A method and device for determining model level

Abstract

The present invention discloses a model level determination method and device, which can be applied to the field of big data or finance, including obtaining the usage rate parameter of each data processing model in the data processing model set, determining the usage rate parameter as a first reference value type; determining the second reference value of each data processing model based on the model call flow chart corresponding to the application system and the initial priority coefficient of each data processing model; obtaining the unused time of each data processing model, and determining the third reference value of each data processing model based on the unused time; determining the target priority coefficient of each data processing model based on the above-mentioned reference values. The present invention can adjust the priority of the data processing model in real time based on the actual usage information of the data processing model, thereby improving the accuracy of the data processing model priority determination and improving the data processing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a model level determination method and device. Background Art

[0002] In the field of big data, computing resource management is a key component of data processing. In massive data, if all data is calculated, it is impossible to balance data processing efficiency and high resource utilization. Massive data is usually processed by calling relevant data processing models. When calling the data processing model, if the target data processing model can be obtained in the optimal scheduling method, the data processing efficiency will be improved. Generally, the model call is completed according to the priority of the data processing model, but the priority of the existing data processing model is usually pre-set, which cannot meet the flexible and changeable data processing application scenarios, reducing the data processing efficiency. Summary of the invention

[0003] In view of the above problems, the present invention provides a model level determination method and device, which improves the accuracy of data processing model priority determination and improves data processing efficiency.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A model level determination method, comprising:

[0006] Obtaining a usage rate parameter of each data processing model in a data processing model set, and determining the usage rate parameter as a first reference value, wherein the data processing model set includes a plurality of data processing models;

[0007] Determining a second reference value of each data processing model based on a model call flow chart corresponding to the application system and an initial priority coefficient of each data processing model, wherein the model call flow chart is an execution order of each data processing model when performing data processing on the application system;

[0008] Acquire the unused time length of each data processing model, and determine a third reference value of each data processing model based on the unused time length;

[0009] Based on the first reference value, the second reference value and the third reference value, a target priority coefficient of each data processing model is determined.

[0010] Optionally, obtaining a usage rate parameter of each data processing model in the data processing model set includes:

[0011] Get the average daily usage of each data processing model;

[0012] Calculate the sum of the daily average usage times of each data processing model in the data processing model set;

[0013] The ratio of the daily average usage times of each data processing model to the total usage times is calculated, and the ratio is determined as the usage rate parameter of each data processing model in the data processing model set.

[0014] Optionally, the determining the second reference value of each data processing model based on the model calling flow chart corresponding to the application system and the initial priority coefficient of each data processing model includes:

[0015] Get the model call flow chart corresponding to the application system;

[0016] If the priority coefficient of the target data processing model is updated, a pre-data processing model corresponding to the target data processing model is acquired based on the model calling flowchart;

[0017] According to the updated priority coefficient of the target data processing model, the initial priority coefficient of the front data processing model is updated;

[0018] The updated priority coefficient of each data processing model is determined as a second reference value of each data processing model.

[0019] Optionally, obtaining the unused time length of each data processing model and determining the third reference value of each data processing model based on the unused time length includes:

[0020] In response to receiving a model call request, obtaining a waiting time during which each data processing model is not called for the call request;

[0021] An adjustment parameter corresponding to the waiting time is obtained, and a current priority parameter of the data processing model is adjusted based on the adjustment parameter to obtain a third reference value of the data processing model.

[0022] Optionally, the method further comprises:

[0023] In response to receiving a model call request, a target data processing model matching the model call request is determined based on a target priority coefficient of each data processing model.

[0024] A model level determination device, comprising:

[0025] a first determining unit, configured to obtain a usage parameter of each data processing model in a data processing model set, and determine the usage parameter as a first reference value, wherein the data processing model set includes a plurality of data processing models;

[0026] A second determining unit is used to determine a second reference value of each data processing model based on a model calling flowchart corresponding to the application system and an initial priority coefficient of each data processing model, wherein the model calling flowchart is an execution order of each data processing model when performing data processing on the application system;

[0027] a third determining unit, configured to obtain an unused time duration of each data processing model, and determine a third reference value of each data processing model based on the unused time duration;

[0028] The fourth determining unit is used to determine the target priority coefficient of each data processing model based on the first reference value, the second reference value and the third reference value.

[0029] Optionally, the first determining unit includes:

[0030] A first acquisition subunit is used to acquire the daily average usage times of each data processing model;

[0031] A first calculation subunit is used to calculate the sum of the daily average usage times of each data processing model in the data processing model set;

[0032] The first determination subunit is used to calculate the ratio of the daily average usage times of each data processing model to the total usage times, and determine the ratio as the usage rate parameter of each data processing model in the data processing model set.

[0033] Optionally, the second determining unit includes:

[0034] The second acquisition subunit is used to acquire the model call flow chart corresponding to the application system;

[0035] A third acquisition subunit is used to acquire a pre-data processing model corresponding to the target data processing model based on the model calling flowchart if the priority coefficient of the target data processing model is updated;

[0036] An updating subunit, configured to update the initial priority coefficient of the pre-data processing model according to the updated priority coefficient of the target data processing model;

[0037] The second determining subunit is used to determine the updated priority coefficient of each data processing model as the second reference value of each data processing model.

[0038] Optionally, the third determining unit includes:

[0039] a fourth acquisition subunit, configured to, in response to receiving a model call request, acquire a waiting time during which each data processing model is not called for the call request;

[0040] The adjustment subunit is used to obtain an adjustment parameter corresponding to the waiting time, and adjust the current priority parameter of the data processing model based on the adjustment parameter to obtain a third reference value of the data processing model.

[0041] Optionally, the device further comprises:

[0042] The fifth determination unit is used to determine, in response to receiving the model call request, a target data processing model that matches the model call request based on the target priority coefficient of each data processing model.

[0043] Compared with the prior art, the present invention provides a model level determination method and device, including obtaining the usage rate parameter of each data processing model in the data processing model set, determining the usage rate parameter as a first reference value type; determining the second reference value of each data processing model based on the model call flow chart corresponding to the application system and the initial priority coefficient of each data processing model; obtaining the unused time of each data processing model, and determining the third reference value of each data processing model based on the unused time; determining the target priority coefficient of each data processing model based on the above reference values. The present invention can adjust the priority of the data processing model in real time based on the actual usage information of the data processing model, thereby improving the accuracy of the data processing model priority determination and improving the data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a model level determination method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the structure of a model level determination device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The terms "first" and "second" and the like in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may include steps or units that are not listed.

[0049] In an embodiment of the present invention, a model level determination method is provided, which mainly determines the priority of various data processing models that can be used in a data processing application system, wherein the data processing models include but are not limited to mathematical models, neural network models, artificial intelligence models, etc.

[0050] The model level determination method and device provided by the present invention can be used in the financial field or other fields, for example, it can be applied to the application scenario of customer data analysis in the financial field. Other fields are any fields outside the financial field, for example, the field of Internet data processing. The above is only an example and does not limit the application field of the model level determination method and device provided by the present invention.

[0051] See also Figure 1 , is a flow chart of a model level determination method provided by an embodiment of the present invention, the method may include the following steps:

[0052] S101. Obtain a usage parameter of each data processing model in a data processing model set, and determine the usage parameter as a first reference value.

[0053] The data processing model set includes multiple data processing models. It can be an overall data processing set, that is, including all data processing models, or it can be a data processing model set created for different application systems or application requirements. For example, the data processing model set corresponding to the application scenario of customer data analysis may include a data normalization processing model, a user portrait data processing model, a data dimension analysis processing model, and so on.

[0054] Different data processing requirements utilize different data processing models. Therefore, when determining the priority of a data processing model, it can be determined based on the usage parameter of the data processing model. The usage parameter represents the importance parameter of the model calculated by dividing the number of times a data processing model is used by the total number of times all data processing models are used.

[0055] S102: Determine a second reference value for each data processing model based on the model calling flowchart corresponding to the application system and the initial priority coefficient of each data processing model.

[0056] The model call flow chart is the execution order of each data processing model when the application system processes data. For example, the data processing models that the current application system needs to call include model 1, model 3, model 4, and model 5, and the corresponding execution order is model 1-model 4-model 3-model 5.

