Model information acquisition method and device

Abstract

The invention provides a model information acquisition method and device, and relates to the technical field of intelligent operation and maintenance. The method comprises the following steps: retrieving business demand information from an index management platform, and if it is determined that there is no model conforming to the business demand information, sending the business demand information to a data analysis platform, so that the data analysis platform obtains index information conforming to the business demand information according to the business demand information, and registers the index information in the index management platform; in response to a processing action of combining the registered index information on the index management platform, obtaining a primary edition model, and performing a first service demand test on the primary edition model; and if the first business demand test result is determined to accord with the business demand information, taking the model passing the test as an independent model, and issuing the model online through the index management platform. The method and the device provided by the embodiment of the invention can adapt to service requirements of different service scenes.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology, specifically to a method and apparatus for acquiring model information. Background Technology

[0002] The accounting risk prevention data analysis system primarily undertakes model building and risk verification work in the field of bank accounting internal control. Currently, the system's model development mainly involves two subsystems: First, the indicator development subsystem, which provides tools and underlying data for writing algorithms for various risk scenarios' indicators. Indicators are developed by writing data analysis scripts; this subsystem is called the Multidimensional Data Analysis Platform. Second, the model building subsystem, which stores risk control indicators for six types of business risk scenarios: core transactions, core operations, tellers, institutions, corporate accounts, and personal accounts. These indicators are configured visually, and "OR" and "AND" relationships between indicators are added to form risk control models; this subsystem is called the Indicator Cube Platform.

[0003] Due to limitations in the original accounting data analysis system architecture and data table structure design, it is currently impossible to select and combine indicators across business scenarios to build risk control rules. For example, teller-related main indicators cannot be combined with core transaction indicators to form a model; they can only be combined within the teller-related main indicator library. Furthermore, the visualized combination logic is limited, only supporting "OR" and "AND" relationships. Such a model building system is insufficient to meet the needs of business scenarios. Summary of the Invention

[0004] To address the problems in the prior art, embodiments of the present invention provide a model information acquisition method and apparatus, which can at least partially solve the problems existing in the prior art.

[0005] On the one hand, this invention proposes a method for obtaining model information, including:

[0006] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0007] If the business requirement information is retrieved from the indicator management platform and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0008] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0009] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0010] The model information acquisition method further includes:

[0011] If the test result of the first business requirement is determined to be inconsistent with the business requirement information, then the target part model that conforms to the business requirement information is selected from the part model library through the data analysis platform;

[0012] The target part models are combined according to preset combination rules to obtain a combined model;

[0013] The combined model is subjected to a second business requirement test. If the result of the second business requirement test is determined to be in accordance with the business requirement information, the model that passes the test is used as the combined model and published online through the data analysis platform so that the model query request sender can obtain it.

[0014] The step of combining the target part models according to preset combination rules to obtain a combined model includes:

[0015] If the combined model is determined to be a quasi-real-time model or a real-time model, then at least one of the target part models is determined to be a quasi-real-time model or a real-time model.

[0016] The operating frequency of the combined model is determined based on the highest frequency model frequency in the target part model;

[0017] Select one model from the target part models as the target main part model of the combined model.

[0018] The model information acquisition method further includes:

[0019] If the test result of the second business requirement is determined to be inconsistent with the business requirement information, then the steps of selecting a target part model that conforms to the business requirement information from the part model library through the data analysis platform and subsequent steps are repeated until the test result of the second business requirement conforms to the business requirement information.

[0020] Maintaining the parts model library includes:

[0021] The models published by the indicator management platform and the data analysis platform are used as part models in the part model library.

[0022] The model information acquisition method further includes:

[0023] If the test result for the first business requirement is determined to be inconsistent with the business requirement information, the model that failed the test will be stored as a part model in the part model library.

[0024] On one hand, the present invention proposes a model information acquisition device comprising:

[0025] The parsing unit is used to receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0026] The retrieval unit is used to retrieve the business requirement information from the indicator management platform. If it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0027] The testing unit is used to respond to the processing action of combining the registered indicator information on the indicator management platform to obtain the initial model, and to perform the first business requirement test on the initial model.

