CN117154940A - Electric power service quality gridding monitoring system and method - Google Patents
Electric power service quality gridding monitoring system and method Download PDFInfo
- Publication number
- CN117154940A CN117154940A CN202311137302.9A CN202311137302A CN117154940A CN 117154940 A CN117154940 A CN 117154940A CN 202311137302 A CN202311137302 A CN 202311137302A CN 117154940 A CN117154940 A CN 117154940A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- event
- module
- work order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 238000013058 risk prediction model Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 230000015654 memory Effects 0.000 claims description 5
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 238000004891 communication Methods 0.000 abstract description 6
- 238000002955 isolation Methods 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 12
- 230000006872 improvement Effects 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000008451 emotion Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 206010063659 Aversion Diseases 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 238000013019 agitation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00004—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the power network being locally controlled
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
- H02J13/00024—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission by means of mobile telephony
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
Abstract
The application discloses a grid monitoring system and method for electric power service quality, comprising a data acquisition module, a data preprocessing module, an event extraction and analysis module, an early warning module, an intelligent work order module and a service quality monitoring module. The data acquisition module is used for acquiring multi-channel data, the data preprocessing module is used for converting, converging and storing the multi-mode data acquired by the multiple channels, the event extraction and analysis module is used for extracting event information in the data to form tuple event information, the early warning module calculates early warning events according to the tuple event information, the intelligent work order module creates work orders according to the tuple event information, the priority ordering can be carried out on the work orders according to the early warning events calculated by the early warning module, and the service quality monitoring module monitors all links of work order processing. The application gathers and uniformly processes the communication data of clients in multiple channels, eliminates the information isolation of each channel, adopts a plurality of intelligent means to cooperatively process, and improves the service quality.
Description
Technical Field
The application relates to the field of power big data analysis, in particular to a power service quality gridding monitoring system and method.
Background
At present, channels for receiving user information by a power grid company comprise complaint telephones such as 12345 and 95598, telephone phones of a power supply station, mobile phones of personnel such as grid service personnel and the like, and WeChat groups established by grid managers, grid service personnel and the like, and the channels have advantages in receiving the user information, such as the WeChat groups have flexibility, are more for users, are convenient to send and stop, and the like, and hotline telephones and fixed telephones are friendly to the old and users of power utilization enterprises. However, the information isolation phenomenon exists in various channels, so that repeated dispatch is caused by difficult information summarization of various channels, complaints are caused by untimely discovery of hot spot complaints, and the problems of inadequate quality control of service and the like are solved.
Therefore, the quality of the service process is managed and controlled on the line of the collected complaint communication and processing process and the service effect of each channel, the information sharing of each channel is realized, the communication data of grid service personnel and clients are collected into the complaint risk application, the existing text analysis model and the complaint management and control flow are utilized, the online offline client complaint hotspot statistical analysis model, the online offline channel data collection and the grid service effect evaluation model are newly added, the management of the client complaint work order creation, distribution, tracking, supervision, problem tracing and service effect in the grid service process is realized, the client complaint of offline service channels is brought into the service quality management and control platform, the unified management, unified support, unified supervision and unified evaluation are realized, the online, the procedural and intelligent of high-quality service management and control work lines are realized, the working pressure of basic service personnel can be helped, and the process management quality of basic service and the customer service satisfaction degree are improved.
Disclosure of Invention
The application aims to solve the problems that information isolation exists in customer information collected by multiple channels, repeated dispatch is caused by difficult information summarization of each channel, complaints are caused by untimely finding of hot spot complaints, and quality of service management is not in place. In order to achieve the above object, the following technical scheme is provided:
the application provides a power service quality gridding monitoring system which is characterized by comprising a data acquisition module, a data preprocessing module, an event extraction and analysis module, an early warning module, an intelligent work order module and a service quality monitoring module;
the data acquisition module is used for acquiring interactive data of multiple channels of users and comprises a fixed telephone voice acquisition unit for acquiring a hot wire telephone, a working mobile phone voice acquisition unit for acquiring power grid service personnel and a micro-community data acquisition unit for acquiring chat records;
the data preprocessing module is used for converting, converging and storing multi-mode data acquired by multiple channels and comprises a voice recognition unit, a data gathering unit and a data storage unit;
the event extraction and analysis module is used for extracting event information in the data, wherein the event information comprises user information, time, event places and event keywords, grids of the events are calculated according to the extracted event information, power grid service personnel are matched, and tuple event information is formed;
the early warning module calculates early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and the complaint high risk events and the hot spot complaint events are sent to related personnel;
the intelligent work order module creates a work order according to the tuple event information, sends the work order to power grid service personnel after confirmation, and can prioritize the work order according to the early warning event calculated by the early warning module;
the service quality monitoring module monitors each link of the work order processing and comprises a work order overtime reminding unit and a feedback information collecting unit; the feedback information collecting unit is used for collecting evaluation information of the user after the work order is checked.
As a further improvement scheme of the application, the voice acquisition unit of the base telephone comprises a telephone recording box, the telephone recording box is connected with the base telephone through a telephone line interface, the telephone recording box uploads the call information to the upper computer through a USB interface, and the upper computer uploads the call information to the data acquisition module.
As a further improvement scheme of the application, the voice acquisition unit of the working mobile phone automatically starts the telephone recording function of the working mobile phone and uploads call recording data to the data acquisition module through a wireless network.
As a further improvement scheme of the application, the micro-letter group data acquisition unit realizes chat record information summarization and archiving by establishing micro-letter applet end micro-application, and the chat record information is uploaded to the data acquisition module through a wireless network according to a preset uploading period.
As a further improvement of the application, the voice recognition unit recognizes the collected voice data as text data and stores the voice data and corresponding text information in the data storage unit; the data aggregation unit aggregates the data according to dimension attributes, wherein the dimension attributes comprise a client dimension, a time dimension, a place dimension and a grid service personnel dimension.
As a further improvement of the present application, the event information in the extracted data specifically includes:
the text data is segmented by a word segmentation tool, a word2vec model is input for word segmentation and trained into word vectors, the trained word vectors are input into a bidirectional long-short term memory network to label entities to obtain entity labeling sequences, the entity labeling sequences are input into a hidden Markov model and combined with a label system to obtain label sequences, then event keyword information is extracted from the label sequences according to a TF-IDF model, and an event classification model obtains event types according to the word vectors.
As a further improvement of the application, the tuple event information comprises user information, event type, time information, event keyword information, belonging grid information and power grid service personnel information; the event classification model is a fusion model of a convolutional neural network model and a self-attention model.
As a further improvement scheme of the application, the convolutional neural network model extracts local features and global features of word vectors, the self-attention model extracts semantic features with high importance from the word vectors, and the local features and the global features and the semantic features are input into a softmax layer to finish event classification.
As a further improvement scheme of the application, the trained risk prediction model is utilized to carry out risk prediction on the tuple event information, and the risk prediction model is a random forest prediction model.
In a second aspect, the present application provides a method for monitoring the grid of the electric power service quality, which is used for the system for monitoring the grid of the electric power service quality, and is characterized in that,
step 101, collecting fixed telephone voice data of a hot wire telephone, working mobile phone voice data of a power grid service person and micro-group chat record data of the power grid service person;
102, identifying the collected voice data to obtain text data, extracting the text data from the chat record, and collecting the text data according to the dimension of a client, the dimension of time, the dimension of a place and the dimension of a grid service personnel; the voice data and the corresponding text data obtained by voice recognition are stored in an associated mode;
step 103, extracting event information from the text data, calculating grids to which the event belongs according to the extracted event information, and matching power grid service personnel to form tuple event information and tuple event information;
104, calculating early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and sending the complaint high risk events and the hot spot complaint events to related personnel;
step 105, creating a work order according to the tuple event information, transmitting the work order to power grid service personnel after confirmation, and sequencing the work order according to the early warning event calculated by the early warning module;
step 106, monitoring each link of the work order processing, including a work order overtime reminding unit and a feedback information collecting unit; the feedback information collecting unit is used for collecting evaluation information of the user after the work order is checked.
The beneficial effects of the application are as follows:
1. the voice data communicated with the clients and the micro-group chat record data are collected through the telephone of the base station and the working mobile phone of the power grid service personnel, and the multi-channel client communication data are collected and processed uniformly, so that information isolation of each channel is eliminated.
2. The intelligent system has the advantages that artificial intelligent models such as a voice recognition model, an event extraction model and an event classification model are integrated, the intelligent level of the system is improved, the models are tightly matched and cooperatively process multi-channel data, high risk of complaints and hot events are automatically recognized for early warning, and occurrence of public opinion events is avoided.
3. And the recognition of the risk event is carried out by combining text data and voice data, so that the recognition accuracy is improved.
4. The method and the system realize the management of customer appeal work order creation, distribution, tracking and service effect in the gridding service process, and realize unified management, unified support, unified supervision and unified evaluation, and realize the upscaling, flow and intellectualization of high-quality service management and control work lines.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate certain embodiments of the present application and therefore should not be considered as limiting the scope.
FIG. 1 is a block diagram of a power quality of service gridding monitoring system of the present application;
fig. 2 is a flow chart of a method for power quality of service gridding monitoring in accordance with the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
Example 1
The application provides an electric power service quality gridding monitoring system, the module structure of which is shown in figure 1, and the system comprises a data acquisition module, a data preprocessing module, an event extraction and analysis module, an early warning module, an intelligent work order module and a service quality monitoring module.
The data acquisition module is used for acquiring interactive data of multiple channels of users and comprises a base phone voice acquisition unit for acquiring hot wire telephones, a work mobile phone voice acquisition unit for acquiring power grid service personnel and a micro-community data acquisition unit for acquiring chat records.
The acquisition module is used for constructing three off-line channels of a WeChat group, a working mobile phone and a power supply station telephone served by power grid service personnel, so that multi-channel data aggregation and sharing are realized, unified processing is realized, and the problem that customer complaints are generated due to untimely processing is reduced, thereby achieving the aims of improving quality, enhancing efficiency and reducing load.
The telephone voice collection unit comprises a telephone recording box, the telephone recording box is connected with the telephone through a telephone line interface, the telephone recording box uploads call information to the upper computer through a USB interface, and the upper computer uploads the call information to the data collection module. There are 1-way and multi-way telephone record boxes on the market, which can be adopted according to the actual needs, and the application is not particularly limited.
The working mobile phone voice acquisition unit automatically starts a telephone recording function of the working mobile phone, and uploads call recording data of grid service personnel and clients to the data acquisition module through a wireless network. When the grid service personnel communicate with electricity consumption demands of electricity consumers through the working mobile phone and the disposal of problems, the working mobile phone voice acquisition unit acquires and stores call voice data of telephone communication, and the voice data is uploaded after the call is completed.
The micro-letter group data acquisition unit realizes chat record information summarization and archiving by establishing micro-letter applet end micro-application, and the chat record information is uploaded to the data acquisition module through a wireless network according to a preset uploading period.
The data preprocessing module is used for converting, converging and storing multi-mode data acquired by multiple channels and comprises a voice recognition unit, a data gathering unit and a data storage unit. Preferably, the data preprocessing module also provides a chat record filtering function, and eliminates information irrelevant to the service.
The voice recognition unit recognizes the collected voice data as text data, and stores the voice data and corresponding text information in the data storage unit. In the prior art, after voice is recognized as characters, the characters are processed, so that a large number of available features in the voice, such as voice attributes of voice speed, tone, jitter and the like, are lost, and the information plays an important role in recognizing emotion of a customer, so that voice data and corresponding character information are associated and stored in a data storage unit, and the voice data and the corresponding character information are convenient for subsequent use.
The data aggregation unit aggregates the data according to dimension attributes, wherein the dimension attributes comprise a client dimension, a time dimension, a place dimension and a grid service personnel dimension. And associating the data of each channel to realize data aggregation. For example, the same business user feeds back information through multiple channels, which needs to be correlated together. For another example, there may be multiple users feeding back through multiple channels in a short period of time for the same failure site, and it is also necessary to aggregate such information together.
