A service optimization scheduling method, device and equipment and storage medium

Abstract

The present application provides a service optimization scheduling method and device, equipment and storage medium, wherein the method comprises: distributing a user service request to a corresponding service provider according to the current weight of each service provider, so that the service provider responds to the user service request, wherein the service provider with a current weight less than a predetermined weight runs an original service model, and the rest of the service providers run an optimized service model; calculating the new weight of each service provider according to the cumulative single service evaluation value of each service provider, the continuous service evaluation value of each service provider and the continuous non-response value of each service provider, and updating the current weight of each service provider with the new weight of each service provider; and adjusting the service model running in the service provider according to the weight change information of the service provider running the optimized service model. The present application can improve the response speed and accuracy of the user service request, optimize the service model in time, and improve the user experience.

Description

Technical Field

[0001] This article relates to the field of service scheduling, and in particular to a service optimization scheduling method, apparatus, device and storage medium. Background Technology

[0002] Existing service processing systems include a scheduling device and multiple service providers. The scheduling device receives user service requests and distributes them to the service providers. Existing service scheduling methods include the following:

[0003] 1. Random scheduling: This means randomly scheduling user service requests to any service provider;

[0004] 2. Schedule according to the current load of the service provider: that is, schedule according to the current usage of the service provider, and prioritize the service provider with less current service volume;

[0005] 3. Scheduling based on service request source attributes: This means scheduling based on a certain attribute of the user's service request, such as the IP source or whether the service has been previously provided.

[0006] Existing service scheduling technologies do not take into account the quality and capacity of services. Therefore, they cannot objectively evaluate the service provider's performance, which leads to low service processing efficiency and a high risk of errors.

[0007] In existing service processing systems, after service optimization and upgrades, the original service model in the service provider is replaced with an optimized service model. This replacement method, combined with the existing service scheduling methods, cannot accurately determine whether the service optimization is effective. Furthermore, if the service optimization plan has vulnerabilities, it will affect the user's service experience. Summary of the Invention

[0008] This paper addresses the problems in existing service scheduling methods that fail to consider the service quality and capabilities of each service provider, thus failing to guarantee service quality and capabilities, and the inability to accurately determine the effectiveness of service optimizations after updates, which negatively impacts user experience.

[0009] To address the aforementioned technical problems, this paper firstly provides a service optimization scheduling method, including:

[0010] Based on the current weight of each service provider, user service requests are allocated to the corresponding service providers so that the service providers can respond to the user service requests. Among them, service providers with a current weight less than the predetermined weight run the original service model, while the other service providers run the optimized service model.

[0011] Based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, calculate the new weight of each service provider, and update the current weight of each service provider using the new weight of each service provider; adjust the service model running in the service provider based on the weight change information of the service provider running the optimized service model.

[0012] As a further embodiment of this paper, user service requests are allocated to the corresponding service providers based on their current weights, including:

[0013] Based on the current weight of each service provider, the service providers are filtered to select those whose current weight is greater than a predetermined threshold or whose weight has not decreased for M consecutive times.

[0014] User service requests are allocated to the appropriate service providers in descending order of their current weights; or

[0015] Calculate the weight ratio of each service provider based on their current weight, and randomly assign user service requests to the corresponding service provider according to their weight ratio.

[0016] As a further embodiment of this paper, a new weight for each service provider is calculated based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, including:

[0017] Calculate the cumulative single service evaluation coefficient for each service provider based on their cumulative single service evaluation value.

[0018] Calculate the continuous service evaluation coefficient for each service provider based on their continuous service evaluation scores.

[0019] Calculate the non-response coefficient for each service provider based on the consecutive non-response values ​​of each service provider;

[0020] The new weights for each service provider are calculated based on their cumulative single service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient.

[0021] As a further embodiment of this paper, the process for determining the cumulative single service evaluation value of each service provider includes:

[0022] The satisfaction level of each service provider is determined based on the service evaluation results of each response.

[0023] Based on the satisfaction level of each service provider for each service, the cumulative single service evaluation value of each service provider is calculated. The cumulative single service evaluation value of each service provider includes: the number of times the service satisfaction level of each service provider is greater than the first predetermined value and the number of times the service satisfaction level of each service provider is less than the second predetermined value. The first predetermined value is greater than the second predetermined value.

[0024] Based on the cumulative single-service evaluation scores of each service provider, the cumulative single-service evaluation coefficient for each service provider is calculated using the following formula: MP i＝ (1-a) z ×(1+a) x ;

[0025] Among them, MP i Let be the cumulative single service evaluation coefficient of service provider i, where a is the first adjustment value, x is the number of times service provider i's service satisfaction level is greater than the first predetermined value, and z is the number of times service provider i's service satisfaction level is less than the second predetermined value.

[0026] As a further embodiment of this document, the process for determining the continuous service evaluation value of each service provider includes:

[0027] For each service provider, after obtaining the service evaluation result for each time, the service satisfaction level of that service provider for that time is determined based on the service evaluation result for that service provider.

[0028] If the satisfaction level is greater than the first predetermined value, the second adjustment value is added to the service provider's previous continuous service evaluation value to obtain the service provider's current continuous service evaluation value;

[0029] If the satisfaction level is between the first predetermined value and the second predetermined value, then the service provider's previous continuous service evaluation value is set as the service provider's current continuous service evaluation value.

