CN116108373A - Bill data classifying and labeling system, electronic equipment and storage medium - Google Patents
Bill data classifying and labeling system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116108373A CN116108373A CN202310405026.3A CN202310405026A CN116108373A CN 116108373 A CN116108373 A CN 116108373A CN 202310405026 A CN202310405026 A CN 202310405026A CN 116108373 A CN116108373 A CN 116108373A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- ticket
- labeling
- annotation
- 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
- 238000002372 labelling Methods 0.000 title claims abstract description 106
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000007689 inspection Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 15
- 238000004891 communication Methods 0.000 description 17
- 239000003795 chemical substances by application Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 7
- 238000013145 classification model Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000013500 data storage Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a call ticket data classification annotation system. The method specifically comprises the following steps: the seat service module and the data synchronization module synchronize original call ticket data generated by the seat service into the data processing module; the data processing module receives the original call ticket data and marks the original call ticket data; the data labeling module is used for acquiring the labeling instruction sent by the front-end module and sending the data labeling result to the data processing module; the data query engine is used for receiving a query request sent by the front-end module, querying according to the query request and generating a search result; the front-end module is used for generating an operation instruction according to the operation of the labeling personnel. According to the method and the device, the original call ticket data are transmitted between the seat service module and the data processing module through the data synchronization module, decoupling between the seat service module and the data processing module is achieved, the influence of one module upgrade on the whole labeling system is avoided, and the labeling efficiency of texts in a system dialogue sheet is improved.
Description
Technical Field
The disclosure relates to the field of data annotation, in particular to a call ticket data classification annotation system, electronic equipment and a storage medium.
Background
In the related art, customer service in a seat system is communication content generated in a customer service process, a large amount of ticket data are generated according to the communication content, classification labeling of the ticket data refers to labeling of text samples in the ticket data through a classification model, and a relationship between ticket data and the labels is established by selecting labels corresponding to the text samples according to a predefined label range and label content.
The data source agent system of the current ticket data and the system for marking are coupled together, so that the service system has more complex functions, the agent system iterates frequently, the influence of the marking system is required to be considered for modification, and the difficulty of the function iteration of the whole service system is improved. Once the data content of the seat system is adjusted, the marking system also needs to be synchronously modified, so that the marking efficiency of the whole system is reduced.
Disclosure of Invention
The disclosure provides a call ticket data classification labeling system, an electronic device and a storage medium. The technical scheme of the present disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a call ticket data classification annotation system, including:
the seat service module is used for performing seat service and generating original call ticket data;
the data synchronization module is used for synchronizing the original call ticket data generated by the seat service into the data processing module;
the data processing module is used for receiving the original ticket data and marking the original ticket data to generate first ticket marking data;
the data labeling module is used for acquiring the labeling instruction sent by the front-end module, sending the data labeling result to the data processing module and generating second ticket labeling data;
the data query engine is used for receiving a query request sent by the front-end module, querying the first ticket annotation data and the second ticket annotation data according to the query request, generating a search result and feeding back the search result to the front-end module;
the front-end module is used for generating an operation instruction according to the operation of the labeling personnel and sending the operation instruction, wherein the operation instruction comprises a query instruction or a labeling instruction.
Optionally, the system further comprises:
the trust authority control module is used for acquiring the white list information and carrying out identity authentication on the labeling personnel of the front-end module according to the white list information.
Optionally, the trust authority control module specifically includes:
the identity data acquisition sub-module is used for interfacing with the labeling personnel database, acquiring white list information from the labeling personnel database, wherein the white list information comprises the identity identification of the labeling personnel, and the identity identification comprises at least one of the following: mobile phone number, enterprise resource planning ERP account, mailbox address or JDPIN account;
and the identity authentication sub-module is used for acquiring the identity mark of the labeling personnel logged in the front-end module and comparing the identity mark with the identity mark in the white list information so as to confirm the identity and authority of the labeling personnel.
Optionally, the data processing module specifically includes:
the ticket storage sub-module is used for storing the original ticket data, wherein the original ticket data comprises a plurality of ticket data, and each ticket data comprises a plurality of clauses;
a ticket inter-rotor module for converting the clauses in the ticket data into a predefined format;
the system labeling sub-module is used for acquiring a quality inspection type, calling a labeling model according to each quality inspection item in the quality inspection type, labeling each clause in the original ticket data, and generating the first ticket labeling data;
the manual annotation sub-module is used for receiving the annotation result sent by the data annotation module, annotating each clause in the original ticket data according to the annotation result and generating the second ticket annotation data;
and the model training sub-module is used for training the annotation model according to the second ticket annotation data.