The event extraction and analysis module is used for extracting event information in the data, wherein the event information comprises user information, time, event places and event keywords, grids of the events are calculated according to the extracted event information, and power grid service personnel are matched to form tuple event information. The tuple event information includes user information, event type, time information, event keyword information, belonging grid information, and power grid attendant information. The event classification model is a fusion model of a convolutional neural network model and a self-attention model.
The event information in the data is extracted, specifically: the text data is segmented by a segmentation tool, the segmentation tool can adopt jieba segmentation, a word2vec model is used for training word vectors, the trained word vectors are input into a bidirectional long-short term memory network to label entities to obtain entity labeling sequences, the entity labeling sequences are input into a hidden Markov model and combined with a label system to obtain a label sequence, and then event keyword information is extracted from the label sequence according to a TF-IDF (word frequency-inverse document frequency) model.
The word2vec model is a bidirectional long-short term memory network, the hidden Markov model is obtained by training according to historical worksheets, and the training method of the model is common knowledge in the field and is not repeated here.
The event classification model obtains the event type according to the word vector, preferably, the convolutional neural network model extracts the local feature and the global feature of the word vector, the self-attention model extracts the semantic feature with high importance degree from the word vector, and the local feature and the global feature as well as the semantic feature are input into a softmax layer to complete the event classification. The types of event types include, but are not limited to, business transaction, complaint, report, and feedback assessment information.
The early warning module calculates early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and the complaint high risk events and the hot spot complaint events are sent to related personnel.
Preferably, the trained risk prediction model is used for carrying out risk prediction on the tuple event information, and the risk prediction model is a random forest prediction model. And counting word frequencies of time keywords of a plurality of tuple event information in a certain time period, wherein the tuple event is a hot spot appeal event when the word frequency is larger than a preset threshold value.
Preferably, for hotline phone voice and working mobile phone voice, risk prediction is performed on a voice recognition text by utilizing a random forest to obtain a risk level. And then acquiring the associated voice data from the data storage unit, and identifying the service attitudes and emotions of operators and clients contained in the voice by using the emotion identification model to acquire emotion categories. Emotional categories include normal, excited, anger, aversion, happiness. And finally, determining the early warning event by combining the risk grade and the emotion type. The risk level is predicted as a medium-level event, but the events with emotion recognition categories of agitation, anger and aversion are marked as early warning events, so that the recall rate of the early warning events is improved, and the complaint risk is reduced. Because the voice data are time sequence data, the application adopts a long-term and short-term memory network as an emotion recognition model.
The intelligent work order module creates a work order according to the tuple event information, sends the work order to power grid service personnel after confirmation, and can order the priority of the work order according to the early warning event calculated by the early warning module. And automatically creating a work order according to the tuple event information, generating a high-level priority work order according to the early warning event marked by the early warning module, and automatically distributing the work order to corresponding power grid service personnel after confirmation of a supervisor.
The service quality monitoring module monitors each link of the work order processing and comprises a work order overtime reminding unit and a feedback information collecting unit. The service handling method recommending unit screens out handling methods of similar worksheets according to the historical worksheets, and the feedback information collecting unit is used for collecting evaluation information of users after the worksheets are checked in. After the power grid service personnel receives the distributed work orders, on-site investigation, treatment and feedback of treatment results are carried out according to the work order instructions, and customer evaluation is collected. The service quality monitoring module collects response time of each link of the work order, a time threshold and a total work order processing duration threshold are set for each link, and the work order exceeding the time threshold is reminded. Preferably, the service quality monitoring module further comprises a service handling method recommending unit, and the service handling method recommending unit screens out handling methods of similar worksheets according to the historical worksheets, and refers to power grid service personnel.
According to the application, the communication data of clients in multiple channels are collected and processed uniformly, the information isolation of each channel is eliminated, the data is processed by utilizing an intelligent model, the event extraction, early warning event identification, intelligent work orders and service quality monitoring are realized, the high-quality service management and control working line is realized, the process and the intellectualization are realized, the working pressure is relieved for basic service staff, and the process management quality and the customer service satisfaction degree of basic service are improved.
Example 2
The application provides a method for monitoring the electric power service quality in a gridding way, which is shown in figure 2 and is used for the electric power service quality gridding monitoring system, and is characterized in that,
step 101, collecting fixed telephone voice data of a hot wire telephone, working mobile phone voice data of a power grid service person and micro-group chat record data of the power grid service person;
102, identifying the collected voice data to obtain text data, extracting the text data from the chat record, and collecting the text data according to the dimension of a client, the dimension of time, the dimension of a place and the dimension of a grid service personnel; the voice data and the corresponding text data obtained by voice recognition are stored in an associated mode;
step 103, extracting event information from the text data, calculating grids to which the event belongs according to the extracted event information, and matching power grid service personnel to form tuple event information and tuple event information;
104, calculating early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and sending the complaint high risk events and the hot spot complaint events to related personnel;
step 105, creating a work order according to the tuple event information, transmitting the work order to power grid service personnel after confirmation, and sequencing the work order according to the early warning event calculated by the early warning module;
step 106, monitoring each link of the work order processing, including a work order overtime reminding unit, a business handling method recommending unit and a feedback information collecting unit; the service handling method recommending unit screens out handling methods of similar worksheets according to the historical worksheets, and the feedback information collecting unit is used for collecting evaluation information of users after the worksheets are checked in.
It should be noted that, according to implementation requirements, each component/step described in the embodiments of the present application may be split into more components/steps, or two or more components/steps or part of operations of the components/steps may be combined into new components/steps, so as to achieve the objects of the embodiments of the present application.
The above-described methods according to embodiments of the present application may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be stored in a local recording medium downloaded through a network, so that the apparatus described herein may be stored on a recording medium using a general purpose computer, a special purpose processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the apparatus described herein. Furthermore, when a general purpose computer accesses code for implementing the apparatus shown herein, execution of the code converts the general purpose computer into a special purpose computer for executing the apparatus shown herein.
Those of ordinary skill in the art will appreciate that the various illustrative elements and apparatus steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying means for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
The above embodiments are only for illustrating the embodiments of the present application, but not for limiting the embodiments of the present application, and various changes and modifications may be made by one skilled in the relevant art without departing from the spirit and scope of the embodiments of the present application, so that all equivalent technical solutions also fall within the scope of the embodiments of the present application, and the scope of the embodiments of the present application should be defined by the claims.
Claims (10)
1. The electric power service quality gridding monitoring system is characterized by comprising a data acquisition module, a data preprocessing module, an event extraction and analysis module, an early warning module, an intelligent work order module and a service quality monitoring module;
the data acquisition module is used for acquiring interactive data of multiple channels of users and comprises a fixed telephone voice acquisition unit for acquiring a hot wire telephone, a working mobile phone voice acquisition unit for acquiring power grid service personnel and a micro-community data acquisition unit for acquiring chat records;
the data preprocessing module is used for converting, converging and storing multi-mode data acquired by multiple channels and comprises a voice recognition unit, a data gathering unit and a data storage unit;
the event extraction and analysis module is used for extracting event information in the data, wherein the event information comprises user information, time, event places and event keywords, grids of the events are calculated according to the extracted event information, power grid service personnel are matched, and tuple event information is formed;
the early warning module calculates early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and the complaint high risk events and the hot spot complaint events are sent to related personnel;
the intelligent work order module creates a work order according to the tuple event information, sends the work order to power grid service personnel after confirmation, and can prioritize the work order according to the early warning event calculated by the early warning module;
the service quality monitoring module monitors each link of the work order processing and comprises a work order overtime reminding unit and a feedback information collecting unit; the feedback information collecting unit is used for collecting evaluation information of the user after the work order is checked.
2. An electric quality of service grid monitoring system as set forth in claim 1, wherein,
the telephone voice collection unit comprises a telephone recording box, the telephone recording box is connected with the telephone through a telephone line interface, the telephone recording box uploads call information to the upper computer through a USB interface, and the upper computer uploads the call information to the data collection module.
