CN113779391A - Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium - Google Patents
Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium Download PDFInfo
- Publication number
- CN113779391A CN113779391A CN202111025858.XA CN202111025858A CN113779391A CN 113779391 A CN113779391 A CN 113779391A CN 202111025858 A CN202111025858 A CN 202111025858A CN 113779391 A CN113779391 A CN 113779391A
- Authority
- CN
- China
- Prior art keywords
- intelligent lock
- data
- unlocking
- user
- model
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
Abstract
The invention discloses an intelligent lock unlocking recommendation method based on modeling, which comprises the steps of obtaining data information of a plurality of intelligent locks, user data information bound by each intelligent lock, and user unlocking data corresponding to each intelligent lock to form a data set and storing the data set in a database, then obtaining a training data set and a testing data set from the database and respectively using the training data set and the testing data set for model training and testing, and using the model after the testing is passed for recommending the unlocking mode of the intelligent lock to a user. According to the method and the device, the automatic recommendation of the user unlocking mode is realized through modeling analysis on the user unlocking data, and the user experience is improved. The invention also provides an intelligent lock unlocking recommendation system, an intelligent lock unlocking recommendation device and a storage medium based on modeling.
Description
Technical Field
The invention relates to intelligent lock control, in particular to an intelligent lock unlocking recommendation method, system, device and storage medium based on modeling.
Background
With the development of science and technology, the intelligent lock can be unlocked in any one or more ways, such as a password, a fingerprint, a lock card, a key, a human face and the like. At present when promoting the user experience of opening the door, most trade companies are through spending a large amount of money, time etc. on the equipment of intelligence lock itself to research and develop novel intelligence lock, for example do more improvement on the structure of intelligence lock, or integrated multiple mode of unblanking etc. promote user experience, but this kind of mode has characteristics such as research and development cost height, applicable time period.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide an intelligent lock unlocking recommendation method based on modeling, which can solve the problems of high research and development cost, short application time and the like caused by improving user experience by improving the structure of an intelligent lock.
The invention also aims to provide an intelligent lock unlocking recommendation system based on modeling, which can solve the problems of high research and development cost, short application time and the like caused by improving user experience by improving the structure of an intelligent lock.
The invention further aims to provide an intelligent lock unlocking recommendation device based on modeling, which can solve the problems of high research and development cost, short application time and the like caused by improvement of user experience through structural improvement of an intelligent lock.
The fourth objective of the present invention is to provide a storage medium, which can solve the problems of high research and development cost, short application time, etc. caused by improving user experience through structural modification of an intelligent lock itself in the prior art.
One of the purposes of the invention is realized by adopting the following technical scheme:
the intelligent lock unlocking recommendation method based on modeling comprises the following steps:
a data acquisition step: acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock, forming a data set, and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode;
model training: obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application steps are as follows: and acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound with the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
Further, the data acquisition step: acquiring data according to a preset data acquisition format; the data information of the intelligent lock comprises the type of the intelligent lock, an unlocking mode supported by the intelligent lock, a manufacturer of the intelligent lock, the production date of the intelligent lock and the type of the intelligent lock;
the user data information comprises one or more combinations of user age, user family address and user family members;
the user unlocking data corresponding to the intelligent lock refers to user unlocking data generated by the intelligent lock binding user within a preset time period;
the user operation data corresponding to the intelligent lock further comprises one or more of unlocking time and weather conditions during unlocking.
Further, the data acquisition step further comprises preprocessing the acquired data.
Further, preprocessing the acquired data comprises cleaning the acquired data; the data cleaning processing refers to clearing processing of null data and abnormal data in the acquired data.
Further, the selected modeling model is a linear regression model.
Further, the model training step further comprises: and (3) testing the model: obtaining a test data set from a database, testing the trained modeling model according to the test data set, and judging whether the trained modeling model meets the system requirements or not according to a test result; if so, taking the trained modeling model as an intelligent lock unlocking recommendation model and executing the application steps; if not, continuing to execute the model training step.
Further, the data set in the database is divided into a training data set and a testing data set according to a preset sampling method.
Further, the method also comprises the updating step: after the unlocking mode recommended by the user corresponding to the intelligent lock to be recommended is obtained, the data information of the intelligent lock, the user data information bound by the intelligent lock and the user unlocking data corresponding to the intelligent lock are stored in a database, a data set in the database is updated, and then a model training step is executed to obtain an updated intelligent lock unlocking recommendation model.
The second purpose of the invention is realized by adopting the following technical scheme:
intelligent lock unblock recommendation system based on modeling includes:
the data acquisition module is used for acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock by a user, forming a data set and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode;
the model training module is used for obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application module is used for acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound to the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
The third purpose of the invention is realized by adopting the following technical scheme:
the modeling-based intelligent lock unlocking recommendation device comprises a processor and a memory for storing a program executable by the processor, wherein the processor executes the program stored by the memory to realize the steps of the modeling-based intelligent lock unlocking recommendation method adopted by one of the purposes of the invention.
The fourth purpose of the invention is realized by adopting the following technical scheme:
a storage medium being a computer readable storage medium having stored thereon a computer program being an intelligent lock unlock recommendation program which, when executed by a processor, implements the steps of a modeling-based intelligent lock unlock recommendation method as employed by one of the objects of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention realizes the incidence relation between the user information and the user unlocking mode by analyzing and modeling the data related to unlocking generated by the system when the user unlocks, thereby automatically recommending a proper unlocking mode for the user and improving the unlocking experience of the user;
(2) in the method, after the unlocking mode of the intelligent lock to be recommended is obtained, a database is updated through data information of the intelligent lock, user data information bound by the intelligent lock and user unlocking data corresponding to the intelligent lock, then the updated data in the database are divided into test data and training data, and a model training step and a model testing step are executed to obtain an updated intelligent lock unlocking recommendation model;
(3) the collected data are preprocessed during modeling, so that the processing efficiency of the system is higher and modeling is more accurate during subsequent model training.
Drawings
FIG. 1 is a schematic block diagram of various parts involved in an intelligent lock unlocking recommendation method based on modeling provided by the invention;
fig. 2 is a flowchart of an intelligent lock unlocking recommendation method provided by the invention in view of modeling.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Example one
The unlocking method of the intelligent lock used by the user is obtained through research on the aspect of user data of the intelligent lock used by the user, so that the personalized requirements of the user can be met, the unlocking experience of the user is improved, and compared with the existing method for improving the unlocking experience of the user through research and development of the equipment structure of the intelligent lock, the intelligent lock has the characteristics of low research and development cost, long application time, wide related population and the like.
As shown in fig. 1-2, the present invention provides a preferred embodiment, a modeling-based intelligent lock unlocking recommendation method, which involves the following steps: data acquisition, data storage, model training, model testing and application.
The data acquisition is used for acquiring data generated in an application APP of the intelligent lock; meanwhile, data requirements for collecting data are set, such as content including data format, data type and the like. In addition, the acquired data is data related to the unlocking mode of the intelligent lock or data influencing the unlocking mode, namely user unlocking data. The user unlocking data comprises user operation data and an unlocking mode. The user operation data refers to direct data and indirect data generated in the APP when the user unlocks, such as unlocking time and weather conditions during unlocking. The unlocking mode comprises a human face, a fingerprint, a password, a lock card and the like.
More specifically, the data collected in this embodiment further includes data information of the smart lock and user data information bound to the smart lock, such as the age of the user, the home address of the user, and family members of the user.
In addition, the acquired data in this embodiment is offline data, and data generated by applying the APP within a preset time period is acquired by setting a preset time period.
The data in this embodiment is not only for a certain smart lock, but also for a plurality of types of smart locks. For example, for a manufacturer, the manufacturer can track the user usage data of all models of smart locks manufactured and sold by the manufacturer, so as to analyze the data later, and recommend an appropriate smart lock to a corresponding user.
And the data storage is used for preprocessing the data acquired by the data acquisition and then storing the data into a corresponding database. Such as removing unsatisfactory data for subsequent modeling processes to improve system processing efficiency and modeling accuracy. Where unsatisfactory data such as null data, exception data, etc. In addition, when the data are stored, the collected data are classified and stored in a time mode.
And model training, namely performing model training on data stored in the database according to the selected model, the prediction problem and the like to obtain a corresponding model.
When the model is trained, the task needing model training is a prediction problem, and the training method is supervised learning, so that the linear regression method is selected for modeling. Meanwhile, the data stored in the database is divided into training data and test data before data training. The training data is used for model training, and the test data is used for testing the trained model.
And testing the model, namely testing the trained model to realize the verification of the model. And testing the trained model to verify whether the trained model meets the system requirements, if so, applying the model, and if not, returning to train the model continuously until the system requirements are met. Testing the trained model so as to obtain a model passing the test for subsequent matching; if the trained model can not pass the test, the model can be continuously trained until the model meeting the system condition is obtained.
And the application means that the model passing the test is applied to corresponding software or an interface is formed and provided for the application. Namely, the obtained model is applied to an actual application scene to realize recommendation of an unlocking mode of a user. For example, the method can be applied to an APP bound by an intelligent lock, and the recommendation of the unlocking mode of the user can be realized.
Meanwhile, the model in the embodiment can also be applied to a merchant, and the merchant can analyze the unlocking modes of all users in a certain specific area so as to formulate a corresponding sales strategy, such as researching, developing or selling an intelligent lock with a recommended proper model for a specific area.
Specifically, as shown in fig. 2, the modeling-based intelligent lock unlocking recommendation method provided in this embodiment includes the following steps:
and step S1, acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock, and storing the data set in a database.
The data information of the intelligent lock comprises various data such as the model of the intelligent lock, the type of the intelligent lock, the unlocking mode supported by the intelligent lock, the manufacturer of the intelligent lock, the production date of the intelligent lock and the like. Because different intelligent locks have different functions, such as different supported unlocking modes and unlocking operations, the data information of the intelligent locks is recommended to be considered when the user recommends the unlocking mode.
The user unlocking data comprises user operation data and an unlocking mode. The user operation data comprises weather conditions and unlocking time during unlocking. The user data information includes the user age, the user home address, and the like.
In addition, when data are counted, statistics can be performed in a day-to-day period, for example, weather conditions, unlocking time, unlocking mode and unlocking times of a user during unlocking every day are counted.
Since the present embodiment is implemented by modeling, the data to be acquired is a large amount of data, and thus, the data may be acquired by setting a time period. Such as historical data generated within the corresponding APP from the beginning of use of an intelligent lock. When the data are collected, the data can be acquired in a point burying mode. For the weather conditions, the weather conditions can be obtained through a third-party platform in the mobile device, such as a china weather network, other weather applications APP, and the like.
Specifically, data is stored in a database while being sorted by time.
Furthermore, all the collected data are preprocessed and then stored in a database. The preprocessing refers to performing data cleaning processing on the acquired data, for example, performing cleaning processing on data such as null data and abnormal data. The abnormal data may include a list of data lacking weather conditions, a negative age of the user, and the like. Null data refers to data whose data type is null, or the like.
In addition, the data in this embodiment is offline data, and the data volume is large, so this embodiment performs data storage by selecting a database, and performs partitioned storage in time during storage.
And step S2, obtaining a training data set from the database, and training the selected modeling model according to the training data set to further obtain an intelligent lock unlocking recommendation model.
More specifically, in order to evaluate the trained model, the embodiment further includes step S3, obtaining a test data set from the database, testing the trained model according to the test data set, and determining whether the trained model meets the requirements according to the test result, if so, taking the trained model as a final intelligent lock-unlocking recommendation model, and then executing step S4; otherwise, execution continues with step S2.
The training data set and the testing data set taken out from the database can divide the data stored in the database according to a preset proportion. For example, the data may be divided into a training data set and a test data set on a 4:1 scale. In addition, when the data is divided, the consistency of the time distribution of the data in the test set and the training set is also ensured. The test set refers to a data set formed by test data, and the training set refers to a data set formed by training data.
More specifically, the model in this embodiment is a linear regression model. That is, modeling is performed according to a linear regression model and the generated model is trained according to training data.
Wherein, in training, the selected attribute X ═ X (X)1,x2,x3,...) wherein xiData representing the collected corresponding items, such as user age, weather conditions, user home address, unlocking time, and the like.
Y is f (x), wherein Y represents the unlocking mode of the intelligent lock.
That is, in the present embodiment, the binding relationship between the unlocking manner of the intelligent lock and the collected data information, the user age, the weather condition, the user home address, the unlocking time, and the like of the intelligent lock is established through the linear regression model, so as to predict the unlocking manner in the following.
During testing, the mean square error can be selected to judge whether the performance of the trained model meets the system requirements. Wherein, the mean square error formula is:
and S4, acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound with the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
After a user installs an intelligent lock, the intelligent lock is bound to an application APP, and then corresponding unlocking modes can be recommended to the user according to the tested model for the user data information of the intelligent lock, the data information of the intelligent lock and the user operation data, so that the user experience is improved.
In addition, the embodiment can also update the modeled model. The newly acquired user data information bound by the intelligent lock to be recommended, the data information of the intelligent lock to be recommended and the user unlocking data generated in the application APP bound by the intelligent lock are stored in the database, so that model training can be continued according to the updated database.
Example two
Based on the first embodiment, the invention also provides an embodiment, and the intelligent lock unlocking recommendation system based on modeling comprises the following modules:
the data acquisition module is used for acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock by a user, forming a data set and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode.
And the model training module is used for obtaining a training data set from a database and training the selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model.
The application module is used for acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound to the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
EXAMPLE III
Based on the first embodiment, the invention further provides another embodiment, and the modeling-based intelligent lock unlocking recommendation device comprises a processor and a memory for storing an executable program of the processor, wherein the processor implements the following steps when executing the program stored in the memory:
a data acquisition step: acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock to form a data set and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode;
model training: obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application steps are as follows: and acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound with the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
Further, the data acquisition step: acquiring data according to a preset data acquisition format; the data information of the intelligent lock comprises the type of the intelligent lock, an unlocking mode supported by the intelligent lock, a manufacturer of the intelligent lock, the production date of the intelligent lock and the type of the intelligent lock;
the user data information comprises one or more combinations of user age, user family address and user family members;
the user unlocking data corresponding to the intelligent lock refers to user unlocking data generated by the intelligent lock binding user within a preset time period;
the user operation data corresponding to the intelligent lock further comprises one or more of unlocking time and weather conditions during unlocking.
Further, the data acquisition step further comprises preprocessing the acquired data.
Further, preprocessing the acquired data comprises cleaning the acquired data; the data cleaning processing refers to clearing processing of null data and abnormal data in the acquired data.
Further, the selected modeling model is a linear regression model.
Further, the model training step further comprises: and (3) testing the model: obtaining a test data set from a system, testing the trained modeling model according to the test data set, and judging whether the trained modeling model meets the system requirements or not according to a test result; if so, taking the trained modeling model as an intelligent lock unlocking recommendation model and executing the application steps; if not, continuing to execute the model training step.
Further, the data set in the database is divided into a training data set and a testing data set according to a preset sampling method.
Further, the processor, when executing the program stored in the memory, implements the steps of: an updating step: after the unlocking mode recommended by the user corresponding to the intelligent lock to be recommended is obtained, the data information of the intelligent lock, the user data information bound by the intelligent lock and the user unlocking data corresponding to the intelligent lock are stored in a database, a data set in the database is updated, and then a model training step is executed to obtain an updated intelligent lock unlocking recommendation model.
Example four
Based on the first embodiment provided by the present invention, the present invention further provides an embodiment, a storage medium, where the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, where the computer program is an intelligent lock unlocking recommendation program, and when executed by a processor, the intelligent lock unlocking recommendation program implements the following steps:
a data acquisition step: acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock to form a data set and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode;
model training: obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application steps are as follows: and acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound with the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
Further, the data acquisition step: acquiring data according to a preset data acquisition format; the data information of the intelligent lock comprises the type of the intelligent lock, an unlocking mode supported by the intelligent lock, a manufacturer of the intelligent lock, the production date of the intelligent lock and the type of the intelligent lock;
the user data information comprises one or more combinations of user age, user family address and user family members;
the user unlocking data corresponding to the intelligent lock refers to user unlocking data generated by the intelligent lock binding user within a preset time period;
the user operation data corresponding to the intelligent lock further comprises one or more of unlocking time and weather conditions during unlocking.
Further, the data acquisition step further comprises preprocessing the acquired data.
Further, preprocessing the acquired data comprises cleaning the acquired data; the data cleaning processing refers to clearing processing of null data and abnormal data in the acquired data.
Further, the selected modeling model is a linear regression model.
Further, the model training step further comprises: and (3) testing the model: obtaining a test data set from a system, testing the trained modeling model according to the test data set, and judging whether the trained modeling model meets the system requirements or not according to a test result; if so, taking the trained modeling model as an intelligent lock unlocking recommendation model and executing the application steps; if not, continuing to execute the model training step.
Further, the data set in the database is divided into a training data set and a testing data set according to a preset sampling method.
Further, when being executed by the processor, the intelligent lock unlocking recommendation program realizes the following steps: an updating step: after the unlocking mode recommended by the user corresponding to the intelligent lock to be recommended is obtained, the data information of the intelligent lock, the user data information bound by the intelligent lock and the user unlocking data corresponding to the intelligent lock are stored in a database, a data set in the database is updated, and then a model training step is executed to obtain an updated intelligent lock unlocking recommendation model.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. The intelligent lock unlocking recommendation method based on modeling is characterized by comprising the following steps:
a data acquisition step: acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock, and storing the data set in a database after forming a data set; the user unlocking data comprises user operation data and an unlocking mode;
model training: obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application steps are as follows: and acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound with the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
2. The modeling-based intelligent lock unlocking recommendation method according to claim 1, wherein the data acquisition step comprises: acquiring data according to a preset data acquisition format; the data information of the intelligent lock comprises the type of the intelligent lock, an unlocking mode supported by the intelligent lock, a manufacturer of the intelligent lock, the production date of the intelligent lock and the type of the intelligent lock;
the user data information comprises one or more combinations of user age, user family address and user family members;
the user unlocking data corresponding to the intelligent lock refers to user unlocking data generated by the intelligent lock binding user within a preset time period;
the user operation data corresponding to the intelligent lock comprises one or more of unlocking time and weather conditions during unlocking.
3. The modeling-based intelligent lock unlocking recommendation method according to claim 2, wherein the data acquisition step further comprises preprocessing the acquired data;
preprocessing the acquired data, including performing data cleaning processing on the acquired data; the data cleaning processing refers to clearing processing of null data and abnormal data in the acquired data.
4. The modeling-based smart lock unlock recommendation method of claim 1 wherein the selected modeling model is a linear regression model.
5. The modeling-based intelligent lock unlocking recommendation method according to claim 1, wherein the model training step is followed by further comprising: and (3) testing the model: obtaining a test data set from a database, testing the trained modeling model according to the test data set, and judging whether the trained modeling model meets the system requirements or not according to a test result; if so, taking the trained modeling model as an intelligent lock unlocking recommendation model and executing the application steps; if not, continuing to execute the model training step.
6. The modeling-based intelligent lock unlocking recommendation method according to claim 5, wherein the data sets in the database are divided into a training data set and a testing data set according to a preset sampling method.
7. The modeling-based intelligent lock unlocking recommendation method according to claim 1, characterized by further comprising the updating step of: after the unlocking mode recommended by the user corresponding to the intelligent lock to be recommended is obtained, the data information of the intelligent lock, the user data information bound by the intelligent lock and the user unlocking data corresponding to the intelligent lock are stored in a database, a data set in the database is updated, and then a model training step is executed to obtain an updated intelligent lock unlocking recommendation model.
8. Intelligence lock recommendation system that unblanks based on modeling, its characterized in that includes:
the data acquisition module is used for acquiring data information of a plurality of intelligent locks, user data information bound by each intelligent lock and user unlocking data corresponding to each intelligent lock by a user, forming a data set and storing the data set in a database; the user unlocking data comprises user operation data and an unlocking mode;
the model training module is used for obtaining a training data set from a database and training a selected modeling model according to the training data set so as to obtain an intelligent lock unlocking recommendation model;
the application module is used for acquiring the intelligent lock to be recommended, and matching the data information of the intelligent lock to be recommended, the user data information bound to the intelligent lock to be recommended, and the real-time user operation data corresponding to the intelligent lock to be recommended with the intelligent lock unlocking recommendation model to obtain the unlocking mode recommended to the user.
9. The modeling-based intelligent lock unlocking recommendation device comprises a processor and a memory for storing a program executable by the processor, and is characterized in that the processor implements the steps of the modeling-based intelligent lock unlocking recommendation method according to any one of claims 1-7 when executing the program stored in the memory.
10. A storage medium, which is a computer readable storage medium, and on which a computer program is stored, wherein the computer program is a smart lock unlock recommendation program, and when executed by a processor, the smart lock unlock recommendation program implements the steps of the modeling-based smart lock unlock recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111025858.XA CN113779391A (en) | 2021-09-02 | 2021-09-02 | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111025858.XA CN113779391A (en) | 2021-09-02 | 2021-09-02 | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113779391A true CN113779391A (en) | 2021-12-10 |
Family
ID=78840885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111025858.XA Pending CN113779391A (en) | 2021-09-02 | 2021-09-02 | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113779391A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115083045A (en) * | 2022-06-24 | 2022-09-20 | 珠海格力电器股份有限公司 | Method and device for awakening unlocking function, door lock, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107742345A (en) * | 2017-11-07 | 2018-02-27 | 特斯联（北京）科技有限公司 | A kind of electronic access method for unlocking and unlocking system based on location-based service |
| CN107977411A (en) * | 2017-11-21 | 2018-05-01 | 腾讯科技(成都)有限公司 | Group recommending method, device, storage medium and server |
| WO2018182357A1 (en) * | 2017-03-30 | 2018-10-04 | Samsung Electronics Co., Ltd. | Data learning server and method for generating and using learning model thereof |
| CN111861619A (en) * | 2019-12-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Recommendation method and system for shared vehicles |
| CN111936795A (en) * | 2018-04-13 | 2020-11-13 | 三星电子株式会社 | Air conditioner and method of controlling the same |
-
2021
- 2021-09-02 CN CN202111025858.XA patent/CN113779391A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018182357A1 (en) * | 2017-03-30 | 2018-10-04 | Samsung Electronics Co., Ltd. | Data learning server and method for generating and using learning model thereof |
| CN107742345A (en) * | 2017-11-07 | 2018-02-27 | 特斯联（北京）科技有限公司 | A kind of electronic access method for unlocking and unlocking system based on location-based service |
| CN107977411A (en) * | 2017-11-21 | 2018-05-01 | 腾讯科技(成都)有限公司 | Group recommending method, device, storage medium and server |
| CN111936795A (en) * | 2018-04-13 | 2020-11-13 | 三星电子株式会社 | Air conditioner and method of controlling the same |
| CN111861619A (en) * | 2019-12-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Recommendation method and system for shared vehicles |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115083045A (en) * | 2022-06-24 | 2022-09-20 | 珠海格力电器股份有限公司 | Method and device for awakening unlocking function, door lock, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rivers et al. | Model selection tests for nonlinear dynamic models | |
| Minku et al. | How to make best use of cross-company data in software effort estimation? | |
| CN110147367A (en) | A kind of temperature missing data complementing method, system and electronic equipment | |
| CN106803799A (en) | A kind of performance test methods and device | |
| CN112668822A (en) | Scientific and technological achievement transformation platform sharing system, method, storage medium and mobile phone APP | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN111199493A (en) | Arrearage risk identification method based on customer payment information and credit investigation information | |
| CN109743200B (en) | Resource feature-based cloud computing platform computing task cost prediction method and system | |
| Mendes et al. | Investigating the use of chronological splitting to compare software cross-company and single-company effort predictions: a replicated study | |
| CN114925895A (en) | Maintenance equipment prediction method, terminal and storage medium | |
| CN112700065B (en) | Business process completion time interval prediction method and system based on deep learning | |
| CN114282657A (en) | Market data long-term prediction model training method, device, equipment and storage medium | |
| CN115081515A (en) | Energy efficiency evaluation model construction method and device, terminal and storage medium | |
| CN113610225A (en) | Quality evaluation model training method and device, electronic equipment and storage medium | |
| CN110263069B (en) | Method and system for extracting and depicting implicit factors of time sequence characteristics of new energy use behaviors | |
| CN112434471A (en) | Method, system, electronic device and storage medium for improving model generalization capability | |
| CN107798124A (en) | Search system and method based on prediction modeling technique | |
| CN106779366A (en) | project management process performance model and its construction method and performance model management system | |
| CN115222149A (en) | Resource conversion parameter management method, device, equipment and storage medium | |
| CN117634871A (en) | Risk assessment model training method and device, storage medium and electronic equipment | |
| CN114004491A (en) | Retail risk exposure pool dividing method and device, computer equipment and medium | |
| JP2024516440A (en) | Systems and methods for data classification | |
| CN117435489A (en) | Method and system for automatically analyzing software function points based on demand documents |
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 |