Information processing method and apparatus, electronic device, and computer-readable storage medium

Abstract

The information processing method provided by the present disclosure can be applied to the technical field of computers and the technical field of financial technology. The information processing method comprises the following steps: in response to receiving an information processing request, obtaining object information corresponding to N operation link identifiers respectively according to M object identifiers indicated by the information processing request, wherein M and N are positive integers; generating a joint model according to the object information corresponding to the N operation link identifiers respectively, wherein the joint model is obtained by jointly training the object information corresponding to the N operation link identifiers by a first terminal and a second terminal; and in response to receiving an object evaluation request from the second terminal, inputting a target object identifier and a target operation link identifier in the object evaluation request into the joint model to obtain an object evaluation result.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the fields of computer technology, information processing technology, blockchain technology and financial technology, and more particularly, to an information processing method and apparatus, an electronic device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the development of computer technology, in order to protect the security of network behavior information flow related to users, privacy computing (i.e. Privacy Compute) technology emerges as the times require.

[0003] The privacy computing technology can refer to a set of technologies for realizing data analysis and computation while protecting data itself from being disclosed to the outside. Through the privacy computing technology, the circulation of data value can be realized.

[0004] In the process of implementing the present concept, the inventors have found that there are at least the following problems in the related art: In some technical fields, there is a problem that the real-time performance of information processing and the security of information cannot be guaranteed, and therefore how to effectively apply the privacy computing technology to these technical fields is a technical problem to be solved. SUMMARY

[0005] Therefore, the present disclosure provides an information processing method and apparatus, an electronic device, a computer readable storage medium and a computer program product.

[0006] According to an aspect of the present disclosure, an information processing method is provided, comprising: in response to receiving an information processing request, obtaining object information corresponding to each of N operation link identifiers according to M object identifiers indicated by the information processing request, wherein M and N are both positive integers. Generating a joint model according to the object information corresponding to each of the N operation link identifiers, wherein the joint model is obtained by jointly training the object information corresponding to each of the N operation link identifiers by a first terminal and a second terminal. In response to receiving an object evaluation request from the second terminal, inputting a target object identifier and a target operation link identifier in the object evaluation request into the joint model to obtain an object evaluation result.

[0007] According to an embodiment of the present disclosure, generating the joint model according to the object information corresponding to each of the N operation link identifiers comprises: processing the object information corresponding to each of the N operation link identifiers to obtain preprocessed information. Sending a predetermined public key and the preprocessed information to the first terminal and the second terminal, so that the first terminal and the second terminal perform local partial model training according to the preprocessed information respectively. In response to receiving initial partial model parameters, determining the joint model according to the preprocessed information and the initial partial model parameters.

[0008] According to an embodiment of the present disclosure, the initial local model parameters include first initial local model parameters from the first terminal and second initial local model parameters from the second terminal. In response to receiving the initial local model parameters, determining the joint model according to the preprocessing information and the initial local model parameters includes: in response to receiving the first initial local model parameters and the second initial local model parameters, processing the first initial local model parameters and the second initial local model parameters to obtain joint model parameters. Training the predetermined model by using the preprocessing information and the joint model parameters to obtain the joint model.

[0009] According to an embodiment of the present disclosure, processing the first initial local model parameters and the second initial local model parameters to obtain the joint model parameters includes: performing decryption processing on the first initial local model parameters and the second initial local model parameters respectively according to a predetermined public key to obtain first local model parameters and second local model parameters. Performing aggregation processing on the first local model parameters and the second local model parameters to obtain the joint model parameters.

[0010] According to an embodiment of the present disclosure, training the predetermined model by using the preprocessing information and the joint model parameters to obtain the joint model includes: inputting the preprocessing information into the predetermined model to obtain initial model parameters. Updating the initial model parameters by using the joint model parameters to obtain the joint model.

[0011] According to an embodiment of the present disclosure, the object information includes first object information from the first terminal and second object information from the second terminal. Processing the object information corresponding to the N operation link identifiers respectively to obtain the preprocessing information includes: for each operation link identifier in the N operation link identifiers, performing multi-party private intersection processing on the first object information and the second object information corresponding to the operation link identifier to obtain object intersection information corresponding to the operation link identifier. Determining the preprocessing information according to the object intersection information corresponding to the N operation link identifiers respectively.

[0012] According to an embodiment of the present disclosure, determining the preprocessing information according to the object intersection information corresponding to the N operation link identifiers respectively includes: performing feature binning processing on the object intersection information corresponding to the N operation link identifiers respectively to obtain binned feature data corresponding to the N operation link identifiers respectively. Performing feature alignment processing on the binned feature data corresponding to the N operation link identifiers respectively to obtain aligned feature data corresponding to the N operation link identifiers respectively. Performing encryption processing on the aligned feature data corresponding to the N operation link identifiers respectively according to a predetermined public key to obtain the preprocessing information.

[0013] According to an embodiment of the present disclosure, the object evaluation request further comprises a user identifier, and the object evaluation result comprises a permission evaluation sub-result and a risk evaluation sub-result. In response to receiving the object evaluation request from the second terminal, inputting the target object identifier and the target operation link identifier in the object evaluation request into the joint model to obtain the object evaluation result comprises: inputting the user identifier, the target object identifier and the target operation link identifier into the joint model to obtain user permission information and user risk information. In response to the user risk information meeting a first predetermined condition, determining a risk evaluation sub-result representing that the user does not have an operation risk. In response to the user permission information meeting a second predetermined condition, determining a permission evaluation sub-result representing that the user has an operation permission corresponding to the target operation link of the target object.

[0014] According to an embodiment of the present disclosure, the operation link identifier is used to represent an operation link, and the data source stores candidate object information corresponding to each of P candidate object identifiers and Q candidate operation link identifiers, wherein P and Q are positive integers. In response to receiving the information processing request, obtaining the object information corresponding to each of the N operation link identifiers according to the M object identifiers indicated by the information processing request comprises: for each object identifier in the M object identifiers, for each operation link identifier in the N operation link identifiers corresponding to the object identifier, matching the P candidate object identifiers in the data source according to the object identifier to obtain an object identifier matching result. In response to the object identifier matching result representing that the object identifier and the candidate object identifier match, matching the Q candidate operation link identifiers corresponding to the candidate object identifier according to the operation link identifier to obtain an operation link identifier matching result. In response to the operation link identifier matching result representing that the operation link identifier and the candidate operation link identifier match, determining the candidate object information corresponding to the candidate operation link identifier as the object information corresponding to the operation link identifier.

