CN117216505B - User habit prediction method and system based on smart home use record - Google Patents
User habit prediction method and system based on smart home use record Download PDFInfo
- Publication number
- CN117216505B CN117216505B CN202311482454.2A CN202311482454A CN117216505B CN 117216505 B CN117216505 B CN 117216505B CN 202311482454 A CN202311482454 A CN 202311482454A CN 117216505 B CN117216505 B CN 117216505B
- Authority
- CN
- China
- Prior art keywords
- prediction
- user
- parameter
- parameters
- fault
- 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 34
- 238000012549 training Methods 0.000 claims abstract description 74
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a user habit prediction method and a system based on intelligent home use records, wherein the method comprises the following steps: acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment; training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical use operation records and the use parameters; acquiring equipment use parameters corresponding to the equipment use request of the target user; and predicting recommended use operation of the target user based on the habit prediction algorithm model according to the target user parameters of the target user and the equipment use parameters. Therefore, the intelligent home service system and the intelligent home service method can provide more intelligent and humanized intelligent home service for the user, reduce misoperation of the user and improve user experience.
Description
Technical Field
The invention relates to the technical field of data prediction, in particular to a user habit prediction method and system based on intelligent home use records.
Background
The development of intelligent household equipment and the improvement of information technology enable the intelligent household equipment to have more powerful processors and information processing capacity and also start to provide more intelligent services for users.
However, when the service is provided, the model training and the subsequent prediction of the operation of the user by using the usage record stored in the processor are not considered in the prior art, so as to improve the service effect, and therefore, it is obvious that the intelligent degree of the service of the intelligent home equipment realized by the prior art is not high enough. It can be seen that the prior art has defects and needs to be solved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide the user habit prediction method and the system based on the intelligent home use record, which can provide more intelligent and humanized intelligent home service for users, reduce the misoperation of the users and improve the user experience.
In order to solve the technical problems, the first aspect of the invention discloses a user habit prediction method based on intelligent home use records, which comprises the following steps:
acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment;
training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical use operation records and the use parameters;
acquiring equipment use parameters corresponding to the equipment use request of the target user;
and predicting recommended use operation of the target user based on the habit prediction algorithm model according to the target user parameters of the target user and the equipment use parameters.
As an optional implementation manner, in the first aspect of the present invention, the usage parameter or the device usage parameter includes at least one of a usage time, a usage scenario, and a usage location; and/or the user parameter or the target user parameter comprises at least one of a user physiological parameter, a user identity parameter and a user history usage record.
As an optional implementation manner, in the first aspect of the present invention, the training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical usage operation record and usage parameters includes:
for any user, the user parameters of the user are formed into training user parameter data;
the normal operation record and the use parameters of the user, which are not subjected to equipment errors after operation, in the historical use operation record are composed into positive prediction sample data;
forming negative prediction sample data by using a fault operation record and a use parameter of equipment errors after operation in the historical use operation record of the user;
and inputting the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user into a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data and predict the fault possibility of the use operation according to the use parameter.
As an optional implementation manner, in the first aspect of the present invention, the habit prediction algorithm model includes an operation prediction model and a fault prediction model; the training is performed according to the training user parameter data and the positive prediction sample data and the negative prediction sample data corresponding to each user, and the training is performed until convergence, so that the habit prediction algorithm model can predict corresponding usage operation according to the training user parameter data, and predict failure possibility of the usage operation according to the usage parameter, including:
inputting the training user parameter data and the positive prediction sample data or the negative prediction sample data corresponding to each user into an operation prediction model for training until convergence, so that the operation prediction model can predict corresponding use operation according to the training user parameter data;
and inputting the positive prediction sample data or the negative prediction sample data into a fault prediction model for training until convergence, so that the fault prediction model can predict the fault possibility of the using operation according to the using operation and the using parameters.
As an optional implementation manner, in the first aspect of the present invention, the predicting, based on the habit prediction algorithm model, the recommended usage operation of the target user according to the target user parameter of the target user and the device usage parameter includes:
inputting target user parameters of the target user into the operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
and screening out recommended use operation of the target user from the plurality of prediction operations according to the equipment use parameters and the fault prediction model.
As an optional implementation manner, in the first aspect of the present invention, the selecting, according to the device usage parameter and the failure prediction model, a recommended usage operation of the target user from the plurality of prediction operations includes:
inputting the equipment use parameters and any one of the prediction operations into the fault prediction model to obtain operation fault possibility corresponding to any one of the prediction operations;
determining a historical use parameter set corresponding to any prediction operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of the operation fault possibility and the parameter difference degree corresponding to any one of the prediction operations to obtain an operation matching degree parameter corresponding to the prediction operation;
and determining the predicted operation with the lowest operation matching degree parameter as the recommended operation of the target user.
As an alternative embodiment, in the first aspect of the present invention, the method further includes:
acquiring real-time use operation input by the target user;
judging whether the real-time use operation is the recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing the real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is the prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameter into the fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
The second aspect of the invention discloses a user habit prediction system based on intelligent home use records, which comprises the following steps:
the first acquisition module is used for acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment;
the training module is used for training to obtain a habit prediction algorithm model according to the user parameters of the user and the history use operation records and the use parameters;
the second acquisition module is used for acquiring equipment use parameters corresponding to the equipment use request of the target user;
and the prediction module is used for predicting recommended use operation of the target user based on the habit prediction algorithm model according to the target user parameters of the target user and the equipment use parameters.
As an optional implementation manner, in the second aspect of the present invention, the usage parameter or the device usage parameter includes at least one of a usage time, a usage scenario, and a usage location; and/or the user parameter or the target user parameter comprises at least one of a user physiological parameter, a user identity parameter and a user history usage record.
In a second aspect of the present invention, as an optional implementation manner, the training module trains a specific manner of obtaining a habit prediction algorithm model according to the user parameters of the user and the historical usage operation record and usage parameters, where the specific manner includes:
for any user, the user parameters of the user are formed into training user parameter data;
the normal operation record and the use parameters of the user, which are not subjected to equipment errors after operation, in the historical use operation record are composed into positive prediction sample data;
forming negative prediction sample data by using a fault operation record and a use parameter of equipment errors after operation in the historical use operation record of the user;
and inputting the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user into a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data and predict the fault possibility of the use operation according to the use parameter.
As an alternative embodiment, in the second aspect of the present invention, the habit prediction algorithm model includes an operation prediction model and a fault prediction model; the training module inputs the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user to a preset habit prediction algorithm model to train until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data, and predicts a fault possibility of the use operation according to the use parameter, and the specific mode comprises the following steps:
inputting the training user parameter data and the positive prediction sample data or the negative prediction sample data corresponding to each user into an operation prediction model for training until convergence, so that the operation prediction model can predict corresponding use operation according to the training user parameter data;
and inputting the positive prediction sample data or the negative prediction sample data into a fault prediction model for training until convergence, so that the fault prediction model can predict the fault possibility of the using operation according to the using operation and the using parameters.
As an optional implementation manner, in the second aspect of the present invention, the predicting module predicts, based on the habit prediction algorithm model, a specific manner of recommending usage operation of the target user according to the target user parameter of the target user and the device usage parameter, including:
inputting target user parameters of the target user into the operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
and screening out recommended use operation of the target user from the plurality of prediction operations according to the equipment use parameters and the fault prediction model.
As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module screens out the recommended usage operation of the target user from the plurality of prediction operations according to the device usage parameter and the fault prediction model includes:
inputting the equipment use parameters and any one of the prediction operations into the fault prediction model to obtain operation fault possibility corresponding to any one of the prediction operations;
determining a historical use parameter set corresponding to any prediction operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of the operation fault possibility and the parameter difference degree corresponding to any one of the prediction operations to obtain an operation matching degree parameter corresponding to the prediction operation;
and determining the predicted operation with the lowest operation matching degree parameter as the recommended operation of the target user.
