CN111932297A - User portrait generation method and recommendation method of air conditioning equipment - Google Patents
User portrait generation method and recommendation method of air conditioning equipment Download PDFInfo
- Publication number
- CN111932297A CN111932297A CN202010717685.7A CN202010717685A CN111932297A CN 111932297 A CN111932297 A CN 111932297A CN 202010717685 A CN202010717685 A CN 202010717685A CN 111932297 A CN111932297 A CN 111932297A
- Authority
- CN
- China
- Prior art keywords
- user
- air conditioner
- evaluated
- dimension
- control mode
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004378 air conditioning Methods 0.000 title claims abstract description 44
- 230000000694 effects Effects 0.000 claims abstract description 103
- 238000004364 calculation method Methods 0.000 claims description 40
- 230000006978 adaptation Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000013139 quantization Methods 0.000 claims description 9
- 239000006185 dispersion Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 29
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 3
- GAAKALASJNGQKD-UHFFFAOYSA-N LY-165163 Chemical compound C1=CC(N)=CC=C1CCN1CCN(C=2C=C(C=CC=2)C(F)(F)F)CC1 GAAKALASJNGQKD-UHFFFAOYSA-N 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000007791 dehumidification Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention provides a user portrait generation method and a recommendation method of air conditioning equipment, wherein the user portrait generation method comprises the following steps: the method comprises the steps that when the air conditioner detects preset type usage log data, the preset type usage log data are uploaded to a server; and after receiving the preset type of use log data, the server generates a user portrait of the user according to the preset type of use log data, wherein the user portrait comprises at least one of a character dimension, an activity dimension and a control mode dimension. The invention can analyze each air conditioner user so as to generate a personalized user portrait, thereby realizing the personalized recommendation of the air conditioner.
Description
Technical Field
The invention relates to the technical field of air conditioners, in particular to a user portrait generation method and a recommendation method of air conditioning equipment.
Background
With the development of air conditioning technology, an air conditioner becomes one of the necessary household appliances for the family, different users have unique use habits when using the air conditioner, and the different use habits enable the different users to have respective preferences for the air conditioner, so that the air conditioner preferred by the users can be obtained by analyzing the use habit data of the users.
However, after the air conditioners are sold, the sales volume or the distribution of the sales area of the air conditioners are generally only analyzed, the user habit data is not fully utilized to effectively analyze the user, the user needs to spend much effort on selecting the air conditioners, and a large amount of sales resources are wasted by air conditioner sellers.
Disclosure of Invention
The invention solves the problem that the user habit data is not fully utilized to effectively analyze the user in the prior art.
To solve the above problem, the present invention provides a user portrait generation method, including:
the method comprises the steps that when the air conditioner detects preset type usage log data, the preset type usage log data are uploaded to a server; and after receiving the preset type of use log data, the server generates a user portrait of the user according to the preset type of use log data, wherein the user portrait comprises at least one of a character dimension, an activity dimension and a control mode dimension.
The user image and the air conditioner are associated by analyzing the use log data generated by the user using the air conditioner to form the dimension required for describing the user portrait, so that the user image and the air conditioner are conveniently subjected to personalized air conditioner related service for the user, and the user is subjected to fine management.
Optionally, the user portrait includes a character dimension, and the generating the user portrait according to the preset type of usage log data includes:
acquiring the number of the function types used by the user from the preset type of use log data; when the number of the functional categories is less than or equal to a first preset threshold value, the character dimension comprises a conservative character type; when the number of the functional categories is larger than the first preset threshold and is smaller than or equal to a second preset threshold, the character dimension comprises a common type character type, wherein the first preset threshold is smaller than the second preset threshold; when the number of functional categories is greater than the second preset threshold, the personality dimension comprises a trial-type personality type.
The character type of the user in the use of the air conditioning function is judged according to the number of the air conditioning functions used by the user, the influence of the richness of the air conditioning function on the user is determined, the data type of the user is enriched, the image of the user to be evaluated in the use of the air conditioner is favorably depicted, and the accuracy of the user portrait related to the air conditioner is improved.
Optionally, the generating a user image according to the preset type of usage log data further includes:
the method comprises the steps of obtaining an air conditioner feature label of the air conditioner, using the air conditioner feature label as an air conditioner feature label preferred by a user, wherein the character dimension comprises the air conditioner feature label preferred by the user, and the air conditioner feature label comprises at least one of functionality, technology, after-sales, quality, appearance and price.
By using the air conditioner characteristic label preferred by the user as the content of the grid dimension in the user portrait, the content of the user portrait is enriched, and the comprehensiveness and the accuracy of the user portrait are improved.
Optionally, the user representation includes a liveness dimension, and the generating the user representation according to the preset type of usage log data includes:
acquiring air conditioner use time data from the preset type of use log data, and determining the activity of the user according to the air conditioner use time data; acquiring a time factor corresponding to the air conditioner use time data, and determining an activity threshold value based on the time factor, wherein the activity threshold values corresponding to spring and autumn are smaller than those corresponding to summer and winter; and determining the activity degree dimension of the user according to the size relation between the activity degree and the activity degree threshold value.
By setting different liveness threshold values in different seasons, more reasonable and accurate liveness dimensionality can be obtained, and the accuracy of portrayal of a user is improved.
Optionally, the determining the activity of the user according to the air conditioner usage time data includes:
acquiring the number of using days and the daily using time from the air conditioner using time data, and calculating the daily average using rate according to the number of using days, the daily using time and a first preset formula;
calculating the utilization rate of the air conditioner according to the number of days of use and a second preset formula;
taking the sum of the daily average utilization rate and the air conditioner utilization rate as the activity of the user;
the first preset formula is as follows:
the second preset formula is as follows:
wherein h1 is the daily average usage rate, h2 is the air conditioner usage rate, n is the days of use, tiAnd N is the total days corresponding to the air conditioner use time data.
The activity of the user to be evaluated is determined according to the daily average utilization rate and the air conditioner utilization rate, so that the importance degree of the air conditioner in the daily life of the user to be evaluated can be determined, the importance degree serves as a basis for judging whether the air conditioner to be evaluated is recommended or not, and the recommendation accuracy and the purchase rate after recommendation can be improved.
Optionally, the user representation includes a control mode dimension, and generating the user representation of the user according to the preset type of usage log data includes:
acquiring the control mode and the type number of the user used from the preset type of use log data;
when the number of the types of the control modes is more than 1, calculating the use frequency of each control mode used by the user, and calculating the dispersion degree of the use frequency of each control mode;
and determining the dimension of the control mode of the user according to the control mode used by the user and the discrete degree of the use frequency of each control mode.
By determining the control modes and the types of the control modes used by the user to be evaluated and the discrete degree of the use frequency of each control mode, the use habits of the user to be evaluated on the control modes can be fully reflected, and the control modes are used as a part of the user portrait, so that the comprehensiveness and the accuracy of the user portrait can be improved.
Optionally, the user representation further includes a consumer capability dimension. By incorporating the consumption capability into the user portrait, the user portrait can be more comprehensively depicted, air conditioners with unmatched prices are screened out in subsequent air conditioner recommendation, and more accurate personalized recommendation is achieved.
The invention provides a recommendation method of air conditioning equipment, which comprises the following steps:
acquiring a user portrait of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, wherein the user portrait is generated according to any one of the user portrait generation methods; calculating the adaptation degree of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics; and when the adaptation degree is larger than or equal to a preset value, recommending the air conditioner to be evaluated to the user to be evaluated.
The method comprises the steps of determining the adaptation degrees of a user to be evaluated and an air conditioner to be evaluated according to the user image of the user to be evaluated and the characteristic attribute of the air conditioner to be evaluated, recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degrees of the user to be evaluated and the air conditioner to be evaluated are larger than or equal to a preset value, realizing personalized recommendation of the air conditioner, and improving the recommendation accuracy of the air conditioner equipment.
Optionally, the user image of the user to be evaluated includes a character dimension and a control mode dimension, the character dimension is determined based on the air conditioner feature tag preferred by the user to be evaluated, the control mode dimension is determined based on the control mode used by the user to be evaluated, and the attribute feature includes the air conditioner feature tag of the air conditioner to be evaluated and a supported control mode.
The user portrait is described based on the air conditioner use data, the user portrait is associated with the air conditioner, and the adaptation degree of the user to be evaluated and the air conditioner to be evaluated can be calculated based on the adapted user portrait dimension and the attribute characteristics of the air conditioner, so that personalized air conditioner recommendation can be conveniently realized.
Optionally, the calculating the degree of adaptation of the user to be evaluated to the air conditioner to be evaluated based on the user portrait and the attribute features includes:
obtaining a plurality of fitness calculation factors based on the user representation and the attribute features, wherein the user representation comprises a personality dimension and the fitness calculation factors comprise personality factors; and/or, the user representation includes a control manner dimension, and the fitness calculation factor includes a control manner factor; and/or, the user representation includes an activity dimension and the fitness calculation factor includes a control mode factor; and acquiring the weight corresponding to each fitness calculation factor, and calculating the weighted sum of each fitness calculation factor, wherein the weighted sum is the fitness of the user to be evaluated and the air conditioner to be evaluated.
The weighted sum is calculated for the plurality of adaptation degree calculation factors and used as the adaptation degree of the user to be evaluated and the air conditioner to be evaluated, so that the adaptation degree can be determined by integrating a plurality of factors, and the accuracy of the adaptation degree calculation is improved.
Optionally, the fitness calculation factor comprises a character factor, and the obtaining a plurality of fitness calculation factors based on the user representation and the attribute feature comprises:
acquiring an air conditioner feature label preferred by the user to be evaluated and a quantized value corresponding to a personality type of the user to be evaluated from the personality dimension, wherein the personality type comprises a conservative personality type, a common personality type and an attempted personality type;
determining an air conditioner characteristic label of the air conditioner to be evaluated from the attribute characteristics, and calculating a first proportion of the air conditioner characteristic label in the air conditioner characteristic label preferred by the user to be evaluated;
determining the character factor based on the first proportion, the quantization value corresponding to the character type of the user to be evaluated and a third preset formula, wherein the third preset formula is as follows:
Pc＝U*e-(1-b)，
wherein Pc is the character factor, U is a quantization value of a character type, and b is the first duty.
The method comprises the steps of quantizing the character dimension in the user image into a character factor through a first proportion of a characteristic label of the air conditioner to be evaluated in an air conditioner characteristic label preferred by a user to be evaluated, a quantization value corresponding to the character type of the user to be evaluated and a third preset formula, so that the matching calculation of the user to be evaluated and the air conditioner to be evaluated is realized, the adaptation degree of the user to be evaluated and the air conditioner to be evaluated can be conveniently and accurately determined subsequently, and the accuracy of the targeted recommendation of the air conditioner is improved.
Optionally, the fitness calculation factor includes a control manner factor, and the obtaining a plurality of fitness calculation factors based on the user portrait and the attribute feature includes:
acquiring the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode from the control mode dimension;
determining the control mode supported by the air conditioner to be evaluated from the attribute characteristics, and calculating a second proportion of the control mode supported by the air conditioner to be evaluated in the control mode used by the user to be evaluated;
determining the control mode factor based on the second proportion, the discrete degree and a fourth preset formula, wherein the fourth preset formula is as follows:
Pm＝s*e-(1-c)，
wherein Pm is the control mode factor, s is the discrete degree, and c is the second proportion.
The quantification of the use habits of the user to be evaluated on the control mode is realized through the second proportion of the control mode supported by the air conditioner to be evaluated in the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode, the control mode dimensionality in the user image is quantified into a control mode factor by combining a fourth preset formula, the matching of the user to be evaluated and the air conditioner to be evaluated on the air conditioner is realized, the accurate adaptation degree is conveniently obtained subsequently, and the accuracy of accurate marketing is improved.
The invention provides a user portrait generation system, comprising: air conditioners and servers; the air conditioner uploads the preset type of use log data to a server when the preset type of use log data is detected; and after receiving the preset type of use log data, the server generates a user portrait of the user according to the preset type of use log data, wherein the user portrait comprises at least one of a character dimension, an activity dimension and a control mode dimension.
Compared with the prior art, the user portrait generation system of the invention has the advantages that the user portrait generation method is consistent with the user portrait generation method, and the description is omitted here.
The present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is read and executed by a processor, the user representation generation method as described in any of the above is implemented.
The beneficial effects of the computer readable storage medium of the present invention compared to the prior art are consistent with the user portrait generation method, which is not repeated herein.
The invention provides a recommendation device of air conditioning equipment, which comprises: the system comprises an acquisition unit, a storage unit and a control unit, wherein the acquisition unit is used for acquiring a user portrait of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, and the user portrait is generated according to the user portrait generation method; the processing unit is used for calculating the adaptation degree of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics; and the recommending unit is used for recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degree is greater than or equal to a preset value.
Compared with the prior art, the recommendation device of the air conditioning equipment has the beneficial effects consistent with the recommendation method of the air conditioning equipment, and the details are not repeated here.
The invention also provides a recommendation terminal, which comprises a computer readable storage medium and a processor, wherein the computer readable storage medium is used for storing a computer program, and the computer program is read by the processor and runs to realize the recommendation method of the air conditioning equipment.
Compared with the prior art, the beneficial effects of the recommendation terminal of the invention are consistent with the recommendation method of the air conditioning equipment, and are not repeated here.
The invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is read and executed by a processor, the computer program implements the recommendation method for air conditioning equipment as described in any one of the above.
Compared with the prior art, the beneficial effects of the computer readable storage medium of the invention are consistent with the recommendation method of the air conditioning equipment, and are not repeated herein.
Drawings
FIG. 1 is a schematic diagram of a user representation generation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of a method for recommending an air conditioning apparatus according to the present invention;
FIG. 3 is a schematic diagram of a user representation generation system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an embodiment of a recommendation apparatus for an air conditioning device according to the present invention;
FIG. 5 is a schematic diagram of a recommendation terminal according to an embodiment of the present invention.
Description of reference numerals:
101-an air conditioner; 102-a server; 201-an acquisition unit; 202-a processing unit; 203-recommendation unit; 301-a processor; 302-computer readable storage medium.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
The invention provides a user portrait generation method. FIG. 1 is a schematic diagram of an embodiment of a user representation generation method according to the present invention, as shown in FIG. 1, the user representation generation method includes:
step S10, when detecting the preset type of usage log data, the air conditioner uploads the preset type of usage log data to a server;
the preset type of usage log data optionally includes function usage data, wherein the function usage data includes the number of types of functions used by the user, may further include usage time data, wherein the usage time data includes usage duration data and/or usage frequency data, and may further include control mode usage data, wherein the control mode usage data includes the number of types and control modes used by the user.
Alternatively, the air conditioner may upload an air conditioner feature tag, an air conditioner model, etc. of the air conditioner to the server, in addition to uploading the preset type of usage log data to the server.
Step S20, after receiving the preset type of usage log data, the server generates a user portrait of the user according to the preset type of usage log data, where the user portrait includes at least one of a character dimension, an activity dimension, and a control manner dimension.
The character dimension is used for characterizing the character characteristics of the user on the air conditioner use and/or the air conditioner purchase, for example, on the air conditioner use, an trying-type user label is added for a user who actively tries a new function or a plurality of functions, and a conservative-type user label is added for a user who only uses a certain function of the air conditioner. The activity dimension is used for representing the air conditioner use frequency of a user, for example, when the use rate of the user is more than 60%, an active user label is added to the user, when the use rate of the user is less than 30%, an inactive user label is added to the user, when the use rate of the user is less than or equal to 60%, and is more than or equal to 30%, a regular user label is added to the user, wherein the use rate is the ratio of the total days of using the air conditioner to the total days of the month in one month time. The control mode dimension is used for representing the control mode frequently used by the user, for example, if the user frequently uses the remote controller for control, the remote controller control label is added for the user.
Optionally, the user representation may further include a consumption capability dimension for characterizing the consumption capability and consumption level of the user in terms of air conditioning, and may have a price range as the consumption capability dimension, for example, 3000-.
Optionally, generating a user portrait of the user according to the preset type of usage log data specifically includes: generating a personality dimension of the user based on air conditioning feature tags of the user preferences including one or more of functionality, technology, after-sales, quality, appearance, price and/or functional usage data including a number of categories of functions used by the user, where the functions include, but are not limited to, cooling, heating, dehumidification, auto-tune mode, playing music;
optionally, generating a user portrait of the user according to the preset type of usage log data specifically includes: generating an activity dimensionality of the user based on the use time data, wherein the use time data comprises use duration data and/or use frequency data, and the use duration data can be the use duration of each time and can also be the use duration of each day; the usage frequency data may be a monthly usage frequency, which may be defined as a value of the number of days of monthly usage divided by the total number of days of monthly;
optionally, generating a user portrait of the user according to the preset type of usage log data specifically includes: and generating a control mode dimension of the user based on the control mode use data, wherein the control mode use data comprises the control modes used by the user and the number of types of the control modes, and the use frequency or frequency of each control mode, and the control modes comprise but are not limited to voice control, APP (application) control, remote controller control and gesture control.
Optionally, the consumption capacity dimension may be determined based on price data of the air conditioner, the consumption capacity of the user may be classified based on a price interval in which the price of the air conditioner falls, and how to classify the specific grade may be determined according to actual needs. By incorporating the consumption capability into the user portrait, the user portrait can be more comprehensively depicted, air conditioners with unmatched prices are screened out in subsequent air conditioner recommendation, and more accurate personalized recommendation is achieved.
The user image and the air conditioner are associated by analyzing the use log data generated by the user using the air conditioner to form the dimension required for describing the user portrait, so that the user image and the air conditioner are conveniently subjected to personalized air conditioner related service for the user, and the user is subjected to fine management.
In an alternative embodiment, the representation of the character dimension is: a user preferred air conditioning feature label. Wherein the air conditioner characteristic label includes one or more of functionality, technology, after-market, quality, appearance, price.
In an alternative embodiment, the representation of the character dimension is: a personality type. The character types can include a conservative type, a common type and a trial type.
In an alternative embodiment, the representation of the character dimension is: air conditioner feature labels, personality types preferred by the user.
Optionally, the user image includes a character dimension, and the generating the user image according to the preset type of usage log data in step S20 includes:
step S200, acquiring the number of the function types used by the user from the preset type of use log data;
step S201, when the number of the functional categories is less than or equal to a first preset threshold, the character dimension comprises a conservative character type;
step S202, when the number of the functional categories is larger than the first preset threshold and is smaller than or equal to a second preset threshold, the character dimension comprises a common character type, wherein the first preset threshold is smaller than the second preset threshold;
step S203, when the number of the functional categories is greater than the second preset threshold, the personality dimension includes an attempted personality type.
The number of the function types used by the user to be evaluated may be the number of the function types after the power-on/off function is removed.
The first preset threshold and the second preset threshold are both default thresholds, and can be determined according to actual needs, the first preset threshold can be selected as 2 or 3, the second preset threshold can be selected as 4 or 5, optionally, if the number of the function types used by the user is less than or equal to 3, the user belongs to a conservative user, if the number of the function types used by the user is greater than 3 or less than or equal to 5, the user belongs to a common user, and if the number of the function types used by the user is greater than 5, the user is willing to explore a new function, and the user belongs to a trial user.
The character type of the user in the use of the air conditioning function is judged according to the number of the air conditioning functions used by the user, the influence of the richness of the air conditioning function on the user is determined, the data type of the user is enriched, the image of the user to be evaluated in the use of the air conditioner is favorably depicted, and the accuracy of the user portrait related to the air conditioner is improved.
Optionally, the generating a user image according to the preset type of usage log data in step S20 further includes:
the method comprises the steps of obtaining an air conditioner feature label of the air conditioner, using the air conditioner feature label as an air conditioner feature label preferred by a user, wherein the character dimension comprises the air conditioner feature label preferred by the user, and the air conditioner feature label comprises at least one of functionality, technology, after-sales, quality, appearance and price.
The air conditioner characteristic label is the characteristic of the air conditioner, and the air conditioner characteristic label comprises but is not limited to functionality, technology, after-sales, quality, appearance and price, wherein the functional label represents more and richer functions of the air conditioner, and when the number of the functions of the air conditioner is greater than or equal to the preset number, the functional label is added to the air conditioner; the technical label represents that the air conditioner adopts a new technology or the technical content is high, and the technical label can be manually added; the after-sale label represents that the air conditioner has better after-sale service, optionally, when the quality guarantee period or the free maintenance period of the air conditioner is longer than or equal to a certain time, the after-sale label is added to the air conditioner, and the after-sale label can also be manually added; the quality label represents that the air conditioner has better product quality, the air conditioner uses components with better quality, the configuration is higher, the quality is better, and the quality label can be added manually; the appearance label represents that the air conditioner has high ornamental value or unique design appearance; the price tag represents that the price of the air conditioner is lower under the same configuration, the air conditioner can be added manually, the air conditioner can also be added based on a preset tag adding program, optionally, for a certain configuration, a price threshold corresponding to the configuration is obtained, and when the price of the certain air conditioner with the configuration is smaller than the price threshold, the price tag is added to the air conditioner.
The user preference air conditioner feature label is used as the content of the grid dimension in the user portrait, so that the user portrait content is enriched, and the comprehensiveness and accuracy of the user portrait are improved.
In an alternative embodiment, the activity dimension is expressed as: and (4) liveness. And acquiring air conditioner use time data from the preset type of use log data, and determining the activity of the user to be evaluated according to the air conditioner use time data, wherein the activity is used as an activity dimension.
Optionally, the user image includes a liveness dimension, and the generating a user image according to the preset type of usage log data in step S20 includes:
step S210, obtaining air conditioner use time data from the preset type use log data, and determining the activity of the user according to the air conditioner use time data;
the activity of the user, specifically the activity of the user in the use of the air conditioner, is characterized by the use time data of the air conditioner, such as the use duration and/or the use frequency. The air conditioner use time data may be data generated when the user uses the air conditioner within a last preset time period (e.g., about 1 to 3 months). Through the latest use time data, the latest use habit of the user can be obtained, and further more accurate activity can be obtained.
In one embodiment, the total usage time within the preset time period is obtained by analyzing the usage time data, a ratio of the total usage time to the preset time period (the preset time period is converted into a value in hours) is calculated, and the ratio is used as the activity of the user, for example, the total usage time is 60 hours, and the preset time period is 720 hours, so the activity of the user is 60/720-8.3%. In another embodiment, the analysis is performed based on the usage time data to obtain the total number of days of usage in the preset time period, the ratio of the number of days of usage to the preset time period (the preset time period is converted into a number in days) is calculated, and the ratio is used as the activity of the user, for example, the total number of days of usage is 10 days, the preset time period is 30 days, and the activity of the user is 1/3. In another embodiment, the total usage duration and the total usage days in the preset duration are obtained by analyzing the usage time data, the ratio of the total usage duration to the preset duration (the preset duration is converted into a numerical value in units of hours) is calculated, the ratio of the usage days to the preset duration (the preset duration is converted into a numerical value in units of days) is calculated, and the sum of the two ratios is used as the activity of the user.
Optionally, step S210 includes:
acquiring the number of using days and the daily using time from the air conditioner using time data, and calculating the daily average using rate according to the number of using days, the daily using time and a first preset formula; calculating the utilization rate of the air conditioner according to the number of days of use and a second preset formula; taking the sum of the daily average utilization rate and the air conditioner utilization rate as the activity of the user;
the first preset formula is as follows:
the second preset formula is as follows:
wherein h1 is the daily average usage rate, h2 is the air conditioner usage rate, n is the days of use, tiThe using time length (unit: hour) of the ith day is shown, and N is the total days corresponding to the using time data of the air conditioner.
Optionally, after detecting the air conditioner use time data of a preset time period, the air conditioner uploads the air conditioner use time data of the preset time period to the server, wherein the total days of the preset time period are the total days corresponding to the air conditioner use time data, and the preset time period is one month. The number of days of use refers to the number of days that the user used the air conditioner.
When calculating the daily average usage, the daily usage of each day is calculated, the daily usage time is divided by the time of the day (i.e., 24 hours), and then the average of the daily usage of all the usage days is calculated, and the average of the daily usage is used as the daily average usage.
And when calculating the air conditioner utilization rate, dividing the utilization days by the total days corresponding to the air conditioner utilization time data to obtain a ratio as the air conditioner utilization rate.
The importance degree of the air conditioner in the daily life of the user can be determined by jointly determining the activity of the user according to the daily average utilization rate and the air conditioner utilization rate, and the importance degree is used as a basis for judging whether the air conditioner to be evaluated is recommended or not, so that the recommendation accuracy and the recommended purchase rate can be improved.
Step S211, acquiring a time factor corresponding to the air conditioner use time data, and determining an activity threshold value based on the time factor, wherein the activity threshold value corresponding to spring and autumn is smaller than the activity threshold value corresponding to summer and winter;
the temperature in spring and autumn is more suitable, and the air conditioner demand in spring and autumn is lower compared with summer and winter, so that the setting of the corresponding activity threshold value in spring and autumn is smaller than that in summer and winter, more reasonable activity dimensionality can be obtained, and the accuracy of user portrait depicting is improved.
The air conditioner use time data includes the time of the user using the air conditioner, the season of the user is determined based on the use time data, and the time factor is determined. The time factor of spring/autumn is different from the time factor of summer/winter, and the time factor can be a numerical value or a time mark. In one embodiment, the time factor is a number, and the activity threshold may be calculated based on the time factor, and optionally, a base threshold is set, and the activity threshold is obtained by multiplying the time factor by the base threshold. For example, if the base threshold is set to 30%, the time factor for spring and autumn is 1, and the time factor for summer and winter is 2, then the activity threshold for spring and autumn is 30%, and the activity threshold for summer and winter is 60%. In another embodiment, the time factor is a time identifier, and different time identifiers are associated with different activity thresholds, and the corresponding activity thresholds can be obtained directly based on the time factor, for example, the time factor corresponding to spring/autumn is a first time identifier, the time factor corresponding to summer/winter is a second time identifier, the activity threshold corresponding to the first time identifier is 30%, and the activity threshold corresponding to the second time identifier is 60%.
Alternatively, when it is determined that the time in which the user uses the air conditioner spans spring and summer, or summer and autumn, or fall and winter, or winter and spring based on the usage time data, it is determined which season the time in which the user uses the air conditioner belongs to is more time, and after the season is determined, the activity threshold is determined by a time factor corresponding to the season. For example, in the usage time data, the time of the user using the air conditioner is 30 days, wherein 10 days are in spring and 20 days are in summer, and the activity threshold is determined by a time factor corresponding to summer.
The time when the user uses the air conditioner in this step explanation is the same as the time when the user uses the air conditioner on which the activity level of the user is determined in step S210.
Step S212, determining the activity degree dimension of the user according to the size relation between the activity degree and the activity degree threshold value.
The activity threshold value can be one or more, and can be determined according to actual requirements.
Optionally, the activity threshold is one, the expression form of the activity dimension is an active user and an inactive user, when the activity of the user is greater than the activity threshold, it is indicated that the user is an active user, the activity dimension is an active user, and when the activity of the user is less than the activity threshold, the activity dimension is an inactive user.
Optionally, the number of the activity thresholds is two, which are a first activity threshold and a second activity threshold, respectively, where the first activity threshold is smaller than the second activity threshold, and the expression form of the activity dimension may be selected as: the active level. When the activity of the user is smaller than the first activity threshold value, the user is an inactive user, the activity level is low, when the activity of the user is larger than or equal to the first activity threshold value and smaller than the second activity threshold value, the user is a common user, in the activity level, when the activity of the user is larger than or equal to the second activity threshold value, the user is an active user, and the activity level is high.
In one embodiment, where the first activity threshold is represented by θ 1, the second activity threshold is represented by θ 2, the time factor is, and H is the activity of the user, then:
H＝h1+h2，
when in use
The user is an inactive user, and the activity degree is high;
when in use
The users are ordinary users, and the liveness is high;
when in use
The users are active users, and the activity is high.
Wherein, the value may be set to 1 in spring and autumn and 2 in summer and winter, and θ 1 and θ 2 may be set to 30% and 60%, respectively.
Optionally, the user representation includes a control mode dimension, and generating the user representation of the user according to the preset type of usage log data includes:
step S220, obtaining the control mode and the type number of the user from the preset type of use log data;
the control modes used by the user include but are not limited to voice control, APP control, remote controller control and gesture control. The control mode use data is the use data within the latest preset time (such as about 1 to 3 months), and the latest use habit of the user can be obtained through the latest use data.
Step S221, when the number of the types of the control modes is larger than 1, calculating the use frequency of each control mode used by the user, and calculating the discrete degree of the use frequency of each control mode;
when the number of the types of the control modes is more than 1, acquiring the frequency of using each control mode by the user in the latest preset time, calculating the use frequency of each control mode, for example, the frequency of controlling the air conditioner by the user in the latest preset time is n1, the frequency of controlling the air conditioner by the APP is n2, the frequency of controlling the air conditioner by the remote controller is n3, calculating the use frequency of each control mode, and PSpeech sound＝n1/(n1+n2+n3)，PAPP＝n2/(n1+n2+n3)，PRemote controllerN3/(n1+ n2+ n3), calculating the dispersion degree of the use frequency of each control mode, and calculating the dispersion degree, wherein the dispersion degree can be measured by calculating the average difference and the standard deviation of the three, and optionally, the dispersion degree is expressed by s, and the calculation method of the dispersion degree is as follows:
avg＝(Pspeech sound+PAPP+PRemote control)/3，
Wherein, the smaller s is, the lower the preference of the user on the control mode is, the more or less each control mode is, and the larger s is, the better the user prefers a certain control mode.
Step S222, determining the dimension of the control mode of the user according to the control mode used by the user and the discrete degree of the use frequency of each control mode.
The control mode dimension of the user can be represented by the following form: control mode, number of control mode types, s. The control mode refers to a control mode with the highest use frequency or use frequency of the user. The control mode dimension of the user can also be represented by the following form: the number of control modes, s.
By determining the control modes and the number of types used by the user and the discrete degree of the use frequency of each control mode, the use habits of the user on the control modes can be fully reflected, and the control modes are used as a part of the user portrait, so that the comprehensiveness and the accuracy of the user portrait can be improved.
The invention further provides a recommendation method of the air conditioning equipment. Fig. 2 is a schematic view of an embodiment of a recommendation method for an air conditioning device according to the present invention, and as shown in fig. 2, the recommendation method for an air conditioning device includes:
step S30, obtaining a user portrait of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, wherein the user portrait is generated according to any one of the user portrait generation methods;
the embodiment of the invention refers to the air conditioner as the air conditioner to be evaluated and refers to the user as the user to be evaluated.
The attribute characteristics of the air conditioner to be evaluated include but are not limited to an air conditioner characteristic label and a supported air conditioner control mode. And storing the attribute characteristics of the air conditioner to be evaluated in association with the air conditioner to be evaluated. The related explanation of the air conditioner feature label is given above and will not be described herein. The supported air conditioner control modes include but are not limited to voice control, APP (application) control, remote controller control and gesture control, and one air conditioner can support one or more control modes.
Step S40, calculating the adaptation degree of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics;
optionally, the user image of the user to be evaluated includes a character dimension and a control mode dimension, the character dimension is determined based on the air conditioner feature tag preferred by the user to be evaluated, the control mode dimension is determined based on the control mode used by the user to be evaluated, and the attribute feature includes the air conditioner feature tag of the air conditioner to be evaluated and a supported control mode.
The adaptation degree of the user to be evaluated and the air conditioner to be evaluated can be calculated based on the character dimension and the air conditioner characteristic label of the air conditioner to be evaluated and based on the dimension of the control mode and the control mode supported by the air conditioner to be evaluated. Therefore, the user portrait is described based on the air conditioner use data, the user portrait is associated with the air conditioner, the adaptation degree of the user to be evaluated and the air conditioner to be evaluated can be calculated based on the adapted user portrait dimension and the attribute characteristics of the air conditioner, and personalized air conditioner recommendation can be conveniently realized.
And step S50, recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degree is greater than or equal to a preset value.
And when the adaptation degree is larger than or equal to the preset value, the air conditioner to be evaluated is possibly more in line with the preference of the user to be evaluated, and the air conditioner to be evaluated can be recommended to the user to be evaluated.
And when the adaptation degree is smaller than the preset value, the air conditioner to be evaluated is not recommended to the user to be evaluated, so that the problem of invalid pushing and trouble brought to the user to be evaluated is avoided.
The method comprises the steps of determining the adaptation degrees of a user to be evaluated and an air conditioner to be evaluated according to the user image of the user to be evaluated and the characteristic attribute of the air conditioner to be evaluated, recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degrees of the user to be evaluated and the air conditioner to be evaluated are larger than or equal to a preset value, and achieving the accuracy of recommendation of the air conditioning equipment.
Optionally, the step S40 includes:
step S41, obtaining a plurality of fitness calculation factors based on the user portrait and the attribute characteristics, wherein the user portrait includes a character dimension, and the fitness calculation factors include character factors; and/or, the user representation includes a control manner dimension, and the fitness calculation factor includes a control manner factor; and/or, the user representation includes an activity dimension and the fitness calculation factor includes a control mode factor;
in one embodiment, the fitness calculation factor includes a character factor, and the step S41 includes:
acquiring an air conditioner feature label preferred by the user to be evaluated and a quantized value corresponding to a personality type of the user to be evaluated from the personality dimension, wherein the personality type comprises a conservative personality type, a common personality type and an attempted personality type; determining an air conditioner characteristic label of the air conditioner to be evaluated from the attribute characteristics, and calculating a first proportion of the air conditioner characteristic label in the air conditioner characteristic label preferred by the user to be evaluated; determining the character factor based on the first proportion, the quantization value corresponding to the character type of the user to be evaluated and a third preset formula, wherein the third preset formula is as follows:
Pc＝U*e-(1-b)，
wherein Pc is the character factor, U is a quantization value of a character type, and b is the first duty.
The method can obtain the air conditioner feature label preferred by the user to be evaluated and the quantized value corresponding to the character type of the user to be evaluated based on the character dimension of the user to be evaluated, and optionally, the numerical quantization of the conservative character type, the ordinary character type and the trial character type can be selected from 0.3, 0.5 and 0.9. b is defined as follows: the air conditioner to be evaluated has a ratio of the characteristic label in the air conditioner characteristic label preferred by the user. For example, the following steps are carried out: example 1, if item a has a characteristic label: the technology, the air conditioner feature tag preferred by the user u1 is functionality, and the technology, after sale, quality, includes the technical tag of the commodity a, and b is 1/4, and if the air conditioner feature tag preferred by the user u1 is appearance, price, and does not include the tag of the commodity a, b is 0.
The method comprises the steps of quantizing the character dimension in the user image into a character factor through a first proportion of a characteristic label of the air conditioner to be evaluated in an air conditioner characteristic label preferred by a user to be evaluated, a quantization value corresponding to the character type of the user to be evaluated and a third preset formula, so that the matching calculation of the user to be evaluated and the air conditioner to be evaluated is realized, the adaptation degree of the user to be evaluated and the air conditioner to be evaluated can be conveniently and accurately determined subsequently, and the accuracy of the targeted recommendation of the air conditioner is improved.
In one embodiment, the fitness calculation factor includes an activity factor, Pa represents the activity factor, and when the expression form of the activity dimension is activity, the activity is the activity factor, and when the expression form of the activity dimension is activity level, the activity level is quantized, and the activity level is quantized to be 0.3, 0.5, and 0.9 respectively in low, medium, and high. The calculation of the activity level and the determination of the activity level have been given above and will not be described herein.
In one embodiment, the fitness calculation factor includes a control mode factor, and the step S41 includes:
acquiring the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode from the control mode dimension; determining the control mode supported by the air conditioner to be evaluated from the attribute characteristics, and calculating a second proportion of the control mode supported by the air conditioner to be evaluated in the control mode used by the user to be evaluated; determining the control mode factor based on the second proportion, the discrete degree and a fourth preset formula, wherein the fourth preset formula is as follows:
Pm＝s*e-(1-c)，
wherein Pm is the control mode factor, s is the discrete degree, and c is the second proportion.
The control mode dimension can comprise the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode, and the control mode used by the user to be evaluated and the discrete degree can be directly obtained after the control mode dimension is obtained. c is the ratio of the control types supported by the air conditioner to the number of the control modes used by the user. For example, if the product B supports APP control, and the control method commonly used by the user u3 is APP control, the remote controller controls two types, c is 1/2.
The quantification of the use habits of the user to be evaluated on the control mode is realized through the second proportion of the control mode supported by the air conditioner to be evaluated in the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode, the control mode dimensionality in the user image is quantified into a control mode factor by combining a fourth preset formula, the matching of the user to be evaluated and the air conditioner to be evaluated on the air conditioner is realized, the accurate adaptation degree is conveniently obtained subsequently, and the accuracy of accurate marketing is improved.
In one embodiment, the fitness calculation factor includes a consumption capacity factor, and the consumption capacity dimension is expressed in the form of: the consumption grade can be quantified, and optionally, the consumption grade is divided into one, two and three grades, and the three grades are respectively quantified to be 0.3, 0.5 and 0.9.
And step S42, acquiring weights corresponding to the fitness calculation factors, and calculating a weighted sum of the fitness calculation factors, wherein the weighted sum is the fitness of the user to be evaluated and the air conditioner to be evaluated.
In one embodiment, the fitness calculation factors include a character factor, an activity factor, a control mode factor, and a consumption capacity factor, and the User uses the fitness calculation factorsscoreThe indication of the degree of adaptation includes:
wherein, α, β, γ are weighting coefficients, and the sum of the four is equal to 1, and corresponding proportions can be assigned according to the importance degree. In one embodiment, > β > α > γ.
The weighted sum is calculated for the plurality of adaptation degree calculation factors and used as the adaptation degree of the user to be evaluated and the air conditioner to be evaluated, so that the adaptation degree can be determined by integrating a plurality of factors, and the accuracy of the adaptation degree calculation is improved.
The invention also provides a user portrait generation system. Referring to FIG. 3, in an embodiment of the user representation generation system of the present invention, the user representation generation system comprises: an air conditioner 101 and a server 102; when detecting the preset type of usage log data, the air conditioner 101 uploads the preset type of usage log data to a server; after receiving the preset type of usage log data, the server 102 generates a user portrait of the user according to the preset type of usage log data, where the user portrait includes at least one of a character dimension, an activity dimension, and a control manner dimension.
Optionally, the user representation generating system is further configured to perform the user representation generating method according to any of the above embodiments, and relevant features and explanations have been given above and are not repeated here.
The present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is read and executed by a processor, the user representation generation method as described in any of the above is implemented.
The beneficial effects of the computer readable storage medium of the present invention compared to the prior art are consistent with the user portrait generation method, which is not repeated herein.
The invention further provides a recommendation device of the air conditioning equipment. As shown in fig. 4, the recommendation apparatus of an air conditioner includes:
an obtaining unit 201, configured to obtain a user portrait of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, where the user portrait is generated according to the user portrait generation method as described in any one of the above;
the processing unit 202 is used for calculating the adaptability of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics;
and the recommending unit 203 is used for recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degree is greater than or equal to a preset value.
Optionally, the recommendation apparatus for an air conditioner of the present invention is further configured to perform the recommendation method for an air conditioner according to any of the above embodiments, and relevant features and explanations have been given above and are not described herein again.
Compared with the prior art, the recommendation device of the air conditioning equipment has the beneficial effects consistent with the recommendation method of the air conditioning equipment, and the details are not repeated here.
The invention provides a recommendation terminal. Fig. 5 is a schematic diagram of a recommendation terminal according to an embodiment of the present invention. Referring to fig. 5, the recommendation terminal of the present invention includes a computer-readable storage medium 302 storing a computer program, and a processor 301, wherein the computer program is read by the processor 301 and executed to implement the recommendation method for air conditioning equipment according to any one of the above.
The recommendation terminal can be selected from mobile terminals such as a tablet computer, a notebook computer and a palm computer, and can also be fixed terminals such as a digital TV and a desktop computer. The recommending terminal can also be implemented on the server, and after the air conditioner to be evaluated is determined to be recommended to the user to be evaluated, the air conditioner to be evaluated is pushed to the mobile terminal or the fixed terminal used by the user to be evaluated. Alternatively, the recommendation terminal may be implemented as the server 102 in the user representation generation system.
Compared with the prior art, the beneficial effects of the recommendation terminal of the invention are consistent with the recommendation method of the air conditioning equipment, and are not repeated here.
The invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is read and executed by a processor, the computer program realizes the recommendation method of the air conditioning equipment.
Compared with the prior art, the beneficial effects of the computer readable storage medium of the invention are consistent with the recommendation method of the air conditioning equipment, and are not repeated herein.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (17)
1. A user representation generation method, comprising:
the method comprises the steps that when the air conditioner detects preset type usage log data, the preset type usage log data are uploaded to a server;
and after receiving the preset type of use log data, the server generates a user portrait of the user according to the preset type of use log data, wherein the user portrait comprises at least one of a character dimension, an activity dimension and a control mode dimension.
2. A user representation generation method as claimed in claim 1, wherein said user representation includes said personality dimension, and said generating a user representation from said preset type of usage log data comprises:
acquiring the number of the function types used by the user from the preset type of use log data;
when the number of the functional categories is less than or equal to a first preset threshold value, the character dimension comprises a conservative character type;
when the number of the functional categories is larger than the first preset threshold and is smaller than or equal to a second preset threshold, the character dimension comprises a common type character type, wherein the first preset threshold is smaller than the second preset threshold;
when the number of functional categories is greater than the second preset threshold, the personality dimension comprises a trial-type personality type.
3. The user representation generation method of claim 2, wherein said generating a user representation from said preset type of usage log data further comprises:
the method comprises the steps of obtaining an air conditioner feature label of the air conditioner, using the air conditioner feature label as an air conditioner feature label preferred by a user, wherein the character dimension comprises the air conditioner feature label preferred by the user, and the air conditioner feature label comprises at least one of functionality, technology, after-sales, quality, appearance and price.
4. The user representation generation method of claim 1, wherein the user representation includes the liveness dimension, and wherein generating a user representation from the preset type of usage log data comprises:
acquiring air conditioner use time data from the preset type of use log data, and determining the activity of the user according to the air conditioner use time data;
acquiring a time factor corresponding to the air conditioner use time data, and determining an activity threshold value based on the time factor, wherein the activity threshold values corresponding to spring and autumn are smaller than those corresponding to summer and winter;
and determining the activity degree dimension of the user according to the size relation between the activity degree and the activity degree threshold value.
5. The user representation generation method of claim 4, wherein said determining a user's liveness from said air conditioning usage time data comprises:
acquiring the number of using days and the daily using time from the air conditioner using time data, and calculating the daily average using rate according to the number of using days, the daily using time and a first preset formula;
calculating the utilization rate of the air conditioner according to the number of days of use and a second preset formula;
taking the sum of the daily average utilization rate and the air conditioner utilization rate as the activity of the user;
the first preset formula is as follows:
the second preset formula is as follows:
wherein h1 is the daily average usage rate, h2 is the air conditioner usage rate, n is the days of use, tiAnd N is the total days corresponding to the air conditioner use time data.
6. A user representation generation method as claimed in claim 1, wherein said user representation includes said control mode dimension, and said generating a user representation of a user from said predetermined type of usage log data comprises:
acquiring the control mode and the type number of the user used from the preset type of use log data;
when the number of the types is more than 1, calculating the use frequency of each control mode used by the user, and calculating the dispersion degree of the use frequency of each control mode;
and determining the dimension of the control mode of the user according to the control mode used by the user and the discrete degree of the use frequency of each control mode.
7. The user representation generation method of any of claims 1-6, wherein the user representation further comprises a consumer capability dimension.
8. A recommendation method of an air conditioning device is characterized by comprising the following steps:
acquiring a user portrait of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, wherein the user portrait is generated according to the user portrait generation method of any one of claims 1 to 7;
calculating the adaptation degree of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics;
and when the adaptation degree is larger than or equal to a preset value, recommending the air conditioner to be evaluated to the user to be evaluated.
9. The recommendation method for air conditioning equipment according to claim 8, wherein the user image of the user to be evaluated comprises a character dimension and a control mode dimension, the character dimension is determined based on the air conditioning feature label preferred by the user to be evaluated, the control mode dimension is determined based on the control mode used by the user to be evaluated, and the attribute features comprise the air conditioning feature label and the supported control mode of the air conditioner to be evaluated.
10. The recommendation method of air conditioning equipment according to claim 8, wherein the calculating the degree of adaptation of the user to be evaluated to the air conditioner to be evaluated based on the user portrait and the attribute feature comprises:
obtaining a plurality of fitness calculation factors based on the user representation and the attribute features, wherein the user representation comprises a personality dimension and the fitness calculation factors comprise personality factors; and/or, the user representation includes a control manner dimension, and the fitness calculation factor includes a control manner factor; and/or, the user representation includes an activity dimension and the fitness calculation factor includes a control mode factor;
and acquiring the weight corresponding to each fitness calculation factor, and calculating the weighted sum of each fitness calculation factor, wherein the weighted sum is the fitness of the user to be evaluated and the air conditioner to be evaluated.
11. The recommendation method for an air conditioner as claimed in claim 10, wherein said fitness calculation factor includes said character factor, and said obtaining a plurality of fitness calculation factors based on said user representation and said attribute feature comprises:
acquiring an air conditioner feature label preferred by the user to be evaluated and a quantized value corresponding to a personality type of the user to be evaluated from the personality dimension, wherein the personality type comprises a conservative personality type, a common personality type and an attempted personality type;
determining an air conditioner characteristic label of the air conditioner to be evaluated from the attribute characteristics, and calculating a first proportion of the air conditioner characteristic label in the air conditioner characteristic label preferred by the user to be evaluated;
determining the character factor based on the first proportion, the quantization value corresponding to the character type of the user to be evaluated and a third preset formula, wherein the third preset formula is as follows:
Pc＝U*e-(1-b)，
wherein Pc is the character factor, U is a quantization value corresponding to the character type of the user to be evaluated, and b is the first ratio.
12. The recommendation method for an air conditioner according to claim 10, wherein said fitness calculation factor includes said control manner factor, and said obtaining a plurality of fitness calculation factors based on said user profile and said attribute feature comprises:
acquiring the control mode used by the user to be evaluated and the discrete degree of the use frequency of each control mode from the control mode dimension;
determining the control mode supported by the air conditioner to be evaluated from the attribute characteristics, and calculating a second proportion of the control mode supported by the air conditioner to be evaluated in the control mode used by the user to be evaluated;
determining the control mode factor based on the second proportion, the discrete degree and a fourth preset formula, wherein the fourth preset formula is as follows:
Pm＝s*e-(1-c)，
wherein Pm is the control mode factor, s is the discrete degree, and c is the second proportion.
13. A user representation generation system, comprising: air conditioners and servers; the air conditioner uploads the preset type of use log data to a server when the preset type of use log data is detected; and after receiving the preset type of use log data, the server generates a user portrait of the user according to the preset type of use log data, wherein the user portrait comprises at least one of a character dimension, an activity dimension and a control mode dimension.
14. A recommendation device of air conditioning equipment is characterized by comprising:
an acquisition unit, configured to acquire a user representation of a user to be evaluated and attribute characteristics of an air conditioner to be evaluated, where the user representation is generated according to the user representation generation method of any one of claims 1 to 7;
the processing unit is used for calculating the adaptation degree of the user to be evaluated and the air conditioner to be evaluated based on the user portrait and the attribute characteristics;
and the recommending unit is used for recommending the air conditioner to be evaluated to the user to be evaluated when the adaptation degree is greater than or equal to a preset value.
15. A recommendation terminal, characterized by comprising a computer-readable storage medium storing a computer program and a processor, the computer program being read and executed by the processor to implement the recommendation method of an air conditioning apparatus according to any one of claims 8 to 12.
16. A computer-readable storage medium, in which a computer program is stored, which, when read and executed by a processor, implements a user representation generation method as claimed in any one of claims 1 to 7.
17. A computer-readable storage medium, characterized in that it stores a computer program which, when read and executed by a processor, implements the recommendation method for an air conditioning apparatus according to any one of claims 8 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010717685.7A CN111932297A (en) | 2020-07-23 | 2020-07-23 | User portrait generation method and recommendation method of air conditioning equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010717685.7A CN111932297A (en) | 2020-07-23 | 2020-07-23 | User portrait generation method and recommendation method of air conditioning equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111932297A true CN111932297A (en) | 2020-11-13 |
Family
ID=73314436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010717685.7A Pending CN111932297A (en) | 2020-07-23 | 2020-07-23 | User portrait generation method and recommendation method of air conditioning equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932297A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112856737A (en) * | 2021-02-07 | 2021-05-28 | 青岛海尔空调器有限总公司 | Preheating control method of air conditioner |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679952A (en) * | 2017-09-30 | 2018-02-09 | 广东美的制冷设备有限公司 | Equipment recommendation method, apparatus and storage medium based on big data |
| CN108920160A (en) * | 2018-05-31 | 2018-11-30 | 深圳壹账通智能科技有限公司 | Upgrade method, device, server and the computer storage medium of application APP |
| CN109118330A (en) * | 2018-08-09 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of household electrical appliances recommended method, device, storage medium and server |
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
| CN110084705A (en) * | 2019-03-19 | 2019-08-02 | 阿里巴巴集团控股有限公司 | A kind of item recommendation method and device, a kind of electronic equipment and storage medium |
| CN111190939A (en) * | 2019-12-27 | 2020-05-22 | 深圳市优必选科技股份有限公司 | User portrait construction method and device |
-
2020
- 2020-07-23 CN CN202010717685.7A patent/CN111932297A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679952A (en) * | 2017-09-30 | 2018-02-09 | 广东美的制冷设备有限公司 | Equipment recommendation method, apparatus and storage medium based on big data |
| CN108920160A (en) * | 2018-05-31 | 2018-11-30 | 深圳壹账通智能科技有限公司 | Upgrade method, device, server and the computer storage medium of application APP |
| CN109118330A (en) * | 2018-08-09 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of household electrical appliances recommended method, device, storage medium and server |
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
| CN110084705A (en) * | 2019-03-19 | 2019-08-02 | 阿里巴巴集团控股有限公司 | A kind of item recommendation method and device, a kind of electronic equipment and storage medium |
| CN111190939A (en) * | 2019-12-27 | 2020-05-22 | 深圳市优必选科技股份有限公司 | User portrait construction method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112856737A (en) * | 2021-02-07 | 2021-05-28 | 青岛海尔空调器有限总公司 | Preheating control method of air conditioner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4524709B2 (en) | Information processing apparatus and method, and program | |
| CN110012060B (en) | Information pushing method and device of mobile terminal, storage medium and server | |
| CN111143697B (en) | Content recommendation method and related device | |
| CN110852772A (en) | Dynamic pricing method, system, device and storage medium | |
| CN109949089B (en) | Method, device and terminal for determining display rate | |
| CN114119111A (en) | Power transaction user management method, device, equipment and medium based on big data | |
| CN111932297A (en) | User portrait generation method and recommendation method of air conditioning equipment | |
| JP5408570B2 (en) | Attribute information update method and information update method | |
| von Rimscha | It’s not the economy, stupid! External effects on the supply and demand of cinema entertainment | |
| CN111512326A (en) | Energy plan communication control system and method based on load shape analysis | |
| Turgeman et al. | Unsupervised learning approach to estimating user engagement with mobile applications: A case study of The Weather Company (IBM) | |
| CN109684546A (en) | Recommended method, device, storage medium and terminal | |
| CN107577587A (en) | Integrate the generation method of form | |
| US20170364946A1 (en) | Determination device, determination method, and non-transitory computer readable storage medium | |
| CN111445280A (en) | Model generation method, restaurant ranking method, system, device and medium | |
| CN111311015A (en) | Personalized click rate prediction method, device and readable storage medium | |
| CN112118546A (en) | Message pushing method, message pushing device, computer equipment and medium | |
| CN108959324B (en) | Method and device for estimating multimedia display resource inventory and storage medium | |
| WO2017157130A1 (en) | Method and device for pushing value-added service information and electronic apparatus | |
| CA2779112A1 (en) | Application ratings based on performance metrics | |
| CN112269933A (en) | Potential customer identification method based on effective connection | |
| CN115357468B (en) | Software performance evaluation method, device, equipment and storage medium | |
| Zhang | The impact of China's accession to the WTO on its economy: an imperfect competitive CGE analysis | |
| CN117236801B (en) | Data processing method, device, electronic equipment and readable storage medium | |
| CN111382363B (en) | Audience extension method, device and equipment |
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 |