CN112413832B - User identity recognition method based on user behavior and electric equipment thereof - Google Patents
User identity recognition method based on user behavior and electric equipment thereof Download PDFInfo
- Publication number
- CN112413832B CN112413832B CN201910781922.3A CN201910781922A CN112413832B CN 112413832 B CN112413832 B CN 112413832B CN 201910781922 A CN201910781922 A CN 201910781922A CN 112413832 B CN112413832 B CN 112413832B
- Authority
- CN
- China
- Prior art keywords
- user
- identity
- behavior
- user behavior
- behavior 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000006399 behavior Effects 0.000 claims abstract description 143
- 238000012216 screening Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention provides a user identity recognition method based on user behaviors and electrical equipment thereof, the technical scheme of the invention is that behavior labels are attached to user behavior data, the behavior labels comprise behavior identity attributes and identity weights, and the identity weights of the same identity attributes in all the behavior labels in a preset time interval are added and summed to respectively obtain user identity confidence values corresponding to different identity attributes; and judging whether the confidence value of the user identity exceeds the confidence threshold value according to the user identity identification table, so as to realize identity identification, and the method has the beneficial technical effects of more accuracy, more optimization and more reasonability.
Description
Technical Field
The invention relates to the field of identity recognition, in particular to a user identity recognition method based on user behaviors and electrical equipment thereof.
Background
After the user purchases the electrical equipment, it is preferable to identify the user in order to provide the user with better service in a targeted manner.
Although the prior art already exists in which the user identity is identified by comparing the user behavior data with the user behavior data in the user behavior database and judging the similarity. However, the traditional identity judgment method has the defect that the collected user information is not comprehensive, so that the analysis of the user identity is inaccurate.
Disclosure of Invention
The invention aims to provide a more accurate user identity identification method based on user behaviors.
In order to achieve the aim, the technical scheme of the invention is as follows:
a user identity identification method based on user behaviors comprises the following steps:
acquiring user behavior data;
attaching a behavior label to user behavior data, wherein the behavior label comprises a behavior identity attribute and an identity weight;
adding and summing the identity weights of the same identity attributes in all the behavior tags in a preset time interval to respectively obtain user identity confidence values corresponding to different identity attributes;
and judging whether the user identity confidence value exceeds a confidence threshold value or not according to a user identity identification table, wherein the user identity identification table comprises a user identity attribute and a confidence threshold value corresponding to the user identity attribute.
Preferably, the user behavior data includes a user behavior event, and the user behavior event includes a behavior time and a behavior name.
Preferably, the user behavior data and the behavior tag are associated through a user behavior tag table, where the user behavior tag table includes the user behavior data and a behavior tag corresponding to the user behavior data.
Preferably, the acquiring of the user behavior data includes a monitoring step and a screening step, the monitoring step acquires the user behavior data in real time, and the screening step screens out the user behavior data capable of representing the user identity from the acquired user data.
Preferably, the labeling of the user behavior data is implemented by using a machine learning algorithm instead of the user behavior label table.
Preferably, if the confidence value of the user identity exceeds the confidence threshold, the user is attached with an identity tag, and the identity tag comprises at least one identity attribute.
The invention also provides electrical equipment capable of more accurately identifying the user identity, and the electrical equipment adopts the method to identify the user identity.
Preferably, the electrical equipment is an air conditioner.
Preferably, the identity attribute includes whether the identity attribute is office class or gender.
Preferably, the user behavior data includes an event of turning off the air conditioner and a time when the event occurs.
Compared with the prior art, the method has the beneficial technical effects that the method has the advantages that the behavior labels are attached to the user behavior data, the behavior labels comprise behavior identity attributes and identity weights, the identity weights of the same identity attributes in all the behavior labels in the preset time interval are added and summed, and user identity confidence values corresponding to different identity attributes are obtained respectively; and judging whether the confidence value of the user identity exceeds the confidence threshold value according to the user identity identification table, so as to realize identity identification, and the method has the beneficial technical effects of more accuracy, more optimization and more reasonability.
Drawings
Fig. 1 is a flowchart of a user identification method of the present invention.
Detailed Description
Example one
Referring to fig. 1, the user identity recognition method based on user behavior of the present embodiment includes:
acquiring user behavior data; after the user behavior data are collected, processing is carried out on a data layer, a data set representing the user behavior is extracted, repeated data, error data, abnormal data and the like are removed, data type division is carried out, and finally the user behavior data capable of representing the user identity are obtained. The types of the user behavior data are various, for example, when the user operates the air conditioner, the user behavior data may include an operating time ratio of each windshield, an operating time ratio in each mode, an operating time ratio of the mute switch, a change in the indoor ambient temperature, an operating time ratio in the super-strong mode, and a behavior of the user at each time period for analysis, including the number of times of turning on and off the air conditioner, the number of times of adjusting each mode, and a setting change in the set ambient temperature.
Attaching a behavior label to user behavior data, wherein the behavior label comprises a behavior identity attribute and an identity weight; the identity attributes comprise office workers, men, women, old people, children and the like, the weight of the identity attributes corresponding to different user behavior data is different, and the larger the weight is, the larger the relevance between the user behavior and the user identity is. The assignment of identity weights may be pre-set based on historical data.
Adding and summing the identity weights of the same identity attributes in all the behavior tags in a preset time interval to respectively obtain user identity confidence values corresponding to different identity attributes;
and judging whether the maximum user identity confidence value exceeds a confidence threshold value or not according to a user identity identification table, wherein the user identity identification table comprises a user identity attribute and a confidence threshold value corresponding to the user identity attribute.
The user behavior data comprises user behavior events, and the user behavior events comprise behavior time and behavior names.
The user behavior data and the behavior tags are associated through a user behavior tag table, and the user behavior tag table comprises the user behavior data and behavior tags corresponding to the user behavior data.
The user behavior data acquisition method comprises a monitoring step and a screening step, wherein the monitoring step is used for acquiring the user behavior data in real time, and the screening step is used for screening the user behavior data capable of representing the identity of a user from the acquired user data.
And if the user identity confidence value exceeds the confidence threshold value, attaching an identity label to the user, wherein the identity label comprises identity attributes.
Example two
An electrical device adopts the method of the first embodiment to identify the identity of a user.
As a preferred embodiment, the electrical equipment is an air conditioner, and the flow of the air conditioner performing the user identification by using the method described in the first embodiment is specifically as follows.
Acquiring user behavior data, wherein the user behavior data comprises a user behavior event as a preferred embodiment, and the user behavior event comprises behavior time and a behavior name.
For example, if the user action time is that the user turns off the air conditioner at 7 am, the action name is that the air conditioner is turned off, and the occurrence time is 7 am.
Attaching a behavior label to user behavior data, wherein the behavior label comprises a behavior identity attribute and an identity weight;
for example, if behavior data in which the user turns off the air conditioner is detected at 7 am is acquired, the behavior data of the user is attached with a behavior tag with an identity attribute of office class and an identity weight of x 1. Similarly, if behavior data that the user sets the air conditioner to the super strong mode is acquired, the user behavior data is attached with the identity attribute of male and the identity weight of y 1.
Adding and summing the identity weights of the same identity attributes in all the behavior tags in a preset time interval to respectively obtain user identity confidence values corresponding to different identity attributes;
for example, assuming that the time interval is monday to sunday, the identity weights in all the behavior tags whose attributes are of the working family within one week are added and summed to obtain a user identity confidence value q (x) ═ x1+ x2+ x3.. + xn, where xn is the identity weight of which the identity attribute is the behavior tag of the working family, and q (x) is the sum of the identity weights in all the behavior tags of which the identity attribute is the working family. Similarly, the identity weights in all the behavior tags with the attribute of the male family in one week are added and summed to obtain a user identity confidence value q (y) 1+ y2+ y3.. + yn, where yn is the identity weight of the behavior tag with the identity attribute of the male, and q (y) is the sum of the identity weights in all the behavior tags with the identity attribute of the male.
And judging whether the maximum user identity confidence value exceeds a confidence threshold value or not according to a user identity identification table, wherein the user identity identification table comprises a user identity attribute and a confidence threshold value corresponding to the user identity attribute.
And if the user identity confidence value exceeds the confidence threshold value, attaching an identity label to the user, wherein the identity label comprises identity attributes.
For example, in the user identification table, the confidence threshold corresponding to the identity attribute of "office worker" is q (x), the confidence threshold corresponding to the identity attribute of "male" is q (y), if q (x) is greater than q (x), the user identity is determined to be the office worker, if q (y) is also satisfied and is greater than q (y), the user identity is determined to be male, and then the user may be tagged with the identity tag of the male office worker.