As an alternative embodiment, in the second aspect of the present invention, the apparatus further performs the following operations:
acquiring real-time use operation input by the target user;
judging whether the real-time use operation is the recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing the real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is the prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameter into the fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
The third aspect of the invention discloses another user habit prediction system based on intelligent home use records, which comprises the following steps:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to execute some or all of the steps in the smart home usage record-based user habit prediction method disclosed in the first aspect of the present invention.
A fourth aspect of the present invention discloses a computer storage medium storing computer instructions for performing part or all of the steps of the smart home usage record-based user habit prediction method disclosed in the first aspect of the present invention when the computer instructions are invoked.
Compared with the prior art, the invention has the following beneficial effects:
according to the method and the system for predicting the habit of the user, the habit prediction model of the user can be trained according to the history of the user, and the predicted use operation of the user is predicted according to the use request of the user, so that more intelligent and humanized intelligent home service can be provided for the user, misoperation of the user is reduced, and user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a user habit prediction method based on smart home usage records according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a user habit prediction system based on smart home usage records according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of another user habit prediction system based on smart home usage records according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a user habit prediction method and a system based on intelligent home use records, which can train a habit prediction model of a user according to the user history records and predict the predicted use operation of the user according to the use request of the user, so that more intelligent and humanized intelligent home service can be provided for the user, misoperation of the user is reduced, and user experience is improved. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of a user habit prediction method based on smart home usage records according to an embodiment of the present invention. The method described in fig. 1 may be applied to a corresponding data processing device, a data processing terminal, and a data processing server, where the server may be a local server or a cloud server, and the embodiment of the present invention is not limited to the method shown in fig. 1, and the method for predicting user habit based on smart home usage records may include the following operations:
101. and acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment.
102. And training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical use operation records and the use parameters.
103. And acquiring the equipment use parameters corresponding to the equipment use request of the target user.
104. And predicting recommended use operation of the target user based on the habit prediction algorithm model according to the target user parameters and the equipment use parameters of the target user.
Optionally, the usage parameter or the device usage parameter includes at least one of a usage time, a usage scenario, and a usage location.
Optionally, the user parameter or target user parameter comprises at least one of a user physiological parameter, a user identity parameter and a user history usage record.
Optionally, the recommended use operation may be displayed to the target user for selection, or the target user may be prompted by voice to remind, or part of the operation pre-data of the recommended use operation may be preloaded to the smart home device to improve the execution efficiency of the operation.
Therefore, the method described by the embodiment of the invention can train the habit prediction model of the user according to the history of the user, and predict the predicted use operation of the user according to the use request of the user, thereby providing more intelligent and humanized intelligent home service for the user, reducing the misoperation of the user and improving the user experience.
As an alternative embodiment, in the step, training to obtain the habit prediction algorithm model according to the user parameters of the user and the historical usage operation records and the usage parameters includes:
for any user, the user parameters of the user are formed into training user parameter data;
the normal operation record and the use parameters of the user, which are not subjected to equipment errors after operation in the historical use operation record, are formed into positive prediction sample data;
forming negative prediction sample data by using a fault operation record and a use parameter of equipment errors after operation in the historical use operation record of the user;
and inputting the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user into a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data and predict the fault possibility of the use operation according to the use parameter.
Optionally, the prediction algorithm model in the invention can be a neural network prediction model of a CNN structure, an RNN structure or an LTSM structure, and an operator can select or test according to actual scenes or data characteristics, and the invention is not limited.
Through the embodiment, the training user parameter data, the positive prediction sample data and the negative prediction sample data can be collected and cleaned, corresponding use operation can be predicted according to the training user parameter data, and the habit prediction algorithm model for predicting the failure possibility of the use operation according to the use parameter can be trained, so that more intelligent and humanized intelligent home service can be provided for users, misoperation of the users can be reduced, and user experience can be improved.
