CN114098515A - Cleaning strategy control method of cleaning robot and cleaning robot - Google Patents
Cleaning strategy control method of cleaning robot and cleaning robot Download PDFInfo
- Publication number
- CN114098515A CN114098515A CN202010869282.4A CN202010869282A CN114098515A CN 114098515 A CN114098515 A CN 114098515A CN 202010869282 A CN202010869282 A CN 202010869282A CN 114098515 A CN114098515 A CN 114098515A
- Authority
- CN
- China
- Prior art keywords
- cleaning
- area
- time
- user
- data
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/28—Floor-scrubbing machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Electric Vacuum Cleaner (AREA)
Abstract
The invention relates to a cleaning strategy control method of a cleaning robot, which is characterized by comprising the following steps: collecting cleaning data generated each time a user performs a single area cleaning using the cleaning robot, the cleaning data including a cleaning area, a cleaning time period, and a time period in which the cleaning is performed; after a user uses the cleaning robot for cleaning a single area for multiple times, cleaning data collected for multiple times are processed to obtain a cleaning model preferred by the user, and output information of the cleaning scheme model comprises cleaning time period preference and cleaning area preference of the user; according to the cleaning scheme model, a reasonable cleaning scheme is recommended for the user, and the cleaning scheme comprises the following steps: cleaning time period, cleaning area, and cleaning duration. Compared with the prior art, the cleaning robot has the advantages that the cleaning robot is more humanized, excessive and complicated operations in the using process of a user are reduced, the cleaning robot is more intelligent, repeated sweeping of a clean area is avoided, and a dirty area is not swept completely.
Description
Technical Field
The invention relates to a cleaning strategy control method of a cleaning robot and the cleaning robot.
Background
In the process of cleaning a room, if only a certain designated area is to be cleaned by the current cleaning robot, the cleaning area needs to be actively divided by mobile phone control each time. In addition, when full-house cleaning is performed, the time distribution of each cleaning area is random or even, and targeted cleaning cannot be performed.
Because before cleaning each time, a user needs to think whether to clean the whole house or only clean a certain area, if the whole house is cleaned, the robot can only clean each area on average, and thus the areas difficult to clean are not cleaned, and the areas which are not cleaned frequently are cleaned repeatedly. However, if the user only needs to clean a certain area, the user must control the cleaning robot through the mobile phone or manually every time, which makes the operation of the cleaning robot cumbersome.
Disclosure of Invention
The invention aims to solve the primary technical problem of providing a cleaning strategy control method of a cleaning robot aiming at the prior art, which can reduce excessive and complicated operations in the using process of a user.
The invention further aims to solve the technical problem of providing a cleaning robot which can reduce too many complicated operations in the using process of a user.
The technical scheme adopted by the invention for solving the above-mentioned primary technical problems is as follows: a cleaning strategy control method of a cleaning robot, characterized by: collecting cleaning data generated each time a user performs area cleaning using the cleaning robot, the cleaning data including a cleaning area, a cleaning time period, and a time period in which cleaning is performed; after a user uses the cleaning robot for cleaning for multiple times, cleaning data acquired for multiple times are processed to obtain a cleaning model preferred by the user, and output information of the cleaning scheme model comprises cleaning time period preference and cleaning area preference of the user; according to the cleaning scheme model, a reasonable cleaning scheme is recommended for the user, and the cleaning scheme comprises the following steps: cleaning time period, cleaning area, and cleaning duration.
As an improvement, the cleaning robot is in communication connection with a cloud server; when the user uses this cleaning robot to clean at every turn, cleaning robot can upload the clean data that it produced to high in the clouds server, is handled the clean data of uploading many times by high in the clouds server to reach the cleaning scheme model, then according to this cleaning scheme model, recommend reasonable cleaning scheme for the user, and return cleaning robot with this reasonable cleaning scheme who recommends.
In a further improvement, the cleaning data generated by the cleaning robot is processed by the following method:
step 1, pre-storing a global map of a cleaned place, and rasterizing the global map of the cleaned place;
step 2, collecting cleaning data generated in the process that a user uses the cleaning robot to clean the area each time, wherein the cleaning data comprises the following steps: the start cleaning timestamp t1, the timestamp t2 of the end of cleaning, and the cleaned area information set the element value of the cleaned area on the grid of the global map to 0, and the element values of the rest of the areas not cleaned on the grid of the global map to 255, so as to obtain a single area cleaning map matrix M of the binarization process, where the single area cleaning map matrix M is expressed as follows:
step 3, initializing a real-time map matrix N, wherein the size of the real-time map matrix N is the same as that of a single regional cleaning map matrix M, and the value of each element is 0;
and 4, updating the real-time map matrix N according to a single area cleaning map matrix M generated after a user uses the cleaning robot to clean the area each time, wherein the specific method comprises the following steps:
if the single-time regional clean map matrix M is obtained for the first time, the real-time map matrix N is directly updated, namely the position of the single-time regional clean map matrix M with the element value of 0 is found, and the element value of the position corresponding to the real-time map matrix N is changed into xiX is the number of the area to be cleaned,any fixed cleaning area uniquely corresponds to one number, the number corresponding to the cleaning area is pre-stored, the area to be cleaned includes but is not limited to a kitchen, a living room, a washroom and a room, i represents the ith cleaning of the x cleaning area, i is 1, 2, 3 and … …, and the real-time map matrix N is stored;
then, each time a new single-time regional clean map matrix M is obtained, whether the position of the element value of 0 in the single-time regional clean map matrix M is overlapped with the position of the corresponding clean region in the stored real-time map matrix N is inquired, if the positions are not overlapped, the real-time map matrix N is updated again, namely the position of the element value of 0 in the single-time regional clean map matrix M is found, the element value of the position corresponding to the real-time map matrix N is changed into xiSimultaneously storing the real-time map matrix N; if the overlap exists, combining the element values of the cleaning areas according to the size of the overlapped part, wherein the specific method comprises the following steps:
finding the position of the single-time regional clean map matrix M with the element value of 0, and changing the element value of the corresponding position in the real-time map matrix N into xiSimultaneously, the rest element values in the real-time map matrix N are xi-1The element value of the region is changed to xiMeanwhile, the update cleaning time period dt:
wherein s1 is the area with the element value of 0 in the single-time area clean map matrix M uploaded this time, and s2 is the area with the element value of x in the corresponding clean area in the real-time map matrix Ni-1The area of the region (d), Δ s is the area of the overlapping part, dt1 is the cleaning duration corresponding to the cleaning region during the current region cleaning, and dt2 is the cleaning duration of the corresponding region stored before;
step 5, obtaining the element value x of each cleaning area according to the element values in the real-time map matrix NiAssigning i to the label r of the corresponding cleaning area;
step 6, converting a timestamp t1 for starting cleaning into a week tw and a specific time point th according to the time information of the area cleaning, calculating the time length dt for cleaning the area by using the difference between a timestamp t2 for finishing cleaning and a timestamp t1 for starting cleaning, converting the unit of the time length dt into minutes, storing tw, th and dt, acquiring labels r of different cleaning areas according to the step 5, and generating a cleaning feature vector Pre preferred by a user:
Pre=[tw th dt r]
step 7, after n times of area cleaning, obtaining a four-dimensional feature matrix X of user cleaning preference according to different cleaning areas and the cleaning feature vector Pre of user preference corresponding to the cleaning area, and defining the feature matrix X as a cleaning model of the user preference for the cleaning area:
in another improvement, the method also comprises the step 8: performing kmeans clustering on tw data in the four-dimensional feature matrix X to obtain preference data of a user per week of cleaning time, performing kmeans clustering on th data in the four-dimensional feature matrix X to obtain preference time period data of the user per day of cleaning, and performing kmeans clustering on n data in the four-dimensional feature matrix X to further obtain the number of a cleaning area which is most frequently cleaned by the user.
