CN111061871B - Method for analyzing tendency of government and enterprise service text - Google Patents
Method for analyzing tendency of government and enterprise service text Download PDFInfo
- Publication number
- CN111061871B CN111061871B CN201911170332.3A CN201911170332A CN111061871B CN 111061871 B CN111061871 B CN 111061871B CN 201911170332 A CN201911170332 A CN 201911170332A CN 111061871 B CN111061871 B CN 111061871B
- Authority
- CN
- China
- Prior art keywords
- government
- enterprise service
- text
- population
- setting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000013461 design Methods 0.000 claims abstract description 19
- 230000003044 adaptive effect Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- GVGLGOZIDCSQPN-PVHGPHFFSA-N Heroin Chemical compound O([C@H]1[C@H](C=C[C@H]23)OC(C)=O)C4=C5[C@@]12CCN(C)[C@@H]3CC5=CC=C4OC(C)=O GVGLGOZIDCSQPN-PVHGPHFFSA-N 0.000 claims description 3
- 108010003272 Hyaluronate lyase Proteins 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 108010074361 factor V clotting antigen Proteins 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for analyzing the tendency of a government and enterprise service text, which optimizes and designs the parameters of a government and enterprise service text classifier by applying a combined sine and cosine algorithm and then analyzes the tendency of the government and enterprise service text by utilizing the optimized government and enterprise service text classifier. In the combined sine and cosine algorithm, a combination factor is generated according to the current evolution state, excellent information extracted from the population is fused by using the combination factor to generate a new individual, and the searching performance of the algorithm is enhanced, so that the efficiency of the text tendency analysis of the government and enterprise services is improved.
Description
Technical Field
The invention relates to the field of text mining, in particular to a method for analyzing text tendency of government and enterprise services.
Background
In order to make enterprise service work more efficient, relevant functional departments establish a government and enterprise service information system. Due to the continuous improvement of the government and enterprise service information system, on one hand, enterprises can consult related functional departments about the handling process of related business on the internet; on the other hand, due to the advanced innovation of related functional departments, more and more businesses such as enterprise support declaration and the like can be handled on the internet. In the system of the government and enterprise service information, a large amount of text of the government and enterprise service is generated, such as business consultation text, consultation reply text, service evaluation text and the like. How to improve the enterprise service level by utilizing the accumulated government and enterprise service texts is a technical challenge faced by the current government and enterprise service information system.
In order to improve the efficiency of the government and enterprise service information system, the tendency of some government and enterprise service texts is often needed to be analyzed, for example, the analysis service evaluates whether the texts are positive, negative or neutral. System design developers typically analyze the tendencies of the text of a government enterprise service by using text classification techniques in artificial intelligence. When the text classification technology is used, parameters of a text classifier are required to be optimally designed, and the optimization result of the parameters of the text classifier can influence the analysis accuracy of the text tendency of the government and enterprise services to a great extent. The sine and cosine algorithm is an effective text classifier parameter optimization design algorithm [ Mirjalli, S. (2016.) SCA: a sine cosine algorithm for optimizing presentation Systems, knowledge-Based Systems,96,120 and 133 ], and achieves certain effects when parameters of a plurality of text classifiers are optimally designed. However, when the parameters of the text classifier of the government and enterprise services are optimally designed by the traditional sine and cosine algorithm, the shortcoming of low convergence speed is easy to occur, and the efficiency of the text tendency analysis of the government and enterprise services is greatly influenced.
Disclosure of Invention
The invention aims to provide a method for analyzing the text tendency of the government and enterprise service. The method overcomes the defect that the convergence speed is low easily when the traditional sine and cosine algorithm is applied to the tendency analysis of the government and enterprise service texts to a certain extent, and can improve the efficiency of the tendency analysis of the government and enterprise service texts.
