CN110929011A - Conversation analysis method, device and equipment - Google Patents
Conversation analysis method, device and equipment Download PDFInfo
- Publication number
- CN110929011A CN110929011A CN201911190774.4A CN201911190774A CN110929011A CN 110929011 A CN110929011 A CN 110929011A CN 201911190774 A CN201911190774 A CN 201911190774A CN 110929011 A CN110929011 A CN 110929011A
- Authority
- CN
- China
- Prior art keywords
- dialog
- quality inspection
- corpus
- text
- inspection rule
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 64
- 238000007689 inspection Methods 0.000 claims abstract description 83
- 238000013145 classification model Methods 0.000 claims abstract description 26
- 230000014509 gene expression Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 7
- 238000003908 quality control method Methods 0.000 description 18
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000009223 counseling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- 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
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to a dialogue analysis method, which comprises the following steps: acquiring a dialog text of a dialog; inputting the dialog texts into a classification model respectively, and determining the categories of the dialog texts; determining a quality inspection rule set for evaluating the dialog text according to the category of the dialog text; respectively inputting the dialogue texts into a corpus model to obtain a corpus analysis result; and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set. The invention realizes intelligent analysis of dialogue data generated in all service processes, reduces the labor cost of quality inspection personnel and improves the service quality. The invention also relates to a dialogue analysis device and equipment.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a dialogue analysis method, a dialogue analysis device and dialogue analysis equipment.
Background
The intelligent dialogue analysis system is mainly applied to a customer service quality management department and used for evaluating service level, finding business opportunities, avoiding customer upgrade complaint risks and the like.
At present mainstream dialogue analytic system, quality control system need drop into special quality control personnel promptly and listen to, discern unusual conversation, for example mood is unusual, illegal conversation, relate to sensitive keyword problem etc. and quality control work consumes a large amount of man-hours, the human cost is high, and faces huge voice record, can't do the quality control examination of full quantity, can only pass through the sampling mode, has most problem recording to miss the risk of examining, also misses partial commodity opportunity easily.
Disclosure of Invention
The invention aims to solve the technical problem of the prior art and provides a conversation analysis method, a conversation analysis device and a conversation analysis equipment.
The technical scheme for solving the technical problems is as follows: a conversation analysis method comprising:
acquiring a dialog text of a dialog;
inputting the dialog texts into a classification model respectively, and determining the categories of the dialog texts;
determining a quality inspection rule set for evaluating the dialog text according to the category of the dialog text;
respectively inputting the dialogue texts into a corpus model to obtain a corpus analysis result;
and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
The invention has the beneficial effects that: the quality grade of the dialog text is determined according to the results output by the classification model and the corpus model and the quality inspection rule set, so that intelligent analysis of dialog data generated in all service processes is realized, the labor cost of quality inspection personnel is reduced, and the service quality is improved.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the quality inspection rule set comprises at least one quality inspection rule, and each quality inspection rule has a corresponding score value;
the quality inspection rule is a logic expression composed of a plurality of semantic operators and logic operators, wherein the semantic operators comprise key intents, keywords, character information, word information and word collocation information.
The beneficial effect of adopting the further scheme is that: the quality inspection rule is a logic expression composed of semantic operators and logic operators, so that the quality inspection rule can be clearly expressed, and the quality of the dialog text can be accurately evaluated.
Further, the determining the quality grade of the dialog text according to the corpus parsing result and the quality inspection rule set specifically includes:
converting all logic expressions in the quality inspection rule set into a rule tree, wherein the rule tree is of a binary tree structure;
traversing a rule tree corresponding to the quality inspection rule set according to the corpus analysis result to detect whether a quality inspection rule matched with the corpus analysis result exists in the quality inspection rule set;
if the matched quality inspection rule exists, adding the score of the dialog text to the score corresponding to the quality inspection rule;
and counting the score value of the dialog text to obtain the quality grade of the dialog text.
The beneficial effect of adopting the further scheme is that: and matching the corpus analysis result with the quality inspection rule set to determine the quality grade of the dialog text, so that the efficiency of evaluating the quality grade of the dialog text is improved.
And further, recording unmatched quality inspection rules, generating a reminding file and sending the reminding file to quality inspection personnel.