[0057] The main purpose of calling the flowchart based on the model is to solve the problem that if the priority parameter of one of the models is adjusted, the priority parameter of the corresponding model will be affected. For example, if the priority of the current data processing model is adjusted, its preceding data processing model also needs to be adjusted accordingly.

[0058] According to the above adjustment rule, the corresponding parameter after the priority parameter of the data processing model of the model calling flowchart is adjusted is the second reference value.

[0059] S103: Obtain the unused time length of each data processing model, and determine a third reference value of each data processing model based on the unused time length.

[0060] This process can be implemented through the task scheduling aging algorithm. After submitting the data processing model call request, the unused time of the data processing model is obtained, that is, the waiting time of the unrunning model is obtained. For example, whenever the waiting time of the data processing model is +1h, the priority is increased. Specifically, 10% of the original model priority score can be increased, and the priority is increased once every hour. The priority of the data processing model obtained according to the processing process is determined as the third reference value.

[0061] S104. Determine a target priority coefficient of each data processing model based on the first reference value, the second reference value and the third reference value.

[0062] After the above processing, after obtaining the reference values ​​corresponding to the priorities of each data processing model, the target priority coefficients of each data processing model can be determined based on these reference values. The process can be a step-by-step determination process, that is, first adjusting according to the first reference value, and then using the parameters adjusted by the first reference value as the basic data for adjusting the second reference value, and then adjusting again to obtain the second reference value, which is then used as the basis for adjusting the third reference value. The obtained third reference value can be the target priority coefficient. It can also be a set of two reference values ​​selected for actual application for adjustment, and the final target priority coefficient can also be obtained based on the weighted calculations of the three adjustments. The present invention is not limited to this.

[0063] The embodiment of the present invention provides a model level determination method, including obtaining the usage rate parameter of each data processing model in the data processing model set, determining the usage rate parameter as a first reference value type; determining the second reference value of each data processing model based on the model call flow chart corresponding to the application system and the initial priority coefficient of each data processing model; obtaining the unused time of each data processing model, and determining the third reference value of each data processing model based on the unused time; and determining the target priority coefficient of each data processing model based on the above-mentioned reference values. The present invention can adjust the priority of the data processing model in real time based on the actual usage information of the data processing model, thereby improving the accuracy of the data processing model priority determination and improving the data processing efficiency.

[0064] In a possible implementation, the usage parameter can be the ratio of the number of calls of the data processing model to the number of calls of all data processing models. The usage parameter can also be the ratio of the daily average usage times. Specifically, obtaining the usage parameter of each data processing model in the data processing model set includes: obtaining the daily average usage times of each data processing model; calculating the sum of the daily average usage times of each data processing model in the data processing model set; calculating the ratio of the daily average usage times of each data processing model to the sum of the times, and determining the ratio as the usage parameter of each data processing model in the data processing model set.

[0065] This process can be implemented based on the PageRank algorithm, which gives each web page the same importance score, and updates the PageRank score of each page node through iterative recursive calculation until the score is stable, so as to evaluate the importance of the web page. The algorithm is applied in the embodiment of the present invention through the data click value evaluation algorithm, collecting the daily average usage times of calling a certain data processing model: according to the model call times of the previous week, the daily average usage times of the data processing model are calculated. And the data of the number of clicks for all models is collected, the importance is calculated and normalized, and a priority ratio of 0-1 is obtained. Assuming that the warehouse contains two models: the anti-money laundering model and the intelligent recommendation model, the average daily query times of the anti-money laundering model is 90 times, and the average daily click times of the intelligent recommendation model is 10 times, then the importance of the anti-money laundering model = 90 / (90+10), the importance of the intelligent recommendation = 10 / (90+10), then the anti-money laundering model is run first when calculating the two sets of data at the same time, ensuring the priority processing and display of important model data, and timely assisting the rapid decision-making in more important anti-money laundering financial service scenarios.

[0066] In an embodiment of the present invention, the second reference value of each data processing model is determined based on the model calling flowchart corresponding to the application system and the initial priority coefficient of each data processing model, including: obtaining the model calling flowchart corresponding to the application system; if the priority coefficient of the target data processing model is updated, obtaining the preceding data processing model corresponding to the target data processing model based on the model calling flowchart; updating the initial priority coefficient of the preceding data processing model according to the updated priority coefficient of the target data processing model; and determining the updated priority coefficient of each data processing model as the second reference value of each data processing model.

[0067] Among them, the model call flow chart is implemented based on the DAG graph. According to the DAG graph of the data lineage model, the importance of other models that precede the data analysis model with high importance is improved, and the importance of all nodes in the data lineage DAG graph of the data analysis model is obtained by cumulative calculation, and the data calculation priority is sorted according to the importance. Taking the business processing of the banking system as an example, the banking business is composed of the model call process completed in the DAG graph. If you simply calculate the importance of a single model, when the importance of the upstream model is low, the call of the model with high importance will be delayed. Therefore, we also need to make a secondary correction of the importance based on the DAG graph. According to the DAG graph of the data lineage model, the importance of other models that precede the high-priority data analysis model is improved. Specifically, increase its original model priority score by 10%.

[0068] In one implementation, the method of obtaining the unused time length of each data processing model and determining the third reference value of each data processing model based on the unused time length includes: in response to receiving a model call request, obtaining the waiting time of each data processing model not being called for the call request; obtaining an adjustment parameter corresponding to the waiting time, adjusting the current priority parameter of the data processing model based on the adjustment parameter, and obtaining the third reference value of the data processing model.

[0069] This process can be implemented based on the aging algorithm of task scheduling. By adding the task scheduling aging algorithm, the priority of the model calculation work that has not been run can be increased every hour to ensure that the batch of the day is completed before the end of the batch day.

[0070] The model's waiting time for the day is the waiting time that has not been called, that is, the waiting time that has not run the model after submitting a data processing model call request. For example, the model waiting time is updated every five minutes. When the model waiting time exceeds 1 hour, the priority is increased. Specifically, the original model priority score is increased by 10%. The priority is increased every hour. Finally, the task enters the running queue after reaching the highest priority, ensuring that the batch of the day is completed before the end of the batch day.

[0071] Based on the above adjustments and optimizations, the target priority coefficient of each data processing model can be obtained. The target priority coefficient can indicate the priority of the data processing model selected the next time the model is called. For example, the data processing model with a priority of 9 will be called first, and the data processing model with a priority of 1 will be selected only after other models are called.

[0072] Therefore, the next specific data processing model to be run first is determined according to the priority score of each data processing model in the waiting queue. That is, in response to receiving a model call request, a target data processing model matching the model call request is determined based on the target priority coefficient of each data processing model.

[0073] A model level determination method provided in an embodiment of the present invention is a data analysis computing model priority evaluation system based on PageRank value evaluation. The management of computing resources in the field of big data has always been an important and critical component. Model calculation requires a large amount of data. For data security and cost savings, multi-threading cannot usually be used. In a library of massive data, if all data is calculated sequentially, it is impossible to balance speed and high resource utilization. If it is possible to determine which request is more important, then tasks with higher priority can be completed when processing data. Therefore, how to prioritize the operation of important models when computing resources are limited is a technical problem that needs to be solved. The embodiment of the present invention provides a data priority evaluation system for a data analysis calculation model. Based on the data click value evaluation algorithm in the PageRank model, the importance of the model is calculated by dividing the number of times the data analysis model is used by the total number of times of all models. At the same time, according to the DAG diagram of the data lineage model, the importance of other models placed in front of the data analysis model with high importance is improved. The importance of all nodes in the data lineage DAG diagram of the data analysis model is obtained by cumulative calculation, and the data calculation priority is sorted according to the importance. There is a problem with this model that if the model has not been used, the data importance is 0. It is possible that the model has been at the end of the queue without calculation. At this time, the task scheduling aging algorithm is introduced. After submitting the data processing model call request, the waiting time of the model is not run. Whenever the model waiting time + 1h, the priority is increased. Specifically, 10% of its original model priority score is increased, and the priority is increased once every hour. Finally, the task priority reaches the highest and enters the running queue to ensure that the batch of the day is completed before the end of the batch day.

[0074] For example, the data processing models of banks cover a wide range of aspects and are large in number, including operational product positioning analysis, customer insight analysis, and customer life cycle management. Service-related personalized seat allocation, intelligent product recommendations, customer churn warning, and customer stickiness calculation. Marketing-related channel effect analysis, differentiated advertising, etc. Risk management-related anti-fraud, anti-money laundering, online authorization and other scenarios. The corresponding data models are also diverse, among which the data processing model can perform functional processing on a certain part of the data, for example: the customer's financial recommendation model can process customer preference data. The above method can be used to obtain the model with the best processing efficiency, making the processing efficiency of business data higher.

[0075] Based on the above embodiments, a model level determination device is also provided in the embodiments of the present invention. Figure 2 ,include:

[0076] A first determining unit 10 is used to obtain a usage parameter of each data processing model in a data processing model set, and determine the usage parameter as a first reference value, wherein the data processing model set includes a plurality of data processing models;

[0077] A second determining unit 20 is used to determine a second reference value of each data processing model based on a model calling flowchart corresponding to the application system and an initial priority coefficient of each data processing model, wherein the model calling flowchart is an execution order of each data processing model when the application system performs data processing;

[0078] The third determining unit 30 is used to obtain the unused time of each data processing model, and determine the third reference value of each data processing model based on the unused time;

[0079] The fourth determination unit 40 is used to determine the target priority coefficient of each data processing model based on the first reference value, the second reference value and the third reference value.

[0080] Optionally, the first determining unit includes:

[0081] A first acquisition subunit is used to acquire the daily average usage times of each data processing model;

[0082] A first calculation subunit is used to calculate the sum of the daily average usage times of each data processing model in the data processing model set;

[0083] The first determination subunit is used to calculate the ratio of the daily average usage times of each data processing model to the total usage times, and determine the ratio as the usage rate parameter of each data processing model in the data processing model set.

[0084] Optionally, the second determining unit includes:

[0085] The second acquisition subunit is used to acquire the model call flow chart corresponding to the application system;

[0086] A third acquisition subunit is used to acquire a pre-data processing model corresponding to the target data processing model based on the model calling flowchart if the priority coefficient of the target data processing model is updated;

[0087] An updating subunit, configured to update the initial priority coefficient of the pre-data processing model according to the updated priority coefficient of the target data processing model;

[0088] The second determining subunit is used to determine the updated priority coefficient of each data processing model as the second reference value of each data processing model.

[0089] Optionally, the third determining unit includes:

[0090] a fourth acquisition subunit, configured to, in response to receiving a model call request, acquire a waiting time during which each data processing model is not called for the call request;

[0091] The adjustment subunit is used to obtain an adjustment parameter corresponding to the waiting time, and adjust the current priority parameter of the data processing model based on the adjustment parameter to obtain a third reference value of the data processing model.

[0092] Optionally, the device further comprises:

[0093] The fifth determination unit is used to determine, in response to receiving the model call request, a target data processing model that matches the model call request based on the target priority coefficient of each data processing model.

[0094] The embodiment of the present invention provides a model level determination device, including obtaining the usage rate parameter of each data processing model in the data processing model set, determining the usage rate parameter as a first reference value type; determining the second reference value of each data processing model based on the model call flow chart corresponding to the application system and the initial priority coefficient of each data processing model; obtaining the unused time of each data processing model, and determining the third reference value of each data processing model based on the unused time; and determining the target priority coefficient of each data processing model based on the above-mentioned reference values. The present invention can adjust the priority of the data processing model in real time based on the actual usage information of the data processing model, thereby improving the accuracy of the data processing model priority determination and improving the data processing efficiency.

[0095] Based on the foregoing embodiments, an embodiment of the present invention provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any of the above model level determination methods.

[0096] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of determining the model level are implemented when the processor executes the program.

[0097] It should be noted that the processor or CPU may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that the electronic device that implements the functions of the processor may also be other, which is not specifically limited in the embodiments of the present invention.

[0098] It should be noted that the above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc (CD-ROM) and other memories; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0099] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0100] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0101] In addition, all functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units. A person of ordinary skill in the art may understand that all or part of the steps of the above-mentioned method embodiments may be completed by hardware related to program instructions, and the above-mentioned program may be stored in a computer-readable storage medium, and when the program is executed, the steps of the above-mentioned method embodiments are executed; and the above-mentioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks, and other media that can store program codes.

