Anti-falling intelligent prediction alarm system and method

Abstract

The invention provides an anti-falling intelligent prediction alarm system and method, and the system comprises a data collection and recording module which is used for collecting and recording a first physical sign data set of a user and a real-time environment data set of the user; the tumble prediction module is used for constructing a prediction model, inputting the recorded first physical sign data set and the real-time environment data set into the prediction model for analysis, and outputting the tumble probability of the user; the first alarm module is used for carrying out first alarm reminding when the falling probability of the user reaches a preset condition; the second alarm module is used for carrying out second alarm reminding after monitoring that the user falls down, collecting a second physical sign data set after the user falls down, carrying out secondary analysis on the second physical sign data set based on the prediction model, and updating the falling probability of the user based on an analysis result; unique and personalized services can be provided for each user, the intelligence is improved, and the safety of the user is further guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent prediction alarm, and in particular to an anti-fall intelligent prediction alarm system and method. Background Art

[0002] At present, with the development of society and the intensification of population aging, falls have become an increasingly prominent public health problem. For the elderly, falls may not only cause serious physical injuries, such as fractures, trauma, etc., but also bring heavy burdens to individuals, families and society.

[0003] Traditional fall prevention measures often have certain limitations. For example, relying on manual care or simple protective equipment cannot achieve real-time, accurate prediction and timely alarm. In this context, it is particularly important and urgent to develop an efficient and intelligent fall prevention intelligent prediction alarm system and method.

[0004] Therefore, in order to overcome the above technical problems, the present invention provides an anti-fall intelligent prediction alarm system and method. Summary of the invention

[0005] The present invention provides an anti-fall intelligent prediction alarm system and method, which is used to predict the probability of falling by collecting and analyzing a first vital sign data set and a real-time environmental data set, and when the first alarm reminder is generated, it can warn of possible falls in advance, take preventive measures in advance, and reduce the occurrence of fall events. When the user falls, a second alarm reminder can be quickly issued to ensure that the user can get help in time and strive for the best rescue time; the second vital sign data set after the fall is collected and analyzed again, which can more accurately understand the user's condition after the fall, and update the data related to the probability of falling to help more comprehensively and accurately evaluate the severity and subsequent impact of the event, and help provide unique and personalized services for each user, improve intelligence and further ensure the safety of users.

[0006] An anti-fall intelligent prediction alarm system, comprising:

[0007] A data collection and recording module is used to collect and record the user's first vital sign data set and the user's real-time environment data set;

[0008] A fall prediction module is used to build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability;

[0009] The first alarm module is used to issue a first alarm reminder when the user's fall probability reaches a preset condition;

[0010] The second alarm module is used to issue a second alarm reminder after monitoring the user's fall. At the same time, it collects the second vital sign data set after the user falls, and performs a secondary analysis on the second vital sign data set based on the prediction model, and updates the user's fall probability in real time based on the analysis results.

[0011] Preferably, an anti-fall intelligent prediction alarm system, a data acquisition and recording module, comprises:

[0012] Data acquisition unit for:

[0013] When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target;

[0014] Collecting a first vital sign data set of the user according to a first data collection target;

[0015] Collecting the user's real-time environment data set according to the second data collection target;

[0016] The data recording unit is used to record the first vital sign data set and the real-time environment data set respectively.

[0017] Preferably, an anti-fall intelligent prediction alarm system, a fall prediction module, comprises:

[0018] A model building unit, used for collecting prediction parameter sample data, learning the prediction parameter sample data, and building a prediction model;

[0019] The prediction analysis unit is used to input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability.

[0020] Preferably, a fall prevention intelligent prediction alarm system, a model building unit, comprises:

[0021] A data collection field determination subunit is used to obtain a first data collection field for vital sign data collection and a second data collection field for environmental data collection;

[0022] The first prediction model building subunit is used to:

[0023] Acquire the data type in the first data collection field, and retrieve a plurality of vital sign sample data corresponding to each data type, and at the same time, determine the first fall case corresponding to the vital sign sample data of each data type;

[0024] Analyze the first fall case to determine the first fall probability distribution state set under different physical sign sample data ranges corresponding to each data type;

[0025] The first data collection field is taken as the first node, the value of the vital sign sample data corresponding to each data type is taken as the first branch node corresponding to the first node, and the first fall probability distribution state set is taken as the first child node of the first branch node;

[0026] The probability values ​​of the corresponding sub-nodes of the physical sign sample data under different branch nodes are averaged, and a probability prediction mechanism is constructed based on the average results;

[0027] Associating the processing flow of the first node, the first branch node, and the first child node based on the probability prediction mechanism to obtain a first prediction model;

[0028] The second prediction model building subunit is used to:

[0029] Determine environmental sample data according to the second data collection field, analyze the environmental sample data, determine obstacle influencing factors relative to the user's position in the environmental sample data, and record a second fall probability distribution state set corresponding to each obstacle influencing factor;

[0030] Constructing a second node according to the second data collection field, taking the obstacle influencing factor as a second branch node of the second node, and taking the second fall probability state set corresponding to the obstacle influencing factor as a second child node of the second branch node;

[0031] Associating the processing flow of the second node, the second branch node, and the second child node to obtain a second prediction model;

[0032] The combining subunit is used to comprehensively analyze the first prediction model and the second prediction model to determine the prediction model.

[0033] Preferably, an anti-fall intelligent prediction alarm system, a prediction analysis unit, comprises:

[0034] A data input subunit, used for inputting the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis;

[0035] The probability output subunit is used to output a first fall probability corresponding to the first vital sign data set and a second fall probability corresponding to the real-time environment data based on the analysis result.

[0036] Preferably, a fall prevention intelligent prediction alarm system, the first alarm module, comprises:

[0037] An address information acquisition unit, used to acquire the address information of the user's watch terminal and the address information of the platform;

[0038] A communication link building unit, used to build a target communication link according to the address information of the user's watch terminal and the address information of the platform;

[0039] The first alarm reminder unit is used to obtain preset conditions, and when the user's fall probability reaches the preset conditions, generate a warning signal on the user's watch terminal, and transmit the warning signal to the platform based on the target communication link for the first alarm reminder.

[0040] Preferably, a fall prevention intelligent prediction alarm system, the second alarm module comprises:

[0041] The second alarm reminder subunit is used for:

[0042] When a user falls, an alarm response instruction is generated, and a voice communication connection is established between the user's watch terminal and the platform based on the alarm response instruction;

[0043] At the same time, the generated real-time location information of the user is transmitted to the platform for a second alarm reminder;

[0044] The probability updating unit is used to collect the second vital sign data set of the user after the fall in real time, and perform a secondary analysis on the second vital sign data set based on the prediction model, and at the same time, update the user's fall probability in real time based on the analysis result.

[0045] Preferably, an anti-fall intelligent prediction alarm system, a data recording unit, comprises:

[0046] The data collection field determination subunit is used to read the first data collection field of the first vital sign data set and use the first data collection field as the first row header, and at the same time, read the second data collection field of the real-time environment data and use the second data collection field as the second row header;

[0047] The data type determination subunit is used to obtain a first data type set of the first vital sign data set, and use the first data type set as a first column header, and at the same time, obtain a second data type set of the real-time environment data set, and use the second data type set as a second column header;

[0048] A data record table generating subunit is used to generate a data record table according to a first row header, a first column header, a second row header, and a second column header, wherein the first row header corresponds to the first column header one-to-one, and the second row header corresponds to the second column header one-to-one;

[0049] The data recording subunit is used to generate data record connections for the collected first vital sign data set and the real-time environment data set according to the first row header, the first column header, the second row header, and the second column header, and fill the collected first vital sign data set and the real-time environment data set into the data recording table according to the data record connections.

[0050] An anti-fall intelligent prediction alarm method, comprising:

[0051] Step 1: Collect and record the user's first vital sign data set and the user's real-time environment data set;

[0052] Step 2: Build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability;

[0053] Step 3: When the user's fall probability reaches a preset condition, a first alarm reminder is issued;

[0054] Step 4: After the user falls, a second alarm is issued. At the same time, a second vital sign data set after the user falls is collected, and the second vital sign data set is secondary analyzed based on the prediction model, and the user's fall probability is updated in real time based on the analysis results.

[0055] Preferably, a fall prevention intelligent prediction alarm method, in step 1, comprises:

[0056] When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target;

[0057] Collecting a first vital sign data set of the user according to a first data collection target;

[0058] Collecting the user's real-time environment data set according to the second data collection target;

[0059] The first vital sign data set and the real-time environment data set are recorded separately.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The probability of falling is predicted by collecting and analyzing the first vital sign data set and the real-time environmental data set, and when the first alarm reminder is generated, it can warn of possible falls in advance, take preventive measures in advance, and reduce the occurrence of falling events. When the user falls, the second alarm reminder can be quickly issued to ensure timely assistance and strive for the best treatment time; the second vital sign data set after the fall is collected and analyzed again, which can more accurately understand the user's condition after the fall. The updated fall probability helps to more comprehensively and accurately assess the severity and subsequent impact of the event, and helps to provide unique and personalized services for each user, improve intelligence and further ensure user safety.

[0062] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0063] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0065] Figure 1 This is a structural diagram of an anti-fall intelligent prediction alarm system in an embodiment of the present invention;

[0066] Figure 2 This is a structural diagram of a data acquisition and recording module in an anti-fall intelligent prediction and alarm system in an embodiment of the present invention;

[0067] Figure 3 The present invention is a flowchart of an anti-fall intelligent prediction alarm method in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0069] In one embodiment, a fall prevention intelligent prediction alarm system is provided. Figure 1 As shown, including:

[0070] A data collection and recording module is used to collect and record the user's first vital sign data set and the user's real-time environment data set;

[0071] A fall prediction module is used to build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability;

[0072] The first alarm module is used to issue a first alarm reminder when the user's fall probability reaches a preset condition;

[0073] The second alarm module is used to issue a second alarm reminder after monitoring the user's fall. At the same time, it collects the second vital sign data set after the user falls, and performs a secondary analysis on the second vital sign data set based on the prediction model, and updates the user's fall probability in real time based on the analysis results.

[0074] In this embodiment, the first vital sign data set may include multiple data types, such as blood pressure, heart rate, etc., which are used as parameters for measuring the probability of falling.

[0075] In this embodiment, the prediction model can be used to implement analysis based on vital sign data and environmental data, and output the user's fall probability, where the user's fall probability is divided into: a first fall probability output based on the vital sign data set and a second fall probability output based on real-time environmental data. The preset conditions can be set in advance. When the first fall probability or the second fall probability meets the preset conditions, a first alarm reminder is issued.

[0076] In this embodiment, the first alarm reminder may generate a warning text message and send it to the platform.

[0077] In this embodiment, the second alarm reminder may generate real-time location information as the content of the second alarm reminder.

[0078] The working principle and beneficial effects of the above technical solution are: by collecting and analyzing the first vital sign data set and the real-time environmental data set to predict the probability of falling, and when the first alarm reminder is generated, it can warn of possible falls in advance, take preventive measures in advance, and reduce the occurrence of falling events. When the user falls, the second alarm reminder can be quickly issued to ensure timely assistance and strive for the best treatment time; the second vital sign data set after the fall is collected and analyzed again, which can more accurately understand the user's condition after the fall. The updated fall probability helps to more comprehensively and accurately evaluate the severity and subsequent impact of the event, and helps to provide unique and personalized services for each user, improve intelligence and further ensure the safety of users.

[0079] In one embodiment, a fall prevention intelligent prediction alarm system is provided. Figure 2 As shown, the data acquisition and recording module includes:

[0080] Data acquisition unit for:

[0081] When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target;

[0082] Collecting a first vital sign data set of the user according to a first data collection target;

[0083] Collecting the user's real-time environment data set according to the second data collection target;

[0084] The data recording unit is used to record the first vital sign data set and the real-time environment data set respectively.

[0085] In this embodiment, the first data collection target may be the collection of a vital sign data set, and the second data collection target may be the collection of the real-time environment in which the user is located.

[0086] The working principle and beneficial effects of the above technical solution are: by determining the first data collection target and the second data collection target by determining the data collection instruction, and realizing the effective collection of the first vital sign data set and the real-time environment data set according to the determined first data collection target and the second data collection target, the accuracy of data collection and recording is ensured.

[0087] In one embodiment, an anti-fall intelligent prediction alarm system is provided, and a fall prediction module includes:

[0088] A model building unit, used for collecting prediction parameter sample data, learning the prediction parameter sample data, and building a prediction model;

[0089] The prediction analysis unit is used to input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability.

[0090] In this embodiment, the prediction parameter sample data may include: sample vital sign data types, data values ​​corresponding to the sample vital sign data types, fall cases under the data values ​​corresponding to each vital sign data type, and sample environmental data, including sample data such as the user's obstacle obstruction.

[0091] The working principle and beneficial effects of the above technical solution are: by collecting prediction parameter sample data and learning the prediction parameter sample data, the prediction model can be accurately and effectively constructed. At the same time, the recorded first vital sign data set and the real-time environmental data set are analyzed through the constructed prediction model to achieve accurate and effective prediction of the user's fall probability, which provides convenience for intelligent prediction alarm for fall prevention.

[0092] In one embodiment, a fall prevention intelligent prediction alarm system is provided, wherein the model building unit comprises:

[0093] A data collection field determination subunit is used to obtain a first data collection field for vital sign data collection and a second data collection field for environmental data collection;

[0094] The first prediction model building subunit is used to:

[0095] Acquire the data type in the first data collection field, and retrieve a plurality of vital sign sample data corresponding to each data type, and at the same time, determine the first fall case corresponding to the vital sign sample data of each data type;

[0096] Analyze the first fall case to determine the first fall probability distribution state set under different physical sign sample data ranges corresponding to each data type;

[0097] The first data collection field is taken as the first node, the value of the vital sign sample data corresponding to each data type is taken as the first branch node corresponding to the first node, and the first fall probability distribution state set is taken as the first child node of the first branch node;

[0098] The probability values ​​of the corresponding sub-nodes of the physical sign sample data under different branch nodes are averaged, and a probability prediction mechanism is constructed based on the average results;

[0099] Associating the processing flow of the first node, the first branch node, and the first child node based on the probability prediction mechanism to obtain a first prediction model;

[0100] The second prediction model building subunit is used to:

[0101] Determine environmental sample data according to the second data collection field, analyze the environmental sample data, determine obstacle influencing factors relative to the user's position in the environmental sample data, and record a second fall probability distribution state set corresponding to each obstacle influencing factor;

[0102] Constructing a second node according to the second data collection field, taking the obstacle influencing factor as a second branch node of the second node, and taking the second fall probability state set corresponding to the obstacle influencing factor as a second child node of the second branch node;

[0103] Associating the processing flow of the second node, the second branch node, and the second child node to obtain a second prediction model;

[0104] The combining subunit is used to comprehensively analyze the first prediction model and the second prediction model to determine the prediction model.

[0105] In this embodiment, the first data collection field refers to the data type that can be used to collect the first vital sign data set, etc.

[0106] In this embodiment, the second data collection field refers to data types that can be used to collect real-time environmental data sets, etc.

[0107] In this embodiment, the vital sign sample data refers to sample data corresponding to each data type, for example, vital sign data such as blood pressure and heart rate.

[0108] In this embodiment, the first iteration case refers to a specific situation corresponding to a fall of the user corresponding to the vital sign sample data.

[0109] In this embodiment, the first fall probability distribution state set refers to the distribution of fall probabilities corresponding to different vital sign sample data values.

[0110] In this embodiment, the first node refers to the values ​​of different vital sign sample data.

[0111] In this embodiment, the obstacle influencing factor refers to an object that affects the user at the user's location.

[0112] In this embodiment, the second fall probability distribution state set refers to the iterative probability distribution caused by different obstacle influencing factors.

[0113] The working principle and beneficial effects of the above technical solution are: first, determine the data collection field, including the first field of vital sign data collection and the second field of environmental data collection; secondly, in the construction of the first prediction model, obtain the data type and the corresponding vital sign sample data in the first field, analyze the fall cases to determine the fall probability distribution state set under different vital sign sample data ranges, construct the relationship between nodes and branch nodes, and construct the probability prediction mechanism through the average probability value to finally obtain the first prediction model; in the construction of the second prediction model, determine the environmental sample data according to the second field, analyze the obstacle influencing factors and their corresponding fall probability distribution state set, construct the corresponding node and branch node relationship to obtain the second prediction model, and finally determine the final prediction model by combining the sub-units to comprehensively analyze the two models, so that the construction and analysis of the model are more systematic and scientific, and can more comprehensively consider the factors related to falls, improve the accuracy of the prediction, and further improve the reliability and comprehensiveness of the prediction of fall situations, which is helpful to take preventive measures in advance and ensure user safety.

[0114] In one embodiment, a fall prevention intelligent prediction alarm system is provided, the prediction analysis unit includes:

[0115] A data input subunit, used for inputting the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis;

[0116] The probability output subunit is used to output a first fall probability corresponding to the first vital sign data set and a second fall probability corresponding to the real-time environment data based on the analysis result.

[0117] In this embodiment, the first fall probability is a corresponding iterative probability obtained after the prediction model analyzes the first vital sign data set.

[0118] In this embodiment, the second fall probability is a fall probability value obtained after the prediction model analyzes the real-time environmental data.

[0119] The working principle and beneficial effect of the above technical solution are: by processing the first vital sign data set and the real-time environmental data set respectively through the prediction model, the first fall probability corresponding to the first vital sign data set and the second fall probability corresponding to the real-time environmental data can be effectively determined.

[0120] In one embodiment, a fall prevention intelligent prediction alarm system is provided, wherein a first alarm module comprises:

[0121] An address information acquisition unit, used to acquire the address information of the user's watch terminal and the address information of the platform;

[0122] A communication link building unit, used to build a target communication link according to the address information of the user's watch terminal and the address information of the platform;

[0123] The first alarm reminder unit is used to obtain preset conditions, and when the user's fall probability reaches the preset conditions, generate a warning signal on the user's watch terminal, and transmit the warning signal to the platform based on the target communication link for the first alarm reminder.

[0124] In this embodiment, the target communication link is a link used to connect the user's watch terminal and the platform.

[0125] In this embodiment, the preset condition is set in advance and is a reference for determining whether to issue the first alarm reminder.

[0126] The working principle and beneficial effects of the above technical solution are: by obtaining the address information of the user's watch terminal and the address information of the platform, a target communication link between the two is constructed according to the address information; secondly, the user's fall probability is compared with the preset conditions, and when the preset conditions are met, the user's watch terminal generates a warning signal which is transmitted to the platform through the target communication link for alarm reminder, thereby improving the timeliness and intelligence of the anti-fall intelligent prediction alarm.

[0127] In one embodiment, a fall prevention intelligent prediction alarm system is provided, wherein the second alarm module comprises:

[0128] The second alarm reminder subunit is used for:

[0129] When a user falls, an alarm response instruction is generated, and a voice communication connection is established between the user's watch terminal and the platform based on the alarm response instruction;

[0130] At the same time, the generated real-time location information of the user is transmitted to the platform for a second alarm reminder;

[0131] The probability updating unit is used to collect the second vital sign data set of the user after the fall in real time, and perform a secondary analysis on the second vital sign data set based on the prediction model, and at the same time, update the user's fall probability based on the analysis result.

[0132] In this embodiment, the second alarm reminder refers to transmitting the real-time location of the user's fall to the platform for alarm reminder.

[0133] In this embodiment, the second vital sign data set refers to the vital sign data corresponding to the user after the fall, including the heart rate and blood pressure data corresponding to the fall.

[0134] The working principle and beneficial effects of the above technical solution are: by generating an alarm response instruction after the user falls, and establishing a voice communication connection between the user's watch terminal and the platform according to the alarm response instruction, it is convenient to interact with the user through the platform by voice; secondly, the generated real-time location information of the user is transmitted to the platform for a second alarm reminder, so that the platform can lock the user's location; finally, the second vital sign data set after the user falls is collected in real time, and the second vital sign data set is analyzed again through the prediction model to effectively update the user's fall probability, so as to effectively grasp the user's subsequent fall probability and improve the intelligence and reliability of the anti-fall intelligent prediction alarm.

[0135] In one embodiment, a fall prevention intelligent prediction alarm system is provided, and a data recording unit includes:

[0136] The data collection field determination subunit is used to read the first data collection field of the first vital sign data set and use the first data collection field as the first row header, and at the same time, read the second data collection field of the real-time environment data and use the second data collection field as the second row header;

[0137] The data type determination subunit is used to obtain a first data type set of the first vital sign data set, and use the first data type set as a first column header, and at the same time, obtain a second data type set of the real-time environment data set, and use the second data type set as a second column header;

[0138] A data record table generating subunit is used to generate a data record table according to a first row header, a first column header, a second row header, and a second column header, wherein the first row header corresponds to the first column header one-to-one, and the second row header corresponds to the second column header one-to-one;

[0139] The data recording subunit is used to generate data record connections for the collected first vital sign data set and the real-time environment data set according to the first row header, the first column header, the second row header, and the second column header, and fill the collected first vital sign data set and the real-time environment data set into the data recording table according to the data record connections.

[0140] In this embodiment, the first row header refers to the data identifier of each row when the first data collection field is used as data record.

[0141] In this embodiment, the second row header refers to the data identifier of each row when the second data collection field is used as data record.

[0142] In this embodiment, the first data type set refers to all data types included in the first vital sign data set.

[0143] In this embodiment, the first column header refers to a data identifier of each column when the first data type set is used as data record.

[0144] In this embodiment, the second data type set refers to all data types included in the real-time environment data set.

[0145] In this embodiment, the second column header refers to the data identifier of each column when the second data type set is used as the data record.

[0146] The working principle and beneficial effect of the above technical solution are: by determining the first row header, the second row header, the first column header and the second column header, a data recording table is constructed according to the first row header, the second row header, the first column header and the second column header, so as to effectively record the first vital sign data set and the real-time environment data set, so as to provide reliable data support for predicting the probability of falling.

[0147] In one embodiment, a fall prevention intelligent prediction alarm method is provided, such as Figure 3 As shown, including:

[0148] Step 1: Collect and record the user's first vital sign data set and the user's real-time environment data set;

[0149] Step 2: Build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability;

[0150] Step 3: When the user's fall probability reaches a preset condition, a first alarm reminder is issued;

[0151] Step 4: After the user falls, a second alarm is issued. At the same time, a second vital sign data set after the user falls is collected, and the second vital sign data set is secondary analyzed based on the prediction model, and the user's fall probability is updated in real time based on the analysis results.

[0152] The working principle and beneficial effects of the above technical solution are: by collecting and analyzing the first vital sign data set and the real-time environmental data set to predict the probability of falling, and when the first alarm reminder is generated, it can warn of possible falls in advance, take preventive measures in advance, and reduce the occurrence of falling events. When the user falls, the second alarm reminder can be quickly issued to ensure timely assistance and strive for the best treatment time; the second vital sign data set after the fall is collected and analyzed again, which can more accurately understand the user's condition after the fall. The updated fall probability helps to more comprehensively and accurately evaluate the severity and subsequent impact of the event, and helps to provide unique and personalized services for each user, improve intelligence and further ensure the safety of users.

[0153] In one embodiment, a fall prevention intelligent prediction alarm method is provided, wherein step 1 includes:

[0154] When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target;

[0155] Collecting a first vital sign data set of the user according to a first data collection target;

[0156] Collecting the user's real-time environment data set according to the second data collection target;

[0157] The first vital sign data set and the real-time environment data set are recorded separately.

[0158] The working principle and beneficial effect of the above technical solution are: by determining the data collection instruction, the first data collection target and the second data collection target are determined, thereby ensuring the accuracy of data collection and recording.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An anti-fall intelligent prediction alarm system, characterized in that: include: A data collection and recording module is used to collect and record the user's first vital sign data set and the user's real-time environment data set; A fall prediction module is used to build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability; The first alarm module is used to issue a first alarm reminder when the user's fall probability reaches a preset condition; The second alarm module is used to issue a second alarm reminder after monitoring the user's fall. At the same time, it collects the second vital sign data set after the user falls, and performs a secondary analysis on the second vital sign data set based on the prediction model, and updates the user's fall probability in real time based on the analysis results.

2. The anti-fall intelligent prediction alarm system according to claim 1 is characterized in that: Data acquisition and recording module, including: Data acquisition unit for: When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target; Collecting a first vital sign data set of the user according to a first data collection target; Collecting the user's real-time environment data set according to the second data collection target; The data recording unit is used to record the first vital sign data set and the real-time environment data set respectively.

3. The anti-fall intelligent prediction alarm system according to claim 1, characterized in that: Fall prediction module, including: A model building unit, used for collecting prediction parameter sample data, learning the prediction parameter sample data, and building a prediction model; The prediction analysis unit is used to input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability.

4. The anti-fall intelligent prediction alarm system according to claim 3, characterized in that: Model building unit, including: A data collection field determination subunit is used to obtain a first data collection field for vital sign data collection and a second data collection field for environmental data collection; The first prediction model building subunit is used to: Acquire the data type in the first data collection field, and retrieve a plurality of vital sign sample data corresponding to each data type, and at the same time, determine the first fall case corresponding to the vital sign sample data of each data type; Analyze the first fall case to determine the first fall probability distribution state set under different physical sign sample data ranges corresponding to each data type; The first data collection field is taken as the first node, the value of the vital sign sample data corresponding to each data type is taken as the first branch node corresponding to the first node, and the first fall probability distribution state set is taken as the first child node of the first branch node; The probability values ​​of the corresponding sub-nodes of the physical sign sample data under different branch nodes are averaged, and a probability prediction mechanism is constructed based on the average results; Associating the processing flow of the first node, the first branch node, and the first child node based on the probability prediction mechanism to obtain a first prediction model; The second prediction model building subunit is used to: Determine environmental sample data according to the second data collection field, analyze the environmental sample data, determine obstacle influencing factors relative to the user's position in the environmental sample data, and record a second fall probability distribution state set corresponding to each obstacle influencing factor; Constructing a second node according to the second data collection field, taking the obstacle influencing factor as a second branch node of the second node, and taking the second fall probability state set corresponding to the obstacle influencing factor as a second child node of the second branch node; Associating the processing flow of the second node, the second branch node, and the second child node to obtain a second prediction model; The combining subunit is used to comprehensively analyze the first prediction model and the second prediction model to determine the prediction model.

5. The anti-fall intelligent prediction alarm system according to claim 3, characterized in that: Predictive Analysis Unit, including: A data input subunit, used for inputting the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis; The probability output subunit is used to output a first fall probability corresponding to the first vital sign data set and a second fall probability corresponding to the real-time environment data based on the analysis result.

6. The anti-fall intelligent prediction alarm system according to claim 1, characterized in that: The first alarm module comprises: An address information acquisition unit, used to acquire the address information of the user's watch terminal and, at the same time, acquire the address information of the platform; A communication link building unit, used to build a target communication link according to the address information of the user's watch terminal and the address information of the platform; The first alarm reminder unit is used to obtain preset conditions, and when the user's fall probability reaches the preset conditions, generate a warning signal on the user's watch terminal, and transmit the warning signal to the platform based on the target communication link for the first alarm reminder.

7. The anti-fall intelligent prediction alarm system according to claim 1, characterized in that: The second alarm module comprises: The second alarm reminder subunit is used for: When a user falls, an alarm response instruction is generated, and a voice communication connection is established between the user's watch terminal and the platform based on the alarm response instruction; At the same time, the generated real-time location information of the user is transmitted to the platform for a second alarm reminder; The probability updating unit is used to collect the second vital sign data set of the user after the fall in real time, and perform a secondary analysis on the second vital sign data set based on the prediction model, and at the same time, update the user's fall probability in real time based on the analysis result.

8. The anti-fall intelligent prediction alarm system according to claim 2, characterized in that: Data recording unit, comprising: The data collection field determination subunit is used to read the first data collection field of the first vital sign data set and use the first data collection field as the first row header, and at the same time, read the second data collection field of the real-time environment data and use the second data collection field as the second row header; The data type determination subunit is used to obtain a first data type set of the first vital sign data set, and use the first data type set as a first column header, and at the same time, obtain a second data type set of the real-time environment data set, and use the second data type set as a second column header; A data record table generating subunit is used to generate a data record table according to a first row header, a first column header, a second row header, and a second column header, wherein the first row header corresponds to the first column header one-to-one, and the second row header corresponds to the second column header one-to-one; The data recording subunit is used to generate data record connections for the collected first vital sign data set and the real-time environment data set according to the first row header, the first column header, the second row header, and the second column header, and fill the collected first vital sign data set and the real-time environment data set into the data recording table according to the data record connections.

9. An anti-fall intelligent prediction alarm method, characterized in that: include: Step 1: Collect and record the user's first vital sign data set and the user's real-time environment data set; Step 2: Build a prediction model, input the recorded first vital sign data set and the real-time environment data set into the prediction model for analysis, and output the user's fall probability; Step 3: When the user's fall probability reaches a preset condition, a first alarm reminder is issued; Step 4: After the user falls, a second alarm is issued. At the same time, a second vital sign data set after the user falls is collected, and the second vital sign data set is secondary analyzed based on the prediction model, and the user's fall probability is updated in real time based on the analysis results.

10. The anti-fall intelligent prediction alarm method according to claim 9, characterized in that: Step 1 includes: When the user successfully wears the watch, a data collection instruction is generated, and the data collection instruction is read to determine the first data collection target and the second data collection target; Collecting a first vital sign data set of the user according to a first data collection target; Collecting the user's real-time environment data set according to the second data collection target; The first vital sign data set and the real-time environment data set are recorded separately.

Images