Data query method, device, apparatus, and storage medium

Abstract

This application provides a data query method, apparatus, device, and storage medium. The method establishes at least one query control model maintenance and update module and an execution query control model aggregation and release module. The query control model maintenance and update module is configured in a sub-data system, and the execution query control model aggregation and release module is configured in the main data system. The query control model maintenance and update module sends sub-models to the execution query control model aggregation and release module according to a first preset period. Upon receiving the sub-models, the execution query control model aggregation and release module establishes or updates a federated learning aggregation model based on the sub-models and adds timestamps to the federated learning aggregation model according to a second preset period. In response to query operations from the execution query control client, the query results are determined based on the federated learning aggregation model, ensuring the timeliness of the model and data, improving the efficiency of data query, thereby improving user experience and reducing the impact of low data timeliness.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data query method, apparatus, device and storage medium. Background Technology

[0002] Network surveillance and control refers to the monitoring and control of information on the internet through technical means. Achieving network surveillance and control relies on various technical means and tools, such as network monitoring software, firewalls, and packet filters. These tools can help monitor network traffic, detect malware, and filter illegal content, thereby ensuring network security.

[0003] Currently, data is queried through a centralized data system to achieve the purpose of online investigation and control. Each database encrypts or de-identifies the data and then publishes some of the data to the centralized system. During online investigation and control, the databases usually provide feedback on the data within about 48 hours.

[0004] However, existing data query methods suffer from low timeliness and low efficiency in obtaining data. Summary of the Invention

[0005] This application provides a data query method, apparatus, device, and storage medium to solve the technical problems of long query time and low efficiency in existing data query methods.

[0006] Firstly, this application provides a data query method, including:

[0007] Establish at least one module for maintaining and updating the investigation and control model and a module for collecting and publishing the investigation and control model.

[0008] The query and control model maintenance and update module is configured in the sub-data system, and the execution query and control model aggregation and release module is configured in the main data system;

[0009] The detection and control model maintenance and update module sends sub-models to the execution detection and control model collection and release module according to the first preset period;

[0010] After receiving the sub-model, the execution control model aggregation and release module establishes or updates the federated learning aggregation model based on the sub-model, and adds a timestamp to the federated learning aggregation model according to the second preset period.

[0011] In response to the query operation performed by the query and control client, the query result is determined based on the federated learning convergence model.

[0012] This application provides a data query method based on federated learning. The query control model maintenance and update module periodically sends sub-models to the execution query control model aggregation and release module. The execution query control model aggregation and release module builds and updates the federated learning aggregation model according to the periodically sent sub-models, thereby ensuring that the model provided to the client for querying is a timely and highly time-sensitive model. It also periodically updates the timestamp of the federated learning aggregation model, adding an expiration period to the federated learning aggregation model, ensuring the timeliness of the model and data, improving the efficiency of data querying, thereby improving the user experience and reducing the impact caused by low data timeliness.

[0013] Optionally, the step of sending sub-models to the execution of the investigation and control model collection and release module according to a first preset period through the investigation and control model maintenance and update module includes:

[0014] The query and control model maintenance and update module obtains the execution query and control requirements from the sub-data system according to the first preset cycle;

[0015] A sub-model is generated based on the execution and control requirements;

[0016] The sub-model is sent to the execution query and control model aggregation and release module.

[0017] In this application, the query and control model maintenance and update module periodically obtains execution query and control requirements from the sub-data system, generates sub-models based on the execution query requests, and uploads the sub-models to the execution query and control model aggregation and release module to participate in the training of the federated learning aggregation model. The periodic acquisition of data ensures the timeliness of the model data source, further ensuring the timeliness of data query and improving data query efficiency.

[0018] Optionally, configuring the query and control model maintenance and update module in the sub-data system includes:

[0019] Obtain the demand of each sub-data system;

[0020] Based on the demand, determine the number of query and control model maintenance and update modules connected to each of the sub-data systems;

[0021] The number of the query and control model maintenance and update modules connected to each of the sub-data systems is used to configure the query and control model maintenance and update modules in the sub-data systems.

[0022] Here, this application deploys the query and control model maintenance and update module on demand according to the usage requirements, adopts a distributed system, and improves concurrency efficiency through load balancing, thereby further improving the efficiency of data query.

[0023] Optionally, before determining the query result based on the federated learning convergence model in response to the query operation of the query control client, the method further includes:

[0024] Establish an execution control model distribution module and an execution control client invocation module;

[0025] Configure the execution control model distribution module and the execution control client invocation module on the execution control client;

[0026] The federated learning convergence model is obtained through the execution control model distribution module, and the validity of the federated learning convergence model is verified based on the timestamp of the federated learning convergence model to determine the valid model;

[0027] Accordingly, the step of responding to the query operation of the query control client and determining the query result based on the federated learning convergence model includes:

[0028] The execution query and control client invocation module responds to the query operation of the execution query and control client and sends the query operation to the execution query and control model distribution module;

[0029] The query results are determined based on the effective model through the execution and control distribution module.

[0030] Here, this application establishes an execution query and control model distribution module and an execution query and control client invocation module, which are used to verify the validity of the model through timestamps and determine the valid model for user data query, as well as to respond to the query operation of the execution query client, thereby further ensuring the validity of the data and improving the accuracy and efficiency of data query.

[0031] Optionally, the step of obtaining the federated learning convergence model through the execution control model distribution module, and verifying the validity of the federated learning convergence model based on its timestamp to determine a valid model includes:

[0032] The federated learning aggregation model is obtained from the execution investigation and control model aggregation and release module through the execution investigation and control model distribution module.

[0033] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified to determine the effective model.

[0034] Optionally, the step of periodically verifying the validity of the timestamp of the federated learning convergence model according to a third preset period, and determining the effective model, includes:

[0035] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified;

[0036] If the timestamp is valid, then the federated learning convergence model is determined to be a valid model;

[0037] If the timestamp is invalid, the federated learning aggregation model is obtained from the execution query and control model aggregation and release module and the valid model is updated.

[0038] In this application, the execution query and control model distribution module periodically verifies the validity of the timestamp of the federated learning aggregation model, which can ensure the real-time performance of the effective model within a certain time range, guarantee the timeliness of the data, further improve the efficiency of data query, and enhance the user experience.

[0039] Optionally, the step of sending the query operation to the execution control model distribution module in response to the query operation of the execution control client through the execution control client invocation module includes:

[0040] The execution query and control client invocation module responds to the transaction initiation operation of the execution query and control client by sending the query operation to the execution query and control model distribution module.

[0041] Here, the execution query and control client calling module can initiate data query and control every time a transaction is initiated, thereby verifying whether the user operating the execution query and control client is trustworthy, thus ensuring data security and improving the reliability and security of transactions.

[0042] Secondly, this application provides a data query device, comprising:

[0043] The first module is used to establish at least one query and control model maintenance and update module and an execution query and control model collection and release module.

[0044] The first configuration module is used to configure the query and control model maintenance and update module in the sub-data system and the execution query and control model aggregation and release module in the main data system;

[0045] The sending module is used to send sub-models to the execution query and control model collection and release module according to a first preset period through the query and control model maintenance and update module;

[0046] The processing module is used to establish or update the federated learning aggregation model according to the sub-model after receiving the sub-model through the execution query and control model aggregation and release module, and add a timestamp to the federated learning aggregation model according to the second preset period.

[0047] The response module is used to respond to the query operation of the query and control client and determine the query result based on the federated learning convergence model.

[0048] Optionally, the sending module is specifically used for:

[0049] The query and control model maintenance and update module obtains the execution query and control requirements from the sub-data system according to the first preset cycle;

[0050] A sub-model is generated based on the execution and control requirements;

[0051] The sub-model is sent to the execution query and control model aggregation and release module.

[0052] Optionally, the first configuration module is specifically used for:

[0053] Obtain the demand of each sub-data system;

[0054] Based on the demand, determine the number of query and control model maintenance and update modules connected to each of the sub-data systems;

[0055] The number of the query and control model maintenance and update modules connected to each of the sub-data systems is used to configure the query and control model maintenance and update modules in the sub-data systems.

[0056] Optionally, before the response module determines the query result based on the federated learning convergence model in response to the query operation of the query control client, it further includes:

[0057] The second module is used to establish the distributed module for execution and control model and the client invocation module for execution and control.

[0058] The second configuration module is used to configure the execution control model distribution module and the execution control client invocation module on the execution control client;

[0059] The determination module is used to obtain the federated learning convergence model through the execution query and control model distribution module, and verify the validity of the federated learning convergence model according to the timestamp of the federated learning convergence model to determine the valid model;

[0060] Accordingly, the response module is specifically used for:

[0061] The execution query and control client invocation module responds to the query operation of the execution query and control client and sends the query operation to the execution query and control model distribution module;

[0062] The query results are determined based on the effective model through the execution and control distribution module.

[0063] Optionally, the determining module is specifically used for:

[0064] The federated learning aggregation model is obtained from the execution investigation and control model aggregation and release module through the execution investigation and control model distribution module.

[0065] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified to determine the effective model.

[0066] Optionally, the determining module is further specifically used for:

[0067] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified;

[0068] If the timestamp is valid, then the federated learning convergence model is determined to be a valid model;

[0069] If the timestamp is invalid, the federated learning aggregation model is obtained from the execution query and control model aggregation and release module and the valid model is updated.

[0070] Optionally, the response module is further specifically used for:

[0071] The execution query and control client invocation module responds to the transaction initiation operation of the execution query and control client by sending the query operation to the execution query and control model distribution module.

[0072] Thirdly, this application provides a data query device, comprising: at least one processor and a memory;

[0073] The memory stores computer-executed instructions;

[0074] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the data query method as described in the first aspect and various possible designs of the first aspect.

[0075] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the data query method described in the first aspect and various possible designs of the first aspect.

[0076] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the data query method described in the first aspect and various possible designs of the first aspect.

[0077] The data query method, apparatus, device, and storage medium provided in this application involve a query control model maintenance and update module that periodically sends sub-models to the execution query control model aggregation and release module. The execution query control model aggregation and release module establishes and updates the federated learning aggregation model based on the periodically sent sub-models, thereby ensuring that the model provided to the client for querying is a timely and highly time-sensitive model. It also periodically updates the timestamp of the federated learning aggregation model, adding an expiration period to the federated learning aggregation model, ensuring the timeliness of the model and data, improving the efficiency of data querying, thereby improving the user experience and reducing the impact caused by low data timeliness. Attached Figure Description

[0078] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0079] Figure 1 This application provides a schematic diagram of a data query system architecture.

[0080] Figure 2 A flowchart illustrating a data query method provided in an embodiment of this application;

[0081] Figure 3 This is a schematic diagram of the structure of a data query device provided in an embodiment of this application;

[0082] Figure 4 This is a schematic diagram of the structure of a data query device provided in an embodiment of this application.

[0083] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0084] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0085] The terms “first,” “second,” “third,” and “fourth,” etc. (if present), in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0086] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0087] Currently, the online execution and control system still has some unavoidable problems. Nowadays, when conducting online execution and control, the database usually provides feedback data in about 48 hours. The data obtained by existing data query methods is not timely and efficient.

[0088] To address the aforementioned technical problems, embodiments of this application provide a data query method, apparatus, device, and storage medium. The method involves a query control model maintenance and update module periodically sending sub-models to an execution query control model aggregation and release module. The execution query control model aggregation and release module establishes and updates the federated learning aggregation model based on the periodically sent sub-models, thereby ensuring that the model provided to the client for querying is a timely and highly efficient model. Furthermore, the timestamp of the federated learning aggregation model is periodically updated, extending its validity period and ensuring the timeliness of the model and data.

[0089] Optional, Figure 1 This is a schematic diagram of a data query system architecture provided in an embodiment of this application. Figure 1 In the above architecture, at least one of receiving device 101, processor 102 and display device 103 is included.

[0090] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the architecture of the data query system. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.

[0091] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface.

[0092] The processor 102 can periodically send sub-models to the execution model collection and release module. The execution model collection and release module establishes and updates the federated learning converged model based on the periodically sent sub-models. It also periodically updates the timestamp of the federated learning converged model, adding an expiration period to the federated learning converged model and ensuring the timeliness of the model and data.

[0093] Display device 103 can be used to display the above results, etc.

[0094] The display device can also be a touch screen, used to receive user commands while displaying the above content, so as to achieve interaction with the user.

[0095] It should be understood that the aforementioned processor can be implemented by reading instructions from memory and executing those instructions, or it can be implemented through chip circuitry.

[0096] Furthermore, the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0097] The technical solutions of this application are described below using several embodiments as examples. The same or similar concepts or processes may not be repeated in some embodiments.

[0098] Figure 2 This is a flowchart illustrating a data query method provided in an embodiment of this application. The execution entity of this embodiment can be... Figure 1 The processor 102 in the code can be specifically executed based on the actual application scenario. For example... Figure 2 As shown, the method includes the following steps:

[0099] S201: Establish at least one module for maintaining and updating the investigation and control model and a module for collecting and publishing the investigation and control model.

[0100] It is understood that the modules in the embodiments of this application are only a division of logical functions; physically, the two can be integrated or independent.

[0101] S202: Configure the query and control model maintenance and update module in the sub-data system, and configure the query and control model aggregation and release module in the main data system.

[0102] Optionally, the retrieval and control model maintenance and update module can be configured in the sub-data system, including:

[0103] Obtain the demand for each sub-data system; based on the demand, determine the number of query and control model maintenance and update modules connected to each sub-data system; configure the query and control model maintenance and update modules in each sub-data system according to the number of query and control model maintenance and update modules connected to each sub-data system.

[0104] Here, in this embodiment of the application, the query and control model maintenance and update module is deployed on demand according to the usage requirements. A distributed system is adopted, and the concurrency efficiency is improved through load balancing, which further improves the efficiency of data query.

[0105] S203: The query and control model maintenance and update module sends the sub-model to the execution query and control model collection and release module according to the first preset cycle.

[0106] Optionally, the control model maintenance and update module sends sub-models to the control model aggregation and release module according to a first preset cycle, including:

[0107] The query and control model maintenance and update module obtains the execution query and control requirements from the sub-data system according to the first preset cycle; generates sub-models based on the execution query and control requirements; and sends the sub-models to the execution query and control model aggregation and release module.

[0108] It is understood that the first preset period can be determined according to the actual situation, and the embodiments of this application do not impose specific restrictions on it.

[0109] In this embodiment, the query and control model maintenance and update module periodically obtains execution query and control requirements from the sub-data system, generates sub-models based on the execution query requests, and uploads the sub-models to the execution query and control model aggregation and release module to participate in the training of the federated learning aggregation model. The periodic acquisition of data ensures the timeliness of the model data source, further ensuring the timeliness of data query and improving data query efficiency.

[0110] S204: After receiving the sub-model, the query and control model aggregation and release module establishes or updates the federated learning aggregation model based on the sub-model, and adds a timestamp to the federated learning aggregation model according to the second preset cycle.

[0111] It is understood that the second preset period can be determined according to the actual situation, and the embodiments of this application do not impose specific restrictions on it.

[0112] Optionally, the second preset period can be longer than the first preset period in order to reduce the calculation time and save system power consumption. For example, the second preset period is 5 minutes and the first preset period is 1 minute.

[0113] S205: In response to the query operation executed by the query control client, the query result is determined based on the federated learning convergence model.

[0114] Optionally, before determining the query results based on the federated learning convergence model in response to the query operation of the query control client, the following steps are also included:

[0115] Establish an execution control model distribution module and an execution control client invocation module; configure the execution control model distribution module and the execution control client invocation module on the execution control client; obtain the federated learning convergence model through the execution control model distribution module, and verify the effectiveness of the federated learning convergence model based on the timestamp of the federated learning convergence model to determine the effective model.

[0116] Accordingly, in response to the query operation executed by the query and control client, the query results are determined based on the federated learning convergence model, including:

[0117] The execution query and control client call module responds to the query operation of the execution query and control client and sends the query operation to the execution query and control model distribution module; the execution query and control distribution module determines the query result based on the effective model.

[0118] Here, in this embodiment of the application, an execution query and control model distribution module and an execution query and control client invocation module are established, which are used to verify the validity of the model through timestamps and determine the valid model for user data query and to respond to the query operation of the execution query client, thereby further ensuring the validity of the data and improving the accuracy and efficiency of data query.

[0119] Optionally, the federated learning convergence model is obtained by executing the query and control model distribution module, and the validity of the federated learning convergence model is verified based on the timestamp of the federated learning convergence model to determine the valid model. This includes: obtaining the federated learning convergence model from the execution query and control model aggregation and release module by executing the query and control model distribution module; and periodically verifying the validity of the timestamp of the federated learning convergence model according to the third preset period to determine the valid model.

[0120] It is understood that the third preset period can be determined according to the actual situation, and the embodiments of this application do not impose specific restrictions on it.

[0121] Optionally, according to a third preset period, the validity of the timestamps of the federated learning convergence model is periodically verified to determine the effective model, including:

[0122] According to the third preset cycle, the validity of the timestamp of the federated learning aggregation model is periodically verified; if the timestamp is valid, the federated learning aggregation model is determined to be a valid model; if the timestamp is invalid, the federated learning aggregation model is obtained from the execution query and control model aggregation and release module and the valid model is updated.

[0123] In this embodiment, the execution query and control model distribution module periodically verifies the validity of the timestamp of the federated learning aggregation model, which can ensure the real-time performance of the effective model within a certain time range, guarantee the timeliness of the data, further improve the efficiency of data query, and enhance the user experience.

[0124] Optionally, in response to the query operation of the query and control client, the execution query and control client calling module sends the query operation to the execution query and control model distribution module, including:

[0125] The query operation is sent to the query and control model distribution module in response to the transaction initiation operation of the query and control client.

[0126] Here, the execution query and control client calling module can initiate data query and control every time a transaction is initiated, thereby verifying whether the user operating the execution query and control client is trustworthy, thus ensuring data security and improving the reliability and security of transactions.

[0127] This application provides a data query method based on federated learning. The query control model maintenance and update module periodically sends sub-models to the execution query control model aggregation and release module. The execution query control model aggregation and release module establishes and updates the federated learning aggregation model according to the periodically sent sub-models, thereby ensuring that the model provided to the client for querying is a timely and highly effective model. It also periodically updates the timestamp of the federated learning aggregation model, adding an expiration period to the federated learning aggregation model, ensuring the timeliness of the model and data, improving the efficiency of data querying, thereby improving the user experience and reducing the impact caused by low data timeliness.

[0128] In one possible implementation, this application provides a data acquisition system for execution investigation and control based on federated learning, which is mainly divided into an execution investigation and control model maintenance and update module, an execution investigation and control model aggregation and release module, an execution investigation and control model distribution module, and an execution investigation and control client invocation module.

[0129] The query and control model maintenance and update module is built within the sub-data systems and deployed on demand according to usage requirements. It employs a distributed system, improving concurrency efficiency through load balancing. Each sub-data system can directly log into its respective query and control model maintenance and update module to submit query and control requests, such as the name and ID number of the person being regulated, or the company's registration number, and the time the request was received. The query and control model maintenance and update module collects these requests to form sub-models and then sends them to the execution query and control model aggregation and release module.

[0130] The execution control model aggregation and release module is built on the main data system. The control model maintenance and update module sends sub-models to the execution control model release and aggregation module every minute. The execution control model release and aggregation module continuously improves the aggregated model based on the received sub-model information and timestamps the model. For example, the effective time of the model is within 5 minutes. To avoid time differences, all times in the system use a unified time zone.

[0131] The execution control model distribution module is deployed within execution control client systems such as banks or bank consortia, and air, land, and sea transportation ticketing systems, as needed. The execution control model distribution module routinely checks the validity of its models based on its own clock. When the validity period expires, it requests a valid model within the current timestamp from the execution control model publishing module and updates its own model. Only when the model in the execution control model distribution module is within a valid timestamp will it open its interface to process data requests sent by the execution control client.

[0132] The execution control client call module is built on each execution control client system. When each transaction occurs, user information is sent to the execution control model distribution module through this module. If the interface is open, the distribution module uses the control model to check if the user is eligible to conduct the transaction and replies to the execution control client, thus completing the control or permission check on the user's behavior. If the interface is closed, the reply is "interface invalid," and the execution control client directly allows the transaction.

[0133] Figure 3 This is a schematic diagram of the structure of a data query device provided in an embodiment of this application, as shown below. Figure 3 As shown, the apparatus in this embodiment includes: a first establishment module 301, a first configuration module 302, a sending module 303, a processing module 304, and a response module 305. The data query apparatus here can be a server or a terminal device, or a chip or integrated circuit that implements the functions of a server or terminal device. It should be noted that the division of the first establishment module 301, the first configuration module 302, the sending module 303, the processing module 304, and the response module 305 is only a logical functional division; physically, they can be integrated or independent.

[0134] The first module is used to establish at least one query and control model maintenance and update module and an execution query and control model collection and release module.

[0135] The first configuration module is used to configure the query and control model maintenance and update module in the sub-data system and to configure the query and control model collection and release module in the main data system.

[0136] The sending module is used to send sub-models to the execution of the query and control model collection and release module according to the first preset period through the query and control model maintenance and update module;

[0137] The processing module is used to establish or update the federated learning aggregation model based on the sub-model after receiving the sub-model by executing the query and control model aggregation and release module, and to add a timestamp to the federated learning aggregation model according to the second preset period.

[0138] The response module is used to respond to query operations executed by the query and control client and determine the query results based on the federated learning convergence model.

[0139] Optionally, the sending module is specifically used for:

[0140] The query and control model maintenance and update module obtains the execution query and control requirements from the sub-data system according to the first preset cycle;

[0141] A sub-model is generated based on the execution and control requirements;

[0142] Send the sub-model to the execution and control model aggregation and release module.

[0143] Optionally, the first configuration module is specifically used for:

[0144] Obtain the demand of each sub-data system;

[0145] Determine the number of query and control model maintenance and update modules connected to each sub-data system based on the demand.

[0146] Configure the Detection and Control Model Maintenance and Update Module in each Sub-Data System according to the number of Detection and Control Model Maintenance and Update Modules connected to each Sub-Data System.

[0147] Optionally, before the response module determines the query results based on the federated learning convergence model in response to the query operation of the query control client, it also includes:

[0148] The second module is used to establish the distributed module for execution and control model and the client invocation module for execution and control.

[0149] The second configuration module is used to configure the execution control model distribution module and the execution control client invocation module on the execution control client.

[0150] The determination module is used to obtain the federated learning convergence model by executing the query and control model distribution module, and to verify the effectiveness of the federated learning convergence model based on the timestamp of the federated learning convergence model, thereby determining the effective model;

[0151] Accordingly, the response module is specifically used for:

[0152] The execution control client call module responds to the query operation of the execution control client and sends the query operation to the execution control model distribution module;

[0153] The query results are determined based on the effective model by executing the query control distribution module.

[0154] Optionally, the module is specifically used for:

[0155] The federated learning convergence model is obtained by executing the execution control model distribution module and then sending it to the execution control model aggregation and release module.

[0156] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified to determine the effective model.

[0157] Optionally, the determination module is also specifically used for:

[0158] According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified;

[0159] If the timestamp is valid, the federated learning convergence model is determined to be a valid model;

[0160] If the timestamp is invalid, the federated learning aggregation model is obtained from the execution control model aggregation and release module and the valid model is updated.

[0161] Optionally, the response module is also specifically used for:

[0162] The query operation is sent to the query and control model distribution module in response to the transaction initiation operation of the query and control client.

[0163] refer to Figure 4The diagram illustrates a structural schematic of a data query device 400 suitable for implementing embodiments of the present disclosure. The data query device 400 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The data query device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0164] like Figure 4 As shown, the data query device 400 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the data query device 400. The processing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0165] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows data query device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 A data query device 400 with various means is shown, but it should be understood that it is not required to implement or have all the means shown. More or fewer means may be implemented or have instead.

[0166] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a storage device 408, or installed from a ROM 402. When the computer program is executed by the processing device 401, it performs the functions defined in the methods of embodiments of this disclosure.

[0167] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0168] The aforementioned computer-readable medium may be included in the aforementioned data query device; or it may exist independently and not assembled into the data query device.

[0169] The aforementioned computer-readable medium carries one or more programs, which, when executed by the data query device, cause the data query device to perform the method shown in the above embodiments.

[0170] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0171] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0172] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0173] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0174] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A data query method, characterized in that, include: Establish at least one module for maintaining and updating the investigation and control model and a module for collecting and publishing the investigation and control model. The query and control model maintenance and update module is configured in the sub-data system, and the execution query and control model aggregation and release module is configured in the main data system; The detection and control model maintenance and update module sends sub-models to the execution detection and control model collection and release module according to the first preset cycle; After receiving the sub-model, the execution control model aggregation and release module establishes or updates the federated learning aggregation model based on the sub-model, and adds a timestamp to the federated learning aggregation model according to the second preset period. In response to the query operation of the query and control client, the query result is determined according to the federated learning convergence model; Before determining the query result based on the federated learning convergence model in response to the query operation of the query control client, the method further includes: Establish an execution control model distribution module and an execution control client invocation module; Configure the execution control model distribution module and the execution control client invocation module on the execution control client; The federated learning convergence model is obtained through the execution control model distribution module, and the validity of the federated learning convergence model is verified based on the timestamp of the federated learning convergence model to determine the valid model; Accordingly, the step of responding to the query operation of the query control client and determining the query result based on the federated learning convergence model includes: The execution query and control client invocation module responds to the query operation of the execution query and control client and sends the query operation to the execution query and control model distribution module; The query results are determined based on the effective model through the execution and control distribution module.

2. The method according to claim 1, characterized in that, The step of sending sub-models to the execution query and control model aggregation and release module according to a first preset period through the query and control model maintenance and update module includes: The query and control model maintenance and update module obtains the execution query and control requirements from the sub-data system according to the first preset cycle; A sub-model is generated based on the execution and control requirements; The sub-model is sent to the execution query and control model aggregation and release module.

3. The method according to claim 1, characterized in that, The step of configuring the investigation and control model maintenance and update module in the sub-data system includes: Obtain the demand of each sub-data system; Based on the demand, determine the number of query and control model maintenance and update modules connected to each of the sub-data systems; The number of the query and control model maintenance and update modules connected to each of the sub-data systems is used to configure the query and control model maintenance and update modules in the sub-data systems.

4. The method according to claim 1, characterized in that, The process of obtaining the federated learning convergence model through the execution control model distribution module and verifying the validity of the federated learning convergence model based on its timestamp to determine a valid model includes: The federated learning aggregation model is obtained from the execution investigation and control model aggregation and release module through the execution investigation and control model distribution module. According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified to determine the effective model.

5. The method according to claim 4, characterized in that, The step of periodically verifying the validity of the timestamp of the federated learning convergence model according to a third preset period, and determining the effective model, includes: According to the third preset period, the validity of the timestamp of the federated learning convergence model is periodically verified; If the timestamp is valid, then the federated learning convergence model is determined to be a valid model; If the timestamp is invalid, the federated learning aggregation model is obtained from the execution query and control model aggregation and release module and the valid model is updated.

6. The method according to claim 4, characterized in that, The step of responding to the query operation of the execution query and control client through the execution query and control client invocation module and sending the query operation to the execution query and control model distribution module includes: The execution query and control client invocation module responds to the transaction initiation operation of the execution query and control client by sending the query operation to the execution query and control model distribution module.

7. A data query device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method described in any one of claims 1 to 6.

Images