[0015] According to an embodiment of the present disclosure, the information processing method further comprises, after inputting the target object identifier and the target operation link identifier in the object evaluation request into the joint model to obtain the object evaluation result in response to receiving the object evaluation request from the second terminal: sending the target object identifier, the target operation link identifier and the object evaluation result to the blockchain network, so that the blockchain network stores the target object identifier, the target operation link identifier and the object evaluation result in association.

[0016] According to another aspect of this disclosure, an information processing apparatus is provided, including an acquisition module, a generation module, and an input module. The acquisition module is configured to, in response to receiving an information processing request, acquire object information corresponding to N operation step identifiers based on M object identifiers indicated in the information processing request, where M and N are both positive integers. The generation module is configured to generate a joint model based on the object information corresponding to the N operation step identifiers, wherein the joint model is obtained by jointly training a first terminal and a second terminal on the object information corresponding to the N operation step identifiers. The input module is configured to, in response to receiving an object evaluation request from the second terminal, input the target object identifier and the target operation step identifier from the object evaluation request into the joint model to obtain an object evaluation result.

[0017] According to another aspect of this disclosure, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more instructions, wherein, when the one or more instructions are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described above.

[0018] According to another aspect of this disclosure, a computer-readable storage medium is provided having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method described above.

[0019] According to another aspect of this disclosure, a computer program product is provided, which includes computer-executable instructions that, when executed, are used to implement the method described above.

[0020] According to embodiments of this disclosure, since the joint model is obtained by jointly training the object information corresponding to each operation link identifier by the first terminal and the second terminal, and the object information corresponding to each operation link identifier is obtained according to the object identifier indicated by the information processing request, joint modeling of the first terminal and the second terminal is realized. This is beneficial for obtaining object evaluation results based on the joint model, thereby improving the real-time performance of information processing. Furthermore, since the object evaluation result is obtained by inputting the target object identifier and target operation link identifier of the object evaluation request terminal into the joint model after receiving the object evaluation request from the second terminal, the object evaluation result can be used to characterize the permission evaluation and risk evaluation situations corresponding to the target object identifier and target operation link identifier. This at least partially overcomes the technical problem in related technologies where it is difficult to apply privacy computing technology to certain technical fields. By performing information processing based on privacy computing, information security during information processing is ensured. Furthermore, by using the joint model obtained through joint training by the first terminal and the second terminal, the accuracy of subsequent information processing is improved. Attached Figure Description

[0021] The above and other objects, features and advantages of the present disclosure will be more clearly understood from the following description taken in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A system architecture to which an information processing method according to an embodiment of the present disclosure can be applied is schematically illustrated;

[0023] Figure 2 A flowchart of an information processing method according to an embodiment of the present disclosure is schematically illustrated;

[0024] Figure 3 A flowchart of an information processing method according to another embodiment of the present disclosure is schematically illustrated;

[0025] Figure 4 A flowchart of an information processing method according to still another embodiment of the present disclosure is schematically illustrated;

[0026] Figure 5 An interaction diagram of an information processing method according to an embodiment of the present disclosure is schematically illustrated;

[0027] Figure 6 A diagram of an information processing method according to an embodiment of the present disclosure is schematically illustrated;

[0028] Figure 7 A block diagram of an information processing apparatus according to an embodiment of the present disclosure is schematically illustrated; and

[0029] Figure 8 A block diagram of an electronic device suitable for implementing an information processing method according to an embodiment of the present disclosure is schematically illustrated. DETAILED DESCRIPTION

[0030] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It is to be understood, however, the description is merely exemplary of the present disclosure, but not intended to be limiting thereof. In the following detailed description of the embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it would be apparent to those skilled in the art that the present disclosure can be practiced without such specific details. In other instances, well-known structures and functions have been not described in detail in order not to obscure the concepts of the present disclosure.

[0031] The terminology used herein is for the purpose of describing embodiments only and is not intended to be limiting of the present disclosure. As used herein, the term "including" and "comprising" and the like are meant to be inclusive in a manner that there are no other non-mentioned items.

[0032] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the use of terms herein, such as should be construed to have a meaning consistent with the context of this specification and relevant art, and should not be construed ideally or overly formally.

[0033] In the case of using expressions similar to "at least one of A, B, and C, etc.", in general, it should be interpreted as having the meaning commonly understood by one of ordinary skill in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.).

[0034] In the technical solutions of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations, necessary security measures are taken, and public order and good customs are not violated.

[0035] In the technical solutions of the present disclosure, the authorization or consent of the user is obtained before acquiring or collecting user personal information.

[0036] The privacy computing technology can include at least one of the following: secure multi-party computation (MPC), federated learning (FL), trusted execution environment (TEE), and multi-party intermediary computation (MPIC).

[0037] In some technical fields, there are problems that the real-time performance of information processing and the security of information cannot be guaranteed. For example, in the medical device field, due to the characteristics of high professionalism and high technical requirements, financial institutions lack the professionalism in the medical device field, and therefore need to use traditional supply chains to meet the financing needs of the medical device field, which makes it difficult to accurately know the production and operation and sales process of various manufacturers in the medical device field, and it is even more difficult to guarantee the security of medical device product information. Therefore, how to effectively apply privacy computing technology to these technical fields in order to realize the management of medical device products is a technical problem to be solved.

[0038] To at least partially solve the technical problems existing in the related art, the present disclosure provides an information processing method, comprising: in response to receiving an information processing request, obtaining object information corresponding to N operation link identifiers respectively according to M object identifiers indicated by the information processing request, wherein M and N are both positive integers. Generating a joint model according to the object information corresponding to the N operation link identifiers respectively, wherein the joint model is obtained by jointly training the object information corresponding to the N operation link identifiers by a first terminal and a second terminal. And in response to receiving an object evaluation request from the second terminal, inputting a target object identifier and a target operation link identifier in the object evaluation request into the joint model to obtain an object evaluation result.

[0039] It should be noted that the information processing method and device provided by the embodiments of the present disclosure can be used in the field of computer technology. The information processing method and device provided by the embodiments of the present disclosure can also be used in any field other than the field of computer technology, for example, applied to the field of financial technology. The application field of the information processing method and device provided by the embodiments of the present disclosure is not limited.

[0040] Figure 1 The system architecture to which the information processing method according to the embodiments of the present disclosure can be applied is schematically shown. It should be noted that, Figure 1 The system architecture shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be applied to other devices, systems, environments or scenarios.

[0041] As Figure 1 shown, the system architecture 100 according to the embodiment can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0042] A user can use at least one of the first terminal device 101, the second terminal device 102 and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102 and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0043] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to a smartphone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0044] The server 105 can be a server providing various services, such as a background management server (as an example only) providing support for a website browsed by a user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server can perform analysis and the like on received user requests and the like, and feed back the processing results (such as a webpage, information, or data generated or obtained according to a user request) to the terminal device.