[0030] If the satisfaction level is less than the second predetermined value, then the service provider's evaluation value for this consecutive service is set as the initial value.

[0031] Based on the continuous service evaluation scores of each service provider, the continuous service evaluation coefficient of each service provider is calculated using the following formula:

[0032]

[0033] Among them, LP i Let P be the continuous service evaluation coefficient for service provider i, c be the preset coefficient, and P be the value of P. i This is the service provider's continuous service evaluation score.

[0034] As a further embodiment of this document, the calculation process for the continuous no-response value of each service provider includes:

[0035] For each service provider, after receiving each response result, it is determined whether the service provider's response result is no response. If there is no response, the third adjustment value is added to the previous consecutive no response value of the service provider to obtain the current consecutive no response value. If there is a response, the third adjustment value is subtracted from the previous consecutive no response value of the service provider to obtain the current consecutive no response value, until it is reduced to 0 and no longer changes.

[0036] Based on the consecutive no-response values ​​of each service provider, the no-response coefficient for each service provider is calculated using the following formula:

[0037] NP i =1-NT i ×X,NT i ∈[0,N-1];

[0038] NP i =0,NT i =N;

[0039] Where X is Retain at least one decimal place, NP i is the non-response coefficient for the service provider, and N is the maximum number of times there is no response.

[0040] As a further embodiment of this paper, the service optimization scheduling method further includes: determining whether the service provider has a non-response coefficient of less than 1 for a continuous period of time; if the determination result is yes, then issuing an alarm reminder.

[0041] As a further embodiment of this paper, calculating the new weight of the service provider based on the service provider's current weight, cumulative single service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient includes calculating the new weight of the service provider using the following formula:

[0042] Q i =BQ i ×MP i ×NP i ×LP i ;

[0043] Among them, Q i For the new weight of service provider i, BQ i For the initial weight of service provider i, MP i To accumulate the evaluation coefficient for a single service, NP i LP is the continuous service evaluation coefficient. i The coefficient is the non-response coefficient.

[0044] In a further embodiment of this paper, the weight change information includes: weight increment value and weight change trend;

[0045] Based on the weight change information of the service providers running the optimized service model, determine the effectiveness of the optimized service model and adjust the service models running in the service providers, including:

[0046] If the weight increment of the service provider running the optimized service model is greater than the first preset increment and / or the weight change trend is continuously rising, then the optimized service model is determined to be effective, and the original service model running by the service provider is replaced with the optimized service model.

[0047] If the weight increment of the service provider running the optimization service model is less than the second preset increment value, or if the weight change trend is a continuous decline, the optimization service model is determined to be invalid, and a prompt message to adjust the optimization service model is issued.

[0048] The second aspect of this paper provides a service optimization scheduling apparatus, comprising:

[0049] The allocation module is used to allocate user service requests to the corresponding service providers according to their current weights, so that the service providers can respond to the user service requests. Among them, service providers with current weights less than predetermined weights run the original service model, while the remaining service providers run the optimized service model.

[0050] The weight update module is used to calculate the new weight of each service provider based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no response value of each service provider, and to update the current weight of each service provider using the new weight of each service provider.

[0051] The service adjustment module is used to adjust the service models running in the service providers based on the weight changes of the service providers running the optimized service models.

[0052] A third aspect of this document provides a computer device including a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, performs instructions of the service optimization scheduling method described in any of the foregoing embodiments.

[0053] A fourth aspect of this document provides a computer storage medium having a computer program stored thereon, which, when executed by a processor of a computer device, executes instructions of the service optimization scheduling method described in any of the foregoing embodiments.

[0054] The service optimization scheduling method, apparatus, equipment, and storage medium presented in this paper enable simultaneous operation of the original service model on some service providers and the optimized service model on the remaining service providers, ensuring service continuity and improving user experience. By calculating the new weights of each service provider based on their cumulative single-service evaluation value, continuous service evaluation value, and continuous no-response value, the service quality and capabilities of each service model can be considered during user service request scheduling. This allows for accurate assessment of whether the optimized service model can stably and effectively provide services (a decrease in weight indicates a vulnerability in the optimized service model, while a weight greater than a preset value indicates effectiveness). By adjusting the service models running on the service providers based on the weight changes of those running the optimized service model, the effectiveness of the optimized service model can be accurately determined, allowing for timely optimization and improved user experience.

[0055] To make the above and other objects, features and advantages of this document more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 The first flowchart of the service optimization scheduling method in the embodiments of this paper is shown;

[0058] Figure 2 The second flowchart of the service optimization scheduling method in the embodiments of this paper is shown;

[0059] Figure 3 A flowchart illustrating the user service request allocation process in an embodiment of this paper is shown.

[0060] Figure 4 A flowchart illustrating the new weight calculation process in the embodiments described herein is shown;

[0061] Figure 5 A flowchart illustrating the calculation process of the cumulative single service evaluation value in the embodiments of this article is shown;

[0062] Figure 6 A flowchart illustrating the calculation process of the continuous service evaluation value in the embodiments of this article is shown;

[0063] Figure 7 A flowchart illustrating the calculation process for continuous no-response values ​​in the embodiments of this paper is shown;

[0064] Figure 8 A structural diagram of the service optimization scheduling device in the embodiments of this article is shown;

[0065] Figure 9 The diagram shows the structure of the service optimization scheduling system in the embodiments of this paper;

[0066] Figure 10 A structural diagram of the computer device described in this embodiment is shown.

