SaaS multi-tenant intelligent work order distribution and processing system based on micro-service architecture

Abstract

The invention discloses an SaaS multi-tenant intelligent work order distribution and processing system based on a micro-service architecture, and belongs to the technical field of multi-tenant work order processing. The SaaS multi-tenant intelligent work order distribution and processing system based on the micro-service architecture comprises a model construction module, a work order distribution module, a work order processing module and a tenant service module. The method solves the problem of low working efficiency caused by more tedious work order tracking and resource allocation in the prior art, can better accord with the business scene of an enterprise, improves the management efficiency, ensures that the problem is solved in time, reduces the labor cost, the time cost and the operation cost of each tenant, and improves the user experience. The management process is simplified, flexibility and efficiency are improved, it is ensured that high-priority customer requests can be processed in time, overall resource utilization is optimized, customer satisfaction is improved, resource waste caused when high-priority tenants wait for low-priority tasks is avoided, and overall operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-tenant work order processing, and specifically to a SaaS multi-tenant intelligent work order distribution and processing system based on a microservice architecture. Background Art

[0002] Multi-tenancy technology is a software architecture technology that can realize the sharing of system instances among multiple tenants while realizing the personalized customization of system instances for tenants. By using multi-tenancy technology, it can be ensured that the common parts of the system are shared and the individual parts are isolated separately. The technical focus of multi-tenancy technology is to maintain the isolation of data between different tenants. When using multi-tenancy technology, the processing of work orders is particularly important, which is related to the work efficiency of tenants and the credibility of multi-tenancy technology.

[0003] A Chinese patent with publication number CN118569601A discloses an automatic work order processing system and method based on a large language model, including: a user terminal, a server and a processing terminal, both of which are connected to the server in communication; the user terminal is used to input the user's service requirements and upload the user's service requirements to the server; the server is used to create and allocate service work orders, and call the work order processing interface, generate work order processing tasks based on the service work orders, and send the work order processing tasks to the processing terminal; the processing terminal is used to record the execution records of the work order processing tasks during the execution of the work order processing tasks, upload the execution records to the server, use the large language model to call the work order interface, realize the automatic generation and distribution of work orders, thereby improving the efficiency and accuracy of work order processing.

[0004] In actual use, the above patent directly allocates work orders when allocating them, which makes work order tracking and resource allocation more cumbersome, and thus leads to low work efficiency; therefore, it does not meet existing needs. In this regard, we propose a SaaS multi-tenant intelligent work order distribution and processing system based on a microservice architecture. Summary of the invention

[0005] The purpose of the present invention is to provide a SaaS multi-tenant intelligent work order distribution and processing system based on a microservice architecture, which can better fit the business scenarios of the enterprise, improve management efficiency, ensure that problems are solved in a timely manner, reduce labor costs, time costs and operating costs of each tenant, simplify the management process, improve flexibility and efficiency, ensure that high-priority customer requests can be processed in a timely manner, improve overall processing efficiency, optimize overall resource utilization, improve customer satisfaction, avoid resource waste caused by high-priority tenants waiting for low-priority tasks, and solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture, comprising:

[0007] The model building module is used to obtain the corresponding work order sample data set in the SaaS historical database, train the initial model based on the work order sample data set, and obtain a multi-tenant intelligent work order distribution model;

[0008] The work order distribution module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan;

[0009] The work order processing module is used to input the multi-tenant intelligent work orders to be processed into the trained deep learning network to generate priority coefficient levels, set the processing deadlines corresponding to the priority levels according to the different priority levels, and generate a processing plan for the multi-tenant intelligent work orders;

[0010] The tenant service module is used to feed back the multi-tenant smart work order distribution information to the corresponding tenant, update the work order status to "resolved", generate an analysis report on the processing of the multi-tenant smart work order, and make corresponding evaluations on the processing of the multi-tenant smart work order.