[0028] The publishing unit is used to publish the model that has passed the test as an independent model and publish it online through the indicator management platform if the test result of the first business requirement is determined to meet the business requirement information, so that the model query request sender can obtain it.

[0029] In another aspect, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the following method:

[0030] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0031] If the business requirement information is retrieved from the indicator management platform and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0032] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0033] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0034] This invention provides a computer-readable storage medium, comprising:

[0035] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the following method:

[0036] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0037] If the business requirement information is retrieved from the indicator management platform and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0038] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0039] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0040] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the following method:

[0041] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0042] If the business requirement information is retrieved from the indicator management platform and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0043] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0044] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0045] The model information acquisition method and apparatus provided in this embodiment of the invention receive a model query request and parse the model query request to obtain business requirement information in the model query request; retrieve the business requirement information from an indicator management platform; if it is determined that no model matches the business requirement information, send the business requirement information to a data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform; respond to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model, and perform a first business requirement test on the preliminary model; if it is determined that the result of the first business requirement test matches the business requirement information, the model that passes the test is used as an independent model and published online through the indicator management platform for the model query request sender to obtain, which can adapt to the business needs of different business scenarios and facilitate the model query request sender to quickly obtain the required model information. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0047] Figure 1 This is a flowchart illustrating a model information acquisition method provided in an embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram of the structure of a model information acquisition device provided in an embodiment of the present invention.

[0049] Figure 3 This is a schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0051] The model in this invention primarily consists of expert rules for risk control scenarios. The original system's model logic was simple and limited to a single scenario, restricting model decision-making across business scenarios (including six categories: core transactions, core operations, tellers, institutions, corporate accounts, and personal accounts). By improving the model construction scheme, the original pre-launch model was reassembled and repackaged into component models. These components can then be reused and combined in systems capable of cross-business scenarios to form more complex risk control models, breaking the limitations of cross-scenario construction, increasing model construction complexity, and expanding model coverage.

[0052] Figure 1 This is a flowchart illustrating a model information acquisition method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the model information acquisition method provided in this embodiment of the invention includes:

[0053] Step S1: Receive the model query request and parse the model query request to obtain the business requirement information in the model query request.

[0054] Step S2: Retrieve the business requirement information from the indicator management platform. If it is determined that there is no model that matches the business requirement information, send the business requirement information to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0055] Step S3: The response is to combine the registered indicator information on the indicator management platform to obtain the initial model, and then perform the first business requirement test on the initial model.

[0056] Step S4: If the test result of the first business requirement is determined to meet the business requirement information, the model that has passed the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0057] In step S1 above, the device receives a model query request and parses the request to obtain the business requirement information. The device can be a computer device executing this method, specifically a server. The acquisition, storage, use, and processing of data in this application all comply with relevant regulations. The sender of the model query request can be a client, and the server receives the model query request sent by the client; the model query request carries business requirement information.

[0058] In step S2 above, the device retrieves the business requirement information from the indicator management platform. If it determines that no model matches the business requirement information, it sends the business requirement information to the data analysis platform. The data analysis platform then obtains indicator information matching the business requirement information and registers the indicator information on the indicator management platform. The indicator management platform, also known as the Indicator Cube platform, automatically searches its model library for a matching model. If a matching model exists, it can be directly called, and the method can terminate execution.

[0059] If no suitable model exists, proceed to the next steps. On the data analysis platform, specifically the multidimensional data analysis platform, generate the required indicator information by developing data analysis scripts, and simultaneously register the relevant indicators on the Indicator Cube platform and add them to the Indicator Cube management system.

[0060] In step S3 above, the device responds to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model, and then performs a first business requirement test on the preliminary model. The preliminary model can be obtained by relevant personnel selecting and combining relevant indicators on the Indicator Cube platform.

[0061] Based on risk control needs, the initial model was tested by running historical data on the Indicator Cube platform to determine whether it met business requirements.

[0062] In step S4 above, if the device determines that the test result of the first business requirement meets the business requirement information, it will treat the model that has passed the test as an independent model and publish it online through the indicator management platform so that the model query request sender can obtain it.

