Model processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a model processing method and device, a storage medium and electronic equipment. The method comprises the steps that model data and application instance data of a service request model are acquired, the model data are used for indicating service nodes in the service request model, the service nodes are used for processing service requests, and the service request model is deployed in a first service system; under the condition that the service request model is enabled and the application instance data is valid, determining a processing mark of a service node according to the model data and the application instance data; executing service rating operation on the processing mark of the service node, the model data and the application instance data to obtain a target rating parameter; and when the target rating parameter is greater than or equal to the rating parameter threshold, deploying the service request model in the second business system. The technical problems of low model resource utilization rate and low service processing efficiency caused by service isolation between different service systems are solved.

Description

Technical Field

[0001] This application relates to the field of computers, and in particular, to a model processing method, apparatus, storage medium, and electronic device. Background Art

[0002] In the current service - providing architecture, multiple business systems operate independently. Even though they can provide the same or similar services, due to the existence of business isolation, the utilization rate of model resources is not high. That is, this business isolation restricts the sharing and optimization of service - request models among different systems, making each system need to independently maintain and upgrade the model, increasing the development and maintenance costs, and at the same time reducing the overall efficiency of service processing. The performance of service - request models among different systems varies greatly, making it difficult to implement a cross - system standardized service process and affecting the consistency of service quality.

[0003] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of this application provide a model processing method, apparatus, storage medium, and electronic device to at least solve the technical problem that business isolation between different business systems leads to low utilization rate of model resources and low service - processing efficiency.

[0005] According to one aspect of the embodiments of this application, a model processing method is provided, including: obtaining model data and application instance data of a service - request model, where the model data is used to indicate service nodes in the service - request model, the service nodes are used to process service requests, the application instance data is used to indicate the processing status of the service requests, and the service - request model is deployed in a first business system; when the service - request model is enabled and the application instance data is valid, determining a processing flag of the service nodes according to the model data and the application instance data; performing a service rating operation on the processing flag of the service nodes, the model data, and the application instance data to obtain a target rating parameter, where the processing flag is used to indicate the progress of the service nodes in processing the service requests, and the target rating parameter is used to indicate the efficiency of the service - request model in processing the service requests; when the target rating parameter is greater than or equal to a rating - parameter threshold, deploying the service - request model in a second business system, where the second business system is different from the first business system, and the second business system can process requests of the same type as the service requests.

[0006] According to another aspect of the embodiments of the present application, a model processing device is further provided, including: an acquisition module, configured to acquire model data and application instance data of a service request model, where the model data is used to indicate service nodes in the service request model, the service nodes are used to process service requests, the application instance data is used to indicate the processing status of the service requests, and the service request model is deployed in a first business system; a determination module, configured to, when the service request model is enabled and the application instance data is valid, determine a processing flag of the service node according to the model data and the application instance data; perform a service rating operation on the processing flag of the service node, the model data, and the application instance data to obtain a target rating parameter, where the processing flag is used to indicate the progress of the service node in processing the service request, and the target rating parameter is used to indicate the efficiency of the service request model in processing the service request; a processing module, configured to, when the target rating parameter is greater than or equal to a rating parameter threshold, deploy the service request model in a second business system, where the second business system is different from the first business system, and the second business system can process requests of the same type as the service request.

[0007] Optionally, the device is configured to perform a service rating operation on the processing flag of the service node, the model data, and the application instance data in the following manner to determine a target rating parameter: perform the service rating operation on the processing flag of the service node, the model data, and the application instance data to obtain a plurality of initial rating parameters, where the plurality of target rating parameters include service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate; perform a merging operation on the plurality of initial rating parameters to generate the target rating parameter.

[0008] Optionally, the device is further configured to: before performing a merging operation on the plurality of initial rating parameters to generate the target rating parameter, set an expected flag for a target node when an expected processing duration is set for the target node, where the processing flag of the service node includes the expected flag, the target node is any one of the service nodes, and the model data includes a parameter for indicating whether the expected processing duration is set for the target node; when at least one node in the service node is set with the expected flag, determine the service timeliness as a first service timeliness; when none of the nodes in the service node is set with the expected flag, determine the service timeliness as a second service timeliness, where the value of the first service timeliness is greater than the value of the second service timeliness.

[0009] Optionally, the device is further configured to: before performing a merging operation on the multiple initial rating parameters to generate the target rating parameter, sum the number of overdue requests corresponding to each request in the service request to obtain the number of service overdue requests; divide the number of service overdue requests by the number of requests in the service request to obtain the service overdue rate; sum the number of unprocessed requests corresponding to each request in the service request to obtain the number of service unprocessed requests; divide the number of service unprocessed requests by the number of requests in the service request to obtain the service unprocessed rate; sum the number of pending requests corresponding to each request in the service request to obtain the number of service pending requests; divide the number of service pending requests by the number of requests in the service request to obtain the service pending rate; sum the number of reassigned requests corresponding to each request in the service request to obtain the number of service reassigned requests; divide the number of service reassigned requests by the number of requests in the service request to obtain the service reassigned rate.

[0010] Optionally, the device is further configured to: determine the number of overdue requests corresponding to one request in the service request through the following steps: when at least one node in the service node sets an overdue flag, set the number of overdue requests corresponding to the one request to 1; when none of the nodes in the service node sets the overdue flag, set the number of overdue requests corresponding to the one request to 0; determine the number of unprocessed requests corresponding to one request in the service request through the following steps: when at least one node in the service node sets an unprocessed flag, set the number of unprocessed requests corresponding to the one request to 1, where the processing flag of the service node includes the unprocessed flag; when none of the nodes in the service node sets the unprocessed flag, set the number of unprocessed requests corresponding to the one request to 0.

[0011] Optionally, the device is further configured to: when the difference between the actual processing time point of the target node and the actual processing time point of the previous node of the target node is greater than the processing time threshold, set the unprocessed flag for the target node; when the difference between the initiation time point of the one request and the actual processing time point of the previous node of the target node is greater than the processing time threshold, set the unprocessed flag for the target node, where the service node includes the target node.

[0012] Optionally, the device is further configured to: determine the number of times a request corresponding to one of the service requests is suspended through the following steps: when at least one service node in the service nodes sets a suspension flag, set the number of times the request corresponding to the one request is suspended to 1, where the processing flag of the service node includes the suspension flag; when none of the nodes in the service nodes sets the suspension flag, set the number of times the request corresponding to the one request is not processed to 0; determine the number of times a request corresponding to one of the service requests is reassigned through the following steps: when at least one service node in the service nodes sets a reassignment flag, set the number of times the request corresponding to the one request is reassigned to 1, where the processing flag of the service node includes the reassignment flag; when none of the nodes in the service nodes sets the reassignment flag, set the number of times the request corresponding to the one request is reassigned to 0.

[0013] Optionally, the device is configured to perform a merging operation on the multiple initial rating parameters in the following manner to generate the target rating parameter: determine the rating scores of the respective initial rating parameters among the multiple initial rating parameters according to a target mapping relationship, where the target mapping relationship includes multiple mapping pairs, and one mapping pair consists of a parameter value range and a rating score; sum up the rating scores of the respective initial rating parameters to generate the target rating parameter.

[0014] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the above-mentioned model processing method when running.

[0015] According to another aspect of the embodiments of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned model processing method.

[0016] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute the above-mentioned model processing method through the computer program.

[0017] In the embodiment of the present application, model data of a service request model and application instance data are obtained. The model data is used to indicate service nodes in the service request model, and the service nodes are used to process service requests. The application instance data is used to indicate the processing status of service requests in the first business system, including processing time, whether it is overdue, customer satisfaction, etc. The service request model is deployed in the first business system, which is the initial environment for service request processing. When the service request model is enabled and the application instance data is valid, a processing flag for each service node is determined based on the model data and the application instance data. The processing flag can be completed on time, overdue, not processed for a long time, suspended for a long time, reassigned by multiple people, etc. These flags reflect the progress and efficiency of the service node in processing service requests. A service rating operation is performed on the processing flag, model data, and application instance data of the service node to obtain a target rating parameter. The target rating parameter is comprehensively calculated based on indicators such as service compliance rate, service implementation on-time rate, and service satisfaction evaluation, and reflects the overall efficiency of the service request model in processing service requests. By analyzing the target rating parameter, the performance of the service request model can be evaluated, and models with high service quality and good processing efficiency can be identified.