3. An electric quality of service grid monitoring system as set forth in claim 1, wherein,
the working mobile phone voice acquisition unit automatically starts a telephone recording function of the working mobile phone and uploads call recording data to the data acquisition module through a wireless network.
4. An electric quality of service grid monitoring system as set forth in claim 1, wherein,
the micro-letter group data acquisition unit realizes chat record information summarization and archiving by establishing micro-letter applet end micro-application, and the chat record information is uploaded to the data acquisition module through a wireless network according to a preset uploading period.
5. An electric quality of service grid monitoring system as set forth in claim 1, wherein,
the voice recognition unit recognizes the collected voice data as text data and stores the voice data and corresponding text information into the data storage unit; the data aggregation unit aggregates the data according to dimension attributes, wherein the dimension attributes comprise a client dimension, a time dimension, a place dimension and a grid service personnel dimension.
6. The system for grid monitoring of power quality of service according to claim 1, wherein the event information in the extracted data is specifically:
the text data is segmented by a word segmentation tool, a word2vec model is input for word segmentation and trained into word vectors, the trained word vectors are input into a bidirectional long-short term memory network to label entities to obtain entity labeling sequences, the entity labeling sequences are input into a hidden Markov model and combined with a label system to obtain label sequences, then event keyword information is extracted from the label sequences according to a TF-IDF model, and an event classification model obtains event types according to the word vectors.
7. The system for grid monitoring of quality of service of electricity of claim 6,
the tuple event information comprises user information, event type, time information, event keyword information, belonging grid information and power grid service personnel information; the event classification model is a fusion model of a convolutional neural network model and a self-attention model.
8. An electric quality of service grid monitoring system as set forth in claim 7, wherein,
the convolutional neural network model extracts local features and global features of word vectors, the self-attention model extracts semantic features with high importance from the word vectors, the local features and the global features and the semantic features are input into a softmax layer, and event classification is completed.
9. An electric quality of service grid monitoring system as set forth in claim 1, wherein,
and carrying out risk prediction on the tuple event information by using a trained risk prediction model, wherein the risk prediction model is a random forest prediction model.
10. An electric power service quality gridding monitoring method, which is used for the electric power service quality gridding monitoring system of claims 1-9, is characterized in that,
step 101, collecting fixed telephone voice data of a hot wire telephone, working mobile phone voice data of a power grid service person and micro-group chat record data of the power grid service person;
102, identifying the collected voice data to obtain text data, extracting the text data from the chat record, and collecting the text data according to the dimension of a client, the dimension of time, the dimension of a place and the dimension of a grid service personnel; the voice data and the corresponding text data obtained by voice recognition are stored in an associated mode;
step 103, extracting event information from the text data, calculating grids to which the event belongs according to the extracted event information, and matching power grid service personnel to form tuple event information and tuple event information;
104, calculating early warning events according to the tuple event information, wherein the early warning events comprise complaint risk events and hot spot complaint events, and sending the complaint high risk events and the hot spot complaint events to related personnel;
step 105, creating a work order according to the tuple event information, transmitting the work order to power grid service personnel after confirmation, and sequencing the work order according to the early warning event calculated by the early warning module;
step 106, monitoring each link of the work order processing, including a work order overtime reminding unit and a feedback information collecting unit; the feedback information collecting unit is used for collecting evaluation information of the user after the work order is checked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311137302.9A CN117154940A (en) | 2023-09-05 | 2023-09-05 | Electric power service quality gridding monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311137302.9A CN117154940A (en) | 2023-09-05 | 2023-09-05 | Electric power service quality gridding monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117154940A true CN117154940A (en) | 2023-12-01 |