[0011] Preferably, the model building module includes:

[0012] The initial model is called to extract the global semantic features of the multi-tenant intelligent work order sample data set in the SaaS historical database;

[0013] The global semantic features of the multi-tenant intelligent work order sample data set are classified and processed to obtain the classification training results;

[0014] Extract the global semantic features of the multi-tenant intelligent work order sample data set to obtain local semantic features;

[0015] Attribute discrimination is performed on local semantic features to obtain attribute training results, where attributes include problem words and non-problem words;

[0016] Determine the first loss based on the classification training results and the classification identification of the multi-tenant intelligent work order sample data set;

[0017] According to the attribute training results and the attribute identification of the multi-tenant intelligent work order sample data set, the second loss is determined, and the initial model is trained according to the first loss and the second loss to obtain the multi-tenant intelligent work order distribution model.

[0018] Preferably, the work order distribution module includes:

[0019] The work order creation module is used to obtain the work order application content of multiple tenants, create a multi-tenant smart work order of the corresponding type according to the work order application content, and set the work order status to "to be resolved";

[0020] The model solving module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan.

[0021] Preferably, the work order creation module includes:

[0022] Obtain the work order application content of multiple tenants, and perform segmentation, sentence processing, and word segmentation processing on the work order application content in sequence to obtain segment-sentence-word information;

[0023] Extract semantic features from paragraph-sentence-word information to obtain type feature vectors, classify the type feature vectors to obtain target classification labels;

[0024] Perform feature processing on the type feature vector to obtain local semantic features, perform attribute discrimination on the local semantic features to obtain each word and the corresponding attribute label;

[0025] Feature extraction is performed on the target question words to obtain the target question features, and feature extraction is performed on all question information under the target classification label stored in the SaaS historical database to obtain candidate question features;

[0026] The semantic similarity between the target question feature and all candidate question features is calculated respectively, and the answer information corresponding to the candidate question whose semantic similarity is greater than a preset threshold is determined as the answer information corresponding to the target question term. This information is the work order type of the multi-tenant smart work order.

[0027] Preferably, the method of solving the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm specifically includes:

[0028] Randomly generate a certain number of multi-tenant intelligent work order distribution solutions as the initial population;

[0029] Calculate the fitness value of each multi-tenant intelligent work order distribution solution based on the objective function;

[0030] Generate a new multi-tenant intelligent work order distribution solution through the Levy flight mode of the cuckoo algorithm;

[0031] Compare the newly generated multi-tenant intelligent work order distribution plan with the current plan. If the new plan has a higher fitness value, replace the original plan.

[0032] When the preset number of iterations is met or a specific accuracy requirement is reached, the algorithm stops and outputs the optimal multi-tenant intelligent work order distribution solution.

[0033] Preferably, the work order processing module includes:

[0034] The work order scoring module is used to input the multi-tenant smart work order to be processed into the trained deep learning network, obtain the estimated scoring data of the current multi-tenant smart work order, and generate the priority coefficient level according to the estimated scoring data;

[0035] A processing solution generation module is used to extract the corresponding reference processing strategy from the rule base and generate a processing solution for the multi-tenant smart work order based on the reference processing strategy;

[0036] The work order time limit setting module is used to set the processing period of the corresponding priority level according to different priority levels before multi-tenant intelligent work order processing.

[0037] Preferably, the work order scoring module includes:

[0038] Build a deep learning network, use the historical work orders of multiple tenants as training sets, and the corresponding scoring data of the historical work orders of multiple tenants as labels, input them into the deep learning network for training, and obtain the trained deep learning network;

[0039] Input the multi-tenant smart work order to be processed into the trained deep learning network to obtain the estimated score data of the current multi-tenant smart work order;

[0040] The estimated scoring data is analyzed and processed to generate a multi-tenant smart work order recommendation coefficient, and the multi-tenant smart work order with the highest priority coefficient is given priority. The highest priority coefficient is set to 1, the second highest priority coefficient is set to 0.8, and the lowest priority coefficient is set to 0.5.

[0041] Preferably, the processing scheme generating module comprises:

[0042] Generate digital tags corresponding to the priority level of multi-tenant smart work orders, and generate text-based classification descriptions corresponding to the triggering event information;

[0043] Input the trigger event information into the rule base for processing strategy matching to obtain the matching result. The rule base contains rules for various work order types and corresponding processing solutions.

[0044] According to the matching results, the corresponding reference processing strategy is extracted from the rule library, and specific operation steps are generated according to the reference processing strategy, which is the processing solution for multi-tenant intelligent work orders.