[0018] Further, when the target rating parameter is greater than or equal to the rating parameter threshold, the service request model is deployed in the second business system. The second business system is different from the first business system but can process requests of the same type as the service requests. That is, when the service request model performs up to or exceeds a certain standard in the first business system, it can be used in the second business system, ensuring the quality and efficiency consistency of the model between different systems.

[0019] Through the service request model sharing and rating mechanism across business systems, the technical effects of improving the utilization rate of model resources and promoting service processing efficiency are achieved. It effectively solves the problems of low utilization rate of model resources and low service processing efficiency caused by business isolation between different business systems, realizes cross-system sharing of high-quality service models, improves the quality and efficiency of service processing, optimizes resource allocation, and reduces the costs of repeated development and testing. Description of the Drawings

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0021] Figure 1 is a schematic diagram of the application environment of an optional model processing method according to an embodiment of the present application;

[0022] Figure 2 is a schematic flowchart of an optional model processing method according to an embodiment of the present application;

[0023] Figure 3 It is a schematic diagram of an optional model processing method according to an embodiment of the present application;

[0024] Figure 4 It is a schematic structural diagram of an optional model processing device according to an embodiment of the present application;

[0025] Figure 5 It is a schematic structural diagram of an optional model processing product according to an embodiment of the present application;

[0026] Figure 6 It is a schematic structural diagram of an optional electronic device according to an embodiment of the present application. Detailed implementation manners

[0027] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] The present application will be described below in conjunction with the embodiments:

[0030] According to one aspect of the embodiments of the present application, a model processing method is provided. Optionally, in this embodiment, the above model processing method can be applied to a hardware environment composed of a server 101 and a terminal device 103 as shown in Figure 1 As shown in Figure 1As shown in the figure, the server 101 is connected to the terminal device 103 through a network and can be used to provide services for the terminal device or the application installed on the terminal device. The application 107 can be a video application, an instant messaging application, a browser application, an educational application, a game application, etc. The database 105 can be set on the server or independently of the server and is used to provide data storage services for the server 101. For example, a game data storage server. The above network can include, but is not limited to: a wired network and a wireless network. Among them, the wired network includes: a local area network, a metropolitan area network, and a wide area network. The wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The terminal device 103 can be a terminal configured with an application and can include, but is not limited to, at least one of the following: a mobile phone (such as an Android mobile phone, an iOS mobile phone, etc.), a laptop computer, a tablet computer, a handheld computer, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, a smart voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a mixed reality (MR) terminal, and other computer devices. The above server can be a single server, a server cluster composed of multiple servers, or a cloud server.

[0031] Combined with Figure 1 As shown in the figure, the above model processing method can be executed by an electronic device, which can be a terminal device or a server. The above model processing method can be implemented separately by the terminal device or the server, or jointly implemented by the terminal device and the server.

[0032] The above is only an example, and this embodiment does not make specific limitations.

[0033] Optionally, as an alternative implementation, as Figure 2 shown in the figure, the above model processing method includes:

[0034] S202, obtaining the model data and application instance data of the service request model, where the model data is used to indicate the service nodes in the service request model, the service nodes are used to process service requests, the application instance data is used to indicate the processing status of the service requests, and the service request model is deployed in the first business system;

[0035] Optionally, in the embodiments of the present application, obtaining the model data and application instance data of the service request model is a basic step for realizing the sharing and optimization of the service request model across business systems. The model data mainly includes the structural information of the service request model, which specifically indicates each service node in the service request processing process. These service nodes define the processing flow of the service request, the processing tasks of each node, the processing time requirements, and possible branch logics, etc. The model data is the core of the service request processing logic, which ensures that the service request can be processed according to the predetermined rules and processes.

[0036] Optionally, in the embodiments of the present application, the application instance data reflects the running situation of the service request model in actual operation, including but not limited to the processing time of the service request, whether it is overdue, whether there is suspension or reassignment during the processing process, and the customer's satisfaction evaluation of the service, etc. These data are the records of the service request processing in actual application, which helps to evaluate the actual performance and effect of the service request model.

[0037] Exemplarily, the service request model is deployed in the first business system, which means that the model is first practiced and verified in a specific business environment. When the model is enabled and the application instance data is valid, by obtaining the model data and application instance data, not only can the logic and rules of the model itself be analyzed, but also the running efficiency and service quality of the model can be evaluated according to the actual processing status. For example, the system can check whether the service nodes complete tasks on time, whether they often need to be suspended or reassigned, and the customer's satisfaction with the service.

[0038] S204, when the service request model is enabled and the application instance data is valid, determine the processing flag of the service node according to the model data and application instance data; perform a service rating operation on the processing flag of the service node, the model data and the application instance data to obtain a target rating parameter, where the processing flag is used to indicate the progress of the service node in processing the service request, and the target rating parameter is used to indicate the efficiency of the service request model in processing the service request;

[0039] Optionally, in the embodiments of the present application, the processing flag of the service node refers to the status identifier of the service node in the process of processing the service request, including but not limited to completing on time, overdue, not processed for a long time, suspended during processing, reassignment during service implementation, etc. These flags reflect the specific progress and efficiency of the service request processing.

[0040] It should be noted that the processing flag of the service node can be determined in various ways. For example, by comparing the end time of each service node with its expected completion time to determine whether it is overdue; by counting whether the service request has been in a pending state for a long time during the processing of a certain node to determine whether it is a long-term suspension; by recording whether the service request has been reassigned to different service nodes multiple times during the processing to identify the reassignment situation. The determination methods of the processing flag are diverse, and the present application does not limit this.

[0041] Optionally, in the embodiments of the present application, the above-mentioned target rating parameter refers to a quantitative evaluation result obtained based on the actual operation effect of the service request model in the first business system. It reflects the efficiency and quality of the model in processing service requests, including but not limited to implementation efficiency scores, customer satisfaction scores, resource utilization efficiency scores, etc. These scores are comprehensively calculated by analyzing model data, application instance data, and service node processing flags.

[0042] It should be noted that in actual applications, the threshold setting of the target rating parameter can be adjusted according to different business requirements and scenarios. For example, during the business peak period, the requirement for efficiency may be higher, so the threshold can be set relatively high; during the off-peak business season, more attention may be paid to service quality, so the threshold can be set relatively low to cover a wider range of service situations. The flexibility of threshold setting helps to adapt to the characteristics of different business systems, and the present application does not limit this.

[0043] S206, when the target rating parameter is greater than or equal to the rating parameter threshold, deploy the service request model in the second business system, where the second business system is different from the first business system, and the second business system can process requests of the same type as the service request.

[0044] Optionally, in the embodiments of the present application, the above-mentioned second business system refers to another business system environment with the same or similar characteristics in terms of business functions and service types as the first business system. It includes but not limited to service platforms of other enterprises, business processing systems in different industry fields, etc. As long as it can process service requests of the same type as those in the first business system, it can be used as the deployment target of the service request model. This deployment method ensures the adaptability and scalability of the model in different environments, thereby improving the overall service quality and efficiency.

[0045] It should be noted that the specific types and characteristics of the second business system may vary greatly in actual deployment, including but not limited to technical architecture, data processing capabilities, user interface design, security, and privacy protection measures.

[0046] In an exemplary embodiment, taking the application scenario of an enterprise customer service department as an example, the model data of the service request model defines the process of customer problem-solving, including multiple service nodes such as preliminary consultation, problem diagnosis, solution provision, and customer feedback collection. Each service node has its specific tasks and completion time requirements. The application instance data records the processing status of each specific service request in the first business system, such as the time from preliminary consultation to solution provision, whether there is a situation of exceeding the promised time limit, and the customer satisfaction evaluation of the service, etc.