As a preferred embodiment, the user behavior data and the behavior tags are associated through a user behavior tag table, where the user behavior tag table includes the user behavior data and the behavior tags corresponding to the user behavior data. Therefore, as long as the user behavior is identified, the corresponding behavior label can be found through table lookup, and the corresponding behavior label can be fast and accurately attached to the user behavior data.
For example, the correspondence between the user behavior event of turning off the air conditioner at 7 am and the behavior label with the identity attribute of working clan and the identity weight of x1 is preset, and specifically, the correspondence is performed through a user behavior label table, and after the specified user behavior data is obtained, the corresponding behavior label is obtained through table lookup.
The user behavior data acquisition method comprises a monitoring step and a screening step, wherein the monitoring step is used for acquiring the user behavior data in real time, and the screening step is used for screening the user behavior data capable of representing the identity of a user from the acquired user data.
EXAMPLE III
On the basis of the first embodiment, the third embodiment provides a user identity identification method based on user behaviors, wherein the method of the third embodiment adopts a machine learning algorithm to replace a user behavior label table of the method of the first embodiment to label user behavior data. The machine learning algorithm may be a neural network learning algorithm.
Example four
Similarly, on the basis of the second embodiment, the fourth embodiment provides an electrical device, and in the process of performing the user identity, the machine learning algorithm is adopted to replace the user behavior tag table of the method in the first embodiment, so as to label the user behavior data.
The above-mentioned embodiments are only used for understanding the technical solutions of the present invention, and should not be construed as limiting the scope of the present invention. It should be noted that variations to those skilled in the art may be made without departing from the spirit of the invention, and these are within the scope of the invention.
Claims (9)
1. A user identity recognition method based on user behaviors is characterized by comprising the following steps:
acquiring user behavior data;
attaching a behavior label to user behavior data, wherein the behavior label comprises a behavior identity attribute and an identity weight;
adding and summing the identity weights of the same identity attributes in all the behavior tags in a preset time interval to respectively obtain user identity confidence values corresponding to different identity attributes;
judging whether the confidence value of the user identity exceeds a confidence threshold value or not according to a user identity identification table, wherein the user identity identification table comprises a user identity attribute and a confidence threshold value corresponding to the user identity attribute,
and if the user identity confidence value exceeds the confidence threshold value, attaching an identity label to the user, wherein the identity label comprises at least one identity attribute.
2. The method according to claim 1, wherein the user behavior data includes a user behavior event, and the user behavior event includes a behavior time and a behavior name.
3. The method according to claim 1 or 2, wherein the user behavior data and the behavior tags are associated by a user behavior tag table, and the user behavior tag table comprises the user behavior data and the behavior tags corresponding to the user behavior data.
4. The method according to claim 3, wherein the step of acquiring the user behavior data includes a monitoring step and a screening step, the monitoring step collects the user behavior data in real time, and the screening step screens out the user behavior data capable of representing the user identity from the collected user data.
5. The method of claim 3, wherein the labeling of the user behavior data is implemented using a machine learning algorithm instead of a user behavior label table.
6. An electrical appliance, characterized in that the electrical appliance performs user identification using the method of any one of claims 1 to 5.
