Intelligent quality inspection evaluation system for power dispatching call

Abstract

The invention relates to an intelligent quality inspection evaluation system for a power dispatching call. The intelligent quality inspection evaluation system comprises a power dispatching call system, a reminding alarm module, a call recording module, a call transfer module, a call analysis module, a sampling quality inspection module, a quality evaluation module, a service evaluation module, an efficiency improvement module, a cost reduction module and an overall planning module. According to the system, through cooperation of the modules, intelligent quality inspection evaluation is realized, the quality inspection accuracy and efficiency are improved, the call condition is comprehensively analyzed, the result is optimized, the efficiency is improved, the cost is reduced, and improvement and upgrading of power dispatching calls are facilitated.

Description

Technical Field

[0001] The present application relates to the technical field of electric power dispatching calls, and more specifically, to an intelligent quality inspection and evaluation system for electric power dispatching calls. Background Art

[0002] The electric power dispatch telephone is an independent telephone channel built by the electric power department according to the importance of dispatch and the busyness of enterprise management. It can realize system dispatch and effectively direct production. The electric power dispatch telephone requires a high degree of reliability. It must ensure smooth telephone communication not only under normal circumstances, but also under severe weather conditions and when accidents occur in the power system. Quality inspection and evaluation work is required in the operation of electric power dispatch calls. The existing quality inspection method is to manually listen to recordings or watch records to make professional judgments according to standards. However, the quality inspection results obtained by such quality inspection and evaluation methods are not objective, and it is difficult to obtain the required quality inspection and evaluation results. In addition, the efficiency of manual quality inspection is too low. With the development of intelligence, this method is gradually being eliminated.

[0003] Prior art, such as the Chinese patent with patent number "CN104168394A", discloses a call center sampling quality inspection method and system, which includes: filtering out voice media stream data related to traffic in the call center platform database and storing it in the traffic quality inspection data server; retrieving corresponding traffic data according to the sampling task set by the traffic quality inspection data server and storing it in the sampling data buffer; performing quality inspection on the data in the sampling data buffer, generating traffic detection results, and sending the traffic detection results to the corresponding operator terminal for pre-announcement; if the operator appeals against the quality inspection results, re-quality inspection of the unqualified data; sending all quality inspection results to the call center platform for display and preservation. The sampling quality inspection method of the present invention can realize real-time monitoring of call content according to actual work, realize comprehensive grasp of business capabilities, improve the timeliness of service management and control, increase the objectivity, fairness and effectiveness of quality inspection results, and improve the service quality of the call center.

[0004] The problem with the above-mentioned prior art is that the sampling tasks and quality inspection standards of this method are relatively fixed. When processing a large amount of call data, it may take a lot of manpower and time to screen and compare data, and the operator complaint process may extend the overall evaluation time. In addition, this aspect focuses on the service evaluation of service personnel, and does not include the call quality (poor call quality due to network-related factors) in the scope of evaluation. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes an intelligent quality inspection and evaluation system for power dispatching calls.

[0006] The technical solution of the present invention is as follows:

[0007] The present invention proposes an intelligent quality inspection and evaluation system for power dispatching calls, including a power dispatching call system, a reminder alarm module, a call recording module, a call transcription module, a call analysis module, a sampling quality inspection module, a quality evaluation module, a service evaluation module, an efficiency improvement module, a cost reduction module and a coordination module;

[0008] The output end of the electric power dispatch call system is connected to the input end of the reminder alarm module and the call recording module respectively;

[0009] The output end of the reminder alarm module is connected to the power dispatch call system and the input end of the quality evaluation module respectively;

[0010] The output end of the call recording module is connected to the input end of the call transcription module;

[0011] The output end of the call transcription module is connected to the input end of the call analysis module;

[0012] The output end of the call analysis module is connected to the input end of the sampling quality inspection module;

[0013] The output end of the sampling quality inspection module is connected to the input end of the quality evaluation module;

[0014] The output end of the quality evaluation module is connected to the input end of the service evaluation module;

[0015] The output ends of the service evaluation module are connected to the input ends of the efficiency improvement module and the cost reduction module;

[0016] The output end of the efficiency improvement module is connected to the input end of the overall planning module;

[0017] The output end of the cost reduction module is connected to the input end of the overall planning module.