[0047] When the service request model is enabled in the first business system, that is, the model starts to process actual service requests, and the application instance data is valid, that is, it records complete request processing information without data loss or abnormality, the system determines the processing flag of each service node according to the model data and the application instance data. For example, if the preliminary consultation node completes the task on time, it is marked as "completed on time"; if the solution provision node fails to solve the problem within the promised time, the system will mark it as "overdue". By collecting such processing flags, the system can comprehensively understand the performance of the service request model during the processing process.

[0048] Furthermore, perform a service rating operation on the collected processing flags, model data, and application instance data to calculate the target rating parameter. The target rating parameter here comprehensively considers factors such as the compliance of service requests, the timeliness of processing, and customer satisfaction, such as the proportion of service requests processed on time, the proportion of requests that have not been processed for a long time, and the average and median values of customer satisfaction. The calculation of the target rating parameter provides a quantitative indicator for the performance evaluation of the model, helping to identify excellent service models.

[0049] In a specific scenario, assume that the preliminary consultation node completes the task within 30 minutes, the problem diagnosis node gives an accurate diagnosis within 2 hours, the solution provision node solves the problem within 24 hours, and the customer's overall service satisfaction score is 4.5 points (out of 5). Then, the system will calculate the target rating parameter of the service request model based on this information. If the target rating parameter is higher than the set rating parameter threshold, it indicates that the model performs well, is efficient, and has high customer satisfaction when processing service requests.

[0050] At this time, the system can deploy the service request model in the second business system. For example, the first business system is the complaint handling system of the enterprise customer service department, and the second business system can be the consultation support system. Although the two systems are different, they can both handle requests made by customers, such as complaints, consultations, product returns, etc.

[0051] By deploying a verified high-quality service request model in the second business system, it is possible to ensure consistent and efficient services in different systems. At the same time, it also promotes the sharing and optimization of high-quality models in different business scenarios, improving the overall service level and customer experience.

[0052] It should be noted that the deployment of the service request model is not limited to different business systems within an enterprise, but can also be carried out between different enterprises as long as they can handle the same type of service requests. At the same time, the specific content of the model data and application instance data can be customized or adjusted according to actual business needs. For example, service nodes can be added, processing times can be adjusted, and the customer satisfaction evaluation mechanism can be optimized. This application does not make any limitations in this regard.

[0053] Through the embodiments of this application, model data and application instance data of the service request model are obtained. Among them, the model data is used to indicate the service nodes in the service request model, and the service nodes are used to process service requests. The application instance data is used to indicate the processing status of the service request in the first business system, including processing time, whether it is overdue, customer satisfaction, etc. The service request model is deployed in the first business system, which is the initial environment for service request processing. When the service request model is enabled and the application instance data is valid, the processing flag of each service node is determined according to the model data and application instance data. The processing flag can be completed on time, overdue, not processed for a long time, suspended for a long time, reassigned by multiple people, etc. These flags reflect the progress and efficiency of the service node in processing service requests. A service rating operation is performed on the processing flag, model data, and application instance data of the service node to obtain the target rating parameter. The target rating parameter is comprehensively calculated based on indicators such as service compliance rate, service implementation on-time rate, and service satisfaction evaluation, reflecting the overall efficiency of the service request model in processing service requests. By analyzing the target rating parameter, the performance of the service request model can be evaluated, and models with high service quality and good processing efficiency can be identified.

[0054] Furthermore, when the target rating parameter is greater than or equal to the rating parameter threshold, the service request model is deployed in the second business system. Among them, the second business system is different from the first business system but can handle requests of the same type as the service request. That is, when the service request model performs up to or exceeds a certain standard in the first business system, it can be used in the second business system, ensuring the quality and efficiency consistency of the model between different systems.

[0055] Through the service request model sharing and rating mechanism across business systems, the technical effects of improving the utilization rate of model resources and promoting service processing efficiency are achieved. It effectively solves the problems of low utilization rate of model resources and low service processing efficiency caused by business isolation between different business systems, realizes the cross-system sharing of high-quality service models, improves the quality and efficiency of service processing, optimizes resource allocation, and reduces the costs of repeated development and testing.

[0056] As an optional solution, performing a service rating operation on the processing flag of the service node, the model data, and the application instance data to determine the target rating parameters includes: performing the service rating operation on the processing flag of the service node, the model data, and the application instance data to obtain a plurality of initial rating parameters, where the plurality of target rating parameters include service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate; performing a merging operation on the plurality of initial rating parameters to generate the target rating parameters.

[0057] Optionally, in the embodiments of the present application, performing a service rating operation on the processing flag of the service node, the model data, and the application instance data refers to the process of quantitatively evaluating the performance of the service request model based on the processing efficiency and effect of the service node, the structure of the model data, and the actual performance of the application instance data. It includes, but is not limited to, calculating service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate, which are specific indicators of the service rating operation and are used to evaluate the ability of the model to process service requests.

[0058] It should be noted that the specific implementation method of the service rating operation can be adjusted according to different business scenarios and requirements. For example, the calculation of service timeliness can be based on the total time from receiving to completing the service request, while the service overdue rate is calculated based on whether the service request exceeds the promised processing time. The present application does not limit this, as long as it can effectively reflect the processing efficiency of the service request model.

[0059] Exemplarily, performing a merging operation on a plurality of initial rating parameters to generate target rating parameters can be to perform a weighted average on indicators such as service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate according to preset weights, or use other statistical methods, such as median, mode, etc., to generate the final target rating parameters to comprehensively reflect the processing efficiency and service quality of the service request model.

[0060] In an exemplary embodiment, taking the application scenario of the enterprise customer service department as an example:

[0061] The first business system first defines the processing flow of service requests based on model data, including multiple service nodes such as preliminary consultation, problem diagnosis, solution provision, and customer feedback collection. The application instance data records the actual processing status of service requests in the first business system (such as a complaint handling system), such as the processing time of each service node, whether it is overdue, customer satisfaction, and other information.

[0062] Next, based on this data, the processing flag for each service node is determined. For example, the preliminary consultation node is completed on time, the problem diagnosis node is overdue, and the solution provision node needs to be reassigned, etc. Then, the system performs service rating operations on the processing flags such as "completed on time" for the preliminary consultation node, "overdue" for the problem diagnosis node, "reassigned" for the solution provision node, as well as the model data and application instance data, and calculates initial rating parameters such as service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate respectively.

[0063] Finally, the system performs a merging operation on these initial rating parameters to generate target rating parameters for comprehensively evaluating the processing efficiency and service quality of the service request model.

[0064] Through the embodiments of this application, by performing service rating operations on the processing flags, model data, and application instance data of service nodes and merging them to generate target rating parameters, the technical effect of quantitatively evaluating the processing efficiency and service quality of the service request model is achieved, and the purpose of optimizing the service request processing flow and improving service quality is achieved.

[0065] As an optional solution, before performing the merging operation on the above-mentioned multiple initial rating parameters to generate the above-mentioned target rating parameters, the method further includes: when an expected processing duration is set for a target node, setting an expected flag for the target node, where the processing flag of the service node includes the expected flag, the target node is any one of the service nodes, and the model data includes a parameter for indicating whether the expected processing duration is set for the target node; when at least one node in the service nodes is set with the expected flag, determining the service timeliness as the first service timeliness; when none of the nodes in the service nodes is set with the expected flag, determining the service timeliness as the second service timeliness, where the value of the first service timeliness is greater than the value of the second service timeliness.

[0066] Optionally, in the embodiments of the present application, the target node refers to a specific service node in the service request model, which can be any node in the model, including but not limited to nodes such as preliminary consultation, problem diagnosis, solution provision, and customer feedback collection. The expectation flag is an identifier set after setting the expected processing duration at the target node, used to indicate that there is a clear service commitment time for this node, and the service timeliness is one of the indicators for evaluating the service request processing efficiency.

[0067] It should be noted that the setting of the expected processing duration can be determined according to the complexity of the service, the availability of resources, and historical data, ensuring that service requests can be processed within a reasonable time and providing an objective evaluation criterion for service rating. The present application does not make any limitations in this regard.