7. The electrical apparatus of claim 6, wherein the electrical apparatus is an air conditioner.
8. The appliance device of claim 7, wherein the identity attribute includes whether it is office class, gender.
9. The electrical apparatus of claim 7 or 8, wherein the user behavior data comprises an event of turning off an air conditioner and a time when the event occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910781922.3A CN112413832B (en) | 2019-08-23 | 2019-08-23 | User identity recognition method based on user behavior and electric equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910781922.3A CN112413832B (en) | 2019-08-23 | 2019-08-23 | User identity recognition method based on user behavior and electric equipment thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112413832A CN112413832A (en) | 2021-02-26 |
| CN112413832B true CN112413832B (en) | 2021-11-30 |
Family
ID=74779302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910781922.3A Active CN112413832B (en) | 2019-08-23 | 2019-08-23 | User identity recognition method based on user behavior and electric equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112413832B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114676400A (en) * | 2022-03-04 | 2022-06-28 | 青岛海尔科技有限公司 | Identity determination method, storage medium and electronic device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101405739A (en) * | 2002-12-26 | 2009-04-08 | 摩托罗拉公司(在特拉华州注册的公司) | Identification apparatus and method |
| CN201724335U (en) * | 2010-06-18 | 2011-01-26 | 广东志高空调有限公司 | Air conditioner with identifying function, remote control and air conditioning system |
| CN102682041A (en) * | 2011-03-18 | 2012-09-19 | 日电（中国）有限公司 | User behavior identification equipment and method |
| US8412466B2 (en) * | 2009-04-13 | 2013-04-02 | Canon U.S. Life Sciences, Inc. | Rapid method of pattern recognition, machine learning, and automated genotype classification through correlation analysis of dynamic signals |
| CN103577991A (en) * | 2012-08-03 | 2014-02-12 | 阿里巴巴集团控股有限公司 | User identification method and device |
| CN103914494A (en) * | 2013-01-09 | 2014-07-09 | 北大方正集团有限公司 | Method and system for identifying identity of microblog user |
| CN106895553A (en) * | 2017-02-14 | 2017-06-27 | 珠海格力电器股份有限公司 | Air conditioner, control method and device thereof, and alarm method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010511954A (en) * | 2006-12-06 | 2010-04-15 | 韓國電子通信研究院 | Trusted link authentication system, authentication method thereof, and authentication display method |
| CN107563160A (en) * | 2017-09-06 | 2018-01-09 | 广东美的暖通设备有限公司 | Maintenance protection personal identification method, system and air-conditioning |
-
2019
- 2019-08-23 CN CN201910781922.3A patent/CN112413832B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101405739A (en) * | 2002-12-26 | 2009-04-08 | 摩托罗拉公司(在特拉华州注册的公司) | Identification apparatus and method |
| US8412466B2 (en) * | 2009-04-13 | 2013-04-02 | Canon U.S. Life Sciences, Inc. | Rapid method of pattern recognition, machine learning, and automated genotype classification through correlation analysis of dynamic signals |
| CN201724335U (en) * | 2010-06-18 | 2011-01-26 | 广东志高空调有限公司 | Air conditioner with identifying function, remote control and air conditioning system |
| CN102682041A (en) * | 2011-03-18 | 2012-09-19 | 日电（中国）有限公司 | User behavior identification equipment and method |
| CN103577991A (en) * | 2012-08-03 | 2014-02-12 | 阿里巴巴集团控股有限公司 | User identification method and device |
| CN103914494A (en) * | 2013-01-09 | 2014-07-09 | 北大方正集团有限公司 | Method and system for identifying identity of microblog user |
| CN106895553A (en) * | 2017-02-14 | 2017-06-27 | 珠海格力电器股份有限公司 | Air conditioner, control method and device thereof, and alarm method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112413832A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190236497A1 (en) | System and method for automated model selection for key performance indicator forecasting | |
| CN110727662A (en) | Low-voltage transformer area user phase identification method and system based on correlation analysis | |
| CN109242552B (en) | Shop positioning method based on big data | |
| CN111984442A (en) | Method and device for detecting abnormality of computer cluster system, and storage medium | |
| CN112413832B (en) | User identity recognition method based on user behavior and electric equipment thereof | |
| CN111444075A (en) | Method for automatically discovering key influence indexes | |
| CN112712112A (en) | Regional floating population identification method, device, equipment and medium | |
| CN115269958A (en) | Internet reliability data information acquisition and analysis system | |
| CN115130847A (en) | Equipment portrait modeling method and system | |
| CN113010394B (en) | Machine room fault detection method for data center | |
| US20210019656A1 (en) | Information processing device, information processing method, and computer program | |
| CN111737763B (en) | System for sorting storage data in block chain in ascending order | |
| CN107451029A (en) | A kind of information processing method and device, equipment | |
| CN109064578B (en) | Attendance system and method based on cloud service | |
| CN107087284A (en) | Quality control method and monitoring system, the server of a kind of network cell | |
| US20230325271A1 (en) | Failure symptom detection system, failure symptom detection method, and recording medium | |
| CN107316130A (en) | A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering | |
| CN116307407B (en) | Enterprise data visualization processing system and method based on cloud computing | |
| CN110569277A (en) | Method and system for automatically identifying and classifying configuration data information | |
| CN116166889B (en) | Hotel product screening method, device, equipment and storage medium | |
| CN114693365B (en) | Central air conditioning efficiency evaluation system | |
| CN117273375B (en) | Distribution network fault handling decision supervision and lifting system based on knowledge graph | |
| CN110582051B (en) | Passenger flow accurate test method based on wireless positioning technology | |
| JP4780670B2 (en) | Traffic analysis model construction method, apparatus, construction program, and storage medium thereof | |
| CN117198263A (en) | Industrial field large space active noise reduction method |
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 |