Robot Communication Method and Device, and Healthcare Robot

Abstract

The present disclosure provides a robot communication method, a device, and a medical and elderly care robot, belonging to the technical field of robot communication. The method includes: determining the comprehensive complexity of target text information; in response to the comprehensive complexity of the target text information being less than a first threshold, extracting features of the target text information based on a first processor to obtain the status information of a target person, and sending the status information to a target device; in response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmitting the target text information and its corresponding identification information to a second processor based on a target policy, where the identification information is used to instruct the second processor to extract features of the target text information to obtain the status information of the target person, and sending the status information to the target device. The robot communication method, device, and medical and elderly care robot provided by the present disclosure can improve the quality and efficiency of medical and elderly care services.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of robot communication, and more specifically, relates to a robot communication method and apparatus, and a medical and elderly care robot. Background Art

[0002] In the fields of medical care and elderly care, medical and elderly care robots are playing an increasingly important role. They can conduct voice interactions with target personnel and assist medical staff and elderly care service providers in their work. However, the existing communication methods for medical and elderly care robots have certain limitations. Existing robots adopt a single processing mode, and regardless of the complexity of voice information, it will be processed by the local processor. For complex voice information, the local processor may not be able to accurately analyze and process it, resulting in the inability to timely and accurately obtain the status information of the target personnel. This makes it difficult for family members and caregivers to understand the situation of the target personnel in a timely and comprehensive manner, affecting the quality and efficiency of medical care and elderly care services. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a robot communication method and apparatus, and a medical and elderly care robot, so as to improve the quality and efficiency of medical care and elderly care services.

[0004] In a first aspect of an embodiment of the present disclosure, a robot communication method is provided, including:

[0005] Determine the comprehensive complexity of target text information, where the target text information is the text information obtained by converting the audio information of a target person;

[0006] In response to the comprehensive complexity of the target text information being less than a first threshold, perform feature extraction on the target text information based on a first processor to obtain the status information of the target person, and send the status information to a target device;

[0007] In response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmit the target text information and its corresponding identification information to a second processor based on a target policy, where the identification information is used to instruct the second processor to perform feature extraction on the target text information to obtain the status information of the target person, and send the status information to the target device;

[0008] The first processor is a processor provided inside the medical and elderly care robot, and the second processor is a processor provided in the cloud.

[0009] In a second aspect of an embodiment of the present disclosure, a robot communication apparatus is provided, including:

[0010] A complexity calculation module, configured to determine the comprehensive complexity of target text information, where the target text information is the text information obtained by converting the audio information of a target person;

[0011] The first communication processing module is configured to, in response to the comprehensive complexity of the target text information being less than the first threshold, extract features of the target text information based on the first processor to obtain the status information of the target person, and send the status information to the target device;

[0012] The second communication processing module is configured to, in response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmit the target text information and its corresponding identification information to the second processor based on the target policy, where the identification information is used to instruct the second processor to extract features of the target text information to obtain the status information of the target person, and send the status information to the target device;

[0013] The first processor is a processor provided inside the medical care robot, and the second processor is a processor provided in the cloud.

[0014] In a third aspect of the embodiments of the present disclosure, a medical care robot is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned robot communication method are implemented.

[0015] The beneficial effects of the robot communication method, device, and medical care robot provided by the embodiments of the present disclosure are as follows: By determining the comprehensive complexity of the target text information and adopting different processing strategies, the embodiments of the present disclosure achieve efficient utilization of resources. For texts with low complexity, they are processed by the first processor inside the medical care robot, reducing the time and resource consumption of communication with the cloud, quickly obtaining the status information of the target person and sending it to the target device, improving the response speed. For texts with high complexity, relying on the powerful computing power and rich data resources of the second processor in the cloud, more accurate and in-depth analysis can be performed, ensuring the accuracy of status information extraction in complex situations. Secondly, the task allocation mechanism of the embodiments of the present disclosure enhances the adaptability and flexibility of the system, can handle voice interactions of different difficulties, improves the service quality and reliability of the medical care robot, enables family members and caregivers to timely and accurately understand the status of the target person, and better provides medical and elderly care services. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic flowchart of the robot communication method provided by an embodiment of the present disclosure;

[0018] Figure 2 Block diagram of a robot communication device provided by an embodiment of the present disclosure;

[0019] Figure 3 Schematic diagram of a medical and elderly care robot provided by an embodiment of the present disclosure. Detailed implementation manners

[0020] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0021] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0022] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a robot communication method provided by an embodiment of the present disclosure. The method is applied to a medical and elderly care robot and includes:

[0023] S101: Determine the comprehensive complexity of the target text information, where the target text information is the text information obtained by converting the audio information of the target person.

[0024] A medical and elderly care robot is an intelligent robot that integrates medical and elderly care service functions. It can assist medical staff and elderly care service providers in medical and elderly care scenarios to provide users with comprehensive and personalized health management and life care services.

[0025] The target person refers to the object that conducts voice interaction with the medical and elderly care robot. It can be people in elderly care institutions, receiving home elderly care services, or rehabilitating in medical institutions, such as the elderly, disabled, and patients with chronic diseases; or people who want to learn medical knowledge and health advice.

[0026] The comprehensive complexity of the target text information is a comprehensive index that measures the complexity of a text converted from the audio information of the target person. The comprehensive index can include, but is not limited to, the following dimensions:

[0027] Lexical complexity, which represents the difficulty and professionalism of the vocabulary used in the target text information;

[0028] Syntactic complexity, which represents the complexity of the sentence structure in the target text information;

[0029] Semantic complexity refers to the degree of abstraction of the meaning expressed in the target text information, the complexity of logical relationships, and the number of involved fields.

[0030] In this embodiment, the medical care robot can obtain the audio information emitted by the target person through an audio acquisition device such as a microphone. Based on speech recognition technology, these audio information are converted into text form to obtain the target text information.

[0031] To determine the comprehensive complexity of the target text information, it is possible to comprehensively consider multiple dimensions of the target text information. For example, if the target text information contains a large number of professional medical terms, complex sentence structures, and knowledge in multiple different fields, the comprehensive complexity of the target text information will be relatively high; conversely, if the target text information is just a simple expression of daily language, the complexity will be relatively low.

[0032] S102: In response to the comprehensive complexity of the target text information being less than the first threshold, based on the first processor, feature extraction is performed on the target text information to obtain the status information of the target person, and the status information is sent to the target device. The first processor is a processor set inside the medical care robot.

[0033] The first threshold is a preset value, representing a boundary of the comprehensive complexity; the comprehensive complexity of the target text information is compared with the first threshold, and the processing strategy to be adopted is determined based on the comparison result.

[0034] In this embodiment, when the comprehensive complexity of the target text information is less than the first threshold, it indicates that the target text information is relatively simple, and the first processor set inside the medical care robot has the ability to process it. The first processor can perform feature extraction on the target text information, specifically including identifying keywords or phrases related to the status of the target person in the target text information, so as to obtain the status information of the target person.

[0035] After completing the feature extraction, the first processor obtains the status information of the target person. Subsequently, through the communication module of the medical care robot, the status information is sent to the target device according to a preset communication protocol (such as Wi-Fi, Bluetooth, 4G / 5G, etc.). The target device can be a terminal device such as a mobile phone, tablet computer, or smart bracelet of a family member or caregiver, so that they can timely understand the status of the target person.

[0036] For example, if the target text information is "I feel a little headache today", the first processor can determine through feature extraction that the current status of the target person is headache. Finally, the first processor sends the extracted status information to the target device, enabling family members, caregivers, etc. to timely understand the status of the target person.

[0037] S103: In response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmit the target text information and its corresponding identification information to the second processor based on the target policy. The identification information is used to instruct the second processor to perform feature extraction on the target text information to obtain the status information of the target person, and send the status information to the target device. The second processor is the processor set in the cloud.

[0038] In this embodiment, if the comprehensive complexity of the target text information is greater than or equal to the first threshold, it indicates that the target text information is relatively complex and exceeds the processing capacity range of the first processor. At this time, the medical and elderly care robot can transmit the target text information and its corresponding identification information to the second processor set in the cloud based on the target policy. The target policy can comprehensively consider various factors, such as network conditions (bandwidth, latency, stability), data volume size, transmission cost, etc., to select the optimal transmission path and method. The identification information contains the key attributes of the target text information, such as text source, generation time, category, etc., and is used to instruct the second processor to process the target text information based on the identification information.

[0039] After receiving the target text information and the identification information, the second processor performs feature extraction on the target text information according to the indication of the identification information, with computing power superior to that of the first processor and rich data resources. The cloud may have more advanced natural language processing models, large-scale knowledge bases, and professional medical knowledge graphs, which can conduct in-depth analysis and understanding of complex texts, so as to more accurately extract the status information of the target person. After the second processor completes the feature extraction and obtains the status information of the target person, it also sends the status information to the target device through network communication. During the sending process, it will follow the same or compatible communication protocol as the first processor to ensure that the status information can reach the target device accurately and without error.

[0040] Exemplarily, in a warm nursing home, a medical and elderly care robot is configured. The old person A anxiously said to the little nurse in the room: "I've been feeling very flustered recently and always having trouble sleeping at night. I've had a history of heart disease before. Could this be a recurrence of the old problem?" After the medical and elderly care robot obtains the audio and converts it into text, it analyzes and finds that the text contains professional terms such as "flustered", "insomnia", and "history of heart disease", the sentence structure is relatively complex and involves medical field knowledge, and the comprehensive complexity is greater than the first threshold. The medical and elderly care robot transmits the text and the identification information to the second processor in the cloud through the 4G network based on the target policy considering factors such as network bandwidth and stability. Relying on the advanced natural language processing model and medical knowledge graph in the cloud, it accurately judges that Grandma Li may have a recurrence of heart disease and promptly sends this status information to the doctor's tablet. The doctor quickly rushes to Grandma Li's room for examination and treatment, avoiding the deterioration of the condition.

[0041] As can be seen from the above, in this embodiment, by determining the comprehensive complexity of the target text information and adopting different processing strategies, the efficient utilization of resources is achieved. For texts with low complexity, they are processed by the first processor inside the medical and elderly care robot, reducing the time and resource consumption of communicating with the cloud. The target personnel's status information can be quickly obtained and sent to the target device, improving the response speed. For texts with high complexity, with the help of the powerful computing power and rich data resources of the second processor in the cloud, more accurate and in-depth analysis can be carried out, ensuring the accuracy of extracting status information in complex situations. Secondly, the task allocation mechanism in this embodiment enhances the adaptability and flexibility of the system, can handle voice interactions of different difficulties, improves the service quality and reliability of the medical and elderly care robot, enables family members and caregivers to understand the status of the target personnel in a timely and accurate manner, and better provides medical and elderly care services.

[0042] In an embodiment of the present disclosure, determining the comprehensive complexity of the target text information includes:

[0043] Extract feature information from the audio information of the target personnel to obtain target audio feature information;

[0044] Conduct semantic analysis on the target text information to obtain target semantic information;

[0045] Determine the communication type between the target personnel and the medical and elderly care robot based on the target text information;

[0046] Allocate first weights to the target audio feature information and the target semantic information respectively based on the communication type;

[0047] Perform weighted fusion on the first weights to obtain the comprehensive complexity of the target text information.

[0048] In this embodiment, the audio information contains clues about the expression state of the target personnel, and different audio features reflect the complexity of the text information. For example, too fast speech speed means that the target personnel wants to express more and urgently, and the text complexity may be higher.

[0049] Audio processing technology can be used to extract the speech speed, intonation, volume, pause frequency, etc. in the audio information. For example, the speech speed is determined by calculating the time interval between adjacent speech frames in the audio; the intonation information is obtained by analyzing the frequency and amplitude changes of the audio. Combine these extracted features to form the target audio feature information.

[0050] In this embodiment, semantic analysis can help understand the meaning expressed by the target text information, the relationships between concepts, and the logical structure, etc.

[0051] Part-of-speech tagging, syntactic analysis, named entity recognition, semantic role labeling, etc. can be performed on the target text information. For example, through part-of-speech tagging, the distribution of different parts of speech in the text can be understood. Complex texts may contain more professional terms and complex vocabulary. Through syntactic analysis, the structural complexity of the sentence can be determined, such as whether there is a nested structure. Integrate the analysis results to obtain the target semantic information.

[0052] In this embodiment, different communication types have different complexity characteristics. For example, communication in the medical consultation category involves professional medical knowledge and complex symptom descriptions, so the complexity is relatively high. While communication in the daily greeting category is usually relatively simple.

[0053] The target text information can be classified through preset classification rules. The preset rules can be defined based on keywords, sentence patterns, etc. in the text. For example, if the text contains keywords such as "symptom" and "treatment method", it indicates communication in the medical consultation category.

[0054] In this embodiment, under different communication types, the influence degrees of audio features and semantic information on text complexity are different. For example, in emergency assistance communication, audio features can better reflect the complexity of the text. While in academic communication, semantic information is more important. Therefore, by assigning different weights to audio feature information and semantic information according to the communication type, these two aspects of factors can be more reasonably considered comprehensively.

[0055] Corresponding weight assignment rules can be preset for different communication types based on experience. For example, for medical consultation communication, a higher weight is assigned to the target semantic information because professional medical knowledge and symptom descriptions are the keys to this type of communication. While for emotional expression communication, a higher weight is assigned to the target audio feature information because intonation, tone, etc. in the audio can better reflect the complexity of emotions. According to the determined communication type, select the corresponding weight from the preset rules and assign it to the target audio feature information and the target semantic information respectively.

[0056] In this embodiment, through weighted fusion, the target audio feature information and the target semantic information can be combined to form a comprehensive complexity index. In this way, factors from both the audio and semantic aspects can be considered comprehensively, so as to more comprehensively and accurately reflect the complexity of the target text information.

[0057] The target audio feature information and the target semantic information can be multiplied by their corresponding first weights respectively, and then the products are added together to obtain the comprehensive complexity of the target text information.

[0058] It can be concluded from the above that in this embodiment, by extracting the target audio feature information and performing semantic analysis, the text complexity is comprehensively considered from both aspects of audio and text semantics. By assigning weights in combination with the communication type, it can more accurately reflect the influence of various factors on the complexity in different communication scenarios. The comprehensive complexity obtained by weighted fusion is more in line with the actual situation, improving the efficiency and accuracy of the medical care robot in processing voice information.

[0059] In an embodiment of the present disclosure, weighted fusion is performed on the first weight to obtain the comprehensive complexity of the target text information, including:

[0060] Based on the first formula, weighted fusion is performed on the first weight to obtain the comprehensive complexity of the target text information;

[0061] The first formula is:

[0062]

[0063] Wherein, represents the comprehensive complexity of the target text information, is the value mapped by the communication type between the target person and the medical care robot, represents the maximum value of the mapped values in all communication types, represents the target audio feature information, represents the first weight corresponding to the target audio feature information, represents the first weight corresponding to the target semantic information, represents the target semantic information, represents the non-linear adjustment index, represents the information timeliness factor.

[0064] In this embodiment, represents the influence of the communication type on the comprehensive complexity, and different communication types (such as daily greetings, medical consultations, emergency assistance, etc.) correspond to different values. is the maximum value of the mapped values in all communication types, which is used to normalize the influence of the communication type. Under different communication types, the importance and complexity of the target audio feature information and the target semantic information are different. For example, in the communication type of emergency assistance, the complexity and importance of both the audio feature and the semantic information will increase. Through this factor, the influence degree of the audio feature and the semantic information on the comprehensive complexity can be amplified or reduced according to the specific communication type.

[0065] and respectively perform weighted summation on the target audio feature information and the target semantic information, and Reflects the relative importance of audio features and semantic information in the comprehensive complexity calculation, which is pre-allocated according to different communication types. Nonlinear adjustment index The introduction of When it can strengthen the influence of high eigenvalues on the comprehensive complexity, that is, the larger the eigenvalue, the greater its contribution to the comprehensive complexity; when

[0066] In the medical care scenario, the timeliness of information is very important. The latest information can often more accurately reflect the current state of the target person. When the information timeliness is strong ( close to 1), the comprehensive complexity calculation result will relatively decrease because the latest information is more reliable, reducing the uncertainty brought by outdated information; conversely, when the information is outdated, close to 0, the comprehensive complexity calculation result will relatively increase, and the target text information needs to be processed more carefully.

[0067] It can be concluded from the above that this embodiment comprehensively considers the communication type, audio and semantic information, and information timeliness. The nonlinear adjustment index enhances the flexibility of the eigenvalue influence, can more accurately reflect the text complexity, provides a more reliable basis for the subsequent processing of the medical care robot, and improves the pertinence and efficiency of the service.

[0068] In an embodiment of the present disclosure, it further includes:

[0069] Determine the threshold adjustment step based on the deviation between the comprehensive complexity and the standard threshold and the resource status of the first processor;

[0070] Adjust the standard threshold based on the threshold adjustment step to obtain the first threshold.

[0071] In this embodiment, the standard threshold is an ideal reference value preset in the scenario where the medical care robot processes the target text information, used to judge whether the target text information should be processed by the first processor inside the medical care robot or transmitted to the second processor in the cloud. However, in actual use, due to the continuous change of the complexity of the target text information and the unstable resource status of the first processor, it is difficult for the standard threshold to accurately adapt to all situations, so there will be a certain error. Therefore, it is necessary to dynamically adjust it in combination with the actual deviation of the comprehensive complexity and the resource status of the first processor to obtain a first threshold that better meets the actual processing requirements.

[0072] In this embodiment, the calculated comprehensive complexity and the standard threshold Make a comparison and calculate the difference:

[0073]

[0074] A positive deviation indicates that the comprehensive complexity is higher than the standard threshold, meaning that the current text information may be more complex than expected; a negative deviation indicates that the comprehensive complexity is lower than the standard threshold, that is, the text information is relatively simple.

[0075] The resource status of the first processor can include multiple aspects such as CPU usage rate and memory occupancy rate. The resource status of the first processor can intuitively reflect the current load situation and processing capacity of the first processor. For the convenience of calculation, the resource status of the first processor can be quantified into a specific index R. For example, it can be represented by the percentage of resource utilization, and the value range is , the larger the value, the more tense the resources of the first processor and the more limited the processing capacity.

[0076] In this embodiment, the threshold adjustment step size can be calculated by weighted calculation, expressed as:

[0077]

[0078] Among them, represents the threshold adjustment step size, represents the weight coefficient corresponding to the deviation between the comprehensive complexity and the standard threshold, represents the weight coefficient corresponding to the resource status of the first processor.

[0079] Adjust the standard threshold accordingly according to the determined threshold adjustment step size. If the threshold adjustment step size is positive, it means that the first threshold needs to be increased so as to allocate more complex text information to the second processor in the cloud for processing and reduce the burden on the first processor; if the threshold adjustment step size is negative, the first threshold needs to be decreased to allow the first processor to process more relatively simple text information and make full use of its resources.

[0080] It can be concluded from the above that in this embodiment, by comprehensively considering the deviation between the comprehensive complexity and the standard threshold and the resource status of the first processor, the threshold adjustment step size is dynamically determined and the standard threshold is adjusted, so as to obtain a first threshold that is more in line with the actual situation. This dynamic adjustment mechanism enables the medical and elderly care robot to flexibly allocate processing tasks according to real-time situations, avoids the limitations of fixed thresholds in complex and changeable actual scenarios, and improves the processing efficiency and adaptability of the system.

[0081] In an embodiment of the present disclosure, based on the first processor, feature extraction is performed on the target text information to obtain the status information of the target person, and the status information is sent to the target device, including:

[0082] Extract the keywords from the target text information;

[0083] Match the keywords with the nodes in the knowledge graph to obtain the status information of the target person;

[0084] Send the status information to the target device.

[0085] In this embodiment, a keyword is a word or phrase with core meaning in the text that can summarize the main content of the text. By extracting keywords, complex text information can be simplified, focusing on the key content, providing a basis for subsequent analysis and processing.

[0086] The keywords in the target text information can be extracted based on the term frequency-inverse document frequency (TF-IDF) algorithm. By calculating the frequency of each word in the text and its inverse document frequency in the entire corpus, its importance is evaluated. Words with high frequency and low frequency in other documents are more likely to be selected as keywords.

[0087] In this embodiment, a knowledge graph is a structured semantic network that can represent various entities (such as diseases, symptoms, treatment methods, etc.) and the relationships between them (such as causal relationships, treatment relationships, etc.) in the form of a graph. Each entity corresponds to a node in the knowledge graph, and the relationship corresponds to the edge between the nodes. By matching the extracted keywords with the nodes in the knowledge graph, the rich knowledge and association information in the knowledge graph can be used to infer the status information of the target person.

[0088] Find the nodes in the knowledge graph that match the extracted keywords. If a keyword directly corresponds to a certain node in the knowledge graph, the information represented by the node and other related node information can be directly obtained.

[0089] For example, if the keyword is "cough", after finding the "cough" node in the knowledge graph, the disease information related to cough (such as cold, pneumonia, etc.), possible causes, and corresponding treatment suggestions can be further obtained. If the keyword does not exactly match the node in the knowledge graph but has semantic associations, the semantic reasoning mechanism of the knowledge graph can be used for association and inference. For example, if the keyword is "uncomfortable throat", through the association between "uncomfortable throat" and symptom nodes such as "sore throat" and "dry throat" in the knowledge graph, relevant disease and treatment information can be further searched to obtain more accurate status information of the target person.

[0090] After obtaining the status information of the target person, it is necessary to timely transmit this information to the relevant target devices so that family members, caregivers, etc. can timely understand the situation of the target person and take corresponding measures.

[0091] As can be seen from the above, in this embodiment, by extracting keywords, the key content of the target text can be quickly focused. Matching the keywords with the nodes of the knowledge graph can accurately infer the status of the target person with the help of the rich information in the knowledge graph. Finally, the status information is sent to the target device, enabling relevant personnel to understand the situation in a timely manner, which helps to take corresponding measures in a timely manner and improve the efficiency and quality of medical and elderly care services.

[0092] In an embodiment of the present disclosure, sending the status information to the target device includes:

[0093] Determining a target network path based on the network status;

[0094] Determining the target transmission rate of the status information based on the target network path, the importance level corresponding to the status information, and the resource status of the first processor;

[0095] Sending the status information to the target device based on the target transmission rate.

[0096] In this embodiment, different network paths have different performance metrics, such as bandwidth, latency, packet loss rate, etc. The quality of the network status directly affects the efficiency and reliability of information transmission. Therefore, it is necessary to monitor the network status in real time and select the network path with the best performance as the target network path to ensure that the status information can be transmitted quickly and stably.

[0097] In this embodiment, the medical and elderly care robot can include multiple network connection methods, such as Wi-Fi, 4G / 5G, etc. By sending test data packets on different network interfaces, performance metrics such as the bandwidth, latency, and packet loss rate of the network are collected. The quality of different network paths is evaluated. For example, an evaluation function can be set to comprehensively consider factors such as bandwidth, latency, and packet loss rate, calculate the score of each network path, and select the network path with the highest score as the target network path.

[0098] In this embodiment, the target network path determines the upper limit of information transmission capacity, the importance level of the status information determines the transmission priority, and the resource status of the first processor affects the transmission rate it can support.

[0099] The importance of the status information is pre-classified. For example, it can be divided into three levels: high, medium, and low. Important information such as urgent medical conditions is classified as high level; general daily situation reports are classified as medium level; less important chat information is classified as low level.

[0100] Determine the maximum transmission rate that the target network path can support according to its performance metrics. At the same time, evaluate the available transmission resources that the first processor can provide based on its resource status (such as CPU usage rate, memory occupancy rate, etc.). Combine the importance level of the status information and determine the target transmission rate according to certain rules. For example, for high-level status information, try to use the maximum transmission rate of the target network path when the resources of the first processor permit; for medium-level status information, appropriately reduce the transmission rate; for low-level status information, the transmission rate can be further reduced.

[0101] In this embodiment, the first processor adjusts the sending frequency and packet size of the status information according to the target transmission rate. By controlling the sending frequency and packet size, the status information is transmitted at the target transmission rate. For example, if the target transmission rate is , the sending time interval of each packet can be calculated and the packet size S, and the status information is sent in sequence according to this time interval and packet size.

[0102] It can be concluded from the above that in this embodiment, by comprehensively considering the network status, the importance level of the status information, and the resource status of the first processor, the target network path and the target transmission rate are dynamically determined, realizing the efficient and reliable transmission of the status information, and improving the performance and service quality of the communication of the medical and elderly care robot.

[0103] In an embodiment of the present disclosure, the identification information includes the importance level corresponding to the target text information;

[0104] The second processor extracts features from the target text information based on the importance level corresponding to the target text information.

[0105] In this embodiment, the medical and elderly care robot can be applied to a nursing home. There are multiple medical and elderly care robots in the nursing home. The second processor may receive multiple target text information at the same time. In order to process this information efficiently and reasonably, the second processor can extract features from the target text information according to the importance level, and give priority to processing the information with high importance to ensure that key information can be analyzed and processed in time.

[0106] In this embodiment, after the medical and elderly care robot obtains the audio information of the target person and converts it into target text information, it can judge the importance level according to the text content. Different types of text information have different degrees of influence on the health, safety, etc. of the target person, so it is necessary to conduct a level division. The importance level can help the second processor clarify the priority of each target text information, so as to reasonably allocate processing resources.

[0107] The medical and elderly care robot can preset rules to determine the importance level. For example, the target text information containing emergency medical assistance (such as "I'm having a heart attack"), serious safety issues (such as "There's a fire"), etc. can be classified as a high importance level; the content involving daily health consultations (such as "I've been having trouble sleeping lately"), general needs (such as "I want to drink some water"), etc. is classified as a medium importance level; small talk and insignificant remarks (such as "The weather is nice today") are classified as a low importance level. After determining the level, it is sent to the second processor together with the target text information as identification information.

[0108] In this embodiment, the second processor can receive the target text information and its identification information from each medical and elderly care robot through the network interface. After receiving the information, it stores it in a processing queue and waits for subsequent processing. The second processor sorts the information stored in the processing queue according to the importance level corresponding to the target text information. It preferentially extracts features from the target text information with a high importance level to ensure that urgent and critical information can be processed and analyzed in a timely manner, providing a basis for subsequent corresponding measures.

[0109] The second processor can, based on the priority queue algorithm, place the target text information with a high importance level at the front of the queue. When performing feature extraction, it processes them in the order of the queue. For the target text information with a high importance level, the second processor can call more advanced processing resources and algorithms to ensure accurate and rapid extraction of key features.

[0110] For example, a natural language processing model and a medical knowledge base can be used to deeply analyze the text involving medical assistance and extract key information such as symptoms and medical history. For the target text information with medium and low importance levels, the processing order and resource allocation are arranged according to the resource situation, and on the premise of ensuring the processing of high-importance information, the feature extraction of other information is gradually completed.

[0111] It can be concluded from the above that in this embodiment, by setting the importance level for the target text information and having the second processor perform feature extraction based on this, the efficient processing and reasonable scheduling of information are achieved in the case where multiple medical and elderly care robots send information simultaneously. It ensures that key information can be analyzed and processed in a timely manner, improving the response speed and quality of medical and elderly care services in the nursing home.

[0112] In an embodiment of the present disclosure, the identification information further includes: the judgment strategy corresponding to the target text information;

[0113] The judgment strategy is used to indicate that when the second processor receives multiple identification information with the same importance level simultaneously, the weights corresponding to the complexity of each dimension in the comprehensive complexity are weighted and calculated to obtain multiple target importance levels.

[0114] In practical applications, multiple healthcare robots convert the audio information of a target person into target text information and send it to a second processor along with identification information. When there are multiple target text information with the same importance level, the original importance level division cannot meet the requirements of reasonable sorting and processing.

[0115] To ensure the reasonable processing of this information, the ranking of multiple target text information with the same importance level can be re - sorted. In this embodiment, with the help of the judgment strategy in the identification information, by performing a weighted calculation on the complexity of each dimension of the comprehensive complexity and its corresponding weight, a new target importance level can be obtained, and then these target text information can be re - sorted to achieve more reasonable feature extraction and processing.

[0116] In this embodiment, when processing target text information, in addition to determining the importance level, the healthcare robot can also generate a judgment strategy according to a preset rule and include it in the identification information.

[0117] After receiving the identification information, when encountering multiple situations with the same importance level, the second processor can enable this judgment strategy.

[0118] The comprehensive complexity of the target text information consists of multiple dimensions, such as lexical complexity, syntactic complexity, and semantic complexity. Each dimension contributes differently to the overall complexity, so it corresponds to a different weight. The evaluation method and corresponding weight of the complexity of each dimension can be preset.

[0119] For example, for lexical complexity, it can be evaluated according to the proportion of technical terms and rare words in the text; for syntactic complexity, it can be measured by the structural complexity of sentences (such as the number of nested layers, sentence length, etc.); for semantic complexity, consider the abstract degree of the meaning expressed by the text, the complexity of logical relationships, etc. The weight can be set according to the actual situation and experience. For example, in a medical scenario, the semantic complexity may have a higher weight.

[0120] In this embodiment, according to the judgment strategy, a weighted calculation is performed on the complexity of each dimension and its corresponding weight in the comprehensive complexity of each target text information. The weighted calculation can comprehensively consider the influence of each dimension and more accurately reflect the actual importance of the text information. In this way, multiple target text information with the same original importance level can be further distinguished.

[0121] Let the lexical complexity be , and the weight be ; the syntactic complexity be , and the weight be ; the semantic complexity be , and the weight be Then the calculation formula for the target importance level I can be expressed as:

[0122]

[0123] Among them, H represents the health risk coefficient of the target person, which can be evaluated based on the target person's medical history, recent health examination results, real-time monitoring data (such as heart rate, blood pressure, etc.). In the medical and elderly care scenario, if the health risk of the target person is relatively high, the importance of the text information related to him (such as symptom description, demand expression, etc.) will increase significantly. By introducing the health risk coefficient, the target importance level can better reflect this actual situation and make the evaluation of the importance level more in line with the scenario requirements.

[0124] U represents the urgency coefficient of the target text information, which can be judged according to factors such as keywords and tone in the text. For example, for texts containing emergency keywords such as "help" and "sudden pain", the value of the urgency coefficient can be set relatively high; while for general daily communication texts, the value of the urgency coefficient is relatively low. In a nursing home, it is very important to process emergency information in a timely manner to ensure the life safety and health of the elderly. After introducing the urgency coefficient, the target importance level can highlight the importance of emergency information, ensure that this information can be processed preferentially, and improve the response efficiency and security of the system.

[0125] Such calculations are performed for each target text information to obtain multiple target importance levels.

[0126] In this embodiment, after obtaining multiple target importance levels, they are compared, and the target text information is sorted in descending order. This can clarify the order of processing, and preferentially perform feature extraction on the target text information with a high target importance level, ensuring that more critical and complex information can be processed in a timely manner.

[0127] The second processor can use a sorting algorithm to sort multiple target importance levels. After sorting, the target text information is sequentially subjected to feature extraction in order. For text information with a high target importance level, more computing resources and more complex processing algorithms can be allocated to ensure accurate extraction of key features; for text information with a lower level, the processing is reasonably arranged according to the resource situation.

[0128] It can be concluded from the above that in this embodiment, through the judgment strategy in the identification information, weighted calculation and comparison are performed on each dimension of the comprehensive complexity, realizing the re-sorting and reasonable processing of multiple target text information with the same importance level, and improving the efficiency and accuracy of the second processor in processing information.

[0129] Corresponding to the robot communication method in the above embodiment, Figure 2The structural block diagram of the robot communication device provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 , the robot communication device 20 includes: a complexity calculation module 21, a first communication processing module 22, and a second communication processing module 23.

[0130] Among them, the complexity calculation module 21 is used to determine the comprehensive complexity of the target text information, where the target text information is the text information obtained by converting the audio information of the target person;

[0131] The first communication processing module 22 is used to, in response to the comprehensive complexity of the target text information being less than the first threshold, perform feature extraction on the target text information based on the first processor to obtain the status information of the target person, and send the status information to the target device;

[0132] The second communication processing module 23 is used to, in response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmit the target text information and its corresponding identification information to the second processor based on the target policy, where the identification information is used to instruct the second processor to perform feature extraction on the target text information to obtain the status information of the target person, and send the status information to the target device;

[0133] The first processor is a processor set inside the medical care robot, and the second processor is a processor set in the cloud.

[0134] In an embodiment of the present disclosure, the complexity calculation module 21 is specifically used for:

[0135] Perform feature extraction on the audio information of the target person to obtain target audio feature information;

[0136] Perform semantic analysis on the target text information to obtain target semantic information;

[0137] Determine the communication type between the target person and the medical care robot based on the target text information;

[0138] Assign first weights to the target audio feature information and the target semantic information respectively based on the communication type;

[0139] Perform weighted fusion on the first weights to obtain the comprehensive complexity of the target text information.

[0140] In an embodiment of the present disclosure, the complexity calculation module 21 is specifically further used for:

[0141] Perform weighted fusion on the first weights based on the first formula to obtain the comprehensive complexity of the target text information;

[0142] The first formula is:

[0143]

[0144] Among them, represents the comprehensive complexity of the target text information, is the value mapped by the communication type between the target person and the medical care robot, represents the maximum value of the mapped values among all communication types, represents the target audio feature information, represents the first weight corresponding to the target audio feature information, represents the first weight corresponding to the target semantic information, represents the target semantic information, represents the non-linear adjustment index, represents the information timeliness factor.

[0145] In an embodiment of the present disclosure, the robot communication device 20 further includes: a threshold determination module; specifically, the threshold determination module is configured to:

[0146] Determine the threshold adjustment step based on the deviation between the comprehensive complexity and the standard threshold and the resource status of the first processor;

[0147] Adjust the standard threshold based on the threshold adjustment step to obtain the first threshold.

[0148] In an embodiment of the present disclosure, the first communication processing module 22 is specifically configured to:

[0149] Extract keywords from the target text information;

[0150] Match the keywords with the nodes in the knowledge graph to obtain the status information of the target person;

[0151] Send the status information to the target device.

[0152] In an embodiment of the present disclosure, the first communication processing module 22 is further specifically configured to:

[0153] Determine the target network path based on the network status;

[0154] Determine the target transmission rate of the status information based on the target network path, the importance level corresponding to the status information, and the resource status of the first processor;

[0155] Send the status information to the target device based on the target transmission rate.

[0156] In an embodiment of the present disclosure, the identification information includes the importance level corresponding to the target text information;

[0157] The second processor extracts features from the target text information based on the importance level corresponding to the target text information.

[0158] In one embodiment of the present disclosure, the identification information further includes: a judgment strategy corresponding to the target text information;

[0159] The judgment strategy is used to indicate that when the second processor receives multiple pieces of identification information with the same importance level simultaneously, a weighted calculation is performed on the weights corresponding to the complexity of each dimension in the comprehensive complexity to obtain multiple target importance levels.

[0160] See Figure 3 , Figure 3 which is a schematic block diagram of a medical and elderly care robot provided in an embodiment of the present disclosure. As Figure 3 shown, the medical and elderly care robot 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module in the above-mentioned device embodiments, such as Figure 2 the functions of the modules 21 to 23 shown.

[0161] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0162] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0163] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may further include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0164] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may implement the implementation manners described in the first and second embodiments of the robot communication method provided by the embodiments of the present disclosure, and may also implement the implementation manner of the medical and elderly care robot described in the embodiments of the present disclosure, which will not be elaborated herein.

[0165] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0166] The computer-readable storage medium may be an internal storage unit of the medical and elderly care robot in any of the foregoing embodiments, such as the hard disk or memory of the medical and elderly care robot. The computer-readable storage medium may also be an external storage device of the medical and elderly care robot, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the medical and elderly care robot. Further, the computer-readable storage medium may include both the internal storage unit and the external storage device of the medical and elderly care robot. The computer-readable storage medium is used to store the computer program and other programs and data required by the medical and elderly care robot. The computer-readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0167] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0168] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described healthcare robots and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0169] In several embodiments provided in this application, it should be understood that the disclosed healthcare robots and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings, direct couplings, or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, or can be electrical, mechanical, or other forms of connection.

[0170] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0171] In addition, the functional units in each embodiment of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0172] The above is only the specific implementation manner of this disclosure, but the protection scope of this disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by this disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be subject to the protection scope of the claims.

Claims

1. A robot communication method, applied to a medical robot, characterized in that: include: Determining the comprehensive complexity of target text information, wherein the target text information is text information obtained by converting audio information of a target person; In response to the comprehensive complexity of the target text information being less than a first threshold, extracting features from the target text information based on the first processor to obtain status information of the target person, and sending the status information to the target device; In response to the comprehensive complexity of the target text information being greater than or equal to the first threshold, transmitting the target text information and its corresponding identification information to the second processor based on the target strategy, wherein the identification information is used to instruct the second processor to perform feature extraction on the target text information to obtain the status information of the target person, and send the status information to the target device; The first processor is a processor set inside the medical robot, and the second processor is a processor set in the cloud; Determining the comprehensive complexity of the target text information includes: Extracting features from the audio information of the target person to obtain target audio feature information; Performing semantic analysis on the target text information to obtain target semantic information; Determine the communication type between the target person and the medical robot based on the target text information; Assigning first weights to the target audio feature information and the target semantic information based on the communication type; Performing weighted fusion on the first weights to obtain the comprehensive complexity of the target text information; The step of performing weighted fusion on the first weights to obtain the comprehensive complexity of the target text information includes: Performing weighted fusion on the first weights based on the first formula to obtain the comprehensive complexity of the target text information; The first formula is: in, Represents the comprehensive complexity of the target text information, The value mapped to the communication type between the target person and the medical robot. Indicates the maximum value of the mapped value among all communication types. Represents the target audio feature information, represents the first weight corresponding to the target audio feature information, represents the first weight corresponding to the target semantic information, Represents the target semantic information, represents the nonlinear regulation index, Represents the information timeliness factor.

2. The robot communication method according to claim 1, characterized in that: Also includes: Determine a threshold adjustment step size based on a deviation between the comprehensive complexity and a standard threshold and a resource state of the first processor; The standard threshold is adjusted based on the threshold adjustment step to obtain the first threshold.

3. The robot communication method according to claim 1, characterized in that: The step of extracting features from the target text information based on the first processor to obtain status information of the target person, and sending the status information to the target device, includes: Extracting keywords from the target text information; Match the keywords with the nodes in the knowledge graph to obtain the status information of the target person; The status information is sent to the target device.

4. The robot communication method according to claim 3, characterized in that: The sending the status information to the target device includes: Determine a target network path based on the network status; determining a target transmission rate of the status information based on the target network path, the importance level corresponding to the status information, and the resource state of the first processor; The status information is sent to a target device based on the target transmission rate.

5. The robot communication method according to claim 1, characterized in that: The identification information includes the importance level corresponding to the target text information; The second processor extracts features of the target text information based on the importance level corresponding to the target text information.

6. The robot communication method according to claim 5, characterized in that: The identification information also includes: a judgment strategy corresponding to the target text information; The judgment strategy is used to indicate that the second processor simultaneously receives multiple identification information with the same importance level, performs weighted calculation on the weight corresponding to the complexity of each dimension in the comprehensive complexity, and obtains multiple target importance levels.

7. A robot communication device, applied to a medical robot, characterized in that: include: A complexity calculation module, used to determine the comprehensive complexity of target text information, wherein the target text information is text information obtained by converting the audio information of the target person; A first communication processing module, configured to extract features of the target text information based on the first processor to obtain status information of the target person in response to the comprehensive complexity of the target text information being less than a first threshold, and send the status information to the target device; A second communication processing module, configured to transmit the target text information and its corresponding identification information to a second processor based on a target strategy in response to the comprehensive complexity of the target text information being greater than or equal to a first threshold, wherein the identification information is used to instruct the second processor to perform feature extraction on the target text information to obtain status information of a target person, and send the status information to a target device; The first processor is a processor set inside the medical robot, and the second processor is a processor set in the cloud; Determining the comprehensive complexity of the target text information includes: Extracting features from the audio information of the target person to obtain target audio feature information; Performing semantic analysis on the target text information to obtain target semantic information; Determine the communication type between the target person and the medical robot based on the target text information; Assigning first weights to the target audio feature information and the target semantic information based on the communication type; Performing weighted fusion on the first weights to obtain the comprehensive complexity of the target text information; The step of performing weighted fusion on the first weights to obtain the comprehensive complexity of the target text information includes: Performing weighted fusion on the first weights based on the first formula to obtain the comprehensive complexity of the target text information; The first formula is: in, Represents the comprehensive complexity of the target text information, The value mapped to the communication type between the target person and the medical robot. Indicates the maximum value of the mapped value among all communication types. Represents the target audio feature information, represents the first weight corresponding to the target audio feature information, represents the first weight corresponding to the target semantic information, Represents the target semantic information, represents the nonlinear regulation index, Represents the information timeliness factor.

8. A medical robot, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images