The beneficial effect of adopting the further scheme is that: and recording unmatched quality inspection rules, generating a reminding file and sending the reminding file to quality inspectors, and reminding workers of paying attention to places which do not meet quality inspection requirements in the service process so as to improve the service quality.
Further, the corpus parsing result includes corpus information, location information of the corpus information, a role type corresponding to the corpus information, and a key intention and a key word of the role type, where the corpus information includes text information, word information, and word collocation information.
Further, the acquiring a dialog text of a dialog specifically includes:
intercepting real-time telephone voice data or recorded telephone voice data, and converting the real-time telephone voice data or the recorded telephone voice data into a dialogue text through an ASR engine.
The beneficial effect of adopting the further scheme is that: and converting the telephone voice data into a dialogue text according to the intercepted real-time telephone voice and the intercepted recorded telephone voice, thereby realizing the quality grade evaluation of the real-time telephone voice and the recorded telephone voice.
And further, inputting the sample text into a TextCNN classification model for training to obtain the classification model.
Further, the method also comprises the step of inputting the sample text into a deep learning Bi-LSTM model to be trained by combining with an Attention mechanism, so as to obtain the corpus model.
Another technical solution of the present invention for solving the above technical problems is as follows:
a conversation analysis apparatus comprising:
the acquisition module is used for acquiring a dialog text of a dialog;
the input module is used for respectively inputting the dialog texts into a classification model, determining the categories of the dialog texts, and determining and evaluating a quality inspection rule set of the dialog texts according to the categories of the dialog texts;
and the evaluation module is used for respectively inputting the dialog text into a corpus model to obtain a corpus analysis result, and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
The invention has the beneficial effects that: the quality grade of the dialog text is determined according to the results output by the classification model and the corpus model and the quality inspection rule set, intelligent analysis of dialog data generated in all service processes is achieved, labor cost of quality inspection personnel is reduced, and meanwhile service quality is improved.
Furthermore, the present invention also provides a computer device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the dialog analysis method according to any one of the above schemes when executing the computer program.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments of the present invention or in the description of the prior art will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a dialogue analysis method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of a dialog analysis method according to another embodiment of the present invention;
fig. 3 is a schematic block diagram of a dialog analysis device according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
As shown in fig. 1, which is a schematic flowchart of a dialog analysis method provided in an embodiment of the present invention, a dialog analysis method includes the following steps:
110. dialog text for a dialog is obtained.
The dialog in this embodiment includes: textual content and/or voice content. The conversation can be conversation content in communication software of the mobile terminal, and content of mutual messages between the opposite side and the user, which the user needs to reply, can be obtained.
The dialog in the embodiment of the application can be voice information or text information, and if the dialog is voice information, the text content of the voice information can be obtained after the voice is converted into text.
120. And respectively inputting the dialog texts into the classification models, and determining the categories of the dialog texts.
130. And determining a quality control rule set for evaluating the dialog text according to the category of the dialog text.
140. And respectively inputting the dialogue texts into a corpus model to obtain a corpus analysis result.
The classification model and the corpus model are formed by training by using a machine learning means based on a sample dialogue text as a training sample. The sample text conversation can be a large amount of conversation contents acquired from a network, the conversation contents are screened, and a large amount of network conversation contents are trained to obtain a classification model and a corpus model. The sample text conversation record can also be a text conversation record generated by communication software used by a client user, and a classification model and a corpus model are obtained through training.
The output of the classification model may be a consultation, a recommendation, an after-sale, a complaint or a purchase, etc.
150. And determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
It is worth noting that during real-time chat, voice recordings within a period of time before, for example, 30 seconds before, may be acquired for analysis as desired.
Based on the dialogue analysis method provided by this embodiment, the quality level of the dialogue text is determined according to the result and the quality inspection rule set output by the classification model and the corpus model by respectively inputting the acquired dialogue text into the classification model and the corpus model, so that intelligent analysis of dialogue data generated in all service processes is realized, the labor cost of quality inspection personnel is reduced, and the service quality is improved.