[0067] Explanation of symbols in the attached drawings:

[0068] 810. Allocation Module;

[0069] 820. Weight Update Module;

[0070] 830. Service Adjustment Module;

[0071] 910. Dispatch device;

[0072] 920. Evaluation device;

[0073] 930. Service Provider;

[0074] 1002. Computer equipment;

[0075] 1004, Processor;

[0076] 1006. Memory;

[0077] 1008. Drive mechanism;

[0078] 1010. Input / Output Module;

[0079] 1012. Input devices;

[0080] 1014. Output devices;

[0081] 1016. Presentation device;

[0082] 1018. Graphical User Interface;

[0083] 1020. Network interface;

[0084] 1022. Communication link;

[0085] 1024. Communication bus. Detailed Implementation

[0086] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0087] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0088] This specification provides the operational steps of the methods described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or drawings can be executed sequentially or in parallel.

[0089] The service provider mentioned in this article can be a virtual service provider or a service processing program in a hardware device, such as a server or a service processing algorithm in an intelligent robot. This article does not limit the specific type of service provider.

[0090] The services described in this article can be any service that responds to a service request, such as image recognition, identity verification, information retrieval, video playback, etc. The service model is the algorithm executed by the service; the original service model is a service algorithm that has already been deployed in production, while the optimized service model can be a newly added service model, or a model optimized based on the original service model.

[0091] In one embodiment of this paper, a service optimization scheduling method is provided to address the problems of existing service scheduling methods that do not consider the service quality and capabilities of each service provider, resulting in low service processing efficiency, high error rates, poor user experience, and inability to guarantee service quality and capabilities. Furthermore, after service optimization and updates, it is impossible to accurately determine whether the optimized service is effective, which negatively impacts the user's service experience. Specifically, such as... Figure 1 As shown, the service optimization scheduling method includes:

[0092] Step 110: Based on the current weight of each service provider, the user service request is allocated to the corresponding service provider so that the service provider can respond to the user service request. Among them, the service provider with the current weight less than the predetermined weight runs the original service model, and the other service providers run the optimized service model.

[0093] Step 120: Calculate the new weight of each service provider based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, and update the current weight of each service provider using the new weight of each service provider.

[0094] Step 130: Adjust the service model running in the service provider based on the weight change information of the service provider running the optimized service model.

[0095] This embodiment achieves simultaneous operation of the original service model on some service providers and the optimized service model on the remaining service providers, ensuring service continuity and improving user experience. By calculating the new weights of each service provider based on their cumulative single-service evaluation value, continuous service evaluation value, and continuous no-response value, the service quality and capabilities of each service model can be considered during user service request scheduling. This accurately assesses whether the optimized service model can stably and effectively provide services (a smaller weight indicates a vulnerability in the optimized service model, while a weight greater than a preset value indicates effectiveness). By adjusting the service models running on the service providers based on the weight changes of those running the optimized service model, service model optimization can be completed in a timely manner, further enhancing user experience.

[0096] This embodiment corresponds to the case of non-initial scheduling. For the initial scheduling, there is no service evaluation of the service provider or the results of the most recent N service provider responses. The initial weights of each service provider can be used for scheduling, and the initial weights of each service provider are values ​​between [0,1]. In specific implementation, the initial weights of each service provider can be set to be the same, or they can be set according to the current load. The higher the load, the lower the initial weight, and the lower the load, the higher the initial weight. After scheduling for a period of time according to the existing scheduling method, the service optimization scheduling method described in this article is then used to schedule user service requests.

[0097] When implementing step 110, the predetermined weights can be set according to actual needs, and this article does not impose any restrictions on this.

[0098] Users can submit service requests through various methods such as the service interface and voice. This document does not limit the method of initiating user service requests. In practice, user service requests can be allocated to the appropriate service providers based on their current weights and using a pre-defined scheduling strategy. The weights of each service provider are values ​​between 0 and 1; the higher the weight value, the stronger the service provider's quality and responsiveness.

[0099] In step 120, new weights can be calculated according to a preset plan. This preset plan could be a predetermined time interval (every five minutes, ten minutes, etc.), after each service provider response, or after a predetermined number of service provider responses. In practice, the preset plan can be set according to requirements; this document does not impose specific limitations on it. In fact, the faster the weights are updated, the more promptly the current service status is reflected, and the higher the quality of service scheduling.

[0100] The cumulative single service evaluation value and the continuous service evaluation value of each service provider are determined based on the results of multiple service evaluations. The continuous non-response value of each service provider is determined based on the results of multiple responses. Service evaluation results include, but are not limited to, satisfactory, neutral, and unsatisfactory. The channels for obtaining service evaluation results differ for different services. These results can be determined by users or third parties based on the service feedback. For example, in a shopping service scenario, the buyer can provide a service evaluation result based on the conversation service provided by customer service. In another example, in an identity recognition scenario, an identity recognition algorithm identifies the user. After the user completes the identification, they can directly provide a service evaluation result, or developers can provide a service evaluation result based on system records. Yet another example is a video playback scenario where a cloud computing platform provides playback services. If a server in the cloud platform malfunctions, causing problems such as slow video loading, the recorded result can be used as the service evaluation result.

[0101] The response result includes no response and a response. The response result can be determined based on the service return result. If the user receives the service return result within the scheduled time period, there is a response; otherwise, there is no response.

[0102] Updating the current weight of a service provider using its new weights means setting the new weight of each service provider to its current weight.

[0103] In step 130, the service provider's weight change information includes the weight increment value and the weight change trend. The weight increment value is, for example, the amount of weight change between two consecutive iterations, and the weight change trend is the pattern of weight variation. Specifically, step 130 includes:

[0104] (1) If the weight increment of the service provider running the optimized service model is greater than the first preset increment (e.g., 0.1) and / or the weight change trend is continuously increasing, then the optimized service model is determined to be effective and can provide normal service. The original service model run by the service provider is then replaced with the optimized service model. In specific implementation, the original service model run by the service provider can be gradually replaced with the optimized service model. For example, N (e.g., 2) more service providers can be added to run the optimized service model each time. Alternatively, from multiple optimized service models, the optimized service model corresponding to the service provider with the largest weight increment or the most obvious change trend can be selected first, and then the original service model run by the service provider can be replaced with the selected optimized service model. There are multiple ways to replace the original service model run by the service provider with the optimized service model, which are not limited here.

[0105] (2) If the weight increment of the service provider running the optimized service model is less than the second preset increment, or if the weight change trend is a continuous decline, the optimized service model is determined to be invalid, and a prompt message for adjusting the optimized service model is issued. Specifically, this prompt message can remind developers to adjust the optimized service model, or it can replace the optimized service model running by the service provider back to the original service model. The first preset increment value is greater than the second preset increment value.

[0106] In one embodiment of this article, such as Figure 2 As shown, the service optimization scheduling method, in addition to steps 110 to 130 mentioned above, also includes:

[0107] Step 140: Determine whether the service provider is abnormal based on its current weight. If the service provider is abnormal, issue an alarm.

[0108] During implementation, step 140 can be executed after step 130 or before step 110. Alarm notifications can be sent via email, SMS, broadcast, etc., and the notification content includes, but is not limited to, the abnormal service provider, the service provider's evaluation results, and response results.

[0109] Step 140 specifically includes: determining whether the service provider meets the preset conditions based on the current weight of the service provider; if it does, then determining that the service provider that meets the conditions is abnormal. The preset conditions include, but are not limited to, the weight value being less than a predetermined threshold or the weight decreasing M times consecutively.

[0110] This embodiment can detect abnormal situations of the service provider in real time, which facilitates the rapid elimination of abnormalities.

[0111] In one embodiment of this paper, in order to improve allocation efficiency and the accuracy of user service request response, such as Figure 3 As shown, step 110 above allocates user service requests to the corresponding service providers based on their current weights, including:

[0112] Step 310: Based on the current weight of each service provider, filter the service providers, selecting those whose current weight is greater than a predetermined threshold or whose weight has not decreased for M consecutive times. Here, M is a positive integer and can be set according to requirements; this document does not impose a specific limit on it. The predetermined threshold is, for example, 0.8, which can be set according to needs. A higher weight indicates stronger service quality and service capabilities from the service provider.

[0113] Step 320: Distribute user service requests to the corresponding service providers in descending order of their current weights; or

[0114] Step 330: Calculate the weight ratio of each service provider based on the current weight of the selected service providers, and randomly assign user service requests to the corresponding service providers according to the weight ratio of each service provider.

[0115] This embodiment can filter out service providers with poor service quality and service capabilities through step 310, and improve the response efficiency of service requests by allocating service requests according to the weight of the filtered service providers.

[0116] In some implementations, during step 320, the same service provider can simultaneously allocate multiple user service requests. When the number of pending user service requests reaches the upper limit, no more service requests will be allocated to that service provider. Instead, user service requests will be allocated to the next service provider according to their current weight order. The upper limit for each service provider is determined based on its service capabilities. For example, if the service provider is a telephone customer service provider, the upper limit is 1; if it is a text-based customer service provider, the upper limit is generally 5 to 10; if it is an ID card recognition service provider, the upper limit can be 50 to 100, and so on.

[0117] In other implementations, when step 320 is performed, user service requests can be cyclically allocated according to the current weight order of each service provider, with one user service request allocated each time. When the number of user service requests to be processed by a service provider reaches the upper limit, no more requests will be allocated to that service provider.

[0118] In step 330, the service provider's weight ratio is calculated using the following formula:

[0119]

[0120] Among them, A i Q represents the weighting of service provider i. i Q represents the current weight of service provider i. j Let j be the current weight of service provider j, and n be the number of service providers selected.

[0121] The service provider weight ratio indicates the probability that the service provider will be invoked; the higher the ratio, the greater the probability of being invoked.

[0122] In practice, in addition to allocating according to the logic of steps 320 and 330, other scheduling logic can also be used to complete the allocation of user service requests.

[0123] In one embodiment of this article, such as Figure 4 As shown, step 120 above calculates the new weights for each service provider based on their cumulative single service evaluation value, continuous service evaluation value, and continuous no-response value.

[0124] Step 410: Calculate the cumulative single service evaluation coefficient for each service provider based on their cumulative single service evaluation value.

[0125] Step 420: Calculate the continuous service evaluation coefficient for each service provider based on their continuous service evaluation value.

[0126] Step 430: Calculate the non-response coefficient of each service provider based on the continuous non-response values ​​of each service provider.

[0127] Step 440: Calculate the new weights for each service provider based on their cumulative single service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient.

[0128] In detail, the cumulative single-service evaluation coefficient of each service provider can reflect the cumulative situation of single-service evaluation.

[0129] The continuity of service evaluation coefficient for each service provider reflects the continuity of their response. A higher continuity of service evaluation coefficient indicates better service quality from the service provider.

[0130] The no-response coefficient for each service provider reflects the stability of its service response. The no-response coefficient is determined based on the principle that the more times there are no responses, the smaller the coefficient becomes, and it reaches zero when it reaches a certain value. The initial value of the no-response coefficient is 1. The larger the no-response coefficient of a service provider, the higher its service capability and the fewer the number of no-response instances.

[0131] This embodiment calculates the service provider's cumulative single-service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient. Based on these coefficients, a new weight is calculated for the service provider, ensuring that the calculated weight comprehensively reflects the true state of service quality and capabilities. Allocating user service requests according to this new weight improves the response quality and efficiency of service requests, thereby enhancing the user experience.

[0132] In one embodiment of this article, such as Figure 5 As shown, the process for determining the cumulative single-service evaluation value for each service provider includes:

[0133] Step 510: Determine the service satisfaction level of each service provider for each service response based on the service evaluation results of each service provider's response.

[0134] Step 520: Based on the satisfaction level of each service provider for each service, calculate the cumulative single service evaluation value of each service provider. The cumulative single service evaluation value of each service provider includes: the number of times the service satisfaction level of each service provider is greater than the first predetermined value and the number of times the service satisfaction level of each service provider is less than the second predetermined value, wherein the first predetermined value is greater than the second predetermined value.

[0135] Furthermore, in step 410 above, based on the cumulative single-service evaluation value of each service provider, the cumulative single-service evaluation coefficient of each service provider is calculated using the following formula:

[0136] MP i＝ (1-a) z ×(1+a) x ;

[0137] Among them, MP i Let be the cumulative single service evaluation coefficient of service provider i, where a is the first adjustment value, x is the number of times service provider i's service satisfaction level is greater than the first predetermined value, and z is the number of times service provider i's service satisfaction level is less than the second predetermined value.

[0138] In detail, (1-a) and (1+a) above can be regarded as single-service evaluation coefficients. The cumulative single-service evaluation system of each service provider is the product of the single-service evaluation coefficients. The process of determining the single-service evaluation coefficients includes:

[0139] Based on the service evaluation results of each service response, the level of satisfaction with each service is determined. Service evaluation results include, but are not limited to, fuzzy classifications such as "satisfied," "neutral," and "unsatisfied," and can also be expressed as evaluation scores, with higher scores indicating a higher level of satisfaction. Service satisfaction is represented numerically as data used in the evaluation results; higher scores correspond to a higher level of satisfaction.

[0140] If the satisfaction level is greater than the first predetermined value, the service evaluation coefficient is obtained by adding a first adjustment value to the benchmark coefficient. The benchmark coefficient is 1, and the first adjustment value is, for example, 0.01. In practice, this can be determined based on the actual situation. Preferably, the first adjustment value ranges from 0.001 to 0.01.

[0141] If the level of satisfaction falls between the first and second predetermined values, then the service evaluation coefficient for that service is the benchmark coefficient. The first predetermined value is greater than the second predetermined value. The specific values ​​of the first and second predetermined values ​​can be determined according to the actual situation, and this article does not impose any restrictions on them.

[0142] If the satisfaction level is less than the second predetermined value, the service weight coefficient is obtained by reducing the first adjustment value based on the benchmark coefficient.

[0143] In some implementations, the initial value of the continuous service evaluation value for each service provider is 0, such as... Figure 6 As shown, the process for determining the continuous service evaluation value for each service provider includes:

[0144] Step 610: For each service provider, after obtaining the service evaluation result for each time, determine the service satisfaction level of the service provider for that time based on the service evaluation result of that service provider.

[0145] If the satisfaction level is greater than the first predetermined value, proceed to step 620;

[0146] If the level of satisfaction is between the first predetermined value and the second predetermined value, then proceed to step 630;

[0147] If the satisfaction level is less than the second predetermined value, proceed to step 640.

[0148] Step 620: Based on the service provider's previous continuous service evaluation value, add a second adjustment value to obtain the service provider's current continuous service evaluation value. In specific implementation, the second adjustment value can be determined according to the actual situation. Preferably, the second adjustment value is 1.

[0149] Step 630: Set the previous continuous service evaluation value of the service provider to the current continuous service evaluation value of the service provider.

[0150] Step 640: Set the service provider's continuous service evaluation value to the initial value.

[0151] Furthermore, in step 420 above, based on the continuous service evaluation value of each service provider, the continuous service evaluation coefficient of each service provider is calculated using the following formula:

[0152]

[0153] Among them, LP i Let P be the continuous service evaluation coefficient for service provider i, c be the preset coefficient, and P be the value of P. i The continuous service evaluation value for service provider i.