In another improvement, the method comprises the following steps of 9: performing kmeans clustering on the data of three dimensions including tw data, th data and n data in the four-dimensional feature matrix X respectively to obtain preference data of a user per week cleaning time, preference time period data of the user per day cleaning and the number of a cleaning area most frequently cleaned by the user, mapping the preference data of the three dimensions, and simultaneously solving the intersection of the preference data and the preference time period data to obtain a conjecture of which area is cleaned by the user in which time period of the day of the week.
And improving the cleaning operation again, when the user selects the cleaning robot to clean the whole house, extracting the information of the four dimensions tw, th and dt in the four-dimensional characteristic matrix X, and executing the cleaning operation according to the information of the three dimensions and the cleaning area number X corresponding to the three dimensions.
According to the invention, the process of processing the cleaning data generated by the cleaning robot is completed by the cloud server.
The technical scheme adopted by the invention for solving the further technical problems is as follows: the utility model provides a cleaning machines people, includes the organism, is equipped with cleaning device on the organism, running gear and the control circuit board that control running gear removed, its characterized in that: the control circuit board performs a cleaning operation according to the cleaning strategy control method described above.
Compared with the prior art, the invention has the advantages that: through the regional information that cleans many times the user and the collection of long waiting data of cleaning, realize each regional time distribution of regional division, reachs the clean data of user's preference to recommend reasonable cleaning scheme for the user, make cleaning machines people more humanized, reduce too much loaded down with trivial details operation in the user's use, can also make cleaning machines people more intelligent, avoid clean region to sweep repeatedly, dirty region does not clean totally.
Detailed Description
The embodiment provides a cleaning robot, and it includes the organism, is equipped with cleaning device on the organism, and cleaning device can be for dust absorption subassembly, the subassembly of sweeping the floor or, drag one or the arbitrary combination in ground subassembly, the scraping subassembly, is equipped with running gear on the organism, is equipped with the control circuit board that control running gear removed in the organism, control circuit board and high in the clouds server communication connection. The cleaning strategy control method of the cleaning robot comprises the following steps:
the method comprises the steps that cleaning data generated when a user uses the cleaning robot to clean an area each time are collected, the cleaning data comprise a cleaning area, cleaning duration and a time period when cleaning is carried out, and the collected data are uploaded to a cloud server to be processed; the cloud server processes the cleaning data uploaded for multiple times after the user uses the cleaning robot for cleaning for multiple times to obtain a cleaning model preferred by the user, wherein the output information of the cleaning scheme model comprises the cleaning time period preference and the cleaning area preference of the user; according to the cleaning scheme model, a reasonable cleaning scheme is recommended for the user, and the cleaning scheme comprises the following steps: cleaning time period, cleaning area, and cleaning duration.