[0045] It should be noted that the information processing method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the information processing apparatus provided by the embodiments of the present disclosure can generally be arranged in the server 105. The information processing method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the information processing apparatus provided by the embodiments of the present disclosure can also be arranged in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0046] Alternatively, the information processing method provided by the embodiments of the present disclosure can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or can also be executed by another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the information processing apparatus provided by the embodiments of the present disclosure can also be arranged in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or can also be arranged in another terminal device different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0047] It should be understood that, Figure 1 The number of terminal devices, networks, and servers in the above-mentioned system is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks, and servers.

[0048] It should be noted that the serial numbers of the various operations in the following methods are only used to represent the operations for description, and should not be regarded as representing the execution sequence of the various operations. Unless explicitly indicated, the method does not need to be executed in the order shown.

[0049] Figure 2 A flowchart of an information processing method according to an embodiment of the present disclosure is shown.

[0050] As shown in Figure 2 The information processing method includes operations S210-S230.

[0051] In operation S210, in response to receiving an information processing request, object information corresponding to N operation link identifiers respectively is acquired according to M object identifiers indicated by the information processing request, where M and N are both positive integers.

[0052] In operation S220, a joint model is generated according to the object information corresponding to the N operation link identifiers respectively.

[0053] In operation S230, in response to receiving an object evaluation request from a second terminal, a target object identifier and a target operation link identifier in the object evaluation request are input into the joint model to obtain an object evaluation result.

[0054] According to an embodiment of the present disclosure, the information processing method 200 can be applied in the field of supply chain management. For example, the information processing method 200 can be applied in the management of medical instrument products, the management of industrial production equipment, etc. The object identifier can represent the unique identifier of the product. For example, in the case where the information processing method is applied in the field of management of medical instrument products, the object identifier can be the product name, for example, the object identifier can be the medical instrument product name "smart blood pressure meter". Alternatively, in the case where the information processing method is applied in the field of management of industrial production equipment, the object identifier can be the equipment name, for example, the object identifier can be the industrial production equipment name "flow meter".

[0055] According to an embodiment of the present disclosure, the operation link identifier represents the identifier of the operation link of the product. The operation link identifier can be the name of the operation link of the product. For example, the operation link can include at least one of the following: product design link, raw material procurement link, production line formulation link, production processing link, finished product assembly link, product warehouse storage link, commodity shelving link, customer ordering link, delivery and transportation link, after-sales link (return and exchange repair), etc.

[0056] According to an embodiment of the present disclosure, the object information represents information generated in a product operation link process. The object information can be information generated in a product operation link process. For example, the object information can be information of a product design link, information of a production line formulation link, information of a production processing link, information of a finished product assembly link, information of a product warehousing storage link, information of an after-sales link, and the like. The information of the production line formulation link can include at least one of scheduling information, quality management information, resource information, product tracking information, production inspection information. The information of the product warehousing storage link can include at least one of receiving mode information, shelving mode information, warehouse details, warehouse use area information. The information of the after-sales link can include at least one of return information, exchange information, repair information, complaint information.

[0057] According to an embodiment of the present disclosure, the first terminal represents a terminal for monitoring the object information. The first terminal can be an industrial internet platform, which can comprehensively and deeply perceive the object information, real-time transmission and exchange, rapid calculation and processing, modeling analysis, and the like.

[0058] According to an embodiment of the present disclosure, the second terminal represents a terminal for obtaining the object evaluation result. The second terminal can be a server of a financial institution. The server of the financial institution can perform modeling analysis on the object information.

[0059] According to an embodiment of the present disclosure, the joint model is obtained by jointly training the first terminal and the second terminal on the object information corresponding to the N operation link identifiers, respectively. The joint training can be a vertical federated mode using a federated learning platform, and the first terminal and the second terminal are respectively taken as an object information holder to achieve joint modeling and calculation through model training and model inference.

[0060] According to an embodiment of the present disclosure, the object evaluation result represents a result of evaluating the object information. The object evaluation result can be a result of analyzing the object information to obtain a risk evaluation result, a credit evaluation result, and the like of the object.

[0061] For example, M is equal to 2, and N is equal to 3. In the case of receiving an information processing request, the information processing request indicates two object identifiers, which are "intelligent blood pressure meter" and "heart rate meter", respectively. The three operation link identifiers are "product design link", "production line formulation link", and "production processing link", respectively. According to the object identifier "intelligent blood pressure meter" indicated by the information processing request, the object information corresponding to the three operation link identifiers is obtained. According to the object identifier "heart rate meter" indicated by the information processing request, the object information corresponding to the three operation link identifiers is obtained.

[0062] On this basis, according to the object information corresponding to the three operation links respectively, the first terminal and the second terminal can be respectively taken as the object information holder, joint modeling and calculation can be realized through model training and model inference, and a joint model can be generated. In the case of receiving an object evaluation request from the second terminal, the target object identifier and the target operation link identifier in the object evaluation request are input into the joint model, and an object evaluation result is obtained.

[0063] According to the embodiments of the present disclosure, since the joint model is obtained by joint training of the first terminal and the second terminal on the object information corresponding to the operation link identifiers respectively, and the object information corresponding to the operation link identifiers is obtained according to the object identifier indicated by the information processing request, the joint modeling of the first terminal and the second terminal is realized, which is beneficial to obtaining the object evaluation result based on the joint model subsequently, thereby improving the real-time performance of information processing. On this basis, since the object evaluation result is obtained by inputting the target object identifier and the target operation link identifier in the object evaluation request into the joint model after receiving the object evaluation request from the second terminal, the object evaluation result can be used to represent the permission evaluation and risk evaluation corresponding to the target object identifier and the target operation link identifier, at least partially overcoming the technical problem that it is difficult to apply the privacy computing technology to some technical fields in the related art, and the information security in the information processing process is ensured by performing information processing based on privacy computing calculation, and on this basis, the accuracy of subsequent information processing is improved by using the joint model obtained by joint training of the first terminal and the second terminal.

[0064] According to the embodiments of the present disclosure, according to the object information corresponding to the N operation link identifiers respectively, the joint model is generated, including: processing the object information corresponding to the N operation link identifiers respectively to obtain preprocessed information. The predetermined public key and the preprocessed information are sent to the first terminal and the second terminal, so that the first terminal and the second terminal perform local partial model training according to the preprocessed information respectively. In response to receiving the initial local model parameters, the joint model is determined according to the preprocessed information and the initial local model parameters.

[0065] According to an embodiment of the present disclosure, the pre-processing information characterizes processed information of the object information corresponding to each of the N operation link identifiers. The processing manner can include at least one of summing, intersection, or the like, of the object information corresponding to each of the N operation link identifiers. The summing can be merging the object information corresponding to the N operation link identifiers of the first terminal and the object information corresponding to the N operation link identifiers of the second terminal. The intersection can be comparing the object information corresponding to the N operation link identifiers of the first terminal and the object information corresponding to the N operation link identifiers of the second terminal to obtain the same information of the object information corresponding to the N operation link identifiers of the first terminal and the second terminal.

[0066] According to an embodiment of the present disclosure, the predetermined public key characterizes a key for encrypting the object information corresponding to each of the N operation link identifiers.

[0067] According to an embodiment of the present disclosure, the local model can include at least one of a Linear Regression model (LR), a Logistic Regression model (LR), a Decision Tree model (DT), a Neural Networks model (NN), or the like.

[0068] According to an embodiment of the present disclosure, the initial local model parameter can be a gradient parameter of the model.

[0069] For example, N is equal to 1. The operation link identifier can be a "production line formulation link". The intersection processing of the object information corresponding to each of the operation link identifier "production line formulation link" of the first terminal and the second terminal obtains the pre-processing information. The predetermined public key is public key 1. The public key 1 and the pre-processing information are sent to the first terminal and the second terminal. The local model training can be a linear regression model training. The first terminal and the second terminal perform local linear regression model training according to the pre-processing information respectively. The initial local model parameter can be a gradient parameter of the initial linear regression model. In response to receiving the gradient parameter of the initial linear regression model, the joint model is determined according to the pre-processing information and the initial local model parameter.

[0070] According to an embodiment of the present disclosure, the predetermined public key and the pre-processing information are sent to the first terminal and the second terminal, so that the first terminal and the second terminal perform local model training according to the pre-processing information respectively. On this basis, by determining the joint model according to the pre-processing information and the initial local model parameter, data leakage can be avoided in the process of determining the joint model, and the security of information processing is improved.

[0071] According to an embodiment of the present disclosure, in response to receiving the initial local model parameters, determining the joint model according to the pre-processing information and the initial local model parameters comprises: in response to receiving the first initial local model parameters and the second initial local model parameters, processing the first initial local model parameters and the second initial local model parameters to obtain joint model parameters. The predetermined model is trained by using the pre-processing information and the joint model parameters to obtain the joint model.

[0072] According to an embodiment of the present disclosure, the initial local model parameters comprise first initial local model parameters from the first terminal and second initial local model parameters from the second terminal.

[0073] For example, the first initial local model parameters can be first initial gradient parameters of the local model from the first terminal. The second initial local model parameters are second initial gradient parameters of the local model from the second terminal. The first initial gradient parameters and the second initial gradient parameters are processed to obtain joint model parameters. The processing manner can be mean variance processing. The predetermined model is trained by using the pre-processing information and the joint model parameters to obtain the joint model.

[0074] According to an embodiment of the present disclosure, by processing the first initial local model parameters and the second initial local model parameters to obtain joint model parameters, and then training the predetermined model to obtain the joint model, the joint model is used for multi-terminal interaction, and the efficiency of information processing between the terminals is improved.

[0075] Figure 3 A flowchart of an information processing method according to another embodiment of the present disclosure is schematically shown.

[0076] As shown in Figure 3 The information processing method of another embodiment of the present disclosure comprises operations S310-S330.

[0077] In operation S310, the first initial local model parameters and the second initial local model parameters are respectively decrypted according to the predetermined public key to obtain the first local model parameters and the second local model parameters.

[0078] In operation S320, the first local model parameters and the second local model parameters are aggregated to obtain joint model parameters.

[0079] In operation S330, the pre-processing information is input into the predetermined model to obtain initial model parameters.

[0080] In operation S340, the initial model parameters are updated by using the joint model parameters to obtain a joint model.

[0081] According to embodiments of this disclosure, the server is responsible for distributing the public key of the first terminal and the public key of the second terminal, but not the private key. Therefore, the decryption process can be that the server uses the private key to decrypt the first initial local model parameters encrypted by the first terminal using the public key, and then decrypts the second initial local model parameters encrypted by the second terminal using the public key.

[0082] According to embodiments of this disclosure, the aggregation process may combine a first local model parameter and a second local model parameter into a single joint model parameter. The aggregation process merges multiple local model parameters to obtain a more comprehensive or more representative representation.

[0083] According to embodiments of this disclosure, the predetermined model may include at least one of the following: a linear regression model, a logistic regression model, a decision tree model, and a neural network model, etc. The predetermined model can obtain object evaluation results based on preprocessed information and joint model parameters.

[0084] For example, the predetermined public key is public key C. The server distributes public key C to the first terminal and the second terminal. The server retains the private key C corresponding to public key C. The server determines the private key C based on public key C. The server uses private key C to decrypt the first initial local model parameters and the second initial local model parameters respectively, obtaining the first local model parameters and the second local model parameters. The first local model parameters and the second local model parameters are aggregated to obtain the joint model parameters. The predetermined model can be a neural network model. Preprocessed information is input into the neural network model to obtain the initial model parameters. The initial model parameters are updated using the joint model parameters to obtain the joint model.

[0085] According to embodiments of this disclosure, by aggregating the parameters of the first local model and the parameters of the second local model, and then using the joint model parameters to update the initial model parameters, a joint model is obtained. This makes the object evaluation results output by the joint model more comprehensive and representative, thereby improving the accuracy of information processing.

[0086] Figure 4 A flowchart illustrating an information processing method according to yet another embodiment of the present disclosure is shown.

[0087] like Figure 4 As shown, another embodiment of the information processing method of this disclosure includes operations S410 to S440.

[0088] In operation S410, for each of the N operation step identifiers, multi-party privacy intersection processing is performed on the first object information and the second object information corresponding to the operation step identifier to obtain the object intersection information corresponding to the operation step identifier.

[0089] At operation S420, feature binning processing is performed on the object intersection information corresponding to each of the N operation link identifiers, to obtain feature data after binning processing corresponding to each of the N operation link identifiers.

[0090] At operation S430, feature alignment processing is performed on the feature data after binning processing corresponding to each of the N operation link identifiers, to obtain feature data after alignment processing corresponding to each of the N operation link identifiers.

[0091] At operation S440, encryption processing is performed on the feature data after alignment processing corresponding to each of the N operation link identifiers according to a predetermined public key, to obtain pre-processing information.

[0092] According to an embodiment of the present disclosure, the object information includes first object information from a first terminal and second object information from a second terminal.

[0093] According to an embodiment of the present disclosure, the multi-party privacy intersection processing can calculate the intersection of the first object information of the first terminal and the second object information from the second terminal without revealing the object information of the first terminal and the second terminal other than the intersection.

