CN113704405B - Quality inspection scoring method, device, equipment and storage medium based on recorded content - Google Patents
Quality inspection scoring method, device, equipment and storage medium based on recorded content Download PDFInfo
- Publication number
- CN113704405B CN113704405B CN202111002989.6A CN202111002989A CN113704405B CN 113704405 B CN113704405 B CN 113704405B CN 202111002989 A CN202111002989 A CN 202111002989A CN 113704405 B CN113704405 B CN 113704405B
- Authority
- CN
- China
- Prior art keywords
- text
- quality inspection
- data
- preset
- original
- 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.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 82
- 238000013077 scoring method Methods 0.000 title claims abstract description 25
- 230000006870 function Effects 0.000 claims description 78
- 238000012545 processing Methods 0.000 claims description 30
- 230000011218 segmentation Effects 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008451 emotion Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Acoustics & Sound (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to artificial intelligence and digital medical technology, and discloses a quality inspection scoring method based on recorded content, which comprises the following steps: converting the original recording data into original text data, comparing the original text data with a preset keyword blacklist, generating keyword scores according to the comparison result, constructing a hyperplane function according to the original text data, classifying the original text data by utilizing the hyperplane function to obtain classification results, scoring the classification results to obtain classification scores, and obtaining quality inspection scores according to the keyword scores, the classification scores and a preset quality inspection scoring formula. In the present invention, the original recording data may be recording data between doctors and patients. In addition, the invention also relates to a blockchain technology, and the original record data can be stored in nodes of the blockchain. The invention further provides a quality inspection scoring device based on the recorded content, electronic equipment and a storage medium. The invention can judge the service quality of the seat to the customer.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a quality inspection scoring method, a quality inspection scoring device, electronic equipment and a computer readable storage medium based on recorded content.
Background
When the customer calls, the seat can determine whether the problem of the customer is solved or not according to the judgment of the seat, and whether a work order needs to be reported to further solve the problem of the customer or not. Because the seat has some manual errors when making the judgment, the problems of many clients are not really solved. Therefore, quality inspection is required to be performed on the recorded content of the client, and corresponding operations are further performed according to the scores obtained by the quality inspection. Therefore, a quality inspection scoring method is needed to evaluate the service quality of the agent to the customer.
Disclosure of Invention
The invention provides a quality inspection scoring method and device based on recorded content and a computer readable storage medium, and mainly aims to judge the service quality of a customer by an agent.
In order to achieve the above object, the quality inspection scoring method based on recorded content provided by the present invention includes:
Acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
Comparing the original text data with a preset keyword blacklist, and generating keyword scores according to a comparison result;
Constructing a hyper-plane function according to the original text data, and classifying the original text data by utilizing the hyper-plane function to obtain a classification result;
scoring the classification result to obtain a classification score;
And taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
Optionally, the text conversion of the original recording data to obtain original text data includes:
Identifying a mute segment in the original recording data, and executing cutting processing on the mute segment to obtain the original recording data;
Extracting features of the initial recording data to obtain a feature vector set;
and carrying out voice recognition on the feature vector set according to a preset acoustic model, a language model and a dictionary to obtain original text data.
Optionally, the performing speech recognition on the feature vector set according to a preset acoustic model, language model and dictionary to obtain original text data includes:
performing phoneme processing on the feature vector set by using a preset acoustic model to obtain phoneme information;
obtaining single characters or single words corresponding to the phoneme information based on a preset dictionary;
and identifying the association probability value between the single words or the single words by using a preset language model, and combining the single words or the single words into the original text data according to the probability value.
Optionally, the identifying the single word or the association probability value between single words using the language model includes:
carrying out vectorization processing on the single word or the single word to obtain a word vector corresponding to the single word and a word vector corresponding to the single word;
converting the word vector or the word vector according to a forward long and short memory network layer and a backward long and short memory network layer in the language model to obtain a vector matrix;
And inputting the vector matrix into a preset activation function to obtain a single word or a correlation probability value among single words.
Optionally, the comparing the original text data with a preset keyword blacklist, and generating a keyword score according to a result obtained by the comparing includes:
Performing word segmentation processing on the original text data to obtain a word segmentation set;
comparing the segmented words in the segmented word set with the keywords in the keyword blacklist, and summarizing the number of segmented words overlapped with the keyword blacklist to obtain an overlap number;
And generating corresponding keyword scores according to different preset numerical intervals to which the coincidence numbers belong.
Optionally, the constructing a hyperplane function according to the original text data includes:
counting the total data corresponding to the original text data, and taking the total data as a characteristic dimension;
Acquiring a preset classified label set, and analyzing the classified label set to obtain the total number of labels;
constructing a multidimensional coordinate system according to the characteristic dimension and the total number of the labels;
Mapping the original text data into the multidimensional coordinate system to obtain a text coordinate set;
Calculating a distance value between any two text coordinates in the text coordinate set;
Sorting the distance values, and selecting two text coordinates corresponding to the minimum distance value as a first text coordinate and a second text coordinate respectively;
Taking the first text coordinate as a left boundary and the second text coordinate as a right boundary, and constructing to obtain a hyperplane;
And selecting the center of the hyperplane to establish a hyperplane function.
Optionally, the classifying the original text data by using the hyperplane function to obtain a classification result includes:
Respectively calculating distance values between the hyper-plane function and the first text coordinate and between the hyper-plane function and the second text coordinate, and constructing a minimum distance function according to the distance values;
Acquiring a preset constraint condition, and solving a minimum distance function based on the constraint condition by using a Lagrange function to obtain a hyperplane;
And classifying the original text data by using the super-plane to obtain a classification result.
In order to solve the above problems, the present invention further provides a quality inspection scoring device based on recorded content, the device comprising:
the text conversion module is used for acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
the keyword comparison module is used for comparing the original text data with a preset keyword blacklist and generating keyword scores according to the comparison result;
The text classification module is used for constructing a hyper-plane function according to the original text data, classifying the original text data by utilizing the hyper-plane function to obtain a classification result, and scoring the classification result to obtain a classification score;
And the quality inspection scoring module is used for taking the keyword scores and the classification scores as input of a preset quality inspection scoring formula to obtain the quality inspection scores of the original recording data.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the recorded content-based quality inspection scoring method described above.
In order to solve the above-mentioned problems, the present invention further provides a computer readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned quality inspection scoring method based on recorded content.
According to the embodiment of the invention, the recording data are converted into text data, and the text data are expressed in a text form, so that the analysis is convenient; further, comparing the text data with a preset keyword blacklist, and primarily scoring the text data from the perspective of the keyword blacklist; and classifying the text data by constructing a hyper-plane function, grading the text data for the first time according to the classification result, and obtaining a final quality inspection grade according to the grading for the second time. The embodiment of the invention considers the grading of more than one dimension, and can judge the service quality of the seat to the customer more accurately. Therefore, the quality inspection scoring method, the quality inspection scoring device, the electronic equipment and the computer readable storage medium based on the recorded content can judge the service quality of the seat to the client.
Drawings
Fig. 1 is a flow chart of a quality inspection scoring method based on recorded content according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of a quality inspection scoring apparatus based on recorded content according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device for implementing the quality inspection scoring method based on recorded content according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a quality inspection scoring method based on recorded content. The execution subject of the quality inspection scoring method based on the recorded content comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the quality inspection scoring method based on recorded content may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flowchart of a quality inspection scoring method based on recorded content according to an embodiment of the present invention is shown. In this embodiment, the quality inspection scoring method based on recorded content includes:
s1, acquiring original recording data, and performing text conversion on the original recording data to obtain original text data.
In the embodiment of the invention, the original recording data is telephone communication content of the seat and the customer without reporting the work order in the intelligent customer service scene.
Specifically, the text conversion of the original recording data to obtain original text data includes:
Identifying a mute segment in the original recording data, and executing cutting processing on the mute segment to obtain the original recording data;
Extracting features of the initial recording data to obtain a feature vector set;
and carrying out voice recognition on the feature vector set according to a preset acoustic model, a language model and a dictionary to obtain original text data.
In detail, the silence segment in the original recording data refers to data without sound in the audio for a long time, and bandwidth resources occupied by the original recording data can be saved by executing cutting processing on the silence segment.
Further, feature extraction is performed on the initial recording data, namely a series of processing such as pre-emphasis processing, framing processing, windowing processing, fast fourier transformation and the like is performed on the initial recording data, a frequency spectrum corresponding to the initial recording data is obtained, and discrete cosine change is performed on the frequency spectrum, so that a feature vector set is obtained.
Specifically, the performing speech recognition on the feature vector set according to a preset acoustic model, language model and dictionary to obtain original text data includes:
performing phoneme processing on the feature vector set by using a preset acoustic model to obtain phoneme information;
obtaining single characters or single words corresponding to the phoneme information based on a preset dictionary;
and identifying the association probability value between the single words or the single words by using a preset language model, and combining the single words or the single words into the original text data according to the probability value.
Preferably, the acoustic model may be a Bert model, and the language model may be a two-way long-short term memory network model.
In the embodiment of the present invention, the phoneme information includes phonetic symbols in english, initials and finals in chinese, and the like. The dictionary comprises phoneme information and single words or words corresponding to the phonemes. According to the embodiment of the invention, through performing traversal operation in the preset dictionary according to the phoneme information, single characters or words corresponding to the phoneme information are obtained.
Further, the identifying the single word or the association probability value between single words using the language model includes:
carrying out vectorization processing on the single word or the single word to obtain a word vector corresponding to the single word and a word vector corresponding to the single word;
converting the word vector or the word vector according to a forward long and short memory network layer and a backward long and short memory network layer in the language model to obtain a vector matrix;
And inputting the vector matrix into a preset activation function to obtain a single word or a correlation probability value among single words.
Preferably, the activation function may be a softmax function.
Further, the embodiment of the invention identifies the single word or the single word as a complete word set according to the probability value, judges according to the probability value of the single word or the single word corresponding to the phoneme information and a preset probability threshold value, reserves the corresponding single word or the single word larger than the probability threshold value, deletes the corresponding single word or the single word smaller than or equal to the probability threshold value, and identifies the reserved single word or the single word as the word set.
For example, the language model identifies that the probability values for the individual words or words are interrelated are: i: 0.0786, is: 0.0546, I are: 0.0967, customer service: 0.06785, customer service personnel: 0.0898, the probability threshold is 0.08, so that ' I'm is ' and ' customer service personnel ' are reserved, the rest are deleted, and the identified text is ' I'm is ' customer service personnel '.
In another embodiment of the present invention, an ASR speech recognition technique may be used to perform text conversion on the original recording data to obtain original text data. Among other things, the ASR speech recognition technique, also known as automatic speech recognition Automatic Speech Recognition (ASR), aims at converting lexical content in human speech into computer-readable inputs, such as keys, binary codes, or character sequences. Unlike speaker recognition and speaker verification, the latter attempts to identify or verify the speaker making the speech, not the lexical content contained therein.
S2, comparing the original text data with a preset keyword blacklist, and generating keyword scores according to the comparison result.
In the embodiment of the invention, the preset keyword blacklist contains some vocabularies which are not allowed to be proposed or are strictly forbidden in a customer service scene, and if keywords overlapped with the keyword blacklist exist in the original text data, the subsequent keyword scoring is affected.
Specifically, the comparing the original text data with a preset keyword blacklist, generating a keyword score according to a result obtained by the comparison, includes:
Performing word segmentation processing on the original text data to obtain a word segmentation set;
comparing the segmented words in the segmented word set with the keywords in the keyword blacklist, and summarizing the number of segmented words overlapped with the keyword blacklist to obtain an overlap number;
And generating corresponding keyword scores according to different preset numerical intervals to which the coincidence numbers belong.
In detail, the word segmentation process can adopt a reference word segmentation device for word segmentation, wherein the reference word segmentation device can be a Hadamard word segmentation device, a word embedding +Bi-LSTM +CRF word segmentation device, a ZPar word segmentation device or a stemming word segmentation tool.
For example, the preset first numerical interval is 0-10, the preset second numerical interval is 11-20, the preset third numerical interval is not 21-30, if the coincidence number belongs to the first numerical interval, the corresponding keyword score is 30 minutes, and so on.
S3, constructing a hyper-plane function according to the original text data, and classifying the original text data by utilizing the hyper-plane function to obtain a classification result.
In an embodiment of the present invention, the constructing a hyperplane function according to the original text data includes:
counting the total data corresponding to the original text data, and taking the total data as a characteristic dimension;
Acquiring a preset classified label set, and analyzing the classified label set to obtain the total number of labels;
constructing a multidimensional coordinate system according to the characteristic dimension and the total number of the labels;
Mapping the original text data into the multidimensional coordinate system to obtain a text coordinate set;
Calculating a distance value between any two text coordinates in the text coordinate set;
Sorting the distance values, and selecting two text coordinates corresponding to the minimum distance value as a first text coordinate and a second text coordinate respectively;
Taking the first text coordinate as a left boundary and the second text coordinate as a right boundary, and constructing to obtain a hyperplane;
And selecting the center of the hyperplane to establish a hyperplane function.
The preset classification label set is an emotion label of the customer.
For example, if two feature subsets exist, the feature dimension is 2, the tag set is taken as the y axis, a two-dimensional coordinate system is constructed by taking the feature subset as the x axis, and the feature subsets are mapped onto the two-dimensional coordinate system, so as to obtain the feature coordinate set on the two-dimensional coordinate system. With the first text coordinate as a left boundary and the second text coordinate as a right boundary, the function of the left boundary may be w×x+b=1, and the function of the right boundary may be w×x+b= -1, so that the hyperplane function is w×x+b=0.
Specifically, the classifying the original text data by using the hyperplane function to obtain a classification result includes:
Respectively calculating distance values between the hyper-plane function and the first text coordinate and between the hyper-plane function and the second text coordinate, and constructing a minimum distance function according to the distance values;
Acquiring a preset constraint condition, and solving a minimum distance function based on the constraint condition by using a Lagrange function to obtain a hyperplane;
And classifying the original text data by using the super-plane to obtain a classification result.
Further, the calculating distance values between the hyperplane function and the first text coordinates and the second text coordinates, respectively, includes:
Wherein, gamma i is a distance value, x i is an ith text coordinate, y i is an ith classification label in the classification label set, and w and b are preset fixed parameters.
In detail, in the embodiment of the present invention, the preset constraint condition is that the distance between each coordinate and the hyperplane is equal to or greater than a minimum distance function.
And S4, scoring the classification result to obtain a classification score.
In the embodiment of the present invention, the scoring the classification result to obtain a classification score includes:
Acquiring a preset classification rule table, wherein the classification rule table comprises classification categories and corresponding scores;
scoring the classification result according to the classification rule table to obtain classification scores,
In detail, the classification result is scored, so that the dimension of the subsequent quality inspection scoring can be increased, and the quality inspection scoring is more accurate.
S5, taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
In the embodiment of the present invention, the inputting the keyword score and the classification score as the preset quality inspection score formula includes:
The preset quality inspection scoring formula is as follows:
Score＝α*q1+β*q2
Wherein Score is the quality inspection Score, q1 is the keyword Score, q2 is the classification Score, and α and β are preset weights.
In detail, the data most likely to be problematic can be ranked according to the quality inspection scores and then delivered to service personnel for checking according to recorded content and converted texts. Meanwhile, the scheme relates to a keyword blacklist and analysis of the emotion category of the client, so that the method is more accurate.
According to the embodiment of the invention, the recording data are converted into text data, and the text data are expressed in a text form, so that the analysis is convenient; further, comparing the text data with a preset keyword blacklist, and primarily scoring the text data from the perspective of the keyword blacklist; and classifying the text data by constructing a hyper-plane function, grading the text data for the first time according to the classification result, and obtaining a final quality inspection grade according to the grading for the second time. The embodiment of the invention considers the grading of more than one dimension, and can judge the service quality of the seat to the customer more accurately. Therefore, the quality inspection scoring method based on the recorded content can realize the judgment of the service quality of the seat to the client.
Fig. 2 is a functional block diagram of a quality inspection scoring device based on recorded content according to an embodiment of the present invention.
The quality inspection scoring apparatus 100 based on recorded content of the present invention may be installed in an electronic device. Depending on the implementation, the quality inspection scoring device 100 based on the recorded content may include a text conversion module 101, a keyword comparison module 102, a text classification module 103, and a quality inspection scoring module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
The text conversion module 101 is configured to obtain original recording data, and perform text conversion on the original recording data to obtain original text data;
The keyword comparison module 102 is configured to compare the original text data with a preset keyword blacklist, and generate a keyword score according to a result obtained by the comparison;
The text classification module 103 is configured to construct a hyper-plane function according to the original text data, classify the original text data by using the hyper-plane function to obtain a classification result, and score the classification result to obtain a classification score;
The quality inspection scoring module 104 is configured to take the keyword score and the classification score as input of a preset quality inspection scoring formula to obtain a quality inspection score of the original recording data.
In detail, the specific implementation modes of the modules of the quality inspection scoring device 100 based on the recorded content are as follows:
step one, obtaining original recording data, and performing text conversion on the original recording data to obtain original text data.
In the embodiment of the invention, the original recording data is telephone communication content of the seat and the customer without reporting the work order in the intelligent customer service scene.
Specifically, the text conversion of the original recording data to obtain original text data includes:
Identifying a mute segment in the original recording data, and executing cutting processing on the mute segment to obtain the original recording data;
Extracting features of the initial recording data to obtain a feature vector set;
and carrying out voice recognition on the feature vector set according to a preset acoustic model, a language model and a dictionary to obtain original text data.
In detail, the silence segment in the original recording data refers to data without sound in the audio for a long time, and bandwidth resources occupied by the original recording data can be saved by executing cutting processing on the silence segment.
Further, feature extraction is performed on the initial recording data, namely a series of processing such as pre-emphasis processing, framing processing, windowing processing, fast fourier transformation and the like is performed on the initial recording data, a frequency spectrum corresponding to the initial recording data is obtained, and discrete cosine change is performed on the frequency spectrum, so that a feature vector set is obtained.
Specifically, the performing speech recognition on the feature vector set according to a preset acoustic model, language model and dictionary to obtain original text data includes:
performing phoneme processing on the feature vector set by using a preset acoustic model to obtain phoneme information;
obtaining single characters or single words corresponding to the phoneme information based on a preset dictionary;
and identifying the association probability value between the single words or the single words by using a preset language model, and combining the single words or the single words into the original text data according to the probability value.
Preferably, the acoustic model may be a Bert model, and the language model may be a two-way long-short term memory network model.
In the embodiment of the present invention, the phoneme information includes phonetic symbols in english, initials and finals in chinese, and the like. The dictionary comprises phoneme information and single words or words corresponding to the phonemes. According to the embodiment of the invention, through performing traversal operation in the preset dictionary according to the phoneme information, single characters or words corresponding to the phoneme information are obtained.
Further, the identifying the single word or the association probability value between single words using the language model includes:
carrying out vectorization processing on the single word or the single word to obtain a word vector corresponding to the single word and a word vector corresponding to the single word;
converting the word vector or the word vector according to a forward long and short memory network layer and a backward long and short memory network layer in the language model to obtain a vector matrix;
And inputting the vector matrix into a preset activation function to obtain a single word or a correlation probability value among single words.
Preferably, the activation function may be a softmax function.
Further, the embodiment of the invention identifies the single word or the single word as a complete word set according to the probability value, judges according to the probability value of the single word or the single word corresponding to the phoneme information and a preset probability threshold value, reserves the corresponding single word or the single word larger than the probability threshold value, deletes the corresponding single word or the single word smaller than or equal to the probability threshold value, and identifies the reserved single word or the single word as the word set.
For example, the language model identifies that the probability values for the individual words or words are interrelated are: i: 0.0786, is: 0.0546, I are: 0.0967, customer service: 0.06785, customer service personnel: 0.0898, the probability threshold is 0.08, so that ' I'm is ' and ' customer service personnel ' are reserved, the rest are deleted, and the identified text is ' I'm is ' customer service personnel '.
In another embodiment of the present invention, an ASR speech recognition technique may be used to perform text conversion on the original recording data to obtain original text data. Among other things, the ASR speech recognition technique, also known as automatic speech recognition Automatic Speech Recognition (ASR), aims at converting lexical content in human speech into computer-readable inputs, such as keys, binary codes, or character sequences. Unlike speaker recognition and speaker verification, the latter attempts to identify or verify the speaker making the speech, not the lexical content contained therein.
And step two, comparing the original text data with a preset keyword blacklist, and generating keyword scores according to the comparison result.
In the embodiment of the invention, the preset keyword blacklist contains some vocabularies which are not allowed to be proposed or are strictly forbidden in a customer service scene, and if keywords overlapped with the keyword blacklist exist in the original text data, the subsequent keyword scoring is affected.
Specifically, the comparing the original text data with a preset keyword blacklist, generating a keyword score according to a result obtained by the comparison, includes:
Performing word segmentation processing on the original text data to obtain a word segmentation set;
comparing the segmented words in the segmented word set with the keywords in the keyword blacklist, and summarizing the number of segmented words overlapped with the keyword blacklist to obtain an overlap number;
And generating corresponding keyword scores according to different preset numerical intervals to which the coincidence numbers belong.
In detail, the word segmentation process can adopt a reference word segmentation device for word segmentation, wherein the reference word segmentation device can be a Hadamard word segmentation device, a word embedding +Bi-LSTM +CRF word segmentation device, a ZPar word segmentation device or a stemming word segmentation tool.
For example, the preset first numerical interval is 0-10, the preset second numerical interval is 11-20, the preset third numerical interval is not 21-30, if the coincidence number belongs to the first numerical interval, the corresponding keyword score is 30 minutes, and so on.
And thirdly, constructing a hyperplane function according to the original text data, and classifying the original text data by utilizing the hyperplane function to obtain a classification result.
In an embodiment of the present invention, the constructing a hyperplane function according to the original text data includes:
counting the total data corresponding to the original text data, and taking the total data as a characteristic dimension;
Acquiring a preset classified label set, and analyzing the classified label set to obtain the total number of labels;
constructing a multidimensional coordinate system according to the characteristic dimension and the total number of the labels;
Mapping the original text data into the multidimensional coordinate system to obtain a text coordinate set;
Calculating a distance value between any two text coordinates in the text coordinate set;
Sorting the distance values, and selecting two text coordinates corresponding to the minimum distance value as a first text coordinate and a second text coordinate respectively;
Taking the first text coordinate as a left boundary and the second text coordinate as a right boundary, and constructing to obtain a hyperplane;
And selecting the center of the hyperplane to establish a hyperplane function.
The preset classification label set is an emotion label of the customer.
For example, if two feature subsets exist, the feature dimension is 2, the tag set is taken as the y axis, a two-dimensional coordinate system is constructed by taking the feature subset as the x axis, and the feature subsets are mapped onto the two-dimensional coordinate system, so as to obtain the feature coordinate set on the two-dimensional coordinate system. With the first text coordinate as a left boundary and the second text coordinate as a right boundary, the function of the left boundary may be w×x+b=1, and the function of the right boundary may be w×x+b= -1, so that the hyperplane function is w×x+b=0.
Specifically, the classifying the original text data by using the hyperplane function to obtain a classification result includes:
Respectively calculating distance values between the hyper-plane function and the first text coordinate and between the hyper-plane function and the second text coordinate, and constructing a minimum distance function according to the distance values;
Acquiring a preset constraint condition, and solving a minimum distance function based on the constraint condition by using a Lagrange function to obtain a hyperplane;
And classifying the original text data by using the super-plane to obtain a classification result.
Further, the calculating distance values between the hyperplane function and the first text coordinates and the second text coordinates, respectively, includes:
Wherein, gamma i is a distance value, x i is an ith text coordinate, y i is an ith classification label in the classification label set, and w and b are preset fixed parameters.
In detail, in the embodiment of the present invention, the preset constraint condition is that the distance between each coordinate and the hyperplane is equal to or greater than a minimum distance function.
And step four, scoring the classification result to obtain classification scores.
In the embodiment of the present invention, the scoring the classification result to obtain a classification score includes:
Acquiring a preset classification rule table, wherein the classification rule table comprises classification categories and corresponding scores;
scoring the classification result according to the classification rule table to obtain classification scores,
In detail, the classification result is scored, so that the dimension of the subsequent quality inspection scoring can be increased, and the quality inspection scoring is more accurate.
And fifthly, taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
In the embodiment of the present invention, the inputting the keyword score and the classification score as the preset quality inspection score formula includes:
The preset quality inspection scoring formula is as follows:
Score＝α*q1+β*q2
Wherein Score is the quality inspection Score, q1 is the keyword Score, q2 is the classification Score, and α and β are preset weights.
In detail, the data most likely to be problematic can be ranked according to the quality inspection scores and then delivered to service personnel for checking according to recorded content and converted texts. Meanwhile, the scheme relates to a keyword blacklist and analysis of the emotion category of the client, so that the method is more accurate.
According to the embodiment of the invention, the recording data are converted into text data, and the text data are expressed in a text form, so that the analysis is convenient; further, comparing the text data with a preset keyword blacklist, and primarily scoring the text data from the perspective of the keyword blacklist; and classifying the text data by constructing a hyper-plane function, grading the text data for the first time according to the classification result, and obtaining a final quality inspection grade according to the grading for the second time. The embodiment of the invention considers the grading of more than one dimension, and can judge the service quality of the seat to the customer more accurately. Therefore, the quality inspection scoring device based on the recorded content can judge the service quality of the seat to the client.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a quality inspection scoring method based on recorded content according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a quality inspection scoring program based on recorded content, stored in the memory 11 and executable on the processor 10.
The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory 11 (for example, executing a quality inspection scoring program based on recorded contents, etc.), and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of quality inspection scoring programs based on recorded content, but also for temporarily storing data that has been output or is to be output.
The communication bus 12 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The quality inspection scoring program based on recorded content stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
Acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
Comparing the original text data with a preset keyword blacklist, and generating keyword scores according to a comparison result;
Constructing a hyper-plane function according to the original text data, and classifying the original text data by utilizing the hyper-plane function to obtain a classification result;
scoring the classification result to obtain a classification score;
And taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
Acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
Comparing the original text data with a preset keyword blacklist, and generating keyword scores according to a comparison result;
Constructing a hyper-plane function according to the original text data, and classifying the original text data by utilizing the hyper-plane function to obtain a classification result;
scoring the classification result to obtain a classification score;
And taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. A quality inspection scoring method based on recorded content, the method comprising:
Acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
Comparing the original text data with a preset keyword blacklist, and generating keyword scores according to a comparison result;
Counting the total data corresponding to the original text data, taking the total data as a characteristic dimension, acquiring a preset classified label set, analyzing the classified label set to obtain a label total number, constructing a multi-dimensional coordinate system by the characteristic dimension and the label total number, mapping the original text data into the multi-dimensional coordinate system to obtain a text coordinate set, calculating a distance value between any two text coordinates in the text coordinate set, sorting the distance values, selecting two text coordinates corresponding to a minimum distance value as a first text coordinate and a second text coordinate, taking the first text coordinate as a left boundary and the second text coordinate as a right boundary, constructing to obtain an initial hyper-plane, selecting the center of the initial hyper-plane to establish a hyper-plane function, respectively calculating the distance value between the hyper-plane function and the first text coordinate and the second text coordinate, constructing a minimum distance function according to the distance value, acquiring a constraint condition by using a Lagrange function to solve a minimum distance based on the constraint condition, obtaining a target hyper-plane based on the constraint condition, and obtaining a classified label set by using the target hyper-plane;
scoring the classification result to obtain a classification score;
And taking the keyword scores and the classification scores as input of a preset quality inspection score formula to obtain quality inspection scores of the original recording data.
2. The quality inspection scoring method based on recorded content of claim 1, wherein the text converting the original recorded data to obtain original text data comprises:
Identifying a mute segment in the original recording data, and executing cutting processing on the mute segment to obtain the original recording data;
Extracting features of the initial recording data to obtain a feature vector set;
and carrying out voice recognition on the feature vector set according to a preset acoustic model, a language model and a dictionary to obtain original text data.
3. The quality inspection scoring method based on recorded content of claim 2, wherein the performing speech recognition on the feature vector set according to a preset acoustic model, language model and dictionary to obtain original text data comprises:
performing phoneme processing on the feature vector set by using a preset acoustic model to obtain phoneme information;
obtaining single characters or single words corresponding to the phoneme information based on a preset dictionary;
and identifying the association probability value between the single words or the single words by using a preset language model, and combining the single words or the single words into the original text data according to the probability value.
4. The method for recording-based quality inspection scoring of claim 3, wherein said identifying the individual words or associated probability values between individual words using the language model comprises:
carrying out vectorization processing on the single word or the single word to obtain a word vector corresponding to the single word and a word vector corresponding to the single word;
converting the word vector or the word vector according to a forward long and short memory network layer and a backward long and short memory network layer in the language model to obtain a vector matrix;
And inputting the vector matrix into a preset activation function to obtain a single word or a correlation probability value among single words.
5. The quality inspection scoring method based on recorded content according to claim 1, wherein the comparing the original text data with a preset keyword blacklist, and generating a keyword score according to a result obtained by the comparison, comprises:
Performing word segmentation processing on the original text data to obtain a word segmentation set;
comparing the segmented words in the segmented word set with the keywords in the keyword blacklist, and summarizing the number of segmented words overlapped with the keyword blacklist to obtain an overlap number;
And generating corresponding keyword scores according to different preset numerical intervals to which the coincidence numbers belong.
6. A quality inspection scoring device based on recorded content, the device comprising:
the text conversion module is used for acquiring original recording data, and performing text conversion on the original recording data to obtain original text data;
the keyword comparison module is used for comparing the original text data with a preset keyword blacklist and generating keyword scores according to the comparison result;
The text classification module is used for counting the total number of data corresponding to the original text data, taking the total number of data as a characteristic dimension, acquiring a preset classification label set, analyzing the classification label set to obtain the total number of labels, constructing a multi-dimensional coordinate system by the characteristic dimension and the total number of labels, mapping the original text data into the multi-dimensional coordinate system to obtain a text coordinate set, calculating a distance value between any two text coordinates in the text coordinate set, sorting the distance value, selecting two text coordinates corresponding to a minimum distance value as a first text coordinate and a second text coordinate respectively, taking the first text coordinate as a left boundary and the second text coordinate as a right boundary, constructing to obtain an initial hyper-plane, selecting the center of the initial hyper-plane to establish a hyper-plane function, respectively calculating distance values between the hyper-plane function and the first text coordinate and the second text coordinate, constructing a minimum distance function according to the distance value, acquiring a preset constraint condition, solving a target hyper-plane function based on the constraint condition by using a Lagrange function, obtaining a target hyper-plane function, and obtaining a classification label by using the target hyper-plane function as a target language label;
scoring the classification result to obtain a classification score;
And the quality inspection scoring module is used for taking the keyword scores and the classification scores as input of a preset quality inspection scoring formula to obtain the quality inspection scores of the original recording data.
7. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the recorded content-based quality inspection scoring method of any one of claims 1 to 5.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the recorded content-based quality inspection scoring method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111002989.6A CN113704405B (en) | 2021-08-30 | 2021-08-30 | Quality inspection scoring method, device, equipment and storage medium based on recorded content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111002989.6A CN113704405B (en) | 2021-08-30 | 2021-08-30 | Quality inspection scoring method, device, equipment and storage medium based on recorded content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113704405A CN113704405A (en) | 2021-11-26 |
| CN113704405B true CN113704405B (en) | 2024-06-28 |
Family
ID=78656641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111002989.6A Active CN113704405B (en) | 2021-08-30 | 2021-08-30 | Quality inspection scoring method, device, equipment and storage medium based on recorded content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704405B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109151218A (en) * | 2018-08-21 | 2019-01-04 | 平安科技（深圳）有限公司 | Call voice quality detecting method, device, computer equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9093081B2 (en) * | 2013-03-10 | 2015-07-28 | Nice-Systems Ltd | Method and apparatus for real time emotion detection in audio interactions |
| CN106407406B (en) * | 2016-09-22 | 2019-12-10 | 国信优易数据有限公司 | text processing method and system |
| US20190385711A1 (en) * | 2018-06-19 | 2019-12-19 | Ellipsis Health, Inc. | Systems and methods for mental health assessment |
| CN109308912B (en) * | 2018-08-02 | 2024-02-20 | 平安科技（深圳）有限公司 | Music style recognition method, device, computer equipment and storage medium |
| CN109327632A (en) * | 2018-11-23 | 2019-02-12 | 深圳前海微众银行股份有限公司 | Intelligent quality inspection system, method and the computer readable storage medium of customer service recording |
| CN111666412A (en) * | 2020-06-02 | 2020-09-15 | 国家计算机网络与信息安全管理中心 | Fraud log text analysis method and system based on SVM text analysis |
| CN112527994A (en) * | 2020-12-18 | 2021-03-19 | 平安银行股份有限公司 | Emotion analysis method, emotion analysis device, emotion analysis equipment and readable storage medium |
-
2021
- 2021-08-30 CN CN202111002989.6A patent/CN113704405B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109151218A (en) * | 2018-08-21 | 2019-01-04 | 平安科技（深圳）有限公司 | Call voice quality detecting method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113704405A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560453B (en) | Voice information verification method and device, electronic equipment and medium | |
| CN113722483B (en) | Topic classification method, device, equipment and storage medium | |
| CN112988963B (en) | User intention prediction method, device, equipment and medium based on multi-flow nodes | |
| CN112527994A (en) | Emotion analysis method, emotion analysis device, emotion analysis equipment and readable storage medium | |
| CN114461777B (en) | Intelligent question-answering method, device, equipment and storage medium | |
| CN112417128B (en) | Method and device for recommending dialect, computer equipment and storage medium | |
| CN113626607B (en) | Abnormal work order identification method and device, electronic equipment and readable storage medium | |
| CN111930792A (en) | Data resource labeling method and device, storage medium and electronic equipment | |
| CN111694937A (en) | Interviewing method and device based on artificial intelligence, computer equipment and storage medium | |
| CN113807103B (en) | Recruitment method, device, equipment and storage medium based on artificial intelligence | |
| CN114387061A (en) | Product pushing method and device, electronic equipment and readable storage medium | |
| CN113064994A (en) | Conference quality evaluation method, device, equipment and storage medium | |
| CN112951233A (en) | Voice question and answer method and device, electronic equipment and readable storage medium | |
| CN113628043B (en) | Complaint validity judging method, device, equipment and medium based on data classification | |
| CN113821602B (en) | Automatic answering method, device, equipment and medium based on image-text chat record | |
| CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN112579781B (en) | Text classification method, device, electronic equipment and medium | |
| CN113808616A (en) | Voice compliance detection method, device, equipment and storage medium | |
| CN114548114B (en) | Text emotion recognition method, device, equipment and storage medium | |
| CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
| CN113704405B (en) | Quality inspection scoring method, device, equipment and storage medium based on recorded content | |
| CN113515591B (en) | Text defect information identification method and device, electronic equipment and storage medium | |
| CN114186028A (en) | Consult complaint work order processing method, device, equipment and storage medium | |
| CN111859985B (en) | AI customer service model test method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |