Method and device for controlling old-age service robot based on wearable device cooperation

Abstract

The invention provides an old-age service robot control method and device based on wearable device cooperation. The method comprises the steps that a service instruction sent by a wearable device is received; if it is determined that the target user is in an abnormal state based on the service instruction, path planning is carried out based on the geographic position, the physiological parameters and the position of the old-age service robot to obtain a first optimal service route, and the old-age service robot is controlled to travel to the geographic position according to the first optimal service route to check the target user; if it is determined that the target user is in a normal state based on the service instruction, performing semantic recognition on the voice instruction, and determining a service demand of the target user; performing path planning based on the geographic position, the service demand and the own position to obtain a second optimal service path; and controlling the old-age service robot to travel to the geographic position according to the second optimal service route so as to execute the corresponding service according to the service demand. According to the invention, timeliness and effectiveness of the old-age care service are realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a control method and device for an elderly care service robot based on collaboration with wearable devices. Background Art

[0002] Currently, common control methods for elderly care robots rely primarily on the interaction between a fixed-position sensor network and the robot itself. Specifically, multiple environmental sensors are deployed throughout the facility to collect indoor environmental data, such as the location and activity status of the elderly. These sensors then transmit this data to the robot control system, which then analyzes and processes the collected data according to pre-set programs to perform corresponding service tasks, such as delivering items to the elderly or reminding them to take medication.

[0003] However, with the current control method, when the elderly leave the sensor coverage area, such as when they are outdoors or in areas with poor sensor signals, the robot will not be able to obtain accurate information about the elderly in a timely manner, resulting in the inability to provide effective services to the elderly. This seriously affects the timeliness and effectiveness of elderly care services and makes it difficult to meet the diverse and dynamic needs of elderly care services. Summary of the Invention

[0004] The present invention provides a control method and device for an elderly care service robot based on collaboration with wearable devices, so as to achieve timeliness and effectiveness of elderly care services.

[0005] In a first aspect, the present invention provides a control method for an elderly care service robot based on collaboration with a wearable device, wherein the wearable device integrates a positioning module, a physiological parameter monitoring module, a voice interaction module, and a wireless communication module; a wireless communication receiving device of a corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot; the method comprises:

[0006] Receiving a service instruction sent by the wearable device; the service instruction carries the geographic location, physiological parameters and voice instruction of the target user;

[0007] If it is determined based on the service instruction that the target user is in an abnormal state, path planning is performed based on the geographic location, the physiological parameters, and the location of the elderly care service robot to obtain a first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to examine the target user;

[0008] If it is determined based on the service instruction that the target user is in an abnormal state, semantic recognition is performed on the voice instruction to determine the service needs of the target user;

[0009] Performing path planning based on the geographic location, the service demand, and the own location to obtain a second optimal service route;

[0010] The elderly care service robot is controlled to travel to the geographical location along the second optimal service route to perform corresponding services according to the service requirements.

[0011] In a second aspect, the present invention further provides a control device for an elderly care service robot based on collaboration with a wearable device, which is applied to the control method for an elderly care service robot based on collaboration with a wearable device as described in the first aspect; the wearable device integrates a positioning module, a physiological parameter monitoring module, a voice interaction module, and a wireless communication module; a wireless communication receiving device of a corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot; the device includes:

[0012] A receiving module, configured to receive a service instruction sent by the wearable device; the service instruction carries the target user's geographic location, physiological parameters, and voice instructions;

[0013] a first service control module, configured to, if it is determined based on the service instruction that the target user is in an abnormal state, perform path planning based on the geographic location, the physiological parameters, and the position of the elderly care service robot to obtain a first optimal service route, and control the elderly care service robot to travel to the geographic location along the first optimal service route to inspect the target user;

[0014] a semantic recognition module, configured to perform semantic recognition on the voice instruction to determine the service requirements of the target user if it is determined based on the service instruction that the target user is in an abnormal state;

[0015] a route planning module, configured to perform route planning based on the geographic location, the service demand, and the own location to obtain a second optimal service route;

[0016] The second service control module is used to control the elderly care service robot to travel to the geographical location along the second optimal service route to perform corresponding services according to the service requirements.

[0017] In a third aspect, the present invention also provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned methods for controlling an elderly care service robot based on collaboration with wearable devices.

[0018] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements any of the above-mentioned methods for controlling an elderly care service robot based on collaboration with wearable devices.

[0019] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for controlling an elderly care service robot based on collaboration with wearable devices.

[0020] The control method for a wearable device-enabled elderly care service robot, provided by an embodiment of the present invention, equips users with wearable devices, enabling them to transmit their location, physiological status, and service needs to the robot in real time, whether indoors or outdoors. This ensures timely elderly care services. Furthermore, the information collected by wearable devices overcomes the coverage limitations of traditional sensor networks, enabling the elderly care robot to obtain real-time information about the user at any location. This information, combined with physiological parameters and service needs, helps plan routes, ensuring that the robot can provide effective services in a variety of complex scenarios, thereby ensuring service effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of a method for controlling an elderly care service robot based on collaboration with wearable devices provided by an embodiment of the present invention;

[0022] Figure 2 Schematic diagram of the structure of a wearable device-based elderly care service robot control device provided by an embodiment of the present invention;

[0023] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0024] Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0027] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0028] See Figure 1 , Figure 1 This is a flow chart of a wearable device-based control method for an elderly care service robot, provided by the present invention. In one embodiment of the present invention, the control method is performed by an elderly care service device. In one scenario, the elderly care service device can be an elderly care service robot. The wearable device in this embodiment integrates a positioning module, a physiological parameter monitoring module, a voice interaction module, and a wireless communication module. A wireless communication receiving device operating in the corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot.

[0029] Therefore, the control method of the elderly care service robot based on the collaboration of wearable devices includes:

[0030] Step 10: Receive a service instruction sent by the wearable device. The service instruction carries the target user's geographic location, physiological parameters, and voice instructions.

[0031] Optionally, the elderly care service robot establishes a connection with a wearable device worn by the target user via a built-in wireless communication module. The wearable device collects the target user's location information, physiological parameters (such as heart rate and blood pressure), and voice commands (such as pressing the call button on the device and then speaking the request) in real time. The wearable device packages this data into service instructions and sends them to the elderly care service robot via the network.

[0032] Furthermore, after receiving the service instructions, the main control system of the elderly care service robot parses the instructions and extracts key information such as geographic location, physiological parameters and voice commands.