[0068] For example, the expected processing duration for preliminary consultation can be set to 10 minutes, the expected processing duration for problem diagnosis is 1 hour, and the expected processing duration for solution provision can be 24 hours.

[0069] Exemplarily, if the expected processing duration is set at the target node, then the expectation flag is set at this node, which indicates that the system will consider the expected processing duration of the target node when evaluating the service timeliness. If at least one node in the service nodes has the expectation flag set, then the first calculation method for service timeliness will be adopted, that is, on the basis of considering the actual processing time of each service node, the actual processing time of the service nodes with overdue processing will be amplified proportionally.

[0070] In an exemplary embodiment, taking the application scenario of an enterprise customer service department as an example, the system first defines the service request processing flow based on model data, including multiple service nodes such as preliminary consultation, problem diagnosis, and solution provision. The expected processing duration of 10 minutes is set at the preliminary consultation node and the expectation flag is set for it. When evaluating the service timeliness, if the actual processing time of the preliminary consultation node exceeds 10 minutes, then when calculating the first service timeliness, the actual processing time of the preliminary consultation node can be amplified according to a preset ratio, while for the service nodes without the expectation flag set (such as the problem diagnosis node), their actual processing times are directly used to calculate the second service timeliness.

[0071] Through the embodiments of the present application, by setting the expectation flag for the target node with the expected processing duration set, the technical effect of differential evaluation of service timeliness is achieved, and the purpose of encouraging timely processing of service requests, handling overdue situations, further optimizing the service request processing flow, and improving the overall service efficiency is achieved. This differential evaluation mechanism can effectively motivate service nodes to follow the committed time, improve the timeliness of processing, and customer satisfaction.

[0072] As an alternative solution, before performing the merging operation on the above-mentioned multiple initial rating parameters to generate the above-mentioned target rating parameters, the above method further includes:

[0073] Sum the number of overdue requests corresponding to each request in the above service request to obtain the service overdue count; divide the above service overdue count by the number of requests in the above service request to obtain the above service overdue rate;

[0074] Sum the number of unprocessed requests corresponding to each request in the above service request to obtain the service unprocessed count; divide the above service unprocessed count by the number of requests in the above service request to obtain the above service unprocessed rate;

[0075] Sum the number of suspended requests corresponding to each request in the above service request to obtain the service suspension count; divide the above service suspension count by the number of requests in the above service request to obtain the above service suspension rate;

[0076] Sum the number of reassigned requests corresponding to each request in the above service request to obtain the service reassignment count; divide the above service reassignment count by the number of requests in the above service request to obtain the above service reassignment rate.

[0077] Optionally, in the embodiments of the present application, the service overdue count refers to the total number of times of overdue processing in all service requests, including but not limited to situations such as the service node taking longer than the promised time to process and processing delays caused by holiday factors. The service unprocessed count is the total number of times that all service requests are not processed or are not resolved for a long time. The service suspension count is the total number of times that service requests are suspended during the processing. The service reassignment count is the total number of times that service requests are reassigned to other service nodes or personnel for various reasons during the processing.

[0078] It should be noted that the number of requests in the service request can be the total number of service requests received within a fixed time period, or the statistical time range can be adjusted according to actual needs, such as daily, weekly, monthly, or yearly statistics, and the present application does not make any limitations in this regard.

[0079] Exemplarily, the system first sums the number of overdue requests corresponding to each request in the service request to obtain the service overdue count; then, divides the service overdue count by the number of requests in the service request to obtain the service overdue rate. The same method can be used to calculate the service unprocessed rate, service suspension rate, and service reassignment rate, providing important input data for the subsequent merging operation to generate target rating parameters reflecting the processing efficiency and quality of the service request model.

[0080] In an exemplary embodiment, taking the application scenario of an enterprise customer service department as an example, the system collects the processing data of all service requests in the past month, including the number of overdue requests, the number of unprocessed requests, the number of pending requests, and the number of reassigned requests.

[0081] Suppose a total of 1000 service requests were received in a month, among which 100 requests were overdue in processing, 20 requests were unprocessed, 30 requests were pending, and 10 requests were reassigned. The system first sums up the number of overdue requests to get 100 service overdue times; then, divides these 100 overdue times by the number of 1000 service requests to obtain a service overdue rate of 10%. Similarly, the system can calculate a service unprocessed rate of 2%, a service pending rate of 3%, and a service reassignment rate of 1%.

[0082] Through the embodiments of the present application, by statistically counting the number of overdue, unprocessed, pending, and reassigned times in service requests and calculating the corresponding rate values, the technical effect of quantitatively evaluating the processing efficiency and service quality of the service request model is achieved.

[0083] As an alternative solution, the above method further includes: determining the number of overdue requests corresponding to one request in the above service requests through the following steps: when at least one node in the above service nodes sets an overdue flag, setting the number of overdue requests corresponding to the above one request to 1; when none of the nodes in the above service nodes set the above overdue flag, setting the number of overdue requests corresponding to the above one request to 0;

[0084] Determining the number of unprocessed requests corresponding to one request in the above service requests through the following steps: when at least one node in the above service nodes sets an unprocessed flag, setting the number of unprocessed requests corresponding to the above one request to 1, where the processing flag of the above service node includes the above unprocessed flag; when none of the nodes in the above service nodes set the above unprocessed flag, setting the number of unprocessed requests corresponding to the above one request to 0.

[0085] Optionally, in the embodiments of the present application, one request in the service requests refers to a single service request instance submitted by the customer and received and started to be processed by the system, including but not limited to customer consultations, complaints, technical assistance requests, etc. The overdue flag and the unprocessed flag are status identifiers attached to the service nodes. The overdue flag indicates that the processing time of a specific service node exceeds the predetermined promised time, and the unprocessed flag identifies that the service node fails to complete the processing task within a specific time.

[0086] It should be noted that the setting of the overdue flag and the unprocessed flag can be based on various factors, such as the setting of the service commitment time, the consideration of holidays, the priority of service requests, etc. This application does not make any limitations in this regard.

[0087] For example, the overdue flag can be the time point after adding holiday adjustments based on the committed time for processing the service request, while the unprocessed flag may be based on the situation that the service request has not been processed at all within a certain period of time.

[0088] Exemplarily, in the embodiment of this application, for each request in the service request, the system checks whether at least one node in the service node has set the overdue flag. If there is an overdue flag, the request overdue count for this request will be set to 1, indicating that the request has been overdue at least at one service node; if there is no overdue flag, the request overdue count is set to 0.

[0089] Similarly, the first business system also checks whether there is an unprocessed flag in the service node. If it exists, the request unprocessed count is set to 1, indicating that at least one node has not completed the processing; if there is no unprocessed flag, the request unprocessed count is set to 0.

[0090] In an exemplary embodiment, taking the application scenario of processing customer consultation requests in the financial service industry as an example, the system receives a customer consultation request regarding credit limit adjustment. During the processing, the preliminary evaluation node completes on time, but at the problem diagnosis and solution providing nodes, due to internal coordination issues in the system, the processing time exceeds the committed time. Therefore, the system sets the overdue flag for these two nodes respectively.

[0091] According to the embodiment of this application, when the system calculates the request overdue count, it finds that at least one node has set the overdue flag, so the request overdue count is set to 1. At the same time, since all service nodes have finally completed the processing and no service node has set the unprocessed flag, the request unprocessed count is set to 0.

[0092] Through the embodiment of this application, by adopting the method of specifically identifying the overdue and unprocessed situations corresponding to each request in the service request, the technical effect of accurately recording the abnormal status during the service request processing is achieved, and the purpose of refined management, timely discovery and solution of process bottlenecks is achieved. By setting the overdue flag and the unprocessed flag, the system can automatically identify and record the abnormal situations in the service request processing, providing an accurate data basis for subsequent statistical analysis and process improvement.

[0093] As an alternative solution, the above method further includes: when the difference between the actual processing time point of the target node and the actual processing time point of the previous node of the target node is greater than the processing time threshold, the unprocessed flag is set on the target node; when the difference between the initiation time point of the one request and the actual processing time point of the previous node of the target node is greater than the processing time threshold, the unprocessed flag is set on the target node, where the service node includes the target node.

[0094] Optionally, in the embodiments of the present application, the actual processing time point refers to the moment when the service node actually completes processing, and the processing time threshold is the maximum expected processing time interval between the target node and its previous node.

[0095] It should be noted that the previous node of the target node refers to the service node immediately preceding the target node in the service request processing flow. The processing time threshold can be a fixed value or dynamically adjusted, and is set according to factors such as business busyness and the type of service node. The present application does not limit this.

[0096] Exemplarily, when the first business system monitors that the difference between the actual processing time point of the target node and the actual processing time point of the previous node is greater than the processing time threshold, it will set the unprocessed flag on the target node.

[0097] In addition, if the time interval from the initiation of a service request to the completion of processing by the previous node of the target node also exceeds the processing time threshold, the unprocessed flag will also be set on the target node. In this way, the system can timely detect abnormal situations in the service process, such as processing delays, improper resource allocation, etc., and provide data support for subsequent process optimization and resource allocation.

[0098] In an exemplary embodiment, taking the application scenario of an enterprise customer service department as an example, the service request processing flow includes service nodes such as preliminary consultation, problem diagnosis, and solution provision. When the system monitors that the time difference between the actual processing time point of the problem diagnosis node and the actual processing time point of the preliminary consultation node exceeds a certain processing time threshold.

[0099] For example, 50 natural days, then the problem diagnosis node will be marked with the unprocessed flag. Similarly, if the time interval between the time point when the customer initiates the request and the time point when the preliminary consultation node completes processing also exceeds 50 natural days, then the problem diagnosis node will also be marked with the unprocessed flag.

[0100] Through the embodiments of the present application, by monitoring whether the processing time interval between service nodes exceeds the processing time threshold and setting the unprocessed flag accordingly, the technical effect of accurately identifying potential problems and bottlenecks in the service request processing flow is achieved, the purpose of improving service efficiency and customer satisfaction is achieved, and it can prompt the service provider to pay attention to each node in the service process, adjust resource allocation in a timely manner, optimize the service process, ensure that service requests can be processed in a timely and efficient manner, and thus improve the overall service quality.

[0101] As an alternative solution, the method further includes:

[0102] In the case where the sum value time point of the target node is earlier than the actual processing time point of the target node, the target node is set with the overdue flag, where the service node includes the target node, the sum value time point of the target node is obtained by adding the expected processing duration and the preset duration to the actual processing time point of the previous node of the target node, the application instance data includes the actual processing time point of the previous node, the preset duration and the actual processing time point of the target node, and the preset time represents the duration during which the first business system is prohibited from working;

[0103] In the case where the difference duration between the suspension end time and the suspension start time of the target node is greater than the suspension duration threshold, the target node is set with the suspension flag, the service node includes the target node, the application instance data includes the suspension end time and the suspension start time of the target node, and the model data includes the suspension duration threshold;

[0104] In the case where the number of times the target node triggers a reassignment operation is greater than or equal to the number threshold, the target node is set with the reassignment flag, the service node includes the target node, the application instance data includes the number of times the target node triggers a reassignment operation, and the model data includes the number threshold.

[0105] Optionally, in the embodiments of the present application, the overdue flag, the suspension flag, and the reassignment flag are used to identify whether the target node has a state of overdue, too long suspension time, or too many reassignment times during the processing.

[0106] It should be noted that the sum value time point is calculated based on the actual processing time point of the previous node of the target node, plus the expected processing duration and the preset duration of the target node. The preset duration refers to the duration when the first business system is in a non-working state, such as holidays, etc., and the present application does not make any limitations on this.

[0107] It should also be noted that the suspension duration threshold and the number threshold can be adjusted according to factors such as service type, business scale, and customer requirements to adapt to different service environments and management requirements, which are not limited in this application.

[0108] Exemplarily, first determine the sum value time point of the target node. If this time point is earlier than the actual processing time point of the target node, set an overdue flag at the target node, indicating that the processing of the target node has exceeded the expected time. It is also possible to monitor the suspension status of the target node. When the difference between the suspension end time and the suspension start time exceeds the suspension duration threshold, set a suspension flag, indicating that the suspension time of the target node is too long.

[0109] In addition, if the number of reassignment operations triggered by the target node during the processing reaches or exceeds the number threshold, the system will set a reassignment flag at the target node, indicating that the number of reassignments during the processing of the target node is too large, which may affect the service efficiency and quality.

[0110] In an exemplary embodiment, taking the application scenario of an enterprise customer service department handling customer complaints as an example, the service request processing flow includes service nodes such as preliminary consultation, problem diagnosis, and solution provision, and the problem diagnosis node is the target node. After the system completes the processing at the preliminary consultation node, according to the expected processing duration of the problem diagnosis node and preset durations such as holidays, the sum value time point of the problem diagnosis node is calculated as 14:00 on M day, N month, X year, while the actual processing time point of the problem diagnosis node is 15:00 on N day, N month, X year. Therefore, the system sets an overdue flag at the problem diagnosis node.

[0111] In another exemplary embodiment, the system monitors the suspension status of the solution provision node. The suspension start time is 11:00 on M day, N month, X year, and the suspension end time is 10:00 on N day, N month, X year. The suspension duration threshold is 72 hours. Since the suspension duration exceeds the threshold, the system sets a suspension flag at the solution provision node.

[0112] In yet another exemplary embodiment, during the processing of the problem diagnosis node, due to the need to transfer to different service personnel for evaluation, the number of reassignment operations triggered reaches 4 times, and the number threshold is 3 times. Therefore, the system sets a reassignment flag at the problem diagnosis node.

[0113] Through the embodiments of this application, by monitoring the sum value time point, suspension duration, and number of reassignments in the service request processing flow and setting the overdue flag, suspension flag, and reassignment flag according to the preset thresholds, the refined management of service request processing is realized, and the inefficiencies and anomalies in the processing flow can be detected in a timely manner, achieving the purpose of optimizing the service process, improving the processing efficiency, and enhancing the service quality.

[0114] As an alternative, the above method further includes:

[0115] The number of times a request corresponding to one of the above service requests is suspended is determined through the following steps: when at least one of the above service nodes has a suspension flag set, the number of times the request corresponding to the above one request is suspended is set to 1, where the processing flag of the above service node includes the above suspension flag; when none of the nodes in the above service node has the above suspension flag set, the number of times the above one request is not processed is set to 0;

[0116] The number of times a request corresponding to one of the above service requests is reassigned is determined through the following steps: when at least one of the above service nodes has a reassignment flag set, the number of times the request corresponding to the above one request is reassigned is set to 1, where the processing flag of the above service node includes the above reassignment flag; when none of the nodes in the above service node has the above reassignment flag set, the number of times the above one request is reassigned is set to 0.

[0117] Optionally, in the embodiments of the present application, one request in the service request refers to a single service request instance, including but not limited to customer inquiries, complaints, technical support requests, etc. The suspension flag and the reassignment flag are status identifiers attached to the service node. The suspension flag indicates that the processing of a specific service node is suspended or put on hold, and the reassignment flag indicates that the processing task of this node is reassigned to another node or person.

[0118] Exemplarily, for each request in the service request, if a suspension flag is set on any one of the service nodes in the processing flow, then the number of times the request is suspended will be set to 1, regardless of the specific duration of the suspension. Similarly, if a reassignment flag is set on any one of the service nodes, then the number of times the request is reassigned will also be set to 1, indicating that the request has been reassigned at least once.

[0119] In an exemplary embodiment, taking the application scenario of an IT service desk handling technical support requests as an example, each service request may include service nodes such as preliminary assessment, problem diagnosis, and solution provision. If a suspension flag is set on the problem diagnosis node because additional hardware test results need to be awaited, then the number of times the service request is suspended will be set to 1.