[0102] The methods disclosed in the several method embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments.

[0103] The features disclosed in several product embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new product embodiments.

[0104] The features disclosed in several method or device embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0106] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0107] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A model level determination method, characterized in that: include: Obtaining a usage rate parameter of each data processing model in a data processing model set, and determining the usage rate parameter as a first reference value, wherein the data processing model set includes a plurality of data processing models; Determining a second reference value for each data processing model based on a model call flow chart corresponding to the application system and an initial priority coefficient of each data processing model, wherein the model call flow chart is an execution order of each data processing model when performing data processing on the application system; Acquire the unused time length of each data processing model, and determine a third reference value of each data processing model based on the unused time length; determining a target priority coefficient for each data processing model based on the first reference value, the second reference value, and the third reference value; The obtaining of the usage rate parameter of each data processing model in the data processing model set includes: Get the average daily usage of each data processing model; Calculate the sum of the daily average usage times of each data processing model in the data processing model set; Calculate the ratio of the daily average usage times of each data processing model to the total usage times, and determine the ratio as the usage rate parameter of each data processing model in the data processing model set; The step of determining the second reference value of each data processing model based on the model calling flow chart corresponding to the application system and the initial priority coefficient of each data processing model includes: Get the model call flow chart corresponding to the application system; If the priority coefficient of the target data processing model is updated, a pre-data processing model corresponding to the target data processing model is acquired based on the model calling flowchart; According to the updated priority coefficient of the target data processing model, the initial priority coefficient of the front data processing model is updated; determining the updated priority coefficient of each data processing model as a second reference value of each data processing model; The obtaining of the unused time length of each data processing model and determining the third reference value of each data processing model based on the unused time length includes: In response to receiving a model call request, obtaining a waiting time during which each data processing model is not called for the call request; An adjustment parameter corresponding to the waiting time is obtained, and a current priority parameter of the data processing model is adjusted based on the adjustment parameter to obtain a third reference value of the data processing model.

2. The method according to claim 1, characterized in that The method further comprises: In response to receiving a model call request, a target data processing model matching the model call request is determined based on a target priority coefficient of each data processing model.

3. A model level determination device, characterized in that: include: a first determining unit, configured to obtain a usage parameter of each data processing model in a data processing model set, and determine the usage parameter as a first reference value, wherein the data processing model set includes a plurality of data processing models; A second determining unit is used to determine a second reference value of each data processing model based on a model calling flowchart corresponding to the application system and an initial priority coefficient of each data processing model, wherein the model calling flowchart is an execution order of each data processing model when performing data processing on the application system; a third determining unit, configured to obtain an unused time duration of each data processing model, and determine a third reference value of each data processing model based on the unused time duration; a fourth determining unit, configured to determine a target priority coefficient of each data processing model based on the first reference value, the second reference value, and the third reference value; The first determining unit includes: A first acquisition subunit is used to acquire the daily average usage times of each data processing model; A first calculation subunit is used to calculate the sum of the daily average usage times of each data processing model in the data processing model set; A first determination subunit is used to calculate the ratio of the daily average usage times of each data processing model to the total number of times, and determine the ratio as the usage rate parameter of each data processing model in the data processing model set; The second determining unit includes: The second acquisition subunit is used to acquire the model call flow chart corresponding to the application system; A third acquisition subunit is used to acquire a pre-data processing model corresponding to the target data processing model based on the model calling flowchart if the priority coefficient of the target data processing model is updated; An updating subunit, configured to update the initial priority coefficient of the pre-data processing model according to the updated priority coefficient of the target data processing model; A second determining subunit, configured to determine the updated priority coefficient of each data processing model as a second reference value of each data processing model; The third determining unit includes: a fourth acquisition subunit, configured to, in response to receiving a model call request, acquire a waiting time during which each data processing model is not called for the call request; The adjustment subunit is used to obtain an adjustment parameter corresponding to the waiting time, and adjust the current priority parameter of the data processing model based on the adjustment parameter to obtain a third reference value of the data processing model.

4. The device according to claim 3, characterized in that The device also includes: The fifth determination unit is used to determine, in response to receiving the model call request, a target data processing model that matches the model call request based on the target priority coefficient of each data processing model.

Images