Pension service self-service system and control method thereof
Through the BP neural network prediction model, the interface display is optimized in the intelligent elderly care service self-service system, which solves the operation difficulty and reading burden of the elderly due to incomplete information display, and improves the convenience of the system and the satisfaction of the elderly.
Patent Information
- Application Number
- CN202411861820.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-04-15
AI Technical Summary
The touch screen information display of the smart elderly care service self-service system is limited, resulting in elderly people with poor vision or poor finger flexibility need to frequently turn pages, increase operation difficulty and reading burden, and reduce system acceptance and satisfaction.
The BP neural network prediction model is adopted to obtain user information and historical browsing data, predict the user's interest in different task layouts, optimize interface display, and give priority to the content that users are most interested in.
By accurately predicting and optimizing interface layout, the operation steps and reading burden of the elderly can be reduced, the convenience of the system is improved and the satisfaction of the elderly can be improved, and at the same time, the elderly care service institutions can better understand user needs and behavior patterns.
Smart Images
Figure CN119829177A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of self-service equipment, and in particular to an intelligent elderly care service self-service system and a control method thereof. Background Art
[0002] The intelligent elderly care service self-service system is an information system that uses modern information technology, such as the Internet, the Internet of Things, big data, and artificial intelligence, to provide comprehensive services for the elderly. It integrates various resources to closely link the elderly, the government, the community, medical institutions, and medical staff to form an efficient and coordinated elderly care service system. Its core goal is to improve the efficiency and quality of elderly care services through intelligent means to meet the diverse needs of the elderly. As an important carrier of the intelligent elderly care service self-service system, the elderly care service self-service integrated machine is usually equipped with a touch screen. Through an intuitive and easy-to-use interface and operation process, the elderly do not need to rely on others, but can complete operations such as physical fitness assessment, information query, and educational entertainment with simple guidance or self-exploration, which greatly improves the availability and convenience of services. The intelligent elderly care service self-service system relies on the elderly care service self-service integrated machine. Since the touch screen can only display a limited amount of information, the main interface information display is incomplete and frequent page turning is required to view information. For the elderly with poor eyesight or poor finger flexibility, it will increase their operation difficulty and reading burden, thereby reducing the elderly's acceptance and satisfaction with the intelligent elderly care service self-service system. Therefore, in response to the above problems, an intelligent elderly care service self-service system and its control method are proposed. Summary of the invention
[0003] The main purpose of the present invention is to provide an intelligent self-service elderly care service system and a control method thereof, which can effectively solve the problem that the amount of information that can be displayed on the touch screen is limited, resulting in incomplete information display on the main interface and the need to frequently turn pages to view information, which increases the difficulty of operation and reading burden for elderly people with poor eyesight or poor finger flexibility.
[0004] To achieve the above object, the technical solution adopted by the present invention is: A control method for an intelligent elderly care service self-service system, comprising: Obtain user information by reading the user's credential card to automatically collect the user's card swiping time period, location when swiping the card, and historical browsing data; Perform data processing on the acquired information, select the most frequent card swiping time and the most recent card swiping time; select the most frequent card swiping address and the most recent card swiping address; select the items with the most historical browsing times, the items with the longest historical browsing time and the most recent historical browsing items; Construct the BP neural network prediction model structure, take the user's card swiping time period, location when swiping the card, and historical browsing data as the input variables of the BP neural network, and take the predicted values of different task layouts as the output variables of the BP neural network. The goal of the model is to predict the user's interest in different task layouts. Application of Results,According to the output of BP neural network, the predicted values of different task pages are sorted, and according to the sorting results, the task page layout of the browsing interface is constructed so that the content that users are most likely to be interested in is displayed first.
[0005] Filter the most frequent card swiping time, set For the set of all card swiping time periods, calculate The number of card swipes in each period is calculated as follows:
[0006] Where: For the set Card swiping time period, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts across all time periods , and select The time period with the largest value; Filter the most recent card swiping period and find the latest period among the card swiping periods by comparing all card swiping periods.
[0007] Filter the most frequently used card swipe addresses, set For the set of all addresses, calculate the number of card swipes for each address, the calculation formula is:
[0008] In the formula, For the set Addresses, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts for all addresses , and select The address with the largest value; Filter the most recent card swiping addresses, and find the latest address during the card swiping period by comparing the card swiping periods at all addresses.
[0009] Filter the items with the most historical views, set For all item sets, calculate The number of views for each item in is calculated as:
[0010] In the formula, for The first in the collection projects, A collection of all browsing records of a user. for The first in the collection Browsing records; Compare All Items Number of views , and select The item with the largest value; Filter the items with the longest browsing history, set For all item sets, calculate The browsing time of each item in is calculated as follows:
[0011] In the formula, for The first in the collection projects, It is Viewed items The end time of It is Viewed items The start time of Compare All Items Total browsing time , and select The item with the largest value; Filter the most recently browsed items in history, and find the item with the latest browsing end time by comparing the most recently browsed time of each item; Determine the BP neural network structure: The time period when the user swipes the card, the location when swiping the card, and the historical browsing data are the input variables of the BP neural network. The predicted values of different task layouts are the output variables of the BP neural network. The number of hidden layer nodes is set to , so the structure of BP neural network is ; Calculate the number of nodes in the hidden layer Values: The calculation formula is:
[0012] In the formula, is the number of neurons in the input layer, is the number of neurons in the output layer, is a tuning parameter; Through questionnaire survey, we collect samples, train BP neural network, and determine the output results by comparing them with the survey results. When the value is 3, When the value of is 5, the prediction effect is the best, so the structure of the BP neural network is determined as .
[0013] The prediction results of the BP neural network are subjected to regression analysis: The user's card swiping time period, location at the time of swiping, and historical browsing data are input into the BP neural network prediction model structure to obtain the prediction results. The prediction results are subjected to regression analysis, and the calculation formula is:
[0014] In the formula, is the predicted value, is the actual value, is the correlation coefficient; Arrange the predicted values output by the BP neural network to form a list or array containing the predicted values of all task layouts; Sort the list or array according to the predicted value. The task layout with a higher predicted value indicates that the user is more interested in it. After the sorting is completed, the top N task layouts with the highest prediction values are selected and used as the main display content of the user browsing interface. Among them, the content that users are most likely to be interested in (i.e. the task layout with the highest prediction value) is displayed in a prominent position on the interface so that users can quickly find and access it; An intelligent self-service elderly care service system, comprising a card information collection module, an information data processing module, a user behavior prediction module, and an interface display optimization module; The card information collection module is used to read the information of the user's credential card, including basic information such as user ID, card swipe time, card swipe location, historical browsing data, etc. The information data processing module is used to receive data from the card information collection module and perform further processing and analysis; The user behavior prediction module is based on the BP neural network prediction model and is used to predict the user's interest in the character layout; The interface display optimization module is used to dynamically adjust the browsing interface of the self-service kiosk; An intelligent self-service elderly care service system also includes a storage device, a processing and computing device, and a computing program stored in the storage device and executable on the processing and computing device.
[0015] The present invention has the following beneficial effects: Compared with the prior art, the present invention realizes in-depth mining and accurate prediction of user behavior by introducing a BP neural network prediction model and a data analysis method, accurately pushes service content through prediction results, optimizes the layout display information of the main interface of the self-service all-in-one machine, helps the elderly reduce their reading burden, and reduces the number of operation steps they need to perform, so that the system can guide the elderly with poor eyesight or poor finger flexibility to complete the required operations more quickly. At the same time, the analysis results of user information data can help elderly care service agencies understand the service needs and behavior patterns of the elderly, thereby more reasonably allocating service resources and improving resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a flow chart of an intelligent elderly care service self-service system and a control method thereof according to the present invention; Figure 2 A BP neural network prediction model in an intelligent elderly care service self-service system and a control method thereof according to the present invention; Figure 3 This is a structural block diagram of an intelligent elderly care service self-service system and a control method thereof according to the present invention. DETAILED DESCRIPTION
[0017] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.
[0018] The specific implementation process of the technical solution of the present invention includes the following steps: Step 1: Obtain user information by reading the user's credential card to automatically collect the user's card swiping time period, location when swiping the card, and historical browsing data; Step 2: Process the acquired information, select the most frequent card swiping time and the most recent card swiping time; select the most frequent card swiping address and the most recent card swiping address; select the items with the most historical browsing times, the items with the longest historical browsing time and the most recent historical browsing items; Step 21: Filter the most frequently used card swiping time periods by evenly dividing them into multiple time periods (the time span of each time period should be as small as possible). For the set of all card swiping time periods, calculate The number of card swipes in each period is calculated as follows:
[0019] Where: For the set Card swiping time period, is the collection of all card swipe records. For the set Card swipe records; As an indicator function, if Recorded in If the card swipe record is , ; Compare card swipe counts across all time periods , and select The time period with the largest value; Step 22: Filter the most recent card swiping time period, and find the latest card swiping time period by comparing all card swiping time periods; Step 23: Filter the most frequently used card swipe addresses and record the addresses of multiple self-service machines. For the set of all addresses, calculate the number of card swipes for each address, the calculation formula is:
[0020] In the formula, For the set Addresses, is the collection of all card swipe records. For the set Card swipe records; As an indicator function, if Recorded in If the card swipe record is ,otherwise ; Compare card swipe counts for all addresses , and select The address with the largest value; Step 24: Filter the most recent card swiping address, and find the latest address during the card swiping period by comparing the card swiping periods at all addresses; Step 25: Filter the items with the most historical views, divide the items in the self-service kiosk, and set For all item sets, calculate The number of views for each item in is calculated as:
[0021] In the formula, for The first in the collection projects, A collection of all browsing records of a user. for The first in the collection Browsing records; As an indicator function, if Recorded the of browsing, then ,otherwise ; Compare All Items Number of views , and select The item with the largest value; Step 26: Filter the items with the longest browsing history, divide the items in the self-service kiosk, and set For all item sets, calculate The browsing time of each item in is calculated as follows:
[0022] In the formula, for The first in the collection projects, It is Viewed items The end time of It is Viewed items The start time of Compare All Items Total browsing time , and select The item with the largest value; Filter the most recently browsed items in history, and find the item with the latest browsing end time by comparing the most recent browsing time of each item.
[0023] Step 3: Construct the BP neural network prediction model structure, take the user's card swiping time period, location when swiping the card, and historical browsing data as the input variables of the BP neural network, and take the predicted values of different task layouts as the output variables of the BP neural network. The goal of the model is to predict the user's interest in different task layouts; The time period when the user swipes the card, the location when swiping the card, and the historical browsing data are the input variables of the BP neural network. The predicted values of different task layouts are the output variables of the BP neural network. The number of hidden layer nodes is set to , so the structure of BP neural network is ; Calculate the number of nodes in the hidden layer Values: The calculation formula is:
[0024] In the formula, is the number of neurons in the input layer, is the number of neurons in the output layer, is a tuning parameter; Through questionnaire survey, samples are collected, BP neural network is trained, and the output results are compared with the survey results. The value can be used to calculate the error between the model's predicted value and the actual value at different hidden layer nodes, and the comparison can be used to determine When the value is 3, When the value of is 5, the prediction effect is the best, so the structure of the BP neural network is determined as ; The prediction results of the BP neural network are subjected to regression analysis: The user's card swiping time period, location at the time of swiping, and historical browsing data are input into the BP neural network prediction model structure to obtain the prediction results. The prediction results are subjected to regression analysis, and the calculation formula is:
[0025] In the formula, is the predicted value, is the actual value, is the correlation coefficient; In this linear regression equation, 1.1 is the slope, which means that for every one unit increase in the actual value, the predicted value will increase by 1.1 units; 0.2 is the intercept, which means that when the actual value is 0, the estimated value of the predicted value is 0.2, that is, there is a one-fifth probability that a new user is interested in the predicted result; It means that the output of the BP neural network prediction model is completely positively correlated with the actual value; Step 4: Result application. According to the output of the BP neural network, the predicted values of different task layouts are sorted. According to the sorting results, the task layout of the browsing interface is constructed so that the content that the user is most likely to be interested in is displayed first.