The technical scheme of the invention is as follows: a method for analyzing text tendency of government and enterprise services comprises the following steps:
step 1, collecting a government and enterprise service text;
step 2, preprocessing the collected government and enterprise service texts to generate a government and enterprise service text data set;
step 3, dividing the government and enterprise service text data set into a training data set and a testing data set;
step 4, determining a government and enterprise service text classifier, and determining parameters of the optimal design required by the government and enterprise service text classifier;
step 5, solving parameters of the optimal design required by the government and enterprise service text classifier by using a combined sine and cosine algorithm;
step 6, utilizing the optimized text classifier of the government and enterprise service to realize the tendency analysis of the text of the government and enterprise service;
the step 5 of solving the parameters of the optimized design required by the text classifier of the government and enterprise service by using the combined sine and cosine algorithm comprises the following steps:
step 5.1, setting the population size MPsize and the maximum search algebra MXG;
step 5.2, setting the current search algebra t to be 0;
step 5.3, randomly generating MPsize individuals to form a population, wherein each individual in the population stores parameters of the optimal design required by the text classifier of the government and enterprise service;
step 5.4, calculating the adaptive value of each individual in the population;
step 5.5, storing the optimal individual SGX in the population;
step 5.6, setting a buffer value kc ═ rand (0,1), wherein rand is a random real number generation function;
step 5.7, setting a threshold probability vp ═ rand (0, 1);
step 5.8, calculating a combination factor vc according to the formula (1):
wherein the inertia weight kw is a random number between [0,0.2 ];
step 5.9, set the scaling factorSetting the zoom angle scag to [0,2 x π]Random real numbers in between; set the spreading factor ser to [0,2]Random real numbers in between;
step 5.10, setting an operator probability value ecp ═ rand (0, 1);
step 5.11, if ecp is less than 0.4, go to step 5.13, otherwise go to step 5.12;
step 5.12, go to step 5.15 if ecp is less than 0.8, otherwise go to step 5.17;
step 5.13, executing a sine search operator according to the formula (2):
wherein the subscript i ═ 1,2, …, MPsize;representing the ith individual in the population;representing the ith individual in the new generation of population; sin is a sine function;
step 5.14, go to step 5.19;
step 5.15, executing a cosine search operator according to the formula (3):
wherein cos is a cosine function;
step 5.16, go to step 5.19;
step 5.17, executing a combined search operator according to the formula (4):
wherein PLB is the current search lower bound of the population; PUB is the current search upper bound of the population; the inverse learning factor kow is a random real number between [0,1 ];
step 5.18, ifIs less than PIi tIf the adaptive value is not the same as the adaptive value, setting a cache value kc as vc, otherwise, keeping kc unchanged;
step 5.19, ifIs less thanThe adaptive value of (1) is then utilizedReplacement ofOtherwise, it keepsThe change is not changed;
step 5.20, storing the optimal individual SGX in the population, and then setting the current search algebra t to t + 1;
step 5.21, if the current search algebra t is smaller than MXG, turning to step 5.7, otherwise, turning to step 5.22;
and 5.22, extracting parameters of the optimized design of the government and enterprise service text classifier from the optimal individual SGX.
The method applies a combined sine and cosine algorithm to optimally design the parameters of the text classifier of the government and enterprise services, and then analyzes the tendency of the text of the government and enterprise services by utilizing the optimally designed text classifier of the government and enterprise services. In the combined sine and cosine algorithm, a combination factor is adaptively generated by utilizing feedback information in the searching process, and then the combination factor is utilized to fuse beneficial information of general reverse learning individuals and optimal individuals in a population, so that the local searching capability of the algorithm is enhanced, the convergence speed of the algorithm is accelerated, a optimally designed government and enterprise service text classifier is obtained, and the efficiency of the analysis of the tendency of the government and enterprise service text is improved.