[0120] In addition, if on the solution provision node, the task is reassigned to a senior technical support person because the original handler cannot solve the complex problem and a reassignment flag is set, then the number of times the service request is reassigned will also be set to 1.

[0121] Through the embodiments of the present application, by monitoring and marking whether a suspension flag and a reassignment flag are set for each request in the service request during the processing process, the technical effect of recording the abnormal state of the service request processing flow is achieved. By recording the suspension and reassignment situations, the service provider can regularly analyze this data, identify common problems, take measures to prevent future suspensions and unnecessary reassignments, and further improve the response speed and problem-solving ability of the service desk.

[0122] As an alternative solution, the above-mentioned merging operation on the multiple initial rating parameters to generate the target rating parameter includes: determining the rating scores of the respective initial rating parameters among the multiple initial rating parameters according to the target mapping relationship, where the target mapping relationship includes multiple mapping pairs, and one mapping pair consists of a parameter value range and a rating score; summing up the rating scores of the respective initial rating parameters to generate the target rating parameter.

[0123] Optionally, in the embodiments of the present application, the multiple initial rating parameters refer to various evaluation indicators involved in the service request processing process, including but not limited to service compliance rate, service implementation on-time rate, service long-term unprocessed rate, service long-term suspension rate, service implementation multiple reassignment rate, service delivery satisfaction average score and median, etc. The target mapping relationship is a rule that matches the above-mentioned parameter value ranges with rating scores, and is used to quantify the evaluation indicators so as to convert them into specific scores for easy calculation and comparison. The target rating parameter is a comprehensive evaluation result generated after summing up the scores of the multiple initial rating parameters.

[0124] It should be noted that the parameter value range can be a preset fixed range, such as 0 - 10%, 11% - 20%, or a dynamically adjustable range, which depends on specific business requirements and evaluation strategies. The setting of the rating scores can also be adjusted according to actual needs. For example, the weights of some indicators may be greater than those of other indicators, thereby affecting the generation of the final target rating parameter. The present application does not make any limitations in this regard.

[0125] Exemplarily, the system first determines the rating scores of each initial rating parameter according to the target mapping relationship. For example, the mapping pair of the parameter value range and the rating score for the service implementation on-time rate can be: 0% - 94% corresponds to 0 points, 95% - 98% corresponds to 4 points, and 99% - 100% corresponds to 10 points. The system calculates that the service implementation on-time rate is 96%, and according to the above mapping relationship, determines the rating score of the on-time rate as 4 points. For other initial rating parameters, a similar method is used to determine their rating scores.

[0126] In an exemplary embodiment, taking the application scenario of an enterprise customer service center handling customer requests as an example, before the system performs a merging operation on multiple initial rating parameters, it first determines the rating scores of each parameter based on the target mapping relationship. For example, if the service compliance rate is 100%, then according to the mapping relationship, 30 points are obtained; if the service implementation on-time rate is 97%, 10 points are obtained; if the long-term unprocessed rate of the service is 0%, 10 points are obtained; if the long-time suspension rate of the service is 0%, 10 points are obtained; if the multi-person reassignment rate of the service implementation is 0%, 10 points are obtained; if the average score of service delivery satisfaction is 4.5, 6 points are obtained. Then, the system sums up the rating scores of the above-mentioned initial rating parameters to generate a target rating parameter, that is, 30 + 10 + 10 + 10 + 10 + 6 = 76 points.

[0127] Through the embodiments of the present application, by using the method of quantifying scores based on the target mapping relationship and summing them up, the technical effect of converting multiple initial rating parameters into a comprehensive score representing the quality and efficiency of service requests is achieved, and the purpose of evaluating and improving the service request processing process and improving customer satisfaction is achieved. It can simplify the complexity of service quality and efficiency evaluation, making it more intuitive, easier to understand and operate, which is beneficial for service providers to adjust service strategies in a timely manner, optimize resource allocation, and improve service efficiency and quality.

[0128] In an exemplary embodiment, Figure 3 is a schematic diagram of an optional model processing method according to an embodiment of the present application, as Figure 3 shown, the above method may include but is not limited to:

[0129] S1, regularly obtain the service request model and the detailed data of work order flow (application instance data):

[0130] At 20:00 every day (the low peak period of service request business), synchronize the service request model data once, and incrementally obtain the service request name, service provider, service node name, and service commitment time of the node; every 10 minutes, incrementally obtain the detailed data of service request work order flow, including work order number, service request name, service node name, the person handling the node, the handling action and time point of the node, work order completion time, overdue mark of the node, and service satisfaction evaluation value.

[0131] S2, obtain valid service request models and work order data:

[0132] Service request model data fields: obtain the service model name, service model ID, model status, affiliated company, service node name, and service commitment time value of the service node;

[0133] Service request work order transfer detail data fields: Obtain the service work order number, service model name, service model ID, work order creation time, work order creator and affiliated company, work order status, name of the transferred service node, handler and affiliated company of each service node, processing action of each service node, start processing time and processing completion time of each service node, start suspension time and suspension end time of each service node (if the processing action is a suspension action), work order completion time, service satisfaction evaluation value.

[0134] S3, Data cleaning:

[0135] Service request model data cleaning rules: Model status, equal to enabled; affiliated company, obtain the company where the current user is located; service model name: obtain the service model name selected by the user (the user query interface should support full selection, multiple selection, and single selection);

[0136] Service request work order transfer detail data cleaning rules: Work order status, excluding invalid work orders that have been closed; work order nodes, excluding work orders where the current service node is in the service application node and the internal review node of the service applicant; work order creation time: obtain service request work orders created within the time period selected by the user; service model name: obtain service request work orders corresponding to the service model name selected by the user (the user query interface should support full selection, multiple selection, and single selection).

[0137] S4, Indicator calculation:

[0138] Service overdue mark (corresponding to the determination of the above overdue flag): (The processing completion time of the previous node of a certain service node + the service commitment time value of this service node + the number of holiday days during the period) is earlier than the processing completion time of this service node, and this service node of the service work order is marked as service overdue;

[0139] Service long-term unprocessed mark (corresponding to the determination of the above unprocessed flag): (The processing completion time of a certain service node - the processing completion time of the previous node of this service node) > 50 natural days, or (the current date - the processing completion time of the previous node of the current service node) > 50 natural days, and this service node of the service work order is marked as service long-term unprocessed;

[0140] Service long-time suspension mark (corresponding to the determination of the above suspension flag): (The suspension end time of a certain service node - the start suspension time of this service node) > 50 natural days, and this service node of the service work order is marked as service long-term unprocessed;

[0141] Service implementation multi-node reassignment mark (corresponding to the determination of the above reassignment flag): The processing action of a certain service node includes a reassignment action and the number of times is greater than 3 times, and this service node of the service work order is marked as service implementation multi-person reassignment;

[0142] Further, a service request corresponds to a work order, and the metric calculation includes but is not limited to:

[0143] Service compliance rate = Number of service models with service commitment time set at service nodes / Total number of service models;

[0144] Service implementation on-time rate = Total number of service work orders marked as overdue / Total number of service request work orders;

[0145] Service unprocessed rate = Total number of service work orders marked as unprocessed for a long time / Total number of service request work orders;

[0146] Service suspension rate = Total number of service work orders marked as suspended / Total number of service request work orders;

[0147] Service reassignment rate = Total number of service work orders marked as having multiple reassignment during service implementation / Total number of service request work orders;

[0148] Average score of service delivery satisfaction: Sum of service delivery satisfaction values of completed service request work orders / Total number of completed service request work orders;

[0149] Median of service delivery satisfaction: Median of service delivery satisfaction values of completed service request work orders;

[0150] S5, Service request quality and efficiency metrics (the above initial rating parameters):

[0151] Calculate the service request quality and efficiency metrics based on the service request model and work order data according to the metric combination rules. The service request quality and efficiency metrics include: service compliance rate, service implementation on-time rate, long-term unprocessed rate of service, long-time suspension rate of service, multiple reassignment rate of service implementation, average score and median of service delivery satisfaction. The score of a single service request model = Sum of the following metric scores. For example, the service request quality and efficiency metrics are determined as shown in Table 1:

[0152]

[0153]

[0154] Table 1

[0155] Further, the rating of a single service request model can be as shown in Table 2:

[0156]

[0157] Table 2

[0158] Through the embodiments of the present application, it focuses on comprehensively integrating the existing service request model information and work order transfer information according to preset rules, constructing a system, cleaning data, improving business, and visual design. Based on the operation of business indicators such as the processing duration, suspension duration, implementation success rate, and service satisfaction evaluation of service requests, it calculates the service compliance rate, service efficiency, and service quality statistics of all services, multiple services, or a single service within a fixed time period, and realizes the scoring and grading of the quality and efficiency of service requests. According to the scoring and grading of the quality and efficiency of service requests, the service request management party can clearly understand the general situation of service requests and at the same time recommend high-quality services to other users.

