Data prediction processing method and device based on artificial intelligence, equipment and medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based data prediction processing method, which comprises the steps of generating a target inner product based on feature data, a weight coefficient and an inner product; generating a first-order partial derivative and a second-order partial derivative of the target inner product; constructing a diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the feature data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative; encrypting the diagonal matrix, the first initial data and the second initial data to obtain encrypted data; calculating an inverse matrix based on the encryption matrix and dividing to obtain a matrix; performing matrix division based on the ciphertext matrix to obtain a division matrix, and generating a first model weight coefficient based on the division matrix; generating a target model weight coefficient based on the first model weight coefficient and the second model weight coefficient; and performing prediction processing on the business data based on the target prediction model. The training efficiency and the model effect of the target prediction model are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based data prediction and processing methods, devices, computer equipment and storage media. Background Art

[0002] In the field of data analysis, Generalized Linear Models (GLMs), as an extension of the linear regression model, have attracted much attention due to their flexibility and wide range of application scenarios. GLMs not only cover traditional linear regression, but also include multiple variants such as Poisson regression and Tweedie regression. These models can handle various types of data distributions and response variables, making them powerful tools for solving complex problems.

[0003] In the auto insurance business scenario, the application of generalized linear models is particularly prominent. For example, the Poisson regression model can be used to predict the frequency of users' accidents, which is crucial for insurance companies to assess risks and formulate premium strategies. The Tweedie regression model is suitable for the prediction of pure premiums. It can effectively deal with zero inflation and overdispersion in insurance claim data and improve the accuracy of predictions. The application of these models not only improves the operating efficiency of insurance companies, but also provides consumers with more fair and reasonable insurance services.

[0004] However, in practical applications, the training process of generalized linear models faces many challenges. Since label data and feature data are often scattered in different institutions or companies, data integration and transmission become a problem. In addition, most existing training methods for generalized linear models rely on gradient descent algorithms to update model parameters. Although these methods are theoretically feasible, in practical applications, they have problems such as long training time, low efficiency, and slow convergence speed, and result in low accuracy in subsequent prediction processing using generalized linear models. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a data prediction and processing method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problem that most of the existing training methods of generalized linear models rely on the gradient descent algorithm to update the model parameters, but in actual applications there are problems such as long training time, low efficiency, slow convergence speed, and resulting in low accuracy of subsequent prediction processing using generalized linear models.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a data prediction and processing method based on artificial intelligence, which adopts the following technical solutions:

[0007] Generate a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received from the non-label party;

[0008] Generate a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a loss function of a preset generalized linear model;

[0009] Constructing a corresponding diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the characteristic data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative;

[0010] Encrypting the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data;

[0011] Based on the received multiple encrypted matrices sent by the non-label party, inverse matrices are calculated and divided to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix;

[0012] Performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generating a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data;

[0013] When a preset iteration termination condition is met, a target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix;

[0014] The business data to be processed is predicted based on the target prediction model corresponding to the target model weight coefficient.

[0015] Furthermore, the step of generating a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received from the non-label party specifically includes:

[0016] Calculating the product of the characteristic data and the weight coefficient to obtain a corresponding specified inner product;

[0017] receiving an inner product sent by the non-label party;

[0018] Calculate the sum of the specified inner product and the inner product;

[0019] The sum is taken as the target inner product.

[0020] Furthermore, the step of encrypting the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data specifically includes:

[0021] Get the preset homomorphic encryption strategy;

[0022] Based on the homomorphic encryption strategy, the diagonal matrix, the first initial data, and the second initial data are encrypted respectively to obtain corresponding first encrypted data, second encrypted data, and third encrypted data;

[0023] Integrate the first encrypted data, the second encrypted data and the third encrypted data to obtain corresponding integrated data;

[0024] The integrated data is used as the encrypted data.

[0025] Further, the step of calculating the inverse matrix and performing division processing based on the received multiple encrypted matrices sent by the non-label party to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix specifically includes:

[0026] Calculate a first specified matrix based on the diagonal matrix and the characteristic data;

[0027] Decrypting the multiple encryption matrices to obtain a corresponding first decryption matrix;

[0028] generating an integrated matrix based on the first specified matrix and the first decryption matrix, and calculating an inverse matrix of the integrated matrix;

[0029] Based on a preset first characteristic dimension, the inverse matrix is ​​divided vertically to obtain the first matrix and the second matrix;

[0030] constructing a second designated matrix based on the first matrix, the characteristic data and the second initial data;

[0031] The second specified matrix is ​​divided horizontally based on the first characteristic dimension to obtain the third matrix and the fourth matrix.

