CN110288130B - User electricity consumption prediction method - Google Patents
User electricity consumption prediction method Download PDFInfo
- Publication number
- CN110288130B CN110288130B CN201910469792.XA CN201910469792A CN110288130B CN 110288130 B CN110288130 B CN 110288130B CN 201910469792 A CN201910469792 A CN 201910469792A CN 110288130 B CN110288130 B CN 110288130B
- Authority
- CN
- China
- Prior art keywords
- electricity consumption
- electricity
- users
- power consumption
- user
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000009826 distribution Methods 0.000 claims description 25
- 239000000203 mixture Substances 0.000 claims description 13
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 239000002699 waste material Substances 0.000 description 2
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for predicting the electricity consumption of a user, which comprises the following steps: 1) Establishing a limited mixed model with accompanying variables by combining the influence of factors such as user attributes, external conditions and the like on electricity demand; 2) Deconstructing the electricity consumption data of users in a certain area according to the limited mixed model established in the step 1); 3) Deconstructing the total electricity consumption of users in a certain area to obtain an expected value of electricity consumption, and completing the prediction of the electricity consumption of the users; 4) And detecting the accuracy and stability of the total power consumption deconstructment in the step 3) by using the relative error. Compared with the prior art, the method and the device can calculate the power consumption demand probability of different users through the accompanying variables, are beneficial to the prediction of the power consumption demands of the users in the auxiliary area, and can effectively reflect the actual change trend of the electric quantity.
Description
Technical Field
The invention relates to the technical field of power market demand prediction analysis, in particular to a user electricity consumption prediction method.
Background
The electric energy is widely applied to industry, agriculture, enterprises and public institutions and daily life of people, and is an indispensable energy source for national economy and people's life. However, while we enjoy the convenience and brightness of the electric energy brought to us, we also waste the electric energy at the moment. For research and analysis of the electricity demand of the user, the available income of people, the electricity price of the user and the electricity consumption of the user in the last period are selected as factors in the prior art, and an error correction prediction model of the life electricity demand of the resident in the current period is established; based on a panel data model, adopting a self-calculated comprehensive electrical appliance index as an explanatory variable to predict the electricity consumption of residents in a China typical city in detail; and based on analysis of electricity demand influence factors, estimating probability of purchasing behavior of residents for purchasing the household appliances by adopting a multi-element selection model, so as to predict potential electricity consumption levels of the household appliances and household illumination. However, the existing study of resident life electricity demand does not directly deconstruct and analyze the big electric power data, and does not consider the influence of factors such as user attributes, external conditions and the like on the electricity demand, namely how the probability of different electricity demands of users changes along with the change of the variables, so that the obtained result of the probability of electricity demands cannot well reflect the actual change trend of electric quantity.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method for predicting the electricity consumption of a user.
The aim of the invention can be achieved by the following technical scheme:
A method for predicting the electricity consumption of a user comprises the following steps:
Step 1: establishing a limited mixed model with accompanying variables by combining the influence of factors such as user attributes, external conditions and the like on electricity demand;
The expression of the established finite mixture model is:
Where z is an accompanying variable, that is, the probability of each different electricity demand distribution will change along with the change of z, λ i (z) is the probability of the ith gaussian distribution under the condition of z, λ i (z) is a load multivariable logic process, K is the number of distributions, θ i is a parameter of electricity regression of each type of user, y is an explained variable, x is an explained variable, and f (y i|x,θi) is a component gaussian distribution function.
The expression of λ i (z) is:
Step 2: and (3) deconstructing the electricity consumption data of the users in a certain area according to the limited hybrid model established in the step (1).
The expression for deconstructing the electricity consumption data of the users in a certain area is as follows:
f(yijt|xt,θij)＝
θji0+θji1TEMPERATUREt+θji2RAINt+θji3HUMIDt+θji4WINDt+εji
Wherein lambda ij(zt) comprises the TEMPERATURE and climate conditions represented by WEATHER, DATE and TIME respectively represent different electricity utilization DATEs and moments, PEOPLE represents personnel flow movement data and the total electricity consumption Y in the current period, f (Y ijt|xt,θij) comprises the influence factors of TEMPERATURE TEMPERRATURE t, rainfall RAIN t, humidity HUMID t and WIND speed WIND t, v ji is the expected value of the j-th electrical appliance in the i state, epsilon ji is the residual error of the j-th electrical appliance in the i state, and the normal distribution is met.
Step 3: and deconstructing the total electricity consumption of the users in a certain area to obtain an expected value of the electricity consumption, and completing the prediction of the electricity consumption of the users.
Predicting each electric appliance according to the current total power consumption Y and the weather, date and time information of the current period, and expressing the sub power consumption Y jy as:
the main input variables are the total power consumption Y t in the current period, weather and time variables;
and respectively calculating the probabilities of different states of the jth electric appliance according to the above formula, and calculating the expected electricity consumption value of the jth electric appliance under the current total Y electricity consumption by combining the probabilities of different states, so as to complete the decomposition of the total electricity consumption in the current period.
Step 4: and detecting the accuracy and stability of the total power consumption deconstructment in the step 3) by using the relative error.
The relative error is expressed as:
wherein N is the total number of electric appliances, and T is the length of data quantity.
Compared with the prior art, the invention has the following advantages:
1. According to the method, the power big data are deconstructed for analysis, and the prediction result of the total power consumption is obtained by combining the influence of factors such as user attributes and external conditions on the power consumption requirement, so that the actual change trend of the electric quantity can be effectively reflected;
2. According to the invention, a finite mixed model with the accompanying variables is introduced, wherein the accompanying variables determine the classification basis of different electricity demands of users, and the probability of the electricity demands of different users can be calculated through the accompanying variables, so that the prediction of the electricity demands of the users in an auxiliary area is facilitated, the reasonable formulation of annual planning of an electric power market is facilitated, and the waste of resources is avoided.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The finite mixture model assumes that the observation sample is a mixture distribution composed of a plurality of distributions together. Specifically, the system F is formed by K distributions together, wherein K is obtained by data driving judgment. The gaussian mixture distribution is a mixture distribution form formed by combining K gaussian distributions, and the expression is as follows:
Wherein F (K, λ, μ, σ) is the observed mixed distribution, F (μ i,σi) is the component Gaussian distribution function, λ i is the probability of each independent distribution occurring, wherein λ i >0, and Marron and Wand (1992) [32] has demonstrated that any one continuous probability distribution can be fitted by a finite number of gaussian distributions, so that the analysis results of the hybrid model do not change with the distribution pattern of observations.
The finite mixture model may divide the observation distribution into a plurality of gaussian distributions and is therefore essentially a classification. When electricity demand research is carried out, not only the electricity demand classification of a user is required to be researched, but also the influence of factors such as user attributes, external conditions and the like on the electricity demand is required to be known.
As shown in fig. 1, the present invention relates to a method for predicting electricity consumption of a user, which includes the following steps:
Step one, establishing a limited hybrid model by combining the influence of factors such as user attributes, external conditions and the like on electricity demand, wherein the basic form is as follows:
where z is an accompanying variable, i.e. the probability that each different electricity demand profile will vary with z, and In the present invention, λ (z) i is considered to be a load multivariable logic process, namely:
Where λ i (z) is the probability of the ith gaussian distribution under z.
Further, one common way to develop the finite mixture model is to develop F (K, λ, μ, σ) in the finite mixture distribution into a regression form, i.e.:
Where y is the interpreted variable, x is the interpreted variable, and θ i is the parameter of each type of user power regression. This formula is the basic form of finite mixture regression, which considers the observed value y to be a conditional distribution based on x.
By combining the two expansion modes, on the basis of the finite mixed regression, the accompanying variable can be added according to the influence of other factors of the observed value on the probability of the regression component of the observed value, namelyWriting:
and secondly, deconstructing the commercial building data by using an FMM model.
When deconstructing and analyzing the sub-item electricity consumption of the commercial building by using the limited hybrid model, the report assumes that the j-th sub-item electricity consumption of the commercial building is composed of K states at the time t, and meanwhile, the probability of different electricity consumption states is influenced by the date, the temperature and the climate condition variable z, so that the report can be rewritten as follows:
The method is characterized in that the method is a finite mixed model of the electricity consumption of the j-th electric appliance t of a building, and theta ij represents the relation between the electricity consumption y ijt of the i-th state of the j-th electric appliance and an influence factor x t; λ is the probability corresponding to the jth electrical apparatus, and z is the influence factor corresponding to the jth electrical apparatus. Therefore, the electric appliance j has different state composition ratios according to different date and time characteristics, and therefore has different temperature sensitivity and other characteristics, so that the electric appliance j has different electric power consumption.
Since commercial buildings have obvious differences in electricity consumption at different times of the year, even the feedback degree of the same climate is different, such as different feedback degrees of the variable of raining at night and daytime; the occurrence probability of different states is also affected by various factors, such as holidays and holidays, and the power consumption of different buildings is increased differently due to the different crowds; even in a day, the electricity demands at different times are different, an office building often enters into an electricity consumption valley after five afternoon, and a market often meets an electricity consumption peak at night in a workday; likewise, different weather at the same time may also have an effect on the probability of the state of electricity usage occurring. Thus, f (y ijt|xt,θij) can be written with λ ij(zt:
f(yijt|xt,θij)＝
θji0+θji1TEMPERATUREt+θji2RAINt+θji3HUMIDt+θji4WINDt+εji
The main variables of lambda ij(zt) include temperature and climate conditions represented by WEATHER, different electricity utilization DATEs and moments represented by DATE and TIME, personnel flow movement data represented by PEOPLE and the current total electricity consumption Y, f (Y ijt|xt,θij) mainly comprise influencing factors of temperature, rainfall, humidity and wind speed. In addition, v ji is the expected value of the j-th electric appliance in the i state, epsilon ji is the residual error of the j-th electric appliance in the i state, and the normal distribution is met.
And thirdly, deconstructing the total power consumption.
The deconstructing of the total power consumption is essentially to predict each power consumption according to the current total power consumption Y and the weather, date and time information of the current period. The distributor demand y j can thus be expressed as:
yj＝E(yj|Y,z,x,βj,θj,Kj)
Wherein Y j is the electricity consumption of a certain electric appliance j, Y is the total electricity consumption in the current period, x is the influencing factor of the state, z is a variable influencing the occurrence probability of different states, beta j,θj is a model parameter, and K j is the total state number of the electric appliance j. Where β j,θj,Kj is affected by the properties of the building, location, skill level, user composition, etc. For the same building, these parameters remain unchanged, so the fractional power usage can be expressed as:
Therefore, the main input variables are the total electricity consumption Y, weather and time variables in the current period, different states of the electricity consumption j are calculated respectively, and the expected electricity consumption value of the electricity consumption j of the current period Y under the total electricity consumption can be calculated by combining the probabilities of the different states, so that the total electricity consumption in the current period is decomposed.
And step four, calculating deconstructing errors.
The accuracy and stability of model deconstructment are expressed by using relative errors, and the relative errors of each electric appliance are defined as follows:
The total error is:
Wherein N is the total number of electric appliances, and T is the length of data quantity.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions may be made without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (3)
1. A method for predicting power consumption of a user, the method comprising the steps of:
1) Establishing a limited mixed model with accompanying variables by combining the influence of user attributes and external conditions on electricity demand;
2) Deconstructing the electricity consumption data of users in a certain area according to the limited mixed model established in the step 1);
3) Deconstructing the total electricity consumption of the users in the area to obtain an expected value of electricity consumption, and completing the prediction of the electricity consumption of the users;
4) Detecting the accuracy and stability of the total power consumption deconstructment in the step 3) by using the relative error;
in the step 1), the expression of the established finite mixture model is as follows:
wherein z is an accompanying variable, namely the probability of each different electricity demand distribution changes along with the change of z, lambda generally refers to the probability of electricity consumption of a user, lambda i (z) is the probability of the ith Gaussian distribution under the condition of z, lambda i (z) is a load multivariable logic process, K is the quantity of the distribution, theta generally refers to the coefficient of electricity consumption regression of the user, theta i is the parameter of electricity consumption regression of each type of user, y is an explained variable, x is an explained variable, and f (y i|x,θi) is a component Gaussian distribution function;
in the step 2), the expression for deconstructing the electricity consumption data of the users in a certain area is as follows:
f(yijt|xt,θji)＝
θji0+θji1TEMPERATUREt+θji2RAINt+θji3HUMIDt+θji4WINDt+εji
Wherein, lambda ij(zt) includes TEMPERATURE and climate condition information represented by WEATHER t, different electricity utilization DATEs represented by DATE t, different electricity utilization moments represented by TIME t, personnel flow movement data represented by PEOPLE and total electricity consumption Y t,f(yijt|xt,θji) in the current period, and the interpretation variables include TEMPERATURE TEMPERTURE t, rainfall RAIN t, humidity HUMID t and WIND speed WIND t,vji are expected values of the j-th electrical appliance in the i state, epsilon ji is residual error of the j-th electrical appliance in the i state, and accords with normal distribution, and beta is a coefficient of logical regression of the general index concomitant variable z;
The specific content of the step 3) is as follows:
The current total power consumption Y t and current weather, date and time information are used for predicting each electric appliance, and the sub power consumption Y jt is expressed as:
The input variables are the total power consumption Y t in the current period, weather and time variables;
And respectively calculating the probabilities of different states of the jth electric appliance according to the above formula, and calculating the expected electricity consumption value of the jth electric appliance under the total electricity consumption Y t in the current period by combining the probabilities of different states, so as to complete the decomposition of the total electricity consumption in the current period.
2. The method for predicting power consumption of a user according to claim 1, wherein in the step 1), λ i (z) has the expression:
3. the method for predicting power consumption of a user according to claim 1, wherein in the step 4), the expression of the relative error is:
Where T is the time series length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910469792.XA CN110288130B (en) | 2019-05-31 | 2019-05-31 | User electricity consumption prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910469792.XA CN110288130B (en) | 2019-05-31 | 2019-05-31 | User electricity consumption prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288130A CN110288130A (en) | 2019-09-27 |
| CN110288130B true CN110288130B (en) | 2024-04-30 |
Family
ID=68003045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910469792.XA Active CN110288130B (en) | 2019-05-31 | 2019-05-31 | User electricity consumption prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288130B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027202B (en) * | 2019-12-04 | 2023-12-15 | 北京软通绿城科技有限公司 | Digital city prediction method, device, equipment and storage medium |
| CN111506636A (en) * | 2020-05-12 | 2020-08-07 | 上海积成能源科技有限公司 | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268769A (en) * | 2014-03-11 | 2015-01-07 | 南方电网科学研究院有限责任公司 | Time-of-use electricity price design method based on model clustering method |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105844351A (en) * | 2016-03-22 | 2016-08-10 | 广西电网有限责任公司电力科学研究院 | Prosperity index prediction method for electric power consumption market |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9595006B2 (en) * | 2013-06-04 | 2017-03-14 | International Business Machines Corporation | Detecting electricity theft via meter tampering using statistical methods |
-
2019
- 2019-05-31 CN CN201910469792.XA patent/CN110288130B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268769A (en) * | 2014-03-11 | 2015-01-07 | 南方电网科学研究院有限责任公司 | Time-of-use electricity price design method based on model clustering method |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105844351A (en) * | 2016-03-22 | 2016-08-10 | 广西电网有限责任公司电力科学研究院 | Prosperity index prediction method for electric power consumption market |
Non-Patent Citations (1)
| Title |
|---|
| 结构化用电客户互动需求信息的比对库设计;窦健 等;《电力系统及其自动化学报》;20160630;第28卷(第6期);80-85 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288130A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zeng et al. | Analysis and forecast of China's energy consumption structure | |
| Parhizkar et al. | Evaluation and improvement of energy consumption prediction models using principal component analysis based feature reduction | |
| Palmer et al. | Modeling the diffusion of residential photovoltaic systems in Italy: An agent-based simulation | |
| Korcaj et al. | Intentions to adopt photovoltaic systems depend on homeowners' expected personal gains and behavior of peers | |
| Fei et al. | Technology gap and CO2 emission reduction potential by technical efficiency measures: A meta-frontier modeling for the Chinese agricultural sector | |
| Yalcintas et al. | An energy benchmarking model based on artificial neural network method utilizing US Commercial Buildings Energy Consumption Survey (CBECS) database | |
| Wei et al. | A study of city-level building energy efficiency benchmarking system for China | |
| Doukas | Modelling of linguistic variables in multicriteria energy policy support | |
| CN110288130B (en) | User electricity consumption prediction method | |
| CN112330065A (en) | Runoff forecasting method based on basic flow segmentation and artificial neural network model | |
| CN110751312A (en) | Multi-factor-based system dynamics life water demand prediction method and system | |
| CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
| CN113326654A (en) | Method and device for constructing gas load prediction model | |
| CN110060109A (en) | It is a kind of for predicting the method, apparatus and computer media of product price | |
| CN115860797A (en) | Electric quantity demand prediction method suitable for new electricity price reform situation | |
| Buera et al. | The stable transformation path | |
| Abulibdeh | Geospatial assessment of the carbon footprint of water and electricity consumption in residential buildings in Doha, Qatar | |
| Liu et al. | Evaluation of the prediction performance of air quality numerical forecast models in Shenzhen | |
| CN117876150A (en) | Short-term multiple comprehensive load prediction method based on non-invasive load decomposition algorithm | |
| Yang et al. | Does the green finance reform and innovation experimental zone policy reduce carbon emission intensity? Evidence from Chinese cities | |
| Liu et al. | Cultural Factors Influencing Domestic Adoption of Solar Photovoltaic Technology: Perspectives from China. | |
| Zapata-Webborn et al. | The short-and long-term impacts of COVID-19 on household energy consumption in England and Wales | |
| Bobinaitė et al. | Theoretical model for electricity market price forecasting | |
| Kaneko et al. | Graphical Modeling for Analysis of Hourly Electricity Demand and Market Price | |
| Qiubo et al. | Do ICTs boost agricultural productivity? |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Su Yun Inventor after: Zhang Qiqi Inventor after: Shi Zhixiong Inventor after: Song Yan Inventor after: Pang Tianyu Inventor after: Shen Quanjiang Inventor after: Wu Libo Inventor after: Zhou Yang Inventor after: Ma Rong Inventor after: Shi Zhengyu Inventor after: Chen Wei Inventor after: Guo Naiwang Inventor after: Tian Yingjie Inventor after: Qu Haini Inventor before: Su Yun Inventor before: Zhang Qiqi Inventor before: Shi Zhixiong Inventor before: Song Yan Inventor before: Pang Tianyu Inventor before: Shen Quanjiang Inventor before: Wu Libo Inventor before: Zhou Yang Inventor before: Ma Rong Inventor before: Shi Zhengyu Inventor before: Chen Wei Inventor before: Guo Naiwang Inventor before: Tian Yingjie Inventor before: Qu Haini |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |