CN112801154B - Behavior analysis method and system for orphan elderly people - Google Patents
Behavior analysis method and system for orphan elderly people Download PDFInfo
- Publication number
- CN112801154B CN112801154B CN202110067644.2A CN202110067644A CN112801154B CN 112801154 B CN112801154 B CN 112801154B CN 202110067644 A CN202110067644 A CN 202110067644A CN 112801154 B CN112801154 B CN 112801154B
- Authority
- CN
- China
- Prior art keywords
- behavior
- orphan
- current
- household appliance
- current moment
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 claims abstract description 23
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000006399 behavior Effects 0.000 claims description 161
- 230000009471 action Effects 0.000 claims description 37
- 230000005611 electricity Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 21
- 230000003542 behavioural effect Effects 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000010411 cooking Methods 0.000 description 29
- 238000007726 management method Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 210000003771 C cell Anatomy 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000010354 integration 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
- 238000000611 regression analysis Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 208000014001 urinary system disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to a behavior analysis method and a system for orphan elderly people, wherein the method comprises the following steps: collecting household appliance use information of the orphan old at the current moment and environment variable characteristic information at the current moment; inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan old people; acquiring a history behavior of the corresponding history moment according to the environment variable characteristic information of the current moment; comparing the current behavior with the historical behavior, and judging the current behavior to be abnormal behavior if the current behavior is dissimilar. The method can solve the problem of low timeliness of the traditional behavior analysis method for the behavior analysis of the orphan aged, can timely process and feed back the abnormal behavior of the orphan aged, is convenient for better caring the orphan aged, can greatly promote the solution of the problem of the orphan aged in social treatment, and lightens the social burden.
Description
Technical Field
The application relates to the field of user behavior analysis, in particular to a behavior analysis method and system for orphan elderly people.
Background
In China, home care is always a traditional care mode, however, china enters an aging society, the trend of nuclear families is obvious, the traditional home care is simply and can not be heavy, and the old, minority, lost business, unmarried and urban are brought into the group of solitary old people. At present, due to the lack of funds and insufficient investment, a part of public welfare care institutions are in embarrassing places in terms of hardware facilities, service quality and management level, and how to care the old people is well, so that the important problems in social management, such as forgetting to turn off a stove fire, tap, forgetting to take medicine, chronic diseases and fraud, are prevented when the old people are singly living in the home.
Of course, in the prior art, a traditional behavior analysis method is adopted to analyze the behavior actions of the user and send out alarm information when the behavior is abnormal, but the traditional behavior analysis method adopts manual statistics or some specific monitoring equipment such as cameras to perform data acquisition and manual analysis, so that the behavior actions of the user are finally obtained, if the traditional behavior analysis method is used for monitoring the orphan, the data acquisition amount is too large, the labor cost is too high, and the timeliness is low, so that the alarm information is difficult to send out in time when the behavior of the orphan is abnormal, and the safety problem of the solitary old at home cannot be really solved.
Disclosure of Invention
The embodiment of the application provides a behavior analysis method and a behavior analysis system for an orphan elderly, which can analyze behavior actions of the orphan elderly based on electricity consumption data and timely discover safety problems of the orphan elderly in the solitary time.
In a first aspect, an embodiment of the present application provides a behavior analysis method for orphan elderly people, the method including: collecting household appliance use information of the orphan old at the current moment and environment variable characteristic information at the current moment; inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan aged, wherein the behavior analysis model is obtained by training the household appliance use information at the historical moment, the environment variable characteristic information and the corresponding historical behavior; acquiring a history behavior of the corresponding history moment according to the environment variable characteristic information of the current moment; comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, judging the behavior of the orphan old people as abnormal behavior.
In a second aspect, an embodiment of the present application provides a behavioral analysis system for orphan elderly people, where the system includes: the collection equipment is used for collecting household appliance use information at the current moment and environment variable characteristics at the current moment, which are generated in the process of using the household appliances by the orphan old people; the internet of things platform is used for acquiring and storing household appliance use information at the current moment and environment variable characteristic information at the current moment; the intelligent middle platform is used for training a behavior analysis model, pre-judging the current behavior of the orphan old people, and comparing the similarity; and the service platform is used for notifying the current behavior to the user terminal.