[0159] Furthermore, it provides capabilities such as horizontal comparison and detailed export of business indicators such as the processing duration, suspension duration, implementation success rate, and service satisfaction evaluation of service requests, helping the service request provider to timely analyze and master the problems existing in the service process, and improving the service implementation efficiency and service delivery quality.

[0160] It can be understood that in the specific implementation manner of the present application, it involves data related to user information, etc. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0161] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0162] According to another aspect of the embodiments of the present application, there is also provided a model processing device for implementing the above model processing method. As Figure 4 shown, the device includes:

[0163] An acquisition module 402, configured to acquire model data and application instance data of a service request model, where the model data is used to indicate service nodes in the service request model, the service nodes are used to process service requests, the application instance data is used to indicate the processing status of service requests, and the service request model is deployed in a first business system;

[0164] A determination module 404, configured to determine a processing flag of a service node according to model data and application instance data when a service request model is enabled and the application instance data is valid; perform a service rating operation on the processing flag, the model data, and the application instance data of the service node to obtain a target rating parameter, where the processing flag is used to indicate the progress of the service node in processing a service request, and the target rating parameter is used to indicate the efficiency of the service request model in processing the service request.

[0165] A processing module 406, configured to deploy the service request model in a second service system when the target rating parameter is greater than or equal to a rating parameter threshold, where the second service system is different from the first service system, and the second service system can process requests of the same type as the service request.

[0166] As an optional solution, the above device is used to perform a service rating operation on the processing flag, the model data, and the application instance data of the service node in the following manner to determine a target rating parameter: perform a service rating operation on the processing flag, the model data, and the application instance data of the service node to obtain a plurality of initial rating parameters, where the plurality of target rating parameters include service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate; perform a merging operation on the plurality of initial rating parameters to generate a target rating parameter.

[0167] As an optional solution, the above device is further used to: before performing a merging operation on the plurality of initial rating parameters to generate a target rating parameter, set an expected flag for a target node when an expected processing duration is set for the target node, where the processing flag of the service node includes the expected flag, the target node is any node in the service nodes, and the model data includes a parameter for indicating whether the expected processing duration is set for the target node; when at least one node in the service nodes is set with the expected flag, determine the service timeliness as a first service timeliness; when none of the nodes in the service nodes is set with the expected flag, determine the service timeliness as a second service timeliness, where the value of the first service timeliness is greater than the value of the second service timeliness.

[0168] As an alternative, the above device is further configured to: before performing a merging operation on multiple initial rating parameters to generate target rating parameters, sum up the number of overdue requests corresponding to each request in the service request to obtain the number of service overdue requests; divide the number of service overdue requests by the number of requests in the service request to obtain the service overdue rate; sum up the number of unprocessed requests corresponding to each request in the service request to obtain the number of service unprocessed requests; divide the number of service unprocessed requests by the number of requests in the service request to obtain the service unprocessed rate; sum up the number of pending requests corresponding to each request in the service request to obtain the number of service pending requests; divide the number of service pending requests by the number of requests in the service request to obtain the service pending rate; sum up the number of reassigned requests corresponding to each request in the service request to obtain the number of service reassigned requests; divide the number of service reassigned requests by the number of requests in the service request to obtain the service reassigned rate.

[0169] As an alternative, the above device is further configured to: determine the number of overdue requests corresponding to a request in the service request through the following steps: when at least one node in the service nodes sets an overdue flag, set the number of overdue requests corresponding to a request to 1; when none of the nodes in the service nodes set an overdue flag, set the number of overdue requests corresponding to a request to 0; determine the number of unprocessed requests corresponding to a request in the service request through the following steps: when at least one node in the service nodes sets an unprocessed flag, set the number of unprocessed requests corresponding to a request to 1, where the processing flag of the service node includes an unprocessed flag; when none of the nodes in the service nodes set an unprocessed flag, set the number of unprocessed requests corresponding to a request to 0;

[0170] As an alternative, the above device is further configured to: when the difference between the actual processing time point of the target node and the actual processing time point of the previous node of the target node is greater than the processing time threshold, set an unprocessed flag for the target node; when the difference between the initiation time point of a request and the actual processing time point of the previous node of the target node is greater than the processing time threshold, set an unprocessed flag for the target node, where the service nodes include the target node.

[0171] As an alternative, the above device is further configured to: determine the number of times a request is suspended for a request in a service request through the following steps: when at least one service node in the service nodes sets a suspension flag, set the number of times the request is suspended for a request to 1, where the processing flag of the service node includes a suspension flag; when none of the nodes in the service nodes set a suspension flag, set the number of times the request is not processed for a request to 0; determine the number of times a request is reassigned for a request in a service request through the following steps: when at least one service node in the service nodes sets a reassignment flag, set the number of times the request is reassigned for a request to 1, where the processing flag of the service node includes a reassignment flag; when none of the nodes in the service nodes set a reassignment flag, set the number of times the request is reassigned for a request to 0.

[0172] As an alternative, the above device is configured to perform a merging operation on multiple initial rating parameters in the following manner to generate a target rating parameter: determine the rating scores of the respective initial rating parameters among the multiple initial rating parameters according to a target mapping relationship, where the target mapping relationship includes multiple mapping pairs, and one mapping pair consists of a parameter value range and a rating score; sum up the rating scores of the respective initial rating parameters to generate a target rating parameter.

[0173] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the function of the module or unit.

[0174] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0175] According to one aspect of the present application, a computer program product is provided, and the computer program product includes a computer program.

[0176] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0177] Figure 5 Schematically shown is a block diagram of a computer system of an electronic device for implementing the embodiments of the present application.

[0178] It should be noted that Figure 5The computer system 500 of the illustrated electronic device is merely an example and shall not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0179] As Figure 5 shown, the computer system 500 includes a central processing unit 501 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 502 (ROM) or the program loaded from the storage section 508 into the random access memory 503 (RAM). In the random access memory 503, various programs and data required for system operation are also stored. The central processing unit 501, the read-only memory 502, and the random access memory 503 are connected to each other via a bus 504. The input / output interface 505 (Input / Output interface, i.e., I / O interface) is also connected to the bus 504.

[0180] The following components are connected to the input / output interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a local area network card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read from it can be installed into the storage section 508 as needed.

[0181] Specifically, according to the embodiments of the present application, the processes described in each method flowchart can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, various functions defined in the system of the present application are executed.

[0182] In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, various functions provided by the embodiments of the present application are executed.

[0183] According to another aspect of the embodiments of the present application, an electronic device for implementing the above model processing method is further provided. The electronic device can be Figure 1 the terminal device or server shown. In this embodiment, the terminal device is taken as an example for illustration. As Figure 6 shown, the electronic device includes a memory 602 and a processor 604. A computer program is stored in the memory 602, and the processor 604 is configured to execute the steps in any of the above method embodiments through the computer program.

[0184] Optionally, in this embodiment, the above electronic device can be at least one of multiple network devices in a computer network.

[0185] Optionally, in this embodiment, the above processor can be configured to execute the methods in the embodiments of the present application through a computer program.

[0186] Optionally, those of ordinary skill in the art can understand that Figure 6 the structure shown is only schematic, Figure 6 and it does not limit the structure of the above electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, etc.) than those shown in Figure 6 , or have a different configuration from that shown in Figure 6 .

[0187] Among them, the memory 602 can be used to store software programs and modules, such as the program instructions / modules corresponding to the model processing method and device in the embodiments of the present application. The processor 604 executes various functional applications and data processing by running the software programs and modules stored in the memory 602, that is, implements the above model processing method. The memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 602 may further include a memory remotely set relative to the processor 604, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and their combinations. Among them, the memory 602 can specifically but not limitedly be used to store information such as model data and application instance data. As an example, as Figure 6As shown, the above-mentioned memory 602 may but is not limited to include the acquisition module 402, the determination module 404, and the processing module 406 in the above-mentioned model processing device. In addition, it may also include but is not limited to other module units in the above-mentioned model processing device, which will not be elaborated in this example.

[0188] Optionally, the above-mentioned transmission device 606 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 606 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable, so as to communicate with the Internet or a local area network. In one example, the transmission device 606 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0189] In addition, the above-mentioned electronic device further includes: a display 608, which is used to display the above-mentioned model data and application instance data; and a connection bus 610, which is used to connect each module component in the above-mentioned electronic device.

[0190] In other embodiments, the above-mentioned terminal device or server may be a node in a distributed system. Among them, the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes can form a peer-to-peer network, and any form of computing device, such as a server, a terminal, etc., can become a node in the blockchain system by joining the peer-to-peer network.

[0191] According to one aspect of the present application, there is provided a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the model processing methods provided in various optional implementation manners of the above-mentioned model processing aspect.

[0192] Optionally, in this embodiment, the above-mentioned computer-readable storage medium may be set to store the methods for executing the embodiments of the present application.

[0193] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the above-mentioned various methods can be completed by instructing the relevant hardware of the terminal device through a program. The program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disc, etc.

[0194] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0195] If the integrated units in the above embodiments are implemented in the form of software function units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more electronic devices to execute all or part of the steps of the methods described in various embodiments of the present application.

[0196] In the above embodiments of the present application, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0197] In the several embodiments provided by the present application, it should be understood that the disclosed application program can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0198] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] In addition, the functional units in the various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software function units.

[0200] The above is only the preferred embodiment of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A model processing method, characterized in that, Including: Obtain the model data and application instance data of the service request model. The model data is used to indicate the service nodes in the service request model. The service nodes are used to process service requests. The application instance data is used to indicate the processing status of the service requests. The service request model is deployed in the first business system. When the service request model is enabled and the application instance data is valid, determine the processing flag of the service node according to the model data and the application instance data; perform a service rating operation on the processing flag, the model data, and the application instance data of the service node to obtain a target rating parameter. The processing flag is used to indicate the progress of the service node in processing the service request. The target rating parameter is used to indicate the efficiency of the service request model in processing the service request. When the target rating parameter is greater than or equal to the rating parameter threshold, deploy the service request model in the second business system. The second business system is different from the first business system. The second business system can process requests of the same type as the service request.

2. The method according to claim 1, characterized in that The performing a service rating operation on the processing flag, the model data, and the application instance data of the service node to determine a target rating parameter includes: Perform the service rating operation on the processing flag, the model data, and the application instance data of the service node to obtain a plurality of initial rating parameters. The plurality of target rating parameters include service timeliness, service overdue rate, service unprocessed rate, service suspension rate, and service reassignment rate. Perform a merging operation on the plurality of initial rating parameters to generate the target rating parameter.

3. The method according to claim 2, wherein Before performing the merging operation on the plurality of initial rating parameters to generate the target rating parameter, the method further includes: When an expected processing duration is set for a target node, set an expected flag for the target node. The processing flag of the service node includes the expected flag. The target node is any one of the service nodes. The model data includes a parameter for indicating whether the expected processing duration is set for the target node. When at least one node in the service node is set with the expected flag, determine the service timeliness as the first service timeliness. When none of the nodes in the service node is set with the expected flag, determine the service timeliness as the second service timeliness. The value of the first service timeliness is greater than the value of the second service timeliness.

4. The method according to claim 2, wherein Before performing the merging operation on the plurality of initial rating parameters to generate the target rating parameter, the method further includes: Sum the number of overdue times corresponding to each request in the service request to obtain the service overdue times; divide the service overdue times by the number of requests in the service request to obtain the service overdue rate. Sum the number of unprocessed times corresponding to each request in the service request to obtain the service unprocessed times; divide the service unprocessed times by the number of requests in the service request to obtain the service unprocessed rate. Sum the number of request suspensions corresponding to each request in the service request to obtain the service suspension count; divide the service suspension count by the number of requests in the service request to obtain the service suspension rate. Sum the number of request reassignment times corresponding to each request in the service request to obtain the service reassignment count; divide the service reassignment count by the number of requests in the service request to obtain the service reassignment rate.

5. The method according to claim 4, wherein The method further includes: Determine the number of request overdue times corresponding to one request in the service request through the following steps: when at least one node in the service node sets an overdue flag, set the number of request overdue times corresponding to the one request to 1; when none of the nodes in the service node set the overdue flag, set the number of request overdue times corresponding to the one request to 0. Determine the number of request unprocessed times corresponding to one request in the service request through the following steps: when at least one node in the service node sets an unprocessed flag, where the processing flags of the service node include the unprocessed flag, set the number of request unprocessed times corresponding to the one request to 1; when none of the nodes in the service node set the unprocessed flag, set the number of request unprocessed times corresponding to the one request to 0.

6. The method according to claim 5, wherein The method further includes: When the difference between the actual processing time point of the target node and the actual processing time point of the previous node of the target node is greater than the processing time threshold, the target node sets the unprocessed flag. When the difference between the initiation time point of the one request and the actual processing time point of the previous node of the target node is greater than the processing time threshold, the target node sets the unprocessed flag, where the service node includes the target node.

7. The method according to claim 4, characterized in that The method further includes: Determine the number of request suspension times corresponding to one request in the service request through the following steps: when at least one service node in the service node sets a suspension flag, where the processing flags of the service node include the suspension flag, set the number of request suspension times corresponding to the one request to 1; when none of the nodes in the service node set the suspension flag, set the number of request unprocessed times corresponding to the one request to 0. Determine the number of request reassignment times corresponding to one request in the service request through the following steps: when at least one service node in the service node sets a reassignment flag, where the processing flags of the service node include the reassignment flag, set the number of request reassignment times corresponding to the one request to 1; when none of the nodes in the service node set the reassignment flag, set the number of request reassignment times corresponding to the one request to 0.

8. The method according to claim 2, characterized in that, The performing the merging operation on the multiple initial rating parameters to generate the target rating parameter includes: Determine the rating scores of the respective initial rating parameters among the multiple initial rating parameters according to the target mapping relationship, where the target mapping relationship includes multiple mapping pairs, and one mapping pair consists of a parameter value range and a rating score; Sum up the rating scores of the respective initial rating parameters to generate the target rating parameter.

9. A model processing device, characterized in that, Comprising: An acquisition module, configured to acquire model data and application instance data of a service request model, where the model data is used to indicate service nodes in the service request model, the service nodes are used to process service requests, the application instance data is used to indicate the processing status of the service requests, and the service request model is deployed in a first service system; A determination module, configured to, when the service request model is enabled and the application instance data is valid, determine a processing flag of the service node according to the model data and the application instance data; perform a service rating operation on the processing flag of the service node, the model data, and the application instance data to obtain a target rating parameter, where the processing flag is used to indicate the progress of the service node in processing the service request, and the target rating parameter is used to indicate the efficiency of the service request model in processing the service request; A processing module, configured to, when the target rating parameter is greater than or equal to a rating parameter threshold, deploy the service request model in a second service system, where the second service system is different from the first service system, and the second service system can process requests of the same type as the service request.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, where the computer program, when run by an electronic device, executes the method described in any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 8.

12. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method described in any one of claims 1 to 8 through the computer program.

Images