As an alternative embodiment, the habit prediction algorithm model includes an operation prediction model and a fault prediction model; in the above steps, according to the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user, the training is performed until convergence, so that the habit prediction algorithm model can predict the corresponding usage operation according to the training user parameter data, and predict the failure probability of the usage operation according to the usage parameter, including:
inputting training user parameter data and positive prediction sample data or negative prediction sample data corresponding to each user into the operation prediction model for training until convergence, so that the operation prediction model can predict corresponding use operation according to the training user parameter data;
and inputting the positive prediction sample data or the negative prediction sample data into a fault prediction model for training until convergence, so that the fault prediction model can predict the fault possibility of the using operation according to the using operation and the using parameters.
Through the embodiment, the operation prediction model and the fault prediction model can be trained, so that the two models can predict corresponding use operations according to the trained user parameter data and predict the habit prediction algorithm model of the fault possibility of the use operations according to the use parameters, thereby facilitating the follow-up provision of more intelligent and humanized intelligent home services to users, reducing the misoperation of the users and improving the user experience.
As an alternative embodiment, in the step, predicting the recommended usage operation of the target user based on the habit prediction algorithm model according to the target user parameter and the device usage parameter of the target user, includes:
inputting target user parameters of a target user into an operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
and screening recommended use operation of the target user from a plurality of prediction operations according to the equipment use parameters and the fault prediction model.
Through the embodiment, the recommended use operation of the target user can be screened from a plurality of prediction operations based on the operation prediction model and the fault prediction model according to the target user parameters and the equipment use parameters of the target user, so that more intelligent and humanized intelligent home service can be provided for the user, misoperation of the user is reduced, and user experience is improved.
As an alternative embodiment, in the step, according to the device usage parameter and the fault prediction model, the selecting the recommended usage operation of the target user from the plurality of prediction operations includes:
inputting the equipment use parameters and any prediction operation into a fault prediction model to obtain operation fault possibility corresponding to any prediction operation;
determining a historical use parameter set corresponding to any predicted operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of operation fault possibility and parameter difference degree corresponding to any prediction operation to obtain an operation matching degree parameter corresponding to the prediction operation;
and determining the prediction operation with the lowest operation matching degree parameter as the recommended use operation of the target user.
Through the embodiment, the operation matching degree parameters corresponding to each prediction operation can be calculated according to the calculated operation fault possibility and the parameter difference degree, so that the recommended operation of the target user is screened out from a plurality of prediction operations, intelligent home service which is more intelligent and humanized is provided for the user, the operation faults of the user are reduced, and the user experience is improved.
As an alternative embodiment, the method further comprises:
acquiring real-time use operation input by a target user;
judging whether the real-time use operation is a recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is a prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameters into a fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
Through the embodiment, under the condition that the user does not select the recommended operation, the fault possibility of the real-time operation of the user can be redetermined to determine whether to execute the operation, so that the supervision of the operation safety can be further improved, more intelligent and humanized intelligent home service is provided for the user, the operation accidents of the user are reduced, and the user experience is improved.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a user habit prediction system based on smart home usage records according to an embodiment of the present invention. The system described in fig. 2 may be applied to a corresponding data processing device, a data processing terminal, and a data processing server, where the server may be a local server or a cloud server, and embodiments of the present invention are not limited. As shown in fig. 2, the system may include:
a first obtaining module 201, configured to obtain a plurality of historical usage operation records and corresponding usage parameters of a plurality of users for a same smart home device;
the training module 202 is configured to train to obtain a habit prediction algorithm model according to user parameters of the user and historical usage operation records and usage parameters;
a second obtaining module 203, configured to obtain a device usage parameter corresponding to a device usage request of a target user;
and the prediction module 204 is used for predicting the recommended use operation of the target user based on the habit prediction algorithm model according to the target user parameters and the equipment use parameters of the target user.
As an alternative embodiment, the usage parameter or device usage parameter includes at least one of a usage time, a usage scenario, and a usage location; and/or the user parameter or target user parameter comprises at least one of a user physiological parameter, a user identity parameter, and a user historical usage record.
As an alternative embodiment, the training module 202 trains a specific mode of obtaining a habit prediction algorithm model according to user parameters of the user and historical usage operation records and usage parameters, and the specific mode comprises the following steps:
for any user, the user parameters of the user are formed into training user parameter data;
the normal operation record and the use parameters of the user, which are not subjected to equipment errors after operation in the historical use operation record, are formed into positive prediction sample data;
forming negative prediction sample data by using a fault operation record and a use parameter of equipment errors after operation in the historical use operation record of the user;
and inputting the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user into a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data and predict the fault possibility of the use operation according to the use parameter.
As an alternative embodiment, the habit prediction algorithm model includes an operation prediction model and a fault prediction model; the training module 202 inputs training user parameter data, positive prediction sample data and negative prediction sample data corresponding to each user to a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding usage operation according to the training user parameter data, and predicts a fault possibility of the usage operation according to the usage parameter, and the specific mode comprises:
inputting training user parameter data and positive prediction sample data or negative prediction sample data corresponding to each user into the operation prediction model for training until convergence, so that the operation prediction model can predict corresponding use operation according to the training user parameter data;
and inputting the positive prediction sample data or the negative prediction sample data into a fault prediction model for training until convergence, so that the fault prediction model can predict the fault possibility of the using operation according to the using operation and the using parameters.
As an alternative embodiment, the prediction module 204 predicts, based on the habit prediction algorithm model, a specific manner of recommending usage operation for the target user according to the target user parameter and the device usage parameter of the target user, including:
inputting target user parameters of a target user into an operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
and screening recommended use operation of the target user from a plurality of prediction operations according to the equipment use parameters and the fault prediction model.
As an alternative embodiment, the prediction module 204 screens the specific manner of recommending the use operation of the target user from the plurality of prediction operations according to the device use parameter and the fault prediction model, including:
inputting the equipment use parameters and any prediction operation into a fault prediction model to obtain operation fault possibility corresponding to any prediction operation;
determining a historical use parameter set corresponding to any predicted operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of operation fault possibility and parameter difference degree corresponding to any prediction operation to obtain an operation matching degree parameter corresponding to the prediction operation;
and determining the prediction operation with the lowest operation matching degree parameter as the recommended use operation of the target user.
As an alternative embodiment, the apparatus further performs the following operations:
acquiring real-time use operation input by a target user;
judging whether the real-time use operation is a recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is a prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameters into a fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
The details and technical effects of the modules in the embodiment of the present invention may refer to the description in the first embodiment, and are not described herein.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of another user habit prediction system based on smart home usage records according to an embodiment of the present invention. As shown in fig. 3, the system may include:
a memory 301 storing executable program code;
a processor 302 coupled with the memory 301;
the processor 302 invokes the executable program code stored in the memory 301 to perform some or all of the steps in the smart home usage record-based user habit prediction method disclosed in the embodiment of the present invention.
Example IV
The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing part or all of the steps in the user habit prediction method based on the intelligent home use record disclosed in the embodiment of the invention when the computer instructions are called.
The system embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a user habit prediction method and system based on smart home use records, which are disclosed by the embodiment of the invention only for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (7)
1. A user habit prediction method based on smart home usage records, the method comprising:
acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment;
training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical use operation records and the use parameters; the habit prediction algorithm model comprises an operation prediction model and a fault prediction model;
acquiring equipment use parameters corresponding to the equipment use request of the target user;
inputting target user parameters of the target user into the operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
inputting the equipment use parameters and any one of the prediction operations into the fault prediction model to obtain operation fault possibility corresponding to any one of the prediction operations;
determining a historical use parameter set corresponding to any prediction operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of the operation fault possibility and the parameter difference degree corresponding to any one of the prediction operations to obtain an operation matching degree parameter corresponding to the prediction operation;
determining the prediction operation with the lowest operation matching degree parameter as the recommended use operation of the target user;
acquiring real-time use operation input by the target user;
judging whether the real-time use operation is the recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing the real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is the prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameter into the fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
2. The smart home usage record-based user habit prediction method of claim 1, wherein the usage parameter or the device usage parameter includes at least one of a usage time, a usage scenario, and a usage location; and/or the user parameter or the target user parameter comprises at least one of a user physiological parameter, a user identity parameter and a user history usage record.
3. The smart home usage record-based user habit prediction method according to claim 2, wherein training to obtain a habit prediction algorithm model according to the user parameters of the user and the historical usage operation record and usage parameters comprises:
for any user, the user parameters of the user are formed into training user parameter data;
the normal operation record and the use parameters of the user, which are not subjected to equipment errors after operation, in the historical use operation record are composed into positive prediction sample data;
forming negative prediction sample data by using a fault operation record and a use parameter of equipment errors after operation in the historical use operation record of the user;
and inputting the training user parameter data, the positive prediction sample data and the negative prediction sample data corresponding to each user into a preset habit prediction algorithm model for training until convergence, so that the habit prediction algorithm model can predict corresponding use operation according to the training user parameter data and predict the fault possibility of the use operation according to the use parameter.
4. A smart home usage record-based user habit prediction method as defined in claim 3, wherein the training is performed by inputting the training user parameter data and the positive prediction sample data and the negative prediction sample data corresponding to each user to a preset habit prediction algorithm model until convergence, so that the habit prediction algorithm model can predict corresponding usage operations according to the training user parameter data, and predict failure probability of the usage operations according to the usage parameters, comprising:
inputting the training user parameter data and the positive prediction sample data or the negative prediction sample data corresponding to each user into an operation prediction model for training until convergence, so that the operation prediction model can predict corresponding use operation according to the training user parameter data;
and inputting the positive prediction sample data or the negative prediction sample data into a fault prediction model for training until convergence, so that the fault prediction model can predict the fault possibility of the using operation according to the using operation and the using parameters.
5. A user habit prediction system based on smart home usage records, the system comprising:
the first acquisition module is used for acquiring a plurality of historical use operation records and corresponding use parameters of a plurality of users aiming at the same intelligent household equipment;
the training module is used for training to obtain a habit prediction algorithm model according to the user parameters of the user and the history use operation records and the use parameters; the habit prediction algorithm model comprises an operation prediction model and a fault prediction model;
the second acquisition module is used for acquiring equipment use parameters corresponding to the equipment use request of the target user;
the prediction module is configured to predict a recommended usage operation of the target user based on the habit prediction algorithm model according to the target user parameter of the target user and the equipment usage parameter, and specifically includes:
inputting target user parameters of the target user into the operation prediction model to obtain a plurality of prediction operations corresponding to the target user;
inputting the equipment use parameters and any one of the prediction operations into the fault prediction model to obtain operation fault possibility corresponding to any one of the prediction operations;
determining a historical use parameter set corresponding to any prediction operation from the historical use operation record;
calculating the parameter difference degree between the equipment use parameter and the historical use parameter set corresponding to any prediction operation; the parameter difference degree is a vector distance parameter;
calculating a weighted sum average value of the operation fault possibility and the parameter difference degree corresponding to any one of the prediction operations to obtain an operation matching degree parameter corresponding to the prediction operation;
determining the prediction operation with the lowest operation matching degree parameter as the recommended use operation of the target user;
the system also performs the following operations:
acquiring real-time use operation input by the target user;
judging whether the real-time use operation is the recommended use operation or not, and obtaining a first judgment result;
if the first judgment result is yes, executing the real-time use operation;
if the first judgment result is negative, judging whether the real-time use operation is the prediction operation or not, and obtaining a second judgment result;
if the second judgment result is yes, determining the operation fault possibility corresponding to the real-time use operation as the operation fault possibility of the corresponding prediction operation;
if the second judgment result is negative, inputting the real-time use operation and the equipment use parameter into the fault prediction model to obtain the operation fault possibility corresponding to the real-time use operation;
and calculating a difference value between the operation fault probability corresponding to the real-time use operation and the operation fault probability of the recommended use operation, judging whether the difference value is smaller than a preset difference value threshold, if so, executing the real-time use operation, and if not, refusing to execute the real-time use operation.
6. A user habit prediction system based on smart home usage records, the system comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the smart home usage record-based user habit prediction method of any one of claims 1-4.
7. A computer storage medium storing computer instructions which, when invoked, are operable to perform the smart home usage record-based user habit prediction method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482454.2A CN117216505B (en) | 2023-11-09 | 2023-11-09 | User habit prediction method and system based on smart home use record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482454.2A CN117216505B (en) | 2023-11-09 | 2023-11-09 | User habit prediction method and system based on smart home use record |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117216505A CN117216505A (en) | 2023-12-12 |
| CN117216505B true CN117216505B (en) | 2024-03-19 |
Family
ID=89051527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311482454.2A Active CN117216505B (en) | 2023-11-09 | 2023-11-09 | User habit prediction method and system based on smart home use record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216505B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707783A (en) * | 2016-12-30 | 2017-05-24 | 中科同德（北京）生态科技有限公司 | KNX bus control method and system for recording user behavior habits |
| CN109471370A (en) * | 2018-11-23 | 2019-03-15 | 珠海格力电器股份有限公司 | Behavior prediction and control method and system based on exhaust fan operation data |
| CN109947029A (en) * | 2019-04-10 | 2019-06-28 | 广东工业大学 | Control method, device and the equipment of smart home device |
| CN111552549A (en) * | 2020-04-26 | 2020-08-18 | 北京四达时代软件技术股份有限公司 | Multitask request dynamic configuration method and system for intelligent equipment |
| WO2022041988A1 (en) * | 2020-08-28 | 2022-03-03 | 青岛海尔空调器有限总公司 | Smart control method and smart control device for air conditioner |
| CN114265320A (en) * | 2021-12-03 | 2022-04-01 | 珠海格力电器股份有限公司 | Smart home control method and system for analyzing user habits based on deep learning |
| CN114265325A (en) * | 2021-12-23 | 2022-04-01 | 深圳康佳电子科技有限公司 | Self-learning intelligent household control method, terminal and computer readable storage medium |
| CN115731684A (en) * | 2022-10-21 | 2023-03-03 | 广州视声智能股份有限公司 | Control method and device of wireless key switch equipment |
| CN115826553A (en) * | 2022-10-31 | 2023-03-21 | 海尔优家智能科技（北京）有限公司 | Fault removing method and electronic device |
| WO2023055047A1 (en) * | 2021-09-29 | 2023-04-06 | Samsung Electronics Co., Ltd. | Prediction model training method, information prediction method and corresponding device |
| CN116226655A (en) * | 2022-12-05 | 2023-06-06 | 广州视声智能股份有限公司 | Smart home environment sensing method and device, storage medium and electronic equipment |
| CN116910707A (en) * | 2023-09-12 | 2023-10-20 | 深圳市智能派科技有限公司 | Model copyright management method and system based on equipment history record |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11120349B1 (en) * | 2018-03-06 | 2021-09-14 | Intuit, Inc. | Method and system for smart detection of business hot spots |
-
2023
- 2023-11-09 CN CN202311482454.2A patent/CN117216505B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707783A (en) * | 2016-12-30 | 2017-05-24 | 中科同德（北京）生态科技有限公司 | KNX bus control method and system for recording user behavior habits |
| CN109471370A (en) * | 2018-11-23 | 2019-03-15 | 珠海格力电器股份有限公司 | Behavior prediction and control method and system based on exhaust fan operation data |
| CN109947029A (en) * | 2019-04-10 | 2019-06-28 | 广东工业大学 | Control method, device and the equipment of smart home device |
| CN111552549A (en) * | 2020-04-26 | 2020-08-18 | 北京四达时代软件技术股份有限公司 | Multitask request dynamic configuration method and system for intelligent equipment |
| WO2022041988A1 (en) * | 2020-08-28 | 2022-03-03 | 青岛海尔空调器有限总公司 | Smart control method and smart control device for air conditioner |
| WO2023055047A1 (en) * | 2021-09-29 | 2023-04-06 | Samsung Electronics Co., Ltd. | Prediction model training method, information prediction method and corresponding device |
| CN114265320A (en) * | 2021-12-03 | 2022-04-01 | 珠海格力电器股份有限公司 | Smart home control method and system for analyzing user habits based on deep learning |
| CN114265325A (en) * | 2021-12-23 | 2022-04-01 | 深圳康佳电子科技有限公司 | Self-learning intelligent household control method, terminal and computer readable storage medium |
| CN115731684A (en) * | 2022-10-21 | 2023-03-03 | 广州视声智能股份有限公司 | Control method and device of wireless key switch equipment |
| CN115826553A (en) * | 2022-10-31 | 2023-03-21 | 海尔优家智能科技（北京）有限公司 | Fault removing method and electronic device |
| CN116226655A (en) * | 2022-12-05 | 2023-06-06 | 广州视声智能股份有限公司 | Smart home environment sensing method and device, storage medium and electronic equipment |
| CN116910707A (en) * | 2023-09-12 | 2023-10-20 | 深圳市智能派科技有限公司 | Model copyright management method and system based on equipment history record |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117216505A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378487A (en) | Laterally model parameter verification method, device, equipment and medium in federal study | |
| CN117632905B (en) | Database management method and system based on cloud use records | |
| CN117235873B (en) | Smart home layout method and system based on historical work record | |
| CN117170873B (en) | Resource pool management method and system based on artificial intelligence | |
| CN111262750B (en) | Method and system for evaluating baseline model | |
| CN116910274B (en) | Test question generation method and system based on knowledge graph and prediction model | |
| CN116910707B (en) | Model copyright management method and system based on equipment history record | |
| CN116777677B (en) | Project data processing method and system based on project starting stage target setting | |
| CN116304250A (en) | Intelligent rule engine management method and system based on visual operation | |
| CN111194027A (en) | Network connection method, device and system | |
| CN117216505B (en) | User habit prediction method and system based on smart home use record | |
| CN114143734B (en) | Data processing method and device for 5G internet of things card flow acquisition | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| CN114997879B (en) | Payment routing method, device, equipment and storage medium | |
| CN117201502B (en) | Intelligent cloud server access method and system based on artificial intelligence | |
| CN114462494A (en) | Intelligent lock fault prediction method, system, electronic device and readable medium | |
| CN116318386A (en) | Failure prediction method of optical module, system and storage medium thereof | |
| CN116976677B (en) | Business risk processing method and device based on artificial intelligence and computer storage medium | |
| CN112070294A (en) | Transaction data processing method and device, computer equipment and storage medium | |
| CN113793162A (en) | Logistics data processing method and device, storage medium and equipment | |
| CN117955765B (en) | KNX-based household equipment configuration method and system | |
| CN117523638B (en) | Face recognition method and system based on priority screening | |
| CN116843203B (en) | Service access processing method, device, equipment, medium and product | |
| CN117615359B (en) | Bluetooth data transmission method and system based on multiple rule engines | |
| CN117492394A (en) | Water volume abnormity monitoring method and device based on water inlet and outlet device |
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 |