[0063] The model information acquisition method further includes:

[0064] If the test result for the first business requirement is determined to be inconsistent with the stated business requirement information, the model that failed the test will be stored as a part model in the part model library. It should be noted that already deployed independent models can be copied as part models and stored in the part model library.

[0065] Maintaining the part model library includes:

[0066] The models published by the indicator management platform and the data analysis platform are used as part models in the part model library. Packaged part models are included in the part model library, supporting two methods: 1. Models published by the indicator cube platform are included in the part model library; 2. Part models generated by the multidimensional data analysis platform through preset scripts are automatically included in the part model library.

[0067] The model information acquisition method further includes:

[0068] If the test result of the first business requirement is determined to be inconsistent with the business requirement information, then the target part model that conforms to the business requirement information is selected from the part model library through the data analysis platform;

[0069] The target part models are combined according to preset combination rules to obtain a combined model;

[0070] The combined model is subjected to a second business requirement test. If the result of the second business requirement test is determined to be in accordance with the business requirement information, the model that passes the test is used as the combined model and published online through the data analysis platform so that the model query request sender can obtain it.

[0071] The step of combining the target part model according to a preset combination rule to obtain a combined model includes:

[0072] If the combined model is determined to be a quasi-real-time model or a real-time model, then at least one of the target part models is determined to be a quasi-real-time model or a real-time model.

[0073] The operating frequency of the combined model is determined based on the highest frequency model frequency in the target part model;

[0074] Select one model from the target part models as the target main part model of the combined model.

[0075] The model information acquisition method further includes:

[0076] If the test result of the second business requirement is determined to be inconsistent with the business requirement information, then the steps of selecting a target part model that conforms to the business requirement information from the part model library through the data analysis platform and subsequent steps are repeated until the test result of the second business requirement conforms to the business requirement information.

[0077] The model information acquisition method provided in this embodiment of the invention receives a model query request and parses the model query request to obtain business requirement information in the model query request; retrieves the business requirement information from an indicator management platform; if it is determined that no model matches the business requirement information, the business requirement information is sent to a data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform; responds to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model, and performs a first business requirement test on the preliminary model; if it is determined that the result of the first business requirement test matches the business requirement information, the model that passes the test is used as an independent model and published online through the indicator management platform for the model query request sender to obtain, which can adapt to the business needs of different business scenarios and facilitate the model query request sender to quickly obtain the required model information.

[0078] In the above optional embodiments, the model information acquisition method further includes:

[0079] If the test result of the first business requirement is determined to be inconsistent with the business requirement information, then the target part model that conforms to the business requirement information is selected from the part model library through the data analysis platform; the above embodiments can be referred to for explanation, and will not be repeated here.

[0080] The target part models are combined according to preset combination rules to obtain a combined model; the above embodiments can be referred to for explanation, and will not be repeated here.

[0081] The combined model undergoes a second business requirement test. If the test result confirms that the model meets the business requirement information, the model that passes the test is used as the combined model and published online through the data analysis platform for the sender of the model query request to access. This can be referred to the above embodiment for further explanation and will not be repeated here.

[0082] In the above optional embodiments, the step of combining the target part model according to a preset combination rule to obtain a combined model includes:

[0083] If the combined model is determined to be a quasi-real-time model or a real-time model, then at least one of the target part models is determined to be a quasi-real-time model or a real-time model; this can be referred to the above embodiments for explanation, and will not be repeated here.

[0084] The operating frequency of the combined model is determined based on the highest frequency model among the target part models; this can be referred to the above embodiments for explanation, and will not be repeated here.

[0085] Select one model from the target part models as the target main part model of the combined model. This can be explained with reference to the above embodiments and will not be repeated here.

[0086] In the above optional embodiments, the model information acquisition method further includes:

[0087] If the test result for the second business requirement is determined to be inconsistent with the business requirement information, then the steps of selecting a target part model from the part model library that conforms to the business requirement information through the data analysis platform and subsequent steps are repeated until the test result for the second business requirement conforms to the business requirement information. This can be referred to the above embodiment for explanation, and will not be repeated here.

[0088] In the above optional embodiments, maintaining the part model library includes:

[0089] The models published by the indicator management platform and the data analysis platform are used as part models in the part model library. This can be referred to the above embodiments for further explanation, and will not be repeated here.

[0090] In the above optional embodiments, the model information acquisition method further includes:

[0091] If the test result for the first business requirement is determined to be inconsistent with the stated business requirement information, the model that failed the test will be stored as a part model in the part model library. This can be referred to the above embodiment for further explanation, and will not be repeated here.

[0092] Figure 2 This is a schematic diagram of the structure of a model information acquisition device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the model information acquisition device provided in this embodiment of the invention includes a parsing unit 201, a retrieval unit 202, a testing unit 203, and a publishing unit 204, wherein:

[0093] The parsing unit 201 is used to receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests; the retrieval unit 202 is used to retrieve the business requirement information from the indicator management platform. If it is determined that there is no model that matches the business requirement information, the retrieval unit 202 sends the business requirement information to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform; the testing unit 203 is used to respond to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model and perform a first business requirement test on the preliminary model; the publishing unit 204 is used to, if it is determined that the result of the first business requirement test matches the business requirement information, publish the model that has passed the test as an independent model through the indicator management platform so that it can be obtained by the sender of the model query request.

[0094] Specifically, the parsing unit 201 in the device is used to receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests; the retrieval unit 202 is used to retrieve the business requirement information from the indicator management platform. If it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform; the testing unit 203 is used to respond to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model and perform a first business requirement test on the preliminary model; the publishing unit 204 is used to, if it is determined that the result of the first business requirement test matches the business requirement information, publish the model that has passed the test as an independent model through the indicator management platform so that it can be obtained by the sender of the model query request.

[0095] The model information acquisition device provided in this embodiment of the invention receives a model query request and parses the model query request to obtain business requirement information in the model query request; retrieves the business requirement information from an indicator management platform; if it is determined that no model matches the business requirement information, it sends the business requirement information to a data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform; responds to the processing action of combining the registered indicator information on the indicator management platform to obtain a preliminary model, and performs a first business requirement test on the preliminary model; if it is determined that the result of the first business requirement test matches the business requirement information, the model that passes the test is used as an independent model and published online through the indicator management platform for the sender of the model query request to obtain, which can adapt to the business needs of different business scenarios and facilitate the sender of the model query request to quickly obtain the required model information.

[0096] In the above optional embodiments, the model information acquisition device is further used for:

[0097] If the test result of the first business requirement is determined to be inconsistent with the business requirement information, then the target part model that conforms to the business requirement information is selected from the part model library through the data analysis platform;

[0098] The target part models are combined according to preset combination rules to obtain a combined model;

[0099] The combined model is subjected to a second business requirement test. If the result of the second business requirement test is determined to be in accordance with the business requirement information, the model that passes the test is used as the combined model and published online through the data analysis platform so that the model query request sender can obtain it.

[0100] In the above optional embodiments, the model information acquisition device is further specifically used for:

[0101] If the combined model is determined to be a quasi-real-time model or a real-time model, then at least one of the target part models is determined to be a quasi-real-time model or a real-time model.

[0102] The operating frequency of the combined model is determined based on the highest frequency model frequency in the target part model;

[0103] Select one model from the target part models as the target main part model of the combined model.

[0104] In the above optional embodiments, the model information acquisition device is further used for:

[0105] If the test result of the second business requirement is determined to be inconsistent with the business requirement information, then the steps of selecting a target part model that conforms to the business requirement information from the part model library through the data analysis platform and subsequent steps are repeated until the test result of the second business requirement conforms to the business requirement information.

[0106] In the above optional embodiments, the model information acquisition device is further used for:

[0107] The models published by the indicator management platform and the data analysis platform are used as part models in the part model library.

[0108] In the above optional embodiments, the model information acquisition device is further used for:

[0109] If the test result for the first business requirement is determined to be inconsistent with the business requirement information, the model that failed the test will be stored as a part model in the part model library.

[0110] The embodiments of the present invention provide a model information acquisition device that can be used to execute the processing flow of the above method embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above method embodiments.