Family
ID=88886496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311137302.9A Pending CN117154940A (en) | 2023-09-05 | 2023-09-05 | Electric power service quality gridding monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117154940A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050262237A1 (en) * | 2004-04-19 | 2005-11-24 | Netqos, Inc. | Dynamic incident tracking and investigation in service monitors |
| US20160142544A1 (en) * | 2014-11-19 | 2016-05-19 | Electronics And Telecommunications Research Institute | Apparatus and method for customer interaction service |
| US20160170814A1 (en) * | 2008-02-25 | 2016-06-16 | Georgetown University | System and method for detecting, collecting, analyzing, and communicating event-related information |
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN110111084A (en) * | 2019-05-16 | 2019-08-09 | 上饶市中科院云计算中心大数据研究院 | A kind of government affairs service hotline analysis method and system |
| CN114169770A (en) * | 2021-12-09 | 2022-03-11 | 福州大学 | Power supply quality complaint early warning system with multiple factors in consideration of personnel |
| CN117371788A (en) * | 2023-10-12 | 2024-01-09 | 贵州电网有限责任公司信息中心 | Electric power marketing risk early warning method and system |
-
2023
- 2023-09-05 CN CN202311137302.9A patent/CN117154940A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050262237A1 (en) * | 2004-04-19 | 2005-11-24 | Netqos, Inc. | Dynamic incident tracking and investigation in service monitors |
| US20160170814A1 (en) * | 2008-02-25 | 2016-06-16 | Georgetown University | System and method for detecting, collecting, analyzing, and communicating event-related information |
| US20160142544A1 (en) * | 2014-11-19 | 2016-05-19 | Electronics And Telecommunications Research Institute | Apparatus and method for customer interaction service |
| CN106815709A (en) * | 2016-12-06 | 2017-06-09 | 国网福建省电力有限公司 | One kind service quick response center support system and method |
| CN110111084A (en) * | 2019-05-16 | 2019-08-09 | 上饶市中科院云计算中心大数据研究院 | A kind of government affairs service hotline analysis method and system |
| CN114169770A (en) * | 2021-12-09 | 2022-03-11 | 福州大学 | Power supply quality complaint early warning system with multiple factors in consideration of personnel |
| CN117371788A (en) * | 2023-10-12 | 2024-01-09 | 贵州电网有限责任公司信息中心 | Electric power marketing risk early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106815709B (en) | Service quick response center support system and method | |
| CN111192060B (en) | Full-channel self-service response implementation method based on power IT service | |
| CN105354762B (en) | Power customer service work order identification and distribution system and method | |
| CN106874134B (en) | Work order type processing method, device and system | |
| CN108764649A (en) | Insurance sales method for real-time monitoring, device, equipment and storage medium | |
| CN110445942A (en) | A kind of outer paging system of intelligence and intelligent calling-out method | |
| CN112564278B (en) | Relay protection fault information sorting and electronic reporting system and method | |
| CN107169744A (en) | The time limit monitoring method and system of a kind of electronic work order | |
| CN110956472A (en) | Application method of man-machine coupling intelligent customer service platform | |
| CN104702759A (en) | Address list setting method and address list setting device | |
| CN111949795A (en) | Work order automatic classification method and device | |
| CN111405236A (en) | Video conference big data analysis method and system | |
| CN111950851A (en) | Work order processing method and device | |
| CN110704628A (en) | System for arranging enterprise management information consultation data | |
| CN107977855B (en) | Method and device for managing user information | |
| CN109040489A (en) | The distribution method and device of telecommunications customer service | |
| CN110011898A (en) | Answering method, device, storage medium and the computer equipment of Email | |
| CN117154940A (en) | Electric power service quality gridding monitoring system and method | |
| CN115860548B (en) | SaaS one-stop platform management method, system and medium based on big data | |
| CN110852646A (en) | On-site fault processing management system based on mobile operation terminal | |
| CN201995020U (en) | Trusteeship call center system with performance calculating and managing functions | |
| CN115860694A (en) | Business expansion process management and control method and system based on instant message technology | |
| CN114363103B (en) | Method, device and computer readable medium for processing conference information | |
| CN112558512A (en) | Intelligent control and application system based on big data and Internet of things technology | |
| CN215679427U (en) | Meteorological data operation monitoring management system on duty |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |