CN113674846A - Hospital intelligent service public opinion monitoring platform based on LSTM network - Google Patents
Hospital intelligent service public opinion monitoring platform based on LSTM network Download PDFInfo
- Publication number
- CN113674846A CN113674846A CN202111090349.5A CN202111090349A CN113674846A CN 113674846 A CN113674846 A CN 113674846A CN 202111090349 A CN202111090349 A CN 202111090349A CN 113674846 A CN113674846 A CN 113674846A
- Authority
- CN
- China
- Prior art keywords
- data
- hospital
- platform
- model
- lstm network
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 235000016709 nutrition Nutrition 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 3
- 230000036541 health Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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
- G06N3/047—Probabilistic or stochastic 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a hospital intelligent service public opinion monitoring platform based on LSTM network in the technical field; the method comprises a comment collection stage, a classification and data conversion stage, a model building stage and a platform application stage. The general environment, ward environment, the hospitalizing process, the operation process, the hospitalizing process, the doctor treatment level, the nurse service level, the hospital health and the like of the hospital are closely related to the patient through establishing the LSTM network model, the information comment public opinion which is easy to cause the shortage of the doctor-patient relationship is monitored, the monitoring result is tidied, analyzed and summarized, the summarized result is transmitted to the hospital management platform, the hospital can take measures aiming at the key and prominent problems, the service level of the hospital is improved, and the hospitalizing experience of the patient is improved.
Description
Technical Field
The invention relates to the field, in particular to a hospital intelligent service public opinion monitoring platform based on an LSTM network.
Background
At present, because the shortage of medical resources and the unbalanced configuration in China cause the huge flow of people in a large hospital, the medical service level of the large hospital is difficult to improve, and the contradiction between doctors and patients is further aggravated, the method is an effective method for effectively analyzing and monitoring the patient comments, for a patient, the outstanding problems existing in the hospital can be reflected by transmitting the own treatment experience to a service platform of the hospital through the Internet, for the hospital, the comments of the patient are analyzed through summarizing, the outstanding problems are found and measures are taken to solve, and therefore the medical service level of the hospital is improved.
At present, for emotion analysis methods for comments, traditional probability analysis type algorithm models such as naive Bayes or simple models such as a snowNLP Chinese text processing library are mainly used, and different models are selected according to different application scenes to improve the analysis accuracy. But hospital reviews relate to many different scenarios such as hospital environment, nurse service level, doctor's treatment level, etc., and cannot be monitored comprehensively. Therefore, those skilled in the art provide a public opinion monitoring platform based on LSTM network for hospital intelligent services to solve the above problems in the background art.
Disclosure of Invention
The invention aims to provide a hospital intelligent service public opinion monitoring platform based on an LSTM network, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the hospital intelligent service public opinion monitoring platform based on the LSTM network comprises a comment collection stage, a classification and data conversion stage, a model building stage and a platform application stage:
the S1 comment collection phase includes: patient comments are collected through APP, wherein the comments include nurse service evaluation, doctor treatment evaluation, hospital environment evaluation and other evaluations;
the classification and data conversion stage of S2 includes: classifying comments collected by a keyword extraction method, converting different types of data, converting the data into supervised learning data with labels, converting the data and corresponding labels into 3D data, and dividing a training set and a test set of the converted different types of data;
the S3 model building stage comprises: building, training and adjusting an LSTM network model in the platform;
the application stage of the S4 platform comprises the following steps: and feeding back and adjusting the actual application and the application condition of the platform.
As a further scheme of the invention: the S2 classification and data conversion stage is divided into the following sub-steps: s201, collecting evaluation data of different aspects of a hospital through the APP platform in the step S100, and classifying the evaluation data by using a keyword extraction method; s202, labeling each classified comment data with different labels, wherein the labels are positive and negative, and further become binary data in supervised learning; s203, dispersing the comment data and the labels in the classified data into character level features with fixed length M, and counting the occurrence times of different characters in the data; and S204, dividing the data into a 90% training sample set and a 10% testing sample set.
As a still further scheme of the invention: the S3 model building stage comprises: s301, an LSTM network model is established in the platform, wherein the network model comprises an Embedding layer Embedding, an LSTM network layer, a Dropout over-fitting prevention layer and an output layer; s302, extracting the divided training sample set in the step S204 and inputting the training sample set into Embedding layer Embedding of the created LSTM network model; s303, the Embedding layer Embedding encodes the input sequence into a dense vector sequence with a dimension of out _ dim ═ 12; s304, setting the neuron n _ units of the LSTM network layer to be 50; s305, in order to prevent the model from generating the overfitting phenomenon, the Dropout layer Dropout of the network model is set to 0.5; s306, setting an activation function of an output layer as softmax as the model mainly aims at the problem of two categories; s307, defining a loss function as category _ cross in the model, and an optimization algorithm as an adam algorithm; s308, applying the well-defined network model to a 90% training sample set, outputting prediction probability to each training sample, and comparing the prediction probability with the actual probability to obtain a cross entropy loss function, wherein a calculation formula of the coordinated _ cross entropy is as follows:
in the formula: y isiAnd
respectively representing the actual probability and the prediction probability of the ith sample, wherein n represents the number of samples in a training sample set; s309, judging whether the nutritional _ cross meets the requirement, if so, only needing the step ST312, otherwise, executing the step S313; s310, regarding as that the network model is successfully built, and finishing the training and tuning process; s311, judging whether the iteration times exceed the specified times, if so, modifying the iteration times, and if not, executing S312; and S312, modifying the initial parameters of the network model when the model is not successfully built, and repeatedly executing S308 until the catagorical _ cross satisfies the requirement.
As a still further scheme of the invention: the S4 platform application phase includes the following substeps: s401, transmitting the comment data of the APP of the platform to a network model according to different categories through conversion to predict whether the comment belongs to a positive or negative type; s402, counting the prediction results of different categories and analyzing the prediction results to obtain the problems of hospital services; and S403, according to the statistical and analysis result of S402, the hospital takes measures aiming at the key problems, so that the service level of the hospital is improved, and the hospitalizing experience of the patient is improved.
To further highlight the effectiveness of the present invention, the prediction is performed by using LSTM network model and traditional na iotave bayes model, and snornlp in the platform, where the prediction accuracy is shown in the table,
the LSTM network model in the platform of the invention is proved to have better prediction effect than other two methods, and the feasibility of the system is proved again.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the LSTM network model is established to monitor the information comment public opinion which is closely related to the overall environment, ward environment, hospitalizing process, operation process, hospitalizing process, doctor treatment level, nurse service level, hospital health and the like of the hospital and easily causes the shortage of doctor-patient relationship, and the monitoring result is rectified, analyzed and summarized, and then the summarized result is transmitted to the hospital management platform, so that the hospital can take measures against the key problem, the service level of the hospital is improved, and the hospitalizing experience of the patient is improved.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of the structural composition of the LSTM network model in the present invention;
FIG. 3 is a schematic flow chart of data transformation according to the present invention;
FIG. 4 is a schematic flow chart of model building according to the present invention;
FIG. 5 is a flowchart illustrating a platform application 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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 5, in the embodiment of the present invention, the LSTM network-based hospital intelligent service public opinion monitoring platform includes a comment collection stage, a classification and data conversion stage, a model building stage, and a platform application stage:
the S1 comment collection phase includes: patient comments are collected through APP, wherein the comments include nurse service evaluation, doctor treatment evaluation, hospital environment evaluation and other evaluations;
the classification and data conversion stage of S2 includes: classifying comments collected by a keyword extraction method, converting different types of data, converting the data into supervised learning data with labels, converting the data and corresponding labels into 3D data, and dividing a training set and a test set of the converted different types of data;
the S3 model building stage comprises: building, training and adjusting an LSTM network model in the platform;
the application stage of the S4 platform comprises the following steps: and feeding back and adjusting the actual application and the application condition of the platform.
The classification and data conversion stage of S2 is divided into the following sub-steps: s201, collecting evaluation data of different aspects of a hospital through the APP platform in the step S100, and classifying the evaluation data by using a keyword extraction method; s202, labeling each classified comment data with different labels, wherein the labels are positive and negative, and further become binary data in supervised learning; s203, dispersing the comment data and the labels in the classified data into character level features with fixed length M, and counting the occurrence times of different characters in the data; and S204, dividing the data into a 90% training sample set and a 10% testing sample set.
The S3 model building stage comprises: s301, an LSTM network model is established in the platform, wherein the network model comprises an Embedding layer Embedding, an LSTM network layer, a Dropout over-fitting prevention layer and an output layer; s302, extracting the divided training sample set in the step S204 and inputting the training sample set into Embedding layer Embedding of the created LSTM network model; s303, the Embedding layer Embedding encodes the input sequence into a dense vector sequence with a dimension of out _ dim ═ 12; s304, setting the neuron n _ units of the LSTM network layer to be 50; s305, in order to prevent the model from generating the overfitting phenomenon, the Dropout layer Dropout of the network model is set to 0.5; s306, setting an activation function of an output layer as softmax as the model mainly aims at the problem of two categories; s307, defining a loss function as category _ cross in the model, and an optimization algorithm as an adam algorithm; s308, applying the well-defined network model to a 90% training sample set, outputting prediction probability to each training sample, and comparing the prediction probability with the actual probability to obtain a cross entropy loss function, wherein a calculation formula of the coordinated _ cross entropy is as follows:
in the formula: y isiAnd
respectively representing the actual probability and the prediction probability of the ith sample, wherein n represents the number of samples in a training sample set; s309, judging whether the nutritional _ cross meets the requirement, if so, only needing the step ST312, otherwise, executing the step S313; s310, regarding as that the network model is successfully built, and finishing the training and tuning process; s311, judging whether the iteration times exceed the specified times, if so, modifying the iteration times, and if not, executing S312; and S312, modifying the initial parameters of the network model when the model is not successfully built, and repeatedly executing S308 until the catagorical _ cross satisfies the requirement.
The S4 platform application phase includes the following substeps: s401, transmitting the comment data of the APP of the platform to a network model according to different categories through conversion to predict whether the comment belongs to a positive or negative type; s402, counting the prediction results of different categories and analyzing the prediction results to obtain the problems of hospital services; and S403, according to the statistical and analysis result of S402, the hospital takes measures aiming at the key problems, so that the service level of the hospital is improved, and the hospitalizing experience of the patient is improved.
The working principle of the invention is as follows: the method comprises the steps of carrying out keyword and word recognition on information of hospital service public sentiment through software, further collecting the public sentiment information, carrying out data analysis through an LSTM model after collection, carrying out data analysis through an LSTM model when analyzing, coding an intensive sequence with the dimension of out-dim being 12 by Embedding layer Embedding in the LSTM network model, wherein Dropout in a Dropout layer of the network model is 0.5, further calculating the actual probability and the predicted probability of a sample through an activation function ftsomax and a loss function category-cross by the calculation formula, and further monitoring and feeding back the public sentiment through the actual calculation probability and the predicted probability.
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 (4)
1. Intelligent service public opinion monitoring platform of hospital based on LSTM network, including comment collection phase, categorised and data conversion phase, model build phase and platform application phase, its characterized in that:
the S1 comment collection phase includes: patient comments are collected through APP, wherein the comments include nurse service evaluation, doctor treatment evaluation, hospital environment evaluation and other evaluations;
the classification and data conversion stage of S2 includes: classifying comments collected by a keyword extraction method, converting different types of data, converting the data into supervised learning data with labels, converting the data and corresponding labels into 3D data, and dividing a training set and a test set of the converted different types of data;
the S3 model building stage comprises: building, training and adjusting an LSTM network model in the platform;
the application stage of the S4 platform comprises the following steps: and feeding back and adjusting the actual application and the application condition of the platform.
2. The LSTM network-based hospital intelligent services public opinion monitoring platform of claim 1, wherein: the S2 classification and data conversion stage is divided into the following sub-steps: s201, collecting evaluation data of different aspects of a hospital through the APP platform in the step S100, and classifying the evaluation data by using a keyword extraction method; s202, labeling each classified comment data with different labels, wherein the labels are positive and negative, and further become binary data in supervised learning; s203, dispersing the comment data and the labels in the classified data into character level features with fixed length M, and counting the occurrence times of different characters in the data; and S204, dividing the data into a 90% training sample set and a 10% testing sample set.
3. The LSTM network-based hospital intelligent services public opinion monitoring platform of claim 1, wherein: the S3 model building stage comprises: s301, an LSTM network model is established in the platform, wherein the network model comprises an Embedding layer Embedding, an LSTM network layer, a Dropout over-fitting prevention layer and an output layer; s302, extracting the divided training sample set in the step S204 and inputting the training sample set into Embedding layer Embedding of the created LSTM network model; s303, the Embedding layer Embedding encodes the input sequence into a dense vector sequence with a dimension of out _ dim ═ 12; s304, setting the neuron n _ units of the LSTM network layer to be 50; s305, in order to prevent the model from generating the overfitting phenomenon, the Dropout layer Dropout of the network model is set to 0.5; s306, setting an activation function of an output layer as softmax as the model mainly aims at the problem of two categories; s307, defining a loss function as category _ cross in the model, and an optimization algorithm as an adam algorithm; s308, applying the well-defined network model to a 90% training sample set, outputting prediction probability to each training sample, and comparing the prediction probability with actual probability to obtain a cross entropy loss function; s309, judging whether the nutritional _ cross meets the requirement, if so, only needing the step ST312, otherwise, executing the step S313; s310, regarding as that the network model is successfully built, and finishing the training and tuning process; s311, judging whether the iteration times exceed the specified times, if so, modifying the iteration times, and if not, executing S312; and S312, modifying the initial parameters of the network model when the model is not successfully built, and repeatedly executing S308 until the catagorical _ cross satisfies the requirement.
4. The LSTM network-based hospital intelligent services public opinion monitoring platform of claim 1, wherein: the S4 platform application phase includes the following substeps: s401, transmitting the comment data of the APP of the platform to a network model according to different categories through conversion to predict whether the comment belongs to a positive or negative type; s402, counting the prediction results of different categories and analyzing the prediction results to obtain the problems of hospital services; and S403, according to the statistical and analysis result of S402, the hospital takes measures aiming at the key problems, so that the service level of the hospital is improved, and the hospitalizing experience of the patient is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111090349.5A CN113674846A (en) | 2021-09-18 | 2021-09-18 | Hospital intelligent service public opinion monitoring platform based on LSTM network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111090349.5A CN113674846A (en) | 2021-09-18 | 2021-09-18 | Hospital intelligent service public opinion monitoring platform based on LSTM network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674846A true CN113674846A (en) | 2021-11-19 |
Family
ID=78549539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111090349.5A Pending CN113674846A (en) | 2021-09-18 | 2021-09-18 | Hospital intelligent service public opinion monitoring platform based on LSTM network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674846A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202037A (en) * | 2022-01-14 | 2022-03-18 | 上海蓬海涞讯数据技术有限公司 | Generation method, prediction method, system and storage medium of hospital prediction model |
| CN114510618A (en) * | 2021-12-31 | 2022-05-17 | 安徽郎溪南方水泥有限公司 | Processing method and device based on smart mine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122607A (en) * | 2018-01-12 | 2018-06-05 | 重庆至道医院管理股份有限公司 | Patient Experience evaluation and test optimization service system is carried out based on big data |
| CN109086393A (en) * | 2018-07-27 | 2018-12-25 | 贵州中科恒运软件科技有限公司 | A kind of the analysis of public opinion system and method |
| CN109670164A (en) * | 2018-04-11 | 2019-04-23 | 东莞迪赛软件技术有限公司 | Healthy the analysis of public opinion method based on the more word insertion Bi-LSTM residual error networks of deep layer |
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
| AU2020100710A4 (en) * | 2020-05-05 | 2020-06-11 | Chen, Dadu Mr | A method for sentiment analysis of film reviews based on deep learning and natural language processing |
| CN111831895A (en) * | 2019-04-19 | 2020-10-27 | 天津科技大学 | Network public opinion early warning method based on LSTM model |
| CN112241626A (en) * | 2020-10-14 | 2021-01-19 | 网易（杭州）网络有限公司 | Semantic matching and semantic similarity model training method and device |
| US20210117796A1 (en) * | 2020-12-01 | 2021-04-22 | Harbin Engineering University | Ship Motion Prediction Method Based on Long Short-Term Memory Network and Gaussian Process Regression |
| CN113239290A (en) * | 2021-06-10 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Data analysis method and device for public opinion monitoring and electronic device |
-
2021
- 2021-09-18 CN CN202111090349.5A patent/CN113674846A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122607A (en) * | 2018-01-12 | 2018-06-05 | 重庆至道医院管理股份有限公司 | Patient Experience evaluation and test optimization service system is carried out based on big data |
| CN109670164A (en) * | 2018-04-11 | 2019-04-23 | 东莞迪赛软件技术有限公司 | Healthy the analysis of public opinion method based on the more word insertion Bi-LSTM residual error networks of deep layer |
| CN109086393A (en) * | 2018-07-27 | 2018-12-25 | 贵州中科恒运软件科技有限公司 | A kind of the analysis of public opinion system and method |
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
| CN111831895A (en) * | 2019-04-19 | 2020-10-27 | 天津科技大学 | Network public opinion early warning method based on LSTM model |
| AU2020100710A4 (en) * | 2020-05-05 | 2020-06-11 | Chen, Dadu Mr | A method for sentiment analysis of film reviews based on deep learning and natural language processing |
| CN112241626A (en) * | 2020-10-14 | 2021-01-19 | 网易（杭州）网络有限公司 | Semantic matching and semantic similarity model training method and device |
| US20210117796A1 (en) * | 2020-12-01 | 2021-04-22 | Harbin Engineering University | Ship Motion Prediction Method Based on Long Short-Term Memory Network and Gaussian Process Regression |
| CN113239290A (en) * | 2021-06-10 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Data analysis method and device for public opinion monitoring and electronic device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114510618A (en) * | 2021-12-31 | 2022-05-17 | 安徽郎溪南方水泥有限公司 | Processing method and device based on smart mine |
| CN114202037A (en) * | 2022-01-14 | 2022-03-18 | 上海蓬海涞讯数据技术有限公司 | Generation method, prediction method, system and storage medium of hospital prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143576A (en) | Event-oriented dynamic knowledge graph construction method and device | |
| CN111914087B (en) | Public opinion analysis method | |
| JPH07295989A (en) | Device that forms interpreter to analyze data | |
| CN109308323A (en) | A kind of construction method, device and the equipment of causality knowledge base | |
| CN113674846A (en) | Hospital intelligent service public opinion monitoring platform based on LSTM network | |
| CN110675023A (en) | Litigation request rationality prediction model training method based on neural network, and litigation request rationality prediction method and device based on neural network | |
| CN114266455A (en) | Knowledge graph-based visual enterprise risk assessment method | |
| Edo-Osagie et al. | Attention-based recurrent neural networks (RNNs) for short text classification: An application in public health monitoring | |
| CN117745048A (en) | Creative flow management method assisted by artificial intelligence | |
| Wen et al. | A cross-project defect prediction model based on deep learning with self-attention | |
| CN114764463A (en) | Internet public opinion event automatic early warning system based on event propagation characteristics | |
| Aliyu et al. | Analysis of cyber bullying on Facebook using text mining | |
| Marerngsit et al. | A two-stage text-to-emotion depressive disorder screening assistance based on contents from online community | |
| CN112966507A (en) | Method, device, equipment and storage medium for constructing recognition model and identifying attack | |
| CN111723127A (en) | Stock trend prediction method and system based on text abstract emotion mining | |
| CN115600602B (en) | Method, system and terminal device for extracting key elements of long text | |
| Ullah et al. | Unveiling the Power of Deep Learning: A Comparative Study of LSTM, BERT, and GRU for Disaster Tweet Classification | |
| Hirakawa et al. | Anomaly detection on software log based on Temporal Memory | |
| CN113706207B (en) | Order success rate analysis method, device, equipment and medium based on semantic analysis | |
| CN113468203B (en) | Financial user image drawing method based on recurrent neural network and attention mechanism | |
| CN111221941B (en) | Social media rumor authentication algorithm based on text content and line style | |
| Fu et al. | Prediction of hot topics of agricultural public opinion based on attention mechanism LSTM model | |
| Fan et al. | Environmental Complaint Text Classification Scheme Combining Automatic Annotation and TextCNN | |
| Narasamma et al. | DETECTING MALICIOUS ACTIVITIES ON TWITTER DATA FOR SENTIMENT ANALYSIS USING A NOVEL OPTIMIZED MACHINE LEARNING APPROACH | |
| CN117422063B (en) | Big data processing method applying intelligent auxiliary decision and intelligent auxiliary decision system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211119 |