As shown in fig. 2, which is a schematic flowchart of a dialog analysis method according to another embodiment of the present invention, wherein step 150 specifically includes:
151. and converting all logic expressions in the quality inspection rule set into a rule tree, wherein the rule tree is of a binary tree structure.
Specifically, the quality control rule set comprises at least one quality control rule, and each quality control rule has a corresponding score value.
The quality inspection rule is a logic expression composed of a plurality of semantic operators and logic operators, wherein the semantic operators comprise key intents, keywords, character information, word information and word collocation information.
152. And traversing the rule tree corresponding to the quality inspection rule set according to the corpus analysis result to detect whether a quality inspection rule matched with the corpus analysis result exists in the quality inspection rule set.
And determining a quality control rule set for evaluating the dialog text according to different categories, for example, when the category is consultation, consulting the corresponding quality control rule set.
153. And if the matched quality inspection rule exists, adding the score corresponding to the quality inspection rule to the score of the dialog text.
154. And counting the score value of the dialog text to obtain the quality grade of the dialog text.
155. And recording unmatched quality inspection rules, generating a reminding file and sending the reminding file to quality inspection personnel.
The result output by the corpus model comprises corpus information, position information of the corpus information and/or role types corresponding to the corpus information, wherein the corpus information comprises character information, word information and word collocation information. The corpus information can be word content, the word information can identify whether keywords exist, the word collocation information can be the use conditions of the action phrases, the adjectives And the adverbs, for example, the quality inspection rule 1 in the dialog text which is not matched with the quality inspection rule set is recorded, the quality inspection rule 1 is good And old (mr. Or women), the unmatched quality inspection rule 1 is recorded, the unmatched quality inspection rule is generated into a file And sent to quality inspectors, the unmatched quality inspection rule can be checked by the quality inspectors And client personnel, And the unmatched quality inspection rule item is obtained.
For example, text information is converted into binary, each non-leaf node of the binary tree is a constant identifier corresponding to an operator, each left-leaf node of the tree stores constant identifiers of corpus information, and each right-leaf node of the tree stores constants. This document is not to be repeated in an exhaustive manner.
And determining the key intention and the key words of each role type in the dialogue text according to the character information, the word information and the word collocation information in the corpus information, for example, if the corresponding word information in the client role is a package purchase, the key intention of the client is a purchase, and the key words are packages.
Each quality control rule has a corresponding score, for example, the score of quality control rule 1 in the quality control rule set of the consultation category is 5 points, and the score of quality control rule 2 is 10 points.
The quality control rule is a logic expression formed by a plurality of semantic operators and logic operators. For example, quality control rule 1 in the quality control rule set of the counseling volume category: and if the corpus information comprises hello And lady, the quality control rule 1 is successfully matched, And then the score value of the dialog text is added with 5 points.
And counting whether each quality inspection rule in the quality inspection rule set is successfully matched, if so, adding the score value corresponding to the quality inspection rule to the score value of the dialog text, and finally obtaining the score value of the dialog text. If the score of the dialog text is 30 points, the quality level of the dialog text is excellent.
Based on the embodiment, the quality inspection rule set for evaluating the dialog text is determined according to the category of the dialog text determined by the classification model, the result output by the corpus model is matched with the quality inspection rule set, the quality grade of the dialog text is determined according to the matching result, the quality inspection rule set is determined based on different dialog categories, and the accuracy of evaluating the quality grade of the dialog text is improved.
Further, real-time telephony voice data or recorded telephony voice is intercepted and converted to dialog text by the ASR engine.
Specifically, intercepting the real-time telephone voice can be performed in a mode of mapping through a switch port without occupying the bandwidth of a server, and voice stream data intercepted in real time is converted into a text through an asr (automatic Speech recognition) voice recognition engine, wherein the frequency of intercepting the real-time telephone voice can be set according to needs.
And further, inputting the sample text into a TextCNN classification model for training to obtain the classification model.
Further, the sample text is input into a deep learning Bi-LSTM model and is trained by combining with an Attention mechanism to obtain a corpus model.
