CN117666377B - Multi-mode data intelligent recommendation method and system based on Internet of things perception - Google Patents
Multi-mode data intelligent recommendation method and system based on Internet of things perception Download PDFInfo
- Publication number
- CN117666377B CN117666377B CN202410137355.9A CN202410137355A CN117666377B CN 117666377 B CN117666377 B CN 117666377B CN 202410137355 A CN202410137355 A CN 202410137355A CN 117666377 B CN117666377 B CN 117666377B
- Authority
- CN
- China
- Prior art keywords
- access
- index
- time
- interval
- equipment
- 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
- 230000008447 perception Effects 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 title claims description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 51
- 238000012502 risk assessment Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000005286 illumination Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000015556 catabolic process Effects 0.000 claims description 6
- 238000006731 degradation reaction Methods 0.000 claims description 6
- 230000014509 gene expression Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000012954 risk control Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009467 reduction Effects 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)
- Telephonic Communication Services (AREA)
Abstract
The application discloses a multi-mode data intelligent recommendation system based on internet of things perception, and relates to the technical field of intelligent recommendation; the system comprises: the system comprises a multimode sensing module, a server, an intelligent recommendation module and a privacy protection module; comprehensively analyzing according to the proper parameters of the user and the sensor information to obtain an environment update index, and accordingly extracting and updating the characteristic parameters of the household equipment to obtain the latest characteristic parameters of the household equipment; according to the characteristic parameter recommendation control mode, intelligent control which is closer to the requirements of users is realized, and unnecessary energy waste is reduced; by identifying the access terminal and extracting the characteristics of the historical access records to obtain corresponding access characteristic parameters and carrying out risk analysis and control on the access terminal, the abnormal access track can be identified, potential security threats can be found in time, and corresponding measures are taken to protect the privacy of the user.
Description
Technical Field
The application relates to the technical field of intelligent recommendation, in particular to an intelligent multi-mode data recommendation method and system based on internet of things perception.
Background
The multi-mode intelligent home recommendation system optimizes the home experience of a user by sensing various data acquired by different internet-of-things devices and sensors in the environment by utilizing the internet of things technology and an intelligent recommendation algorithm; by analyzing the multi-modal data, the system can know the behavior habit, preference and current environmental condition of the user, so as to intelligently recommend more proper living experience for the user; therefore, the multi-mode data intelligent recommendation is particularly important for realizing the intelligent home experience;
The current multi-mode data intelligent recommendation is extremely convenient and fast, so that a user is extremely wasted in the process of using the intelligent home, for example, the intelligent home is excessively active to automatically open and close equipment according to the habitual behavior of the user, and the actual demand is ignored, so that energy waste is caused; meanwhile, the identity of the visitor is directly identified at present when the intelligent recommendation is performed according to the preference of the visitor, and identity authentication of the visitor is absent, so that the risk of household privacy disclosure exists.
Disclosure of Invention
The application provides an intelligent multi-mode data recommendation method and system based on internet of things perception, which are used for solving the problems mentioned in the background art.
According to one aspect of the present application, there is provided an intelligent multi-modal data recommendation system based on internet of things sensing, the system comprising: the system comprises a multimode sensing module, a server, an intelligent recommendation module and a privacy protection module;
The intelligent recommendation module obtains characteristic parameters by carrying out characteristic extraction on the household equipment information, and recommends a control strategy according to the characteristic parameters; the method comprises the following steps:
Extracting characteristic parameters: any one of the household devices is fetched, the use times of the household device, the corresponding use start time and use end time of each use are fetched, the time difference value between the use start time and the use end time is calculated to obtain single use duration, and the use start time is taken as the use time of the single use duration; thereby obtaining the use time of a single use duration; sequencing the single use time according to the corresponding use time, and calculating the time difference value of the use time corresponding to the two adjacent single use time to obtain a use interval; carrying out refinement analysis on the single use duration and the use interval to obtain a demand index and a use index, and recording the demand index and the use index as characteristic parameters of household equipment;
the method comprises the steps of calling a demand index and a use index of household equipment, and comparing and analyzing the demand index and the use index with a set demand interval and a set use interval respectively to obtain a use type and a demand type, wherein the use type comprises primary use equipment, secondary use equipment and tertiary use equipment; the demand type comprises primary demand equipment, secondary demand equipment and tertiary demand equipment;
Classifying the household equipment which is marked as the first-level demand household equipment and the first-level use equipment into a full-automatic mode, classifying the household equipment which is marked as the third-level demand household equipment and the third-level use household equipment into a manual mode, and classifying other household equipment into a semi-automatic mode; and running the household equipment in a corresponding control mode according to the corresponding category.
Optionally, the step of extracting the characteristic parameters of the household equipment comprises the following steps:
Obtaining a usage track graph of the equipment by taking time as an abscissa and single usage duration as an ordinate; the point of use is taken as a curve tangent, the slope of the tangent is calculated and recorded as a use slope and is recorded as Kr, wherein r=1, 2,3 … … R, the value of R is a positive integer, R represents the total number of single use, and R is the number of any single use; summing the single-use slopes greater than zero to obtain a use increment score A1; summing the using slopes smaller than zero and taking absolute values to obtain a using degradation degree which is marked as A2;
numbering the using intervals according to the corresponding using time, and obtaining a using interval change line diagram of the equipment by taking the numbering as an abscissa and the using interval as an ordinate; calculating the slope of a line segment formed by two adjacent interval points as Summing the interval slopes greater than zero to obtain a frequency degradation degree which is marked as A3; summing the interval slopes smaller than zero to obtain a frequency increment score A4;
slope Kr will be used, interval slope The set formula group/>, is substituted by the increasing degree A1, the decreasing degree A2, the frequency decreasing degree A3 and the frequency increasing degree A4A calculation is performed to obtain a usage index Ak1 and a demand index Ak2, where a1, a2, a3, and a4 are set scaling coefficients, respectively.