[0111] Figure 3 This is a schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention, such as... Figure 3As shown, the computer device includes: a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302. When the processor 302 executes the computer program, it implements the following method:

[0112] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0113] If the business requirement information is retrieved from the indicator management platform, and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0114] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0115] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0116] This embodiment discloses a computer program product, which includes a computer program that, when executed by a processor, implements the following method:

[0117] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0118] If the business requirement information is retrieved from the indicator management platform, and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0119] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0120] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0121] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the following method:

[0122] Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests;

[0123] If the business requirement information is retrieved from the indicator management platform, and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform.

[0124] The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test.

[0125] If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

[0126] Compared with existing technologies, the model information acquisition method provided in this invention receives a model query request and parses the request to obtain business requirement information. It then retrieves the business requirement information from an indicator management platform. If no model matching the business requirement information exists, the method sends the information to a data analysis platform, enabling the platform to obtain indicator information matching the information and register it on the platform. The method also responds to a combined process on the platform to obtain a preliminary model, which undergoes a first business requirement test. If the test result matches the business requirement information, the model passes the test and is published on the platform for the model query request sender to access. This method adapts to different business scenarios and allows the requester to quickly obtain the required model information.

[0127] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0132] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for acquiring model information, characterized in that, include: Receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests; If the business requirement information is retrieved from the indicator management platform and it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform. The response involves combining the registered indicator information on the indicator management platform to obtain a preliminary model, which is then subjected to a first business requirement test. If the test result of the first business requirement is determined to meet the business requirement information, the model that passes the test will be used as an independent model and published online through the indicator management platform so that the model query request sender can obtain it.

2. The model information acquisition method according to claim 1, characterized in that, The model information acquisition method further includes: If the test result of the first business requirement is determined to be inconsistent with the business requirement information, then the target part model that conforms to the business requirement information is selected from the part model library through the data analysis platform; The target part models are combined according to preset combination rules to obtain a combined model; The combined model is subjected to a second business requirement test. If the result of the second business requirement test is determined to be in accordance with the business requirement information, the model that passes the test is used as the combined model and published online through the data analysis platform so that the model query request sender can obtain it.

3. The model information acquisition method according to claim 2, characterized in that, The step of combining the target part model according to a preset combination rule to obtain a combined model includes: If the combined model is determined to be a quasi-real-time model or a real-time model, then at least one of the target part models is determined to be a quasi-real-time model or a real-time model. The operating frequency of the combined model is determined based on the highest frequency model frequency in the target part model; Select one model from the target part models as the target main part model of the combined model.

4. The model information acquisition method according to claim 2, characterized in that, The model information acquisition method further includes: If the test result of the second business requirement is determined to be inconsistent with the business requirement information, then the steps of selecting a target part model that conforms to the business requirement information from the part model library through the data analysis platform and subsequent steps are repeated until the test result of the second business requirement conforms to the business requirement information.

5. The model information acquisition method according to claim 2, characterized in that, Maintaining the part model library includes: The models published by the indicator management platform and the data analysis platform are used as part models in the part model library.

6. The model information acquisition method according to claim 1, characterized in that, The model information acquisition method further includes: If the test result for the first business requirement is determined to be inconsistent with the business requirement information, the model that failed the test will be stored as a part model in the part model library.

7. A model information acquisition device, characterized in that, include: The parsing unit is used to receive model query requests and parse the model query requests to obtain the business requirement information in the model query requests; The retrieval unit is used to retrieve the business requirement information from the indicator management platform. If it is determined that there is no model that matches the business requirement information, the business requirement information is sent to the data analysis platform so that the data analysis platform can obtain indicator information that matches the business requirement information and register the indicator information on the indicator management platform. The testing unit is used to respond to the processing action of combining the registered indicator information on the indicator management platform to obtain the initial model, and to perform the first business requirement test on the initial model. The publishing unit is used to publish the model that has passed the test as an independent model and publish it online through the indicator management platform if the test result of the first business requirement is determined to meet the business requirement information, so that the model query request sender can obtain it.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images