[0154] In one embodiment of this article, such as Figure 7 As shown, the calculation process for the continuous no-response value of each service provider includes:

[0155] Step 710: For each service provider, after obtaining each response result, determine whether the response result of that service provider is no response. If there is no response, proceed to step 720; if there is a response, proceed to step 730.

[0156] Step 720: Add a third adjustment value to the previous consecutive no-response value of the service provider to obtain the current consecutive no-response value.

[0157] Step 730: Determine if the previous consecutive no-response value is 0. If the determination result is yes, set the current consecutive no-response value to 0. If the determination result is no, reduce the third adjustment value based on the previous consecutive no-response value of the service provider to obtain the current consecutive no-response value.

[0158] Furthermore, in step 430, based on the consecutive non-response values ​​of each service provider, the non-response coefficient of each service provider is calculated using the following formula:

[0159] NP i =1-NT i ×X,NT i ∈[0,N-1];

[0160] NP i =0,NT i =N;

[0161] Where X is Retain at least one decimal place, NP i This represents the non-response coefficient of the service provider.

[0162] In a further embodiment, the service scheduling method further includes: determining whether the non-response coefficient of the service provider is less than 1 for a continuous period of time; if the determination result is yes, then issuing an alarm reminder.

[0163] Step 440 calculates the new weights for each service provider based on their cumulative single service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient, including using the following formula:

[0164] Q i =BQ i ×MP i ×NP i ×LP i ;

[0165] Among them, Q i For the new weight of service provider i, BQ i MP is the initial weight of service provider i. i To accumulate the weight coefficient for a single service, NP i LP is the continuous service evaluation coefficient. i The coefficient is the non-response coefficient.

[0166] In one embodiment of this paper, in order to improve statistical efficiency and avoid repeatedly analyzing the service evaluation results and response results of historical responses each time the weight is calculated, the above step 120 calculates the new weight of each service provider based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, including:

[0167] 1) Based on the service evaluation results and response results of each service provider generated between the current weight calculation time and the current time, update the cumulative single service evaluation value, continuous service evaluation value and continuous no response value of each service provider corresponding to the current weight. For the specific update process, please refer to the above process for determining the cumulative single service evaluation value, continuous service evaluation value and continuous no response value of each service provider.

[0168] 2) Calculate the new weights of each service provider based on their updated cumulative single service evaluation value, continuous service evaluation value, and continuous no-response value.

[0169] Based on the same inventive concept, this paper also provides a service optimization scheduling device, as described in the following embodiments. Since the principle of the service optimization scheduling device in solving the problem is similar to that of the service scheduling method, the implementation of the service optimization scheduling device can refer to the service optimization scheduling method, and repeated details will not be elaborated further. Specifically, as... Figure 8 As shown, the service optimization scheduling device includes:

[0170] The allocation module 810 is used to allocate user service requests to the corresponding service providers according to the current weight of each service provider, so that the service providers can respond to the user service requests. Among them, the service providers with a current weight less than the predetermined weight run the original service model, and the other service providers run the optimized service model.

[0171] The weight update module 820 is used to calculate the new weight of each service provider based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, and to update the current weight of each service provider using the new weight of each service provider.

[0172] The service adjustment module 830 is used to adjust the service model running in the service provider based on the weight change information of the service provider running the optimized service model.

[0173] The service optimization scheduling device provided in this embodiment can improve the response speed and accuracy of user service requests, accurately judge the effectiveness of the optimized service model, complete the optimization of the service model in a timely manner, and improve the user experience.

[0174] In one embodiment of this document, a service scheduling system is also provided, such as... Figure 9 As shown, the system includes: a scheduling device 910, an evaluation device 920, and multiple service providers 930. The scheduling device 910 is connected to the evaluation device 920 and the service providers 930, and is used to obtain service evaluation results from the evaluation device 920 and service response results from the service providers 930; based on the service evaluation results and service response results, it calculates the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value for each service provider (see [reference] for the specific calculation process). Figures 5-7The process involves: calculating new weights for each service provider based on their cumulative single service evaluation value, continuous service evaluation value, and continuous no-response value; updating the current weights of each service provider using these new weights; allocating user service requests to the corresponding service providers 930 based on their current weights; and adjusting the service models running in the service providers based on the weight changes of the service providers running the optimized service models. The evaluation device 920 evaluates the service response results of each service provider to obtain service evaluation results. Service providers 930 respond to user service requests allocated by the scheduling device; some service providers run the original service model, while the remaining service providers run the optimized service model.

[0175] Specifically, assuming the service evaluation results include three categories: satisfactory, average, and unsatisfactory, the scheduling device 910 re-determines the current weight of the service provider after each response to a user service request. The specific determination process includes:

[0176] 1) Obtain the service evaluation results of each service provider's response from the evaluation device 920. For each service evaluation result, if the service evaluation result is satisfactory, the evaluation coefficient is set to be 0.01 higher than the baseline coefficient. For general service evaluation, the evaluation coefficient is set to be 1. For unsatisfactory service evaluation, the evaluation coefficient is set to be 0.01 higher than the baseline coefficient.

[0177] The cumulative single-service evaluation coefficient for each service provider can be calculated using the following formula:

[0178] MP i＝ (1-0.01) z ×(1+0.01) x ;

[0179] Among them, MP i Let x be the cumulative single service evaluation coefficient of service provider i, x be the number of times service provider i was satisfied with the service, and z be the number of times service provider i was dissatisfied with the service.

[0180] 2) Set the value for continuous no response to NT. i ∈[0,4].

[0181] (1) When service provider i is requested for the nth time, it makes the following judgment based on the response result of the service request:

[0182] If the service provider does not respond when called, then NT i Increase by 1;

[0183] If the service provider responds when called, then NT i Reduce by 1.

[0184] (2) When service i is requested for the (n+1)th time, the coefficient is adjusted according to the response result of the nth service request, and the rule is as follows:

[0185] If NT i If ∈[0,3], then NP i =1-NT i ×0.33;

[0186] If NT i =4, then NP i =0.

[0187] 3) For the scheduled service provider i (i∈[1,m]), set a continuous service evaluation value P. i and continuous service evaluation coefficient LP i Continuous service evaluation value P i The initial value is 0, and the continuous service evaluation coefficient LP i The initial value is 1.

[0188] After each request, service provider i adjusts its service evaluation score according to the following rules:

[0189] If the service evaluation result is satisfactory, then P i Increase by 1;

[0190] If the service evaluation result is average, then P i constant;

[0191] If the service evaluation result is unsatisfactory, then P i Set to 0.

[0192] Based on the continuous service evaluation value, the continuous service evaluation coefficient can be obtained.

[0193] 4) Based on the values ​​calculated in 1) and 3), the new weight Q of each service provider is calculated using the following formula. i for:

[0194] Q i =BQ i ×MP i ×NP i ×LP i ;

[0195] Among them, Q i For the new weight of service provider i, BQ i For the initial weight of service provider i, MP i To accumulate the weight coefficient for a single service, NP i LP is the continuous service evaluation coefficient. i The coefficient is the non-response coefficient.

[0196] Furthermore, in addition to calculating the weights of each service provider and allocating user service requests according to those weights, the scheduling device 910 also performs alarm detection, specifically including:

[0197] 1) For the absence of response coefficient NP i Real-time monitoring is possible. If the non-response coefficient NP of service provider i... i If the value remains 0 or less than 1 for an extended period, it indicates a service provider malfunction, and an alert can be issued to alert relevant personnel to confirm the service's operational status.

[0198] 2) For real-time weight Q i Real-time monitoring is also possible, if Q i If the rate of decline continues (e.g., it declines N times consecutively, and the frequency of each decline is greater than the predetermined value), it indicates that service provider i is also experiencing an anomaly, and its service quality is deteriorating. It is necessary to issue an alarm and remind relevant personnel to confirm the cause of the problem.

[0199] In one embodiment of this paper, in order to ensure that abnormal service providers (e.g., those with no response coefficient NP) i (If the weight Qi is 0 and continues to decrease, the system actively participates in the service. The scheduling device 910 also sends a test request instruction to the abnormal service provider at predetermined time intervals. If the abnormal service provider has recovered, it will receive the evaluation result and response result. The calculated weight is non-zero, which enables the abnormal service provider to participate in the service in a timely manner after recovering from the abnormality, thereby improving the service response.

[0200] In one embodiment of this document, a computer device is also provided, such as... Figure 10 As shown, computer device 1002 may include one or more processors 1004, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Computer device 1002 may also include any memory 1006 for storing information of any kind, such as code, settings, data, etc. Non-limitingly, for example, memory 1006 may include any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Furthermore, any memory may provide volatile or non-volatile retention of information. Furthermore, any memory may represent a fixed or removable component of computer device 1002. In one case, when processor 1004 executes associated instructions stored in any memory or combination of memories, computer device 1002 may perform any operation of the associated instructions. Computer device 1002 also includes one or more drive mechanisms 1008 for interacting with any memory, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0201] Computer device 1002 may also include an input / output module 1010 (I / O) for receiving various inputs (via input device 1012) and providing various outputs (via output device 1014). A specific output mechanism may include a presentation device 1016 and an associated graphical user interface 1018 (GUI). In other embodiments, the input / output module 1010 (I / O), input device 1012, and output device 1014 may be omitted, and the device may function solely as a computer device within a network. Computer device 1002 may also include one or more network interfaces 1020 for exchanging data with other devices via one or more communication links 1022. One or more communication buses 1024 couple the components described above together.

[0202] The communication link 1022 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. The communication link 1022 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0203] Corresponding to Figures 1-7 In addition to the methods described above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described methods.

[0204] This embodiment also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the following: Figures 1 to 7 The method shown.

[0205] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0206] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0207] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0208] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0209] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0210] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0211] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0212] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this paper, 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0213] This document uses specific embodiments to illustrate the principles and implementation methods of this document. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this document. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this document. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A service optimization scheduling method, characterized in that, include: Based on the current weight of each service provider, user service requests are allocated to the corresponding service providers so that the service providers can respond to the user service requests. Among them, service providers with a current weight less than the predetermined weight run the original service model, while the other service providers run the optimized service model. Based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no-response value of each service provider, calculate the new weight of each service provider, and update the current weight of each service provider using the new weight of each service provider. Based on the weight change information of the service providers in the service optimization service model, adjust the service models running in the service providers. The weight change information includes: weight increment value and weight change trend; Based on the weight change information of the service providers in the optimized service model, adjust the service models running in the service providers, including: If the weight increment of the service provider running the optimized service model is greater than the first preset increment and / or the weight change trend is continuously rising, then the optimized service model is determined to be effective, and the original service model run by the service provider is replaced with the optimized service model. If the weight increment of the service provider running the optimization service model is less than the second preset increment value, or if the weight change trend is a continuous decline, the optimization service model is determined to be invalid, and a prompt message to adjust the optimization service model is issued.

2. The service optimization scheduling method as described in claim 1, characterized in that, Based on the current weight of each service provider, user service requests are allocated to the appropriate service provider, including: Based on the current weight of each service provider, the service providers are filtered to select those whose current weight is greater than a predetermined threshold or whose weight has not decreased for M consecutive times. User service requests are allocated to the appropriate service providers in descending order of their current weights; or Calculate the weight ratio of each service provider based on their current weight, and randomly assign user service requests to the corresponding service provider according to their weight ratio.

3. The service optimization scheduling method as described in claim 1, characterized in that, Based on each service provider's cumulative single service evaluation value, continuous service evaluation value, and continuous no-response value, a new weight for each service provider is calculated, including: Calculate the cumulative single service evaluation coefficient for each service provider based on their cumulative single service evaluation value. Calculate the continuous service evaluation coefficient for each service provider based on their continuous service evaluation scores. Calculate the non-response coefficient for each service provider based on the consecutive non-response values ​​of each service provider; The new weights for each service provider are calculated based on their cumulative single service evaluation coefficient, continuous service evaluation coefficient, and no-response coefficient.

4. The service optimization scheduling method as described in claim 3, characterized in that, The process for determining the cumulative single service evaluation value for each service provider includes: The satisfaction level of each service provider is determined based on the service evaluation results of each response. Based on the satisfaction level of each service provider for each service, the cumulative single service evaluation value of each service provider is calculated. The cumulative single service evaluation value of each service provider includes: the number of times the service satisfaction level of each service provider is greater than the first predetermined value and the number of times the service satisfaction level of each service provider is less than the second predetermined value. The first predetermined value is greater than the second predetermined value. Based on the cumulative single-service evaluation scores of each service provider, the cumulative single-service evaluation coefficient for each service provider is calculated using the following formula: ； in, MP i This represents the cumulative single-service evaluation coefficient for service provider i. a The first adjustment value, x The number of times that the service satisfaction level of service provider i is greater than the first predetermined value. z The number of times that the service satisfaction level of service provider i is less than the second predetermined value.

5. The service optimization scheduling method as described in claim 3, characterized in that, The process for determining the continuous service evaluation value of each service provider includes: For each service provider, after obtaining the service evaluation result for each time, the service satisfaction level of that service provider for that time is determined based on the service evaluation result for that service provider. If the satisfaction level is greater than the first predetermined value, the second adjustment value is added to the service provider's previous continuous service evaluation value to obtain the service provider's current continuous service evaluation value; If the satisfaction level is between the first predetermined value and the second predetermined value, then the service provider's previous continuous service evaluation value is set as the service provider's current continuous service evaluation value. If the satisfaction level is less than the second predetermined value, then the service provider's evaluation value for this consecutive service is set as the initial value. Based on the continuous service evaluation scores of each service provider, the continuous service evaluation coefficient of each service provider is calculated using the following formula: ； in, LP i Let i be the continuous service evaluation coefficient. c For preset coefficients, P i The continuous service evaluation value for service provider i.

6. The service optimization scheduling method as described in claim 3, characterized in that, The calculation process for the continuous no-response value of each service provider includes: For each service provider, after receiving each response result, it is determined whether the service provider's response result is no response. If there is no response, the third adjustment value is added to the previous consecutive no response value of the service provider to obtain the current consecutive no response value. If there is a response, the third adjustment value is subtracted from the previous consecutive no response value of the service provider to obtain the current consecutive no response value, until it is reduced to 0 and no longer changes. Based on the consecutive no-response values ​​of each service provider, the no-response coefficient for each service provider is calculated using the following formula: ； ； Where X is Retain at least one decimal place. NP i The non-response coefficient of the service provider. N This represents the maximum number of times there will be no response.

7. A service optimization scheduling device, characterized in that, include: The allocation module is used to allocate user service requests to the corresponding service providers according to their current weights, so that the service providers can respond to the user service requests. Among them, service providers with current weights less than predetermined weights run the original service model, while the remaining service providers run the optimized service model. The weight update module is used to calculate the new weight of each service provider based on the cumulative single service evaluation value, the continuous service evaluation value, and the continuous no response value of each service provider, and to update the current weight of each service provider using the new weight of each service provider. The service adjustment module is used to adjust the service models running in the service providers based on the weight changes of the service providers running the optimized service models. The weight change information includes: weight increment value and weight change trend; Based on the weight change information of the service providers in the optimized service model, adjust the service models running in the service providers, including: If the weight increment of the service provider running the optimized service model is greater than the first preset increment and / or the weight change trend is continuously rising, then the optimized service model is determined to be effective, and the original service model run by the service provider is replaced with the optimized service model. If the weight increment of the service provider running the optimization service model is less than the second preset increment value, or if the weight change trend is a continuous decline, the optimization service model is determined to be invalid, and a prompt message to adjust the optimization service model is issued.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor of the computer device, it executes the instructions of the method according to any one of claims 1-6.

Images