include a display panel 151. Optionally, the display panel 151 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0061] Furthermore, when the input unit includes a touch panel, the touch panel may cover the display panel 151. When the touch panel detects a touch event on or near it, it transmits the touch event to the processor 110 to determine the type of the touch event and perform a corresponding operation.

[0062] The processor 110 is the control center of the computer device, and uses various interfaces and lines to connect the above components. The processor 110 can complete various functions of the computer device by executing program instructions stored in the memory 120 and calling data stored in the memory 120 to implement the behavior detection method provided in the embodiment of the present application.

[0063] Optionally, the processor 110 may include one or more processing units. Specifically, the processing unit may include a hardware device such as a CPU and / or a GPU capable of floating-point operations. The processing unit can determine the credit score of the user and output it. When the processor 110 of the computer device implements the behavior detection method, the processing unit reads the user's user data from the storage data area of ​​the memory 120, and outputs the user's credit score based on the user's user data.

[0064] The computer device also includes a power supply 160 (such as a battery) for supplying power to various components. Optionally, the power supply 160 can be logically connected to the processor 110 through a power management system, so that the power management system can realize functions such as charging and discharging of the computer device.

[0065] Although not shown, the computer device may also include components such as a camera, a sensor, and an audio collector, which will not be described in detail here.

[0066] The present application embodiment provides a behavior detection method. Figure 1 The processor in the computer device shown executes. Figure 2 As shown, the process of the method includes:

[0067] S201: The processor obtains a first credit score and N first sub-credit scores of a first user.

[0068] In the embodiment of the present application, the first credit score and the N first sub-credit scores are obtained by inputting the M first feature domains of the first user acquired at the first moment into the credit score model, where M is an integer greater than 1, and N is an integer greater than or equal to M. The first moment may be the current moment, or any moment before the current moment, which is not limited here.

[0069] The present application embodiment provides a method for determining M first feature domains of a first user, which may include: Figure 3 The following steps are shown:

[0070] S301: The processor obtains first user data of a first user at a first moment, where the first user data includes a plurality of first feature data.

[0071] In the embodiment of the present application, each user corresponds to the same multiple user features, and each user feature corresponds to a feature data. User features can be used to describe the user's identity information, behavior information, etc. For example, the user features can be the user's name, age, gender, salary, company, deposit amount, total loan amount, repaid amount, etc., which are not limited here.

[0072] For any user feature, at different times, the feature data corresponding to the user feature of the same user may be the same or different. At the same time, the feature data corresponding to the user feature of different users may be the same or different.

[0073] In order to facilitate user behavior detection, the user's characteristic data can be stored in a database or other storage media. When the user's behavior changes cause the user's characteristic data to change accordingly, the user's characteristic data stored in the database is also updated accordingly.

[0074] In the case where the characteristic data of the user is stored in a database, the processor may access the database at a first moment and obtain a plurality of first characteristic data of the first user from the database.

[0075] For example, Table 1 shows that the processor accesses the database at the first moment and obtains multiple first features and multiple first feature data of the first user “Zhang San”.

[0076] Table 1.

[0077] Name age gender Salary Employment Company Deposit Amount Total loan amount Amount repaid Zhang San 25 male 20 xx Company 0 300 100

[0078] In Table 1, the deposit amount of the first user "Zhang San" is 0. After "Zhang San" deposits 200 into the bank, the deposit amount stored in the database is 200, as shown in Table 2.

[0079] Table 2.

[0080] Name age gender Salary Employment Company Deposit Amount Total loan amount Amount repaid Zhang San 25 male 20 xx Company 200 300 100

[0081] S302: The processor divides the plurality of first feature data based on a preset division rule to obtain M first feature domains.

[0082] In the embodiment of the present application, the preset division rule can be determined based on human experience, or can be determined by other methods, which are not limited here. The preset division rule can make feature data with similar attribute information be divided into the same feature domain.

[0083] For example, the first characteristic data within the scope of personal information can be classified into the same first characteristic domain, for example, the name ("Zhang San"), age ("25"), and gender ("male") are classified into the same first characteristic domain. The first characteristic data within the scope of work can be classified into the same first characteristic domain, for example, the salary ("20") and the company ("xx company") are classified into the same first characteristic domain. The first characteristic data within the scope of funds can be classified into the same first characteristic domain, for example, the deposit amount ("200"), the total loan amount ("300"), and the repaid amount ("100") are classified into the same first characteristic domain.

[0084] It should be understood that a single first feature data may be divided into one first feature domain or into multiple first feature domains. Each first feature domain includes at least one first feature data.

[0085] In the above method, a method for determining M first feature domains is provided, so that the obtained first feature domains can include feature data with similar attribute information.

[0086] In the embodiment of the present application, the credit score model can be trained based on the first data set, wherein the first data set includes at least one set of M preset feature domains with credit score labels. How to determine the structure of the credit score model and how to use the first data set to train the credit score model will be explained later and will not be described in detail here.

[0087] The method for obtaining M preset feature domains is similar to the method for obtaining M first feature domains, and is specifically as follows:

[0088] For any group of M preset feature domains with credit score labels in the first data set, the group of M preset feature domains can be obtained by the following steps: the processor obtains preset user data of any preset user at a third moment, wherein the preset user data includes a plurality of preset feature data, and the processor divides the plurality of preset feature data based on a preset division rule to obtain M preset feature domains. The third moment can be any moment before the first moment.

[0089] In the embodiment of the present application, the structure of the credit score model is as follows: Figure 4As shown, it includes a mapping module, a feature extraction module and a credit score output module. Among them, the mapping module includes an embedding layer and a first splicing layer. The feature extraction module includes a feature cross layer, L connection layers and a second splicing layer, where L is a non-negative integer. The credit score output module includes P connection layers and a fully connected layer, where P is a non-negative integer.

[0090] In order to describe the structure of the credit score model in detail, Figure 5 A detailed example is given in conjunction with the embodiment. The first user corresponds to three first feature domains, namely the first feature domain 1, the first feature domain 2 and the first feature domain 3, wherein the first feature domain 1 includes the name ("Zhang San"), age ("25"), and gender ("male"), the first feature domain 2 includes the salary ("20"), and the company ("xx company"), and the first feature domain 3 includes the deposit amount ("200"), the total loan amount ("300"), and the repaid amount ("100"). The three first feature domains are input into the credit score model, and the credit score model can output the first credit score of the first user and four first sub-credit scores.

[0091] refer to Figure 4 or Figure 5 The credit score model structure in the present application embodiment provides a method for obtaining a first credit score and N first sub-credit scores of a first user, which may include Figure 6 The following steps are shown.

[0092] S601: The processor inputs at least one first feature data of M first feature domains into a mapping module to obtain first feature domain vectors corresponding to the M first feature domains respectively.

