Business processing method, device, equipment and medium based on cloud-based middle-end architecture

Abstract

The embodiment of the present application provides a business processing method, device, equipment and medium based on a cloud-based middle-end architecture, which belongs to the field of computer science. The method includes: when the first processing terminal other than the highest level receives the target business, detecting the communication status between the first processing terminal and the remaining multiple second processing terminals, as well as the remaining computing resources of the multiple second processing terminals; based on the communication status and / or the remaining computing resources of the remaining multiple second processing terminals, determining the third processing terminal for processing the target business from the multiple second processing terminals; sending the target business to the third processing terminal, the third processing terminal is used to train an algorithm model for the target business, and the target business is processed by the trained algorithm model, and the processing result output by the algorithm model is sent to the first processing terminal; based on the processing result output by the algorithm model, action planning is performed for each level involved in fire fighting. The present application aims to improve the level of intelligence in processing the target business.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and specifically, to business processing methods, devices, equipment and media based on a cloud-based middle-end architecture. Background Art

[0002] The fire command system is the command and management center of the fire department. It solves major problems that occur in various fires. At the same time, it is responsible for assisting decision-makers, firefighters, fire trucks and related departments to complete the command and handling of emergency accidents such as fires and forest fires and other major emergencies. At present, the level of intelligence of the fire command system is low, and the command system has a large gap with actual needs in terms of response speed, flexibility and accuracy. For example, in terms of information generation, the fire command system takes a long time to process and integrate various types of information, has a high degree of dependence on manual labor, and has a low level of automation. In terms of task planning and decision support, the fire command system usually calculates and judges conflicts based on set rules and formulas according to input conditions. In actual use, it has more constraints, a low level of intelligence, and poor ability to respond to emergencies. For this reason, it is urgent to carry out intelligent upgrades while improving the information level of the fire command system.

[0003] With the vigorous development of artificial intelligence (AI) technology, AI technology, especially deep learning technology, has achieved remarkable achievements in target recognition, multi-source information fusion, semantic understanding, solution optimization, intelligent recommendation and other fields. AI technology represented by deep learning-based target recognition and deep reinforcement learning-based auxiliary decision-making and task planning has great application potential in improving the performance of fire command systems.

[0004] In practical applications, usually under the same deep learning technology architecture, the better the sample completeness and the more layers of the deep learning network, the higher the calculation accuracy and the better the application effect of the deep learning model. Therefore, existing AI algorithms often require strong computing power as a basis; in the AI ​​algorithm model training stage, it usually relies on high-performance computing resources such as CPU and GPU clusters. In the AI ​​algorithm model application stage, deep learning models with good application effects also usually require high-performance computing equipment support. However, in the daily fire command system, because the computing resources that can be carried on various devices are limited, the dependence on computing resources limits the application of deep learning technology in the frontier of fire fighting. Summary of the invention

[0005] The embodiments of the present application provide a business processing method, device, equipment and medium based on a cloud-based middle-end architecture, aiming to improve the intelligence level of the business processing system in a complex environment.

[0006] In a first aspect, an embodiment of the present application provides a business processing method based on a cloud-based middle platform architecture, the method being applied to a business processing system, the business processing system being used to process a target business, the target business including participating in action planning at various levels in fire fighting, the business processing system including a plurality of processing terminals of different levels, the processing terminal of a high level having higher computing resources, the method comprising:

[0007] When a first processing end other than the highest level receives a target service, the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends are detected; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end;

[0008] Determine a third processing end for processing the target service from among the plurality of second processing ends based on communication conditions with the rest of the plurality of second processing ends and / or their respective remaining computing resources;

[0009] Sending the target service to the third processing end, the third processing end is used to train an algorithm model for the target service, process the target service through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end;

[0010] Based on the processing results output by the algorithm model, action planning is performed for each level involved in the fire fighting.

[0011] Optionally, determining a third processing end for processing the target service from the plurality of second processing ends based on communication conditions with the remaining plurality of second processing ends and / or the respective remaining computing resources comprises at least one of the following:

[0012] Sending the target service to a third processing terminal whose communication status is a preset level;

[0013] Sending the target service to a third processing terminal whose remaining computing resources exceed a preset resource threshold;

[0014] The target service is sent to a third processing end whose communication status is the preset level and whose remaining computing resources exceed the preset resource threshold.

[0015] Optionally, each of the processing ends includes an AI business module, and the AI ​​business module calculates the target business based on the algorithm model to obtain a calculation result.

[0016] Optionally, each of the processing ends includes an AI remote support module;

[0017] The detecting the communication status between the first processing end and the remaining plurality of second processing ends includes:

[0018] Detect the communication status between the AI ​​business module of the first processing end and the remaining multiple AI remote support modules of the second processing end.

[0019] Optionally, the detecting the communication status between the first processing end and the remaining plurality of second processing ends includes:

[0020] Acquiring the time characteristics of the target business;

[0021] Acquire a communication rate between the first processing end and the second processing end;

[0022] Based on the time feature and the communication rate, a communication status between the first processing end and the second processing end is acquired.

[0023] Optionally, the time feature includes a strong real-time requirement and a weak real-time requirement; and obtaining the communication status between the first processing end and the second processing end based on the time feature and the communication rate includes:

[0024] If the time feature is a strong real-time requirement, and the communication rate is greater than or equal to a first communication rate preset value, determining that the communication state is good;

[0025] If the time feature is a weak real-time requirement and the communication rate is greater than or equal to a second communication rate preset value, it is determined that the communication state is good.

[0026] Optionally, the processing end further includes an AI data module, an AI environment module and an AI training module; wherein,

[0027] The AI ​​data module is used to provide basic data required for AI training, and the basic data includes a bare algorithm model and training data resources;

[0028] The AI ​​environment module is used to provide the training environment required for AI training, and the training environment includes a software support environment and a hardware support environment;

[0029] The AI ​​training module trains the bare algorithm model based on the target business to obtain an algorithm model.

[0030] In a second aspect, an embodiment of the present application provides a business processing device based on a cloud-based middle platform architecture, which is applied to a business processing system, wherein the business processing system is used to process a target business, wherein the target business includes specific action plans at various levels involved in fire fighting, and the business processing system includes multiple processing terminals with different levels, and the processing terminals with high levels have higher computing resources, and the device includes: a resource determination module, a processing terminal determination module, a transmission module, and a planning module, wherein:

[0031] A resource determination module, when a first processing end other than the highest level receives a target service, detects the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end;

[0032] A processing end determining module, configured to determine a third processing end for processing the target service from among the plurality of second processing ends based on the communication status with the rest of the plurality of second processing ends and / or the remaining computing resources of each of the plurality of second processing ends;

[0033] A transmission module, used to send the target service to the third processing end, the third processing end is used to train an algorithm model for the target service, process the target service through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end;

[0034] The planning module is used to carry out action planning for each level involved in the fire fighting based on the processing results output by the algorithm model.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when executed, the processor implements a business processing method based on a cloud-based middle-office architecture as described in any one of the first aspects.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that enables a processor to execute a business processing method based on a cloud-based middle-end architecture as described in any one of the first aspects.

[0037] Beneficial effect: When multiple processing terminals of different levels within the business processing system process the target business, because the processing terminals at higher levels have higher computing resources, when the business processing system processes the target business, the communication status between the first processing terminal and multiple second processing terminals is detected, and a third processing terminal is determined between the first processing terminal and the second processing terminals. The algorithm model corresponding to the target business is trained through the determined third processing terminal to process the target business, and the processing result is sent to the first processing terminal for action planning. Because the third processing terminal determined from multiple second processing terminals has more computing resources than the first processing terminal, processing the target business through the third processing terminal can be more efficient, thereby achieving the effect of improving the intelligence level of the business processing system in a complex environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 This is a flowchart of the steps of a business processing method based on a cloud-based middle-end architecture proposed in one embodiment of the present application;

[0040] Figure 2 It is a functional module diagram of a business processing device based on a cloud-based middle-end architecture proposed in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] Embodiment 1

[0043] Reference Figure 1 , which shows a flow chart of the steps of a business processing method based on a cloud-based middle-end architecture in an embodiment of the present invention, such as Figure 1 As shown, the method is applied to a business processing system, the business processing system is used to process target business, the target business includes participating in action planning at various levels in fire fighting, the business processing system includes multiple processing terminals with different levels, and the processing terminals with higher levels have higher computing resources. The business processing method may specifically include the following steps:

[0044] S101, when a first processing end other than the highest level receives a target service, detecting the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end;

[0045] In this embodiment, the target business is to provide action planning for the fire department when the fire department is conducting fire fighting, for example, planning the action trajectories of fire trucks and firefighters, equipping the fire scene with firefighting equipment according to the specific fire situation, etc.; and the target business is generally an algorithm model. In actual application, by real-time training of the algorithm model, the algorithm model can be made more adaptable to the on-site situation, so as to improve the level of intelligence when planning the action plan.