Drawings
FIG. 1 is a flow chart of a combined sine and cosine algorithm.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b):
in this embodiment, as shown in fig. 1 of the accompanying drawings, the specific implementation steps of the present invention are as follows:
step 1, collecting a government and enterprise service text;
step 2, preprocessing the collected government and enterprise service texts to generate a government and enterprise service text data set, wherein the government and enterprise service text data set consists of 6800 government and enterprise service text samples; the sample of the government and enterprise service text comprises a feature vector of the government and enterprise service text and a tendency category of the government and enterprise service text; the propensity categories for the text of the government enterprise service include, but are not limited to: a positive category, a negative category, and a neutral category; the government and enterprise service text comprises a business consultation text, a consultation reply text and a service evaluation text; the government and enterprise service text can be exported from a government and enterprise service information system;
step 3, dividing the government and enterprise service text data set into a training data set and a testing data set;
step 4, determining that the government and enterprise service text classifier is XGboost, wherein the input variable of the XGboost is a feature vector of the government and enterprise service text, and the output of the XGboost is the tendency category of the government and enterprise service text; determining the learning rate of XGboost, the maximum depth of the decision tree and the number of the decision trees as the parameters of the optimal design required by the government and enterprise service text classifier;
and 5, solving parameters of the optimal design required by the text classifier of the government and enterprise service by using a combined sine and cosine algorithm: the learning rate of the XGboost, the maximum depth of the decision tree and the number of the decision trees;
step 6, utilizing the optimized text classifier of the government and enterprise service to realize the tendency analysis of the text of the government and enterprise service;
the step 5 of solving the parameters of the optimized design required by the text classifier of the government and enterprise service by using the combined sine and cosine algorithm comprises the following steps:
step 5.1, setting the population size MPsize to be 30 and the maximum search algebra MXG to be 5000;
step 5.2, setting the current search algebra t to be 0;
and 5.3, randomly generating MPsize individuals to form a population, wherein each individual in the population stores parameters of the optimized design required by the text classifier XGboost of the government and enterprise services: learning rate, maximum depth of decision tree and number of decision trees;
step 5.4, calculating the adaptive value of each individual in the population, wherein the method for calculating the adaptive value comprises the following steps: extracting the learning rate of the XGboost, the maximum depth of the decision tree and the number of the decision trees from the individual; then, training an enterprise service text classifier XGboost on a training data set by using the extracted learning rate of the XGboost, the maximum depth of the decision trees and the number of the decision trees, calculating the classification error xgb _ err of the trained enterprise service text classifier XGboost on a testing data set, and setting xgb _ err as an individual adaptive value;
step 5.5, storing the optimal individual SGX in the population;
step 5.6, setting a buffer value kc ═ rand (0,1), wherein rand is a random real number generation function;
step 5.7, setting a threshold probability vp ═ rand (0, 1);
step 5.8, calculating a combination factor vc according to the formula (1):
wherein the inertia weight kw is a random number between [0,0.2 ];
step 5.9, set the scaling factorSetting the zoom angle scag to [0,2 x π]Random real numbers in between; set the spreading factor ser to [0,2]Random real numbers in between;
step 5.10, setting an operator probability value ecp as rand (0,1), wherein the rand function is a random number function, and the parameter of the rand function is the range generated by the random number;
step 5.11, if ecp is less than 0.4, go to step 5.13, otherwise go to step 5.12;
step 5.12, go to step 5.15 if ecp is less than 0.8, otherwise go to step 5.17;
step 5.13, executing a sine search operator according to the formula (2):
wherein the subscript i ═ 1,2, …, MPsize;representing the ith individual in the population;representing the ith individual in the new generation of population; sin is a sine function;
step 5.14, go to step 5.19;
step 5.15, executing a cosine search operator according to the formula (3):
wherein cos is a cosine function;
step 5.16, go to step 5.19;
step 5.17, executing a combined search operator according to the formula (4):
wherein PLB is the current search lower bound of the population; PUB is the current search upper bound of the population; the inverse learning factor kow is a random real number between [0,1 ];
step 5.18, ifIs less thanIf the adaptive value is not the same as the adaptive value, setting a cache value kc as vc, otherwise, keeping kc unchanged;
step 5.19, ifIs less thanThe adaptive value of (1) is then utilizedReplacement ofOtherwise, it keepsThe change is not changed;
step 5.20, storing the optimal individual SGX in the population, and then setting the current search algebra t to t + 1;
step 5.21, if the current search algebra t is smaller than MXG, turning to step 5.7, otherwise, turning to step 5.22;
and 5.22, extracting parameters of the optimized design of the government and enterprise service text classifier from the optimal individual SGX.
The optimized text classifier of the government and enterprise services is obtained by an optimally designed parameter setting classifier, and the classifier comprises but is not limited to XGboost.
Claims (1)
1. A method for analyzing the tendency of a text of a government and enterprise service is characterized by comprising the following steps:
step 1, collecting a government and enterprise service text;
step 2, preprocessing the collected government and enterprise service texts to generate a government and enterprise service text data set;
step 3, dividing the government and enterprise service text data set into a training data set and a testing data set;
step 4, determining a government and enterprise service text classifier, and determining parameters of the optimal design required by the government and enterprise service text classifier;
step 5, solving parameters of the optimal design required by the government and enterprise service text classifier by using a combined sine and cosine algorithm;
step 6, utilizing the optimized text classifier of the government and enterprise service to realize the tendency analysis of the text of the government and enterprise service;
the step 5 of solving the parameters of the optimized design required by the text classifier of the government and enterprise service by using the combined sine and cosine algorithm comprises the following steps:
step 5.1, setting the population size MPsize and the maximum search algebra MXG;
step 5.2, setting the current search algebra t to be 0;
step 5.3, randomly generating MPsize individuals to form a population, wherein each individual in the population stores parameters of the optimal design required by the text classifier of the government and enterprise service;
step 5.4, calculating the adaptive value of each individual in the population;
step 5.5, storing the optimal individual SGX in the population;
step 5.6, setting a buffer value kc ═ rand (0,1), wherein rand is a random real number generation function;
step 5.7, setting a threshold probability vp ═ rand (0, 1);
step 5.8, calculating a combination factor vc according to the formula (1):
wherein the inertia weight kw is a random number between [0,0.2 ];
step 5.9, set the scaling factorSetting the zoom angle scag to [0,2 x π]Random real numbers in between; set the spreading factor ser to [0,2]Random real numbers in between;
step 5.10, setting an operator probability value ecp ═ rand (0, 1);
step 5.11, if ecp is less than 0.4, go to step 5.13, otherwise go to step 5.12;
step 5.12, go to step 5.15 if ecp is less than 0.8, otherwise go to step 5.17;
step 5.13, executing a sine search operator according to the formula (2):
wherein the subscript i ═ 1,2, …, MPsize;representing the ith individual in the population;representing the ith individual in the new generation of population; sin is a sine function;
step 5.14, go to step 5.19;
step 5.15, executing a cosine search operator according to the formula (3):
wherein cos is a cosine function;
step 5.16, go to step 5.19;
step 5.17, executing a combined search operator according to the formula (4):
wherein PLB is the current search lower bound of the population; PUB is the current search upper bound of the population; the inverse learning factor kow is a random real number between [0,1 ];
step 5.18, ifIs less thanIf the adaptive value is not the same as the adaptive value, setting a cache value kc as vc, otherwise, keeping kc unchanged;
step 5.19, ifIs less thanThe adaptive value of (1) is then utilizedReplacement ofOtherwise, it keepsThe change is not changed;
step 5.20, storing the optimal individual SGX in the population, and then setting the current search algebra t to t + 1;
step 5.21, if the current search algebra t is smaller than MXG, turning to step 5.7, otherwise, turning to step 5.22;
and 5.22, extracting parameters of the optimized design of the government and enterprise service text classifier from the optimal individual SGX.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911170332.3A CN111061871B (en) | 2019-11-26 | 2019-11-26 | Method for analyzing tendency of government and enterprise service text |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911170332.3A CN111061871B (en) | 2019-11-26 | 2019-11-26 | Method for analyzing tendency of government and enterprise service text |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111061871A CN111061871A (en) | 2020-04-24 |
CN111061871B true CN111061871B (en) | 2022-02-22 |
Family
ID=70298257
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911170332.3A Active CN111061871B (en) | 2019-11-26 | 2019-11-26 | Method for analyzing tendency of government and enterprise service text |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111061871B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111581384B (en) * | 2020-04-30 | 2022-06-10 | 广东奥博信息产业股份有限公司 | Enterprise policy text clustering method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103517413A (en) * | 2013-10-09 | 2014-01-15 | 江西理工大学 | WSN node locating method based on heterogeneous double-population particle swarm optimization |
CN104715490A (en) * | 2015-04-09 | 2015-06-17 | 江西理工大学 | Navel orange image segmenting method based on adaptive step size harmony search algorithm |
CN108254678A (en) * | 2018-01-19 | 2018-07-06 | 成都航空职业技术学院 | A kind of analog circuit fault sorting technique based on sine and cosine algorithm |
CN110135752A (en) * | 2019-05-22 | 2019-08-16 | 华东理工大学 | A kind of dispatching method of the whole-set order with switching time |
-
2019
- 2019-11-26 CN CN201911170332.3A patent/CN111061871B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103517413A (en) * | 2013-10-09 | 2014-01-15 | 江西理工大学 | WSN node locating method based on heterogeneous double-population particle swarm optimization |
CN104715490A (en) * | 2015-04-09 | 2015-06-17 | 江西理工大学 | Navel orange image segmenting method based on adaptive step size harmony search algorithm |
CN108254678A (en) * | 2018-01-19 | 2018-07-06 | 成都航空职业技术学院 | A kind of analog circuit fault sorting technique based on sine and cosine algorithm |
CN110135752A (en) * | 2019-05-22 | 2019-08-16 | 华东理工大学 | A kind of dispatching method of the whole-set order with switching time |
Non-Patent Citations (2)
Title |
---|
引入改进鸽群搜索算子的粒子群优化算法;马龙等;《模式识别与人工智能》;20181015(第10期);第909-920页 * |
粒子群优化算法中惯性权值调整的一种新策略;郭文忠等;《计算机工程与科学》;20070128(第01期);第70-72,75页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111061871A (en) | 2020-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lin et al. | An ensemble random forest algorithm for insurance big data analysis | |
Brest et al. | Self-adaptive differential evolution algorithm in constrained real-parameter optimization | |
Temitayo et al. | Hybrid GA-SVM for efficient feature selection in e-mail classification | |
Harikrishnan et al. | A machine learning approach towards phishing email detection | |
CN110472046B (en) | Government and enterprise service text clustering method | |
Hamdi et al. | Assessing and minimizing the impact of OCR quality on named entity recognition | |
Ikeda et al. | Semi-Supervised Learning for Blog Classification. | |
CN111061871B (en) | Method for analyzing tendency of government and enterprise service text | |
Habib et al. | Automatic email spam detection using genetic programming with SMOTE | |
Khairi et al. | Stock price prediction using technical, fundamental and news based approach | |
Setiono et al. | A note on knowledge discovery using neural networks and its application to credit card screening | |
CN106250398A (en) | A kind of complaint classifying content decision method complaining event and device | |
Bondielli et al. | On the use of summarization and transformer architectures for profiling résumés | |
CN108170697A (en) | A kind of international trade document handling method, system and a kind of server | |
US11741318B2 (en) | Open information extraction from low resource languages | |
Jacob et al. | Data Intelligence and Cognitive Informatics Proceedings of ICDICI 2020 | |
Alothman et al. | Towards using transfer learning for botnet detection | |
Frank et al. | Improving on bagging with input smearing | |
Obasa et al. | Hybridization of bag-of-words and forum metadata for web forum question post detection | |
Radaideh et al. | A novel approach to predict the real time sentimental analysis by Naive Bayes & RNN algorithm during the COVID pandemic in UAE | |
JP2010272004A (en) | Discriminating apparatus, discrimination method, and computer program | |
Renuka et al. | An ensembled classifier for email spam classification in hadoop environment | |
US20220365983A1 (en) | Product features map | |
Mahapatra et al. | A systematic approach to enhance the forecasting of bankruptcy data | |
Mallampati et al. | Supervised machine learning classifier for Email spam filtering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Tendency Analysis Method of Government Enterprise Service Text Effective date of registration: 20220930 Granted publication date: 20220222 Pledgee: Guangdong Shunde Rural Commercial Bank Co.,Ltd. science and technology innovation sub branch Pledgor: GUANGDONG OKING INFORMATION INDUSTRY CO.,LTD. Registration number: Y2022980017199 |