Optionally, the system further comprises a server, a multimode sensing module and a privacy protection module;
the server comprehensively analyzes the proper parameters set by the user and the sensor information to obtain an environment update index, and when the environment update index is greater than a set threshold value, an acquisition instruction is generated and sent to the multimode sensing module; the multi-mode sensing module acquires household equipment information and sends the household equipment information to a server for storage when receiving an acquisition instruction;
the privacy protection module obtains access characteristic parameters by carrying out characteristic extraction on the access terminal logging in the intelligent home system, carries out risk analysis according to the access characteristic parameters to obtain risk indexes, and executes corresponding protection measures according to the risk indexes to finish safety authentication on the access terminal.
Optionally, the environment update index is obtained by comprehensively analyzing the suitable parameters set by the user and the sensor information, which is specifically:
Obtaining suitable parameters, wherein the suitable parameters comprise suitable temperature, suitable humidity and suitable illumination, and recording the suitable parameters as Y1, Y2 and Y3 respectively; acquiring temperature, humidity and illumination intensity at different acquisition moments, respectively marking the temperature, humidity and illumination intensity as P1, P2 and P3, and utilizing a set formula Calculating to obtain an environment update index YP, wherein y1, y2 and y3 are respectively set proportionality coefficients; and when the environment update index is larger than the set update threshold, sending an acquisition instruction to the multi-mode sensing module.
Optionally, the access characteristic parameter extraction process is as follows:
Calculating the time difference between the access starting time and the access ending time to obtain single access duration, and taking the access starting time of the access as the access time of the access, thereby obtaining the single access duration and the access time of each access; taking time as an abscissa and access time as an ordinate to obtain a graph of the change of the access time along with time; tangent lines of the curve are made at the position of the access point, tangent line expressions are obtained through data fitting, derivative operation is conducted on the tangent line data expressions to obtain derivative Dj of the access point, wherein j=1, 2,3 … … J, the value of J is a positive integer, J represents the total number of access times, and J is any access time; summing the derivatives larger than zero to obtain a single increment degree of the duration and marking the single increment degree as Z1, summing the derivatives smaller than zero to obtain an absolute value and marking the single decrement degree of the duration as Z2; substituting the derivative Dj, the duration single increment Z1 and the duration single decrement Z2 of the access point into a set formula Performing calculation to obtain access index DZ, wherein d1, d2 and d3 are respectively set proportionality coefficients,/>The derivative mean value corresponding to all access points is obtained;
Dividing each day into a plurality of time periods based on the day; comparing the access time period with each time period to be matched with the corresponding time period, and accumulating each access into the corresponding time period according to the access time; any one time period is taken, the accumulated access times and the corresponding access time length in the time period are obtained, and the access time length corresponding to each accumulated access time is summed up and calculated to obtain the accumulated access time length in the time period; substituting the accumulated access times F1 and the accumulated access time length F2 into a set formula Ft=f1×F1+f2×F2 to calculate so as to obtain an accumulated habit index Ft in the time period, wherein F1 and F2 are respectively set proportionality coefficients, and thus the accumulated habit index of each access terminal in each time period can be obtained;
Comparing and analyzing the access time length with a set time length threshold value to obtain an abnormal access time length, sequencing the abnormal access time length according to the corresponding access time to obtain an abnormal access track, and calculating the time difference value of the access time corresponding to the two adjacent abnormal access time lengths to obtain an abnormal access interval; numbering the abnormal access intervals according to the corresponding access time sequence, taking the numbers as the abscissa, taking the abnormal access intervals as the ordinate, calculating the slope of a line segment formed by two adjacent abnormal points, carrying out summation calculation on the slope larger than zero to obtain an abnormal increment degree which is marked as H1, and carrying out summation calculation on the slope smaller than zero to obtain an abnormal decrement degree which is marked as H2; substituting the abnormal increment degree H1 and the abnormal decrement degree H2 into a set formula Calculating to obtain an abnormal access index Hz, wherein h1 and h2 are set proportionality coefficients respectively; and recording the access index, the accumulated habit index of each time period and the abnormal access index as access characteristic parameters, thereby obtaining the access characteristic parameters of each access terminal.
Optionally, the specific steps of risk analysis are:
When the access terminal enters the intelligent home network, the access terminal is identified, the corresponding access characteristic parameters are called, and the login behavior of the access terminal entering the intelligent home is obtained; comparing the login time with each time period to obtain a corresponding accumulated habit index; selecting the largest accumulated habit index in each time period and marking the accumulated habit index as a high-frequency index;
Setting a corresponding safety coefficient for each login address, comparing the login address with all the set login addresses to match the corresponding safety coefficient, and obtaining the distance between the login address and the intelligent home network as a separation distance; substituting the cumulative habit index Ft, the abnormal access index Hz, the safety coefficient gamma 1, the interval distance gamma 2 and the high frequency index Ftmax into a set formula:
Calculating to obtain a risk index FH of the access terminal accessed at the time, wherein b1, b2, b3 and b4 are respectively set proportionality coefficients; comparing and analyzing the risk index with a set risk interval, and controlling the user terminal to enter a locking state when the risk index is larger than the maximum value in the set risk interval; when the risk index is within the set risk interval, the user side is controlled to enter a local limiting mode; and when the risk index is smaller than the minimum value in the set risk interval, controlling the user side to enter an unlimited module.
According to the application. In another aspect, a multi-mode data intelligent recommendation method based on internet of things perception is provided, which comprises the following steps:
S1: comprehensively analyzing sensor information and proper parameters set by a user to obtain an environment update index, and sending an acquisition instruction to the multi-mode sensing module when the environment update index is greater than a set threshold value;
s2: the multimode sensing module is in communication connection with each household device, and when receiving the acquisition instruction, acquires household device information and sends the household device information to the server for storage;
S3: extracting features by calling the household information to obtain feature parameters of household equipment, and performing personalized analysis according to the feature parameters to generate an intelligent household recommendation strategy;
s4: the risk index is obtained by carrying out risk analysis on the access terminal, safety authentication is carried out according to the risk index, and corresponding protection measures are executed to realize privacy and safety guarantee of the user.
Compared with the prior art, the invention has the beneficial effects that:
(1) Comprehensively analyzing according to the proper parameters of the user and the sensor information to obtain an environment update index, and accordingly extracting and updating the characteristic parameters of the household equipment to obtain the latest characteristic parameters of the household equipment; the requirements and the usability of the household equipment are compared and analyzed according to the characteristic parameters to obtain a requirement index and a use index, and a control mode (a full-automatic mode, a semi-automatic mode and a manual mode) is recommended according to the requirement index and the use index, so that intelligent control which is more close to the requirements of users is realized, and unnecessary energy waste is reduced;
(2) By identifying the access terminal and extracting the characteristics of the historical access records to obtain corresponding access characteristic parameters and carrying out risk analysis and control on the access terminal, the abnormal access track can be identified, potential security threats can be found in time, and corresponding measures are taken to protect the privacy of the user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a general block diagram of a system of the present invention;
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application 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 application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party.
As shown in fig. 1, according to an embodiment of the present application, there is provided an intelligent multi-modal data recommendation system based on internet of things perception, the system comprising: the intelligent recommendation system comprises a multimode sensing module, a server, an intelligent recommendation module and a privacy protection module;
The server stores proper parameters, wherein the proper parameters comprise proper temperature, proper humidity and proper illumination, and the proper parameters are respectively marked as Y1, Y2 and Y3; wherein the proper parameters are set by the user according to the preference of the user; the server is in communication connection with the environment sensor to obtain the temperature, humidity and illumination intensity at different acquisition moments, and respectively marks the temperature, humidity and illumination intensity as P1, P2 and P3, and a set formula is utilized Calculating to obtain an environment update index YP, wherein y1, y2 and y3 are respectively set proportionality coefficients; as can be seen from the formula, the closer the sensor information is to the appropriate parameters, the smaller the environment update index is; comparing and analyzing the environment update index with a set update threshold, and when the environment update index is larger than the set update threshold, indicating that the environment parameter is larger than the proper parameter of the user, re-extracting the characteristics of the use requirement of the household equipment of the user, analyzing the characteristics to obtain the requirement state and the use state of each household equipment, and sending an acquisition instruction to the multi-mode sensing module;
The multi-mode sensing module is in communication connection with each household device, and when an acquisition instruction is received, the household information server is acquired and stored;
The intelligent recommendation module performs characteristic extraction by calling the household information to obtain characteristic parameters of household equipment, performs personalized analysis according to the characteristic parameters to generate an intelligent household recommendation strategy so as to realize the intellectualization of the household equipment, and reduces energy waste while being closer to the needs of users; the method comprises the following steps:
Retrieving furniture equipment information and sensor information, wherein the household equipment information comprises equipment types, equipment positions and use records; the sensor information comprises temperature, humidity and illumination intensity, and the sensor information refers to the temperature, humidity and illumination intensity of the external environment;
Extracting characteristic parameters: any one of the household devices is fetched, the use times of the household device, the corresponding use start time and use end time of each use are fetched, the time difference value between the use start time and the use end time is calculated to obtain single use duration, and the use start time is taken as the use time of the single use duration; thereby obtaining the use time of a single use duration;
Constructing a two-dimensional rectangular coordinate system by taking time as an abscissa and taking single use time as an ordinate, inputting the single use time into the coordinate system according to corresponding use time, marking the position of the single use time in the coordinate system as a use point, and sequentially connecting the use points by adopting a smooth curve to obtain a use track graph of the equipment; the point of use is taken as a curve tangent, the slope of the tangent is calculated and recorded as a use slope and is recorded as Kr, wherein r=1, 2,3 … … R, the value of R is a positive integer, R represents the total number of single use, and R is the number of any single use; summing the single-use slopes greater than zero to obtain a use increment score A1; summing the using slopes smaller than zero and taking absolute values to obtain a using degradation degree which is marked as A2;
Sequencing the single use time according to the corresponding use time, and calculating the time difference value of the use time corresponding to the two adjacent single use time to obtain a use interval; sequentially numbering the using intervals according to the corresponding using time, constructing a two-dimensional rectangular coordinate system by taking the numbers as abscissa and taking the using intervals as ordinate, marking the positions of the using intervals in the coordinate system as interval points, and sequentially connecting the interval points to obtain a using interval change line diagram of the equipment; calculating the slope of a line segment formed by two adjacent interval points as Note that, the use point r+1, the use point r, and the use point r-1 constitute two adjacent interval points (r+1, r) and (r, r-1), and therefore the slope of the line segment formed by the two adjacent interval points is denoted as interval slope/>; Summing the interval slopes greater than zero to obtain a frequency degradation degree which is marked as A3; summing the interval slopes smaller than zero to obtain a frequency increment score A4;
slope Kr will be used, interval slope The usage increment A1, the usage decrement A2, the frequency decrement A3 and the frequency increment A4 are determined by a set formula group/>Calculating to obtain a use index Ak1 and a demand index Ak2, wherein a1, a2, a3 and a4 are set proportionality coefficients respectively; the formula shows that when the using time is more stable and the using times are more stable, the demand index is larger, so that the equipment belongs to household equipment with large household use demands; when the using time length is longer, the interval time length is shorter, the using index is longer, and the household equipment is indicated to belong to the household equipment with larger household using frequency; the demand index and the use index of each household device can be obtained, and the demand index and the use index are recorded as characteristic parameters of the household device;
optimizing intelligent home recommendation strategies: the method comprises the steps of calling a demand index and a use index of household equipment, and comparing and analyzing the demand index and the use index with a set demand interval and a set use interval: when the demand index is larger than the maximum value in the set demand interval, the household equipment is marked as first-level demand household equipment; when the demand index is within the set demand interval, the household equipment is marked as a secondary demand equipment household; when the demand index is smaller than the minimum value in the set demand interval, marking the household equipment as three-level demand household equipment;
When the use index is larger than the maximum value in the set use interval, the household equipment is marked as first-level use equipment; when the use index is within the set interval, the device is marked as secondary use device; when the usage index is smaller than the minimum value in the set usage interval, the device is marked as three-level usage device;
Classifying the household equipment which is marked as the first-level demand household equipment and the first-level use equipment into a full-automatic mode, classifying the household equipment which is marked as the third-level demand household equipment and the third-level use household equipment into a manual mode, and classifying other household equipment into a semi-automatic mode; the household equipment is subjected to corresponding control modes according to the corresponding categories, so that the intelligent household equipment can save energy sources;
It should be noted that the full-automatic mode means that the control of the home device is automatically performed by the intelligent system, and no user intervention is required, so as to meet the user's requirement and improve the energy utilization efficiency. For example, when a certain home device is marked as a primary demand and primary usage device, the intelligent system can automatically optimize its operating parameters to ensure that the device is operating in an optimal state; the semi-automatic mode is a control mode between a full-automatic mode and a manual mode, in the semi-automatic mode, the intelligent system can provide some suggestions or default settings according to the characteristic parameters of the equipment and the preference of a user, and the user can determine the working state and the operation mode of the equipment according to the recommendation of the intelligent system or the judgment of the user; the semi-automatic mode can flexibly meet the requirements of different users and save energy to a certain extent; the manual mode refers to that a user selects different equipment working modes according to actual needs, such as starting, closing or adjusting working parameters of equipment;
Comprehensively analyzing according to the proper parameters of the user and the sensor information to obtain an environment update index, and accordingly extracting and updating the characteristic parameters of the household equipment to obtain the latest characteristic parameters of the household equipment; the requirements and the usability of the household equipment are compared and analyzed according to the characteristic parameters to obtain the requirement index and the use index, and the control modes (a full-automatic mode, a semi-automatic mode and a manual mode) are recommended according to the requirement index and the use index, so that the intelligent household equipment can be realized, and meanwhile, unnecessary energy waste can be reduced to the greatest extent.
The privacy protection module obtains a risk index by performing risk analysis on the access terminal, performs security authentication according to the risk index and executes corresponding protection measures to realize privacy and security guarantee of a user; the method comprises the following steps:
Analyzing the historical access records to extract access characteristic parameters: access records of all access terminals stored in the server are called, wherein the access records comprise access times, login behaviors corresponding to each access, access starting time, access ending time and operation behaviors; it should be noted that, a plurality of access terminals exist in the same intelligent home system, and each access terminal corresponds to one family member;
Calculating the time difference between the access starting time and the access ending time to obtain single access duration, and taking the access starting time of the access as the access time of the access, thereby obtaining the single access duration and the access time of each access; constructing a two-dimensional rectangular coordinate system by taking time as an abscissa and taking access time as an ordinate, inputting the access time into the coordinate system according to the access time of each access, marking the position of the access time in the coordinate system as an access point, and sequentially connecting the access points by adopting a smooth curve to obtain a graph of the change of the access time along with the time; tangent lines of the curve are made at the position of the access point, tangent line expressions are obtained through data fitting, derivative operation is conducted on the tangent line data expressions to obtain derivative marks of the access point as Dj, wherein j=1, 2,3 … … J, the value of J is a positive integer, J represents total access times, and J is any access; summing the derivatives larger than zero to obtain a single increment degree of the duration and marking the single increment degree as Z1, summing the derivatives smaller than zero to obtain an absolute value and marking the single decrement degree of the duration as Z2; using a set formula Performing calculation to obtain access index DZ, wherein d1, d2 and d3 are respectively set proportionality coefficients,/>The derivative mean value corresponding to all access points is obtained; as can be seen from the formula, when the access of the access terminal shows an increasing trend, the access index is larger;
Dividing each day into a plurality of time periods based on the day; comparing the access time period with each time period to match the access time period to the corresponding time period, and accumulating one access in one time period when the access time belongs to one time period; accumulating each access to a corresponding time period according to the access time; taking any one of the time periods, obtaining the accumulated access times in the time period as F1 and the corresponding access time length, summing the access time length corresponding to each accumulated access time to obtain the accumulated access time length in the time period as F2, and calculating by using a set formula Ft=f1×F1+f2×F2 to obtain an accumulated habit index Ft in the time period, wherein F1 and F2 are respectively set proportionality coefficients; thus, the accumulated habit index of each access terminal in each time period can be obtained;
Comparing and analyzing the access time length with a set time length threshold, when the access time length is larger than the set time length threshold, indicating that the access abnormality risk of the access terminal is larger at the time, marking the access time length as an abnormal access time length, thereby obtaining all abnormal access time lengths of the access user terminal, sequencing the abnormal access time lengths according to the corresponding access time to obtain an abnormal access track, and calculating time difference values of access time corresponding to the two adjacent abnormal access time lengths to obtain an abnormal access interval; numbering the abnormal access intervals according to the corresponding access time sequence, constructing a two-dimensional rectangular coordinate system by taking the numbers as abscissa and taking the abnormal access intervals as ordinate, inputting the abnormal access intervals into the coordinate system according to corresponding division numbers, marking the positions of the abnormal access intervals in the coordinate system as abnormal points, sequentially connecting the abnormal points to obtain an abnormal access interval change line graph, calculating the slope of a line segment formed by two adjacent abnormal points, carrying out summation calculation on the slope larger than zero to obtain an abnormal increment degree marked as H1, and carrying out summation calculation on the slope smaller than zero to obtain an abnormal reduction degree marked as H2; using a set formula Calculating to obtain an abnormal access index Hz, wherein h1 and h2 are set proportionality coefficients respectively;
Recording the access index, the accumulated habit index of each time period and the abnormal access index as access characteristic parameters, thereby obtaining the access characteristic parameters of each access terminal;
When the access terminal enters the intelligent home network, the access terminal is identified, the corresponding access characteristic parameters are called, and the login behavior of the access terminal entering the intelligent home is obtained; the login behavior comprises login times, login time and login addresses, wherein the login times refer to the times of attempting to login by using login credentials when the access terminal logs in to enter the intelligent home network; comparing the login time with each time period to obtain a corresponding accumulated habit index; selecting the largest accumulated habit index in each time period and marking the accumulated habit index as a high-frequency index Ftmax;
Setting a corresponding safety coefficient for each login address, comparing the login address with all the set login addresses to match the corresponding safety coefficient, and marking the safety coefficient as gamma 1; it should be noted that, the more the number of times of use, the larger the corresponding security coefficient of the login address, and the smaller the corresponding security coefficient of the new login address which does not appear before; acquiring the distance between the login address and the intelligent home network and recording the distance as a separation distance gamma 2; it should be noted that, the larger the distance between the login address and the location of the smart home network is, the greater the risk of unauthorized access or off-site login is; using a set formula Calculating to obtain a risk index of the access terminal, wherein b1, b2, b3 and b4 are respectively set proportionality coefficients; comparing and analyzing the risk index with a set risk interval, and controlling the user side to enter a locking state when the risk index is larger than the maximum value in the set risk interval, which indicates that the user side has larger safety risk in the access; when the risk index is within the set risk interval, the user side is controlled to enter a local limiting mode; when the risk index is smaller than the minimum value in the set risk interval, the user side is controlled to enter an unlimited module;
The locking mode refers to locking the access terminal, and cannot adjust equipment parameters of the intelligent home (including opening and closing of intelligent home equipment) and check data in the server; the local limiting module is a household device which does not allow the access terminal to view the authority of the data in the service and allows the access terminal to adjust the security level to three levels; the household equipment is classified into primary safety equipment, secondary safety equipment and tertiary safety equipment according to the safety level; the primary safety equipment is mainly equipment with higher safety level, such as intelligent door locks, intelligent monitoring and the like; the three-level safety equipment is furniture equipment with lower safety level, such as intelligent sockets, intelligent curtains and the like;
By identifying the access terminal and extracting the characteristics of the historical access records to obtain corresponding access characteristic parameters and carrying out risk analysis and control on the access terminal, the abnormal access track can be identified, potential security threats can be found in time, and corresponding measures are taken to protect the privacy of the user.
As shown in fig. 2, according to an embodiment of the present application, there is provided an intelligent multi-modal data recommendation method based on internet of things sensing, the method including:
S1: the server stores various data generated by the home system, including but not limited to equipment use data, user preference data, safety monitoring data and the like, and comprehensively analyzes sensor information and proper parameters set by a user to obtain an environment update index, and when the environment update index is greater than a set threshold value, an acquisition instruction is sent to the multi-mode sensing module;
s2: the multimode sensing module is in communication connection with each household device, and when receiving the acquisition instruction, acquires household device information and sends the household device information to the server for storage;
S3: the intelligent recommendation module performs characteristic extraction by calling the household information to obtain characteristic parameters of household equipment, and performs personalized analysis according to the characteristic parameters to generate an intelligent household recommendation strategy;
s4: the privacy protection module obtains a risk index by performing risk analysis on the access terminal, performs security authentication according to the risk index, and executes corresponding protection measures to realize privacy and security guarantee of a user.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (6)
1. The utility model provides a multimode data intelligent recommendation system based on thing perception which characterized in that includes: an intelligent recommendation module;
The intelligent recommendation module performs feature extraction on the household equipment information to obtain feature parameters, and recommends a control strategy according to the feature parameters; the method comprises the following steps:
Extracting characteristic parameters: any one of the household devices is fetched, the use times of the household device, the corresponding use start time and use end time of each use are fetched, the time difference value between the use start time and the use end time is calculated to obtain single use duration, and the use start time is taken as the use time of the single use duration; thereby obtaining the use time of a single use duration; sequencing the single use time according to the corresponding use time, and calculating the time difference value of the use time corresponding to the two adjacent single use time to obtain a use interval; carrying out refinement analysis on the single use duration and the use interval to obtain a demand index and a use index, and recording the demand index and the use index as characteristic parameters of household equipment;
the method comprises the steps of calling a demand index and a use index of household equipment, and comparing and analyzing the demand index and the use index with a set demand interval and a set use interval respectively to obtain a use type and a demand type, wherein the use type comprises primary use equipment, secondary use equipment and tertiary use equipment; the demand type comprises primary demand equipment, secondary demand equipment and tertiary demand equipment;
Classifying the household equipment which is marked as the first-level demand household equipment and the first-level use equipment into a full-automatic mode, classifying the household equipment which is marked as the third-level demand household equipment and the third-level use household equipment into a manual mode, and classifying other household equipment into a semi-automatic mode; the household equipment is operated in a corresponding control mode according to the corresponding category;
the characteristic parameters of the household equipment are extracted by the following steps:
Obtaining a usage track graph of the equipment by taking time as an abscissa and single usage duration as an ordinate; the point of use is taken as a curve tangent, the slope of the tangent is calculated and recorded as a use slope and is recorded as Kr, wherein r=1, 2,3 … … R, the value of R is a positive integer, R represents the total number of single use, and R is the number of any single use; summing the single-use slopes greater than zero to obtain a use increment score A1; summing the using slopes smaller than zero and taking absolute values to obtain a using degradation degree which is marked as A2;
numbering the using intervals according to the corresponding using time, and obtaining a using interval change line diagram of the equipment by taking the numbering as an abscissa and the using interval as an ordinate; calculating the slope of a line segment formed by two adjacent interval points as Summing the interval slopes greater than zero to obtain a frequency degradation degree which is marked as A3; summing the interval slopes smaller than zero to obtain a frequency increment score A4;
slope Kr will be used, interval slope The set formula group/>, is substituted by the increasing degree A1, the decreasing degree A2, the frequency decreasing degree A3 and the frequency increasing degree A4And calculating to obtain a use index Ak1 and a demand index AK2, wherein a1, a2, a3 and a4 are respectively set proportionality coefficients, and the use index and the demand index are recorded as characteristic parameters of the household equipment.
2. The intelligent multi-mode data recommendation system based on the internet of things perception according to claim 1, further comprising a server, a multi-mode perception module and a privacy protection module;
The server comprehensively analyzes the proper parameters set by the user and the sensor information to obtain an environment update index, and when the environment update index is greater than a set threshold value, an acquisition instruction is generated and sent to the multimode sensing module;
When the multimode sensing module receives the acquisition instruction, acquiring household equipment information and sending the household equipment information to a server for storage;
The privacy protection module performs feature extraction on the visiting end logging in the intelligent home system to obtain access feature parameters, performs risk analysis according to the access feature parameters to obtain risk indexes, and performs corresponding protection measures according to the risk indexes to complete safety authentication on the visiting end.
3. The intelligent multi-mode data recommendation system based on the internet of things perception according to claim 2, wherein the environment update index is obtained by comprehensively analyzing the suitable parameters set by the user and the sensor information, specifically:
Obtaining suitable parameters, wherein the suitable parameters comprise suitable temperature, suitable humidity and suitable illumination, and recording the suitable parameters as Y1, Y2 and Y3 respectively; acquiring temperature, humidity and illumination intensity at different acquisition moments, respectively marking the temperature, humidity and illumination intensity as P1, P2 and P3, and utilizing a set formula Calculating to obtain an environment update index YP, wherein y1, y2 and y3 are respectively set proportionality coefficients; and when the environment update index is larger than the set update threshold, sending an acquisition instruction to the multi-mode sensing module.
4. The intelligent multi-mode data recommendation system based on the internet of things perception according to claim 2, wherein the access characteristic parameter extraction process is as follows:
Calculating the time difference between the access starting time and the access ending time to obtain single access duration, and taking the access starting time of the access as the access time of the access, thereby obtaining the single access duration and the access time of each access; taking time as an abscissa and access time as an ordinate to obtain a graph of the change of the access time along with time; tangent lines of the curve are made at the position of the access point, a tangent line expression is obtained through data fitting, and derivative operation is conducted on the tangent line data expression to obtain the derivative of the access point; summing the derivatives larger than zero to obtain a single increment of the time length, summing the derivatives smaller than zero to obtain an absolute value to obtain a single decrement of the time length; carrying out formulated calculation analysis on the derivative, the time length single increment and the time length single decrement of the access point to obtain an access index;
Dividing each day into a plurality of time periods based on the day; comparing the access time period with each time period to be matched with the corresponding time period, and accumulating each access into the corresponding time period according to the access time; any one time period is taken, the accumulated access times and the corresponding access time length in the time period are obtained, and the access time length corresponding to each accumulated access time is summed up and calculated to obtain the accumulated access time length in the time period; performing numerical analysis on the accumulated access times and the accumulated access time to obtain accumulated habit indexes in the time period, thereby obtaining the accumulated habit indexes of each access terminal in each time period;
Comparing and analyzing the access time length with a set time length threshold value to obtain an abnormal access time length, sequencing the abnormal access time length according to the corresponding access time to obtain an abnormal access track, and calculating the time difference value of the access time corresponding to the two adjacent abnormal access time lengths to obtain an abnormal access interval; numbering the abnormal access intervals according to the corresponding access time sequence, taking the numbers as the abscissa, taking the abnormal access intervals as the ordinate, calculating the slope of a line segment formed by two adjacent abnormal points, carrying out summation calculation on the slope larger than zero to obtain abnormal increment, and carrying out summation calculation on the slope smaller than zero to obtain abnormal decrement; carrying out numerical analysis on the abnormal increment degree and the abnormal decrement degree to obtain an abnormal access index; and recording the access index, the accumulated habit index of each time period and the abnormal access index as access characteristic parameters, thereby obtaining the access characteristic parameters of each access terminal.
5. The intelligent multi-modal data recommendation system based on internet of things perception according to claim 4, wherein the specific steps of risk analysis are as follows:
When the access terminal enters the intelligent home network, the access terminal is identified, the corresponding access characteristic parameters are called, and the login behavior of the access terminal entering the intelligent home is obtained; comparing the login time with each time period to obtain a corresponding accumulated habit index; selecting the largest accumulated habit index in each time period as a high-frequency index;
Setting a corresponding safety coefficient for each login address, comparing the login address with all the set login addresses to match the corresponding safety coefficient, and obtaining the distance between the login address and the intelligent home network as a separation distance; carrying out formula calculation analysis on the accumulated habit index, the abnormal access index, the safety coefficient, the interval distance and the high-frequency index to obtain a risk index of the access terminal accessed at the time; comparing and analyzing the risk index with a set risk interval, and controlling the access terminal to enter a locking state when the risk index is larger than the maximum value in the set risk interval; when the risk index is within the set risk interval, the access terminal is controlled to enter a local limiting mode; and when the risk index is smaller than the minimum value in the set risk interval, controlling the access terminal to enter an unrestricted mode.
6. The intelligent multi-mode data recommending method based on the internet of things perception is characterized by being applied to the intelligent multi-mode data recommending system based on the internet of things perception as set forth in any one of claims 1 to 5, and comprises the following steps:
S1: comprehensively analyzing sensor information and proper parameters set by a user to obtain an environment update index, and sending an acquisition instruction to the multi-mode sensing module when the environment update index is greater than a set threshold value;
s2: the multimode sensing module is in communication connection with each household device, and when receiving the acquisition instruction, acquires household device information and sends the household device information to the server for storage;
S3: extracting features by calling the household information to obtain feature parameters of household equipment, and performing personalized analysis according to the feature parameters to generate an intelligent household recommendation strategy;
s4: the risk index is obtained by carrying out risk analysis on the access terminal, safety authentication is carried out according to the risk index, and corresponding protection measures are executed to realize privacy and safety guarantee of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410137355.9A CN117666377B (en) | 2024-02-01 | 2024-02-01 | Multi-mode data intelligent recommendation method and system based on Internet of things perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410137355.9A CN117666377B (en) | 2024-02-01 | 2024-02-01 | Multi-mode data intelligent recommendation method and system based on Internet of things perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117666377A CN117666377A (en) | 2024-03-08 |
| CN117666377B true CN117666377B (en) | 2024-04-23 |
Family
ID=90086638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410137355.9A Active CN117666377B (en) | 2024-02-01 | 2024-02-01 | Multi-mode data intelligent recommendation method and system based on Internet of things perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117666377B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005282219A (en) * | 2004-03-30 | 2005-10-13 | Mitsubishi Motors Corp | Operating device control unit |
| CN104166396A (en) * | 2014-08-27 | 2014-11-26 | 深圳创维－Rgb电子有限公司 | Intelligent home control method and system |
| WO2017008322A1 (en) * | 2015-07-10 | 2017-01-19 | 西安交通大学 | Smart home energy management method based on social networking behavior detection |
| CN109062076A (en) * | 2018-10-19 | 2018-12-21 | 杭州虹晟信息科技有限公司 | Intelligent home control system based on Internet of Things |
| CN113268661A (en) * | 2021-04-28 | 2021-08-17 | 青岛海尔科技有限公司 | Method and device for recommending user functions and intelligent household appliance |
| 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 |
| CN115933421A (en) * | 2022-11-30 | 2023-04-07 | 珠海格力电器股份有限公司 | Energy-saving control method and device for electrical equipment and electrical equipment |
| CN116540556A (en) * | 2023-03-30 | 2023-08-04 | 海尔优家智能科技（北京）有限公司 | Equipment control method and device based on user habit |
| CN116679577A (en) * | 2023-07-03 | 2023-09-01 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent family sensing and control terminal |
| CN117235797A (en) * | 2023-09-28 | 2023-12-15 | 广州工程技术职业学院 | Intelligent management method, device, equipment and system for big data resource access |
| CN117348434A (en) * | 2023-11-16 | 2024-01-05 | 佛山市康利家具有限公司 | Intelligent home management system based on user living habit |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016155021A1 (en) * | 2015-04-03 | 2016-10-06 | 绿仕科技控股有限公司 | Environmental control system |
| CN110456647B (en) * | 2019-07-02 | 2020-11-27 | 珠海格力电器股份有限公司 | Intelligent household control method and intelligent household control device |
-
2024
- 2024-02-01 CN CN202410137355.9A patent/CN117666377B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005282219A (en) * | 2004-03-30 | 2005-10-13 | Mitsubishi Motors Corp | Operating device control unit |
| CN104166396A (en) * | 2014-08-27 | 2014-11-26 | 深圳创维－Rgb电子有限公司 | Intelligent home control method and system |
| WO2017008322A1 (en) * | 2015-07-10 | 2017-01-19 | 西安交通大学 | Smart home energy management method based on social networking behavior detection |
| CN109062076A (en) * | 2018-10-19 | 2018-12-21 | 杭州虹晟信息科技有限公司 | Intelligent home control system based on Internet of Things |
| CN113268661A (en) * | 2021-04-28 | 2021-08-17 | 青岛海尔科技有限公司 | Method and device for recommending user functions and intelligent household appliance |
| 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 |
| CN115933421A (en) * | 2022-11-30 | 2023-04-07 | 珠海格力电器股份有限公司 | Energy-saving control method and device for electrical equipment and electrical equipment |
| CN116540556A (en) * | 2023-03-30 | 2023-08-04 | 海尔优家智能科技（北京）有限公司 | Equipment control method and device based on user habit |
| CN116679577A (en) * | 2023-07-03 | 2023-09-01 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent family sensing and control terminal |
| CN117235797A (en) * | 2023-09-28 | 2023-12-15 | 广州工程技术职业学院 | Intelligent management method, device, equipment and system for big data resource access |
| CN117348434A (en) * | 2023-11-16 | 2024-01-05 | 佛山市康利家具有限公司 | Intelligent home management system based on user living habit |
Non-Patent Citations (1)
| Title |
|---|
| 基于嵌入式系统的用户行为识别方法研究;吕志;翟超;;工业控制计算机;20190525(第05期);67-69 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117666377A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101408754B (en) | Intelligent house optimizing system based on data excavation | |
| CN105607508A (en) | Smart home device control method and system based on user behavior analysis | |
| Meliou et al. | Nonmyopic informative path planning in spatio-temporal models | |
| CN105068513B (en) | Wired home energy management method based on social networks behavior perception | |
| US20160266181A1 (en) | Electric power demand prediction system, electric power demand prediction method, consumer profiling system, and consumer profiling method | |
| CN106022664A (en) | Big data analysis based network intelligent power saving monitoring method | |
| CN110991477A (en) | Method and system for identifying users in abnormal industry and abnormal electricity utilization behaviors of power system | |
| CN109460644A (en) | A kind of determination method and apparatus of user right | |
| CN117666377B (en) | Multi-mode data intelligent recommendation method and system based on Internet of things perception | |
| US20140088945A1 (en) | System and method for an energy management system | |
| CN108475257A (en) | It handles far distance instrument and reads data to analyze consumption pattern | |
| CN105324761A (en) | Energy management system | |
| CN113988723A (en) | User behavior locking method and system based on power consumption data anomaly analysis | |
| CN107422703A (en) | A kind of apparatus control method and device | |
| CN111340104B (en) | Method and device for generating control rules of intelligent equipment, electronic equipment and readable storage medium | |
| CN102682290A (en) | Respective type biological feature identifying method and system | |
| CN112769234A (en) | Intelligent sensing system and method for power load | |
| US20170160892A1 (en) | Individual customization system and method | |
| CN114355784A (en) | Pushing method and device for use suggestion, smart home system and storage medium | |
| CN111242308B (en) | Energy-saving strategy recommendation method, device, computer equipment and storage medium | |
| CN110889465B (en) | Power demand side equipment identification method and system based on self-adaptive resonant network | |
| CN111103805A (en) | Method, system and device for controlling household appliance and household appliance | |
| CN107958289B (en) | Data processing method and device for robot and robot | |
| CN109271590B (en) | Recommendation method based on time sequence decision model | |
| CN105700371A (en) | Method and apparatus for controlling switch |
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 |