[0018] As a preferred implementation, the reminder alarm module is used to issue a reminder alarm for call quality problems generated during a call, and includes a call detection unit and a reminder alarm unit; the call detection unit is used to detect call fluency; the reminder alarm unit is used to detect call failures and issue a reminder alarm.

[0019] As a preferred embodiment, the call recording module is used to store call recordings, and includes a recording start unit, a call recording unit and a call retention unit; the recording start unit is used to detect and confirm the start of a call, and issue instructions to the call recording unit to record; the call recording unit is used to record the call; and the call retention unit is used to store the call recording.

[0020] As a preferred embodiment, the call transcription module is used to receive call recordings, remove noise from them, and then convert the call recordings into text, and includes a recording receiving unit, a noise removal unit, and a text conversion unit; the recording receiving unit is used to receive stored call recordings; the noise removal unit is used to perform noise removal processing on the received call recordings; and the text conversion unit is used to convert the noise-removed call recordings into text.

[0021] As a preferred embodiment, the call analysis module recognizes and processes the speech rate, emotions and keywords in the processed call recording through a multimodal model, and includes a speech rate recognition unit, an emotion recognition unit and a keyword recognition unit; the speech rate recognition unit recognizes and analyzes the speech rate in the call recording; the emotion recognition unit is used to recognize and analyze the emotions in the call recording; the keyword recognition unit is used to recognize and analyze the keywords in the call recording.

[0022] As a preferred embodiment, the sampling quality inspection module is used to cut the processed call recording into multiple segments and then perform sampling quality inspection on the segments, including a preprocessing unit, a segmentation unit and a segment quality inspection unit; the preprocessing unit is used to preprocess the stored call recording; the segmentation unit is used to extract and segment the preprocessed call recording; the segment quality inspection unit is used to perform sampling quality inspection on the segmented call recording segments.

[0023] As a preferred implementation, the quality evaluation module is used to analyze and score the network delay, network stability and voice clarity of the call, and includes a clarity evaluation unit, a stability evaluation unit and a delay evaluation unit; the clarity evaluation unit is used to evaluate whether the call recording sound is clear and whether there is noise and echo; the stability evaluation unit is used to evaluate whether the call connection is stable; the delay evaluation unit is used to evaluate the fluency of the call and whether there is delay and freeze.

[0024] As a preferred implementation, the service evaluation module is used for the user to score the call and describe the call defects, including a service scoring unit and a defect supplement unit; the service scoring unit is used to score the quality of the call; the defect supplement unit is used to supplement the description of the call defects.

[0025] As a preferred implementation, the efficiency improvement module is used to receive call quality evaluation results, summarize the call quality evaluation results by generating reports and visualization tools, and adjust the call service strategy, including a report generation unit, a visual tool unit and an efficiency optimization unit; the report generation unit is used to generate a report based on the call quality evaluation results; the visual tool unit is used to use visual tools to understand the call quality evaluation results; the efficiency optimization unit is used to adjust the call service strategy according to the call quality evaluation results and optimize service efficiency.

[0026] As a preferred implementation, the coordination module uses a genetic algorithm to summarize and calculate the efficiency optimization and cost reduction plan information to obtain a final optimization plan, including a data summary unit and an optimization unit; the data summary unit is used to summarize the efficiency optimization and cost reduction plans; the optimization unit calculates and outputs the final optimization plan through a genetic algorithm.

[0027] The present invention has the following beneficial effects: by adding a call transcription module, the present invention can receive the recording, remove the noise therein, and then convert the recording into text, so as to facilitate the understanding of the call situation for subsequent quality inspection and evaluation work; by adding a call analysis module, the speech speed, emotions and keywords in the processed recording are identified and processed, so that the accuracy of the quality inspection results can be ensured when the recording is quality inspected and evaluated, and the final result can be prevented from being affected by external factors; by adding a sampling quality inspection module for cutting the processed recording into multiple segments, and then performing sampling quality inspection on these segments, it is possible to perform quality inspection work without manual work and perform multiple sampling Quality inspection work can ensure the accuracy of quality inspection and evaluation, and can improve efficiency; by adding a quality evaluation module to analyze and score the network latency, network stability and voice clarity of calls, it can intelligently analyze the call situation and then analyze the specific causes of defects; by adding a service evaluation module for users to score the call and supplement the call defects, it can cooperate with the caller's evaluation to understand the defects, and thus make the quality inspection and evaluation results more accurate. By adding the above modules, intelligent quality inspection and evaluation can be achieved, which not only makes the functionality of the quality inspection and evaluation system more comprehensive, but also handles defects in a timely manner to improve and upgrade power dispatch calls. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 This is the process architecture diagram of the intelligent quality inspection and evaluation system for power dispatch calls; DETAILED DESCRIPTION

[0030] 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.