[0033] In one embodiment, elderly user A wears a smart bracelet that collects real-time data on their current location (latitude and longitude coordinates: 39.9042°N, 116.4074°E) and physiological parameters (heart rate 120 beats / minute, blood pressure 160 / 100 mmHg). This information, along with voice commands, is packaged into a service instruction and sent via a 4G network to a senior care service robot responsible for caring for elderly user A. The robot then interprets the instruction and retrieves the relevant data.

[0034] Step 20: If it is determined based on the service instruction that the target user is in an abnormal state, path planning is performed based on the geographic location, physiological parameters and the elderly care service robot's own position to obtain the first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to inspect the target user.

[0035] Furthermore, after receiving the service instruction, the elderly care service robot first analyzes the target user's physiological parameters to determine whether the target user is in an abnormal state, as specifically described in steps 201 to 203. Simultaneously, the elderly care service robot combines the geographic location and its own position (the robot obtains its own position through a built-in positioning module) to calculate the first optimal service route from the robot's current location to the target user's geographic location using a preset path planning algorithm, as specifically described in steps 204 to 207.

[0036] Furthermore, the elderly care service robot controls its own movement according to the planned route through motor drive, navigation system, etc., drives to the location of the target user, and performs a physical examination on the user, such as measuring body temperature through sensors, re-detecting heart rate, etc., to determine the user's specific physical condition.

[0037] Continuing with the above example, after interpreting the service instruction, the elderly care service robot determines that elderly user A is in an abnormal state. The robot then uses its location to plan a route, taking into account real-time traffic flow data on surrounding roads, to calculate the optimal service route that avoids congestion and minimizes distance. Following the planned route, the robot drives along the roads to the park where elderly user A is located. Upon arrival, the robot measures elderly user A's temperature using a built-in infrared thermometer and checks their heart rate using a portable electrocardiogram (ECG) device, further verifying their physical condition.

[0038] Step 30: If it is determined based on the service instruction that the target user is in a normal state, semantic recognition is performed on the voice instruction to determine the service needs of the target user.

[0039] Furthermore, after the elderly care service robot determines that the user is in a normal state, it uses voice recognition technology to convert the voice instructions in the service instructions into text information, and then uses natural language processing (NLP) technology to conduct in-depth analysis of the text through methods such as keyword extraction, grammatical analysis, and semantic understanding, so as to understand the true intentions in the user's words and accurately determine the user's specific service needs, such as needing help buying daily necessities, wanting someone to chat with, accompany entertainment, requesting assistance with daily rehabilitation training, etc.

[0040] Continuing with the above example, elderly care user A at home presses the service request button on their watch and says, "I want to play chess." The smartwatch immediately collects user A's current location and real-time physiological parameters (heart rate 72 beats / minute, blood pressure 120 / 80 mmHg). This information, along with the voice command, is packaged into a service instruction and sent via the 5G network to the elderly care service robot responsible for caring for user A. After receiving the instruction, the robot analyzes and determines that user A's physiological parameters are normal. It then processes the voice instruction "I want to play chess." Speech recognition technology is used to convert the speech into text, and then natural language processing technology is used to determine that the service request is "want" and "play chess."

[0041] Step 40: perform route planning based on the geographical location, service demand and own location to obtain the second optimal service route.

[0042] Furthermore, the elderly care service robot performs path planning based on the geographical location, service needs and its own location to obtain the second optimal service route, as specifically described in the process from step 401 to step 405 .

[0043] Step 50: Control the elderly care service robot to travel to the geographical location along the second optimal service route to perform corresponding services according to service requirements.

[0044] Furthermore, after obtaining the second optimal service route, the elderly care service robot drives along the route through the navigation and motion control system. After arriving at the target user's geographic location, the elderly care service robot performs the corresponding service according to the determined service requirements.

[0045] By equipping users with wearable devices, this embodiment of the present invention enables them to transmit their location, physiological status, and service needs to robots in real time, whether indoors or outdoors. This ensures timely elderly care services. Furthermore, the information collected by wearable devices transcends the coverage limitations of traditional sensor networks, enabling elderly care robots to obtain real-time information about users at any location. This information, combined with physiological parameters and service needs, helps them plan routes, ensuring that the robots can provide effective services in a variety of complex scenarios, thereby ensuring service effectiveness.

[0046] In one embodiment, steps 201 to 203 are described as follows:

[0047] Step 201: Perform region judgment based on the geographical location to determine whether the target user is within a preset safe activity area.

[0048] Optionally, the elderly care service robot pre-stores information about the target user's preset safe activity area. This area can be a polygonal area bounded by multiple coordinate points, or a specific range defined using geo-fencing technology. After receiving a service command and obtaining the target user's geographic location, the robot uses a point-to-polygon position relationship determination algorithm (such as the ray method or cross product method) to determine whether the target user's location is within the preset safe activity area. For example, the ray method draws a ray from the target user's location in a certain direction and counts the number of intersections between the ray and the preset safe activity area boundary. If the number of intersections is odd, the target user is within the area; if it is even, the target user is outside the area.

[0049] Continuing with the above example, elderly care user A's daily activities primarily occur within their residential complex and the surrounding plaza. The elderly care service robot has pre-stored the boundary coordinates of the complex and plaza (e.g., the longitude and latitude coordinates of the four corners of the complex and multiple coordinate points along the plaza's boundary) as a pre-set safe activity zone. One day, elderly care user A's wearable device sends a service instruction to the robot, including the geographic location (39.9060° North Latitude, 116.4090° East Longitude). Using the ray method, the robot draws a ray from this location to the right. After calculation, the robot finds that the ray intersects the pre-set safe activity zone boundary at an odd number of three points, thus determining that elderly care user A is within the pre-set safe activity zone.

[0050] Step 202: If the target user is outside the safe activity area, the target user is determined to be in an abnormal state. If the target user is within the safe activity area, a physiological state detection is performed based on physiological parameters to determine whether the target user's physiological state is normal.

[0051] Furthermore, when step 201 determines that the target user is outside the safe activity area, it is directly determined that the target user is in an abnormal state.

[0052] Furthermore, if the target user is within the safe activity area, the robot analyzes the physiological parameters in the service instruction and performs physiological status detection based on the physiological parameters to determine whether the physiological status of the target user is normal, as shown in the process from step 2021 to step 2025.

[0053] Step 203: If the physiological state is in an abnormal state, it is determined that the target user is in an abnormal state. If the physiological state is in a normal state, it is determined that the target user is in a normal state.

[0054] Furthermore, based on the physiological status determination result obtained in step 202, if the physiological status is abnormal, the target user is directly determined to be in an abnormal state; if the physiological status is normal, the target user is determined to be in a normal state. Continuing with the above embodiment, if the physiological status of elderly care user A is determined to be normal in step 202, then it is determined in step 203 that elderly care user A is in a normal state. At this point, the elderly care service robot can follow the user's voice command "I want to play chess" and subsequently carry out the corresponding service process, such as finding the chessboard and chess pieces, and planning a route to a suitable chess playing location.