[0094] According to an embodiment of the present disclosure, the feature binning processing is a method of grouping a plurality of continuous value object intersection information into a smaller number of "bins". The feature binning processing can include at least one of the following: equal-width binning, equal-frequency binning, or clustering binning.

[0095] According to an embodiment of the present disclosure, the feature alignment processing can be a collation of user information of the intersection of the first object information of the first terminal and the second object information of the second terminal. Since the first object information of each user of the first terminal and the second object information of each user of the second terminal do not completely coincide, collation is needed through the object information of each user to determine the common operation link information.

[0096] For example, N is equal to 1. For the operation link identifier "production line planning link", the first object information corresponding to the operation link identifier "production line planning link" includes "scheduling information" and "quality management information". The second object information corresponding to the operation link identifier "production line planning link" includes "quality management information". The multi-party privacy intersection processing is performed on the first object information and the second object information corresponding to the operation link identifier "production line planning link", to obtain the object intersection information corresponding to the operation link identifier, i.e., the object intersection information is "quality management information".

[0097] The feature binning processing is performed on the "quality management information" corresponding to the operation link identifier "production line planning link", to obtain the feature data after binning processing corresponding to the operation link identifier "production line planning link".

[0098] According to the detailed operation information in the quality management information, the feature data corresponding to the operation link identified as the production line setting link after the binning processing is subjected to feature alignment processing, to obtain the feature data corresponding to the operation link identified as the production line setting link after the alignment processing.

[0099] The predetermined public key can be the public key D. According to the predetermined public key D, the feature data corresponding to the operation link identified as the production line setting link after the alignment processing is subjected to encryption processing, to obtain the preprocessing information.

[0100] According to the embodiments of the present disclosure, by performing multi-party private intersection processing, feature binning processing, feature alignment processing and encryption processing on the first object information and the second object information corresponding to the operation link, the preprocessing information with reliability and accuracy can be obtained, thereby improving the efficiency and accuracy of information processing.

[0101] According to the embodiments of the present disclosure, in response to receiving the object evaluation request from the second terminal, the target object identifier and the target operation link identifier in the object evaluation request are input into the joint model to obtain the object evaluation result, including: inputting the user identifier, the target object identifier and the target operation link identifier into the joint model to obtain the user permission information and the user risk information. In response to the user risk information meeting the first predetermined condition, a risk evaluation sub-result representing that the user does not exist operation risk is determined. In response to the user permission information meeting the second predetermined condition, a permission evaluation sub-result representing that the user has the operation permission corresponding to the target operation link of the target object is determined.

[0102] According to the embodiments of the present disclosure, the object evaluation request further includes the user identifier, and the object evaluation result includes the permission evaluation sub-result and the risk evaluation sub-result. The permission evaluation sub-result represents that the user has the operation permission corresponding to the target operation link of the target object. The risk evaluation sub-result represents whether the user exists operation risk.

[0103] According to the embodiments of the present disclosure, the user permission information represents the operation link permission information that the user can perform. The user risk information represents the risk information of the user performing the operation link.

[0104] For example, the user identifier can be “A user”, the target object identifier can be “intelligent blood pressure instrument”, and the target operation link identifier can be “production line setting link”. “A user”, “intelligent blood pressure instrument” and “production line setting link” are input into the joint model to obtain the user permission information and the user risk information. The user permission information includes “A user can perform production line setting”, and the user risk information includes “A user does not exist operation risk of production line setting”.

[0105] The first predetermined condition can be that the user risk information includes information that "the user does not have an operational risk", and then a risk assessment sub-result that characterizes that the user does not have a target operational risk is determined. If the user risk information does not include information that "the user does not have a target operational risk", then a risk assessment sub-result that characterizes that the user has an operational risk is determined.

[0106] The second predetermined condition can be that the user permission information includes information that "the user can perform a target operation", and then a permission assessment sub-result that characterizes that the user has an operation permission corresponding to a target operation link of a target object is determined. If the user permission information does not include information that "the user can perform a target operation", then a permission assessment sub-result that characterizes that the user does not have an operation permission corresponding to a target operation link of a target object is determined.

[0107] According to an embodiment of the present disclosure, according to whether the user risk information meets the first predetermined condition, a risk assessment sub-result that characterizes whether the user has an operational risk is determined, and according to whether the user permission information meets the second predetermined condition, a permission assessment sub-result that characterizes whether the user has an operation permission corresponding to a target operation link of a target object is determined, which can make the object assessment result obtained by the joint model more accurate and help improve the accuracy of subsequent information processing.

[0108] According to an embodiment of the present disclosure, in response to receiving an information processing request, obtaining object information corresponding to each of the N operation link identifiers according to the M object identifiers indicated by the information processing request includes: for each of the M object identifiers, for each of the N operation link identifiers corresponding to the object identifier, matching the P candidate object identifiers in the data source according to the object identifier respectively to obtain an object identifier matching result. In response to the object identifier matching result characterizing that the object identifier and the candidate object identifier match, matching the Q candidate operation link identifiers corresponding to the candidate object identifier according to the operation link identifier respectively to obtain an operation link identifier matching result. In response to the operation link identifier matching result characterizing that the operation link identifier and the candidate operation link identifier match, determining the candidate object information corresponding to the candidate operation link identifier as the object information corresponding to the operation link identifier.

[0109] According to an embodiment of the present disclosure, the operation link identifier is used to characterize an operation link, and the data source stores candidate object information corresponding to each of the P candidate object identifiers and the Q candidate operation link identifiers, and P and Q are both positive integers.

[0110] For example, M equals 2, N equals 1, and P equals 4. For each of the two object identifiers, and for each of the one operation step identifiers corresponding to the object identifier, the four candidate object identifiers in the data source are matched according to the object identifier to obtain the object identifier matching result. Q equals 2. In response to the object identifier matching result indicating that the object identifier and the candidate object identifier match, the two candidate operation step identifiers corresponding to the candidate object identifier are matched according to the operation step identifier to obtain the operation step identifier matching result. In response to the operation step identifier matching result indicating that the operation step identifier and the candidate operation step identifier match, the candidate object information corresponding to the candidate operation step identifier is determined as the object information corresponding to the operation step identifier.

[0111] According to embodiments of this disclosure, by matching the object identifier with the candidate object identifier in the data source, and by matching the operation step identifier with the candidate operation step identifier in the data source, the candidate object information corresponding to the candidate operation step identifier can be determined as the object information corresponding to the operation step identifier, thereby improving information processing efficiency.

[0112] According to embodiments of this disclosure, the above information processing method further includes, in response to receiving an object evaluation request from a second terminal, inputting the target object identifier and the target operation step identifier in the object evaluation request into the joint model to obtain the object evaluation result: sending the target object identifier, the target operation step identifier, and the object evaluation result to the blockchain network so that the blockchain network can associate and store the target object identifier, the target operation step identifier, and the object evaluation result.