Optionally, the data query engine specifically includes:
the request analysis sub-module is used for analyzing the query request and acquiring a field to be queried and a corresponding screening condition;
and the retrieval sub-module is used for querying fields to be queried in the first ticket annotation data and the second ticket annotation data, integrating the ticket data meeting the screening conditions to generate the retrieval result and transmitting the retrieval result to the front-end module.
Optionally, the system further comprises:
and the concurrency engine is used for receiving a query request sent by the front-end module when the operation instruction sent by the front-end module is greater than a preset threshold value, querying the first ticket annotation data and the second ticket annotation data according to the query request, generating a retrieval result and feeding back the retrieval result to the front-end module.
According to a second aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the system of any of the first aspects.
According to a third aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the system of any one of the first aspects.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
the original call ticket data is transmitted between the seat service module and the data processing module through the data synchronization module, so that decoupling between the seat service module and the data processing module is realized, the influence of one module upgrade on the whole labeling system is avoided, and the labeling efficiency of the system on texts is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
Fig. 1 is a block diagram illustrating a call ticket data classification annotation system according to an exemplary embodiment.
Fig. 2 is a block diagram of an apparatus according to an example embodiment.
Fig. 3 is a block diagram of an apparatus according to an example embodiment.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the disclosure as detailed in the accompanying claims.
The user information (including but not limited to user equipment information, user personal information, etc.) related to the present disclosure is information authorized by the user or sufficiently authorized by each party.
The text classification data labeling refers to labeling processing of text samples depending on classification model training, selecting a label corresponding to the text sample aiming at a label range and a label value which are defined in advance, establishing a relation between the sample and the label, such as aiming at client privacy leakage violation detection in a customer service quality inspection scene, defining 2 label classifications of normal and client questioning personal information leakage, selecting one ticket record corresponding to a labeled client questioning personal information leakage label, establishing the relation between the text and the label, and further requiring a customer service personnel to avoid the risk of client complaining personal information leakage.
The bill data classification labeling can be performed by a manual combination system mode, and specifically comprises the following steps:
and (3) marking the system, analyzing json format text data in a storage medium through java engineering, converting the format data corresponding to the ticket and clause, processing the converted format data into a system front-end access page, authenticating a marking person, logging in the system to perform label marking work, establishing a relationship between a label and a text on the basis of fully understanding a predefined label range and value, clicking and storing, and automatically persisting the system into the storage medium for training a text classification model. After the text classification model is trained, the ticket data is processed by the data text classification model, clauses in the text classification model automatic dialogue ticket are analyzed, corresponding labels are obtained, and the clauses are marked.
Manually labeling, namely exporting the format text data converted by the system labeling into EXCEL, transmitting the EXCEL offline to labeling personnel, learning and understanding a label range and a label value which are defined in advance by the labeling personnel, manually establishing a relationship between the label and the text data, manually checking the accuracy after the labeling is completed, and transmitting the accuracy back to a storage medium through a data importing tool.
However, the prior art has the following problems:
1) Functional coupling problem: the agent service system serving as a data source and the labeling system are functionally coupled together, so that the service system is more complex in function, the customer service system is frequently iterated, the influence of the labeling system is required to be considered in modification, and the difficulty of the service system function iteration is improved. Once the data content of the customer service system is adjusted, the labeling system also needs to be synchronously modified.
2) Data format flexibility problem: the original ticket data comprises more than 70 dimensional information such as agents, customer service, job sites and the like, temporary adjustment and change of the marked transmission information exist, the existing java engineering has higher realization cost, and the temporary change requirement is difficult to adapt.
3) Complex conditional sampling is not supported: when the original data of the marked ticket are sampled, the sampling needs to be distributed randomly, and the current conditions cannot support sampling logics such as random time, random quality control item, random positive sample, random seat personnel, random job site and the like. The sample still needs to be repeatedly extracted, adjusted and processed after being sampled, and the time cost is huge.
4) The number of samples is limited: the number of records of the single words of the customer service seat is more than 10 hundred million, the number of the single words is more than 4000, the content of single sample data is more than 1M, once the sampling is more than 1000, the network pressure is huge, and the time consumption seriously influences the experience.
5) Data security compliance problem: the content of the existing data annotation relates to the personal demands of clients, sensitive information, a system is needed to be exported in the annotation process, leakage risks exist in confidential information, and meanwhile, once leakage occurs, the source cannot be traced and responsibility cannot be determined.
Fig. 1 is a block diagram of a call ticket data classification annotation system according to an exemplary embodiment, and as shown in fig. 1, the system 100 includes:
the seat service module 110 is configured to perform a seat service and generate original ticket data.
In this embodiment, the seat staff refers to working in a call center or a customer service department in a company enterprise, and the main working content is to process transactions such as service, sales, data acquisition, information investigation, business return visit and the like by answering or dialing a call. Such staff members are known as seat members. The agent service module 110 is a system for communication between an agent and a customer, the communication mode includes telephone communication, and for a conversation generated by the agent in a complete communication with the customer, called a ticket, the communication content can be converted into text through a pre-trained voice recognition model, that is, the original ticket is generated, one original ticket data includes a plurality of clauses, and each clause has information of more than 70 dimensions of the corresponding agent, customer service, job site, and the like.
The data synchronization module 120 is configured to synchronize the original call ticket data generated by the seat service to the data processing module.
In this embodiment, the agent service module 110 provides the original call ticket data, the data processing module 130 marks the original call ticket data, and the data synchronization module 120 synchronizes the original call ticket data of the agent service module 110 to the data processing module 130 through a timing task or a triggering task and persists the data into storage. The service system changes can be well shielded from being influenced mutually, the service system changes are insensitive, and if the seat service module 110 or the data processing module 130 has changes (such as version upgrade and the like) or faults (such as downtime and the like), the data processing module 130 can still label the original call ticket data normally, so that the data labeling task is completed. This completes the decoupling of the decoupled seat service module 110 and the data processing module 130.
The data processing module 130 is configured to receive the original ticket data, label the original ticket data, and generate first ticket labeling data.
In this embodiment, the data processing module 130 integrates the functions of data storage and data processing.
Optionally, the data processing module 130 specifically includes:
the ticket storage sub-module 131 is configured to store the original ticket data, where the original ticket data includes a plurality of ticket data, and each ticket data includes a plurality of clauses.
A ticket inter-rotor module 132 for converting the clauses in the ticket data into a predefined format.
In this embodiment, the ticket data is in JSON format, and the ticket and corresponding clause formatting service is provided by the ticket mutual rotor module 132, so that the ticket data can be converted from JSON format into format which can be directly queried by the front end module according to a predefined format, so that the annotators operating the front end module can query the content in the ticket data.
The system labeling sub-module 133 is configured to obtain a quality inspection type, call a labeling model according to each quality inspection item in the quality inspection type, label each clause in the original ticket data, and generate the first ticket labeling data.
In this embodiment, the seat service includes a plurality of services, that is, quality inspection types. There are different requirements for various services, which are reflected in particular in a plurality of quality check items.
The system labeling sub-module 133 includes a labeling model, where the labeling model is a neural network model trained in advance through a training data set, the training data is clauses in a ticket, each clause is labeled with a corresponding type, and the labeling model is trained for multiple rounds through the training data set until the loss function converges, so that training of the labeling model is completed.
In one possible embodiment, for the quality check type of the promotional service, where one quality check item is a clause that violates the privacy rules, i.e., the agent cannot ask the customer's privacy, if a clause asking for the customer's privacy appears in the original ticket data, the system labeling sub-module 133 would label that clause as "violation of privacy.
And the manual annotation sub-module 134 is configured to receive the annotation result sent by the data annotation module, annotate each clause in the original ticket data according to the annotation result, and generate the second ticket annotation data.
In this embodiment, after the labeling sub-module 133 performs labeling, manual spot check is performed on the labeling result of the system by a labeling person. The labeling personnel performs spot check on the first ticket labeling data at the front-end module 160 to recheck the accuracy of the labeled data, if an error label is found, the labeling personnel re-labels the first ticket labeling data, the labeling result generated after the labeling instruction is sent to the data labeling module 140 is sent to the manual labeling sub-module 134, and the process is the cross-validation of the labeling result.
And the model training sub-module 135 is configured to train the labeling model according to the second ticket labeling data.
In this embodiment, in order to make the labeling model in the system labeling sub-module 133 continuously learn, improve the labeling accuracy, after the error labeling occurs and the second ticket labeling data is generated, the labeling model is further trained by using the second ticket labeling data.
Optionally, the data query engine 150 specifically includes:
the request analysis sub-module 151 is configured to parse the query request, and obtain a field to be queried and a corresponding filtering condition.
In this embodiment, the data query engine 150 employs CK (clickhouse) of the Online analytical processing (Online AnalyticalProcessing, OLAP) engines. The CK engine is an open-source high-performance data multidimensional query framework, supports the column storage and data compression capacity, is particularly suitable for real-time query of large-scale ticket data, has a low-delay return result scene, and is very critical for good experience of labeling personnel in the process of querying massive original tickets; meanwhile, the cloud primary CK (Clickhouse) engine built based on the cloud platform supports the characteristics of dynamic expansion and contraction and the like, and is very beneficial to reasonably controlling the calculation and storage cost. For the CK engine, the storage structure includes fields such as "ticket ID", "client number", "account type", "area ID", "job site ID", etc. At the time of query, the annotator may select one or more fields in the front-end module 160 as fields to be queried, and set query conditions of the respective fields. The fields of the ticket ID, the job site ID of the agent, the group name of the agent, the agent conversation operation and the creation time are necessary.
The query request generated by the labeling personnel after the front-end module performs the query operation is received by the data query engine 150, and the request analysis sub-module 151 analyzes the query request to obtain the fields to be queried and the corresponding screening conditions.
And the retrieving sub-module 152 is configured to query a field to be queried in the first ticket annotation data and the second ticket annotation data, integrate the ticket data meeting the screening condition to generate the retrieval result, and send the retrieval result to the front-end module.
In one possible embodiment, the search results are shown in Table 1
TABLE 1
The search report in table 1 is a result generated by the data query engine 150 searching the first ticket annotation data and the second ticket annotation data after the front-end module sends the query request for the seat person a, and extracting the ticket of the seat person a.
The data labeling module 140 is configured to obtain the labeling instruction sent by the front-end module, send the data labeling result to the data processing module, and generate second ticket labeling data.
The data query engine 150 is configured to receive a query request sent by the front end module, query the first ticket annotation data and the second ticket annotation data according to the query request, generate a search result, and feed back the search result to the front end module;
the front end module 160 is configured to generate an operation instruction according to an operation of a labeling person, and send the operation instruction, where the operation instruction includes a query instruction or a labeling instruction.
In this embodiment, the front end module 160 is a module that interacts with a labeling person, and the labeling person can perform the following operations in the front end module 160:
the marking results are cross-verified, the marking personnel performs spot check on the first ticket marking data at the front end module 160 to recheck the accuracy of the marked data, if the error marking is found, the marking personnel re-marks the first ticket marking data, the marking results generated after the marking instructions are sent to the data marking module 140 are sent to the manual marking sub-module 134, and the process is the cross-verification of the marking results.
The ticket data is inquired and marked, and when a person needing marking carries out marking again, the person can check the original ticket data at the front end module 160, and judge whether the predefined violation label is hit or not according to the ticket content.
Optionally, the system further comprises:
the trust authority control module 170 is configured to obtain whitelist information, and perform identity authentication on a labeling person of the front-end module according to the whitelist information.
Optionally, the trust authority control module 170 specifically includes:
the identity data obtaining sub-module 171 is configured to dock the labeling personnel database, obtain whitelist information from the labeling personnel database, where the whitelist information includes an identity identifier of a labeling personnel, and the identity identifier includes at least one of the following: mobile phone number, enterprise resource planning ERP account, mailbox address or JDPIN account;
the identity authentication sub-module 172 is configured to obtain an identity of a labeling person logged in the front-end module, and compare the identity with the identity in the whitelist information to confirm the identity and authority of the labeling person.
Optionally, the system further comprises:
and the concurrency engine 180 is configured to receive a query request sent by the front end module when an operation instruction sent by the front end module is greater than a preset threshold, query the first ticket annotation data and the second ticket annotation data according to the query request, generate a search result, and feed back the search result to the front end module.
In this embodiment, the concurrency engine 180 is an Elastic Search (ES) high-performance concurrency engine, and when the concurrency number of operation instructions sent by the front-end module is greater than a preset threshold, the front-end query request is served by using the elastic search to store the labeling data, the data storage format is in a Key-value format, the Key value is calibrated by using a ticket ID, and the value is stored in a json format.
In a possible embodiment, the preset threshold is set to 200, that is, when the concurrency number of the operation instructions sent by the front-end module is greater than 200, the ES engine is used to process the query request sent by the front-end module 160.
However, for a scenario with fewer annotators (less than 200 concurrency), the front-end query module may directly request the data query engine 150, and the data storage format may use multiple copies, multiple pieces of storage to ensure that the data is safe and not lost, and performance requirements.
Fig. 3 is a block diagram illustrating an apparatus 800 according to an example embodiment. For example, the apparatus 800 may be a server for implementing the above-described call ticket data classification annotation system.
Referring to fig. 3, apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.
The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or one component of the apparatus 800, the presence or absence of user contact with the apparatus 800, an orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a storage medium is also provided, such as a memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
Fig. 3 is a block diagram illustrating an apparatus 900 for implementing the above-described call ticket classification annotation system according to an exemplary embodiment. For example, apparatus 900 may be provided as a server. Referring to fig. 3, apparatus 900 includes a processing component 922 that further includes one or more processors, and memory resources represented by memory 932, for storing instructions, such as applications, executable by processing component 1922. The application programs stored in memory 932 may include one or more modules that each correspond to a set of instructions. Further, processing component 922 is configured to execute instructions to perform the above-described methods.
The apparatus 900 may also include a power component 926 configured to perform power management of the apparatus 900, a wired or wireless network interface 950 configured to connect the apparatus 900 to a network, and an input output (I/O) interface 958. The device 900 may operate based on an operating system stored in memory 932, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (8)
1. A call ticket data classification annotation system, comprising:
the seat service module is used for performing seat service and generating original call ticket data;
the data synchronization module is used for synchronizing the original call ticket data generated by the seat service into the data processing module;
the data processing module is used for receiving the original ticket data and marking the original ticket data to generate first ticket marking data;
the data labeling module is used for acquiring the labeling instruction sent by the front-end module, sending the data labeling result to the data processing module and generating second ticket labeling data;
the data query engine is used for receiving a query request sent by the front-end module, querying the first ticket annotation data and the second ticket annotation data according to the query request, generating a search result and feeding back the search result to the front-end module;
the front-end module is used for generating an operation instruction according to the operation of the labeling personnel and sending the operation instruction, wherein the operation instruction comprises a query instruction or a labeling instruction.
2. The system of claim 1, wherein the system further comprises:
the trust authority control module is used for acquiring the white list information and carrying out identity authentication on the labeling personnel of the front-end module according to the white list information.
3. The system of claim 2, wherein the trust authority control module specifically comprises:
the identity data acquisition sub-module is used for interfacing with the labeling personnel database, acquiring white list information from the labeling personnel database, wherein the white list information comprises the identity identification of the labeling personnel, and the identity identification comprises at least one of the following: mobile phone number, enterprise resource planning ERP account, mailbox address or JDPIN account;
and the identity authentication sub-module is used for acquiring the identity mark of the labeling personnel logged in the front-end module and comparing the identity mark with the identity mark in the white list information so as to confirm the identity and authority of the labeling personnel.
4. The system according to claim 1, wherein the data processing module specifically comprises:
the ticket storage sub-module is used for storing the original ticket data, wherein the original ticket data comprises a plurality of ticket data, and each ticket data comprises a plurality of clauses;
a ticket inter-rotor module for converting the clauses in the ticket data into a predefined format;
the system labeling sub-module is used for acquiring a quality inspection type, calling a labeling model according to each quality inspection item in the quality inspection type, labeling each clause in the original ticket data, and generating the first ticket labeling data;
the manual annotation sub-module is used for receiving the annotation result sent by the data annotation module, annotating each clause in the original ticket data according to the annotation result and generating the second ticket annotation data;
and the model training sub-module is used for training the annotation model according to the second ticket annotation data.
5. The system of claim 1, wherein the data query engine specifically comprises:
the request analysis sub-module is used for analyzing the query request and acquiring a field to be queried and a corresponding screening condition;
and the retrieval sub-module is used for querying fields to be queried in the first ticket annotation data and the second ticket annotation data, integrating the ticket data meeting the screening conditions to generate the retrieval result and transmitting the retrieval result to the front-end module.
6. The system of claim 1, wherein the system further comprises:
and the concurrency engine is used for receiving a query request sent by the front-end module when the operation instruction sent by the front-end module is greater than a preset threshold value, querying the first ticket annotation data and the second ticket annotation data according to the query request, generating a retrieval result and feeding back the retrieval result to the front-end module.
7. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the system of any one of claims 1 to 6.
8. A computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the system of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310405026.3A CN116108373A (en) | 2023-04-17 | 2023-04-17 | Bill data classifying and labeling system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310405026.3A CN116108373A (en) | 2023-04-17 | 2023-04-17 | Bill data classifying and labeling system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116108373A true CN116108373A (en) | 2023-05-12 |
Family
ID=86254756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310405026.3A Pending CN116108373A (en) | 2023-04-17 | 2023-04-17 | Bill data classifying and labeling system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116108373A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111739519A (en) * | 2020-06-16 | 2020-10-02 | 平安科技（深圳）有限公司 | Dialogue management processing method, device, equipment and medium based on voice recognition |
| WO2021004481A1 (en) * | 2019-07-08 | 2021-01-14 | 华为技术有限公司 | Media files recommending method and device |
| CN113645357A (en) * | 2021-08-06 | 2021-11-12 | 深圳追一科技有限公司 | Call quality inspection method and device, computer equipment and computer readable storage medium |
| CN113723975A (en) * | 2021-09-13 | 2021-11-30 | 国泰君安证券股份有限公司 | System, method, device, processor and computer readable storage medium for realizing intelligent quality inspection processing in intelligent return visit service |
| WO2023272616A1 (en) * | 2021-06-30 | 2023-01-05 | 东莞市小精灵教育软件有限公司 | Text understanding method and system, terminal device, and storage medium |
-
2023
- 2023-04-17 CN CN202310405026.3A patent/CN116108373A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021004481A1 (en) * | 2019-07-08 | 2021-01-14 | 华为技术有限公司 | Media files recommending method and device |
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111739519A (en) * | 2020-06-16 | 2020-10-02 | 平安科技（深圳）有限公司 | Dialogue management processing method, device, equipment and medium based on voice recognition |
| WO2023272616A1 (en) * | 2021-06-30 | 2023-01-05 | 东莞市小精灵教育软件有限公司 | Text understanding method and system, terminal device, and storage medium |
| CN113645357A (en) * | 2021-08-06 | 2021-11-12 | 深圳追一科技有限公司 | Call quality inspection method and device, computer equipment and computer readable storage medium |
| CN113723975A (en) * | 2021-09-13 | 2021-11-30 | 国泰君安证券股份有限公司 | System, method, device, processor and computer readable storage medium for realizing intelligent quality inspection processing in intelligent return visit service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11379686B2 (en) | Deploying data processing service plug-ins into a cloud-based collaboration platform | |
| CN112106049B (en) | System and method for generating privacy data quarantine and report | |
| US12032644B2 (en) | Systems and methods for displaying contextually relevant links | |
| KR20210036878A (en) | Method and apparatus for pushing information, device and storage medium | |
| US20210144197A1 (en) | Method for Presenting Schedule Reminder Information, Terminal Device, and Cloud Server | |
| CN105354284A (en) | Template processing method and apparatus and short message identification method and apparatus | |
| CN111813932B (en) | Text data processing method, text data classifying device and readable storage medium | |
| CN112183953A (en) | Method and device for allocating customer service resources, electronic equipment and storage medium | |
| CN113435205B (en) | Semantic analysis method and device | |
| CN114201484A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN114219443A (en) | Document data processing method, device and equipment | |
| CN107329744A (en) | The functional module of application program starts method and device | |
| CN116108373A (en) | Bill data classifying and labeling system, electronic equipment and storage medium | |
| CN115640790A (en) | Information processing method and device and electronic equipment | |
| CN114896165A (en) | Testing method and device of conversation robot system, electronic equipment and storage medium | |
| CN110765111B (en) | Storage and reading method and device, electronic equipment and storage medium | |
| CN110472026B (en) | Text information processing method and system, readable storage medium and terminal equipment | |
| CN114239531A (en) | Template recommendation method and device, electronic equipment and storage medium | |
| CN107733779B (en) | Function expansion method and device based on contact persons | |
| CN111898100A (en) | Code leakage tracing method and device and terminal equipment | |
| US10536833B1 (en) | Artificial intelligence internet protocol private branch exchange (IP-PBX) system with mobile value-added services | |
| CN115529172A (en) | Data processing method, device, equipment, storage medium and product | |
| CN117149649A (en) | Transaction testing method and device and electronic equipment | |
| CN115455007A (en) | Data processing method, device, equipment and storage medium | |
| CN117708120A (en) | Report system and report generation method based on real-time database and relational database |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230512 |