[0055] The embodiment of the present invention first determines whether the user has exceeded the preset safe activity area based on the geographic location, and quickly identifies possible abnormal situations such as getting lost; for users in the safe area, their health status is further detected through physiological parameters to avoid missing sudden physical abnormalities, thereby improving the accuracy and reliability of abnormal status judgment and ensuring the safety and health of elderly users.

[0056] In one embodiment, steps 2021 to 2025 are described as follows:

[0057] Step 2021 : Based on the historical baseline of each physiological parameter of the target user within a preset historical window time, the floating range of each physiological parameter is determined.

[0058] Optionally, the elderly care service robot records the target user's heart rate parameters, systolic blood pressure parameters, diastolic blood pressure parameters and body temperature parameter data within a preset historical window (such as the past month). Statistical methods are used to calculate the historical baseline of each parameter. Taking the heart rate parameter as an example, if the heart rate data in the historical window is , its historical baseline (mean) , standard deviation Set coefficients based on medical experience (like The heart rate parameter can float within the range of Similarly, for systolic blood pressure parameters , historical baseline , standard deviation The parameter floating range is , ; Diastolic blood pressure parameters and body temperature parameters are also calculated in this way.

[0059] Continuing with the above embodiment, the elderly care user Physiological parameter data of the past month. Heart rate data is (times / minute), systolic blood pressure data are SBP1=120, SBP2=122, ..., SBP 30 =125 (mmHg), diastolic blood pressure data is , the body temperature data is

[0060] Therefore, the heart rate history baseline can be calculated , standard deviation , the heart rate parameter can float within the range of Second-rate minutes; historical baseline systolic blood pressure , standard deviation The floating range of systolic blood pressure parameters is ; Historical baseline of diastolic blood pressure , standard deviation The floating range of diastolic pressure parameters is ;Body temperature historical baseline Standard deviation The floating range of body temperature parameters is .

[0061] Step 2022 : determining a correlation degree deviation value based on the deviation between the first parameter correlation degree of each physiological parameter of the target user in a normal state and the second parameter correlation degree of each physiological parameter at the current time.

[0062] Furthermore, the robot pre-analyzes the correlation between the target user's heart rate parameters, systolic blood pressure parameters, diastolic blood pressure parameters, and body temperature parameters under normal conditions using a machine learning algorithm (such as multiple linear regression) to obtain the correlation degree of the first parameter, which is expressed as a correlation coefficient matrix, such as:

[0063]

[0064] When the physiological parameters of the current time are received, the same algorithm is used again to calculate the correlation between the current parameters to obtain the second parameter correlation degree matrix The correlation degree deviation value is determined by calculating the square root of the sum of the squares of the differences between the corresponding elements of the two correlation coefficient matrices.

[0065] Continuing with the above embodiment, the elderly care user Under normal conditions, the first parameter correlation matrix of the four physiological parameters is:

[0066]

[0067] The second parameter correlation matrix calculated from the physiological parameters received at a certain moment is:

[0068]

[0069] According to the formula, the correlation degree deviation value is 0.265.

[0070] Step 2023, based on the correlation degree deviation value, the current parameter values ​​corresponding to each physiological parameter at the current time are corrected to obtain the corrected parameter values, and the parameter deviation value is determined based on the current parameter values ​​corresponding to each physiological parameter at the current time and the parameter historical baseline of each physiological parameter.

[0071] Furthermore, according to the correlation degree deviation value obtained in step 2022 , using the formula Correct the current parameter values ​​of each physiological parameter at the current time, where is the corrected parameter value, is the current parameter value, is the correction factor (assuming After obtaining the corrected parameter value, the formula Calculate the parameter deviation value, It is the historical baseline of the physiological parameter.

[0072] Continuing with the above embodiment, the elderly care user Current heart rate value Second-rate minute, systolic blood pressure value , diastolic blood pressure value Body temperature value Correlation degree deviation value , correction factor The corrected heart rate value is Heart rate parameter deviation ; Corrected systolic blood pressure value Systolic blood pressure parameter deviation ; Corrected diastolic blood pressure value Diastolic blood pressure parameter deviation ; Corrected body temperature value , body temperature parameter deviation value .

[0073] In step 2024 , if the corrected parameter values ​​of the physiological parameters are all within the corresponding parameter floating ranges, and the parameter deviations are all less than the preset deviation thresholds, it is determined that the physiological state of the target user is normal.

[0074] Furthermore, the corrected parameter values ​​of each physiological parameter obtained in step 2023 are compared with the parameter floating range determined in step 2021; at the same time, the deviation value of each parameter is compared with the preset deviation threshold (such as the preset deviation threshold of heart rate is 3 times / minute, the preset deviation threshold of systolic blood pressure is , the diastolic pressure preset deviation threshold is , the preset deviation threshold of body temperature is Comparison. Only when all physiological parameters simultaneously meet the requirement that the corrected parameter values ​​are within the floating range and the parameter deviation value is less than the preset deviation threshold, is the physiological state of the target user determined to be normal.

[0075] Continuing with the above embodiment, the elderly care user Corrected heart rate value: 74.96 Minutes in The heart rate parameter deviation value of 1.96 is less than the preset deviation threshold 3 times within the range minutes; corrected systolic blood pressure exist The systolic blood pressure parameter deviation value of 1.68 is less than the preset deviation threshold. ; Diastolic blood pressure corrected value exist The diastolic pressure parameter deviation value of 1.71 is less than the preset deviation threshold. ; Temperature corrected value exist The temperature parameter deviation value is 0.1 less than the preset deviation threshold. At this time, determine the elderly care users The physiological state is in normal state.

[0076] In step 2025, if at least one of the corrected parameter values ​​of each physiological parameter is outside the corresponding parameter floating range, or / and at least one parameter deviation value is greater than or equal to a preset deviation threshold, it is determined that the physiological state of the target user is abnormal.

[0077] Furthermore, as long as the corrected parameter value of any physiological parameter exceeds the corresponding parameter floating range, or any parameter deviation value is greater than or equal to the preset deviation threshold, it is determined that the physiological state of the target user is in an abnormal state. The corrected value of systolic blood pressure is , exceeding Range, even if the heart rate, diastolic blood pressure and body temperature meet the conditions, it is still determined that the elderly care user The physiological state is in an abnormal state.

[0078] The embodiment of the present invention achieves accurate judgment of the physiological state of the target user by combining the historical data of the individual physiological parameters of the user and the correlation between the parameters. It not only takes into account the individual differences of the users through the floating range of the parameters, but also can more sensitively capture the subtle changes in the user's physiological state through the deviation value of the parameter correlation degree. Therefore, it avoids misjudgment caused by individual differences and can discover potential health problems in advance through changes in the correlation between parameters, thereby improving the accuracy and reliability of physiological state judgment.

[0079] In one embodiment, steps 204 to 207 are described as follows:

[0080] Step 204: Determine the emergency level of the abnormality based on the physiological parameters.

[0081] Optionally, the elderly care service robot compares the received physiological parameters (heart rate parameters, systolic blood pressure parameters, diastolic blood pressure parameters and body temperature parameters) with the preset abnormality level threshold. Each physiological parameter is divided into different emergency levels according to the degree of deviation from the normal range, such as mild abnormality, moderate abnormality, and severe abnormality. Set the weights corresponding to different levels, for example, the weight of mild abnormality is 1, the weight of moderate abnormality is 3, and the weight of severe abnormality is 5, and the comprehensive abnormality urgency value is obtained through weighted calculation. For example, heart rate Systolic blood pressure Diastolic blood pressure body temperature The corresponding emergency level weights are , then the abnormal urgency .

[0082] Continuing with the above embodiment, the elderly care user The physiological parameter is heart rate Second-rate Minutes (outside the normal range, judged as mild abnormality, Systolic blood pressure (Beyond the normal range, judged as moderately abnormal , diastolic blood pressure (outside the normal range, judged as mild abnormality, heart DBP=1), body temperature (Beyond the normal range, it is judged as moderate abnormality, Calculate the abnormal urgency according to the formula Indicates a moderate state of emergency.

[0083] Step 205: Generate multiple first initial candidate paths based on the polar coordinate ray method with the own position as the starting point and the geographical location as the end point. The turning point in the path is the intersection of the ray and the environmental obstacle.

[0084] Furthermore, the elderly care service robot takes its own position as the origin of the polar coordinates , with the target user's geographic location as the end point From the origin Start from different angles Rays are emitted (e.g. every 15 degrees) and the intersection of the rays with obstacles in the environment (such as building walls, trees, etc.) is the turning point of the path. These turning points are connected in sequence to form multiple first initial candidate paths. For example, within the robot's perception range, there are For each ray, the path turning point is determined by calculating the intersection of the ray equation and the obstacle boundary equation. The ray equation can be expressed as (in The coordinates of the point on the ray is the polar diameter, is the polar angle), the boundary equation of the obstacle is determined according to its shape (such as rectangle, circle, etc.), and the intersection point is solved by solving the simultaneous equations.

[0085] Continuing with the above embodiment, the elderly care service robot is located at point , elderly care users Located at point (Unit: meter). The robot takes itself as the origin and emits a ray every 15 degrees. There are 3 buildings as obstacles within its sensing range. For example, the ray equation is Solve the equations together with the building boundary equation to get two intersection points A (20, 11.55) and B (50, 28.87). end Connect them in sequence to form a first initial candidate path. According to this method, a plurality of first initial candidate paths corresponding to rays at different angles are generated.

[0086] Step 206 : Screen each first initial candidate path based on the abnormal urgency and the number of turning points in each first initial candidate path to obtain a first target candidate path.

[0087] Furthermore, a threshold value of the number of turning points related to the urgency of the abnormality is set. For example, when the abnormal urgency is 1 (mild), ; When the abnormal urgency is 2 (medium), ; When the abnormal urgency level is 3 (severe), The number of turning points in each first initial candidate path is compared with the threshold Compare and filter out turning points whose number is less than or equal to the threshold The path with the smallest turning points is selected as the first candidate path for the target. The fewer turning points the robot has to make, the shorter the driving time may be, which is more suitable for reaching the target quickly in an emergency.

[0088] Continuing with the above embodiment, it is known that elderly care users The degree of emergency The corresponding turning point number threshold . In the first initial candidate path generated before, the path There are 4 turning points, the path There are 6 turning points, the path There are 3 turning points. Then filter out the path and path As the first target candidate path, the path Excluded because the number of turning points exceeds the threshold.

[0089] Step 207 : Path planning is performed based on the terrain type between the turning points in each first target candidate path, the operating capability of the elderly care service robot in different terrains, and the degree of abnormal urgency to obtain a first optimal service route.

[0090] Furthermore, the elderly care service robot performs path planning based on the terrain type between the turning points in each first target candidate path, the operating capability of the elderly care service robot in different terrains, and the degree of abnormal urgency to obtain the first optimal service route, as specifically described in the process from step 2071 to step 2075.

[0091] The embodiment of the present invention quantifies physiological parameters into urgency levels, combines the polar coordinate ray method to generate candidate paths, and screens and optimizes paths based on the number of turning points and terrain factors. This enables the robot to quickly plan the optimal service route that takes into account both timeliness and feasibility in different emergency situations. This fully considers the user's emergency needs and the actual environmental conditions, improves the service response efficiency and the reliability of the robot's operation, and provides a strong guarantee for timely meeting the needs of elderly care users.

[0092] In one embodiment, steps 2071 to 2075 are described as follows:

[0093] Step 2071: For each first target candidate path, the terrain difficulty coefficient of each path segment is calculated based on the terrain type between its path turning points and the operating capabilities of the elderly care service robot in different terrains, and the cumulative terrain difficulty is determined based on the terrain difficulty coefficient of each path segment.

[0094] Optionally, the elderly care service robot pre-establishes a table of correspondence between terrain types and operating capabilities, such as the corresponding operating speed for flat ground. Energy consumption coefficient 1; grass corresponds to running speed Energy consumption coefficient 2; corresponding running speed on sand Energy consumption coefficient 3, etc. For the path segment between each two adjacent path turning points in the first target candidate path, according to the terrain type of the path segment and the robot's ability to operate on the terrain, the formula Calculate the terrain difficulty coefficient, where For the The terrain difficulty coefficient of the segment, is the energy consumption coefficient of the terrain is the running speed of the terrain. Add up the terrain difficulty coefficients of each section of the path to get the cumulative terrain difficulty is the number of path segments.

[0095] Continuing with the above example, a first target candidate path of the elderly care service robot includes three segments: the first segment is flat ground (50 meters in length), the second segment is grass (30 meters in length), and the third segment is sand (20 meters in length). According to the corresponding relationship table, the energy consumption coefficient of flat ground is , running speed , then the terrain difficulty coefficient of the first section of the path is ;Energy consumption coefficient of grassland , running speed , the terrain difficulty coefficient of the second section of the path ;Energy consumption coefficient of sandy land , running speed , the terrain difficulty coefficient of the third section of the trail The cumulative terrain difficulty of the trail .

[0096] Step 2072: Determine the abnormal impact factor of the abnormality based on the accumulated terrain difficulty and abnormal urgency, and calculate the feasibility index based on the abnormal impact factor and the operating ability of the elderly care service robot in each path.

[0097] Furthermore, a mapping relationship is established between the cumulative terrain difficulty, the abnormal urgency and the abnormal impact factor. For example, when the cumulative terrain difficulty is less than 5 and the abnormal urgency is mild, the abnormal impact factor is 0.2; when the cumulative terrain difficulty is between 5-10 and the abnormal urgency is moderate, the abnormal impact factor is 0.5, etc. The abnormal impact factor is determined by querying the mapping relationship. Then, for each path, according to the formula Calculate the feasible speed of this path, and then use the formula Calculate the feasibility index, where is the feasibility index, For the The length of the segment path.

[0098] Continuing with the above embodiment, it is known that the cumulative terrain difficulty of a first target candidate path is Elderly care users The abnormal urgency level is medium (for example, the medium urgency level corresponds to an abnormal impact factor of 0.5). The length of the first flat path Meters, feasible speed ; Length of the second grass path Meters, feasible speed ; Length of the third sandy path Meters, feasible speed The feasibility index of this path .

[0099] Step 2073: Determine the path association degree between the path segment and each adjacent path based on the terrain change between the path segment and each adjacent path segment, and determine the path smoothness index based on the path association degree between the path segment and each adjacent path segment.

[0100] Furthermore, the difference score of the terrain change type is defined, for example, the difference score from flat land to grass is 1, and the difference score from flat land to sand is 2. For each path segment, the sum of the terrain change difference scores between it and the adjacent path segments is calculated, and the formula is used Calculate the path correlation, where For the Segment path and The path association of the segment path, For the Segment path and The path smoothness index is obtained by adding the path correlation of all adjacent path segments. .

[0101] Continuing with the above embodiment, for the first target candidate path containing three segments, the terrain change difference score from the first flat land segment to the second grass segment is , then the path correlation ; Difference score of terrain change from the second section of grassland to the third section of sand , path correlation The path smoothness index of the path .

[0102] Step 2074: Determine the comprehensive performance index based on the feasibility index and the path smoothness index.

[0103] Furthermore, through the formula Calculate the comprehensive performance index, where Comprehensive performance index is the feasibility index, is the path smoothness index. Continuing with the above embodiment, the feasibility index of the above path is known to be , path smoothness index , then the comprehensive performance index of the path .

[0104] Step 2075 , traverse the comprehensive performance index of each first target candidate path, and determine the first target candidate path with the largest comprehensive performance index as the first optimal service route.

[0105] Furthermore, the elderly care service robot calculates the comprehensive performance index of each first target candidate path in turn, compares these indexes, and selects the path with the largest comprehensive performance index value as the first optimal service route. Continuing with the above embodiment, there are three first target candidate paths, and the calculated path The comprehensive performance index is 253.33, and the path The comprehensive performance index is 200, the path The comprehensive performance index of the path is 230. By comparison, we can see that the path The comprehensive performance index of Determine the first optimal service route so that the elderly care service robot can follow this route to the elderly care user. Geographic location is checked.

[0106] The embodiment of the present invention introduces multi-dimensional evaluation indicators such as terrain difficulty coefficient, abnormal impact factor, and path correlation, and comprehensively considers the advantages and disadvantages of paths from aspects such as feasibility of passage and smoothness of terrain changes, so that it can more comprehensively adapt to the emergency situations and complex environmental conditions of different users. The planned first optimal service route can not only ensure the efficient passage of the robot, but also reduce the adverse effects of terrain changes, improve the stability of the robot operation and the service response efficiency, and provide more reliable service guarantees for elderly users.

[0107] In one embodiment, steps 401 to 405 are described as follows:

[0108] Step 401 : construct a service demand feature vector based on the service type and service duration, and spatially associate the geographical location with its own location information to construct a location association matrix.

[0109] Optionally, the elderly care service robot classifies and codes the service requirements. For example, "I want to play chess" belongs to the entertainment service type and is coded as 03. At the same time, the estimated service time is recorded, for example, 60 minutes. The service type code and service time are combined to form a service demand feature vector, such as For geographical location and self-location information, the longitude and latitude coordinates are used to express them. By calculating the spatial relationship between two points, such as the Euclidean distance and azimuth, a position correlation matrix is ​​constructed. For example, the robot's own position coordinates are The target user's geographic location coordinates are Then the position incidence matrix in is the distance between two points, is the azimuth.

[0110] In one embodiment, the position coordinates of the elderly care service robot are (Unit: m), elderly care users The geographic coordinates of (Unit: meter), the service demand is "I want to play chess", the service time is expected to be 60 minutes. The service demand feature vector . Calculate the positional association matrix:

[0111] ,

[0112] ,

[0113] Side position correlation matrix .

[0114] Step 402: Perform relationship mapping based on the service demand feature vector and the location association matrix to obtain an association mapping result. The association mapping result represents the information dimension association between different service demand features and location information.

[0115] Furthermore, the embodiment of the present invention uses the self-attention mechanism in deep learning to map the relationship between the service demand feature vector and the position association matrix. Therefore, the elderly care service robot takes the elements of the service demand feature vector and the position association matrix as input, and obtains the association mapping result by calculating the attention weights between different elements. For example, the service demand feature vector and position correlation matrix ,The attention weight is calculated by the attention formula, and the final association mapping result is a new matrix that integrates the service demand and location information, reflecting the association relationship between the two.

[0116] Continuing with the above embodiment, the service demand feature vector in step 401 is and position correlation matrix As input, after calculation by the self-attention mechanism, the association mapping result matrix is ​​obtained ,For example The elements in this matrix represent the degree of association between different service demand characteristics and location information.

[0117] Step 403: Determine the second initial candidate paths based on the association mapping result, and construct a route feature matrix based on the route features of each second initial candidate path. The route features include environmental complexity and service interference factors.

[0118] Furthermore, based on the association mapping results, a graph search algorithm is used to search for possible paths on the map to generate multiple second initial candidate paths, as shown in the process from step 4031 to step 4034. For each second initial candidate path, its environmental complexity (such as the number of obstacles in the path, the narrowness of the road, etc.) and service interference factors (such as whether it passes through a noisy area, whether there is frequent pedestrian interference, etc.) are evaluated. The environmental complexity and service interference factors are quantified into numerical values ​​to construct a route feature matrix. For example, the environmental complexity of a path is , the service interference factor is , then the route feature matrix

[0119] Continuing with the above embodiment, based on the association mapping result matrix obtained in step 402 , search on the map and get three second initial candidate paths .path Passing 3 obstacles, the road is narrow and the environment is complex ; Passing near a school, service interference factors , its route feature matrix Similarly, calculate the path and Route feature matrix and .

[0120] Step 404 : Screen each second initial candidate path based on the service demand feature vector and the route feature matrix to obtain a second target candidate path.

[0121] Furthermore, a matching rule is established between service cloud demand characteristics and route characteristics. For example, entertainment service demand has a high tolerance for environmental complexity but is more sensitive to service interference factors. By calculating the matching degree between the service demand feature vector and the route feature matrix, the second initial candidate path is screened. The matching degree calculation formula is: in are the elements of the service demand feature vector, 、 are the elements of the route feature matrix, It is the weight set according to service demand (such as in entertainment services, A matching threshold is set, and paths with matching degrees greater than the threshold are selected as candidate paths for the second target.

[0122] Continuing with the above example, for the path , its route feature matrix Service demand feature vector , calculate the matching degree according to the formula . Set the matching threshold to 0.3, Less than the threshold, Excluded; calculated similarly and The matching degree is greater than 0.3, and the paths with matching degree greater than 0.3 are screened as the second target candidate paths.

[0123] Step 405 : Screen the second target candidate paths based on the route difference and service urgency between any two paths in the second target candidate paths to obtain a second optimal service route.

[0124] Furthermore, the route difference between any two paths in the second target candidate path can be calculated by calculating the difference in the number of path nodes, the similarity of path shapes, etc. and , the route difference calculation formula is: ,in, is the number of nodes in the two paths, is the similarity of the shapes of the two paths (which can be calculated by shape matching algorithm), is the weight coefficient (such as Combined with the service urgency (for example, the service urgency of playing chess is 1, and the smaller the value, the less urgent it is), the path with the smallest route difference and meeting the service urgency requirements is selected as the second best service route.

[0125] Hormones have the above embodiments, for example, after screening, two second target candidate pathways are obtained and Number of nodes Number of nodes , calculate the shape similarity of the two paths through the shape matching algorithm Calculating route differences +0.5×(1-0.7)= +0.5×0.3≈0.17+0.15=0.32. Since the service urgency is low, the path with the smallest route difference is selected as the second best service route. If the value is smaller after comparison, It is determined to be the second best service route, and the robot follows this route to the elderly care user. Play chess.

[0126] The embodiment of the present invention constructs a service demand feature vector and a location association matrix, uses the self-attention mechanism for relationship mapping, and fully explores the potential connection between service demand and location information. It combines route feature screening and route difference calculation, and comprehensively considers multiple factors such as environmental complexity and service interference factors. It enables dynamic adjustment of path planning strategies according to different service types and urgency, and plans a second optimal service route that better meets service needs and takes into account both traffic efficiency and service quality, effectively improving the service accuracy and user experience of the elderly care service robot.

[0127] In one embodiment, steps 4031 to 4034 are described as follows:

[0128] Step 4031 , using the own location as the starting node and the geographical location as the ending node, the node connection relationship between each node in space is determined based on the information dimension association in the association mapping result.

[0129] Optionally, the elderly care service robot abstracts its own location and the target user's geographic location as nodes in a graph structure, with its own location as the starting node. , the target user's geographic location is used as the end node . The association mapping result reflects the association between service demand characteristics and location information. Based on this association information, the robot analyzes the potential connections between nodes at different locations on the map. For example, if the association mapping result shows that the demand for entertainment services is highly correlated with locations such as parks and leisure squares, then when building node connection relationships, priority will be given to establishing connections between these location nodes and the starting and ending nodes. By calculating factors such as the spatial distance between nodes and path accessibility, it is determined whether there are connecting edges between nodes and the weight of the connecting edges (for example, nodes with close distances have low connecting edge weights, indicating that they are easier to pass). Set the node and nodes The spatial distance between like Less than the preset threshold , and the path is unobstructed, then at node and nodes Establish a connection edge between them, weight

[0130] Continuing with the above embodiment, the position coordinates of the elderly care service robot itself are (Unit: meter), as the starting node Elderly care users The geographic coordinates of , as the end node The association mapping results show that the entertainment service demand of "I want to play chess" is related to the nearby community activity center (coordinates (30, 30), node and Park (coordinates (40, 40), node The correlation is high. Calculate the distance between nodes:

[0131] ;

[0132] ;

[0133] ;

[0134] .

[0135] For example, the preset threshold meters, and these paths are free of obstacles, then at node and and and and Connect edges are established between them, and the weights are .

[0136] Step 4032 , starting from the starting node, adjacent nodes are explored in sequence based on the spatial proximity of node connection relationships between the nodes in space until the end node is reached, thereby generating an initial service route.

[0137] Furthermore, the robot uses the depth-first search (DFS) or breadth-first search (BFS) algorithm to explore adjacent nodes starting from the starting node according to the node connection relationship and spatial proximity (preferentially selecting adjacent nodes with small connection edge weights, that is, nodes that are close). During the exploration process, the order of the nodes passed is recorded to form a path. When the end node is searched, the search stops and the path is the initial service route. Taking the depth-first search as an example, the robot starts from the starting node and continues to search. Departure, check out The node with the smallest weight among the connected nodes is assumed to be node , then move to the node , and then from the node Set out to find Connect the nodes with the smallest weight among the nodes that have not been visited until the end node is reached Record the node sequence passed, such as This is the initial service route generated.

[0138] Continuing with the above embodiment, based on the node connection relationship, the elderly care service robot starts from the starting node Starting from, use the depth-first search algorithm. Connected nodes and middle Less than , so move to node first From the node Departure, with The only connected and unvisited nodes are , so move to the end node , the generated initial service route is .

[0139] Step 4033 : At each target node of each route in the initial service route, check whether there are other nodes that have not been explored and are associated with the association mapping result.

[0140] The robot then traverses each node (target node) in the initial service route. For each target node, the robot checks the map based on the association mapping results to see if there are any other nodes on the map that have not yet been explored and are associated with the current service demand (reflected by the association mapping results). For example, if the association mapping results show that the demand for entertainment services is related to certain leisure venues, the robot will check whether the nodes corresponding to these types of venues on the map have not yet been explored.

[0141] Continuing with the above example, for the initial service route The robot first checks the starting node ,According to the association mapping results, it is found that although the connected Node, but there is also a park node Unexplored and related to the entertainment service demand of "I want to play chess"; then check the node , also found the node Unexplored and relevant; check the endpoint , no unexplored and relevant nodes were found.

[0142] Step 4034: If it exists, the target node starts and explores new path branches according to the steps of generating the initial service route to generate a second initial candidate path.

[0143] Furthermore, if other unexplored nodes associated with the association mapping result are found in step 4033, the robot uses the target node as a new starting point and again uses a depth-first search or breadth-first search algorithm based on node connectivity, exploring new path branches in the same manner as the initial service route generated in step 4032. During the exploration process, new node sequences are recorded to form new paths, which become the second initial candidate paths.

[0144] Continuing with the above embodiment, since it is found in step 4033 that the slave node and nodes Starting from, there are unexplored and relevant nodes From the node Start by moving to node 1 according to the depth-first search algorithm. , and then from the node Move to the end node , generate a new path Slave nodes Start by moving to the node , and then to the node , generating a path These two paths and This is the second initial candidate path generated.

[0145] The embodiment of the present invention constructs a node connection relationship based on the association mapping result, generates an initial service route using a search algorithm, and explores new path branches on this basis. It can comprehensively mine multiple potential paths that meet service needs, fully considering the relationship between service needs and geographical locations, as well as the actual traffic conditions in the environment. The generated second initial candidate path is more in line with the actual service scenario needs, providing rich and high-quality path selection for the subsequent screening of the optimal service route, improving the flexibility and adaptability of the robot path planning, and helping to improve the efficiency and quality of elderly care services.

[0146] The following describes the elderly care service robot control device based on wearable device collaboration provided by the present invention. The elderly care service robot control device based on wearable device collaboration described below and the elderly care service robot control method based on wearable device collaboration described above can be referenced to each other.

[0147] Optional, see Figure 2 , Figure 2 This is a structural schematic diagram of the elderly care service robot control device based on the collaboration of wearable devices provided by the present invention. The wearable device integrates a positioning module, a physiological parameter monitoring module, a voice interaction module and a wireless communication module; a wireless communication receiving device of the corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot; the elderly care service robot control device based on the collaboration of wearable devices includes.

[0148] The receiving module 210 is configured to receive a service instruction sent by the wearable device; the service instruction carries the target user's geographic location, physiological parameters, and voice instructions;

[0149] The first service control module 220 is configured to, if it is determined based on the service instruction that the target user is in an abnormal state, perform path planning based on the geographic location, physiological parameters, and the elderly care service robot's own position to obtain a first optimal service route, and control the elderly care service robot to travel to the geographic location along the first optimal service route to examine the target user;

[0150] The semantic recognition module 230 is configured to perform semantic recognition on the voice command to determine the service requirements of the target user if it is determined based on the service command that the target user is in an abnormal state;

[0151] A route planning module 240 is used to plan a route based on the geographic location, service demand, and the user's own location to obtain a second optimal service route;

[0152] The second service control module 250 is used to control the elderly care service robot to travel to the geographical location along the second optimal service route to perform corresponding services according to service requirements.

[0153] By equipping users with wearable devices, this embodiment of the present invention enables them to transmit their location, physiological status, and service needs to robots in real time, whether indoors or outdoors. This ensures timely elderly care services. Furthermore, the information collected by wearable devices transcends the coverage limitations of traditional sensor networks, enabling elderly care robots to obtain real-time information about users at any location. This information, combined with physiological parameters and service needs, helps them plan routes, ensuring that the robots can provide effective services in a variety of complex scenarios, thereby ensuring service effectiveness.

[0154] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0155] Receive service instructions sent by the wearable device; the service instructions carry the target user's geographic location, physiological parameters and voice instructions;

[0156] If the target user is determined to be in an abnormal state based on the service instruction, a path planning is performed based on the geographic location, physiological parameters, and the elderly care service robot's own position to obtain a first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to inspect the target user;

[0157] If the target user is determined to be in a normal state based on the service instruction, semantic recognition is performed on the voice instruction to determine the service needs of the target user;

[0158] Path planning is performed based on geographic location, service demand, and own location to obtain the second best service route;

[0159] The elderly care service robot is controlled to travel to the geographical location along the second optimal service route to perform corresponding services according to service requirements.

[0160] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0161] Receive service instructions sent by the wearable device; the service instructions carry the target user's geographic location, physiological parameters and voice instructions;

[0162] If the target user is determined to be in an abnormal state based on the service instruction, a path planning is performed based on the geographic location, physiological parameters, and the elderly care service robot's own position to obtain a first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to inspect the target user;

[0163] If the target user is determined to be in a normal state based on the service instruction, semantic recognition is performed on the voice instruction to determine the service needs of the target user;

[0164] Path planning is performed based on geographic location, service demand, and own location to obtain the second best service route;

[0165] The elderly care service robot is controlled to travel to the geographical location along the second optimal service route to perform corresponding services according to service requirements.

[0166] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the control method of the elderly care service robot based on wearable device collaboration provided by the above methods, which includes:

[0167] Receive service instructions sent by the wearable device; the service instructions carry the target user's geographic location, physiological parameters and voice instructions;

[0168] If the target user is determined to be in an abnormal state based on the service instruction, a path planning is performed based on the geographic location, physiological parameters, and the elderly care service robot's own position to obtain a first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to inspect the target user;

[0169] If the target user is determined to be in a normal state based on the service instruction, semantic recognition is performed on the voice instruction to determine the service needs of the target user;

[0170] Path planning is performed based on geographic location, service demand, and own location to obtain the second best service route;

[0171] The elderly care service robot is controlled to travel to the geographical location along the second optimal service route to perform corresponding services according to service requirements.

[0172] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0173] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A control method for an elderly care service robot based on wearable device collaboration, characterized in that: The wearable device integrates a positioning module, a physiological parameter monitoring module, a voice interaction module, and a wireless communication module; a wireless communication receiving device of a corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot; the method includes: Receiving a service instruction sent by the wearable device; the service instruction carries the geographic location, physiological parameters and voice instruction of the target user; If it is determined based on the service instruction that the target user is in a normal state, path planning is performed based on the geographic location, the physiological parameters, and the location of the elderly care service robot to obtain a first optimal service route, and the elderly care service robot is controlled to travel to the geographic location along the first optimal service route to examine the target user; If it is determined based on the service instruction that the target user is in an abnormal state, semantic recognition is performed on the voice instruction to determine the service needs of the target user; Performing path planning based on the geographic location, the service demand, and the own location to obtain a second optimal service route; The elderly care service robot is controlled to travel to the geographical location along the second optimal service route to perform corresponding services according to the service requirements.

2. The control method of the elderly care service robot based on wearable device collaboration according to claim 1 is characterized in that: The performing path planning based on the geographical location, the physiological parameters, and the position of the elderly care service robot to obtain a first optimal service route includes: determining an abnormality urgency based on the physiological parameters; Based on the polar coordinate ray method, a plurality of first initial candidate paths are generated with the own position as the starting point and the geographical location as the end point; the path turning point in the path is the intersection point of the ray and the environmental obstacle; Screening each first initial candidate path based on the abnormal urgency and the number of turning points in each first initial candidate path to obtain a first target candidate path; Path planning is performed based on the terrain type between the turning points in each first target candidate path, the operating capability of the elderly care service robot in different terrains, and the degree of abnormal urgency to obtain the first optimal service route.

3. The control method of the elderly care service robot based on wearable device collaboration according to claim 2 is characterized in that: The performing of path planning based on the terrain type between the turning points in each first target candidate path, the operating capability of the elderly care service robot in different terrains, and the degree of emergency of the abnormality to obtain the first optimal service route includes: For each first target candidate path, calculate the terrain difficulty coefficient of each path segment based on the terrain type between its path turning points and the operating ability of the elderly care service robot in different terrains, and determine the cumulative terrain difficulty based on the terrain difficulty coefficient of each path segment; Based on the cumulative terrain difficulty and the urgency of the abnormality, determine the abnormality impact factor of the abnormality, and calculate the feasibility index based on the abnormality impact factor and the operating ability of the elderly care service robot in each section of the path; Determine the path association degree between the path segment and each adjacent path based on the terrain changes between the path segment and each adjacent path, and determine the path smoothness index based on the path association degree between the path segment and each adjacent path; Determine its comprehensive performance index based on feasibility index and path smoothness index; The comprehensive performance index of each first target candidate path is traversed, and the first target candidate path with the largest comprehensive performance index is determined as the first optimal service route.

4. The control method of the elderly care service robot based on wearable device collaboration according to claim 1 is characterized in that: The service requirements include service type, service duration and service urgency; The performing path planning based on the geographical location, the service demand, and the own location to obtain a second optimal service route includes: constructing a service demand feature vector based on the service type and the service duration, and spatially correlating the geographical location with the own location information to construct a location correlation matrix; Performing relationship mapping based on the service demand feature vector and the location association matrix to obtain an association mapping result; the association mapping result represents the information dimension association between different service demand features and location information; Determining a second initial candidate path based on the association mapping result, and constructing a route feature matrix based on the route features of each second initial candidate path; the route features include environmental complexity and service interference factors; Screening each second initial candidate path based on the service demand feature vector and the route feature matrix to obtain a second target candidate path; The second target candidate paths are screened based on the route difference between any two paths in the second target candidate paths and the service urgency to obtain the second optimal service route.

5. The control method of the elderly care service robot based on wearable device collaboration according to claim 4 is characterized in that: The determining a second initial candidate path based on the association mapping result includes: Taking the own location as the starting node and the geographical location as the ending node, determining the node connection relationship between the nodes in space based on the information dimension association in the association mapping result; Starting from the starting node, adjacent nodes are explored in sequence based on the spatial proximity of node connection relationships between the nodes until the end node is reached, thereby generating an initial service route; At each target node of each route in the initial service route, checking whether there are other nodes that have not been explored and are associated with the association mapping result; If so, the target node starts out and explores new path branches according to the steps of generating the initial service route to generate the second initial candidate path.

6. The control method of the elderly care service robot based on wearable device collaboration according to any one of claims 1 to 5, characterized in that: The specific steps of determining whether the target user is in an abnormal state based on the service instruction include: Performing area judgment based on the geographical location to determine whether the target user is within a preset safe activity area; If the target user is outside the safe activity area, determining that the target user is in an abnormal state; if the target user is within the safe activity area, performing a physiological state detection based on the physiological parameters to determine whether the physiological state of the target user is normal; If the physiological state is in an abnormal state, it is determined that the target user is in an abnormal state; if the physiological state is in a normal state, it is determined that the target user is in a normal state.

7. The control method of the elderly care service robot based on wearable device collaboration according to claim 6 is characterized in that: The physiological parameters include heart rate parameters, systolic blood pressure parameters, diastolic blood pressure parameters and body temperature parameters; The performing physiological state detection based on the physiological parameters to determine whether the physiological state of the target user is normal includes: Determining a floating range of each physiological parameter based on a historical baseline of each physiological parameter of the target user within a preset historical window time; Determining a correlation degree deviation value based on a deviation between a first parameter correlation degree of each physiological parameter of the target user in a normal state and a second parameter correlation degree of each physiological parameter at a current time; performing deviation correction on the current parameter values ​​corresponding to the respective physiological parameters at the current time based on the correlation degree deviation value to obtain a corrected parameter value, and determining a parameter deviation value based on the current parameter values ​​corresponding to the respective physiological parameters at the current time and a parameter historical baseline of the respective physiological parameters; If the corrected parameter values ​​of each physiological parameter are all within the corresponding parameter floating range, and the parameter deviation values ​​are all less than the preset deviation threshold, it is determined that the physiological state of the target user is in a normal state; If at least one of the corrected parameter values ​​of each physiological parameter is outside the corresponding parameter floating range, or / and at least one parameter deviation value is greater than or equal to a preset deviation threshold, it is determined that the physiological state of the target user is in an abnormal state.

8. A control device for an elderly care service robot based on collaboration with wearable devices, characterized in that: The wearable device integrates a positioning module, a physiological parameter monitoring module, a voice interaction module, and a wireless communication module; a wireless communication receiving device of a corresponding frequency band is installed on the elderly care service robot to establish a communication connection between the wearable device and the elderly care service robot; the device includes: A receiving module, configured to receive a service instruction sent by the wearable device; the service instruction carries the target user's geographic location, physiological parameters, and voice instructions; a first service control module, configured to, if it is determined based on the service instruction that the target user is in an abnormal state, perform path planning based on the geographic location, the physiological parameters, and the position of the elderly care service robot to obtain a first optimal service route, and control the elderly care service robot to travel to the geographic location along the first optimal service route to inspect the target user; a semantic recognition module, configured to perform semantic recognition on the voice instruction to determine the service requirements of the target user if it is determined based on the service instruction that the target user is in an abnormal state; a route planning module, configured to perform route planning based on the geographic location, the service demand, and the own location to obtain a second optimal service route; The second service control module is used to control the elderly care service robot to travel to the geographical location along the second optimal service route to perform corresponding services according to the service requirements.

9. An electronic device comprising: Memory for storing computer software programs; A processor for reading and executing the computer software program, characterized in that when the processor executes the computer software program, it implements the elderly care service robot control method based on wearable device collaboration as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer software program, wherein: When the computer software program is executed by the processor, the elderly care service robot control method based on wearable device collaboration as described in any one of claims 1 to 7 is implemented.

Images