CN112199592B - Bank public opinion style control method and system based on knowledge distillation for model compression - Google Patents

Bank public opinion style control method and system based on knowledge distillation for model compression Download PDF

Info

Publication number
CN112199592B
CN112199592B CN202011079319.XA CN202011079319A CN112199592B CN 112199592 B CN112199592 B CN 112199592B CN 202011079319 A CN202011079319 A CN 202011079319A CN 112199592 B CN112199592 B CN 112199592B
Authority
CN
China
Prior art keywords
model
module
compression
public opinion
model compression
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
Application number
CN202011079319.XA
Other languages
Chinese (zh)
Other versions
CN112199592A (en
Inventor
蒋海啸
林路
刘卫东
陈芃
郏维强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Xinyada Fintech Technology Co ltd
Sinyada Technology Co ltd
Original Assignee
Sinyada Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sinyada Technology Co ltd filed Critical Sinyada Technology Co ltd
Priority to CN202011079319.XA priority Critical patent/CN112199592B/en
Publication of CN112199592A publication Critical patent/CN112199592A/en
Application granted granted Critical
Publication of CN112199592B publication Critical patent/CN112199592B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • 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
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Probability & Statistics with Applications (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 discloses a bank public opinion pneumatic control method and system based on knowledge distillation for model compression, which comprises the following steps: the system comprises a distributed message queue module, a model compression entity identification module and a model compression public opinion classification module; the output end of the distributed message queue module is connected with the input end of the model compression entity identification module, and the output end of the model compression entity identification module is connected with the input end of the model compression public opinion classification module. According to the invention, the advanced pre-training model in the industry is compressed by a knowledge distillation technology, the structure of the neural network model is simplified, the performance and effect of the model can be ensured under the condition of less model parameters, the model prediction accuracy can be improved, the prediction time can be reduced, the model prediction response time is reduced through the deployment of a distributed message queue and a distributed cache, and the high real-time requirement of a bank is met.

Description

Bank public opinion style control method and system based on knowledge distillation for model compression
Technical Field
The invention relates to the technical field of bank public opinion pneumatic control systems, in particular to a bank public opinion pneumatic control method and system for performing model compression based on knowledge distillation.
Background
At present, the bank has higher and higher requirements on the accuracy and the real-time performance of public opinion pneumatic control, and the traditional mode is to purchase the public opinion data of a third-party data provider, but the following pain points exist: the public opinion risk early warning is not accurate enough, and the public opinion risk early warning is not timely enough. The bank labor cost increases: due to the fact that public opinion risk early warning is not accurate enough, large manual auditing cost needs to be consumed, although the accuracy of a pre-training model popular in the industry is high, model parameters are too large, hardware cost is high, model prediction time is long, and engineering landing is difficult.
Disclosure of Invention
The invention aims to provide a bank public opinion pneumatic control method and system for carrying out model compression based on knowledge distillation. The model prediction accuracy can be improved, and the prediction time can be reduced.
In order to achieve the purpose, the invention adopts the following technical scheme: the bank public opinion trend control method for model compression based on knowledge distillation comprises the following steps:
s1: constructing a model compression entity identification module, wherein the model compression entity identification module is a neural network model for carrying out model compression based on knowledge distillation, and the construction process of the model compression entity identification module is a teacher model trained on samples through an original model, and then processing is carried out through a compression model to obtain the final classification probability;
s2: constructing a model compression public opinion classification module, wherein the model compression public opinion classification module is a neural network model for performing model compression based on knowledge distillation, and the construction process of the model compression public opinion classification module is a teacher model trained by an original model based on samples, and then performing knowledge distillation training based on the same samples through the compression model to complete the whole knowledge distillation process;
s3: real-time public sentiment news provided by the bank is transmitted to the model compression entity recognition module and the model compression public sentiment classification module in a distributed message queue mode for analysis and processing, and the wind control early warning of bank monitoring clients is completed.
The step S1 of constructing a model compression entity identification module specifically includes the following steps:
s1.1: training an original model: the network structure of the original model is based on a pretrained model Bert12 layer + Bi-LSTM + CRF; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on a ground-truth, and obtaining a result called hard-target;
s1.2: training a compression model based on knowledge distillation: and selecting a simple Bi-LSTM + CRF model from the network structure of the compression model, acquiring sequence characteristics and outputting label emission probability by the Bi-LSTM, accessing the label emission probability into the CRF to generate transition probability, and outputting and acquiring the final classification probability of the label according to the emission probability + the transition probability.
The step S2 of constructing the model compression public opinion classification module specifically comprises the following steps:
s2.1: the network structure of the original model is based on a pretrained model Bert12 layer + TextCNN; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on ground-truth to obtain a result;
s2.2: training a compression model based on knowledge distillation: selecting a simple model of TextCNN for a network structure of a compression model, distilling and training Net-S based on the same sample Y, taking 4 distillation temperatures, simultaneously inputting the sample Y into a teacher model Net-T and a student model Net-S, outputting soft-target by the Net-T, and simultaneously outputting soft-target and hard-target in the Net-S training process; adding the cross entropies corresponding to the soft-target of Net-T and the soft-target of Net-S to obtain Lsoft of the whole model loss function; and simultaneously, taking the cross entropy of the hard-target and the ground-truth of the Net-S as Lhard of the whole model loss function, and carrying out the Net-S training by a back propagation training method until the training is stopped, thereby completing the whole knowledge distillation process.
Public opinion system of bank based on knowledge distillation carries out model compression includes: the system comprises a distributed message queue module, a model compression entity identification module and a model compression public opinion classification module;
the output end of the distributed message queue module is connected with the input end of the model compression entity identification module, and the output end of the model compression entity identification module is connected with the input end of the model compression public opinion classification module;
the distributed message queue module is used for transmitting real-time public sentiment news provided by a bank to the model compression entity identification module for processing in a distributed message queue mode;
the model compression entity recognition module is used for automatically recognizing entity information in the input text;
the model compression public opinion classification module is used for classifying and predicting input public opinion information.
As a further description of the above technical solution:
the distributed message queue module adopts a Rabbit-MQ-based distributed message queue module, and adopts a multi-producer and multi-consumer service architecture.
As a further description of the above technical solution:
the system also comprises a distributed cache module;
the distributed cache module adopts a Redis-based distributed cache module;
the distributed cache module is connected with the distributed message queue module and used for caching the requests which are not processed in time by the distributed message queue module and then processed by the model compression entity recognition module and the model compression public opinion classification module.
As a further description of the above technical solution:
the distributed cache module comprises an MQ timeout mechanism cache module;
and the MQ timeout mechanism cache module writes the timeout message into a distributed cache Redis, and acquires the timeout message from the Redis for processing when the resources of the model compression entity identification module and the model compression public opinion classification module are idle.
As a further description of the above technical solution:
the distributed cache module comprises an FIFO elimination mechanism module;
the FIFO elimination mechanism module is used for persisting the information to a database through the FIFO elimination mechanism module after the Redis cache is full, setting the state mark as unprocessed, and processing the information by the model compression entity identification module and the model compression public opinion classification module subsequently.
As a further description of the above technical solution:
the entity information is the company name and the person name of the client concerned by the bank.
The invention provides a bank public opinion pneumatic control system for model compression based on knowledge distillation. The method has the following beneficial effects:
(1): this bank public opinion air control system based on knowledge distillation carries out model compression compresses the leading pre-training model in industry through the technique of knowledge distillation, simplifies the structure of neural network model, and under the less condition of model parameter, can also guarantee the performance, the effect of model, can improve the model prediction rate of accuracy, can reduce the prediction time again.
(2): the bank public opinion pneumatic control system for model compression based on knowledge distillation reduces model prediction response time through the deployment of distributed message queues and distributed caches, and meets the high real-time requirement of banks.
(3): and the pneumatic control early warning of the bank monitoring client is completed by realizing a named entity recognition model and a public opinion early warning classification model.
Drawings
Fig. 1 is an overall schematic diagram of a bank public opinion pneumatic control system based on knowledge distillation for model compression according to the present invention;
fig. 2 is a schematic diagram of a distributed cache module according to 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 only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1-2, the bank public opinion trend control method based on knowledge distillation model compression comprises the following steps:
s1: constructing a model compression entity identification module, wherein the model compression entity identification module is a neural network model for carrying out model compression based on knowledge distillation, and the construction process of the model compression entity identification module is a teacher model trained on samples through an original model, and then processing is carried out through a compression model to obtain the final classification probability;
s2: constructing a model compression public opinion classification module, wherein the model compression public opinion classification module is a neural network model for performing model compression based on knowledge distillation, and the construction process of the model compression public opinion classification module is a teacher model trained by an original model based on samples, and then performing knowledge distillation training based on the same samples through the compression model to complete the whole knowledge distillation process;
s3: real-time public sentiment news provided by the bank is transmitted to the model compression entity recognition module and the model compression public sentiment classification module in a distributed message queue mode for analysis and processing, and the wind control early warning of bank monitoring clients is completed.
Step S1 of constructing a model compression entity identification module specifically includes the following steps:
s1.1: training an original model: the network structure of the original model is based on a pretrained model Bert12 layer + Bi-LSTM + CRF; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on a ground-truth, and obtaining a result called hard-target;
s1.2: training a compression model based on knowledge distillation: and selecting a simple model of Bi-LSTM + CRF according to the network structure of the compression model, acquiring sequence characteristics and outputting the label emission probability by the Bi-LSTM, accessing the LAbel emission probability into the CRF to generate transition probability, and outputting and acquiring the final classification probability of the label according to the emission probability and the transition probability.
Furthermore, the model compression entity recognition module builds soft-target in the original model training to participate in the subsequent knowledge distillation training process, and the soft-target is used as the loss function input of the compression model training
Step S2, the step of constructing a model compression public opinion classification module specifically comprises the following steps:
s2.1: the network structure of the original model is based on a pretrained model Bert12 layer + TextCNN; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on ground-truth to obtain a result;
s2.2: training a compression model based on knowledge distillation: selecting a simple model of TextCNN for a network structure of a compression model, distilling and training Net-S based on the same sample Y, taking 4 distillation temperatures, simultaneously inputting the sample Y into a teacher model Net-T and a student model Net-S, outputting soft-target by the Net-T, and simultaneously outputting soft-target and hard-target in the Net-S training process; adding the cross entropies corresponding to the soft-target of Net-T and the soft-target of Net-S to obtain Lsoft of the whole model loss function; and simultaneously, taking the cross entropy of the hard-target and the ground-truth of the Net-S as Lhard of the whole model loss function, and carrying out the Net-S training by a back propagation training method until the training is stopped, thereby completing the whole knowledge distillation process.
Public opinion system of bank based on knowledge distillation carries out model compression includes: the system comprises a distributed message queue module, a model compression entity identification module and a model compression public opinion classification module;
the output end of the distributed message queue module is connected with the input end of the model compression entity identification module, and the output end of the model compression entity identification module is connected with the input end of the model compression public opinion classification module;
the distributed message queue module is used for transmitting real-time public sentiment news provided by a bank to the model compression entity identification module for processing in a distributed message queue mode;
the model compression entity recognition module is used for automatically recognizing entity information in the input text,
predicting a time comparison result: the average prediction time of the original model is 247 milliseconds, the prediction time after knowledge distillation is 33 milliseconds, and the time is shortened by 7 times.
The model compression public opinion classification module is used for classifying and predicting input public opinion information, and predicting time comparison results: the average prediction time of the original model is 150 milliseconds, the prediction time after knowledge distillation is 17 milliseconds, and the time is shortened by 8 times.
The distributed message queue module adopts a Rabbit-MQ-based distributed message queue module, and adopts a multi-producer and multi-consumer service architecture.
Furthermore, the advanced pre-training model in the industry is compressed through the knowledge distillation technology, the structure of the neural network model is simplified, and the performance and the effect of the model can be ensured under the condition of less model parameters. The method can improve the accuracy of model prediction and reduce the prediction time, and completes the wind control early warning of bank monitoring clients by realizing a named entity recognition model and a public opinion early warning classification model.
The system also comprises a distributed cache module;
the distributed cache module adopts a Redis-based distributed cache module;
the distributed cache module is connected with the distributed message queue module and is used for caching the requests which are not processed in time by the distributed message queue module and then processed by the model compression entity recognition module and the model compression public opinion classification module.
The distributed cache module comprises an MQ timeout mechanism cache module;
and the MQ timeout mechanism cache module writes the timeout message into a distributed cache Redis, and acquires the timeout message from the Redis for processing when the resources of the model compression entity identification module and the model compression public opinion classification module are free, so that the operation of reading the message from a database is avoided, and the processing time delay is reduced.
The distributed cache module comprises an FIFO elimination mechanism module;
the FIFO elimination mechanism module is used for persisting the message to a database through the FIFO elimination mechanism module after the Redis cache is full, setting the state mark as unprocessed, and processing the message by the model compression entity identification module and the model compression public opinion classification module subsequently.
During a peak period, more service requests are made, the execution time of a downstream module is relatively increased, more messages backlogged in a Rabbit-MQ message queue are generated, the messages cannot be processed in time, the processing time delay is increased, the user experience is reduced, the memory module of an MQ timeout mechanism writes the timeout messages into a distributed cache Redis, and the timeout messages are obtained from the Redis to be processed when resources of a model compression entity recognition module and a model compression public sentiment classification module are free, so that the message reading operation from a database is avoided, and the processing time delay is reduced.
Through the deployment of the distributed message queue and the distributed cache, the model prediction response time is reduced, and the high real-time requirement of a bank is met.
The entity information is the company name and the person name of the client concerned by the bank.
In the description herein, references to the description of "one embodiment," "an example," "a specific example," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (7)

1. The bank public opinion trend control method for model compression based on knowledge distillation is characterized by comprising the following steps of:
s1: constructing a model compression entity recognition module which is a neural network model for model compression based on knowledge distillation, wherein the model compression entity recognition module is used for constructing a teacher model trained on samples through an original model and then processing the teacher model through a compression model to obtain the final classification probability,
the step S1 of constructing a model compression entity identification module specifically includes the following steps:
s1.1: training an original model: the network structure of the original model is based on a pretrained model Bert12 layer + Bi-LSTM + CRF; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on a ground-truth, and obtaining a result called hard-target;
s1.2: training a compression model based on knowledge distillation: selecting a simple Bi-LSTM + CRF model from a network structure of a compression model, acquiring sequence characteristics and outputting label emission probability by the Bi-LSTM, accessing the label emission probability into the CRF to generate transition probability, and outputting and acquiring final classification probability of the label according to the emission probability and the transition probability;
s2: constructing a model compression public opinion classification module, wherein the model compression public opinion classification module is a neural network model for performing model compression based on knowledge distillation, and the construction process of the model compression public opinion classification module is a teacher model trained by an original model based on samples, and then performing knowledge distillation training based on the same samples through the compression model to complete the whole knowledge distillation process;
the step S2 of constructing the model compression public opinion classification module specifically comprises the following steps:
s2.1: the network structure of the original model is based on a pretrained model Bert12 layer + TextCNN; then, based on a teacher model trained by a sample Y, carrying out maximum likelihood estimation based on ground-truth to obtain a result;
s2.2: training a compression model based on knowledge distillation: selecting a simple model of TextCNN for a network structure of a compression model, distilling and training Net-S based on the same sample Y, taking 4 distillation temperatures, simultaneously inputting the sample Y into a teacher model Net-T and a student model Net-S, outputting soft-target by the Net-T, and simultaneously outputting soft-target and hard-target in the Net-S training process; adding the cross entropies corresponding to the soft-target of Net-T and the soft-target of Net-S to obtain Lsoft of the whole model loss function; simultaneously, the cross entropy of the hard-target and the ground-truth of the Net-S is used as Lhard of the whole model loss function, the Net-S training is carried out by a back propagation training method until the training is stopped, and the whole knowledge distillation process is completed;
s3: real-time public sentiment news provided by the bank is transmitted to the model compression entity recognition module and the model compression public sentiment classification module in a distributed message queue mode for analysis and processing, and the wind control early warning of bank monitoring clients is completed.
2. The bank public opinion pneumatic control system based on knowledge distillation for model compression is based on the bank public opinion pneumatic control method based on knowledge distillation for model compression in claim 1, and is characterized by comprising the following steps: the system comprises a distributed message queue module, a model compression entity identification module and a model compression public opinion classification module;
the output end of the distributed message queue module is connected with the input end of the model compression entity identification module, and the output end of the model compression entity identification module is connected with the input end of the model compression public opinion classification module;
the distributed message queue module is used for transmitting real-time public sentiment news provided by a bank to the model compression entity identification module for processing in a distributed message queue mode;
the model compression entity recognition module is used for automatically recognizing entity information in the input text;
the model compression public opinion classification module is used for classifying and predicting input public opinion information.
3. The bank public opinion style system based on knowledge distillation for model compression as claimed in claim 2, wherein the distributed message queue module employs a Rabbit-MQ based distributed message queue module, and the distributed message queue module employs a multi-producer and multi-consumer service architecture.
4. The bank public opinion pneumatic control system based on knowledge distillation for model compression as claimed in claim 2, further comprising a distributed cache module;
the distributed cache module adopts a Redis-based distributed cache module;
the distributed cache module is connected with the distributed message queue module and used for caching the requests which are not processed in time by the distributed message queue module and then processed by the model compression entity recognition module and the model compression public opinion classification module.
5. The bank public opinion style system based on knowledge distillation for model compression according to claim 4, wherein the distributed cache module comprises an MQ timeout mechanism cache module;
and the MQ timeout mechanism cache module writes the timeout message into a distributed cache Redis, and acquires the timeout message from the Redis for processing when the resources of the model compression entity identification module and the model compression public opinion classification module are idle.
6. The bank public opinion pneumatic control system based on knowledge distillation for model compression as claimed in claim 4, wherein the distributed cache module comprises a FIFO elimination mechanism module;
the FIFO elimination mechanism module is used for persisting the information to a database through the FIFO elimination mechanism module after the Redis cache is full, setting the state mark as unprocessed, and processing the information by the model compression entity identification module and the model compression public opinion classification module subsequently.
7. The bank public opinion pneumatic system based on knowledge distillation for model compression as claimed in claim 2, wherein the entity information is company name and person name of the bank concerned client.
CN202011079319.XA 2020-10-10 2020-10-10 Bank public opinion style control method and system based on knowledge distillation for model compression Active CN112199592B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011079319.XA CN112199592B (en) 2020-10-10 2020-10-10 Bank public opinion style control method and system based on knowledge distillation for model compression

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011079319.XA CN112199592B (en) 2020-10-10 2020-10-10 Bank public opinion style control method and system based on knowledge distillation for model compression

Publications (2)

Publication Number Publication Date
CN112199592A CN112199592A (en) 2021-01-08
CN112199592B true CN112199592B (en) 2022-06-03

Family

ID=74012714

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011079319.XA Active CN112199592B (en) 2020-10-10 2020-10-10 Bank public opinion style control method and system based on knowledge distillation for model compression

Country Status (1)

Country Link
CN (1) CN112199592B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699678B (en) * 2021-03-24 2021-06-18 达而观数据(成都)有限公司 Model distillation method combined with dynamic vocabulary enhancement
CN114095447B (en) * 2021-11-22 2024-03-12 成都中科微信息技术研究院有限公司 Communication network encryption flow classification method based on knowledge distillation and self-distillation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110232109A (en) * 2019-05-17 2019-09-13 深圳市兴海物联科技有限公司 A kind of Internet public opinion analysis method and system
CN110633373A (en) * 2018-06-20 2019-12-31 上海财经大学 Automobile public opinion analysis method based on knowledge graph and deep learning
CN111611377A (en) * 2020-04-22 2020-09-01 淮阴工学院 Knowledge distillation-based multi-layer neural network language model training method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10402701B2 (en) * 2017-03-17 2019-09-03 Nec Corporation Face recognition system for face recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110633373A (en) * 2018-06-20 2019-12-31 上海财经大学 Automobile public opinion analysis method based on knowledge graph and deep learning
CN110232109A (en) * 2019-05-17 2019-09-13 深圳市兴海物联科技有限公司 A kind of Internet public opinion analysis method and system
CN111611377A (en) * 2020-04-22 2020-09-01 淮阴工学院 Knowledge distillation-based multi-layer neural network language model training method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
巫继鹏等.结合规则蒸馏的情感原因发现.《清华大学学报（自然科学版）》.2020,第60卷(第5期), *

Also Published As

Publication number Publication date
CN112199592A (en) 2021-01-08

Similar Documents

Publication Publication Date Title
US20220019855A1 (en) Image generation method, neural network compression method, and related apparatus and device
US11043209B2 (en) System and method for neural network orchestration
US11257493B2 (en) Vision-assisted speech processing
CN112199592B (en) Bank public opinion style control method and system based on knowledge distillation for model compression
CN113326764A (en) Method and device for training image recognition model and image recognition
WO2019169996A1 (en) Video processing method and apparatus, video retrieval method and apparatus, storage medium and server
CN112492343B (en) Video live broadcast monitoring method and related device
CN111680155A (en) Text classification method and device, electronic equipment and computer storage medium
CN113239204A (en) Text classification method and device, electronic equipment and computer-readable storage medium
CN110781849A (en) Image processing method, device, equipment and storage medium
CN113282433A (en) Cluster anomaly detection method and device and related equipment
CN112995414A (en) Behavior quality inspection method, device, equipment and storage medium based on voice call
US20230290126A1 (en) Method for training roi detection model, method for detecting roi, device, and medium
CN116741159A (en) Audio classification and model training method and device, electronic equipment and storage medium
CN116524931A (en) System, method, electronic equipment and medium for converting voice of 5G rich media message into text
CN116432664A (en) Dialogue intention classification method and system for high-quality data amplification
CN114565080A (en) Neural network compression method and device, computer readable medium and electronic equipment
CN114464195A (en) Voiceprint recognition model training method and device for self-supervision learning and readable medium
CN111382191A (en) Machine learning identification method based on deep learning
CN110647810A (en) Method and device for constructing and identifying radio signal image identification model
CN114626430B (en) Emotion recognition model training method, emotion recognition device and emotion recognition medium
CN116453023B (en) Video abstraction system, method, electronic equipment and medium for 5G rich media information
CN116467223B (en) Method, device, system, equipment and medium for generating test report
CN116127074B (en) Anchor image classification method based on LDA theme model and kmeans clustering algorithm
US20240119295A1 (en) Generalized Bags for Learning from Label Proportions

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
CB02 Change of applicant information

Address after: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051

Applicant after: Sinyada Technology Co.,Ltd.

Address before: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051

Applicant before: SUNYARD SYSTEM ENGINEERING Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20230803

Address after: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051

Patentee after: Sinyada Technology Co.,Ltd.

Patentee after: HANGZHOU XINYADA FINTECH TECHNOLOGY Co.,Ltd.

Address before: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051

Patentee before: Sinyada Technology Co.,Ltd.

TR01 Transfer of patent right