The cloud server specifically processes cleaning data generated by the cleaning robot by the following method:
step 1, pre-storing a global map of a cleaned place on a cloud server, and rasterizing the global map of the cleaned place to obtain a rasterized map matrix, wherein the rasterized map matrix is represented as follows:
step 2, after a user uses the cleaning robot to clean a single area each time, the cleaning data generated by the user is uploaded to a cloud server, and the cleaning data comprises: the start cleaning timestamp t1, the timestamp t2 of the end of cleaning, and the cleaned area information set the element value of the cleaned area on the grid of the global map to 0, and the element values of the rest of the areas not cleaned on the grid of the global map to 255, so as to obtain a single area cleaning map matrix M of the binarization process, where the single area cleaning map matrix M is expressed as follows:
in the step, the cleaning robot uploads the generated cleaning data to the cloud server only when a single area is cleaned under the instruction of a user, and if the cleaning robot performs whole-house cleaning or performs cleaning of a plurality of cleaning areas simultaneously, the cleaning data are not uploaded;
step 3, initializing a real-time map matrix N, wherein the size of the real-time map matrix N is the same as that of a single regional cleaning map matrix M, and the value of each element is 0;
and 4, updating the real-time map matrix N according to a single area cleaning map matrix M generated after a user uses the cleaning robot to clean a single area each time, wherein the specific method comprises the following steps:
if the single-time regional clean map matrix M is obtained for the first time, the real-time map matrix N is directly updated, namely the position of the single-time regional clean map matrix M with the element value of 0 is found, and the element value of the position corresponding to the real-time map matrix N is changed into xiX is the number of the cleaned area, any fixed cleaning area uniquely corresponds to one number, the number corresponding to the cleaning area is pre-stored in the cloud server, the cleaned area includes but is not limited to a kitchen, a living room, a washroom and a room, i represents the ith cleaning of the x cleaning area, i is 1, 2, 3 and … …, and the real-time map matrix N is stored;
then, each time a new single-time regional clean map matrix M is obtained, whether the position of the element value of 0 in the single-time regional clean map matrix M is overlapped with the position of the corresponding clean region in the stored real-time map matrix N is inquired, if the positions are not overlapped, the real-time map matrix N is updated again, namely the position of the element value of 0 in the single-time regional clean map matrix M is found, the element value of the position corresponding to the real-time map matrix N is changed into xiSimultaneously storing the real-time map matrix N; if the overlap exists, combining the element values of the cleaning areas according to the size of the overlapped part, wherein the specific method comprises the following steps:
finding the position of the single-time regional clean map matrix M with the element value of 0, and changing the element value of the corresponding position in the real-time map matrix N into xiSimultaneously, the rest element values in the real-time map matrix N are xi-1The element value of the region is changed to xiMeanwhile, the update cleaning time period dt:
wherein s1 is the area with the element value of 0 in the single-time area clean map matrix M uploaded this time, and s2 is the area with the element value of x in the corresponding clean area in the real-time map matrix Ni-1Area of (d), Δ s is the area of the overlap, dt1 is the cleaning area pair at the time of the present area cleaningThe corresponding cleaning duration, dt2 is the cleaning duration of the corresponding region previously saved;
step 5, obtaining the element value x of each cleaning area according to the element values in the real-time map matrix NiAssigning i to the label r of the corresponding cleaning area;
step 6, converting a timestamp t1 for starting cleaning into a week tw and a specific time point th according to the time information of the area cleaning, calculating the time length dt for cleaning the area by using the difference between a timestamp t2 for finishing cleaning and a timestamp t1 for starting cleaning, converting the unit of the time length dt into minutes, storing tw, th and dt, acquiring labels r of different cleaning areas according to the step 5, and generating a cleaning feature vector Pre preferred by a user:
Pre=[tw th dt r]
step 7, after n times of area cleaning, obtaining a four-dimensional (4 × n) feature matrix X of user cleaning preference according to different cleaning areas and the cleaning feature vector Pre of user preference corresponding to the cleaning area, and defining the feature matrix X as a cleaning model of user preference:
and 8: performing kmeans clustering on tw data in the four-dimensional feature matrix X to obtain preference data of a user per cleaning time, such as the maximum number of cleaning times on weekends, the number of cleaning times on saturday and the minimum number of cleaning times on monday; performing kmeans clustering on th data in the five-dimensional characteristic matrix X to obtain preference time period data of daily cleaning of a user, and performing kmeans clustering on n data in the five-dimensional characteristic matrix X to further obtain the number of a cleaning area which is most frequently cleaned by the user;
and step 9: performing kmeans clustering on the data of three dimensions including tw data, th data and n data in the four-dimensional feature matrix X respectively to obtain preference data of a user per week cleaning time, preference time period data of the user per day cleaning and the number of a cleaning area most frequently cleaned by the user, mapping the preference data of the three dimensions, and simultaneously solving the intersection of the preference data and the preference time period data to obtain a conjecture of which area is cleaned by the user in which time period of the day of the week.
In addition, when the user selects the cleaning robot to clean the whole house, the cloud server extracts information of three dimensions of tw, th and dt in the four-dimensional feature matrix X corresponding to different cleaning areas, sends the information of the three dimensions and the cleaning area number X corresponding to the information of the three dimensions to the cleaning robot, and the cleaning robot executes cleaning operation according to the information of the four dimensions of X, tw, th and dt.
Claims (8)
1. A cleaning strategy control method of a cleaning robot, characterized by: collecting cleaning data generated each time a user performs a single area cleaning using the cleaning robot, the cleaning data including a cleaning area, a cleaning time period, and a time period in which the cleaning is performed; after a user uses the cleaning robot for cleaning a single area for multiple times, cleaning data collected for multiple times are processed to obtain a cleaning model preferred by the user, and output information of the cleaning scheme model comprises cleaning time period preference and cleaning area preference of the user; according to the cleaning scheme model, a reasonable cleaning scheme is recommended for the user, and the cleaning scheme comprises the following steps: cleaning time period, cleaning area, and cleaning duration.
2. The cleaning strategy control method of claim 1, wherein: the cleaning robot is in communication connection with the cloud server; when the user uses this cleaning robot to carry out single regional cleanness at every turn, cleaning robot can upload the clean data that it produced to high in the clouds server, is handled the clean data of uploading many times by high in the clouds server to reach the cleaning scheme model, then according to this cleaning scheme model, recommend reasonable cleaning scheme for the user, and return cleaning robot with this reasonable cleaning scheme who recommends.
3. The cleaning strategy control method according to claim 1 or 2, characterized in that: processing cleaning data generated by the cleaning robot by:
step 1, pre-storing a global map of a cleaned place, and rasterizing the global map of the cleaned place;
step 2, collecting cleaning data generated in the process that a user uses the cleaning robot to clean a single area each time, wherein the cleaning data comprises the following steps: the start cleaning timestamp t1, the timestamp t2 of the end of cleaning, and the cleaned area information set the element value of the cleaned area on the grid of the global map to 0, and the element values of the rest of the areas not cleaned on the grid of the global map to 255, so as to obtain a single area cleaning map matrix M of the binarization process, where the single area cleaning map matrix M is expressed as follows:
step 3, initializing a real-time map matrix N, wherein the size of the real-time map matrix N is the same as that of a single regional cleaning map matrix M, and the value of each element is 0;
and 4, updating the real-time map matrix N according to a single area cleaning map matrix M generated after a user uses the cleaning robot to clean a single area each time, wherein the specific method comprises the following steps:
if the single-time regional clean map matrix M is obtained for the first time, the real-time map matrix N is directly updated, namely the position of the single-time regional clean map matrix M with the element value of 0 is found, and the element value of the position corresponding to the real-time map matrix N is changed into xiX is the number of the cleaned area, any fixed cleaning area uniquely corresponds to one number, the number corresponding to the cleaning area is pre-stored, the cleaned area comprises but is not limited to a kitchen, a living room, a washroom and a room, i represents the ith cleaning of the x cleaning area, i is 1, 2, 3 and … …, and the real-time map matrix N is stored;
then, each time a new single-time regional clean map matrix M is acquired, the position of the element value of 0 in the single-time regional clean map matrix M is inquired and the corresponding position in the stored real-time map matrix NWhether the positions of the cleaning areas are overlapped or not is judged, if not, the real-time map matrix N is updated again, namely the position where the element value in the cleaning map matrix M in the single area is 0 is found, and the element value of the position corresponding to the real-time map matrix N is changed into xiSimultaneously storing the real-time map matrix N; if the overlap exists, combining the element values of the cleaning areas according to the size of the overlapped part, wherein the specific method comprises the following steps:
finding the position of the single-time regional clean map matrix M with the element value of 0, and changing the element value of the corresponding position in the real-time map matrix N into xiSimultaneously, the rest element values in the real-time map matrix N are xi-1The element value of the region is changed to xiMeanwhile, the update cleaning time period dt:
wherein s1 is the area with the element value of 0 in the single-time area clean map matrix M uploaded this time, and s2 is the area with the element value of x in the corresponding clean area in the real-time map matrix Ni-1The area of the region (d), Δ s is the area of the overlapping part, dt1 is the cleaning duration corresponding to the cleaning region during the current region cleaning, and dt2 is the cleaning duration of the corresponding region stored before;
step 5, obtaining the element value x of each cleaning area according to the element values in the real-time map matrix NiAssigning i to the label r of the corresponding cleaning area;
step 6, converting a timestamp t1 for starting cleaning into a week tw and a specific time point th according to the time information of the area cleaning, calculating the time length dt for cleaning the area by using the difference between a timestamp t2 for finishing cleaning and a timestamp t1 for starting cleaning, converting the unit of the time length dt into minutes, storing tw, th and dt, acquiring labels r of different cleaning areas according to the step 5, and generating a cleaning feature vector Pre preferred by a user:
Pre=[tw th dt r]
step 7, after n times of area cleaning, obtaining a four-dimensional feature matrix X of user cleaning preference according to different cleaning areas and the cleaning feature vector Pre of user preference corresponding to the cleaning area, and defining the feature matrix X as a cleaning model of the user preference for the cleaning area:
4. a cleaning strategy control method of a cleaning robot according to claim 3, characterized in that: further comprising the step 8: performing kmeans clustering on tw data in the four-dimensional feature matrix X to obtain preference data of a user per week of cleaning time, performing kmeans clustering on th data in the four-dimensional feature matrix X to obtain preference time period data of the user per day of cleaning, and performing kmeans clustering on n data in the four-dimensional feature matrix X to further obtain the number of a cleaning area which is most frequently cleaned by the user.
5. The cleaning strategy control method of a cleaning robot according to claim 4, characterized in that: the method comprises the following steps of 9: performing kmeans clustering on the data of three dimensions including tw data, th data and n data in the four-dimensional feature matrix X respectively to obtain preference data of a user per week cleaning time, preference time period data of the user per day cleaning and the number of a cleaning area most frequently cleaned by the user, mapping the preference data of the three dimensions, and simultaneously solving the intersection of the preference data and the preference time period data to obtain a conjecture of which area is cleaned by the user in which time period of the day of the week.
6. The cleaning strategy control method of a cleaning robot according to claim 5, characterized in that: when a user selects the cleaning robot to clean the whole house, the three-dimensional information of tw, th and dt in the four-dimensional feature matrix X corresponding to different cleaning areas is extracted, and cleaning operation is performed according to the three-dimensional information and the cleaning area number X corresponding to the three-dimensional information.
7. A cleaning strategy control method of a cleaning robot according to claim 3, characterized in that: the process of processing the cleaning data generated by the cleaning robot is completed by the cloud server.
8. The utility model provides a cleaning machines people, includes the organism, is equipped with cleaning device on the organism, running gear and the control circuit board that control running gear removed, its characterized in that: the control circuit board performs a cleaning operation according to the cleaning strategy control method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010869282.4A CN114098515B (en) | 2020-08-26 | 2020-08-26 | Cleaning strategy control method of cleaning robot and cleaning robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010869282.4A CN114098515B (en) | 2020-08-26 | 2020-08-26 | Cleaning strategy control method of cleaning robot and cleaning robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114098515A true CN114098515A (en) | 2022-03-01 |
CN114098515B CN114098515B (en) | 2022-11-25 |
Family
ID=80373952
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010869282.4A Active CN114098515B (en) | 2020-08-26 | 2020-08-26 | Cleaning strategy control method of cleaning robot and cleaning robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114098515B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204950817U (en) * | 2015-04-15 | 2016-01-13 | 小米科技有限责任公司 | Intelligence cleaning device |
US20180284786A1 (en) * | 2017-03-31 | 2018-10-04 | Neato Robotics, Inc. | Robot with automatic styles |
US20180368312A1 (en) * | 2015-12-16 | 2018-12-27 | Vorwerk & Co. Interholding Gmbh | System and Method for Processing a Ground with a Mobile Robot Unit |
CN110399563A (en) * | 2019-08-05 | 2019-11-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of preference pattern and customized information active recommended method based on user behavior analysis |
CN111374601A (en) * | 2018-12-28 | 2020-07-07 | 珠海市一微半导体有限公司 | Operation planning method and device of sweeping robot and cleaning system |
CN111563461A (en) * | 2020-05-11 | 2020-08-21 | 追创科技(苏州)有限公司 | Cleaning path acquisition method and device for cleaning equipment and storage medium |
CN111568311A (en) * | 2020-04-22 | 2020-08-25 | 青岛海尔空调器有限总公司 | Equipment control method and device and electronic equipment |
-
2020
- 2020-08-26 CN CN202010869282.4A patent/CN114098515B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204950817U (en) * | 2015-04-15 | 2016-01-13 | 小米科技有限责任公司 | Intelligence cleaning device |
US20180368312A1 (en) * | 2015-12-16 | 2018-12-27 | Vorwerk & Co. Interholding Gmbh | System and Method for Processing a Ground with a Mobile Robot Unit |
US20180284786A1 (en) * | 2017-03-31 | 2018-10-04 | Neato Robotics, Inc. | Robot with automatic styles |
CN111374601A (en) * | 2018-12-28 | 2020-07-07 | 珠海市一微半导体有限公司 | Operation planning method and device of sweeping robot and cleaning system |
CN110399563A (en) * | 2019-08-05 | 2019-11-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of preference pattern and customized information active recommended method based on user behavior analysis |
CN111568311A (en) * | 2020-04-22 | 2020-08-25 | 青岛海尔空调器有限总公司 | Equipment control method and device and electronic equipment |
CN111563461A (en) * | 2020-05-11 | 2020-08-21 | 追创科技(苏州)有限公司 | Cleaning path acquisition method and device for cleaning equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN114098515B (en) | 2022-11-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106913289B (en) | Sweeping processing method and device of sweeping robot | |
CN109953700B (en) | Cleaning method and cleaning robot | |
CN110251004B (en) | Sweeping robot, sweeping method thereof and computer-readable storage medium | |
CN105892321B (en) | A kind of dispatching method and dispatching device of clean robot | |
CN112842149B (en) | Control method of intelligent cleaning equipment and intelligent cleaning equipment | |
CN110135341B (en) | Weed identification method and device and terminal equipment | |
CN110174888B (en) | Self-moving robot control method, device, equipment and storage medium | |
CN112971615A (en) | Control method of intelligent cleaning equipment and intelligent cleaning equipment | |
EP3327500A1 (en) | Automated walking device | |
CN110750567A (en) | Wearing and matching data generation method and system based on intelligent wardrobe | |
CN107943036A (en) | Purging zone system of selection and device | |
US11222207B2 (en) | Intelligent sweeping robot | |
CN110764513B (en) | Map blind area identification method | |
CN110928282A (en) | Control method and device for cleaning robot | |
CN111973097A (en) | Sweeper control method and device, sweeper and computer readable storage medium | |
CN107977003A (en) | Connected relation method for building up and device | |
CN114098515B (en) | Cleaning strategy control method of cleaning robot and cleaning robot | |
CN110702120A (en) | Map boundary processing method, system, robot and storage medium | |
CN113780233B (en) | Aisle area identification method and device | |
CN113349188B (en) | Lawn and forage precise weeding method based on cloud weeding spectrum | |
CN111435426A (en) | Method and device for determining cooking mode based on rice grain recognition result and cooking appliance | |
CN114547227A (en) | Ant colony and A-Star algorithm parallel grid map path planning method | |
CN112515542A (en) | Control method and system of sweeping robot for sweeping hair | |
US20200130179A1 (en) | Sweeping control method | |
CN109712110B (en) | Crop real-time water consumption monitoring method and device based on machine vision |
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 |