[0045] Preferably, the work order time limit setting module includes:

[0046] Before multi-tenant smart work orders are processed, the processing period of the corresponding priority level is set according to the different priority levels. The processing period is the time when the corresponding work order process is created when the tenant initiates the application to the time when the processing personnel arrives at the location where the work order is created;

[0047] The highest priority multi-tenant smart work order has a deadline of 2 hours, the second highest priority multi-tenant smart work order has a deadline of 4 hours, and the lowest priority multi-tenant smart work order has a deadline of 6 hours.

[0048] Preferably, the tenant service module includes:

[0049] The interactive service module is used to feed back the multi-tenant intelligent work order distribution information to the corresponding tenant, obtain the interactive service results, and determine whether the multi-tenant declaration information of the tenant has been resolved;

[0050] The information upload module is used to update the status of the work order to "solved" after the work order problem created by multiple tenants is solved, and to perform testing and verification. The tenant confirms that the problem has been solved and uploads the processing completion information;

[0051] The work order tracking and reporting module is used to track the life cycle of multi-tenant smart work orders and generate analysis reports on the processing of multi-tenant smart work orders;

[0052] The service evaluation module is used to close resolved multi-tenant smart work orders and conduct corresponding evaluation on the handling of multi-tenant smart work orders.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention can better fit the business scenarios of enterprises, improve management efficiency, ensure that problems are solved in a timely manner, reduce labor costs, time costs and operating costs of each tenant, simplify the management process, improve flexibility and efficiency, ensure that high-priority customer requests can be processed in a timely manner, improve overall processing efficiency, and allocate resources according to the needs and importance of tenants, thereby optimizing overall resource utilization, improving customer satisfaction, avoiding resource waste caused by high-priority tenants waiting for low-priority tasks, and helping to reduce operating costs and improve overall operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a schematic diagram of the module of the SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture of the present invention;

[0056] Figure 2 It is a flow chart of the distribution and processing of SaaS multi-tenant intelligent work orders based on microservice architecture of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] In order to solve the problem that in the actual use of the existing patent, the work order is directly allocated when the work order is allocated, which makes the work order tracking and resource allocation more cumbersome, thereby resulting in low work efficiency, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0059] SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture, including:

[0060] The model building module is used to obtain the corresponding work order sample data set in the SaaS historical database, train the initial model based on the work order sample data set, and obtain a multi-tenant intelligent work order distribution model;

[0061] The work order distribution module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan;

[0062] The work order processing module is used to input the multi-tenant intelligent work orders to be processed into the trained deep learning network to generate priority coefficient levels, set the processing deadlines corresponding to the priority levels according to the different priority levels, and generate a processing plan for the multi-tenant intelligent work orders;

[0063] The tenant service module is used to feed back the multi-tenant smart work order distribution information to the corresponding tenant, update the work order status to "resolved", generate an analysis report on the processing of the multi-tenant smart work order, and make corresponding evaluations on the processing of the multi-tenant smart work order.

[0064] Model building modules, including:

[0065] The initial model is called to extract the global semantic features of the multi-tenant intelligent work order sample data set in the SaaS historical database;

[0066] The global semantic features of the multi-tenant intelligent work order sample data set are classified and processed to obtain classification training results, where the classification types include problem type, function type and operation type;

[0067] Extract the global semantic features of the multi-tenant intelligent work order sample data set to obtain local semantic features;

[0068] Attribute discrimination is performed on local semantic features to obtain attribute training results, where attributes include problem words and non-problem words;

[0069] Determine the first loss based on the classification training results and the classification identification of the multi-tenant intelligent work order sample data set;

[0070] According to the attribute training results and the attribute identification of the multi-tenant intelligent work order sample data set, the second loss is determined, and the initial model is trained according to the first loss and the second loss to obtain the multi-tenant intelligent work order distribution model.

[0071] A multi-tenant intelligent work order distribution model is constructed using the multi-tenant intelligent work order sample data set in the SaaS historical database. It can be customized according to the actual needs of the enterprise to meet the enterprise's special requirements in terms of processes, marketing methods, etc., better fit the enterprise's business scenarios, and achieve unified management. It is easy to track, monitor and count, improve management efficiency, and has good collaborative functions. It can achieve cross-departmental and cross-regional team collaboration, improve work efficiency, and promptly remind processing personnel of the work order status to ensure that problems are solved in a timely manner. Through data collection, analysis and mining, insights into bottlenecks and optimization space can be obtained, providing strong support for decision-making.

[0072] Work order distribution module, including:

[0073] The work order creation module is used to obtain the work order application content of multiple tenants, create a multi-tenant smart work order of the corresponding type according to the work order application content, and set the work order status to "to be resolved";

[0074] The model solving module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan.

[0075] The cuckoo algorithm simulates the breeding behavior and Levy flight mode of cuckoos. Cuckoos lay eggs in the nests of other birds. Each nest in the algorithm represents a possible solution, and the eggs symbolize the quality of the solution. Cuckoos will randomly choose nests to lay eggs. If the newly generated solution is better than the solution in the original nest, the new solution will replace the old solution. Cuckoos use the Levy flight mode when looking for new nests. This flight mode enables the algorithm to search long and short distances in the search space, which helps to jump out of the local optimal solution and explore a wider area. The extreme value dynamics optimization algorithm is an optimization algorithm based on physical principles. It simulates the dynamic process in the physical system. The algorithm finds the optimal solution by simulating the dynamic behavior of the system. In the multi-tenant intelligent work order distribution model, the extreme value dynamics optimization algorithm can be used to adjust the strategy and parameters of the multi-tenant intelligent work order distribution to optimize the overall efficiency and cost. By combining the cuckoo algorithm and the extreme value dynamics optimization algorithm, the advantages of both can be fully utilized to improve the efficiency and accuracy of the multi-tenant intelligent work order distribution.

[0076] Work order creation module, including:

[0077] Obtain the work order application content of multiple tenants, and perform segmentation, sentence processing, and word segmentation processing on the work order application content in sequence to obtain segment-sentence-word information;

[0078] Extract semantic features from paragraph-sentence-word information to obtain type feature vectors, classify the type feature vectors to obtain target classification labels, which include question type, function type, and operation type;

[0079] Perform feature processing on the type feature vector to obtain local semantic features, perform attribute discrimination on the local semantic features to obtain each word and the corresponding attribute label, the attribute label includes problem words and non-problem words;

[0080] Feature extraction is performed on the target question words to obtain the target question features, and feature extraction is performed on all question information under the target classification label stored in the SaaS historical database to obtain candidate question features;

[0081] Calculate the semantic similarity between the target question feature and all candidate question features respectively, and determine the answer information corresponding to the candidate question whose semantic similarity is greater than a preset threshold as the answer information corresponding to the target question word, which is the work order type of the multi-tenant smart work order;

[0082] By confirming the type of multi-tenant smart work order, generating a processing plan based on the type of multi-tenant smart work order, and then distributing the multi-tenant smart work order and the processing plan, since all tenants share the same software instance, only one software instance needs to be maintained, rather than maintaining an independent instance for each tenant. This not only reduces the cost of purchasing, installing and maintaining hardware and software, but also reduces labor costs and time costs, significantly reducing the operating costs of each tenant, reducing the maintenance of physical and software resources, simplifying the management process, and improving flexibility and efficiency.

[0083] The multi-tenant intelligent work order distribution model is solved based on the cuckoo algorithm and extreme value dynamics optimization algorithm, including:

[0084] A certain number of multi-tenant intelligent work order distribution schemes are randomly generated as the initial population. Each scheme can be regarded as a "bird's nest" representing a possible solution.

[0085] Calculate the fitness value of each multi-tenant intelligent work order distribution solution according to the objective function. The fitness value is usually related to factors such as the efficiency and cost of multi-tenant intelligent work order distribution.

[0086] Generate a new multi-tenant intelligent work order distribution solution through the Levy flight mode of the cuckoo algorithm. Levy flight is a random walk whose step size follows the Levy distribution. It helps to perform long-distance and short-distance searches in the search space, helps to jump out of the local optimal solution and explore a wider area.

[0087] Compare the newly generated multi-tenant intelligent work order distribution plan with the current plan. If the new plan has a higher fitness value, replace the original plan, discard some inferior plans with a certain probability, and regenerate a new plan.

[0088] When the preset number of iterations is met or a specific accuracy requirement is reached, the algorithm stops and outputs the optimal multi-tenant intelligent work order distribution solution.

[0089] Work order processing module, including:

[0090] The work order scoring module is used to input the multi-tenant smart work order to be processed into the trained deep learning network, obtain the estimated scoring data of the current multi-tenant smart work order, and generate the priority coefficient level according to the estimated scoring data;

[0091] A processing solution generation module is used to extract the corresponding reference processing strategy from the rule base and generate a processing solution for the multi-tenant smart work order based on the reference processing strategy;

[0092] The work order time limit setting module is used to set the processing period of the corresponding priority level before multi-tenant intelligent work order processing.

[0093] Ticket scoring module, including:

[0094] Build a deep learning network, use the historical work orders of multiple tenants as training sets, and the corresponding scoring data of the historical work orders of multiple tenants as labels, input them into the deep learning network for training, and obtain the trained deep learning network;

[0095] Input the multi-tenant smart work order to be processed into the trained deep learning network to obtain the estimated score data of the current multi-tenant smart work order;

[0096] The estimated scoring data is analyzed and processed to generate a multi-tenant smart work order recommendation coefficient, and the multi-tenant smart work order with the highest priority coefficient is given priority. The highest priority coefficient is set to 1, the second highest priority coefficient is set to 0.8, and the lowest priority coefficient is set to 0.5.

[0097] Processing solution generation module, including:

[0098] Generate digital tags corresponding to the priority level of multi-tenant smart work orders, and generate text-based classification descriptions corresponding to the triggering event information;

[0099] Input the trigger event information into the rule base for processing strategy matching to obtain the matching result. The rule base contains rules for various work order types and corresponding processing solutions.

[0100] According to the matching results, the corresponding reference processing strategy is extracted from the rule library, and specific operation steps are generated according to the reference processing strategy, which is the processing solution for multi-tenant intelligent work orders.

[0101] The work order time limit setting module includes:

[0102] Before multi-tenant smart work orders are processed, the processing period of the corresponding priority level is set according to the different priority levels. The processing period is the time when the corresponding work order process is created when the tenant initiates the application to the time when the processing personnel arrives at the location where the work order is created;

[0103] The highest priority multi-tenant smart work order has a deadline of 2 hours, the second highest priority multi-tenant smart work order has a deadline of 4 hours, and the lowest priority multi-tenant smart work order has a deadline of 6 hours.

[0104] By generating priority levels and giving priority to those with high priority, it can be ensured that high-priority customer requests can be processed in a timely manner. For example, high-priority customer requests can be automatically assigned to experienced support staff, while lower-priority requests can be assigned to new employees. This intelligent allocation mechanism not only reduces the time for task allocation, but also improves overall processing efficiency. Resources can be allocated according to the needs and importance of tenants. High-priority tenants can obtain more resources to ensure that their needs are met in a timely manner, while low-priority tenants can be processed when resources permit, thereby optimizing overall resource utilization and ensuring that important customers' requests are given priority, thereby improving customer satisfaction. This is of great significance for maintaining customer relationships and improving customer loyalty. By allocating resources reasonably, it can avoid the waste of resources caused by high-priority tenants waiting for low-priority tasks, which helps to reduce operating costs and improve overall operating efficiency.

[0105] Tenant service module, including:

[0106] The interactive service module is used to feed back the multi-tenant intelligent work order distribution information to the corresponding tenant, obtain the interactive service results, and determine whether the multi-tenant declaration information of the tenant has been resolved;

[0107] The information upload module is used to update the status of the work order to "solved" after the work order problem created by multiple tenants is solved, and to perform testing and verification. The tenant confirms that the problem has been solved and uploads the processing completion information;

[0108] The work order tracking and reporting module is used to track the life cycle of multi-tenant smart work orders throughout the process, ensure timely processing, and generate analysis reports on the processing of multi-tenant smart work orders;

[0109] The service evaluation module is used to close resolved multi-tenant smart work orders and conduct corresponding evaluation on the handling of multi-tenant smart work orders.

[0110] When using the SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture, according to Figure 1 and Figure 2 , including the following steps:

[0111] Step 1: Obtain the corresponding work order sample data set in the SaaS historical database, train the initial model based on the work order sample data set, and obtain a multi-tenant intelligent work order distribution model;

[0112] Step 2: Get the multi-tenant work order application content, create a multi-tenant smart work order of the corresponding type based on the work order application content, and set the work order status to "to be resolved"

[0113] Step 3: Solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm, obtain the work order distribution plan, and feed back the multi-tenant intelligent work order distribution information to the corresponding tenants;

[0114] Step 4: Input the multi-tenant smart work order to be processed into the trained deep learning network to generate a priority coefficient level, set the processing period corresponding to the priority level according to the different priority levels, and generate a processing plan for the multi-tenant smart work order;

[0115] Step 5: Distribute the multi-tenant smart work orders and the processing solutions corresponding to the multi-tenant smart work orders according to the work order distribution plan;

[0116] Step 6: When the work order is processed, update the work order status to "solved", generate an analysis report on the processing of the multi-tenant smart work order, and make a corresponding evaluation of the processing of the multi-tenant smart work order.

[0117] In summary, the SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture of the present invention uses the multi-tenant intelligent work order sample data set in the SaaS historical database to build a multi-tenant intelligent work order distribution model, which better fits the business scenarios of the enterprise, improves management efficiency, has good collaborative functions, realizes cross-departmental and cross-regional team collaboration, improves work efficiency, and promptly reminds processing personnel of the work order status to ensure that problems are solved in a timely manner. By confirming the type of multi-tenant intelligent work order and generating a processing plan based on the type of multi-tenant intelligent work order, and then distributing the multi-tenant intelligent work order and the processing plan, it reduces the labor cost, time cost and operating cost of each tenant, reduces the maintenance of physical resources and software resources, simplifies the management process, improves flexibility and efficiency, and prioritizes high-priority customer requests to ensure that they can be processed in a timely manner, thereby improving the overall processing efficiency. Resources can be allocated according to the needs and importance of tenants, thereby optimizing overall resource utilization, improving customer satisfaction, and avoiding resource waste caused by high-priority tenants waiting for low-priority tasks, which helps to reduce operating costs and improve overall operating efficiency.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0119] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture, characterized by: include: The model building module is used to obtain the corresponding work order sample data set in the SaaS historical database, train the initial model based on the work order sample data set, and obtain a multi-tenant intelligent work order distribution model; The work order distribution module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan; The work order processing module is used to input the multi-tenant intelligent work orders to be processed into the trained deep learning network to generate priority coefficient levels, set the processing deadlines corresponding to the priority levels according to the different priority levels, and generate a processing plan for the multi-tenant intelligent work orders; The tenant service module is used to feed back the multi-tenant smart work order distribution information to the corresponding tenant, update the work order status to "solved", generate an analysis report on the processing of the multi-tenant smart work order, and make corresponding evaluations on the processing of the multi-tenant smart work order.

2. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 1 is characterized by: The model building module comprises: The initial model is called to extract the global semantic features of the multi-tenant intelligent work order sample data set in the SaaS historical database; The global semantic features of the multi-tenant intelligent work order sample data set are classified and processed to obtain the classification training results; Extract the global semantic features of the multi-tenant intelligent work order sample data set to obtain local semantic features; Attribute discrimination is performed on local semantic features to obtain attribute training results, where attributes include problem words and non-problem words; Determine the first loss based on the classification training results and the classification identification of the multi-tenant intelligent work order sample data set; According to the attribute training results and the attribute identification of the multi-tenant intelligent work order sample data set, the second loss is determined, and the initial model is trained according to the first loss and the second loss to obtain the multi-tenant intelligent work order distribution model.

3. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 1 is characterized by: The work order distribution module includes: The work order creation module is used to obtain the work order application content of multiple tenants, create a multi-tenant smart work order of the corresponding type according to the work order application content, and set the work order status to "to be resolved"; The model solving module is used to solve the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme dynamics optimization algorithm, obtain the work order distribution plan, and perform multi-tenant intelligent work order distribution according to the work order distribution plan.

4. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 3 is characterized by: The work order creation module includes: Obtain the work order application content of multiple tenants, and perform segmentation, sentence processing, and word segmentation processing on the work order application content in sequence to obtain segment-sentence-word information; Extract semantic features from paragraph-sentence-word information to obtain type feature vectors, classify the type feature vectors to obtain target classification labels; Perform feature processing on the type feature vector to obtain local semantic features, perform attribute discrimination on the local semantic features to obtain each word and the corresponding attribute label; Feature extraction is performed on the target question words to obtain the target question features, and feature extraction is performed on all question information under the target classification label stored in the SaaS historical database to obtain candidate question features; The semantic similarity between the target question features and all candidate question features is calculated respectively, and the answer information corresponding to the candidate questions whose semantic similarity is greater than a preset threshold is determined as the answer information corresponding to the target question words, and the answer information is the work order type of the multi-tenant smart work order.

5. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 3 is characterized by: The method for solving the multi-tenant intelligent work order distribution model based on the cuckoo algorithm and the extreme value dynamics optimization algorithm specifically includes: Randomly generate a certain number of multi-tenant intelligent work order distribution solutions as the initial population; Calculate the fitness value of each multi-tenant intelligent work order distribution solution based on the objective function; Generate a new multi-tenant intelligent work order distribution solution through the Levy flight mode of the cuckoo algorithm; Compare the newly generated multi-tenant intelligent work order distribution plan with the current plan. If the new plan has a higher fitness value, replace the original plan. When the preset number of iterations is met or a specific accuracy requirement is reached, the algorithm stops and outputs the optimal multi-tenant intelligent work order distribution solution.

6. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 1 is characterized by: The work order processing module includes: The work order scoring module is used to input the multi-tenant smart work order to be processed into the trained deep learning network, obtain the estimated scoring data of the current multi-tenant smart work order, and generate the priority coefficient level according to the estimated scoring data; A processing solution generation module is used to extract the corresponding reference processing strategy from the rule base and generate a processing solution for the multi-tenant smart work order based on the reference processing strategy; The work order time limit setting module is used to set the processing period of the corresponding priority level before multi-tenant intelligent work order processing.

7. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 6 is characterized by: The work order scoring module includes: Build a deep learning network, use the historical work orders of multiple tenants as training sets, and the corresponding scoring data of the historical work orders of multiple tenants as labels, input them into the deep learning network for training, and obtain the trained deep learning network; Input the multi-tenant smart work order to be processed into the trained deep learning network to obtain the estimated score data of the current multi-tenant smart work order; The estimated scoring data is analyzed and processed to generate a multi-tenant smart work order recommendation coefficient, and the multi-tenant smart work order with the highest priority coefficient is given priority. The highest priority coefficient is set to 1, the second highest priority coefficient is set to 0.8, and the lowest priority coefficient is set to 0.

5.

8. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 6 is characterized by: The processing scheme generating module comprises: Generate digital tags corresponding to the priority level of multi-tenant smart work orders, and generate text-based classification descriptions corresponding to the triggering event information; Input the trigger event information into the rule base for processing strategy matching to obtain the matching result. The rule base contains rules for various work order types and corresponding processing solutions. According to the matching results, the corresponding reference processing strategy is extracted from the rule library, and specific operation steps are generated according to the reference processing strategy to provide a processing solution for multi-tenant intelligent work orders.

9. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 6 is characterized by: The work order time limit setting module includes: Before multi-tenant smart work orders are processed, the processing period of the corresponding priority level is set according to the different priority levels. The processing period is the time when the corresponding work order process is created when the tenant initiates the application to the time when the processing personnel arrives at the location where the work order is created; The highest priority multi-tenant smart work order has a deadline of 2 hours, the second highest priority multi-tenant smart work order has a deadline of 4 hours, and the lowest priority multi-tenant smart work order has a deadline of 6 hours.

10. The SaaS multi-tenant intelligent work order distribution and processing system based on microservice architecture according to claim 1, characterized in that: The tenant service module includes: The interactive service module is used to feed back the multi-tenant intelligent work order distribution information to the corresponding tenant, obtain the interactive service results, and determine whether the multi-tenant declaration information of the tenant has been resolved; The information upload module is used to update the status of the work order to "solved" after the work order problem created by multiple tenants is solved, and to perform testing and verification. The tenant confirms that the problem has been solved and uploads the processing completion information; The work order tracking and reporting module is used to track the life cycle of multi-tenant smart work orders and generate analysis reports on the processing of multi-tenant smart work orders; The service evaluation module is used to close resolved multi-tenant smart work orders and conduct corresponding evaluation on the handling of multi-tenant smart work orders.

Images