Fig. 3 is a schematic block configuration diagram of a dialog analysis apparatus according to another embodiment of the present invention, and the dialog analysis apparatus includes:
the acquisition module is used for acquiring a dialog text of a dialog;
the input module is used for respectively inputting the dialog texts into the classification model, determining the categories of the dialog texts, and determining a quality inspection rule set for evaluating the dialog texts according to the categories of the dialog texts;
and the evaluation module is used for respectively inputting the dialog text into the corpus model to obtain a corpus analysis result, and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
According to the dialogue analysis device provided by the embodiment, the acquired dialogue texts are respectively input into the classification model and the corpus model, and the quality grade of the dialogue texts is determined according to the output results of the classification model and the corpus model and the quality inspection rule set, so that intelligent analysis on the dialogue data generated in all service processes is realized, the labor cost of quality inspection personnel is reduced, and the service quality is improved.
Based on the above embodiment, further, the evaluation module is further configured to convert all the logical expressions in the quality inspection rule set into a rule tree, where the rule tree is a binary tree structure;
traversing a rule tree corresponding to the quality inspection rule set according to the corpus analysis result to detect whether a quality inspection rule matched with the corpus analysis result exists in the quality inspection rule set;
if the matched quality inspection rule exists, adding the score of the dialog text to the score corresponding to the quality inspection rule;
and counting the score value of the dialog text to obtain the quality grade of the dialog text.
Further, the evaluation module is also used for recording the unmatched quality inspection rules and generating a reminding file to send to quality inspection personnel if the unmatched quality inspection rules exist.
Furthermore, the acquisition module is also used for intercepting the real-time telephone voice data or the recorded telephone voice data and converting the real-time telephone voice data or the recorded telephone voice data into a dialogue text through the ASR engine.
Further, the input module is further configured to input the sample text into the TextCNN classification model for training to obtain the classification model.
Further, the input module is used for inputting the sample text into the deep learning Bi-LSTM model to be trained by combining with an Attention mechanism to obtain a corpus model.
Furthermore, the present invention also provides a computer device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the dialog analysis method according to any one of the above schemes when executing the computer program.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A conversation analysis method, comprising:
acquiring a dialog text of a dialog;
inputting the dialog texts into a classification model respectively, and determining the categories of the dialog texts;
determining a quality inspection rule set for evaluating the dialog text according to the category of the dialog text;
respectively inputting the dialogue texts into a corpus model to obtain a corpus analysis result;
and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
2. The dialogue analysis method according to claim 1,
the quality inspection rule set comprises at least one quality inspection rule, and each quality inspection rule has a corresponding score value;
the quality inspection rule is a logic expression composed of a plurality of semantic operators and logic operators, wherein the semantic operators comprise key intents, keywords, character information, word information and word collocation information.
3. The dialog analysis method according to claim 2, wherein the determining the quality level of the dialog text according to the corpus parsing result and the quality inspection rule set specifically comprises:
converting all logic expressions in the quality inspection rule set into a rule tree, wherein the rule tree is of a binary tree structure;
traversing a rule tree corresponding to the quality inspection rule set according to the corpus analysis result to detect whether a quality inspection rule matched with the corpus analysis result exists in the quality inspection rule set;
if the matched quality inspection rule exists, adding the score of the dialog text to the score corresponding to the quality inspection rule;
and counting the score value of the dialog text to obtain the quality grade of the dialog text.
4. The dialogue analysis method according to claim 3, further comprising recording the quality inspection rules that do not match and generating a prompt file to send to a quality inspector.
5. The dialogue analysis method according to claim 1,
the corpus parsing result comprises corpus information, position information of the corpus information, role types corresponding to the corpus information, and key intentions and keywords of the role types, wherein the corpus information comprises character information, word information and word collocation information.
6. The dialog analysis method according to claim 1, wherein the obtaining of the dialog text of the dialog specifically comprises:
intercepting real-time telephone voice data or recorded telephone voice data, and converting the real-time telephone voice data or the recorded telephone voice data into a dialogue text through an ASR engine.
7. The dialog analysis method according to any of claims 1-6, further comprising entering sample text into a TextCNN classification model for training, resulting in the classification model.
8. The dialog analysis method according to any one of claims 1-6, further comprising training a sample text input deep learning Bi-LSTM model in combination with an Attention mechanism to obtain the corpus model.
9. A dialogue analysis apparatus, comprising:
the acquisition module is used for acquiring a dialog text of a dialog;
the input module is used for respectively inputting the dialog texts into a classification model, determining the categories of the dialog texts, and determining and evaluating a quality inspection rule set of the dialog texts according to the categories of the dialog texts;
and the evaluation module is used for respectively inputting the dialog text into a corpus model to obtain a corpus analysis result, and determining the quality grade of the dialog text according to the corpus analysis result and the quality inspection rule set.
10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the dialog analysis method according to any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911190774.4A CN110929011A (en) | 2019-11-28 | 2019-11-28 | Conversation analysis method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911190774.4A CN110929011A (en) | 2019-11-28 | 2019-11-28 | Conversation analysis method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929011A true CN110929011A (en) | 2020-03-27 |
Family
ID=69847474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911190774.4A Pending CN110929011A (en) | 2019-11-28 | 2019-11-28 | Conversation analysis method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929011A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627461A (en) * | 2020-05-29 | 2020-09-04 | 平安医疗健康管理股份有限公司 | Voice quality inspection method and device, server and storage medium |
| CN111984779A (en) * | 2020-09-10 | 2020-11-24 | 支付宝(杭州)信息技术有限公司 | Dialog text analysis method, device, equipment and readable medium |
| CN112201225A (en) * | 2020-09-30 | 2021-01-08 | 北京大米科技有限公司 | Corpus obtaining method and device, readable storage medium and electronic equipment |
| CN112463962A (en) * | 2020-11-18 | 2021-03-09 | 深圳木成林科技有限公司 | Chat record quality inspection method and device |
| CN113065328A (en) * | 2021-04-06 | 2021-07-02 | 浙江百应科技有限公司 | Conversation content analysis method based on regular and text truncation |
| CN113553861A (en) * | 2021-07-30 | 2021-10-26 | 出门问问信息科技有限公司 | Information processing method and device based on dialog system and storage medium |
| CN113657773A (en) * | 2021-08-19 | 2021-11-16 | 中国平安人寿保险股份有限公司 | Method and device for testing speech technology, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446388A (en) * | 2018-03-22 | 2018-08-24 | 平安科技（深圳）有限公司 | Text data quality detecting method, device, equipment and computer readable storage medium |
| CN108962282A (en) * | 2018-06-19 | 2018-12-07 | 京北方信息技术股份有限公司 | Speech detection analysis method, apparatus, 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 |
| CN109448730A (en) * | 2018-11-27 | 2019-03-08 | 广州广电运通金融电子股份有限公司 | A kind of automatic speech quality detecting method, system, device and storage medium |
| CN109902957A (en) * | 2019-02-28 | 2019-06-18 | 腾讯科技（深圳）有限公司 | A kind of data processing method and device |
| CN110083689A (en) * | 2019-03-20 | 2019-08-02 | 上海拍拍贷金融信息服务有限公司 | Customer service quality determining method and device, readable storage medium storing program for executing |
| CN110309216A (en) * | 2019-05-10 | 2019-10-08 | 焦点科技股份有限公司 | A kind of customer service voices quality detecting method based on text classification |
-
2019
- 2019-11-28 CN CN201911190774.4A patent/CN110929011A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446388A (en) * | 2018-03-22 | 2018-08-24 | 平安科技（深圳）有限公司 | Text data quality detecting method, device, equipment and computer readable storage medium |
| CN108962282A (en) * | 2018-06-19 | 2018-12-07 | 京北方信息技术股份有限公司 | Speech detection analysis method, apparatus, 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 |
| CN109448730A (en) * | 2018-11-27 | 2019-03-08 | 广州广电运通金融电子股份有限公司 | A kind of automatic speech quality detecting method, system, device and storage medium |
| CN109902957A (en) * | 2019-02-28 | 2019-06-18 | 腾讯科技（深圳）有限公司 | A kind of data processing method and device |
| CN110083689A (en) * | 2019-03-20 | 2019-08-02 | 上海拍拍贷金融信息服务有限公司 | Customer service quality determining method and device, readable storage medium storing program for executing |
| CN110309216A (en) * | 2019-05-10 | 2019-10-08 | 焦点科技股份有限公司 | A kind of customer service voices quality detecting method based on text classification |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627461A (en) * | 2020-05-29 | 2020-09-04 | 平安医疗健康管理股份有限公司 | Voice quality inspection method and device, server and storage medium |
| CN111984779A (en) * | 2020-09-10 | 2020-11-24 | 支付宝(杭州)信息技术有限公司 | Dialog text analysis method, device, equipment and readable medium |
| CN111984779B (en) * | 2020-09-10 | 2024-05-28 | 支付宝(杭州)信息技术有限公司 | Dialogue text analysis method, device, equipment and readable medium |
| CN112201225A (en) * | 2020-09-30 | 2021-01-08 | 北京大米科技有限公司 | Corpus obtaining method and device, readable storage medium and electronic equipment |
| CN112201225B (en) * | 2020-09-30 | 2024-02-02 | 北京大米科技有限公司 | Corpus acquisition method and device, readable storage medium and electronic equipment |
| CN112463962A (en) * | 2020-11-18 | 2021-03-09 | 深圳木成林科技有限公司 | Chat record quality inspection method and device |
| CN113065328A (en) * | 2021-04-06 | 2021-07-02 | 浙江百应科技有限公司 | Conversation content analysis method based on regular and text truncation |
| CN113553861A (en) * | 2021-07-30 | 2021-10-26 | 出门问问信息科技有限公司 | Information processing method and device based on dialog system and storage medium |
| CN113553861B (en) * | 2021-07-30 | 2023-11-14 | 出门问问信息科技有限公司 | Information processing method, device and storage medium based on dialogue system |
| CN113657773A (en) * | 2021-08-19 | 2021-11-16 | 中国平安人寿保险股份有限公司 | Method and device for testing speech technology, electronic equipment and storage medium |
| CN113657773B (en) * | 2021-08-19 | 2023-08-29 | 中国平安人寿保险股份有限公司 | Method and device for voice operation quality inspection, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929011A (en) | Conversation analysis method, device and equipment | |
| CN110197672B (en) | Voice call quality detection method, server and storage medium | |
| JP6998680B2 (en) | Interactive business support system and interactive business support program | |
| CN111182162B (en) | Telephone quality inspection method, device, equipment and storage medium based on artificial intelligence | |
| CN111210842B (en) | Voice quality inspection method, device, terminal and computer readable storage medium | |
| US9710829B1 (en) | Methods, systems, and articles of manufacture for analyzing social media with trained intelligent systems to enhance direct marketing opportunities | |
| CN111640436B (en) | Method for providing dynamic customer portraits of conversation objects to agents | |
| CN104301554A (en) | Device and method used for detecting service quality of customer service staff | |
| CN111598485A (en) | Multi-dimensional intelligent quality inspection method, device, terminal equipment and medium | |
| CN109345282A (en) | A kind of response method and equipment of business consultation | |
| CN111641757A (en) | Real-time quality inspection and auxiliary speech pushing method for seat call | |
| CN110839112A (en) | Problem voice detection method and device | |
| CN111314566A (en) | Voice quality inspection method, device and system | |
| US11687946B2 (en) | Systems and methods for detecting complaint interactions | |
| WO2023272850A1 (en) | Decision tree-based product matching method, apparatus and device, and storage medium | |
| US11495227B2 (en) | Artificial intelligence (AI) based user query intent analyzer | |
| CN109582954A (en) | Method and apparatus for output information | |
| CN112860868A (en) | Customer service telephone analysis method, system, equipment and storage medium | |
| CN111831875A (en) | Data processing method, device, equipment and storage medium | |
| CN113407677A (en) | Method, apparatus, device and storage medium for evaluating quality of consultation session | |
| CN114186040A (en) | Operation method of intelligent robot customer service | |
| CN112200465A (en) | Electric power AI method and system based on multimedia information intelligent analysis | |
| CN114049895B (en) | ASR-based voice quality inspection analysis method and system | |
| KR20230140722A (en) | Method and apparatus for artificial intelligence psychological counseling based on chat bot | |
| Bianchi et al. | A machine learning based help desk approach for units involved in official surveys |
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: 20200327 |