[0113] For example, the target object identifier could be "smart blood pressure monitor" and the target operation step identifier could be "production line designation step". The "smart blood pressure monitor", "production line designation step", and object evaluation results are sent to a blockchain network. The blockchain network stores the "smart blood pressure monitor", "production line designation step", and object evaluation results in a linked manner.

[0114] According to embodiments of this disclosure, by sending the target object identifier, the target operation link identifier, and the object evaluation result to the blockchain network, the problems of information leakage and tampering can be solved, thereby improving the security of information processing.

[0115] Figure 5 The illustration shows an interactive diagram of an information processing method according to an embodiment of the present disclosure.

[0116] like Figure 5 As shown, the information processing method of this embodiment includes operations S501 to S512.

[0117] At operation S501, in response to receiving the information processing request, the server can obtain object information corresponding to the N operation link identifiers according to the M object identifiers indicated by the information processing request.

[0118] At operation S502, the server can process the object information corresponding to the N operation link identifiers to obtain preprocessed information.

[0119] At operation S503, the server can send the predetermined public key and the preprocessed information to the first terminal.

[0120] At operation S504, the server can send the predetermined public key and the preprocessed information to the second terminal.

[0121] At operation S505, the first terminal can perform local partial model training according to the preprocessed information to obtain first initial partial model parameters.

[0122] At operation S506, the first terminal can send the first initial partial model parameters to the server.

[0123] At operation S507, the second terminal can perform local partial model training according to the preprocessed information to obtain second initial partial model parameters.

[0124] At operation S508, the second terminal can send the second initial partial model parameters to the server.

[0125] At operation S509, in response to receiving the initial partial model parameters, the server can determine a joint model according to the preprocessed information and the initial partial model parameters.

[0126] At operation S510, the second terminal can send an object evaluation request to the server.

[0127] At operation S511, in response to receiving the object evaluation request from the second terminal, the server can input a target object identifier and a target operation link identifier in the object evaluation request into the joint model to obtain an object evaluation result.

[0128] At operation S512, the server can send the object evaluation result to the second terminal.

[0129] Figure 6 A schematic diagram of an information processing method according to an embodiment of the present disclosure is schematically shown.

[0130] As Figure 6As shown, the information processing method of this embodiment includes an operation step 610, a first terminal 620, a joint model 630, a second terminal 640, and a blockchain network 650. The operation step 610 includes a production operation step 611, a warehousing operation step 612, a sales operation step 613, a delivery operation step 614, and a usage operation step 615.

[0131] The first terminal 620 can perform comprehensive and in-depth perception of object information, real-time transmission and exchange, rapid calculation and processing, and modeling and analysis.

[0132] The joint model 630 can be used to generate object evaluation results. The joint model 630 is obtained by the first terminal 620 and the second terminal 640 jointly training the object information corresponding to the operation identifier.

[0133] The second terminal 640 can be used to receive the object evaluation results generated by the joint model 630.

[0134] Blockchain network 650 can be used to associate and store target object identifiers, target operation link identifiers, and object evaluation results.

[0135] Figure 7 A block diagram of an information processing apparatus according to an embodiment of the present disclosure is shown schematically.

[0136] like Figure 7 As shown, the information processing device 700 may include an acquisition module 710, a generation module 720, and an input module 730.

[0137] The acquisition module 710 is used to, in response to receiving an information processing request, acquire object information corresponding to each of the N operation step identifiers based on the M object identifiers indicated in the information processing request, where M and N are both positive integers. The acquisition module 710 can be used to execute the operation S210 described above, which will not be repeated here.

[0138] The generation module 720 is used to generate a joint model based on the object information corresponding to each of the N operation step identifiers. The joint model is obtained by jointly training the first terminal and the second terminal using the object information corresponding to each of the N operation step identifiers. The generation module 720 can be used to execute the operation S220 described above, which will not be repeated here.

[0139] Input module 730 is used to respond to receiving an object evaluation request from the second terminal by inputting the target object identifier and target operation step identifier from the object evaluation request into the joint model to obtain the object evaluation result. Input module 730 can be used to perform the operation S230 described above, which will not be repeated here.

[0140] According to an embodiment of the present disclosure, the generating module 720 comprises a processing submodule, a sending submodule and a first determining submodule. The processing submodule is configured to process the object information corresponding to each of the N operation link identifiers to obtain preprocessed information. The sending submodule is configured to send the predetermined public key and the preprocessed information to the first terminal and the second terminal, so that the first terminal and the second terminal perform local partial model training according to the preprocessed information respectively. The first determining submodule is configured to determine the joint model according to the preprocessed information and the initial partial model parameters in response to receiving the initial partial model parameters.

[0141] According to an embodiment of the present disclosure, the initial partial model parameters comprise first initial partial model parameters from the first terminal and second initial partial model parameters from the second terminal. The determining submodule comprises a processing unit and a training unit. The processing unit is configured to process the first initial partial model parameters and the second initial partial model parameters to obtain joint model parameters in response to receiving the first initial partial model parameters and the second initial partial model parameters. The training unit is configured to train the predetermined model by using the preprocessed information and the joint model parameters to obtain the joint model.

[0142] According to an embodiment of the present disclosure, the processing unit comprises a decryption processing subunit and an aggregation processing subunit. The decryption processing subunit is configured to perform decryption processing on the first initial partial model parameters and the second initial partial model parameters respectively according to the predetermined public key to obtain first partial model parameters and second partial model parameters. The aggregation processing subunit is configured to perform aggregation processing on the first partial model parameters and the second partial model parameters to obtain the joint model parameters.

[0143] According to an embodiment of the present disclosure, the training unit comprises an input subunit and an update subunit. The input subunit is configured to input the preprocessed information to the predetermined model to obtain initial model parameters. The update subunit is configured to update the initial model parameters by using the joint model parameters to obtain the joint model.

[0144] According to an embodiment of the present disclosure, the object information comprises first object information from the first terminal and second object information from the second terminal. The processing submodule comprises a multi-party privacy intersection unit and a determining unit. The multi-party privacy intersection unit is configured to perform multi-party privacy intersection processing on the first object information and the second object information corresponding to each of the N operation link identifiers to obtain object intersection information corresponding to the operation link identifier. The determining unit is configured to determine the preprocessed information according to the object intersection information corresponding to each of the N operation link identifiers.

[0145] According to an embodiment of the present disclosure, the determining unit comprises a bin processing subunit, a feature alignment subunit and an encryption processing subunit. The bin processing subunit is configured to perform feature bin processing on the object intersection information corresponding to the N operation link identifiers respectively, to obtain the bin-processed feature data corresponding to the N operation link identifiers respectively. The feature alignment subunit is configured to perform feature alignment processing on the bin-processed feature data corresponding to the N operation link identifiers respectively, to obtain the alignment-processed feature data corresponding to the N operation link identifiers respectively. The encryption processing subunit is configured to perform encryption processing on the alignment-processed feature data corresponding to the N operation link identifiers respectively according to a predetermined public key, to obtain the pre-processing information.

[0146] According to an embodiment of the present disclosure, the object evaluation request further comprises a user identifier, and the object evaluation result comprises a permission evaluation sub-result and a risk evaluation sub-result. The input module 730 comprises an input sub-module, a second determination sub-module and a third determination sub-module. The input sub-module is configured to input the user identifier, the target object identifier and the target operation link identifier to the joint model, to obtain the user permission information and the user risk information. The second determination sub-module is configured to determine the risk evaluation sub-result representing that the user does not have operation risk, in response to the user risk information meeting a first predetermined condition. The third determination sub-module is configured to determine the permission evaluation sub-result representing that the user has the operation permission corresponding to the target operation link of the target object, in response to the user permission information meeting a second predetermined condition.

[0147] According to an embodiment of the present disclosure, the operation link identifier is used to represent an operation link, and the data source stores candidate object information corresponding to P candidate object identifiers and Q candidate operation link identifiers respectively, wherein P and Q are positive integers. The obtaining module 710 comprises a first matching sub-module, a second matching sub-module and a fourth determination sub-module. The first matching sub-module is configured to, for each object identifier in the M object identifiers, and for each operation link identifier in the N operation link identifiers corresponding to the object identifier, match the P candidate object identifiers in the data source according to the object identifier respectively, to obtain an object identifier matching result. The second matching sub-module is configured to, in response to the object identifier matching result representing that the object identifier and the candidate object identifier match, match the Q candidate operation link identifiers corresponding to the candidate object identifier according to the operation link identifier respectively, to obtain an operation link identifier matching result. The fourth determination sub-module is configured to, in response to the operation link identifier matching result representing that the operation link identifier and the candidate operation link identifier match, determine the candidate object information corresponding to the candidate operation link identifier as the object information corresponding to the operation link identifier.

[0148] According to an embodiment of the present disclosure, the information processing apparatus further includes a sending module configured to, in response to receiving the object evaluation request from the second terminal, input the target object identifier and the target operation link identifier in the object evaluation request into the joint model to obtain the object evaluation result, and then send the target object identifier, the target operation link identifier, and the object evaluation result to the blockchain network, so that the blockchain network stores the target object identifier, the target operation link identifier, and the object evaluation result in association.

[0149] Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be implemented at least in part as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware by integrating or packaging the circuit, or in any one of software, hardware, and firmware or in an appropriate combination of any of them. Alternatively, one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be implemented at least in part as computer program modules that can perform corresponding functions when executed.

[0150] For example, any of the plurality of the acquisition module 710, the generation module 720 and the input module 730 can be combined in one module / unit / sub-unit, or any of the module / unit / sub-unit can be split into a plurality of modules / units / sub-units. Or, at least part of the function of one or more of the modules / units / sub-units can be combined with at least part of the function of other modules / units / sub-units, and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the acquisition module 710, the generation module 720 and the input module 730 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner that can be integrated or packaged to a circuit, etc. in hardware or firmware, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Or, at least one of the acquisition module 710, the generation module 720 and the input module 730 can be at least partially implemented as a computer program module which can perform the corresponding function when the computer program module is run.

[0151] It should be noted that the information processing device part in the embodiments of the present disclosure corresponds to the information processing method part in the embodiments of the present disclosure, and the description of the information processing device part is specifically referred to the information processing method part, which will not be repeated here.

[0152] Figure 8 A block diagram of an electronic device suitable for implementing the information processing method according to an embodiment of the present disclosure is schematically shown. Figure 8 The electronic device shown is merely an example, and should not bring any limitation to the function and use range of the embodiments of the present disclosure.

[0153] As Figure 8 shown, the computer electronic device 800 according to an embodiment of the present disclosure includes a processor 801 which can perform various appropriate actions and processes according to the program stored in a read-only memory (ROM) 802 or the program loaded from a storage part 808 to a random access memory (RAM) 803. The processor 801 can include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 801 can also include an on-board memory for cache use. The processor 801 can include a single processing unit or a plurality of processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0154] In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other via the bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 802 and / or the RAM 803. It is noted that the programs can also be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 can also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0155] According to an embodiment of the present disclosure, the electronic device 800 can further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 can further include one or more of the following components connected to the input / output (I / O) interface 805: an input part 806 including a keyboard, a mouse, etc.; an output part 807 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 808 including a hard disk, etc.; and a communication part 809 including a network interface card such as a LAN card, a modem, etc. The communication part 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 810 as necessary, so that a computer program read therefrom is installed in the storage part 808 as necessary.

[0156] According to an embodiment of the present disclosure, the method flow according to the embodiments of the present disclosure can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable storage medium, the computer program containing program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network by the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above-described functions defined in the system of the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the system, the device, the apparatus, the module, the unit, etc. described above can be implemented by computer program modules.

[0157] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist independently without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which when executed, implement the method according to the embodiments of the present disclosure.

[0158] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium. For example, it can include, but is not limited to: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in connection with an instruction execution system, apparatus, or device.

[0159] For example, according to an embodiment of the present disclosure, the computer readable storage medium can include one or more memories of the above-described ROM 802 and / or RAM 803 and / or one or more memories other than the ROM 802 and the RAM 803.

[0160] Embodiments of the present disclosure also include a computer program product, which includes a computer program containing program codes for executing the method provided by the embodiments of the present disclosure, and when the computer program product is run on an electronic device, the program codes are used to make the electronic device implement the information processing method provided by the embodiments of the present disclosure.

[0161] When the computer program is executed by the processor 801, the above functions defined in the system / apparatus of the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the above-described system, apparatus, module, unit, etc. can be implemented by computer program modules.

[0162] In one embodiment, the computer program can rely on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal on a network medium, and be downloaded and installed through the communication part 809, and / or be installed from the detachable medium 811. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to wireless, wired, etc., or any appropriate combination thereof.

[0163] According to embodiments of the present disclosure, program code of a computer program provided by embodiments of the present disclosure can be written in any combination of one or more programming languages, and specifically, can be implemented using a high-level procedural and / or object-oriented programming language, and / or an assembly / machine language. Programming languages include, but are not limited to, Java, C++, python, "C" language, or similar programming languages. Program code can execute entirely on a user's computing device, partly on a user device, partly on a remote computing device, or entirely on a remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0164] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0165] Embodiments of the present disclosure have been described above. However, these embodiments are merely intended to illustrate the present disclosure, and are not intended to limit the scope of the present disclosure. Although each of the embodiments is described above separately, this does not mean that the measures in each of the embodiments cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and these substitutions and modifications should all fall within the scope of the present disclosure.

Claims

1. An information processing method, comprising: In response to receiving an information processing request, based on the M object identifiers indicated by the information processing request, obtain object information corresponding to each of the N operation link identifiers, where M and N are both positive integers; A joint model is generated based on the object information corresponding to each of the N operation stage identifiers, wherein the joint model is obtained by jointly training the first terminal and the second terminal on the object information corresponding to each of the N operation stage identifiers; and In response to receiving an object evaluation request from the second terminal, the target object identifier and the target operation link identifier in the object evaluation request are input into the joint model to obtain the object evaluation result; The step of generating the joint model based on the object information corresponding to each of the N operation links includes: The object information corresponding to each of the N operation step identifiers is processed to obtain preprocessed information; The predetermined public key and the preprocessing information are sent to the first terminal and the second terminal so that the first terminal and the second terminal can perform local model training locally according to the preprocessing information. The predetermined public key represents the key used to encrypt the object information corresponding to the identifiers of the N operation links. In response to receiving a first initial local model parameter from the first terminal and a second initial local model parameter from the second terminal, the first initial local model parameter and the second initial local model parameter are processed to obtain joint model parameters; and Using the preprocessed information and the joint model parameters, a predetermined model is trained to obtain the joint model.

2. The method according to claim 1, wherein, The process of processing the first initial local model parameters and the second initial local model parameters to obtain the joint model parameters includes: Based on the predetermined public key, the first initial local model parameters and the second initial local model parameters are decrypted respectively to obtain the first local model parameters and the second local model parameters; and The first local model parameters and the second local model parameters are aggregated to obtain the joint model parameters.

3. The method according to claim 1, wherein, The step of training a predetermined model using the preprocessed information and the joint model parameters to obtain the joint model includes: The preprocessed information is input into the predetermined model to obtain initial model parameters; and The initial model parameters are updated using the joint model parameters to obtain the joint model.

4. The method according to claim 1, wherein, The object information includes first object information from the first terminal and second object information from the second terminal; The process of processing the object information corresponding to each of the N operation step identifiers to obtain preprocessed information includes: For each of the N operation step identifiers, Perform multi-party privacy intersection processing on the first object information and the second object information corresponding to the operation step identifier to obtain the object intersection information corresponding to the operation step identifier; as well as The preprocessing information is determined based on the intersection information of the objects corresponding to the N operation step identifiers.

5. The method according to claim 4, wherein, The step of determining the preprocessing information based on the intersection information of the objects corresponding to the identifiers of the N operation steps includes: The intersection information of the objects corresponding to the N operation step identifiers is subjected to feature binning to obtain the binned feature data corresponding to the N operation step identifiers. The binned feature data corresponding to each of the N operation step identifiers are subjected to feature alignment processing to obtain aligned feature data corresponding to each of the N operation step identifiers; and Based on the predetermined public key, the aligned feature data corresponding to each of the N operation step identifiers is encrypted to obtain the preprocessed information.

6. The method according to any one of claims 1 to 5, wherein, The object assessment request also includes a user identifier, and the object assessment result includes a permission assessment sub-result and a risk assessment sub-result. In response to receiving an object evaluation request from the second terminal, the target object identifier and target operation step identifier in the object evaluation request are input into the joint model to obtain the object evaluation result, including: The user identifier, the target object identifier, and the target operation step identifier are input into the joint model to obtain user permission information and user risk information. In response to the user risk information meeting a first predetermined condition, a risk assessment sub-result indicating that the user has no operational risk is determined; and In response to the user permission information meeting the second predetermined condition, a permission evaluation sub-result is determined, which represents that the user has the operation permission corresponding to the target operation link of the target object.

7. The method according to any one of claims 1 to 5, wherein, The operation step identifier is used to characterize the operation step. The data source stores candidate object information corresponding to each of the P candidate object identifiers and the Q candidate operation step identifiers, where P and Q are both positive integers. The step of responding to receiving an information processing request and obtaining object information corresponding to each of the N operation step identifiers based on the M object identifiers indicated by the information processing request includes: For each of the M object identifiers, and for each of the N operation step identifiers corresponding to the object identifier, Based on the object identifier, the P candidate object identifiers in the data source are matched respectively to obtain the object identifier matching result; In response to the object identifier matching result indicating that the object identifier and the candidate object identifier match, the Q candidate operation step identifiers corresponding to the candidate object identifier are matched according to the operation step identifier to obtain the operation step identifier matching result; and In response to the matching result of the operation step identifier indicating that the operation step identifier and the candidate operation step identifier are matched, the candidate object information corresponding to the candidate operation step identifier is determined as the object information corresponding to the operation step identifier.

8. The method according to any one of claims 1 to 5, further comprising, after receiving an object evaluation request from the second terminal, inputting the target object identifier and the target operation link identifier in the object evaluation request into the joint model to obtain the object evaluation result: The target object identifier, the target operation step identifier, and the object evaluation result are sent to the blockchain network so that the blockchain network can associate and store the target object identifier, the target operation step identifier, and the object evaluation result.

9. An information processing apparatus, comprising: The acquisition module is used to respond to receiving an information processing request and, based on the M object identifiers indicated by the information processing request, acquire object information corresponding to each of the N operation link identifiers, where M and N are both positive integers; The generation module is configured to generate a joint model based on the object information corresponding to each of the N operation step identifiers, wherein the joint model is obtained by jointly training the first terminal and the second terminal on the object information corresponding to each of the N operation step identifiers; and The input module is used to respond to receiving an object evaluation request from the second terminal by inputting the target object identifier and the target operation link identifier in the object evaluation request into the joint model to obtain the object evaluation result; The generation module includes: The processing submodule is used to process the object information corresponding to each of the N operation links to obtain preprocessed information; A sending submodule is used to send a predetermined public key and the preprocessing information to the first terminal and the second terminal, so that the first terminal and the second terminal can perform local model training on their respective localities based on the preprocessing information. The predetermined public key represents a key used to encrypt object information corresponding to the identifiers of the N operation links. A processing unit is configured to, in response to receiving first initial local model parameters from the first terminal and second initial local model parameters from the second terminal, process the first initial local model parameters and the second initial local model parameters to obtain joint model parameters; and The training unit is used to train a predetermined model using the preprocessed information and the joint model parameters to obtain the joint model.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more instructions. When the one or more instructions are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method of any one of claims 1 to 8.

11. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8.

12. A computer program product comprising computer-executable instructions, which, when executed, are used to implement the method of any one of claims 1 to 8.

Images