[0032] Furthermore, the step of performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain the fifth matrix and the sixth matrix specifically includes:

[0033] Decrypting the ciphertext matrix to obtain a corresponding second decryption matrix;

[0034] Obtaining a preset second characteristic dimension;

[0035] The second decryption matrix is ​​horizontally divided based on the second characteristic dimension to obtain the fifth matrix and the sixth matrix.

[0036] Furthermore, when the preset iteration termination condition is met, the step of generating the target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party specifically includes:

[0037] When a preset iteration termination condition is met, receiving a second model weight coefficient sent by the non-label party;

[0038] Get preset integration strategies;

[0039] Integrate the first model weight coefficient and the second model weight coefficient based on the integration strategy to obtain a corresponding integration coefficient;

[0040] The integration coefficient is used as the target model weight coefficient.

[0041] Furthermore, before the step of performing prediction processing on the service data to be processed based on the target prediction model corresponding to the target model weight coefficient, the method further includes:

[0042] Determining a specified storage strategy corresponding to the target prediction model;

[0043] Invoking a specified storage medium corresponding to the specified storage strategy;

[0044] The target prediction model is stored based on the designated storage medium.

[0045] In order to solve the above technical problems, the embodiment of the present application also provides a data prediction and processing device based on artificial intelligence, which adopts the following technical solution:

[0046] A first generating module, configured to generate a corresponding target inner product based on preset feature data, a weight coefficient and an inner product received from a non-label party;

[0047] A second generating module, used for generating a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a preset loss function of a generalized linear model;

[0048] A construction module, configured to construct a corresponding diagonal matrix based on the second-order partial derivative, construct first initial data based on the diagonal matrix and the characteristic data, and construct second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative;

[0049] An encryption module, used to encrypt the diagonal matrix, the first initial data and the second initial data respectively to obtain corresponding encrypted data;

[0050] A partitioning module, configured to calculate an inverse matrix and perform partitioning processing based on the received multiple encrypted matrices sent by the non-label party to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix;

[0051] A third generating module, configured to perform matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generate a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data;

[0052] A fourth generation module, configured to generate a target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party when a preset iteration termination condition is met; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix;

[0053] A processing module is used to perform prediction processing on the business data to be processed based on the target prediction model corresponding to the target model weight coefficient.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0055] Generate a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received from the non-label party;

[0056] Generate a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a loss function of a preset generalized linear model;

[0057] Constructing a corresponding diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the characteristic data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative;

[0058] Encrypting the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data;

[0059] Based on the received multiple encrypted matrices sent by the non-label party, inverse matrices are calculated and divided to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix;

[0060] Performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generating a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data;

[0061] When a preset iteration termination condition is met, a target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix;

[0062] The business data to be processed is predicted based on the target prediction model corresponding to the target model weight coefficient.

[0063] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0064] Generate a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received from the non-label party;

[0065] Generate a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a loss function of a preset generalized linear model;

[0066] Constructing a corresponding diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the characteristic data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative;

[0067] Encrypting the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data;

[0068] Based on the received multiple encrypted matrices sent by the non-label party, inverse matrices are calculated and divided to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix;

[0069] Performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generating a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data;

[0070] When a preset iteration termination condition is met, a target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix;

[0071] The business data to be processed is predicted based on the target prediction model corresponding to the target model weight coefficient.

[0072] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0073] The present application first generates a corresponding target inner product based on preset feature data, weight coefficients and the inner product received from the non-label party; then generates a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on the preset loss function of the generalized linear model; and constructs a corresponding diagonal matrix based on the second-order partial derivative, and constructs first initial data based on the diagonal matrix and the feature data, and constructs second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative; then encrypts the diagonal matrix, the first initial data and the second initial data respectively to obtain corresponding encrypted data; subsequently, based on the received The multiple encrypted matrices sent by the non-label party are calculated for inverse matrix and partition processing to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix; further based on the received ciphertext matrix sent by the non-label party, matrix partition is performed to obtain the fifth matrix and the sixth matrix, and the first model weight coefficient is generated based on the third matrix and the fifth matrix; when the preset iteration termination condition is met, the target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; finally, the target prediction model corresponding to the target model weight coefficient is used to predict the business data to be processed. This application constructs the target prediction model by using the generalized linear model training method of vertical federated learning. Compared with the gradient descent method, it can make the model converge faster with fewer iterations, and is insensitive to the initialization value of the model parameters, and is not easy to fall into the saddle point, which effectively improves the training efficiency of the target prediction model and can obtain better model effects after training; at the same time, in terms of security in the calculation process, by using encryption and decryption for the intermediate results, the original data of each participant and their respective model parameters can be prevented from being leaked or inferred, effectively protecting the modeling process of the entire target prediction model. This enables the subsequent use of the target prediction model to accurately predict the business data and obtain corresponding prediction results, thereby improving the prediction effect of the prediction processing of the business data and improving the accuracy of the generated prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0076] Figure 2 A flowchart of an embodiment of a data prediction processing method based on artificial intelligence according to the present application;

[0077] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based data prediction and processing device according to the present application;

[0078] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0079] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0080] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0081] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0082] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0083] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0084] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0085] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0086] It should be noted that the artificial intelligence-based data prediction and processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based data prediction and processing device is generally set in the server / terminal device.

[0087] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0088] Continue to refer Figure 2, showing a flowchart of an embodiment of an artificial intelligence-based data prediction processing method according to the present application. According to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted. The artificial intelligence-based data prediction processing method provided in the embodiment of the present application can be applied to any scenario where data prediction is required, and the artificial intelligence-based data prediction processing method can be applied to products in these scenarios, for example, data prediction processing in the financial insurance field. The artificial intelligence-based data prediction processing method comprises the following steps:

[0089] Step S201, generating a corresponding target inner product based on preset feature data, weight coefficients and the inner product received from the non-label party.

[0090] In this embodiment, the data prediction processing method based on artificial intelligence is executed on the electronic device (for example Figure 1 The server / terminal device shown in the figure) can obtain feature data and weight coefficients through wired connection or wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future. The execution of this application is specifically to have tag data, feature data X A , and the weight coefficient w A The non-label party B has feature data X B , and the weight coefficient w B Among them, the specific implementation process of generating the corresponding target inner product based on the preset feature data, weight coefficient and the inner product received from the non-label party will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated here.

[0091] In this embodiment, illustratively, in the business scenario of financial insurance product push, the business tracking data may include transaction data, payment data, business data, and the like.

[0092] Step S202, generating a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a preset loss function of a generalized linear model.

[0093] In this embodiment, the present application can be applied to the prediction of the frequency of accidents of users or the prediction of pure premiums in the auto insurance business scenario. The above-mentioned generalized linear model may include a Poisson regression model for predicting the frequency of accidents of users in the auto insurance business scenario, or it may also be a Tweedie regression model for predicting pure premiums, and so on. Specifically, the first-order partial derivative g and the second-order partial derivative h of the loss function L with respect to the target inner product η can be calculated. Among them, the loss function L and its first-order partial derivative g and second-order partial derivative h can be generated using different formulas according to the specific generalized linear model.

[0094] Step S203, constructing a corresponding diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the feature data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative.

[0095] In this embodiment, the diagonal matrix includes: W=diag(h), where W is a diagonal matrix with h as a diagonal element, and h is a second-order partial derivative. The first initial data includes WX A . Where W is a diagonal matrix, X A The second initial data includes Wz, z=η-W T g,WX A . Where η is the target inner product, W is a diagonal matrix, and g is the first-order partial derivative.

[0096] Step S204: encrypt the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data.

[0097] In this embodiment, the specific implementation process of encrypting the diagonal matrix, the first initial data and the second initial data to obtain the corresponding encrypted data will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here. In addition, when obtaining the encrypted data Enc(W), Enc(WX A ),Enc(Wz), the encrypted data will be sent to the non-label party B.

[0098] Step S205, based on the received multiple encrypted matrices sent by the non-tagged party, calculate the inverse matrix and perform division processing to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix; wherein the encrypted matrix is ​​generated based on the encrypted data; the third matrix and the fourth matrix are generated based on the first matrix.

[0099] In this embodiment, the non-label party B receives the encrypted data Enc(W), Enc(Wx A),Enc(Wz), combined with the internal feature data X B According to the following calculation formula Calculate and obtain three encrypted matrices Enc(D AB ), Enc(D BA ), Enc(D BB ), and sent to the tag party A. The above-mentioned specific implementation process of calculating the inverse matrix and dividing the multiple encrypted matrices sent by the non-tag party to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here. In addition, the second matrix and the fourth matrix are further sent to the non-tag party B.

[0100] Step S206, performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generating a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data.

[0101] In this embodiment, the specific implementation process of performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain the fifth matrix and the sixth matrix, and generating the first model weight coefficient based on the third matrix and the fifth matrix, will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here. In addition, the first model weight coefficient includes: β A =M A1 +M A2 Among them, β A is the weight coefficient of the first model, M A1 is the third matrix, M A2 is the fifth matrix.

[0102] Step S207, when the preset iteration termination condition is met, the target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix.