[0031] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0032] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0033] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0034] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0035] Embodiment 1:

[0036] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be combined with the specific embodiments of the present application and refer to the attached Figure 1 , clearly and completely describe the technical solution of the present invention.

[0037] In order to solve the problems of the prior art, the present invention provides an intelligent quality inspection and evaluation system for power dispatching calls, including: a power dispatching call system, a reminder alarm module, a call recording module, a call transcription module, a call analysis module, a sampling quality inspection module, a quality evaluation module, a service evaluation module, an efficiency improvement module, a cost reduction module and a coordination module;

[0038] The output end of the electric power dispatch call system is connected to the input end of the reminder alarm module and the call recording module respectively;

[0039] The output end of the reminder alarm module is connected to the power dispatch call system and the input end of the quality evaluation module respectively;

[0040] The reminder alarm module is used to issue a reminder alarm for call quality problems generated during a call, and includes a call detection unit and a reminder alarm unit; the call detection unit is used to detect call fluency; the reminder alarm unit is used to detect call failures and issue a reminder alarm.

[0041] The output end of the call recording module is connected to the input end of the call transcription module;

[0042] The call recording module is used to store call recordings, and includes a recording start unit, a call recording unit and a call retention unit; the recording start unit is used to detect and confirm the start of a call, and issue instructions to the call recording unit to record; the call recording unit is used to record the call; and the call retention unit is used to store the call recording.

[0043] The output end of the call transcription module is connected to the input end of the call analysis module;

[0044] The call transcription module is used to receive call recordings, remove noise from them, and then convert the call recordings into text, and includes a recording receiving unit, a noise removal unit, and a text conversion unit; the recording receiving unit is used to receive stored call recordings; the noise removal unit is used to perform noise removal processing on the received call recordings; and the text conversion unit is used to convert the noise-removed call recordings into text.

[0045] The output end of the call analysis module is connected to the input end of the sampling quality inspection module;

[0046] The call analysis module recognizes and processes the speech rate, emotions and keywords in the processed call recordings through a multimodal model, and includes a speech rate recognition unit, an emotion recognition unit and a keyword recognition unit; the speech rate recognition unit recognizes and analyzes the speech rate in the call recordings; the emotion recognition unit is used to recognize and analyze the emotions in the call recordings; the keyword recognition unit is used to recognize and analyze the keywords in the call recordings.

[0047] The output end of the sampling quality inspection module is connected to the input end of the quality evaluation module;

[0048] The sampling quality inspection module is used to cut the processed call recording into multiple segments and then perform sampling quality inspection on the segments, including a preprocessing unit, a segmentation unit and a segment quality inspection unit; the preprocessing unit is used to preprocess the stored call recording; the segmentation unit is used to extract and segment the preprocessed call recording; the segment quality inspection unit is used to perform sampling quality inspection on the segmented call recording segments.

[0049] The output end of the quality evaluation module is connected to the input end of the service evaluation module;

[0050] The quality evaluation module is used to analyze and score the network delay, network stability and voice clarity of the call, and includes a clarity evaluation unit, a stability evaluation unit and a delay evaluation unit; the clarity evaluation unit is used to evaluate whether the call recording sound is clear and whether there is noise and echo; the stability evaluation unit is used to evaluate whether the call connection is stable; the delay evaluation unit is used to evaluate the fluency of the call and whether there is delay and freeze.

[0051] The output ends of the service evaluation module are connected to the input ends of the efficiency improvement module and the cost reduction module;

[0052] The service evaluation module is used for the user to score the call and describe the call defects, and includes a service scoring unit and a defect supplement unit; the service scoring unit is used to score the quality of the call; the defect supplement unit is used to supplement the description of the call defects.

[0053] The output end of the efficiency improvement module is connected to the input end of the overall planning module;

[0054] The efficiency improvement module is used to receive call quality evaluation results, summarize the call quality evaluation results by generating reports and visualization tools, and adjust the call service strategy, including a report generation unit, a visual tool unit and an efficiency optimization unit; the report generation unit is used to generate a report based on the call quality evaluation results; the visual tool unit is used to use visual tools to understand the call quality evaluation results; the efficiency optimization unit is used to adjust the call service strategy according to the call quality evaluation results and optimize service efficiency.