[0046] When processing the target business, the target business is mainly processed through the first processing end and multiple second processing ends, wherein the first processing end is the processing end that receives the target business. If the first processing end that receives the target business is the highest-level processing end, then the first processing end has the most computing resources in the entire business processing system, and the most efficient processing result can be obtained by directly using the highest-level processing end to process the target business; if the processing end that receives the target business is not the highest-level processing end, then by detecting the communication status between the first processing end and multiple second processing ends and the remaining computing resources of the multiple second processing ends, a processing end that can process the target business faster is found among the multiple second processing ends.

[0047] S102: Determine a third processing end for processing the target service from among the plurality of second processing ends based on the communication status with the rest of the plurality of second processing ends and / or the remaining computing resources of each.

[0048] By judging the communication status between the first client and the rest of the plurality of second processing terminals and / or the respective remaining computing resources, a third processing terminal is determined from the plurality of second processing terminals, and the third processing terminal is used to train the algorithm model.

[0049] S103, sending the target business to the third processing end, the third processing end is used to train an algorithm model for the target business, process the target business through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end.

[0050] After sending the target business to the third processing end, the third processing end trains the corresponding algorithm model for the target business, and uses the trained algorithm model to process the target business, so as to obtain the corresponding processing result, which is used to plan actions for each level involved in fire fighting, and then sends the processing result back to the first processing end.

[0051] S104: Based on the processing results output by the algorithm model, action planning is performed for each level involved in the fire fighting.

[0052] After the first processing end receives the processing result, it can make action plans for each level involved in fire fighting based on the processing result.

[0053] In this embodiment, when multiple processing terminals of different levels within the business processing system process the target business, because the processing terminals with higher levels have higher computing resources, when the business processing system processes the target business, the communication status between the first processing terminal and multiple second processing terminals is detected, and a third processing terminal is determined between the first processing terminal and the second processing terminals. The algorithm model corresponding to the target business is trained by the determined third processing terminal to process the target business, and the processing result is sent to the first processing terminal for action planning. Because the third processing terminal determined from the multiple second processing terminals has more computing resources than the first processing terminal, it is more efficient to process the target business through the third processing terminal, thereby achieving the effect of improving the intelligence level of the business processing system in a complex environment.

[0054] Embodiment 2

[0055] Reference Figure 1 As shown, a flowchart of the steps of a business processing method based on a cloud-based middle-end architecture in an embodiment of the present application is shown, the method is applied to a business processing system, the business processing system is used to process a target business, the target business includes participating in action planning at various levels in fire fighting, the business processing system includes a plurality of processing terminals at different levels, and the processing terminal at a higher level has higher computing resources; as shown Figure 1 As shown, the business processing method based on the cloud-based middle platform architecture may specifically include the following steps:

[0056] S101, when a first processing end other than the highest level receives a target service, detecting the communication status between the first processing end and the remaining plurality of second processing ends, and the remaining computing resources of each of the plurality of second processing ends; wherein the target service is used to plan actions for each level involved in fire fighting;

[0057] The cloud-based middle-end architecture integrates CPU, distributed hardware, algorithms and models, and has core functions such as sample and training environment, vertical field model algorithm and comparison evaluation optimization engine, distributed cloud training computing power, front-end and back-end service-oriented interactive application interface, etc. Through the cloud-based middle-end architecture, it can support upper-layer applications, manage underlying hardware, and provide hardware services for upper-layer applications. In this embodiment, multiple processing terminals at different levels can be regarded as cloud-based middle-end architecture.

[0058] When conducting firefighting, because the situation at the firefighting site is complicated, it is necessary to use algorithm models to assist decision-making and conduct action planning; when conducting action planning, because the situations faced at the firefighting site are different, it is necessary to generate target services for different situations, and train algorithm models for specific target services, process the target services through the algorithm model, obtain the processing results, and use the processing results to conduct action planning for each level involved in firefighting.

[0059] Each of the processing ends includes an AI business module, and the AI ​​business module calculates the target business based on the algorithm model to obtain a calculation result.

[0060] Each of the processing ends includes an AI remote support module;

[0061] In this embodiment, the first processing end is the processing end that receives the target business, and the second processing end is the processing end in the business system except the first processing end. Multiple processing ends in the business system can be regarded as the first processing end or the second processing end; the target business is a task generated according to specific needs at the fire fighting scene, which can be a fire truck action trajectory planning task, which plans the action trajectory for the fire truck, or it can be a specific fire fighting task or rescue task planning for a certain firefighter, which plans specific actions for the firefighter; planning by processing the target business can improve the level of intelligence in the fire fighting process.

[0062] Processing the target business requires training the AI ​​algorithm model, so an AI business module and an AI remote support module are set up in each processing end; the target business can be calculated through the AI ​​business module, and the AI ​​remote support module can be connected to other processing ends.

[0063] Therefore, detecting the communication status between the first processing end and the remaining plurality of second processing ends includes:

[0064] Detect the communication status between the AI ​​business module of the first processing end and the remaining multiple AI remote support modules of the second processing end.

[0065] Detecting the communication status between the first processing end and the remaining plurality of second processing ends includes:

[0066] The time characteristics of the target business are obtained; the time characteristics refer to the real-time requirements of the target business. When fire fighting is carried out and action planning is carried out, some target businesses are not particularly urgent, and there can be a certain delay in the target businesses. The time characteristics of such target businesses can be regarded as weak real-time requirements; while some target businesses are more urgent and require faster processing speeds. The time characteristics of such target businesses can be regarded as strong real-time requirements.

[0067] The communication rate between the first processing end and the second processing end is obtained; the communication rate between the first processing end and the second processing end refers to the speed of information transmission.

[0068] Based on the time feature and the communication rate, a communication status between the first processing end and the second processing end is acquired.

[0069] The method comprises: if the time feature is a strong real-time requirement and the communication rate is greater than or equal to a first communication rate preset value, determining that the communication state is good;

[0070] If the time feature is a weak real-time requirement, and the communication rate is greater than or equal to a second communication rate preset value, determining that the communication state is good;

[0071] In this embodiment, the first communication rate preset value is set to 10 m / s; the second communication rate preset value is set to 5 m / s.

[0072] The processing end also includes an AI data module, an AI environment module and an AI training module; wherein,

[0073] The AI ​​data module is used to provide basic data required for AI training, and the basic data includes a bare algorithm model and training data resources;

[0074] The AI ​​environment module is used to provide the training environment required for AI training, and the training environment includes a software support environment and a hardware support environment;

[0075] The AI ​​training module trains the bare algorithm model based on the target business to obtain a business algorithm type.

[0076] During AI training, the processing end that handles the target business connects with other processing ends through the AI ​​remote support module, obtains the target business, and trains the algorithm model through the AI ​​data module, AI environment module and AI training module; finally, the AI ​​business module uses the trained algorithm model to process the target business and obtain the processing result.

[0077] Among them, algorithm models include bare algorithm models and algorithm models. Naked algorithm models refer to algorithm models without meaningful parameters, and algorithm models refer to algorithm models with meaningful parameters that support specific command business. Training data resources include training samples and simulation training models. The AI ​​environment module is used to schedule and manage the software support environment and hardware support environment that support algorithm model training and online computing in the cloud. The software support environment includes AI computing framework, simulation training engine and AI support class library. The hardware support environment includes computing environment and storage environment.

[0078] The AI ​​training module selects a raw algorithm model and training data resources according to the specific target business, and uses the selected training data resources to train the selected raw algorithm model to obtain an algorithm model for processing the target business.

[0079] However, in the process of fire fighting, because the computing resources of multiple processing terminals configured in the business processing system are different, it is necessary to find the most suitable processing terminal among the multiple processing terminals to process the target business, so as to plan actions for each level involved in fire fighting faster and better. When finding the most suitable processing terminal among the multiple processing terminals, the communication status between the first processing terminal and the remaining multiple second processing terminals and / or the remaining computing resources of the multiple second processing terminals are used as decisive factors.

[0080] S102: Determine a third processing end for processing the target service from among the plurality of second processing ends based on the communication status with the rest of the plurality of second processing ends and / or the remaining computing resources of each.

[0081] The determining of the third processing end for processing the target service from the plurality of second processing ends based on the communication status with the remaining plurality of second processing ends and / or the remaining computing resources of each of the plurality of second processing ends comprises at least one of the following:

[0082] Sending the target service to a third processing terminal whose communication status is a preset level;

[0083] If the communication status between the first processing end and one of the multiple second processing ends reaches a preset level, the target service is sent to the second processing end. Because the communication status between the second processing end and the first processing end reaches the preset level, when processing the target service, the connection speed between the second processing end and the first processing end is faster, and the processing result is obtained earlier, so it is determined as the third processing end.

[0084] Sending the target service to a third processing terminal whose remaining computing resources exceed a preset resource threshold;

[0085] When processing the target business, because the computing resources required to process the target business are constant, if the remaining computing resources of one of the second processing ends reaches the preset resource threshold, then the second processing end can definitely process the target business. Therefore, after the target business is sent to the second processing end whose remaining computing resources exceed the preset resource threshold, the second processing end can process the target business, and the processing speed reaches the fastest, and it is determined as the third processing end.

[0086] The target service is sent to a third processing end whose communication status is the preset level and whose remaining computing resources exceed the preset resource threshold.

[0087] If the communication status between one of the second processing terminals and the first processing terminal reaches a preset level and the remaining computing resources exceed the preset resource threshold, the second processing terminal is selected as the third processing terminal to achieve the fastest connection speed and processing speed.

[0088] S103, sending the target business to the third processing end, the third processing end is used to train an algorithm model for the target business, process the target business through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end.

[0089] After determining the third processing end, the AI ​​remote support module in the third processing end is used to connect to the first processing end to obtain the target business, and the algorithm model is trained through the AI ​​data module, AI environment module and AI training module; finally, the AI ​​business module uses the trained algorithm model to process the target business and obtain the processing result.

[0090] S104: Based on the processing results output by the algorithm model, action planning is performed for each level involved in the fire fighting.

[0091] In this implementation, when multiple processing terminals of different levels within the business processing system process the target business, because the processing terminals at higher levels have higher computing resources, when the business processing system processes the target business, the communication status between the first processing terminal and multiple second processing terminals is detected, a third processing terminal is determined between the first processing terminal and the second processing terminals, and the algorithm model corresponding to the target business is trained through the determined third processing terminal to process the target business, and the processing result is sent to the first processing terminal for action planning; because the third processing terminal determined from the multiple second processing terminals has more computing resources than the first processing terminal, it is more efficient to process the target business through the third processing terminal, thereby achieving the effect of improving the intelligence level of the business processing system in a complex environment.

[0092] By way of example, the present application introduces the business processing method based on the cloud-based middle-office architecture of the present application with an exemplary fire handling system. In the fire handling system, there are five levels of processing ends, namely, a fixed command center, a subordinate command center, a temporary command center, a command vehicle and an execution end. Among them, the fixed command center can be set in a provincial capital city in a certain province. It has the highest level. Because it is a fixed setting, the fixed command center is also equipped with the most computing resources in the fire handling system; the subordinate command center can be set in a prefecture-level city, which is also a fixed setting and has the second highest level. The computing resources equipped in the subordinate command center are second only to the fixed command center; the temporary command center and the command vehicle can be set at the command site. They are equipped with the same computing resources and are at a lower level than the fixed command center and the subordinate command center. The difference between the two is that the command vehicle can be moved for command; the execution end is the processing end that performs specific firefighting tasks. Because it is necessary to consider mobility and be equipped with equipment for handling fires, it is equipped with the least computing resources and has the lowest level in the fire handling system.

[0093] In the process of carrying out a forest fire fighting mission, the execution end is the fire-fighting aircraft. Because there are multiple fire points in a forest fire, when the fire-fighting aircraft carries water to perform the fire-fighting mission, because the degree of fire and importance of each fire point are different, the fire-fighting aircraft needs to plan the fire-fighting path according to the specific conditions of each fire point in the forest to achieve the highest fire-fighting efficiency. At this time, a target business is generated, which is used to plan the fire-fighting path for the fire-fighting aircraft.

[0094] As the execution end, the fire-fighting aircraft has the lowest level and the least computing resources in the entire fire command system. If the computing resources of the execution end are used to process the generated target business, the processing speed will be low. If the target business method is not used to plan the fire-fighting path for the fire-fighting aircraft, it will not be possible to extinguish the fire with the highest fire-fighting efficiency.

[0095] At this time, a business processing method based on a cloud-based middle-end architecture provided in Example 1 is adopted, and the fire-fighting aircraft is regarded as the first processing end, and the fixed command center, the subordinate command center, the temporary command center and the command vehicle are all regarded as the second processing end. By detecting the communication status between the first processing end and the remaining multiple second processing ends, as well as the remaining computing resources of the multiple second processing ends, one of the multiple second processing ends is determined as the third processing end to process the target business, and the calculation results are returned to the fire-fighting aircraft. The fire-fighting aircraft then plans the fire-fighting path according to the calculation results; the effect of improving the level of intelligence in the forest fire extinguishing process is achieved.

[0096] Accordingly, this embodiment can also be applied to a municipal fire protection system, in which there are a municipal command center, a street command center, an on-site command vehicle and a firefighter's personal client. When firefighting is carried out, there are only on-site command vehicles and firefighter's personal clients at the fire scene, and the on-site command vehicle and the firefighter's personal client can only carry limited computing resources, which will result in a long time for training the algorithm model, unable to meet the needs in actual applications, and a low level of intelligence.

[0097] Therefore, in the municipal fire protection system, if the firefighter's personal client is regarded as the first processing terminal; the municipal command center, the street command center and the on-site command vehicle are regarded as the second processing terminal; when the firefighter's personal client receives the target business, because the computing resources carried by the firefighter's personal client are insufficient, the firefighter's personal client detects the communication status and remaining computing resources between multiple second processing terminals, and selects one of the second processing terminals as the third processing terminal according to the detection results. It can then use the computing resources carried by the municipal command center, the street command center or the on-site command vehicle to process the target business; train the algorithm model for the target business and process the target business, the time for training the algorithm model is shorter, and the time for obtaining the processing result is also shorter, and the action trajectory or task of the firefighter is planned through the obtained processing results, thereby improving the level of intelligence in the fire fighting process.

[0098] Embodiment 3

[0099] Based on the same inventive concept, Figure 2 A schematic diagram of a business processing device based on a cloud-based middle-end architecture is shown, referring to Figure 2 As shown, the business processing device is applied to a business processing system, the business processing system is used to process target business, the target business includes specific action commands at various levels involved in fire fighting, the business processing system includes multiple processing terminals at different levels, and the processing terminals at higher levels have higher computing resources;

[0100] The device comprises: a resource determination module, a processing end determination module, a transmission module and a planning module, wherein:

[0101] A resource determination module, when a first processing end other than the highest level receives a target service, detects the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end;

[0102] A processing end determining module, configured to determine a third processing end for processing the target service from among the plurality of second processing ends based on the communication status with the rest of the plurality of second processing ends and / or the remaining computing resources of each of the plurality of second processing ends;

[0103] A transmission module, used to send the target service to the third processing end, the third processing end is used to train an algorithm model for the target service, process the target service through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end;

[0104] The planning module is used to carry out action planning for each level involved in the fire fighting based on the processing results output by the algorithm model.

[0105] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0106] Embodiment 4

[0107] Based on the same inventive concept, embodiment 4 of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes, it implements a business processing method based on a cloud-based middle-office architecture as described in any one of embodiments 1 to 3.

[0108] Embodiment 5

[0109] Based on the same inventive concept, embodiment 4 of the present application provides a computer-readable storage medium, which stores a computer program that enables a processor to execute a business processing method based on a cloud-based middle-office architecture as described in any one of embodiments 1 to 2.

[0110] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0111] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented 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.

[0112] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0116] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0117] Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A business processing method based on cloud-based middle-end architecture, characterized in that: The method is applied to a business processing system, the business processing system is used to process a target business, the target business includes action planning at various levels involved in fire fighting, the business processing system includes a plurality of processing terminals with different levels, the processing terminals with higher levels have higher computing resources, each of the processing terminals includes an AI business module, the AI ​​business module calculates the target business based on the algorithm model to obtain a calculation result, the method includes: When a first processing end other than the highest level receives a target service, the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends are detected; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end; Determine a third processing end for processing the target service from among the plurality of second processing ends based on communication conditions with the rest of the plurality of second processing ends and / or their respective remaining computing resources; Sending the target service to the third processing end, the third processing end is used to train an algorithm model for the target service, process the target service through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end; Based on the processing results output by the algorithm model, action planning is performed for each level involved in the fire fighting.

2. According to claim 1, a business processing method based on cloud-based middle-end architecture is characterized in that: The determining, based on the communication status with the other plurality of second processing terminals and / or the remaining computing resources of each, of a third processing terminal for processing the target service from the plurality of second processing terminals comprises at least one of the following: Sending the target service to a third processing terminal whose communication status is a preset level; Sending the target service to a third processing terminal whose remaining computing resources exceed a preset resource threshold; The target service is sent to a third processing end whose communication status is the preset level and whose remaining computing resources exceed the preset resource threshold.

3. A business processing method based on cloud-based middle-end architecture according to claim 2, characterized in that: Each of the processing ends includes an AI remote support module; The detecting the communication status between the first processing end and the remaining plurality of second processing ends includes: Detect the communication status between the AI ​​business module of the first processing end and the remaining multiple AI remote support modules of the second processing end.

4. A business processing method based on cloud-based middle-end architecture according to claim 3, characterized in that: The detecting the communication status between the first processing end and the remaining plurality of second processing ends includes: Acquire the time characteristics of the target business; Acquire a communication rate between the first processing end and the second processing end; Based on the time feature and the communication rate, a communication status between the first processing end and the second processing end is acquired.

5. A business processing method based on cloud-based middle-end architecture according to claim 4, characterized in that: The time feature includes a strong real-time requirement and a weak real-time requirement; and obtaining the communication status between the first processing end and the second processing end based on the time feature and the communication rate includes: If the time feature is a strong real-time requirement, and the communication rate is greater than or equal to a first communication rate preset value, determining that the communication state is good; If the time feature is a weak real-time requirement and the communication rate is greater than or equal to a second communication rate preset value, it is determined that the communication state is good.

6. A business processing method based on cloud-based middle-end architecture according to claim 5, characterized in that: The processing end also includes an AI data module, an AI environment module and an AI training module; wherein, The AI ​​data module is used to provide basic data required for AI training, and the basic data includes a bare algorithm model and training data resources; The AI ​​environment module is used to provide the training environment required for AI training, and the training environment includes a software support environment and a hardware support environment; The AI ​​training module trains the bare algorithm model based on the target business to obtain an algorithm model.

7. A business processing device based on a cloud-based middle-end architecture, characterized in that: Applied to a business processing system, the business processing system is used to process a target business, the target business includes specific action plans at various levels involved in fire fighting, the business processing system includes multiple processing terminals with different levels, the processing terminals with high levels have higher computing resources, each of the processing terminals includes an AI business module, the AI ​​business module calculates the target business based on the algorithm model to obtain a calculation result, the device includes: a resource determination module, a processing terminal determination module, a transmission module and a planning module, wherein: A resource determination module, when a first processing end other than the highest level receives a target service, detects the communication status between the first processing end and the remaining multiple second processing ends, and the remaining computing resources of each of the multiple second processing ends; wherein the target service is used to plan actions for each level involved in fire fighting; and the levels of the remaining multiple second processing ends are all higher than the first processing end; A processing end determining module, configured to determine a third processing end for processing the target service from among the plurality of second processing ends based on the communication status with the rest of the plurality of second processing ends and / or the remaining computing resources of each of the plurality of second processing ends; A transmission module, used to send the target service to the third processing end, the third processing end is used to train an algorithm model for the target service, process the target service through the trained algorithm model, and send the processing result output by the algorithm model to the first processing end; The planning module is used to carry out action planning for each level involved in the fire fighting based on the processing results output by the algorithm model.

8. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, a business processing method based on a cloud-based middle-end architecture as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer program stored therein enables the processor to execute a business processing method based on a cloud-based middle-end architecture as described in any one of claims 1-6.

Images