[0103] In this embodiment, the non-label party B updates its second model weight coefficient β by calculating B =M B1 +M B2 , where β B is the weight coefficient of the second model, M B1 is the fourth matrix, M B2is the sixth matrix. Among them, the specific implementation process of generating the target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party when the preset iteration termination condition is met, this application will be further described in detail in the subsequent specific embodiments, and will not be elaborated on here. In addition, the loop steps S201-S207 or the end of the model training process can be selected according to the loss function value or the total number of iterations.

[0104] Step S208: performing prediction processing on the business data to be processed based on the target prediction model corresponding to the target model weight coefficient.

[0105] In this embodiment, after the final target model weight coefficient is obtained, the trained model can be represented by the target model weight coefficient, that is, the target prediction model can be represented as y=β T X+∈, where y is the target variable and X is the feature vector (in this embodiment, the feature data X A and feature data X B ), β is the weight vector (composed of β A and β B Integrate), ∈ is the error term. Among them, in the business scenario of the financial field, the above business data can be the user data required for predicting the user's accident frequency in the auto insurance business scenario, or it can also be the user data required for pure premium prediction. Specifically, by inputting the above-mentioned business data to be processed into the target prediction model, the business data is predicted and processed by the target prediction model, so as to output the prediction result corresponding to the business data, such as the user's accident frequency result or the premium prediction result.

[0106] The present application first generates a corresponding target inner product based on preset feature data, weight coefficients and the inner product received from the non-label party; then generates a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on the preset loss function of the generalized linear model; and constructs a corresponding diagonal matrix based on the second-order partial derivative, and constructs first initial data based on the diagonal matrix and the feature data, and constructs second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative; then encrypts the diagonal matrix, the first initial data and the second initial data respectively to obtain corresponding encrypted data; subsequently, based on the received The multiple encrypted matrices sent by the non-label party are calculated for inverse matrix and partition processing to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix; further based on the received ciphertext matrix sent by the non-label party, matrix partition is performed to obtain the fifth matrix and the sixth matrix, and the first model weight coefficient is generated based on the third matrix and the fifth matrix; when the preset iteration termination condition is met, the target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; finally, the target prediction model corresponding to the target model weight coefficient is used to predict the business data to be processed. This application constructs the target prediction model by using the generalized linear model training method of vertical federated learning. Compared with the gradient descent method, it can make the model converge faster with fewer iterations, and is insensitive to the initialization value of the model parameters, and is not easy to fall into the saddle point, which effectively improves the training efficiency of the target prediction model and can obtain better model effects after training; at the same time, in terms of security in the calculation process, by using encryption and decryption for the intermediate results, the original data of each participant and their respective model parameters can be prevented from being leaked or inferred, effectively protecting the modeling process of the entire target prediction model. This enables the subsequent use of the target prediction model to accurately predict the business data and obtain corresponding prediction results, thereby improving the prediction effect of the prediction processing of the business data and improving the accuracy of the generated prediction results.

[0107] In some optional implementations, step S201 includes the following steps:

[0108] The product of the feature data and the weight coefficient is calculated to obtain a corresponding specified inner product.

[0109] In this embodiment, the tag side A has tag data y and feature data X. A And the weight coefficient w A The unlabeled party B has feature data X B , and the weight coefficient w B The inner product η is specified above A =X A w A.

[0110] An inner product sent by the non-label party is received.

[0111] In this embodiment, the non-label party B calculates X B With w B The product of B .

[0112] The sum of the specified inner product and the inner product is calculated.

[0113] In this embodiment, by calculating η A +η B The sum value η of is obtained to obtain the target inner product.

[0114] The sum is taken as the target inner product.

[0115] The present application obtains the corresponding designated inner product by calculating the product of the feature data and the weight coefficient; then receives the inner product sent by the non-label party; then calculates the sum of the designated inner product and the inner product; and subsequently uses the sum as the target inner product. The present application obtains the designated inner product by calculating the product of the feature data and the weight coefficient, and then calculates the sum between the designated inner product and the inner product received and sent by the non-label party, so that the corresponding target inner product can be calculated quickly and accurately, ensuring the data accuracy of the obtained target inner product.

[0116] In some optional implementations of this embodiment, step S204 includes the following steps:

[0117] Get the preset homomorphic encryption strategy.

[0118] In this embodiment, there is no specific limitation on the selection of homomorphic encryption strategy. For example, Paillier encryption, fully homomorphic encryption and other strategies can be selected.

[0119] Based on the homomorphic encryption strategy, the diagonal matrix, the first initial data and the second initial data are encrypted respectively to obtain corresponding first encrypted data, second encrypted data and third encrypted data.

[0120] In this embodiment, according to the additive homomorphic property of the above-mentioned homomorphic encryption strategy, the diagonal matrix, the first initial data and the second initial data can be encrypted respectively to obtain the corresponding first encrypted data, second encrypted data and third encrypted data.

[0121] The first encrypted data, the second encrypted data and the third encrypted data are integrated to obtain corresponding integrated data.

[0122] In this embodiment, the integrated data includes the first encrypted data, the second encrypted data and the third encrypted data.

[0123] The integrated data is used as the encrypted data.

[0124] This application obtains a preset homomorphic encryption strategy; then, based on the homomorphic encryption strategy, the diagonal matrix, the first initial data, and the second initial data are encrypted respectively to obtain corresponding first encrypted data, second encrypted data, and third encrypted data; then, the first encrypted data, the second encrypted data, and the third encrypted data are integrated to obtain corresponding integrated data; and the integrated data is subsequently used as the encrypted data. This application can achieve homomorphic encryption processing of the diagonal matrix, the first initial data, and the second initial data respectively based on the use of a homomorphic encryption strategy, thereby improving the data accuracy and data security of the generated encrypted data. And the processing based on homomorphic encryption can effectively prevent the original data of each participant and their respective model parameters from being leaked or inferred, and effectively protect the security of the model building process of the target prediction model.

[0125] In some optional implementations, step S205 includes the following steps:

[0126] A first specified matrix is ​​calculated based on the diagonal matrix and the characteristic data.

[0127] In this embodiment, according to the formula The first specified matrix is ​​calculated. AA is the first specified matrix, W is a diagonal matrix, X A is the characteristic data, The T in represents the transpose of the feature data.

[0128] The multiple encryption matrices are decrypted to obtain a corresponding first decryption matrix.

[0129] In this embodiment, the above encryption matrix includes three encrypted matrices Enc (D AB ), Enc(D BA ), Enc(D BB ). The encryption matrix may be decrypted to obtain a plurality of corresponding first decryption matrices.

[0130] An integration matrix is ​​generated based on the first specified matrix and the first decryption matrix, and an inverse matrix of the integration matrix is ​​calculated.

[0131] In this embodiment, H can be obtained by using the first designated matrix and the first decryption matrix as blocks to form a large integrated matrix and obtaining the corresponding inverse matrix.inv .

[0132] The inverse matrix is ​​divided vertically based on a preset first characteristic dimension to obtain the first matrix and the second matrix.

[0133] In this embodiment, the first characteristic dimension specifically refers to the dimension of each participant's characteristics. inv According to the characteristics of each participant, it is divided into H A and H B Two matrices, namely, the first matrix and the second matrix.

[0134] A second designated matrix is ​​constructed based on the first matrix, the characteristic data and the second initial data.

[0135] In this embodiment, by calculating To obtain the second specified matrix mentioned above. Among them, H A is the first matrix, X A is the characteristic data, and Wz is the second initial data.

[0136] The second specified matrix is ​​divided horizontally based on the first characteristic dimension to obtain the third matrix and the fourth matrix.

[0137] In this embodiment, the second specified matrix According to the characteristics of each participant, it is divided into M A1 and M B1 Two matrices, namely the third matrix and the fourth matrix. B and M B1 Sent to non-tagged party B.

[0138] The present application obtains a first designated matrix by calculating based on the diagonal matrix and the characteristic data; then decrypts the multiple encrypted matrices to obtain the corresponding first decrypted matrix; then generates an integrated matrix based on the first designated matrix and the first decrypted matrix, and calculates the inverse matrix of the integrated matrix; subsequently, the inverse matrix is ​​vertically divided based on a preset first characteristic dimension to obtain the first matrix and the second matrix; further, a second designated matrix is ​​constructed based on the first matrix, the characteristic data and the second initial data; finally, the second designated matrix is ​​horizontally divided based on the first characteristic dimension to obtain the third matrix and the fourth matrix. In this way, the present application performs vertical and horizontal division processing on the inverse matrix and the second designated matrix constructed by the multiple encrypted matrices sent by the non-label party based on the use of the first characteristic dimension, so that the corresponding first matrix, second matrix, third matrix and fourth matrix can be obtained quickly and accurately, thereby improving the processing efficiency and accuracy of matrix division.

[0139] In some optional implementations, step S206 includes the following steps:

[0140] The ciphertext matrix is ​​decrypted to obtain a corresponding second decryption matrix.

[0141] In this embodiment, the above ciphertext matrix is ​​specifically: H B is the second matrix, X B is the feature data in the non-labeled area, and Wz is the second initial data.

[0142] Get the preset second characteristic dimension.

[0143] In this embodiment, the second characteristic dimension specifically refers to the dimension of the characteristics of each participant.

[0144] The second decryption matrix is ​​horizontally divided based on the second characteristic dimension to obtain the fifth matrix and the sixth matrix.

[0145] In this embodiment, the second decryption matrix is ​​horizontally divided into M according to the feature dimension size of each participant. A2 and M B2 Two matrices, thereby obtaining the fifth matrix and the sixth matrix.

[0146] The present application obtains the corresponding second decryption matrix by decrypting the ciphertext matrix; then obtains the preset second characteristic dimension; and subsequently divides the second decryption matrix horizontally based on the second characteristic dimension to obtain the fifth matrix and the sixth matrix. The present application obtains the corresponding second decryption matrix by decrypting the ciphertext matrix, and then divides the second decryption matrix horizontally based on the use of the second characteristic dimension, so that the corresponding fifth matrix and the sixth matrix can be obtained quickly and accurately, effectively improving the processing efficiency and accuracy of matrix division.

[0147] In some optional implementations of this embodiment, step S207 includes the following steps:

[0148] When a preset iteration termination condition is met, a second model weight coefficient sent by the non-label party is received.

[0149] In this embodiment, the above-mentioned iteration termination condition refers to the loss function value reaching a certain numerical threshold or the total number of iterations reaching a preset maximum number of iterations. There is no specific limitation on the selection of the numerical threshold and the maximum number of iterations, which can be set according to actual business needs. In addition, the weight coefficient of the second model can be obtained by adding the fourth matrix and the sixth matrix, that is, β B =MB1 +M B2 Among them, β B is the weight coefficient of the second model, M B1 is the fourth matrix, M B2 is the sixth matrix.

[0150] Get the preset integration strategy.

[0151] In this embodiment, the strategy content of the above integration strategy may include appropriate splicing or weighting processing according to the characteristics and dimensions of each participant's feature data.

[0152] The first model weight coefficient and the second model weight coefficient are integrated based on the integration strategy to obtain a corresponding integration coefficient.

[0153] In this embodiment, the first model weight coefficient and the second model weight coefficient may be integrated according to the policy content of the above-mentioned integration policy, so as to obtain a corresponding integration coefficient and use it as the corresponding target model weight coefficient.

[0154] The integration coefficient is used as the target model weight coefficient.

[0155] When the preset iteration termination condition is met, the present application receives the second model weight coefficient sent by the non-label party; then obtains the preset integration strategy; then integrates the first model weight coefficient and the second model weight coefficient based on the integration strategy to obtain the corresponding integration coefficient; and subsequently uses the integration coefficient as the target model weight coefficient.

[0156] In some optional implementations of this embodiment, before step S208, the electronic device may further perform the following steps:

[0157] A specified storage strategy corresponding to the target prediction model is determined.

[0158] In this embodiment, there is no specific limitation on the selection of the above-mentioned designated storage strategy, which can be determined according to the actual storage business needs. Exemplarily, the designated storage strategy can adopt any one of blockchain storage, cloud server storage, local database storage, etc.

[0159] A designated storage medium corresponding to the designated storage policy is called.

[0160] In this embodiment, the above-mentioned target storage medium may include a blockchain, a cloud server, a local database, etc.

[0161] The target prediction model is stored based on the designated storage medium.

[0162] In this embodiment, after determining the designated storage medium corresponding to the designated storage strategy, the target prediction model is stored in the designated storage medium to complete the storage process of the target prediction model.

[0163] The present application determines a designated storage strategy corresponding to the target prediction model; then calls a designated storage medium corresponding to the designated storage strategy; and subsequently performs storage processing on the target prediction model based on the designated storage medium. The present application determines a designated storage strategy corresponding to the target prediction model, and then calls a designated storage medium corresponding to the designated storage strategy to perform storage processing on the target prediction model, which can effectively ensure the data security of the target prediction and improve the storage intelligence of the target prediction model.

[0164] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0165] This application is based on the application of iterative reweighted least squares method in generalized linear models, decomposes its formula and encrypts the data and applies it to the vertical federated learning of two parties to protect data privacy, and proposes a generalized linear model training method for vertical federated learning.

[0166] In addition, the non-Company software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0167] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0168] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target model weight coefficient, the above-mentioned target model weight coefficient can also be stored in a node of a blockchain.

[0169] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0170] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0171] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0173] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0174] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a data prediction processing device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0175] like Figure 3As shown, the artificial intelligence-based data prediction processing device 300 described in this embodiment includes: a first generation module 301, a second generation module 302, a construction module 303, an encryption module 304, a division module 305, a third generation module 306, a fourth generation module 307 and a processing module 308. Among them:

[0176] A first generating module 301, configured to generate a corresponding target inner product based on preset feature data, a weight coefficient and an inner product received from a non-label party;

[0177] A second generating module 302 is used to generate a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a preset loss function of a generalized linear model;

[0178] A construction module 303 is used to construct a corresponding diagonal matrix based on the second-order partial derivative, construct first initial data based on the diagonal matrix and the characteristic data, and construct second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative;

[0179] An encryption module 304 is used to encrypt the diagonal matrix, the first initial data and the second initial data respectively to obtain corresponding encrypted data;

[0180] A partitioning module 305 is used to calculate an inverse matrix and perform partitioning processing based on the received multiple encryption matrices sent by the non-label party to obtain corresponding first, second, third and fourth matrices; wherein the encryption matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix;

[0181] A third generating module 306 is configured to perform matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generate a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data;

[0182] A fourth generation module 307, configured to generate a target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party when a preset iteration termination condition is met; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix;

[0183] The processing module 308 is used to perform prediction processing on the business data to be processed based on the target prediction model corresponding to the target model weight coefficient.

[0184] In some optional implementations of this embodiment, the first generating module 301 includes:

[0185] A first calculation submodule, used for calculating the product of the feature data and the weight coefficient to obtain a corresponding specified inner product;

[0186] A first receiving submodule, configured to receive an inner product sent by the non-label party;

[0187] A second calculation submodule, used for calculating the sum of the specified inner product and the inner product;

[0188] The first determination submodule is used to use the sum value as the target inner product.

[0189] In some optional implementations of this embodiment, the encryption module 304 includes:

[0190] A first acquisition submodule is used to obtain a preset homomorphic encryption strategy;

[0191] An encryption submodule, used to encrypt the diagonal matrix, the first initial data and the second initial data respectively based on the homomorphic encryption strategy to obtain corresponding first encrypted data, second encrypted data and third encrypted data;

[0192] A first integration submodule, configured to integrate the first encrypted data, the second encrypted data and the third encrypted data to obtain corresponding integrated data;

[0193] The second determining submodule is used to use the integrated data as the encrypted data.

[0194] In some optional implementations of this embodiment, the division module 305 includes:

[0195] A third calculation submodule, configured to calculate a first specified matrix based on the diagonal matrix and the characteristic data;

[0196] A first decryption submodule, configured to perform decryption processing on the plurality of encryption matrices to obtain a corresponding first decryption matrix;

[0197] A generating submodule, configured to generate an integrated matrix based on the first specified matrix and the first decryption matrix, and calculate an inverse matrix of the integrated matrix;

[0198] A first division submodule, configured to vertically divide the inverse matrix based on a preset first characteristic dimension to obtain the first matrix and the second matrix;

[0199] A construction submodule, configured to construct a second specified matrix based on the first matrix, the characteristic data and the second initial data;

[0200] The second division submodule is used to divide the second specified matrix horizontally based on the first characteristic dimension to obtain the third matrix and the fourth matrix.

[0201] In some optional implementations of this embodiment, the third generating module 306 includes:

[0202] A second decryption submodule is used to decrypt the ciphertext matrix to obtain a corresponding second decryption matrix;

[0203] A second acquisition submodule, used to acquire a preset second feature dimension;

[0204] The third division submodule is used to divide the second decryption matrix horizontally based on the second characteristic dimension to obtain the fifth matrix and the sixth matrix.

[0205] In some optional implementations of this embodiment, the fourth generating module 307 includes:

[0206] A second receiving submodule, configured to receive a second model weight coefficient sent by the non-label party when a preset iteration termination condition is met;

[0207] The third acquisition submodule is used to acquire a preset integration strategy;

[0208] A second integration submodule, configured to integrate the first model weight coefficient and the second model weight coefficient based on the integration strategy to obtain a corresponding integration coefficient;

[0209] The third determination submodule is used to use the integration coefficient as the target model weight coefficient.

[0210] In some optional implementations of this embodiment, the data prediction processing device based on artificial intelligence further includes:

[0211] A determination module, used to determine a specified storage strategy corresponding to the target prediction model;

[0212] A calling module, used for calling a specified storage medium corresponding to the specified storage strategy;

[0213] A storage module is used to store the target prediction model based on the specified storage medium.

[0214] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0215] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0216] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0217] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a data prediction processing method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0218] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based data prediction processing method.

[0219] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0220] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based data prediction processing method.

[0221] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0222] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data prediction and processing method based on artificial intelligence, characterized in that: The steps include: Generate a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received from the non-label party; Generate a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a loss function of a preset generalized linear model; Constructing a corresponding diagonal matrix based on the second-order partial derivative, constructing first initial data based on the diagonal matrix and the characteristic data, and constructing second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative; Encrypting the diagonal matrix, the first initial data, and the second initial data respectively to obtain corresponding encrypted data; Based on the received multiple encrypted matrices sent by the non-label party, inverse matrices are calculated and divided to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix; Performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generating a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data; When a preset iteration termination condition is met, a target model weight coefficient is generated based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix; The business data to be processed is predicted based on the target prediction model corresponding to the target model weight coefficient.

2. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: The step of generating a corresponding target inner product based on the preset feature data, the weight coefficient and the inner product received and sent by the non-label party specifically includes: Calculating the product of the feature data and the weight coefficient to obtain a corresponding specified inner product; receiving an inner product sent by the non-label party; Calculate the sum of the specified inner product and the inner product; The sum is taken as the target inner product.

3. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: The step of respectively encrypting the diagonal matrix, the first initial data, and the second initial data to obtain corresponding encrypted data specifically includes: Get the preset homomorphic encryption strategy; Based on the homomorphic encryption strategy, the diagonal matrix, the first initial data, and the second initial data are encrypted respectively to obtain corresponding first encrypted data, second encrypted data, and third encrypted data; Integrate the first encrypted data, the second encrypted data and the third encrypted data to obtain corresponding integrated data; The integrated data is used as the encrypted data.

4. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: The step of calculating the inverse matrix and performing division processing based on the received multiple encrypted matrices sent by the non-label party to obtain the corresponding first matrix, second matrix, third matrix and fourth matrix specifically includes: Calculate a first specified matrix based on the diagonal matrix and the characteristic data; Decrypting the multiple encryption matrices to obtain a corresponding first decryption matrix; generating an integrated matrix based on the first specified matrix and the first decryption matrix, and calculating an inverse matrix of the integrated matrix; Based on a preset first characteristic dimension, the inverse matrix is ​​divided vertically to obtain the first matrix and the second matrix; constructing a second designated matrix based on the first matrix, the characteristic data and the second initial data; The second specified matrix is ​​divided horizontally based on the first characteristic dimension to obtain the third matrix and the fourth matrix.

5. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: The step of performing matrix division based on the received ciphertext matrix sent by the non-label party to obtain the fifth matrix and the sixth matrix specifically includes: Decrypting the ciphertext matrix to obtain a corresponding second decryption matrix; Obtaining a preset second characteristic dimension; The second decryption matrix is ​​horizontally divided based on the second characteristic dimension to obtain the fifth matrix and the sixth matrix.

6. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: The step of generating a target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party when a preset iteration termination condition is met specifically includes: When a preset iteration termination condition is met, receiving a second model weight coefficient sent by the non-label party; Get preset integration strategies; Integrate the first model weight coefficient and the second model weight coefficient based on the integration strategy to obtain a corresponding integration coefficient; The integration coefficient is used as the target model weight coefficient.

7. The data prediction and processing method based on artificial intelligence according to claim 1 is characterized in that: Before the step of performing prediction processing on the service data to be processed based on the target prediction model corresponding to the target model weight coefficient, the method further includes: Determining a specified storage strategy corresponding to the target prediction model; Invoking a specified storage medium corresponding to the specified storage strategy; The target prediction model is stored based on the designated storage medium.

8. A data prediction and processing device based on artificial intelligence, characterized in that: include: A first generating module, configured to generate a corresponding target inner product based on preset feature data, a weight coefficient and an inner product received from a non-label party; A second generating module, used for generating a first-order partial derivative and a second-order partial derivative corresponding to the target inner product based on a preset loss function of a generalized linear model; A construction module, configured to construct a corresponding diagonal matrix based on the second-order partial derivative, construct first initial data based on the diagonal matrix and the characteristic data, and construct second initial data based on the diagonal matrix, the target inner product and the first-order partial derivative; An encryption module, used to encrypt the diagonal matrix, the first initial data and the second initial data respectively to obtain corresponding encrypted data; A partitioning module, configured to calculate an inverse matrix and perform partitioning processing based on the received multiple encrypted matrices sent by the non-label party to obtain corresponding first, second, third and fourth matrices; wherein the encrypted matrix is ​​generated based on the encrypted data; and the third and fourth matrices are generated based on the first matrix; A third generating module, configured to perform matrix division based on the received ciphertext matrix sent by the non-label party to obtain a fifth matrix and a sixth matrix, and generate a first model weight coefficient based on the third matrix and the fifth matrix; wherein the ciphertext matrix is ​​generated based on the second matrix and the second initial data; A fourth generation module, configured to generate a target model weight coefficient based on the first model weight coefficient and the second model weight coefficient received and sent by the non-label party when a preset iteration termination condition is met; wherein the second model weight coefficient is generated based on the fourth matrix and the sixth matrix; A processing module is used to perform prediction processing on the business data to be processed based on the target prediction model corresponding to the target model weight coefficient.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the artificial intelligence-based data prediction processing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based data prediction processing method according to any one of claims 1 to 7.

Images