[0026] Step 41: Arrange the predicted values output by the BP neural network to form a list or array containing all the predicted values of the task layouts; Step 42: sorting the list or array according to the predicted values, wherein a task layout with a higher predicted value indicates that the user has a higher interest in it; Step 43: After the sorting is completed, the first N task layouts with the highest prediction values are selected and used as the main display content of the user browsing interface. Among them, the content that the user is most likely to be interested in (i.e., the task layout with the highest prediction value) is displayed in a prominent position on the interface so that the user can quickly find and access it.
[0027] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A control method for an intelligent elderly care service self-service system, characterized in that: The following steps are involved: S1: Obtain user information by reading the user's credential card and automatically collecting the user's card swiping time period, location when swiping the card, and historical browsing data; S2: Process the acquired information and select the most frequent card swiping time period and the most recent card swiping time period; Select the address where the card is swiped most often and the address where the card is swiped most recently; Select the items with the most history views, the items with the longest history views, and the items with the most recent history views; S3: Construct the BP neural network prediction model structure, take the user's card swiping time period, location when swiping the card, and historical browsing data as the input variables of the BP neural network, and take the predicted values of different task layouts as the output variables of the BP neural network. The goal of the model is to predict the user's interest in different task layouts; S4: Application of results, according to the output of the BP neural network, the predicted values of different task layouts are sorted, and according to the sorting results, the task layout of the browsing interface is constructed so that the content that users are most likely to be interested in is displayed first.
2. The control method of a smart elderly care service self-service system according to claim 1, characterized in that: The step S2 comprises the steps of: S21: Filter the most frequent card swiping time period, set For the set of all card swiping time periods, calculate The number of card swipes in each period is calculated as follows: Where: For the set Card swiping time period, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts across all time periods , and select The time period with the largest value; S22: Filter the most recent card swiping time period, and find the latest time period among the card swiping time periods by comparing all the card swiping time periods.
3. The control method of a smart elderly care service self-service system according to claim 1, characterized in that: The step S2 comprises the steps of: S23: Filter the addresses where the card is swiped most frequently, set For the set of all addresses, calculate the number of card swipes for each address, the calculation formula is: In the formula, For the set Addresses, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts for all addresses , and select The address with the largest value; S24: Filter the most recent card swiping address, and find the most recent address during the card swiping period by comparing the card swiping periods at all addresses.
4. The control method of a smart elderly care service self-service system according to claim 1, characterized in that: The step S2 comprises: S25: Filter the items with the most historical views, set For all item sets, calculate The number of views for each item in is calculated as: In the formula, for The first in the collection projects, A collection of all browsing records of a user. for The first in the collection Browsing records; Compare All Items Number of views , and select The item with the largest value; S26: Filter the items with the longest browsing history, set For all item sets, calculate The browsing time of each item in is calculated as follows: In the formula, for The first in the collection projects, It is Viewed items The end time of It is Viewed items The start time of Compare All Items Total browsing time , and select The item with the largest value; S27: Filter the most recently browsed items in history, and find the item with the latest browsing end time by comparing the most recently browsed time of each item.
5. The control method of a smart elderly care service self-service system according to claim 1, characterized in that: Determine the BP neural network structure: The user's card swiping time period, location when swiping the card, and historical browsing data are the input variables of the BP neural network, and the task layout is the output variable of the BP neural network. The number of hidden layer nodes is set to , so the structure of BP neural network is .
6. The control method of a smart elderly care service self-service system according to claim 5, characterized in that: Calculate the number of nodes in the hidden layer Values: The calculation formula is: In the formula, is the number of neurons in the input layer, is the number of neurons in the output layer, is a tuning parameter; Through questionnaire survey, we collect samples, train BP neural network, and determine the output results by comparing them with the survey results. When the value is 3, When the value of is 5, the prediction effect is the best, so the structure of the BP neural network is determined as .
7. The control method of a smart elderly care service self-service system according to claim 5, characterized in that: The prediction results of the BP neural network are subjected to regression analysis: The user's card swiping time period, location at the time of swiping, and historical browsing data are input into the BP neural network prediction model structure to obtain the prediction results. The prediction results are subjected to regression analysis, and the calculation formula is: In the formula, is the predicted value, is the actual value, is the correlation coefficient.
8. The control method of a smart elderly care service self-service system according to claim 1, characterized in that: The step S4 comprises: S41: sorting the predicted values output by the BP neural network to form a list or array containing all the task layout prediction values; S42: sorting the list or array according to the predicted values, wherein a task layout with a higher predicted value indicates that the user has a higher interest in it; S43: After the sorting is completed, the first N task layouts with the highest prediction values are selected and used as the main display content of the user browsing interface. Among them, the content that the user is most likely to be interested in (i.e., the task layout with the highest prediction value) is preferentially displayed in a prominent position on the interface so that the user can quickly find and access it.
9. An intelligent self-service elderly care service system, characterized in that: It includes card information collection module, information data processing module, user behavior prediction module, and interface display optimization module; The card information collection module is used to read the information of the user's credential card, including basic information such as user ID, card swipe time, card swipe location, historical browsing data, etc. The information data processing module is used to receive data from the card information collection module and further process and analyze it through a series of data quantification processing formulas, including the following steps: screening the most frequent card swiping time period, setting For the set of all card swiping time periods, calculate The number of card swipes in each period is calculated as follows: Where: For the set Card swiping time period, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts across all time periods , and select The time period with the largest value; Filter the most recent card swiping time period and find the latest card swiping time period by comparing all card swiping time periods; Filter the most frequently used card swipe addresses, set For the set of all addresses, calculate the number of card swipes for each address, the calculation formula is: In the formula, For the set Addresses, is the collection of all card swipe records. For the set Card swipe records; Compare card swipe counts for all addresses , and select The address with the largest value; Filter the most recent card swiping address, and find the latest address during the card swiping period by comparing the card swiping periods of all addresses; Filter the items with the most historical views, set For all item sets, calculate The number of views for each item in is calculated as: In the formula, for The first in the collection projects, A collection of all browsing records of a user. for The first in the collection Browsing records; Compare All Items Number of views , and select The item with the largest value; Filter the items with the longest browsing history, set For all item sets, calculate The browsing time of each item in is calculated as follows: In the formula, for The first in the collection projects, It is Viewed items The end time of It is Viewed items The start time of Compare All Items Total browsing time , and select The item with the largest value; Filter the most recently browsed items in history, and find the item with the latest browsing end time by comparing the most recently browsed time of each item; The user behavior prediction module is based on a BP neural network prediction model and is used to predict the user's interest in the character layout, including the following steps: determining the BP neural network structure: The time period when the user swipes the card, the location when swiping the card, and the historical browsing data are the input variables of the BP neural network. The predicted values of different task layouts are the output variables of the BP neural network. The number of hidden layer nodes is set to , so the structure of BP neural network is ; Calculate the number of nodes in the hidden layer Values: The calculation formula is: In the formula, is the number of neurons in the input layer, is the number of neurons in the output layer, is a tuning parameter; Through questionnaire survey, we collect samples, train BP neural network, and determine the output results by comparing them with the survey results. When the value is 3, When the value of is 5, the prediction effect is the best, so the structure of the BP neural network is determined as ; The prediction results of the BP neural network are subjected to regression analysis: The user's card swiping time period, location at the time of swiping, and historical browsing data are input into the BP neural network prediction model structure to obtain the prediction results. The prediction results are subjected to regression analysis, and the calculation formula is: In the formula, is the predicted value, is the actual value, is the correlation coefficient; The interface display optimization module is used to dynamically adjust the browsing interface of the self-service integrated machine, including the following steps: Arrange the predicted values output by the BP neural network to form a list or array containing the predicted values of all task layouts; Sort the list or array according to the predicted value. The task layout with a higher predicted value indicates that the user is more interested in it. After the sorting is completed, the top N task layouts with the highest predicted values are selected and used as the main display content of the user browsing interface. Among them, the content that the user is most likely to be interested in (i.e. the task layout with the highest predicted value) is displayed in a prominent position on the interface so that the user can quickly find and access it.
10. The intelligent self-service elderly care service system according to claim 9, characterized in that: The system further comprises a storage device, a processing computing device and a computing program stored in the storage device and executable on the processing computing device, wherein the processing computing device can implement the steps of the method described in any one of claims 1 to 8 when executing the program.