CN117149979A - Method and device for constructing intelligent question-answering and review module before loan - Google Patents
Method and device for constructing intelligent question-answering and review module before loan Download PDFInfo
- Publication number
- CN117149979A CN117149979A CN202311192351.2A CN202311192351A CN117149979A CN 117149979 A CN117149979 A CN 117149979A CN 202311192351 A CN202311192351 A CN 202311192351A CN 117149979 A CN117149979 A CN 117149979A
- Authority
- CN
- China
- Prior art keywords
- question
- loan
- answer
- answering
- score
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012552 review Methods 0.000 title claims abstract description 24
- 230000008451 emotion Effects 0.000 claims abstract description 47
- 238000012502 risk assessment Methods 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 230000014509 gene expression Effects 0.000 claims description 12
- 239000002131 composite material Substances 0.000 claims description 6
- 230000002996 emotional effect Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 208000019901 Anxiety disease Diseases 0.000 claims description 3
- 230000036506 anxiety Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 230000003111 delayed effect Effects 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010071299 Slow speech Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012216 screening Methods 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
- G06F16/332—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
- G06F16/33—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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/338—Presentation of query results
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of risk assessment before loan, in particular to a method and a device for constructing an intelligent question-answering and review module before loan, which comprises the following steps: s1, building an intelligent question-answer knowledge base; s2, performing intelligent question answering through man-machine interaction; s3, analyzing a question-answer text; s4, analyzing question and answer sounds; s5, analyzing a question and answer picture; and S6, weighting and calculating the sound emotion score and the picture emotion score by taking the single problem as a unit to obtain emotion score indexes of the problems. Compared with the prior art, the invention can improve the perceptibility and the risk prediction capability of the pre-loan model.
Description
Technical Field
The invention relates to the field of risk assessment before loan, and particularly provides a method and a device for constructing an intelligent question-answering and review module before loan.
Background
The traditional on-line pre-loan auditing is mostly based on an analysis model of business data, and the risk assessment value is obtained through comprehensively analyzing the basic condition, finance, credit and other business data of a loan object.
Further information of which dimensions can be added to enhance the robustness of the pre-loan risk assessment model is a matter of urgent need for those skilled in the art.
Disclosure of Invention
The invention provides a method for constructing a pre-loan intelligent question-answering and review module with high practicability aiming at the defects of the prior art.
The invention further aims to provide a construction device of the intelligent pre-loan question-answering and review module, which is reasonable in design, safe and applicable.
The technical scheme adopted for solving the technical problems is as follows:
a method for constructing a pre-loan intelligent question-answering and review module comprises the following steps:
s1, building an intelligent question-answer knowledge base;
s2, performing intelligent question answering through man-machine interaction;
s3, analyzing a question-answer text;
s4, analyzing question and answer sounds;
s5, analyzing a question and answer picture;
and S6, weighting and calculating the sound emotion score and the picture emotion score by taking the single problem as a unit to obtain emotion score indexes of the problems.
Further, in step S1, the intelligent question-answering knowledge base is a source of the man-machine interaction problem in step S2, the knowledge base includes a general problem for measuring the performance, the property condition and the repayment capability of the loan object, the problem is designed as an open problem, and the expression time of the loan object is increased;
after intelligent question answering is triggered in the loan flow, the problems conforming to the current business scene are screened out according to the business information of the current loan which is transmitted into the flow upstream, and meanwhile, the question bank is intelligently upgraded according to the characteristic information of the current loan, so that the problems conforming to the current object and the current scene are increased.
Further, in step S2, a speech synthesis, speech recognition and image acquisition module capable of supporting intelligent questions and answers is included, and according to the custom questions of the present loan, measurements including the loan object line, property condition and repayment capability are included, the loan object is queried one by one, and simultaneously, the questions and answers are acquired in an audio-visual manner, so as to be used as analysis materials of step S3, step S4 and step S5.
Further, in step S3, semantic analysis and emotion analysis are performed on the answer content of the loan object, where the semantic analysis is based on the completion degree and accuracy analysis of the question answer, and the completion degree is whether the answer content completely covers the question, and whether there is a phenomenon of missing and one-sided answer;
the correct answer is the absolute requirement of the question or the answer intelligently analyzed according to the current scene, the answer content of each question of the loan object is analyzed as a basis, the score is calculated, and the answer score index of each question is obtained;
and the emotion analysis is to analyze emotion polarity and degree of answer content of each question, and quantitatively count positive and negative emotion and degree based on a dictionary to obtain emotion score indexes of each question.
Further, in step S4, analysis of the pitch, loudness, speed of the sound is included, and the analysis of the sound is performed to correctly perceive the emotional state of the loan object when answering the question;
in the process of identifying the answer questions, the loan object is too small or too high in volume, the tones are too high or the tones are light, the olefinic and the viscosity is high, the speech speed is too slow or the score plate repeats the characteristics of negative emotions which are usually lie, are delayed, hidden and are not self-credible to the questions respondent, and the answer of a single question is taken as a statistical interval to count the negative directivity characteristics appearing in the voice, so that the voice emotion score index is obtained.
Further, in step S5, analyzing the picture of the loan object in the question and answer process, and performing expression and micro-expression recognition to sense the emotional state of the loan object when answering the question;
when the loan object answers the questions, anxiety, fear, nose rubbing, eyes watching right, mouth folding, neck feeling and shoulder shrugging appear for a plurality of times, and the negative directional expression and the micro expression with lie, tardy, disguise and distrust are represented, the answer of a single question is taken as a statistical interval, and the characteristics with negative directivity appearing in the picture are counted to obtain the picture emotion score index.
Further, in step S6, the answer score, emotion score and emotion score of each question are weighted to obtain a composite score of a single question, and three dimension composite scores are respectively counted according to the question types, so as to obtain risk assessment results of the integrity, property status and repayment capability of the loan object, and further, the composite score of the intelligent question and answer is obtained through weighted calculation.
A construction device of a pre-loan intelligent question-answering and review module comprises: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to execute a method for constructing a pre-lending intelligent question-answering and review module.
Compared with the prior art, the method and the device for constructing the intelligent question-answering and review module before lending have the following outstanding beneficial effects:
according to the pre-loan risk assessment model, by adding the pre-loan intelligent question-answering and review module, intelligent question-answering is performed on the line, property condition and repayment capability of a loan object, semantic analysis, emotion analysis and emotion analysis are performed on the answer content, and factors such as the integrity, property condition and repayment capability of the loan object are assessed at multiple angles, so that the perception capability and the prediction risk capability of the pre-loan model are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow diagram of a method for constructing a pre-loan intelligent question-answering and review module;
FIG. 2 is a schematic diagram of an intelligent review flow in the method for constructing the pre-loan intelligent question-answering and review module.
Detailed Description
In order to provide a better understanding of the aspects of the present invention, the present invention will be described in further detail with reference to specific embodiments. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A preferred embodiment is given below:
as shown in fig. 1 and 2, the method for constructing the intelligent question-answering and review module before lending in this embodiment includes the following steps:
s1, building an intelligent question-answer knowledge base;
the intelligent question-answering knowledge base is a problem source of man-machine interaction in the step 2. The elements such as the line, the year, the interest rate and the like of the loan are calculated by the traditional pre-loan model according to the business data of the loan object, the knowledge base focuses on the measurement of the property line, the property condition and the repayment capability of the loan object, and the loan elements are optimized according to the measured values.
The knowledge base contains the general problems of measuring the loan object, property conditions and repayment capability, the problems are designed to be open problems, and the expression time of the loan object is prolonged.
After triggering intelligent question answering in the loan flow, screening out the questions conforming to the current business scene according to the business information of the current loan which is transmitted into the flow upstream, and simultaneously intelligently upgrading the question bank according to the characteristic information (such as information of a loan object, loan amount, loan application and the like) of the current loan, so that the questions conforming to the current object and the current scene are increased, and the query of the loan object is more conforming to the characteristics of the user.
S2, performing intelligent question answering through man-machine interaction;
the process comprises a voice synthesis module, a voice recognition module, an image acquisition module and the like which can support intelligent questions and answers. The system inquires the loan objects one by one according to the custom questions of the current loan, including the measurements of the loan object rows, the property conditions and the repayment capacity, and simultaneously collects audio and video of the inquiry and answer process as analysis materials of the steps S3, S4 and S5.
S3, analyzing a question-answer text;
this process involves semantic analysis and emotion analysis of the answer content of the loan object. The semantic analysis is based on the completion degree and correctness analysis of the answer of the question, wherein the completion degree is whether the answer content completely covers the question, and whether the phenomena of omission and one-sided answer exist; the correct answer is the absolute requirement of the question or the answer intelligently analyzed according to the current scene, the answer content of each question of the loan object is analyzed based on the absolute requirement or the answer, the score is calculated, and the answer score index of each question is obtained.
The emotion analysis is to analyze emotion polarity and degree of answer content of each question, and quantitatively count positive and negative emotion and degree based on a dictionary to obtain emotion score indexes of each question.
S4, analyzing question and answer sounds;
this process involves analysis of the pitch, loudness, speed of sound, and sound related analysis to have a correct perception of the emotional state of the lender when answering the question.
In the process of identifying and answering the questions, the loan object has the characteristics of undershot or overhigh volume, excessively high tone, lighter tone, higher olefinic precision, higher viscosity, excessively slow speech speed, repeated score, and the like, which usually points to negative emotions of questions respondents, such as lie, tardy, mask, non-confidence, and the like, and the negative directivity characteristics appearing in the voice are counted by taking the answers of single questions as a counting interval to obtain the voice emotion score index.
S5, analyzing a question and answer picture;
and analyzing pictures in the question and answer process of the loan object, and carrying out expression and micro-expression recognition, wherein the process is also used for sensing the emotional state of the loan object when answering the questions.
When the loan object answers questions, anxiety, fear, nose rubbing, eyes watching right, mouth folding, neck feeling, shoulder shrugging and other negative directional expressions with lie, tardy, disguise, non-confidence and other micro expressions appear for a plurality of times, the answers of the single questions are used as statistical intervals, and the characteristics with negative directivity appearing in the picture are counted to obtain picture emotion score indexes.
And S6, weighting and calculating the sound emotion score and the picture emotion score by taking the single problem as a unit to obtain emotion score indexes of the problems.
And weighting and calculating answer scores, emotion scores and emotion scores of all the questions to obtain comprehensive scores of single questions, respectively counting three-dimensional comprehensive scores according to the categories of the questions (object rows, property conditions and repayment capacity), so as to obtain risk assessment results of the integrity, property conditions and repayment capacity of the loan objects, and further obtaining comprehensive scores of the intelligent questions and answers through weighting calculation.
Emotion analysis index weight:
single question scoring index weight:
| index name | Index weight |
| Answer score | 30％ |
| Emotion score | 30％ |
| Emotion score | 40％ |
Based on the above method, the device for constructing the intelligent question-answering and review module before lending in this embodiment includes: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to execute a method for constructing a pre-lending intelligent question-answering and review module.
The above-mentioned specific embodiments are merely specific examples of the present invention, and the scope of the present invention is not limited to the specific embodiments, and any suitable changes or substitutions made by those skilled in the art, which conform to the technical solutions described in the claims of the present invention, should fall within the scope of the present invention.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The method for constructing the intelligent question-answering and review module before the loan is characterized by comprising the following steps of:
s1, building an intelligent question-answer knowledge base;
s2, performing intelligent question answering through man-machine interaction;
s3, analyzing a question-answer text;
s4, analyzing question and answer sounds;
s5, analyzing a question and answer picture;
and S6, weighting and calculating the sound emotion score and the picture emotion score by taking the single problem as a unit to obtain emotion score indexes of the problems.
2. The method for constructing a pre-loan intelligent question-answer and review module according to claim 1, wherein in step S1, an intelligent question-answer knowledge base is a source of questions of man-machine interaction in step S2, the knowledge base includes general questions for measuring loan object lines, property conditions and repayment capability, the questions are designed as open questions, and the expression time of the loan object is increased;
after intelligent question answering is triggered in the loan flow, the problems conforming to the current business scene are screened out according to the business information of the current loan which is transmitted into the flow upstream, and meanwhile, the question bank is intelligently upgraded according to the characteristic information of the current loan, so that the problems conforming to the current object and the current scene are increased.
3. The method for constructing a pre-loan intelligent question-answering and review module according to claim 2, wherein in step S2, a speech synthesis, speech recognition and image acquisition module capable of supporting intelligent question-answering is included, and according to the custom questions of the current loan, measurements including three aspects of loan object line, property condition and repayment capability are included, question-by-question inquiry is performed on the loan object, and simultaneously, an audio-visual acquisition is performed on the question-answering process as analysis materials of step S3, step S4 and step S5.
4. The method for constructing a pre-loan intelligent question-answering and review module according to claim 3, wherein in step S3, semantic analysis and emotion analysis are performed on answer contents of loan objects, and the semantic analysis is based on the completion degree and correctness analysis of question answers, wherein the completion degree is whether the answer contents completely cover the questions, and whether missing and one-sided answer phenomena exist;
the correct answer is the absolute requirement of the question or the answer intelligently analyzed according to the current scene, the answer content of each question of the loan object is analyzed as a basis, the score is calculated, and the answer score index of each question is obtained;
and the emotion analysis is to analyze emotion polarity and degree of answer content of each question, and quantitatively count positive and negative emotion and degree based on a dictionary to obtain emotion score indexes of each question.
5. The method according to claim 4, wherein in step S4, the pitch, loudness and speed of the sound are analyzed, and the analysis of the sound is performed to correctly perceive the emotional state of the loan object when answering the question;
in the process of identifying the answer questions, the loan object is too small or too high in volume, the tones are too high or the tones are light, the olefinic and the viscosity is high, the speech speed is too slow or the score plate repeats the characteristics of negative emotions which are usually lie, are delayed, hidden and are not self-credible to the questions respondent, and the answer of a single question is taken as a statistical interval to count the negative directivity characteristics appearing in the voice, so that the voice emotion score index is obtained.
6. The method for constructing a pre-loan intelligent question-answering and review module according to claim 5, wherein in step S5, the frames of the loan object in the question-answering process are analyzed to perform expression and microexpressive recognition, which is to sense the emotional state of the loan object when answering the question;
when the loan object answers the questions, anxiety, fear, nose rubbing, eyes watching right, mouth folding, neck feeling and shoulder shrugging appear for a plurality of times, and the negative directional expression and the micro expression with lie, tardy, disguise and distrust are represented, the answer of a single question is taken as a statistical interval, and the characteristics with negative directivity appearing in the picture are counted to obtain the picture emotion score index.
7. The method for constructing a pre-loan intelligent question-answering and review module according to claim 6, wherein in step S6, the answer score, emotion score and emotion score of each question are weighted to obtain a composite score of a single question, and three dimension composite scores are respectively counted according to the question category, so as to obtain risk assessment results of the integrity, property status and repayment capability of the loan object, and further the composite score of the current intelligent question-answering is obtained through weighted calculation.
8. The device for constructing the intelligent question-answering and review module before the loan is characterized by comprising the following components: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor being configured to invoke the machine readable program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311192351.2A CN117149979A (en) | 2023-09-15 | 2023-09-15 | Method and device for constructing intelligent question-answering and review module before loan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311192351.2A CN117149979A (en) | 2023-09-15 | 2023-09-15 | Method and device for constructing intelligent question-answering and review module before loan |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117149979A true CN117149979A (en) | 2023-12-01 |
Family
ID=88884098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311192351.2A Pending CN117149979A (en) | 2023-09-15 | 2023-09-15 | Method and device for constructing intelligent question-answering and review module before loan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117149979A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117422547A (en) * | 2023-12-18 | 2024-01-19 | 湖南三湘银行股份有限公司 | Auditing device and method based on intelligent dialogue system and micro expression recognition |
-
2023
- 2023-09-15 CN CN202311192351.2A patent/CN117149979A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117422547A (en) * | 2023-12-18 | 2024-01-19 | 湖南三湘银行股份有限公司 | Auditing device and method based on intelligent dialogue system and micro expression recognition |
| CN117422547B (en) * | 2023-12-18 | 2024-04-02 | 湖南三湘银行股份有限公司 | Auditing device and method based on intelligent dialogue system and micro expression recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108281052B (en) | A kind of on-line teaching system and online teaching method | |
| CN109785698B (en) | Method, device, electronic equipment and medium for oral language level evaluation | |
| CN110942229A (en) | Service quality evaluation method and device, electronic equipment and storage medium | |
| Räsänen et al. | ALICE: An open-source tool for automatic measurement of phoneme, syllable, and word counts from child-centered daylong recordings | |
| US8708702B2 (en) | Systems and methods for learning using contextual feedback | |
| Van Nuffelen et al. | Speech technology‐based assessment of phoneme intelligibility in dysarthria | |
| Preston et al. | Developing a weighted measure of speech sound accuracy | |
| CN110443427A (en) | Result prediction method and its system based on cognitive knowledge spectrum | |
| CN103559894A (en) | Method and system for evaluating spoken language | |
| CN113314100B (en) | Method, device, equipment and storage medium for evaluating and displaying results of spoken language test | |
| CN117149979A (en) | Method and device for constructing intelligent question-answering and review module before loan | |
| CN103054586A (en) | Chinese speech automatic audiometric method based on Chinese speech audiometric dynamic word list | |
| US11024329B2 (en) | Word repetition in separate conversations for detecting a sign of cognitive decline | |
| CN115796653A (en) | Interview speech evaluation method and system | |
| Wang | Detecting pronunciation errors in spoken English tests based on multifeature fusion algorithm | |
| CN114897077A (en) | English reading literacy evaluation method based on machine learning | |
| CN110705523B (en) | Entrepreneur performance evaluation method and system based on neural network | |
| CN107578785A (en) | The continuous emotional feature analysis evaluation method of music based on Gamma distributional analysis | |
| CN109389493A (en) | Customized test question mesh input method, system and equipment based on speech recognition | |
| CN114241835A (en) | Student spoken language quality evaluation method and device | |
| Ha | The Predictability of Naturalistic Evaluation of All-Day Recordings for Speech and Language Development | |
| Beaman et al. | Measuring change in lectal coherence across real-and apparent-time | |
| CN111612324B (en) | Multi-dimensional assessment method based on oral English examination | |
| Crosby et al. | Begging for bags: BAG-raising and prescriptive ideologies in Spokane Washington | |
| CN113726962B (en) | Method and device for evaluating service quality, electronic device 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 |