In a third aspect, an embodiment of the present application provides a behavior analysis device for orphan elderly people, where the device includes: the acquisition unit is used for acquiring household appliance use information at the current moment of the orphan old people and environment variable characteristic information at the current moment; the input unit is used for inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan old people, wherein the behavior analysis model is obtained by training the household appliance use information at the historical moment, the environment variable characteristic information and the corresponding historical behavior; the acquisition unit is used for acquiring the corresponding historical behaviors of the historical moment according to the environmental variable characteristic information of the current moment; and the comparison unit is used for comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, the behavior of the orphan aged is judged to be abnormal.
In a fourth aspect, the present application proposes an electronic device comprising a memory, in which a computer program is stored, and a processor arranged to run the computer program to perform a method of behavioral analysis of orphan elderly people as in the first aspect described above.
In a fifth aspect, the present application proposes a storage medium having stored therein a computer program, wherein the computer program is arranged to perform the behavior analysis method of orphan elderly people as described in the first aspect at run-time.
Compared with the traditional behavior analysis method which adopts manual statistics or some specific monitoring equipment such as cameras to carry out data acquisition and manual analysis and finally obtains the behavior actions of the orphan aged, the method can solve the problem of low timeliness of the traditional behavior analysis method on the behavior analysis of the orphan aged, can timely process and feed back the abnormal behaviors of the orphan aged, is convenient for better caring the orphan aged, can greatly promote the solution of the problem of the orphan aged in social management, and lightens the social burden.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
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 application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of a behavioral analysis method for orphan elderly people according to an embodiment of the present application
FIG. 2 is a model diagram of a behavioral analysis system for orphan elderly people according to an embodiment of the present application;
fig. 3 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with aspects of one or more embodiments of the present description as detailed in the accompanying claims.
It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. Furthermore, individual steps described in this specification, in other embodiments, may be described as being split into multiple steps; while various steps described in this specification may be combined into a single step in other embodiments.
Example 1
Referring to fig. 1, a behavior analysis method for orphan aged people in a first embodiment of the present invention is shown, and the method includes steps S101 to S105:
s101, acquiring household appliance use information of the orphan old people at the current moment and environment variable characteristic information at the current moment;
s102, inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan aged, wherein the behavior analysis model is obtained by training the household appliance use information at the historical moment, the environment variable characteristic information and the corresponding historical behavior;
s103, acquiring a history behavior of the corresponding history moment according to the environment variable characteristic information of the current moment;
s104, comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, judging the behavior of the orphan old people as abnormal behavior;
and S105, if the current behavior is similar to the historical behavior, judging that the behavior of the orphaned old people is normal, and updating a training behavior analysis model according to the household appliance use information at the current moment, the environment variable characteristic information at the current moment and the current behavior.
In this embodiment, by collecting historical electricity consumption data of the orphan aged as a training sample, the historical electricity consumption data includes household appliance usage information and environment variable characteristic information at a historical moment, wherein the environment variable characteristic information is used for analyzing behavior habits of people with different areas and different electricity consumption habits, a behavior habit knowledge base corresponding to the area/the specific aged is established, the behavior habit knowledge base is utilized to calculate the real-time household appliance usage information of the orphan aged, and whether the current behavior of the orphan aged is abnormal behavior is judged. The historical behaviors are obtained from the behavior habit knowledge base. The abnormal state refers to the fact that the electricity consumption behavior of the orphan aged is quite different from the habit behavior of the orphan aged. If the frequency of switching on and off the lamp becomes very high, and the condition that the behavior of the old is very different from that of the old is reflected by searching for related things by using the lamp frequently, the old is judged to be abnormal.
In S101, the environmental variable characteristic information includes environmental variables that affect the usage of the home appliance, such as electricity preference, external weather, time, etc.; the household appliance use information comprises the use condition of the solitary old man on different household appliances and the power consumption of the different household appliances. The power consumption is used for judging whether the power consumption data is abnormal, and when the behavior analysis model is trained, a more accurate training sample can be obtained by removing a part of historical power consumption data with abnormal power consumption. The current behaviors of the orphan aged can be obtained by collecting the use conditions and the electricity consumption of the orphan aged for different household appliances and combining the electricity consumption preference and the external weather.
By combining the characteristic information of the environmental variables, the electricity consumption habits of people with different characteristics can be analyzed, so that the learning result of the behavior analysis model obtained through training is more in line with the true value.
For example, the external weather mainly includes air temperature, air pressure, humidity, wind power, weather conditions, etc., and the electricity consumption conditions of the orphan aged are different based on different external weather. The electricity consumption preference includes, but is not limited to, academic education level, hobbies, territories acquired through questionnaires or external systems, and furthermore, the electricity consumption preference may also include the number of households, age distribution, etc. affecting electricity consumption conditions.
In S101, after "collect historical usage information and electricity consumption of orphan aged people to different home appliances", the method further includes: and simulating the use data of the unconventional electric appliance, and performing sample expansion on the household appliance use information at the historical moment.
In the step, the accuracy of the behavior analysis model in recognition is improved through sample expansion. Specifically, the trained behavior analysis model is obtained by taking manually marked household appliance use information as input, manually marked action information as supervision and training. The collected data can be adopted as sample data, and the data is unbalanced due to the fact that the collected data is high in singleness and low in richness in data in some cases. For example, the data of electrical appliances conventionally used such as lighting, televisions, gas cookers and the like are very rich, and the use data of non-conventional electrical appliances such as electric dust collectors, automatic dish washers and the like are relatively less, so that the sample data of the non-conventional electrical appliances are expanded.
The sample data expansion mode adopted by the invention is as follows: simulating the usage data of the unconventional electrical appliance. For example, a simulator is established, in which various types of non-conventional electric appliances are provided, operation instructions are input to the non-conventional electric appliances, and an operation for performing simulation use is executed in accordance with the operation instructions, so that simulation of use data is achieved. By means of the sample expansion method, the richness of the samples obtained by original acquisition is improved, and the identification accuracy of the trained model is improved. In addition, the samples can be enriched through a behavior analysis model, for example, an electrical appliance operation instruction is input into the behavior analysis model, and the use data of the electrical appliance are obtained. It is obvious that the above-mentioned manner of expanding the sample is merely exemplary, and in practical applications, a person skilled in the art may expand the sample based on actual needs.
In S101, the "home appliance usage information of the orphan aged at the current time" includes one or more of a home appliance type, a home appliance temperature, a home appliance switching time, a home appliance usage duration, and a home appliance usage period.
In this example, the collected household appliance usage information can be mainly classified into the following two types, 1, continuous data: such as a real-time consumption curve of the total electric quantity, the temperature of an electric appliance and the like; 2. discrete data: based on the data of different types, clustering and regression analysis are performed by combining the electricity consumption preference with sample data such as external weather, time and the like, and behavior habits including but not limited to electricity consumption, electricity consumption time period, electric appliance preference and the like can be analyzed. In addition, the specific data of the specific household appliance can be acquired for analysis.
Taking the abnormal state of the cooking equipment as an example, the abnormal state can be judged by setting a threshold value of a fixed algorithm index: acquiring current cooking time and/or current cooking temperature of cooking equipment, wherein the cooking equipment comprises a cooking electric appliance for cooking an oven and/or a cooking range, the current cooking time and/or the current cooking temperature are acquired and acquired by the cooking equipment, the state of the cooking equipment is determined based on the current cooking time and/or the current cooking temperature, and when the state of the cooking equipment is abnormal, the behavior of the orphan aged is judged to be abnormal.
Illustratively, determining that the cooking apparatus is abnormal includes the steps of: acquiring historical cooking time and/or historical cooking temperature of the cooking equipment; acquiring historical average cooking time length and/or historical average cooking temperature of the cooking equipment based on the information; and judging abnormal states of the cooking equipment when the current cooking time length and/or the current cooking temperature continuous time period of the cooking equipment are different from the historical average cooking time length and/or the historical average cooking temperature of the cooking equipment.
In S102, "acquiring household appliance usage information at the current moment of the orphan aged and environment variable feature information at the current moment, inputting the household appliance usage information at the current moment and the environment variable feature information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan aged" includes: acquiring household appliance use information of the orphan old at the current moment and environment variable characteristic information at the current moment, wherein the household appliance use information at the current moment comprises power consumption data of different household appliances; inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model to obtain a current action corresponding to each household appliance output by the trained behavior analysis model; and integrating the current actions in parallel in a period of time according to the time sequence to obtain the current behavior of the orphan elderly.
In other words, the current behavior is composed of at least one current action within a set period of time, and each current action corresponds to household appliance usage information of an individual household appliance.
In this example, the current actions of the orphan aged are respectively estimated according to the current usage information of different home appliances, and then the current actions of the orphan aged which are respectively estimated are integrated to obtain the final current behavior. The following describes the integration of behavior information of home appliances a and B in detail. The method comprises the steps that when a plurality of electric appliances are used in parallel in electricity consumption data, the sequence of the use of the electric appliances A and the use of the electric appliances B and the parallel conditions form a sequence within a period of time, the electric appliance A is opened to display normal behavior, the electric appliance B is closed to display abnormal behavior within the period of time, similarity comparison is carried out on the two actions, the actions of the electric appliances A and the electric appliance B are obtained and classified into the same type of action, and then the normal current action is taken, so that the current behavior of the orphan can be reflected more accurately. Taking a television and a computer as examples, when the electricity utilization habit of a user is reflected in entertainment action in a period of time, if the television is on and the computer is off in the period of time, the normal current action is taken as entertainment action, and the action of the old is described as normal.
Further, the household appliances may be classified, and the actions may be integrated according to the level of the household appliances, and the higher the household appliance level is, the higher the influence factor of the household appliance in the current behavior is, and conversely, the lower the influence factor is. By the method, similar actions can be integrated within a period of time, and analysis results of the actions are improved.
In S102, home appliances include televisions, radios, microwave ovens, gas ranges, electric lamps, and the like. The use information comprises the starting-up time and the shutdown time of the television, and the television is used for a certain time; the use time of the microwave oven and the use time period; the use time of the gas cooker, the use time period, the electric quantity and the like. In specific use, the method can be based on data sensor or intelligent socket collection on the household appliance, for example, when the television is turned on, the turn-on time of the television is recorded through the sensor, when the television is turned off, the turn-off time of the television is recorded through the sensor, or the turn-on time of the microwave oven is recorded through the sensor on the microwave oven, and the like; the method comprises the steps of modifying a home circuit, dividing lines and uniformly accessing external equipment to collect; the switching-on time and the like of the household appliances are recorded through the household appliances, such as a television, a radio and the like.
Aiming at the steps 101-105, the invention provides a behavior analysis method for the orphan aged, which can analyze the behavior of the orphan aged based on electricity consumption data and timely find the safety problem of the orphan aged when the orphan aged is in residence. The action reflects a specific behavior of the orphan elderly, for example, the action of the behavior related to turning on and off of the light may reflect the physical condition of the elderly, and if the behavior is very high here, it may reflect that the body of the orphan elderly may have some condition, for example, urinary system disease, etc. Only one example is given here, and the current action corresponding to each electrical data is not particularly limited in this example. In another example shown, it is also possible to determine whether other actions of the orphan are performed by lawless persons, for example, whether the lawless persons perform fraud, if the lawless persons perform fraud on the orphan, the actions of the orphan may have corresponding characteristics, for example, electric lamps may be often used to find related things such as property, passbooks, etc., and the characteristics may be necessarily different from normal actions, and whether the lawless persons perform fraud may be analyzed according to the characteristics. The behavior of the orphan aged is obtained by analyzing the behavior of the orphan aged, the household appliance use information at the current moment, the environment variable characteristic information at the current moment and the current behavior are updated to the sample library, the sample is further expanded, the recognition result output by the model is more similar to the action behavior true value of the orphan aged, the orphan aged can be better cared by analyzing the action and the behavior, the personal safety problem of the orphan aged in the home is avoided, the corresponding policy and the corresponding solution scheme for solving the problem can be timely designed when the abnormality is found, the problem of the orphan aged can be greatly promoted and solved, the social burden is reduced, and the like.
Example two
Referring to fig. 2, a behavior analysis system for orphan elderly people in a second embodiment of the present invention is shown, the system includes:
the collection equipment is used for collecting household appliance use information at the current moment and environment variable characteristics at the current moment, which are generated in the process of using the household appliances by the orphan old people;
the internet of things platform is used for acquiring and storing household appliance use information at the current moment and environment variable characteristic information at the current moment;
the intelligent middle platform is used for training a behavior analysis model, pre-judging the current behavior of the orphan old people, and comparing the similarity;
and the service platform is used for notifying the current behavior to the user terminal.
In this example, the collection device may include a wireless sensor and the like, upload the collected household appliance usage information at the current moment to the internet of things platform, where the internet of things platform stores the household usage information at the current moment in the database, and build a model library on the intelligent middle platform, and obtain a trained behavior analysis model from the model library through training data. When training the behavior analysis model, firstly, a proper loss function is designed, in this example, 0-1 loss aiming at classification is adopted, the estimated value of correct classification is taken as 0, and otherwise, 1 is taken as 1. The loss function is set depending on the model requirements, which may be the accuracy of the behavior analysis, the performance parameters of the model, the time the performance parameters of the model are trained, the size of the model, etc. For classified loss functions, there is a cross entropy loss function, which is a smooth function, and the cross entropy in information theory is essentially applied to classification problems. It is known from the definition of cross entropy that minimizing cross entropy is equivalent to minimizing the relative entropy of the observed and estimated values, i.e., the Kullback-Leibler divergence of both probability distributions, and is therefore a proxy penalty providing unbiased estimation. In the training process, after the model converges, training of the model is ended, and a behavior analysis model is obtained.
In this example, since a large amount of household appliance usage information is collected, the storage of data is also a problem to be considered, and the existing data storage can have multiple storage modes, for example, direct storage in a server, distributed storage by establishing a server cluster, storage of data in a cloud end by using a cloud end server, and the like. The servers have corresponding disadvantages, such as higher cost and less data volume stored in the local server; the data stored in the cloud server has security problems. In order to improve the storage security and the reliability of data, guarantee that the electricity data of the orphan elder can not be revealed, the application establishes a server cluster to store data, and specifically, the behavior analysis system of the orphan elder is deployed on a server, and comprises: a local server cluster is established, and distributed management is carried out on the servers, so that different local servers store data of different areas; and establishing a cloud server cluster, and storing, managing and inquiring the data by using the unified port. Different servers are numbered to manage different storage contents by carrying out distributed management on the local servers, and the power consumption data of the orphan aged in different areas can be stored in different local servers, for example, data of A, B, C cells is stored in one server, and data of D, E, F cells is stored in the other server. The cloud server cluster comprises a cloud server management platform, authentication and identification are carried out on the identity when data access is carried out through platform management data, and the security of the data is enhanced by adopting modes such as symmetric encryption of the cloud platform, ciphertext policy attribute base encryption (CP-ABE) and the like. When accessing data, the flow is managed by the way of FIFO queuing.
Example III
The embodiment also provides a behavior analysis device for orphan elderly people, which is characterized in that the device comprises:
the acquisition unit is used for acquiring household appliance use information at the current moment of the orphan old people and environment variable characteristic information at the current moment;
the input unit is used for inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan old people, wherein the behavior analysis model is obtained by training the household appliance use information at the historical moment, the environment variable characteristic information and the corresponding historical behavior;
the acquisition unit is used for acquiring the corresponding historical behaviors of the historical moment according to the environmental variable characteristic information of the current moment;
and the comparison unit is used for comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, the behavior of the orphan aged is judged to be abnormal.
Example IV
Referring to fig. 3, the present embodiment further provides an electronic device, including a memory 304 and a processor 302, where the memory 304 stores a computer program, and the processor 302 is configured to execute the computer program to perform the steps in any of the above method embodiments.
In particular, the processor 302 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
Memory 304 may include, among other things, mass storage 304 for data or instructions. By way of example, and not limitation, memory 304 may comprise a Hard Disk Drive (HDD), floppy disk drive, solid State Drive (SSD), flash memory, optical disk, magneto-optical disk, tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Memory 304 may include removable or non-removable (or fixed) media, where appropriate. Memory 304 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 304 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, memory 304 includes Read-only memory (ROM) and Random Access Memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or FLASH memory (FLASH) or a combination of two or more of these. The RAM may be Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM) where appropriate, and the DRAM may be fast page mode dynamic random access memory 304 (FPMDRAM), extended Data Output Dynamic Random Access Memory (EDODRAM), synchronous Dynamic Random Access Memory (SDRAM), or the like.
Memory 304 may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by processor 302.
The processor 302 reads and executes the computer program instructions stored in the memory 304 to implement any orphan or orphan behavior analysis method in the above embodiment.
Optionally, the electronic apparatus may further include a transmission device 306 and an input/output device 308, where the transmission device 306 is connected to the processor 302, and the input/output device 308 is connected to the processor 302.
The transmission device 306 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through the base station to communicate with the internet. In one example, the transmission device 306 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
The input-output device 308 is used to input or output information. For example, the input/output device may be a display screen, a mouse, a keyboard, or other devices. In this embodiment, the input device is configured to input acquired information, where the input information may be data, a table, an image, a real-time video, and the output information may be text, a chart, and alarm information displayed by the service system.
Alternatively, in the present embodiment, the above-mentioned processor 302 may be configured to execute the following steps by a computer program:
s101, acquiring household appliance use information of the orphan old people at the current moment and environment variable characteristic information at the current moment;
s102, inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model, and pre-judging to obtain the current behavior of the orphan aged, wherein the behavior analysis model is obtained by training the household appliance use information at the historical moment, the environment variable characteristic information and the corresponding historical behavior;
s103, acquiring a history behavior of the corresponding history moment according to the environment variable characteristic information of the current moment;
s104, comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, judging the behavior of the orphan old people as abnormal behavior;
and S105, if the current behavior is similar to the historical behavior, judging that the behavior of the orphaned old people is normal, and updating a training behavior analysis model according to the household appliance use information at the current moment, the environment variable characteristic information at the current moment and the current behavior.
In addition, in combination with the behavior analysis method of the orphan elderly in the above embodiment, the embodiment of the application may provide a storage medium for implementation. The storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements the behavior analysis method of any orphan elderly person in the above embodiment.
It should be understood by those skilled in the art that the technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features. The foregoing examples merely represent several embodiments of the present application, the description of which is more specific and detailed and which should not be construed as limiting the scope of the present application in any way. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (11)
1. A behavioral analysis method for orphan elderly people, the method comprising:
acquiring household appliance use information of the orphan old at the current moment and environment variable characteristic information at the current moment, wherein the household appliance use information at the current moment comprises power consumption data of different household appliances;
inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into a trained behavior analysis model to obtain a current action corresponding to each household appliance output by the trained behavior analysis model; integrating the current actions in parallel in a period of time according to a time sequence to obtain the current behavior of the orphan elderly; the behavior analysis model is obtained by training household appliance use information, environment variable characteristic information and corresponding historical behaviors at historical moments;
acquiring a history behavior of the corresponding history moment according to the environment variable characteristic information of the current moment;
comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, judging the behavior of the orphan old people as abnormal behavior.
2. The behavioral analysis method for an orphan according to claim 1, wherein the steps further comprise: if the current behavior is similar to the historical behavior, judging that the behavior of the orphaned old people is normal, and updating a training behavior analysis model according to the household appliance use information at the current moment, the environment variable characteristic information at the current moment and the current action.
3. The behavioral analysis method for an orphan aged according to claim 1, wherein the environmental variable characteristic information at the present time and the environmental variable characteristic information at the historic time include electricity preference, external weather, and time.
4. The behavioral analysis method of an orphan according to claim 3, wherein "the behavioral analysis model is trained from historical time home appliance usage information, environmental variable characteristic information, and corresponding historical behaviors" further comprises:
and simulating the use data of the unconventional electric appliance, and performing sample expansion on the household appliance use information at the historical moment.
5. The behavioral analysis method for an orphan aged according to claim 4, wherein the "home appliance usage information at the current time of the orphan aged" includes one or more of a home appliance type, a home appliance temperature, a home appliance switching time, a home appliance usage duration, and a home appliance usage period.
6. The behavioral analysis method for an orphan according to claim 1, wherein the household appliance usage information of the orphan at the current time is collected by at least one of the following means:
based on data sensors or smart sockets on the household appliances;
uniformly accessing external equipment to collect on a household circuit;
recorded by the household appliance itself.
7. A behavioral analysis system for orphan elderly people, the system comprising:
the household appliance management system comprises an acquisition device, a control device and a control device, wherein the acquisition device is used for acquiring household appliance use information at the current moment and environment variable characteristics at the current moment, which are generated in the process of using household appliances by the orphan old people, wherein the household appliance use information at the current moment comprises power consumption data of different household appliances;
the internet of things platform is used for acquiring and storing household appliance use information at the current moment and environment variable characteristic information at the current moment;
the intelligent middle platform is used for training a behavior analysis model, inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into the trained behavior analysis model to obtain the current action corresponding to each household appliance output by the trained behavior analysis model, integrating the current actions in parallel in a period of time according to a time sequence to obtain the current behavior of the orphan and the old and comparing the similarity;
and the service platform is used for notifying the current behavior to the user terminal.
8. A behavioral analysis apparatus for orphan elderly people, the apparatus comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring household appliance use information of the orphan old people at the current moment and environment variable characteristic information of the current moment, and the household appliance use information of the current moment comprises power utilization data of different household appliances;
the input unit is used for inputting the household appliance use information at the current moment and the environment variable characteristic information at the current moment into the trained behavior analysis model to obtain the current action corresponding to each household appliance output by the trained behavior analysis model; integrating the current actions in parallel in a period of time according to a time sequence to obtain the current behavior of the orphan aged, wherein the behavior analysis model is obtained by training household appliance use information, environment variable characteristic information and corresponding historical behaviors at historical moments;
the acquisition unit is used for acquiring the corresponding historical behaviors of the historical moment according to the environmental variable characteristic information of the current moment;
and the comparison unit is used for comparing the current behavior with the historical behavior, and if the current behavior is dissimilar, the behavior of the orphan aged is judged to be abnormal.
9. The behavioral analysis device of an orphan elderly person of claim 8, wherein the behavioral analysis system of an orphan elderly person is deployed on a server, comprising:
a local server cluster is established, distributed management is carried out on the local servers, and data of different areas are stored by different local servers;
and establishing a cloud server cluster, and storing, managing and inquiring the data by using the unified port.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the behavioral analysis method of an orphan elderly person according to any of claims 1 to 6.
11. A storage medium, characterized in that the storage medium has stored therein a computer program, wherein the computer program is arranged to perform the behavioral analysis method of an orphan elderly person according to any one of claims 1 to 6 at run-time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110067644.2A CN112801154B (en) | 2021-01-19 | 2021-01-19 | Behavior analysis method and system for orphan elderly people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110067644.2A CN112801154B (en) | 2021-01-19 | 2021-01-19 | Behavior analysis method and system for orphan elderly people |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801154A CN112801154A (en) | 2021-05-14 |
| CN112801154B true CN112801154B (en) | 2024-02-02 |
Family
ID=75810373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110067644.2A Active CN112801154B (en) | 2021-01-19 | 2021-01-19 | Behavior analysis method and system for orphan elderly people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801154B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298175B (en) * | 2021-06-10 | 2023-09-12 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of solitary old people based on multiple scenes and multiple data |
| CN113298577A (en) * | 2021-06-23 | 2021-08-24 | 福建亿力优能电力科技有限公司 | Abnormal state alarm monitoring method for solitary old people based on intelligent monitoring terminal |
| CN113780452B (en) * | 2021-09-16 | 2024-06-14 | 国网北京市电力公司 | Monitoring method and monitoring device for solitary group and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1752720A (en) * | 2004-09-23 | 2006-03-29 | 浙江工业大学 | Old solitary people safety protection device based on life supply line |
| KR101097235B1 (en) * | 2011-09-09 | 2011-12-22 | (주) 대호아이앤티 | Safety network system for solitude oldster and service providing method thereof |
| KR20160112736A (en) * | 2015-03-20 | 2016-09-28 | 부산대학교 산학협력단 | System and Method for Safety managing elderly by using social information and power consumption pattern of the individual appliance |
| CN111179109A (en) * | 2019-11-29 | 2020-05-19 | 国网浙江省电力有限公司杭州供电公司 | Electricity consumption data processing method for detecting elderly people living alone |
-
2021
- 2021-01-19 CN CN202110067644.2A patent/CN112801154B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1752720A (en) * | 2004-09-23 | 2006-03-29 | 浙江工业大学 | Old solitary people safety protection device based on life supply line |
| KR101097235B1 (en) * | 2011-09-09 | 2011-12-22 | (주) 대호아이앤티 | Safety network system for solitude oldster and service providing method thereof |
| KR20160112736A (en) * | 2015-03-20 | 2016-09-28 | 부산대학교 산학협력단 | System and Method for Safety managing elderly by using social information and power consumption pattern of the individual appliance |
| CN111179109A (en) * | 2019-11-29 | 2020-05-19 | 国网浙江省电力有限公司杭州供电公司 | Electricity consumption data processing method for detecting elderly people living alone |
Non-Patent Citations (2)
| Title |
|---|
| 孤寡老人看护系统的设计与实现;李鹏;孙欣;郑琳;;卫星电视与宽带多媒体(03);全文 * |
| 独居老人行动分析及异常报警系统的电路设计;王锐, 陈安宇;中国医疗器械杂志(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801154A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801154B (en) | Behavior analysis method and system for orphan elderly people | |
| US20220044160A1 (en) | Electrical panel for determining device state changes using smart plugs | |
| US10175276B2 (en) | Identifying and categorizing power consumption with disaggregation | |
| CN105068513A (en) | Intelligent home energy management method based on social network behavior perception | |
| CN110136024B (en) | Method and device for acquiring electricity utilization characteristics, electricity utilization habits and electricity consumption predicted values of users | |
| Yang | A novel cloud information agent system with Web service techniques: Example of an energy-saving multi-agent system | |
| CN111623486B (en) | Method and device for determining starting time, storage medium and electronic device | |
| Abreu et al. | Identification of residential energy consumption behaviors | |
| CN108196461A (en) | Control method, device and the intelligent domestic system of smart home device | |
| CN113777941B (en) | Equipment operation control method, device, equipment and storage medium | |
| CN114493028A (en) | Method and device for establishing prediction model, storage medium and electronic device | |
| AU2017435881A1 (en) | Decoupled modeling methods and systems | |
| US20180157310A1 (en) | Method for analyzing client events of electric power consumer | |
| CN115481315B (en) | Recommendation information determining method and device, storage medium and electronic device | |
| CN116704731A (en) | Safe electricity utilization pre-alarm method based on current fingerprint technology | |
| CN109062396B (en) | Method and device for controlling equipment | |
| CN108107740B (en) | Household appliance control method and device | |
| Maury et al. | Savings at home by modifying the energy consumption pattern using gamification, predictive models and Energy Management Systems | |
| KR102542488B1 (en) | Method and Apparatus for Predicting Appliance Power Usage State Using Non Intrusive Load Monitoring Based on Long-Short Term Memory | |
| CN114819216A (en) | Maintenance service recommendation method for air conditioner and server | |
| Tang et al. | A data-driven approach for online aggregated load modeling through intelligent terminals | |
| CN114676400A (en) | Identity determination method, storage medium and electronic device | |
| CN113852657A (en) | Intelligent home local control method and system based on edge calculation | |
| US20150112617A1 (en) | Real-time monitoring and analysis of energy use | |
| CN112163709B (en) | Method and device for electricity utilization promotion, storage medium, and electronic 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 |