[0093] For the jth first feature domain among the M first feature domains, where j is an integer that runs through [1,M], the following steps are performed: the processor first inputs at least one first feature data in the jth first feature domain into the embedding layer, and determines that at least one first feature data in the jth first feature domain corresponds to a first feature vector. The processor then splices at least one first feature vector in the jth first feature domain based on the first splicing layer to obtain a first feature domain vector corresponding to the jth first feature domain. The splicing order of at least one first feature vector in the jth first feature domain is not limited.

[0094] It should be understood that since there are no trainable network parameters for the embedding layer and the first concatenation layer, each of the M first feature domains can use the same embedding layer and the same first concatenation layer. The embedding layer can be a trained word2vec, etc., which is not limited here.

[0095] In an embodiment of the present application, the dimensions of the first feature vectors corresponding to different first feature data are the same. When the number of first feature data included in different first feature domains is the same, the dimensions of the first feature domain vectors corresponding to different first feature domains are the same. When the number of first feature data included in different first feature domains is different, the dimensions of the first feature domain vectors corresponding to different first feature domains are different.

[0096] For example, in Figure 5 In the example, the first feature domain 1 includes three first feature data, namely name ("Zhang San"), age ("25"), and gender ("male"); the first feature domain 2 includes two first feature data, namely salary ("20") and company ("xx company"); the first feature domain 3 includes three first feature data, namely deposit amount ("200"), total loan amount ("300"), and repaid amount ("100"). The first feature domain 1, the first feature domain 2, and the first feature domain 3 are input into the mapping module to obtain three first feature domain vectors, namely, the first feature domain vector 1 corresponding to the first feature domain 1, the first feature domain vector 2 corresponding to the first feature domain 2, and the first feature domain vector 3 corresponding to the first feature domain 3.

[0097] If the dimension of the first feature vector corresponding to each first feature data is 16, since the first feature domain 1 includes 3 first feature data, the dimension of the first feature domain vector 1 is 48; since the first feature domain 2 includes 2 first feature data, the dimension of the first feature domain vector 2 is 32; since the first feature domain 3 includes 3 first feature data, the dimension of the first feature domain vector 3 is 48.

[0098] S602: The processor inputs the obtained M first feature domain vectors into a feature extraction module to obtain N first cross vectors.

[0099] The embodiment of the present application provides a method for obtaining N first cross vectors, which may include: Figure 7 The following steps are shown:

[0100] S701: The processor inputs M first feature domain vectors into a feature cross layer to obtain N second cross vectors.

[0101] The embodiment of the present application provides a method for obtaining N second cross vectors, which may include the following steps: for the jth first feature domain vector among the M first feature domain vectors, the processor performs matrix dot multiplication on the jth first feature domain vector and the jth first feature domain vector to obtain a first type vector corresponding to the jth first feature domain vector. The processor then determines at least one group of two associated first feature domain vectors based on a preset cross rule, and performs matrix dot multiplication on each group of two associated first feature domain vectors to obtain at least one second type vector. Finally, the processor uses the first type vector and at least one second type vector corresponding to the jth first feature domain vector as N second cross vectors.

[0102] In an embodiment of the present application, the preset intersection rule is determined based on the first data set. The preset intersection rule can be determined based on multiple groups of M preset feature domains with credit score labels in the first data set, or it can be determined based on a group of M preset feature domains with credit score labels in the first data set. The preset intersection rule includes at least one group of identifiers of two associated preset feature domains. The processor can obtain the identifiers of at least one group of two associated preset feature domains from the preset intersection rule, and determine the identifiers of the two preset feature domains associated with at least one group, and the corresponding at least one group of two associated first feature domain vectors. The processor then performs matrix dot multiplication on each group of two associated first feature domain vectors to obtain at least one second type vector.

[0103] For example, the preset crossover rule includes <preset feature domain 2, preset feature domain 3>. Figure 5 In , after the processor inputs three first feature domain vectors (first feature domain vector 1, first feature domain vector 2 and first feature domain vector 3) into the feature cross layer, the processor can perform matrix dot product of first feature domain vector 1 and first feature domain vector 1 to obtain second cross vector 1. The processor then performs matrix dot product of first feature domain vector 2 and first feature domain vector 2 to obtain second cross vector 2. The processor then performs matrix dot product of first feature domain vector 3 and first feature domain vector 3 to obtain second cross vector 3. Then, the processor obtains a group of identifiers of two associated preset feature domains from the preset cross rule, namely preset feature domain 2 and preset feature domain 3, and determines two associated first feature domain vectors, namely first feature domain vector 2 and first feature domain vector 3, according to the identifiers of the group of two associated preset feature domains. The processor performs matrix dot product of first feature domain vector 2 and first feature domain vector 3 to obtain second cross vector 4. Therefore, the processor inputs the three first feature domain vectors Figure 5 The feature cross layer in , four second cross vectors can be obtained, namely second cross vector 1, second cross vector 2, second cross vector 3 and second cross vector 4.

[0104] In the embodiment of the present application, when performing matrix dot multiplication on two associated first feature domain vectors, if the dimensions of the two associated first feature domain vectors are the same, the two associated first feature domain vectors can be directly matrix dot multiplied; if the dimensions of the two associated first feature domain vectors are different, the first preset length is intercepted from the two associated first feature domain vectors, and then the matrix dot multiplication is performed. Generally speaking, the first preset length can be determined based on the first feature domain vector with a smaller dimension of the two associated first feature domain vectors.

[0105] For example, the dimension of the first feature domain vector 2 is 32, and the dimension of the first feature domain vector 3 is 48. When the processor performs matrix dot product on the first feature domain vector 2 and the first feature domain vector 3, since the dimensions of the first feature domain vector 2 and the first feature domain vector 3 are different, the dimension 32 of the first feature domain vector 2 is smaller than the dimension 48 of the first feature domain vector 3. Therefore, the processor can set the first preset length to 32. The processor can intercept 32 dimensions from the first feature domain vector 3 as a temporary feature domain vector, and then perform matrix dot product on the first feature domain vector 2 and the temporary feature domain vector to obtain the second cross vector 4.

[0106] It should be understood that when truncating the first preset length of the first feature domain vector, the first preset length can be truncated from the first half of the first feature domain vector as a temporary feature domain vector, or the first preset length can be truncated from the second half of the first feature domain vector as a temporary feature domain vector, or the first preset length can be randomly truncated from the first feature domain vector as a temporary feature domain vector, which is not limited here.

[0107] In the above method, each first feature domain vector has a strong correlation with itself. In addition, two associated first feature domain vectors can be determined according to a preset crossover rule. The feature crossover layer performs matrix dot multiplication of the first feature domain vector with itself and matrix dot multiplication of the two associated first feature domain vectors, so as to obtain more and more detailed features between each first feature domain vector.

[0108] The following describes how to determine a preset crossover rule based on a set of M preset feature domains with credit score labels in the first data set.

[0109] The processor can obtain any group of M preset feature domains with credit score labels in the first data set, and obtain the rth preset feature domain and the sth preset feature domain from the M preset feature domains, where r is an integer that runs through [1, M], s is an integer that runs through [1, M], r and s are different, the rth preset feature domain is used as the first preset feature domain, the sth preset feature domain is used as the second preset feature domain, and the first similarity between the first preset feature domain and the second preset feature domain is calculated. If the first similarity is greater than the first similarity value, the association relationship between the first preset feature domain and the second preset feature domain is added to the preset intersection rule; if the first similarity is less than or equal to the first similarity value, no processing is performed.

[0110] For example, the first data set includes a group of three preset feature domains with credit score labels, namely preset feature domain 1, preset feature domain 2 and preset feature domain 3. The processor can calculate the first similarity between preset feature domain 1 and preset feature domain 2, the first similarity between preset feature domain 1 and preset feature domain 3, and the first similarity between preset feature domain 2 and preset feature domain 3. If the first similarity between preset feature domain 1 and preset feature domain 2 is less than the first similarity value, no processing is performed; if the similarity between preset feature domain 1 and preset feature domain 3 is less than the first similarity value, no processing is performed; if the similarity between preset feature domain 2 and preset feature domain 3 is greater than the first similarity value, the association relationship between preset feature domain 2 and preset feature domain 3 is added to the preset intersection rule.

[0111] After the above calculations, the preset crossover rules may include the following:

[0112] <Preset feature domain 2, preset feature domain 3>

[0113] The method for determining the preset intersection rules based on multiple groups of M preset feature domains with credit score labels in the first data set is similar to the method for determining the preset intersection rules based on one group of M preset feature domains with credit score labels in the first data set, and will not be repeated here.

[0114] In an embodiment of the present application, the first similarity between the first preset feature domain and the second preset feature domain can be determined based on the calculation formula of cosine similarity. The processor can first determine the first preset feature domain vector A corresponding to the first preset feature domain and the second preset feature domain vector B corresponding to the second preset feature domain based on the embedding layer and the first splicing layer, wherein the dimensions of the first preset feature domain vector A and the second preset feature domain vector B are both n. By calculating the similarity of the first preset feature domain vector A and the second preset feature domain vector B, the first similarity between the first preset feature domain and the second preset feature domain is determined. The similarity of the first preset feature domain vector A and the second preset feature domain vector B can be determined using formula (1):

[0115] Wherein, cos(A,B) represents the similarity between the first preset feature domain vector A and the second preset feature domain vector B, a k represents the k-th dimension feature in the first preset feature domain vector A, b k Represents the k-th dimension feature in the second preset feature domain vector B.

[0116] It should be understood that the first similarity between the first preset feature domain and the second preset feature domain may also be determined in other ways, which are not limited here.

[0117] In the embodiment of the present application, since there are no trainable network parameters in the feature cross layer, the M first feature domain vectors can use the same feature cross layer.

[0118] S702: The processor inputs N second cross vectors to L connection layers to obtain N third cross vectors.

[0119] In the embodiment of the present application, since the connection layer in the feature extraction module has trainable network parameters, the N second cross vectors do not share the same connection layer. Therefore, each second cross vector corresponds to L connection layers, and the network parameters in the L connection layers corresponding to different second cross vectors are not the same.

[0120] S703: The processor inputs the N third cross vectors and the M first feature domain vectors into the second concatenation layer to obtain N first cross vectors.

[0121] In an embodiment of the present application, for the pth third cross vector among N third cross vectors, where p is an integer spanning [1, N], the following steps are performed: the processor determines at least one first feature domain vector corresponding to the pth third cross vector as the target feature vector, concatenates the pth third cross vector with the at least one target feature domain vector, and obtains the first cross vector corresponding to the pth third cross vector.

[0122] For example, in Figure 5 In the example, the third cross vector 1 is only related to the first feature domain vector 1, so the target feature vector corresponding to the third cross vector 1 is the first feature domain vector 1. The processor concatenates the third cross vector 1 and the first feature domain vector 1 to obtain the first cross vector 1 corresponding to the third cross vector 1.

[0123] The third cross vector 2 is only related to the first feature domain vector 2, so the target feature vector corresponding to the third cross vector 2 is the first feature domain vector 2. The processor concatenates the third cross vector 2 and the first feature domain vector 2 to obtain the first cross vector 2 corresponding to the third cross vector 2.

[0124] The third cross vector 3 is only related to the first feature domain vector 3, so the target feature vector corresponding to the third cross vector 3 is the first feature domain vector 3. The processor concatenates the third cross vector 3 and the first feature domain vector 3 to obtain the first cross vector 3 corresponding to the third cross vector 3.

[0125] The third cross vector 4 is related to the first feature domain vector 2 and the first feature domain vector 3, so the target feature vector corresponding to the third cross vector 4 is the first feature domain vector 2 and the first feature domain vector 3. The processor concatenates the third cross vector 4, the first feature domain vector 2 and the first feature domain vector 3 to obtain the first cross vector 4 corresponding to the third cross vector 4.

[0126] In the embodiment of the present application, since there are no trainable network parameters in the second concatenation layer, the N third cross vectors can use the same second concatenation layer.

[0127] S603: The processor inputs the N first cross vectors into a credit score output module to obtain a first credit score and N first sub-credit scores.

[0128] In the embodiment of the present application, the processor inputs N first cross vectors into P connection layers to obtain N reference scores, and then inputs the N reference scores into the fully connected layer to obtain a first credit score and N first sub-credit scores. The first credit score is determined based on the N first sub-credit scores, that is, the sum of the N first sub-credit scores can be used as the first credit score.

[0129] In one possible implementation, the fully connected layer includes N fully connected layer parameters, which are fully connected layer parameters 1, ..., and fully connected layer parameters N. After the N reference scores are input into the fully connected layer, each reference score is multiplied by the corresponding fully connected layer parameter to obtain N first sub-credit scores, and then the N first sub-credit scores are added to obtain the first credit score. Among them, the N fully connected layer parameters are all determined after training.

[0130] For example, in Figure 5 , reference score 1 is multiplied by fully connected layer parameter 1 to obtain first sub-credit score 1, reference score 2 is multiplied by fully connected layer parameter 2 to obtain first sub-credit score 2, reference score 3 is multiplied by fully connected layer parameter 3 to obtain first sub-credit score 3, reference score 4 is multiplied by fully connected layer parameter 4 to obtain first sub-credit score 4, and first sub-credit score 1, first sub-credit score 2, first sub-credit score 3 and first sub-credit score 4 are added to obtain the first credit score.

[0131] In the embodiment of the present application, since the connection layer in the output module has trainable network parameters, the N first cross vectors do not share the same connection layer. Therefore, each first cross vector corresponds to P connection layers, and the network parameters in the P connection layers corresponding to different first cross vectors are not the same. In addition, the N reference scores share the same connection layer.

[0132] In the embodiment of the present application, each first sub-credit score in the N first sub-credit scores corresponds to at least one first feature domain in the M first feature domains, that is, each first sub-credit score is determined by at least one first feature domain. In order to facilitate the determination of the correspondence between each first sub-credit score and at least one first feature domain, the correspondence between each first sub-credit score and at least one first feature domain can be stored in the storage area.

[0133] by Figure 5 For example, the corresponding relationship between the first sub-credit score and the first feature domain stored in the storage area is as follows:

[0134] <First sub-credit score 1: first feature domain 1>

[0135] <First sub-credit score 2: first feature domain 2>

[0136] <First sub-credit score 3: first feature domain 3>

[0137] <First sub-credit score 4: first feature field 2, first feature field 3>

[0138] The storage area may also store a corresponding relationship between the first feature domain and the first feature data, as follows:

[0139] <First feature field 1: name ("Zhang San"), age ("25"), gender ("Male")>

[0140] <First feature field 2: salary ("20"), company ("xx company")>

[0141] <First feature field 3: deposit amount ("200"), total loan amount ("300"), repaid amount ("100")>

[0142] In the above method, since the storage area stores the correspondence between the first sub-credit score and the first characteristic domain, as well as the correspondence between the first characteristic domain and the first characteristic data, when the first sub-credit score changes, the first characteristic domain that causes the change in the first sub-credit score can be conveniently determined based on the correspondence between the first sub-credit score and the first characteristic domain, and then the first characteristic data that causes the change in the first sub-credit score can be determined based on the correspondence between the first characteristic domain and the first characteristic data.

[0143] S202: The processor obtains a second credit score and N second sub-credit scores of the first user.

[0144] In the embodiment of the present application, the second credit score and N second sub-credit scores are obtained by inputting the M second feature domains of the first user obtained at the second moment into the credit score model, the second credit score is determined based on the N second sub-credit scores, each of the N second sub-credit scores corresponds to at least one second feature domain in the M second feature domains, and each second feature domain includes at least one second feature data. The second moment can be any moment before the first moment, which is not limited here.

[0145] The method for determining the second credit score and N second sub-credit scores of the first user through the credit score model is the same as the method for determining the first credit score and N first sub-credit scores of the first user through the credit score model, and is not described in detail here.

[0146] If the first user data of the first user obtained by the processor at the first moment is the same as the first user data of the first user obtained by the processor at the second moment, then the first credit score and the second credit score of the first user are the same, and the N first sub-credit scores and the N second sub-credit scores are also the same accordingly.

[0147] S203, when the first credit score is different from the second credit score, the processor compares the N first sub-credit scores with the N second sub-credit scores to determine S first sub-credit scores and S second sub-credit scores corresponding to the S first sub-credit scores, wherein the S first sub-credit scores are different from the S second sub-credit scores, and S is a positive integer less than or equal to N.

[0148] In a possible implementation, when the first credit score is the same as the second credit score, the processor may directly output the first credit score and may also output the change in the first credit score relative to the second credit score. If the processor is located in a terminal device, the first credit score and the change in the first credit score relative to the second credit score may be directly displayed on a display interface of the terminal device.

[0149] In the embodiment of the present application, the change of the first credit score relative to the second credit score includes at least one of the following: the amount of change of the first credit score relative to the second credit score, or the sign of the change of the first credit score relative to the second credit score, wherein the change sign includes an increasing sign or a decreasing sign.

[0150] For example, the first moment is the current moment, and the second moment is one day ago. The processor may obtain that the second credit score of the first user one day ago is 720, and the processor may obtain that the first credit score of the first user at the current moment is also 720. After obtaining the first credit score, the processor determines that the first credit score is the same as the second credit score, that is, the change in the first credit score relative to the second credit score is 0, such as Figure 8 As shown, the processor can directly output the first credit score of 720 points, output an increasing symbol at the same time, and display the change of the first credit score relative to the second credit score of 0 points near the increasing symbol. The processor can also output an explanatory description, that is, "Compared to 1 day ago, the credit score increased by 0 points."

[0151] S204, the processor compares the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores, and determines at least one target behavior information that causes the first credit score to change relative to the second credit score.

[0152] In an embodiment of the present application, after determining at least one target behavior information that causes the first credit score to change relative to the second credit score, the processor can output at least one target behavior information that causes the first credit score to change relative to the second credit score, and can also output the first credit score, and can also output the change of the first credit score relative to the second credit score.

[0153] In the embodiment of the present application, for the ith first sub-credit score among the S first sub-credit scores, and the ith second sub-credit score among the S second sub-credit scores, the ith first sub-credit score corresponds to the ith second sub-credit score, and i is an integer that ranges from [1, S], the following steps are performed: the processor determines at least one first data to be compared, wherein the at least one first data to be compared is the first feature data in at least one first feature domain corresponding to the ith first sub-credit score, and the processor may also determine at least one second data to be compared, wherein the at least one second data to be compared is the second feature data in at least one second feature domain corresponding to the ith second sub-credit score. Finally, the processor determines at least one target behavior information that causes the ith first sub-credit score to change relative to the ith second sub-credit score based on the at least one first data to be compared and the at least one second data to be compared.

[0154] In addition, after determining at least one target behavior information that causes the i-th first sub-credit score to change relative to the i-th second sub-credit score, the processor may also determine the credit score corresponding to each target behavior information, which may be determined in the following manner:

[0155] If the change of the i-th first sub-credit score relative to the i-th second sub-credit score is caused by one target behavior information, the difference between the i-th first sub-credit score and the i-th second sub-credit score can be directly used as the credit score corresponding to the target behavior information. If the change of the i-th first sub-credit score relative to the i-th second sub-credit score is caused by W target behavior information, where W is an integer greater than 1, the difference between the i-th first sub-credit score and the i-th second sub-credit score is used as the first reference value, and the result of dividing the first reference value by W is used as the credit score corresponding to each target behavior information in the W target behavior information.

[0156] In the embodiment of the present application, i may be an integer ranging from [1, S]. As the value of i changes, at least one target behavior information may be determined, and the credit score corresponding to each target behavior information may also be determined.

[0157] When i takes different values, the determined target behavior information can be the same or different. If there is a target behavior information corresponding to a credit score, then the credit score is directly used as the total credit score of the target behavior information. If there is a target behavior information corresponding to multiple credit scores, then the sum of the multiple credit scores is used as the total credit score of the target behavior information.

[0158] For example, the first moment is the current moment, and the second moment is one day ago. The processor can obtain the first credit score and four first sub-credit scores of the first user at the current moment, as shown in Table 3.

[0159] Table 3.

[0160] First credit score First sub-credit score 1 First Sub Credit 2 First sub-credit score 3 First sub-credit score 4 740 360 200 60 120

[0161] The processor may obtain the second credit score and four second sub-credit scores of the first user one day ago, as shown in Table 4.

[0162] Table 4.

[0163] Second credit score Second sub-credit score 1 Second Sub-Credit 2 Second sub-credit score 3 Second sub-credit score 4 720 360 200 50 110

[0164] Since the first credit score 740 is different from the second credit score 720, the four first sub-credit scores in Table 3 are compared with the four second sub-credit scores in Table 4 to determine two different first sub-credit scores (i.e., first sub-credit score 3 and first sub-credit score 4) and two second sub-credit scores (i.e., second sub-credit score 3 and second sub-credit score 4).

[0165] The corresponding relationship between the first sub-credit score and the first feature domain stored in the storage area is set as follows:

[0166] <First sub-credit score 1, first feature domain 1>

[0167] <First sub-credit score 2, first feature domain 2>

[0168] <First sub-credit score 3, first feature field 3>

[0169] <First sub-credit score 4, first feature field 2, first feature field 3>

[0170] The corresponding relationship between the first feature domain and the first feature data stored in the storage area is as follows:

[0171] <First feature field 1: name ("Zhang San"), age ("25"), gender ("Male")>

[0172] <First feature field 2: salary ("20"), company ("xx company")>

[0173] <First feature field 3: deposit amount ("200"), total loan amount ("300"), repaid amount ("100")>

[0174] The corresponding relationship between the second sub-credit score and the second characteristic domain stored in the storage area is set as follows:

[0175] <Second sub-credit score 1, second feature field 1>

[0176] <Second sub-credit score 2, second feature field 2>

[0177] <Second sub-credit score 3, second feature field 3>

[0178] <Second sub-credit score 4, second feature field 2, second feature field 3>

[0179] The correspondence between the second characteristic domain and the second characteristic data stored in the storage area is as follows:

[0180] <Second feature field 1: name ("Zhang San"), age ("25"), gender ("Male")>

[0181] <Second feature field 2: salary ("20"), company ("xx company")>

[0182] <Second feature field 3: deposit amount ("400"), total loan amount ("300"), repaid amount ("100")>

[0183] The processor can determine that the first sub-credit score 3 corresponds to the first feature domain 3 based on the correspondence between the first sub-credit score and the first feature domain, and can determine that the first feature data corresponding to the first feature domain 3 includes the deposit amount ("200"), the total loan amount ("300"), and the repaid amount ("100") based on the correspondence between the first feature domain and the first feature data. Therefore, the three first data to be compared determined by the processor include the deposit amount ("200"), the total loan amount ("300"), and the repaid amount ("100").

[0184] The processor can also determine that the second sub-credit score 3 corresponds to the second feature domain 3 based on the correspondence between the second sub-credit score and the second feature domain, and can determine that the second feature data corresponding to the second feature domain 3 includes the deposit amount ("400"), the total loan amount ("300"), and the repaid amount ("100") based on the correspondence between the second feature domain and the second feature data. Therefore, the three second data to be compared determined by the processor include the deposit amount ("400"), the total loan amount ("300"), and the repaid amount ("100").

[0185] Based on the three first data to be compared and the three second data to be compared, it can be determined that the deposit amount has changed, so the target behavior information that causes the change in the first sub-credit score 3 relative to the second sub-credit score 3 can be determined, that is, "the deposit amount increased from 200 to 400, and the deposit amount increased by 200."

[0186] Since the change in the first sub-credit score 3 relative to the second sub-credit score 3 is caused by a target behavior information, the difference between the first sub-credit score 3 and the second sub-credit score 3 can be directly taken as the credit score corresponding to the target behavior information "the deposit amount increased from 200 to 400, and the deposit amount increased by 200", that is, the credit score corresponding to the target behavior information "the deposit amount increased from 200 to 400, and the deposit amount increased by 200" is 10 (that is, 60-50=10).

[0187] The processor can determine that the first sub-credit score 4 corresponds to the first feature domain 2 and the first feature domain 3 based on the correspondence between the first sub-credit score and the first feature domain, and can determine that the first feature data corresponding to the first feature domain 2 includes salary ("20") and the company ("xx company") based on the correspondence between the first feature domain and the first feature data, and that the first feature data corresponding to the first feature domain 3 includes deposit amount ("200"), total loan amount ("300"), and repaid amount ("100"). Therefore, the processor can determine 5 first data to be compared, including salary ("20"), company ("xx company"), deposit amount ("200"), total loan amount ("300"), and repaid amount ("100").

[0188] The processor can determine that the second sub-credit score 4 corresponds to the second feature domain 2 and the second feature domain 3 based on the correspondence between the second sub-credit score and the second feature domain, and can determine that the second feature data corresponding to the second feature domain 2 includes salary ("20") and the company ("xx company") based on the correspondence between the second feature domain and the second feature data, and that the second feature data corresponding to the second feature domain 3 includes deposit amount ("400"), total loan amount ("300"), and repaid amount ("100"). Therefore, the processor can determine 5 second data to be compared, including salary ("20"), company ("xx company"), deposit amount ("400"), total loan amount ("300"), and repaid amount ("100").

[0189] Based on the 5 first data to be compared and the 5 second data to be compared, it can be determined that the deposit amount has changed, so the target behavior information that causes the first sub-credit score 4 to change relative to the second sub-credit score 4 can be determined, that is, "the deposit amount increased from 200 to 400, and the deposit amount increased by 200."

[0190] Since the change in the first sub-credit score 4 relative to the second sub-credit score 4 is caused by a target behavior information, the difference between the first sub-credit score 4 and the second sub-credit score 4 can be directly taken as the credit score corresponding to the target behavior information "the deposit amount increased from 200 to 400, and the deposit amount increased by 200", that is, the credit score corresponding to the target behavior information "the deposit amount increased from 200 to 400, and the deposit amount increased by 200" is 10 (that is, 120-110=10).

[0191] In summary, since the target behavior information "the deposit amount increased from 200 to 400, and the deposit amount increased by 200" corresponds to two credit scores, both of which are 10, the total credit score of the target behavior information is 20 (ie, 10+10=20).

[0192] The processor may determine that the first credit score is 740, the change in the first credit score relative to the second credit score is 20, the change sign of the first credit score relative to the second credit score is an increasing sign, the target behavior information that causes the first credit score to change relative to the second credit score is "the deposit amount increases from 200 to 400, and the deposit amount increases by 200", and the total credit score corresponding to the target behavior information is 20. The processor may output the above information, such as Fig. 9 shown.

[0193] In the embodiment of the present application, the processor can also give suggestions to the first user based on the target behavior information and the total credit score corresponding to the target behavior information. For example, if the total credit score corresponding to the target behavior information "the deposit amount increases from 200 to 400, and the deposit amount increases by 200" is 20, the processor can give suggestions, for example, if the deposit amount increases by another 200, the credit score can be increased by another 20 points accordingly.

[0194] In addition, the processor can also set different loan amounts and loan interest rates for different credit scores. The higher the credit score, the higher the corresponding loan amount and the lower the loan interest rate.

[0195] In addition, the processor may also output the credit score of the first user according to a preset period, which may be one month, one week, one day, etc., and is not limited here. For example, if the preset period is one day, the processor may determine and output the credit score of the first user every day.

[0196] In order to facilitate the first user to view, the processor determines the credit score of the first user according to a preset period, and displays the determined credit score of the first user in the form of a chart. Fig.10 As shown, the preset period is set to one day, and the processor can determine the credit score of the first user every day, wherein the credit score of the first user from 2023.2.1 to 2023.2.3 is 724, and the credit score of the first user from 2023.2.4 to 2023.2.6 is 728.

[0197] In the above method, the user behavior that causes the credit score change can be accurately determined, making the credit score determined by the present application explainable.

[0198] In the embodiment of the present application, the structure of the credit score model is as follows: Figure 4 As shown, it includes a mapping module, a feature extraction module and a credit score output module. Among them, the mapping module includes an embedding layer and a first splicing layer. The feature extraction module includes a feature cross layer, L connection layers and a second splicing layer, where L is a non-negative integer. The credit score output module includes P connection layers and 1 fully connected layer, where P is a non-negative integer.

[0199] Generally speaking, when L takes different values ​​and P takes different values, the structure of the credit score model is different, and the effect of the trained credit score model is also different. In the embodiment of the present application, in order to increase the model training speed, the value of P is 1. The embodiment of the present application provides a method for determining the value of L.

[0200] In the embodiment of the present application, first construct Fig.11The first model shown in the figure has a structure including a mapping module, a feature extraction module, a credit score output module and a loss function module. The mapping module includes an embedding layer and a first concatenation layer. The feature extraction module includes a feature cross layer and a connection layer. The credit score output module includes a connection layer and a fully connected layer. The loss function module includes a loss function layer, and the loss function layer can be a mean square error (MSE) loss function, etc., which is not limited here.

[0201] The first model is trained using the first data set, and after the training is completed, the first model can be verified using the second data set. The second data set includes at least one set of M preset feature domains with credit score labels, and the first data set and the second data set do not have the same set of data.

[0202] When the second data set is used for verification, the processor can input a set of M preset feature domains with credit score labels into the trained first model. If the difference between the preset credit score output by the first model and the credit score label is within the first preset range, the constructed first model structure is usable. For example, if the preset credit score output by the first model is 728, the credit score label is 725, and the first preset range is [-10, 10], the difference between the preset credit score 728 and the credit score label 725 output by the first model is 3, and the difference 3 is within the first preset range [-10, 10], so the constructed first model structure is usable.

[0203] If the difference between the preset credit score output by the first model and the credit score label exceeds the first preset range, the constructed first model structure is unusable. A connection layer can be added to the feature extraction module of the first model to construct the following structure: Fig.12 The second model shown in the figure has a structure including a mapping module, a feature extraction module, a credit score output module and a loss function module. The mapping module, the credit score output module and the loss function module in the second model are the same as those in the first model. The feature extraction module in the second model includes two connection layers, while the feature extraction module in the first model includes one connection layer.

[0204] The second model is trained in the same way as the first model. After the training is completed, the second data set can be used to verify the trained second model. If the difference between the preset credit score and the credit score label output by the second model exceeds the first preset range, the constructed second model structure is unusable, and a connection layer can be added to the feature extraction module of the second model, and so on. If the difference between the preset credit score and the credit score label output by the second model is within the first preset range, the constructed second model structure is usable.

[0205] When it is determined that the constructed second model structure is available, the first data set is used to retrain the second model. During the training of the second model, the parameter gradient value corresponding to the last connection layer in the feature extraction module of the second model is monitored. If the parameter gradient value corresponding to the last connection layer in the feature extraction module of the second model is less than the first preset gradient value, a second splicing layer is added after the connection layer in the feature extraction module of the second model to construct the second model. Fig.13 After determining the structure of the third model, the first data set is used to fine-tune the third model to obtain the trained third model, and the trained third model is used as the credit score model used in the embodiment of the present application.

[0206] Through the above method, a more accurate and efficient credit score model can be determined.

[0207] Based on the above embodiments, the present application also provides a behavior detection device, which is applied to Figure 1 The processor of the computer device shown is used to implement Figure 2 The embodiment shown provides a behavior detection method. Fig.14 As shown, the device includes: a transceiver unit 1401 and a processing unit 1402. Among them:

[0208] The transceiver unit 1401 is used to obtain a first credit score and N first sub-credit scores of a first user, wherein the first credit score and the N first sub-credit scores are obtained by inputting M first feature domains of the first user obtained at a first moment into a credit score model, wherein the first credit score is determined based on the N first sub-credit scores, each of the N first sub-credit scores corresponds to at least one first feature domain of the M first feature domains, and each first feature domain includes at least one first feature data; M is an integer greater than 1, and N is an integer greater than or equal to M; the credit score model is trained based on a first data set, and the first data set includes at least one group of M preset feature domains with credit score labels.

[0209] The transceiver unit 1401 is also used to obtain the second credit score and N second sub-credit scores of the first user, the second credit score and the N second sub-credit scores are obtained by inputting M second feature domains of the first user obtained at a second moment into a credit score model, the second moment is before the first moment, and the second credit score is determined based on the N second sub-credit scores; each second sub-credit score in the N second sub-credit scores corresponds to at least one second feature domain in the M second feature domains, and each second feature domain includes at least one second feature data.

[0210] Processing unit 1402 is also used to compare the N first sub-credit scores with the N second sub-credit scores when the first credit score is different from the second credit score, to determine S first sub-credit scores and S second sub-credit scores corresponding to the S first sub-credit scores, and the S first sub-credit scores and the S second sub-credit scores are different; wherein S is a positive integer less than or equal to N.

[0211] Processing unit 1402 is also used to compare the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores, and determine at least one target behavior information that causes the first credit score to change relative to the second credit score.

[0212] In a possible implementation manner, the M first feature domains of the first user are obtained by dividing a plurality of first feature data included in the first user data of the first user acquired at the first moment based on a preset division rule.

[0213] In one possible implementation, the credit score model includes a mapping module, a feature extraction module and a credit score output module; the processing unit 1402 can obtain the first credit score and N first sub-credit scores in the following manner: input at least one first feature data of the M first feature domains into the mapping module to obtain the first feature domain vectors corresponding to the M first feature domains respectively; input the obtained M first feature domain vectors into the feature extraction module to obtain N first cross vectors; input the N first cross vectors into the credit score output module to obtain the first credit score and N first sub-credit scores.

[0214] In one possible implementation, the mapping module includes an embedding layer and a first splicing layer; the processing unit 1402 can obtain M first feature domain vectors in the following manner: for the jth first feature domain among the M first feature domains, where j is an integer that spans [1,M], the following steps are performed: at least one first feature data in the jth first feature domain is input into the embedding layer, and it is determined that at least one first feature data in the jth first feature domain corresponds to a first feature vector; based on the first splicing layer, at least one first feature vector corresponding to the jth first feature domain is spliced ​​to obtain the first feature domain vector corresponding to the jth first feature domain.

[0215] In one possible implementation, the feature extraction module includes a feature cross layer, L connection layers and a second splicing layer, where L is a non-negative integer; the processing unit 1402 can obtain N first cross vectors in the following manner: input M first feature domain vectors into the feature cross layer to obtain N second cross vectors; input N second cross vectors into L connection layers to obtain N third cross vectors; input N third cross vectors and M first feature domain vectors into the second splicing layer to obtain N first cross vectors.

[0216] In a possible implementation, when the processing unit 1402 inputs M first feature domain vectors into the feature intersection layer and obtains N second cross vectors, it is specifically used to: for the j-th first feature domain vector among the M first feature domain vectors, perform matrix dot multiplication on the j-th first feature domain vector and the j-th first feature domain vector to obtain a first type vector corresponding to the j-th first feature domain vector, where j is an integer ranging from [1, M]; based on a preset intersection rule, determine at least one group of two associated first feature domain vectors, perform matrix dot multiplication on each group of two associated first feature domain vectors to obtain at least one second type vector; and use the first type vector and at least one second type vector corresponding to the j-th first feature domain vector as N second cross vectors.

[0217] In one possible implementation, the processing unit 1402 inputs N third cross vectors and M first feature domain vectors into the second splicing layer to obtain N first cross vectors, and is specifically used to: for the p-th third cross vector among the N third cross vectors, where p is an integer ranging from [1, N], perform the following steps: determine at least one first feature domain vector corresponding to the p-th third cross vector as the target feature vector; splice the p-th third cross vector with at least one target feature domain vector to obtain the first cross vector corresponding to the p-th third cross vector.

[0218] In one possible implementation, when processing unit 1402 compares the first feature data in the first feature domain corresponding to S first sub-credit scores with the second feature data in the second feature domain corresponding to S second sub-credit scores, and determines at least one target behavior information that causes the first credit score to change relative to the second credit score, it is specifically used to: for the i-th first sub-credit score among the S first sub-credit scores, and the i-th second sub-credit score among the S second sub-credit scores, the i-th first sub-credit score corresponds to the i-th second sub-credit score, and i is an integer ranging from [1, S], perform the following steps: determine at least one first data to be compared, the at least one first data to be compared is the first feature data in at least one first feature domain corresponding to the i-th first sub-credit score; determine at least one second data to be compared, the at least one second data to be compared is the second feature data in at least one second feature domain corresponding to the i-th second sub-credit score; and determine at least one target behavior information that causes the i-th first sub-credit score to change relative to the i-th second sub-credit score based on the at least one first data to be compared and the at least one second data to be compared.

[0219] In a possible implementation, the processing unit 1402 may further output at least one target behavior information causing the first credit score to change relative to the second credit score.

[0220] In a possible implementation, the processing unit 1402 may further output at least one of the following: output a change in the first credit score relative to the second credit score, or output the first credit score.

[0221] In a possible implementation, the change of the first credit score relative to the second credit score includes at least one of the following: the amount of change of the first credit score relative to the second credit score, or the sign of the change of the first credit score relative to the second credit score.

[0222] An embodiment of the present application provides a behavior detection device, which can determine at least one target behavior that causes a change in the first credit score when the first credit score is different from the second credit score, and can accurately determine which behavioral changes of the user will cause a change in the credit score, so that the credit score determined by the present application is explainable.

[0223] It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0224] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0225] Based on the above embodiments, the present application also provides a computer device, which is used to implement the following Figure 2 The behavior detection method shown has the following features: Fig.14 The behavior detection device shown here has the following functions. Fig.15 As shown, the computer device includes: a processor 1501 and a memory 1502.

[0226] The processor 1501 and the memory 1502 are connected to each other. Optionally, the processor 1501 and the memory 1502 can be connected to each other via a bus 1503; the bus 1503 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.15 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0227] Optionally, the computer device 1500 further includes a communication module 1504 for communicating and interacting with other devices. Optionally, the communication module 1504 can communicate with other devices via wireless connection, for example, the communication module 1504 can be an RF circuit, a WiFi module, etc. The communication module 1504 can also communicate with other devices via physical connection, for example, the communication module 1504 can be a communication interface.

[0228] The processor 1501 is used to implement Figure 2The specific process of the behavior detection method shown can refer to the specific description in the above embodiment, which will not be repeated here.

[0229] The memory 1502 is used to store programs and data. Specifically, the program may include program code, which includes instructions for computer operation. The memory 1502 may include random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory. The processor 1501 executes the program stored in the memory 1502 to implement the above functions, thereby achieving the following: Figure 2 The behavioral detection method shown.

[0230] The present application also provides a computer storage medium, wherein a computer program is stored in the computer storage medium, and when the computer program is executed by a computer, the computer executes Figure 2 The behavioral detection method shown.

[0231] In summary, the embodiments of the present application provide a behavior detection method and device. In this method, when the first credit score is different from the second credit score, at least one target behavior that causes the change in the first credit score can be determined, and it can be accurately determined which behavioral changes of the user will cause the credit score to change, so that the credit score determined by the present application is explainable.

[0232] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0233] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0234] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0235] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0236] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A behavior detection method, It is characterized in that The method comprises: Obtaining a first credit score and N first sub-credit scores of a first user, wherein the first credit score and the N first sub-credit scores are obtained by inputting M first feature domains of the first user obtained at a first moment into a credit score model, wherein the first credit score is determined based on the N first sub-credit scores, each first sub-credit score of the N first sub-credit scores corresponds to at least one first feature domain of the M first feature domains, and each first feature domain includes at least one first feature data; M is an integer greater than 1, and N is an integer greater than or equal to M; the credit score model is trained based on a first data set, and the first data set includes at least one group of M preset feature domains with credit score labels; Acquire a second credit score and N second sub-credit scores of the first user, wherein the second credit score and the N second sub-credit scores are obtained by inputting M second feature domains of the first user acquired at a second moment into the credit score model, the second moment being before the first moment, and the second credit score is determined based on the N second sub-credit scores; each second sub-credit score of the N second sub-credit scores corresponds to at least one second feature domain of the M second feature domains, and each second feature domain includes at least one second feature data; If the first credit score is different from the second credit score, the N first sub-credit scores are compared with the N second sub-credit scores to determine S first sub-credit scores and S second sub-credit scores corresponding to the S first sub-credit scores, the S first sub-credit scores are different from the S second sub-credit scores, and S is a positive integer less than or equal to N; The first feature data in the first feature domain corresponding to the S first sub-credit scores are compared with the second feature data in the second feature domain corresponding to the S second sub-credit scores to determine at least one target behavior information that causes the first credit score to change relative to the second credit score.

2. The method according to claim 1, It is characterized in that The M first feature domains of the first user are obtained by dividing a plurality of first feature data included in the first user data of the first user acquired at a first moment based on a preset division rule.

3. The method according to claim 1, It is characterized in that The credit score model includes a mapping module, a feature extraction module and a credit score output module; The first credit score and the N first sub-credit scores are obtained in the following manner: Inputting at least one first feature data of the M first feature domains into the mapping module to obtain first feature domain vectors respectively corresponding to the M first feature domains; Input the obtained M first feature domain vectors into the feature extraction module to obtain N first cross vectors; The N first cross vectors are input into the credit score output module to obtain the first credit score and the N first sub-credit scores.

4. The method according to claim 3, It is characterized in that The mapping module includes an embedding layer and a first splicing layer; The M first feature domain vectors are obtained in the following manner: For the j-th first feature domain among the M first feature domains, where j is an integer ranging from [1, M], perform the following steps: Inputting at least one first feature data in the j-th first feature domain into the embedding layer, and determining that at least one first feature data in the j-th first feature domain respectively corresponds to a first feature vector; Based on the first concatenated layer, at least one first feature vector corresponding to the j-th first feature domain is concatenated to obtain a first feature domain vector corresponding to the j-th first feature domain.

5. The method according to claim 3, It is characterized in that The feature extraction module includes a feature cross layer, L connection layers and a second splicing layer, where L is a non-negative integer; The N first cross vectors are obtained in the following manner: Inputting the M first feature domain vectors into the feature cross layer to obtain N second cross vectors; Inputting the N second cross vectors into the L connection layers to obtain N third cross vectors; The N third cross vectors and the M first feature domain vectors are input into the second concatenation layer to obtain the N first cross vectors.

6. The method according to claim 5, It is characterized in that The step of inputting the M first feature domain vectors into the feature cross layer to obtain N second cross vectors includes: For the j-th first feature domain vector among the M first feature domain vectors, perform matrix dot multiplication on the j-th first feature domain vector and the j-th first feature domain vector to obtain a first type vector corresponding to the j-th first feature domain vector, where j is an integer that runs through [1, M]. Based on a preset crossover rule, at least one group of two associated first feature domain vectors is determined, and matrix point multiplication is performed on each group of two associated first feature domain vectors to obtain at least one second type vector; The first type vector corresponding to the j-th first feature domain vector and the at least one second type vector are used as the N second cross vectors.

7. The method according to claim 5 or 6, It is characterized in that The step of inputting the N third cross vectors and the M first feature domain vectors into the second concatenation layer to obtain the N first cross vectors includes: For the pth third cross vector among the N third cross vectors, where p is an integer ranging from [1, N], the following steps are performed: Determine at least one first feature domain vector corresponding to the p-th third cross vector as a target feature vector; The p-th third cross vector is concatenated with at least one target feature domain vector to obtain a first cross vector corresponding to the p-th third cross vector.

8. The method according to any one of claims 1 to 7, It is characterized in that Comparing the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores, and determining at least one target behavior information causing the first credit score to change relative to the second credit score, includes: For the ith first sub-credit score among the S first sub-credit scores and the ith second sub-credit score among the S second sub-credit scores, the ith first sub-credit score corresponds to the ith second sub-credit score, where i is an integer ranging from [1, S], perform the following steps: Determine at least one first data to be compared, where the at least one first data to be compared is first feature data in at least one first feature domain corresponding to the i-th first sub-credit score; Determine at least one second data to be compared, where the at least one second data to be compared is second feature data in at least one second feature field corresponding to the i-th second sub-credit score; At least one target behavior information causing the i-th first sub-credit score to change relative to the i-th second sub-credit score is determined based on the at least one first data to be compared and the at least one second data to be compared.

9. The method according to any one of claims 1 to 8, It is characterized in that Also includes: Output at least one target behavior information causing the first credit score to change relative to the second credit score.

10. The method according to claim 9, It is characterized in that Also includes at least one of the following: Outputting the change of the first credit score relative to the second credit score, or, The first credit score is output.

11. The method according to claim 10, It is characterized in that The change of the first credit score relative to the second credit score includes at least one of the following: the change in the first credit score relative to the second credit score, or, The sign of the change in the first credit score relative to the second credit score.

12. A behavior detection device, It is characterized in that The device comprises: a transceiver unit, used for obtaining a first credit score and N first sub-credit scores of a first user, wherein the first credit score and the N first sub-credit scores are obtained by inputting M first feature domains of the first user obtained at a first moment into a credit score model, wherein the first credit score is determined based on the N first sub-credit scores, each first sub-credit score of the N first sub-credit scores corresponds to at least one first feature domain of the M first feature domains, and each first feature domain includes at least one first feature data; M is an integer greater than 1, and N is an integer greater than or equal to M; the credit score model is trained based on a first data set, and the first data set includes at least one group of M preset feature domains with credit score labels; The transceiver unit is further used to obtain a second credit score and N second sub-credit scores of the first user, wherein the second credit score and the N second sub-credit scores are obtained by inputting M second feature domains of the first user obtained at a second moment into the credit score model, wherein the second moment is before the first moment, and the second credit score is determined based on the N second sub-credit scores; each second sub-credit score of the N second sub-credit scores corresponds to at least one second feature domain of the M second feature domains, and each second feature domain includes at least one second feature data; the processing unit is further configured to, if the first credit score is different from the second credit score, compare the N first sub-credit scores with the N second sub-credit scores to determine S first sub-credit scores and S second sub-credit scores corresponding to the S first sub-credit scores, the S first sub-credit scores being different from the S second sub-credit scores, and S being a positive integer less than or equal to N; The processing unit is further used to compare the first feature data in the first feature domain corresponding to the S first sub-credit scores with the second feature data in the second feature domain corresponding to the S second sub-credit scores, and determine at least one target behavior information that causes the first credit score to change relative to the second credit score.

13. A computer device, It is characterized in that include: Memory, used to store programs and data; A processor, configured to run the program stored in the memory, and to execute the method according to any one of claims 1 to 11 according to the data stored in the memory.

14. A computer storage medium, It is characterized in that The computer storage medium stores a computer program, and when the computer program is executed by a computer, the computer executes the method provided in any one of claims 1 to 11.

Images