[0055] The output end of the cost reduction module is connected to the input end of the overall planning module.

[0056] The cost reduction module includes an automatic quality inspection unit, a cost analysis unit and a solution giving unit. The automatic quality inspection unit is used to adopt automated quality inspection processing; the cost analysis unit is used to analyze the cost after automated quality inspection processing; and the solution giving unit is used to reduce costs and give cost reduction solutions.

[0057] The input end of the coordination module is connected to the output ends of the cost reduction module and the efficiency improvement module;

[0058] The coordination module uses a genetic algorithm to summarize and calculate the efficiency optimization and cost reduction plan information to obtain a final optimization plan, including a data summary unit and an optimization unit; the data summary unit is used to summarize the efficiency optimization and cost reduction plans; the optimization unit calculates and outputs the final optimization plan through a genetic algorithm.

[0059] This embodiment also provides a method for using the intelligent quality inspection and evaluation system for power dispatch calls:

[0060] Specifically, when in use, when a call is in progress, the reminder alarm module will promptly issue a reminder alarm for problems arising during the call, and the internal call detection unit will detect the fluency of the call, and at the same time, the reminder alarm unit will promptly issue a reminder alarm when a call failure is detected, and the call recording module will store the recording during the call, and the internal call start unit will automatically start the recording function during the call, and then the call recording unit will record the call, and finally the call retention unit will store the recording, and when the recording needs to be processed, the call transcription module will receive the recording, remove the noise, and then convert the recording into text, and the stored recording will be received by the internal recording receiving unit, and then the recording will be stored by the call storage unit. The noise removal unit performs noise removal processing on the received recording, and converts the noise-removed recording into text through the text conversion unit. After the recording is completed, the call process is analyzed by the call analysis module and the multimodal model to identify the speech rate, emotions and keywords in the processed recording, and the internal speech rate recognition unit recognizes and analyzes the speech rate in the call, and the emotion recognition unit recognizes and analyzes the emotions in the call, and the keyword recognition unit recognizes and analyzes the keywords in the call. After that, when the call recording is quality-checked, the processed recording is cut into multiple segments through the sampling quality inspection module, and then these segments are sampled for quality inspection, and the stored The recording is preprocessed, and then the preprocessed recording is extracted and cut into multiple segments through the sampling and clipping unit. Finally, the multiple cut segments are sampled and inspected through the segment quality inspection unit. When evaluating the call quality, the network delay, network stability and voice clarity of the call are analyzed and scored through the quality evaluation module. The internal clarity evaluation unit is used to evaluate whether the call sound is clear and whether there is noise and conference sound. Then, the internal stability evaluation unit is used to evaluate whether the call connection is stable. Finally, the delay evaluation unit is used to evaluate the fluency of the call and whether there is delay and jamming. When it is necessary to evaluate the call situation, the user will score the call through the service evaluation module and make evaluations on the call defects. Supplement, and score the quality of this call through the internal service scoring unit, and then make supplementary comments on the defects of this call through the defect supplement unit. When it is necessary to improve efficiency, the efficiency improvement module generates reports and uses visualization tools to understand the service situation and adjust the management and processing methods. The internal report generation unit will produce reports for calls and recordings, and then use visual tools through the visual tool unit to understand the call situation. Finally, the efficiency optimization unit adjusts and optimizes the call strategy. When it is necessary to reduce costs, the cost reduction module uses automated quality inspection to reduce labor costs, and the corresponding cost plan is obtained through algorithms, and the internal automatic quality inspection unit uses automated quality inspection processing.Then, the cost analysis unit analyzes the cost after automated quality inspection, and finally gives a cost reduction plan through the plan. When all the information and plans need to be summarized, the efficiency and cost plan information is summarized and processed through the overall planning module, and then the final optimization plan is calculated and output through the genetic algorithm.

[0061] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0062] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0063] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0064] In several embodiments provided in the present application, if any function is implemented in the form of 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 the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0065] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent quality inspection and evaluation system for power dispatching calls, characterized in that: include: Power dispatch call system, reminder alarm module, call recording module, call transcription module, call analysis module, sampling quality inspection module, quality evaluation module, service evaluation module, efficiency improvement module, cost reduction module and overall planning module; The output end of the electric power dispatch call system is connected to the input end of the reminder alarm module and the call recording module respectively; The output end of the reminder alarm module is connected to the power dispatch call system and the input end of the quality evaluation module respectively; The output end of the call recording module is connected to the input end of the call transcription module; The output end of the call transcription module is connected to the input end of the call analysis module; The output end of the call analysis module is connected to the input end of the sampling quality inspection module; The output end of the sampling quality inspection module is connected to the input end of the quality evaluation module; The output end of the quality evaluation module is connected to the input end of the service evaluation module; The output ends of the service evaluation module are connected to the input ends of the efficiency improvement module and the cost reduction module; The output end of the efficiency improvement module is connected to the input end of the overall planning module; The output end of the cost reduction module is connected to the input end of the overall planning module.

2. According to claim 1, the intelligent quality inspection and evaluation system for power dispatching calls is characterized by: The reminder alarm module is used to give a reminder alarm for call quality problems generated during a call, and includes a call detection unit and a reminder alarm unit; The call detection unit is used to detect call fluency; The reminder alarm unit is used to detect call failures and issue reminder alarms.

3. According to claim 1, the intelligent quality inspection and evaluation system for power dispatching calls is characterized by: The call recording module is used to store call recordings, including a recording start unit, a call recording unit and a call retention unit; the recording start unit is used to detect and confirm the start of a call, and issue an instruction to the call recording unit to record; The call recording unit is used to record the call; the call storage unit is used to store the call recording.

4. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The call transcription module is used to receive call recordings, remove noise from them, and then convert the call recordings into text, and includes a recording receiving unit, a noise removal unit, and a text conversion unit; the recording receiving unit is used to receive stored call recordings; the noise removal unit is used to perform noise removal processing on the received call recordings; and the text conversion unit is used to convert the noise-removed call recordings into text.

5. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The call analysis module recognizes and processes the speech rate, emotions and keywords in the processed call recordings through a multimodal model, and includes a speech rate recognition unit, an emotion recognition unit and a keyword recognition unit; the speech rate recognition unit recognizes and analyzes the speech rate in the call recordings; the emotion recognition unit is used to recognize and analyze the emotions in the call recordings; the keyword recognition unit is used to recognize and analyze the keywords in the call recordings.

6. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The sampling quality inspection module is used to cut the processed call recording into multiple segments and then perform sampling quality inspection on the segments, including a preprocessing unit, a segmentation unit and a segment quality inspection unit; the preprocessing unit is used to preprocess the stored call recording; the segmentation unit is used to extract and segment the preprocessed call recording; the segment quality inspection unit is used to perform sampling quality inspection on the segmented call recording segments.

7. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The quality evaluation module is used to analyze and score the network delay, network stability and voice clarity of the call, and includes a clarity evaluation unit, a stability evaluation unit and a delay evaluation unit; the clarity evaluation unit is used to evaluate whether the call recording sound is clear and whether there is noise and echo; the stability evaluation unit is used to evaluate whether the call connection is stable; the delay evaluation unit is used to evaluate the fluency of the call and whether there is delay and freeze.

8. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The service evaluation module is used for the user to score the call and describe the call defects, including a service scoring unit and a defect supplement unit; the service scoring unit is used to score the quality of the call; The defect supplement unit is used to supplement the description of the defects of the call.

9. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The efficiency improvement module is used to receive call quality evaluation results, summarize the call quality evaluation results by generating reports and visualization tools, and adjust the call service strategy, including a report generation unit, a visualization tool unit and an efficiency optimization unit; The report generation unit is used to generate a report based on the call quality evaluation result; The visual tool unit is used to use visual tools to understand the call quality evaluation results; the efficiency optimization unit is used to adjust the call service strategy according to the call quality evaluation results to optimize the service efficiency.

10. The intelligent quality inspection and evaluation system for power dispatching calls according to claim 1 is characterized by: The coordination module uses a genetic algorithm to aggregate and calculate the efficiency optimization and cost reduction scheme information to obtain a final optimization scheme, including a data aggregation unit and an optimization unit; The data aggregation unit is used to aggregate efficiency optimization and cost reduction solutions; the optimization unit calculates and outputs a final optimization solution through a genetic algorithm.

Images