Method for ward round based on chest card recorder system and related device

Abstract

This application provides a ward round method and related apparatus based on a badge recorder system, comprising: determining the ward round progress of the users based on a database of users to be ward rounded, location data of the users to be ward rounded collected by the badge recorder, and audio data; determining multiple users to be ward rounded based on the ward round progress of the users to be ward rounded and a preset ward round order; determining the ward round order of the multiple users to be ward rounded based on the location data of the users to be ward rounded, the location data of the multiple users to be ward rounded, and the severity of their illness; and sending the location data and illness data of the next user to be ward rounded to the badge recorder based on the ward round order and the database of users to be ward rounded, so as to improve the efficiency of ward rounds.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a ward round method and related devices based on a name tag recorder system. Background Technology

[0002] Ward rounds refer to the regular medical activities conducted by physicians to examine hospitalized patients, check their physical signs, evaluate and adjust treatment plans, and simultaneously conduct teaching explanations and case discussions. This directly impacts the quality of care. A scientifically sound ward round sequence can effectively plan the ward round route, prioritize the treatment of critically ill patients, and thus improve ward round efficiency.

[0003] Currently, during clinical ward rounds, doctors often rely on experience or paper records to arrange the order of ward rounds, lacking analysis of real-time patient information. This makes it difficult to determine the order of subsequent patients to be ward rounds in a timely and reasonable manner, which can easily lead to a chaotic ward round rhythm and thus affect the efficiency of ward rounds. Summary of the Invention

[0004] This application provides a ward round method and related apparatus based on a name tag recorder system to improve the efficiency of ward rounds.

[0005] In a first aspect, embodiments of this application provide a ward round method based on a name tag recorder system, applied to a server of the name tag recorder system, wherein the server of the name tag recorder system communicates with the name tag recorders of the name tag recorder system, and the method includes: The ward round progress of the ward round is determined based on the database of ward round users, the location data of the ward round users collected by the name tag recorder, and the audio data. Based on the room-checking progress of the users and the preset room-checking order, multiple users to be checked are identified; The ward round order of the multiple patients to be ward rounded is determined based on the location data of the patients being ward rounded, the location data of the multiple patients to be ward rounded, and the severity of their illnesses. Based on the ward round order and the database of patients to be ward rounded, the location data and medical condition data of the next patient to be ward rounded are sent to the name tag recorder.

[0006] Secondly, embodiments of this application provide a ward round device based on a name badge recorder system, comprising: The first processing unit is used to determine the ward round progress of the ward round based on the database of ward round users, the location data of the ward round users collected by the name badge recorder, and the audio data. The second processing unit is used to determine multiple users to be checked based on the check-up progress of the users and the preset check-up order; The third processing unit is used to determine the ward round order of the multiple patients to be ward rounded based on the location data of the patients being ward rounded, the location data of the multiple patients to be ward rounded, and the severity of their illnesses. The fourth processing unit is used to send the location data and medical condition data of the next patient to be checked to the name tag recorder based on the ward round order and the database of patients to be checked.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and one or more programs, the one or more programs being stored in the memory and configured to be executed by the processor, the programs including instructions for performing steps in the method as described in the first aspect of this application.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions, when executed by a processor, implement the steps of the method described in the first aspect of this application.

[0009] As can be seen, in this embodiment, by combining the database of patients to be examined, the doctor's location data collected by the badge recorder, and the audio data, the progress of the ward round is determined, and the doctor's current ward round node is grasped, avoiding delays or deviations in progress judgment. Then, based on the ward round progress and the preset ward round order, patients to be examined are screened, which can narrow the scope of the ward round and achieve dynamic locking of the patients to be examined. Furthermore, by combining the doctor's location, the location of the patients to be examined, and the severity of their conditions, the ward round order is optimized, which can both plan the optimal route and prioritize patients to receive timely treatment, taking into account both the rationality of the path and the priority of treatment. Finally, the location and condition information of the next patient are sent to the badge recorder in the determined order, allowing doctors to obtain key information in advance and reducing the time spent on information retrieval. The overall ward round process is intelligently scheduled, thereby significantly improving the efficiency of doctors' ward rounds. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of the architecture of a name tag recorder system provided in an embodiment of this application; Figure 2 This is a schematic diagram of a badge recorder management interface provided in an embodiment of this application; Figure 3 This is a flowchart of a ward round method based on a name tag recorder system provided in an embodiment of this application; Figure 4 This is a schematic diagram of a process for determining the ward round progress of the user provided in an embodiment of this application; Figure 5 This is a schematic diagram of a process for determining the matching probability between the user being checked and the plurality of users to be checked, provided in an embodiment of this application; Figure 6 This is a flowchart illustrating another ward round method based on a name tag recorder system provided in an embodiment of this application; Figure 7 This is a flowchart illustrating a method for determining the ward inspection order of the plurality of ward inspection users, provided in an embodiment of this application. Figure 8 This is a schematic diagram illustrating a scenario for confirming the next user to be checked, provided in an embodiment of this application. Figure 9 This is a schematic diagram of the structure of a ward round device based on a name tag recorder system provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of a computer provided in an embodiment of this application. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0013] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0014] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0015] Ward rounds refer to the regular medical activities conducted by physicians to examine hospitalized patients, check their physical signs, evaluate and adjust treatment plans, and simultaneously conduct teaching explanations and case discussions. This directly impacts the quality of care. A scientifically sound ward round sequence can effectively plan the ward round route, prioritize the treatment of critically ill patients, and thus improve ward round efficiency.

[0016] Currently, during clinical ward rounds, doctors often rely on experience or paper records to arrange the order of ward rounds, lacking analysis of real-time patient information. This makes it difficult to determine the order of subsequent patients to be ward rounds in a timely and reasonable manner, which can easily lead to a chaotic ward round rhythm and thus affect the efficiency of ward rounds.

[0017] This solution determines the progress of ward rounds by combining a database of patients awaiting rounds, doctor location data collected by badge recorders, and audio data, thus keeping track of the doctor's current ward round stage and avoiding delays or inaccuracies in progress assessment. Then, based on the ward round progress and a preset ward round order, patients awaiting rounds are filtered, narrowing the scope of rounds and dynamically locking onto patients. Furthermore, the ward round order is optimized by combining the doctor's location, the location of patients awaiting rounds, and the severity of their conditions. This allows for the planning of the optimal route while prioritizing timely treatment for critically ill patients, balancing route rationality and treatment priority. Finally, the location and condition information of the next patient are transmitted to the badge recorders in a predetermined order, allowing doctors to obtain key information in advance and reducing information retrieval time. This overall intelligent scheduling of the ward round process significantly improves the efficiency of doctor ward rounds.

[0018] The ward round method, computer, storage medium, and program product based on the name badge recorder system provided in this application embodiment can be applied to, for example... Figure 1 Please refer to the name tag recorder system shown. Figure 1 , Figure 1 This is a schematic diagram of the architecture of a name tag recorder system provided in an embodiment of this application. The name tag recorder system 100 includes a client 101 and a server 102. The client 101 can communicate with the server 102 via a network. The client 101 refers to the device used by the user, such as the name tag recorder mentioned in this solution. In this solution, the client 101 can collect various types of information, such as location data and audio data. Through the client 101, the user can interact with the name tag recorder system 100.

[0019] Please refer to Figure 2 , Figure 2 This is a schematic diagram of a badge recorder management interface provided in an embodiment of this application, as shown below. Figure 2 As shown, users can access the badge recorder management interface through server 102 to obtain relevant information collected by the badge recorder and manage the badge recorder. Specifically, users can log in using a pre-set account and password, and after logging in, they will receive... Figure 2 The displayed management interface features a vertically arranged navigation menu on the left, containing multiple functional module entries. From top to bottom, these are: Workbench, List of Users to be Rounded, Badge Management, Organization Management, Permission Management, and System Settings. The default initial functional module for users entering the management interface is the Workbench. At this point, area A on the right displays the current badge recorder's version information (e.g., current version 0.6.9) and storage method (e.g., local storage). Area B displays the number of badge recorders currently managed, the number of badge recorders online, and the total number of currently stored recording files. Area C provides multiple quick access points using icons and text, including Device Management, Recording File Preview, Device Log View, Doctor Management, Department Management, and Position Management. Users can directly jump to the corresponding page after clicking. Area D visualizes the recording trend over a period of time using a line graph, with the horizontal axis representing dates and the vertical axis representing the number of recordings, thus intuitively showing the recent trend in the number of recordings.

[0020] Specifically, when a user clicks on the list of patients awaiting rounds, the right-hand area displays relevant information for all patients, such as their name, consultation date, and number of consultations. Users can quickly search for a specific patient using the filter bar on the right. When a user clicks on badge management, the right-hand area displays the device codes, users, and device addition times for multiple currently connected badge recorders. Users can also view audio files and device logs in badge management. When a user clicks on organization management, the right-hand area displays the names of different doctors and their departments. When a user clicks on permission management, the right-hand area displays the names and order of the various functional modules in the left navigation bar. When a user clicks on system settings, the right-hand area displays the current storage method and corresponding website information.

[0021] Server 102 refers to a remote computer used for processing large amounts of computing tasks and storing data. In this solution, server 102 is responsible for determining the ward round progress of the users based on the database of users to be ward rounded, the location data of the users collected by the badge recorder, and the audio data; then, based on the ward round progress of the users to be ward rounded and the preset ward round order, determining multiple users to be ward rounded; then, based on the location data of the users to be ward rounded, the location data of the multiple users to be ward rounded, and the severity of their illness, determining the ward round order of the multiple users to be ward rounded; finally, based on the ward round order and the database of users to be ward rounded, sending the location data and illness data of the next user to be ward rounded to the badge recorder.

[0022] Based on this, this application provides a ward round method, computer, storage medium, and program product based on a name tag recorder system. The following is a detailed description of this application with reference to the accompanying drawings.

[0023] Please see Figure 3 , Figure 3 This is a flowchart of a ward round method based on a name tag recorder system provided in an embodiment of this application, such as... Figure 3 As shown, the ward round method based on the name tag recorder system includes the following steps: S301, determine the ward round progress of the ward round user based on the database of users to be checked, the location data of the ward round user collected by the name tag recorder, and the audio data.

[0024] The implementing entity of this plan can be... Figure 1 Server 102 of the badge recorder system 100.

[0025] The database of patients awaiting ward rounds refers to a database that stores data including basic information of hospitalized patients, bed distribution, disease severity, and treatment plans. The database of patients awaiting ward rounds can provide basic data support for judging the progress of ward rounds.

[0026] This can be achieved by performing structured analysis on the ward round plan for the day to extract the target patient set for this ward round task. ,in This refers to the total number of patients during this ward round, and each patient... Corresponding to a unique patient identification identifier Ward number Bed number Preset ward round sequence number .

[0027] Then, the target patient set is retrieved from the database of patients to be examined. Construct a patient information mapping table using complete basic information of all patients. Each field corresponds to the patient's name, language preference, place of origin / region information, type of surgery, past medical history, and main diagnostic information.

[0028] Among these, a patient spatial location mapping table was constructed by combining the indoor electronic map of the ward. ,in This refers to the three-dimensional spatial coordinates of the patient's bed within the room. Then, based on a pre-set ward round sequence... Construct the initial ward round progress state vector ,in This refers to the ward round number that has been completed so far. This is the ID of the patient currently being rounded. The status of the ward rounds (0 = not started, 1 = on the way to the ward, 2 = during ward rounds, 3 = ward rounds completed). The confidence level for the state estimate.

[0029] Among them, the name tag recorder is an integrated intelligent data collection terminal worn by ward round doctors. Its appearance is similar to a work name tag, and it can be worn directly on the chest without hand operation. The name tag recorder integrates components such as a positioning module and a sound pickup module, enabling it to collect doctors' location data in real time, simultaneously collect audio data from communication with patients, inquiries about patient conditions, and the issuance of medical orders during ward rounds, and upload this data to server 102 in real time. This allows for continuous collection of multi-dimensional ward round information without interfering with the normal ward round process.

[0030] The ward round progress state vector is used to determine the progress of ward rounds. The ward round progress represents the number of patients the doctor has completed ward rounds for, the location of the ward, and the stage of treatment being conducted or completed. Ward round users refer to the medical staff performing ward rounds, and their location and behavior data are continuously collected by badge recorders.

[0031] Specifically, the database of patients awaiting ward rounds is used as the primary source of information. Combined with real-time data on the doctor's location and ward round audio transmitted by the badge recorder, the system conducts comprehensive analysis of multi-dimensional information to accurately determine the doctor's current ward round progress. This enables precise perception of the ward round execution status and provides a reliable basis for subsequent screening of patients awaiting ward rounds and optimization of the ward round order.

[0032] In one possible implementation, please refer to Figure 4 , Figure 4 This is a flowchart illustrating a process for determining the ward round progress of the user, as provided in an embodiment of this application. Figure 4 As shown, the ward round progress of a user is determined based on the database of users to be rounded, the location data of the users being rounded collected by the name tag recorder, and the audio data. This includes the following steps: S401, based on the database of users to be checked, and the location data and audio data of the users to be checked collected by the name tag recorder, determine the matching probability between the user to be checked and the multiple users to be checked.

[0033] Among them, the name tag recorder is an integrated intelligent data collection terminal worn by ward round doctors. Its appearance is similar to a work name tag, and it can be worn directly on the chest without hand operation. The name tag recorder integrates components such as a positioning module and a sound pickup module, enabling it to collect doctors' location data in real time, simultaneously collect audio data from communication with patients, inquiries about patient conditions, and the issuance of medical orders during ward rounds, and upload this data to server 102 in real time. This allows for continuous collection of multi-dimensional ward round information without interfering with the normal ward round process.

[0034] Among them, the matching probability refers to the value calculated by server 102 through a specific algorithm, which represents the degree of correlation between the current location of the ward round doctor, the content of the voice interaction and a certain ward round user, and is used to determine whether the doctor is conducting ward rounds on that patient.

[0035] Specifically, S401 first uses patient bed and ward information in the database of users to be rounded as a reference, and combines it with the location data of the ward doctor transmitted in real time by the name tag recorder to determine the spatial proximity between the doctor and each user to be rounded. At the same time, it combines the collected audio data to identify ward round interaction behavior, and comprehensively calculates and determines the matching probability between the ward doctor and multiple users to be rounded, so as to realize the quantitative judgment of the doctor's current ward round object.

[0036] S402, determine the ward round progress based on the matching probability.

[0037] The system calculates the correlation and matching degree between the attending physician and each patient awaiting rounds; a higher probability indicates that the physician is more likely to be currently making rounds for that patient. The rounds progress reflects the comprehensive status information of the number of patients the attending physician has completed rounds for, the current stage of the rounds, and the overall progress of the rounds. This information is crucial for planning the subsequent rounds sequence and disseminating patient information.

[0038] The progress of ward rounds can be determined based on the matching probability by setting a matching probability threshold or by sorting and comparing.

[0039] Specifically, based on the matching probability obtained in S401, S402 identifies the target patient that the doctor is currently making rounds with, combines the patient records of patients who have completed rounds, comprehensively judges and outputs the doctor's current rounds progress, realizes the accurate determination of the rounds execution status, and provides a basis for the screening and order optimization of subsequent patients to be rounded.

[0040] As can be seen in this example, by first combining the location and audio data collected by the name tag recorder to calculate the matching probability between the ward round doctor and each patient to be rounded, and then accurately determining the ward round progress based on the matching probability, it is possible to accurately determine the doctor's ward round status, avoid errors caused by manual recording, and accurately grasp the progress of the ward round in real time. This provides reliable data support for the subsequent dynamic planning of the ward round sequence and the synchronization of patient information, thereby improving the overall smoothness and efficiency of the ward round.

[0041] In one possible implementation, please refer to Figure 5 , Figure 5 This is a flowchart illustrating a process for determining the matching probability between the user being checked and the plurality of users to be checked, as provided in an embodiment of this application. Figure 5 As shown, based on the database of users to be checked, and the location and audio data of users to be checked collected by the name tag recorder, the matching probability between the user to be checked and the multiple users to be checked is determined, including the following steps: S501, based on the database of users to be checked, determines the location data and voiceprint data of multiple users to be checked.

[0042] The database of patients awaiting ward rounds is a pre-stored database containing information on all inpatients, including bed location, ward distribution, patient identification, historical medical history, treatment records, and pre-collected voiceprint data. The location data of patients awaiting ward rounds includes their ward number, bed number, and ward coordinates, used to determine the spatial distance between doctors and patients. The voiceprint data of patients awaiting ward rounds refers to unique acoustic features extracted from patients' voices, used to distinguish different patients' voices; this data is pre-collected by server 102 and stored in the database.

[0043] S502, based on the location data of the multiple users to be checked and the location data of the user checking, determine the location matching probability between the user checking and the multiple users to be checked.

[0044] The location data of patients during ward rounds is obtained by real-time collection and uploading of the doctor's current spatial coordinates and ward location information through a built-in positioning module on the doctor's badge recorder. The location matching probability is used to quantify the spatial proximity between the ward round doctor and a patient to be rounded; the higher the value, the closer the two are.

[0045] In acquiring the location data of users during ward rounds, the indoor location data can be preprocessed to process the raw location coordinate sequences collected in real time. (t is the current timestamp), Kalman filtering is used for denoising and smoothing to eliminate positioning drift and random noise. The filter update formula is as follows: ; in: The optimal position estimate after filtering at time t; For t The prior prediction of the position at time t based on the state at time 1. is the Kalman gain at time t, used to balance the weights of prior predictions and real-time observations; H is the observation matrix, used to map the state vector to the observation space. These are the original positioning observations collected at time t.

[0046] Specifically, the spatial location modal probability can be based on the doctor's real-time location. Location of each patient's bed The spatial distance is calculated. The probability of location matching is then calculated. The formula is as follows: ; in, σ is a two-dimensional / three-dimensional Euclidean distance operator; σ is the bandwidth parameter of the distance Gaussian kernel, which is preset based on the ward space size; the closer the distance, the closer the location matching probability is to 1, and vice versa.

[0047] S503, based on the voiceprint data and medical condition data of the multiple users to be checked, and the audio data of the user to be checked, determine the audio matching probability between the user to be checked and the multiple users to be checked.

[0048] The audio data of the patients being rounded is collected in real-time by the microphone module of the name tag recorder, including voice information such as doctor inquiries, patient responses, and discussions about their conditions. The audio matching probability refers to the similarity score obtained through voiceprint comparison, used to determine whether the voice collected on-site belongs to the corresponding patient to be rounded. The medical condition data refers to patient diagnosis, symptoms, medical history, and other information stored in the database of patients to be rounded, which can further constrain the voiceprint matching process.

[0049] After collecting the audio data of users during ward rounds, audio data preprocessing can be performed. Specifically, the raw audio stream acquired by the microphone array is first preprocessed by frame segmentation and windowing, and then the Voice Activity Detection (VAD) algorithm is used to distinguish between valid speech segments and silent / environmental noise segments, eliminating invalid noise data. The VAD decision formula is as follows: ; in, This indicates that the audio frame at time t is a valid speech frame. Invalid noise frame; Let be the short-time energy of the audio frame at time t; The preset short-time energy threshold is adaptively adjusted based on the ambient noise level in the ward area. Let be the zero-crossing rate of the audio frame at time t; The preset zero-crossing rate threshold is used to distinguish between unfiltered sounds and ambient noise.

[0050] Simultaneously, noise reduction and gain normalization are performed on the effective speech frames to output effective interactive audio segments in different time periods. , where ts is the start timestamp of the segment and te is the end timestamp of the segment.

[0051] Specifically, for effective interactive audio segments Voiceprint features are extracted and matched with voiceprint features in the patient voiceprint-identity mapping table. The output interaction object is the patient. Voiceprint matching probability Simultaneously, it identifies the doctor's voice characteristics, confirms that the interacting subject is the currently logged-in ward round doctor, and eliminates voice interference unrelated to ward rounds.

[0052] Optionally, video data can also be collected via a name tag recorder. For the collected video data, the current patient's image acquisition authorization status is first verified. Video data is only retained if the authorization status is "agreed"; otherwise, it is discarded directly on the device without transmission or storage. The authorized video data undergoes image stabilization and keyframe extraction processing to output a compliant image acquisition stream. .

[0053] S504, perform speech recognition on the audio data of the ward round user to obtain text data.

[0054] Speech recognition converts the speech signal in the audio into readable text. The text data consists of the text content obtained after recognizing the audio from the ward round, including doctor's questions, patient answers, medical orders, and descriptions of the patient's condition.

[0055] Specifically, the audio data of ward round users collected by the name tag recorder is automatically processed by speech recognition to convert continuous speech signals into structured text data.

[0056] S505, based on the medical condition data of the multiple patients to be visited and the text data, determine the text matching probability between the patient to be visited and the multiple patients to be visited.

[0057] Specifically, S505 performs keyword matching and / or semantic similarity calculation on the text data obtained in S504 with the patient condition data in the database of users to be visited, and determines the text matching probability between the user to be visited and each user to be visited based on the degree of content relevance.

[0058] Specifically, effective interactive audio segments are transcribed into speech to obtain text data. By using a medical semantic recognition model, entity information such as patient name, bed number, disease, and surgery is extracted from the dialogue, and the text data is compared with the patient's. Information matching probability The higher the matching degree, the closer the probability is to 1.

[0059] S506, Based on the location matching probability, the audio matching probability, and the text matching probability, determine the matching probability.

[0060] The location matching probability, audio matching probability, and text matching probability are individual matching results obtained from the three dimensions of spatial location, voiceprint identity, and ward round content, respectively. The comprehensive matching probability is the final total matching value obtained by weighting and fusing the probabilities of the three dimensions, and is used to uniquely identify the ward patient currently being rounded by the doctor.

[0061] Specifically, the final matching probability can be obtained by weighting and fusing the location matching probability, audio matching probability, and text matching probability.

[0062] As can be seen in this example, by obtaining patient location and voiceprint data from the database of users to be rounded, and combining it with doctor location and audio information collected by the name tag recorder, the corresponding probabilities are calculated from three dimensions: spatial location, patient voiceprint, and matching of ward round voice text with the patient's condition. Then, the multi-dimensional matching probabilities are fused to obtain a comprehensive matching probability. This enables accurate multimodal identification of ward round subjects, effectively avoids errors caused by single data judgment, significantly improves the accuracy and reliability of ward round progress determination, provides data support for subsequent intelligent planning of the ward round sequence, and thus improves the overall efficiency of ward rounds.

[0063] In one possible implementation, please refer to Figure 6 , Figure 6 This is a flowchart illustrating another ward round method based on a name tag recorder system provided in this application embodiment, as shown below. Figure 6 As shown, the method also includes the following steps: S601, Based on the ward round progress, determine the predicted matching probability between the ward round user and the multiple ward round users; S602, For each user to be checked, calculate the first product of the predicted matching probability, the location matching probability, the audio matching probability, and the text matching probability between the user to be checked and each user to be checked; S603, normalize the first product to obtain the matching probability between the user being checked and each of the multiple users to be checked.

[0064] Specifically, the final matching probability can be calculated using multimodal joint posterior probability. More specifically, based on a Bayesian filtering framework, the prior ward round order probability is fused with the three types of single-modal observation probabilities to calculate the doctor's response to the patient at the current moment. Posterior probability of ward round status The formula is as follows: ; in, Based on the ward round status at the previous moment The patients obtained The prior probability, i.e. the predicted match probability, is given by N, where N is the total number of patients. Based on the ward round status at the previous moment The patients obtained The prior probability is calculated based on the preset ward round order and the completed progress. Patients who have not yet been ward rounded in the preset order have a higher prior probability. The numerator of the calculation formula is the first product of the predicted matching probability, the location matching probability, the audio matching probability, and the text matching probability of the ward round user and each user to be ward rounded. The denominator is the joint probability normalization term of all target patients, ensuring that the sum of the posterior probabilities of all patients is 1.

[0065] Among them, the optimal decision-making and update of ward round status involves selecting the patient with the highest posterior probability. ,satisfy , and when ( When the preset probability threshold (recommended value 0.85) is used to determine the current ward round patient as... Simultaneously, based on the semantics of the dialogue, determine the current status of the ward round. Update the current ward round progress state vector to determine the ward round progress. The formula for updating the current ward round progress state vector is as follows: ; If the highest posterior probability is lower than the threshold, the state vector from the previous time step is maintained and not updated to avoid misjudgment.

[0066] Among them, based on the current ward round status vector Determine the current status of the patient's ward round completion. (Ward rounds completed) and When the patient's ward round task is completed, mark the patient as having completed the task and update the set of patients who have completed ward rounds.

[0067] As can be seen, in this example, by combining the ward round progress to determine the predicted matching probability, and by multiplying and normalizing the predicted matching probability, location matching probability, audio matching probability, and text matching probability, it is possible to fully integrate multi-dimensional information such as historical progress, spatial location, voice identity, and diagnosis and treatment content. This allows each matching dimension to cross-verify, effectively improving the accuracy of the final matching result. As a result, it is possible to more accurately identify the ward round subjects and determine the ward round progress, providing a reliable basis for optimizing the ward round order and further improving the efficiency of ward rounds.

[0068] S302, based on the room-checking progress of the users and the preset room-checking order, determine multiple users to be checked.

[0069] The preset ward round order refers to the routine ward round sequence pre-configured on server 102, which is generally arranged based on factors such as ward distribution, patient condition severity, and departmental treatment habits. Based on the doctor's current ward round progress and the pre-set routine ward round order, patients who have already completed their ward rounds are screened and excluded from all inpatients, dynamically identifying multiple users who have not yet been rounded, thus achieving real-time updates of the list of patients awaiting ward rounds.

[0070] S303, determine the ward round order of the multiple patients to be ward rounded based on the location data of the patients being ward rounded, the location data of the multiple patients to be ward rounded, and the severity of their illnesses.

[0071] The location data for ward round users refers to the location information, including the ward area, ward, and coordinates, currently held by the doctor performing the ward round, collected and uploaded in real time by the name tag recorder. The location data for patients awaiting ward rounds refers to the fixed location information, such as the bed and ward, of each patient to be rounded, obtained from the database of patients awaiting ward rounds. The severity of illness refers to the pre-recorded severity classification of patients' conditions in the database of patients awaiting ward rounds, used to differentiate treatment priorities; generally, critically ill patients receive higher priority.

[0072] In one possible implementation, please refer to Figure 7 , Figure 7 This is a flowchart illustrating a method for determining the ward round order of the multiple users to be checked, as provided in an embodiment of this application. Figure 7 As shown, the ward round order for multiple patients to be rounded is determined based on the location data of the patients being rounded, the preset ward round sequence number, the location data of the multiple patients to be rounded, and the severity of their conditions. This includes the following steps: S701, based on the location data of the user being checked and the location data of the multiple users to be checked, determine the distance between the user being checked and the multiple users to be checked.

[0073] The location data of patients making rounds is collected and uploaded in real time by doctors using name tag recorders, including their current location information such as ward, room, bed, and location coordinates. The location data of patients to be rounded can be obtained from a database of patients to be rounded, including their fixed location information such as their room and bed. Distance refers to the physical distance between the doctor making rounds and each patient to be rounded, calculated using spatial coordinates, reflecting the distance of the path.

[0074] Specifically, S701 uses the real-time location data of the patients being checked as a benchmark, combined with the fixed location data of each patient to be checked, and calculates the physical distance between the doctor and each patient through an algorithm, providing a quantitative basis for the path distance for subsequent comprehensive scoring.

[0075] S702, based on the preset ward round number of each ward round user, the distance between each ward round user and the ward round user, and the severity of the illness of each ward round user, the score of each ward round user is obtained.

[0076] The preset ward round sequence number is a basic ward round order number pre-set by server 102, reflecting the routine ward round arrangements and departmental habits. The severity of illness refers to the grading of the patient's condition obtained from the database of users awaiting ward rounds, used to reflect the priority of diagnosis and treatment. The score of the user awaiting ward rounds is a ranking score calculated based on multiple factors; the higher the score, the higher the priority for ward rounds.

[0077] Specifically, S702 calculates a comprehensive score for each patient awaiting ward rounds based on their preset ward round number, distance from other patients, and severity of illness. This score prioritizes critically ill patients while balancing routine arrangements and reasonable pathways.

[0078] S703, the room inspection order of the multiple users to be inspected is obtained by sorting the scores of each user to be inspected from largest to smallest.

[0079] S703 sorts the patients to be examined in descending order based on the comprehensive scores obtained from S702, and automatically generates the optimal ward round order that takes into account distance, conventional order and disease priority, so as to realize the intelligent coordination of ward round route and treatment priority.

[0080] The process involves obtaining a score for each patient based on their preset ward round number, the distance between them and the ward round operator, and the severity of their condition. This includes: obtaining a second product of a first weight and the reciprocal of the preset ward round number; obtaining a third product of a second weight and the reciprocal of the distance between them; obtaining a fourth product of a third weight and the severity of their condition; and obtaining the sum of the second, third, and fourth products, where the sum is the score for each patient. The sum of the first, second, and third weights is 1.

[0081] Specifically, this refers to the group of patients who have not completed ward rounds. By combining the preset ward round order, the doctor's real-time location and distance from the ward, and the patient's condition level, a score is calculated for each patient to be rounded, i.e., priority weight. The formula is as follows: ; in, Preset room check sequence number for each user to be checked; The distance between each user to be checked and the user being checked; The severity of the illness for each patient awaiting rounds; The preset coefficients for each weight item, namely the first weight, the second weight, and the third weight, satisfy the following conditions: It can adaptively adjust based on departmental ward round habits, with a default value. , , .

[0082] Among them, according to priority weight Sort the patients from highest to lowest priority to obtain a priority list for the next ward round. Select the patient ranked first as the best predicted patient for the next ward round. .

[0083] After identifying the next patient for ward rounds, the next patient to be rounded can be selected. Patient information mapping table The system filters out key fields that doctors are interested in before ward rounds (name, language preference, place of origin, type of surgery, and main diagnosis), generates structured information broadcast text, converts it into a voice broadcast audio stream through the client-side TTS engine of 101, and simultaneously displays the key information on the front-end display screen of the badge recorder. It supports automatic pre-broadcasting while the doctor is on their way to the next ward, without the doctor having to manually trigger it.

[0084] Optionally, after receiving the doctor's voice query command fragment, the query text can be obtained through speech-to-text transcription. Based on semantic understanding, the patient identifier and information dimensions of the query can be extracted from the patient information mapping table. The system matches the corresponding information content, generates a natural language response text, and converts it into a speech response audio stream via TTS, enabling instant response with a response latency of less than 1 second.

[0085] As can be seen in this example, by first calculating the distance between the doctor and each patient to be examined, and then combining the preset ward round number, distance, and severity of illness for a comprehensive score, and finally determining the ward round order according to the score, the system can simultaneously take into account the optimal ward round path, the standardization of routine procedures, and the priority of critically ill patients. This achieves a balance between path planning and treatment priority, reduces unnecessary back-and-forth trips, and improves the continuity and rationality of ward rounds, thereby significantly improving the overall efficiency of ward rounds.

[0086] S304, based on the ward round order and the database of patients to be ward rounded, send the location data and medical condition data of the next patient to be ward rounded to the name tag recorder.

[0087] The ward round order is determined in step S303, specifying the sequence of patients to be rounded. The ward round database stores patient information such as identity, bed location, medical history, and treatment records. The name tag recorder is a portable smart terminal worn by the ward round patient, capable of receiving and displaying or broadcasting patient information from the backend, facilitating real-time monitoring by doctors. The location and medical history data of the next patient to be rounded refers to information such as bed location, diagnosis, and key medical history of the next patient to be rounded, obtained according to the ward round order.

[0088] Specifically, based on the established ward round order, the corresponding patient information is retrieved from the database of patients to be ward rounded, and the location and condition data of the next patient to be ward rounded are sent in real time to the recorder on the doctor's badge. This allows the doctor to obtain key patient information in advance while moving around, without having to consult additional materials, thus ensuring a smooth and continuous ward round.

[0089] For example, please refer to Figure 8 , Figure 8 This is a schematic diagram illustrating a scenario for confirming the next user to be checked, as provided in an embodiment of this application. Figure 8 As shown, there are 16 patients waiting for rounds, corresponding to numbers 1-16. Patient 4 has already completed the round. At this point, based on the location data of the patient who was rounded, the location data of multiple patients waiting for rounds, and the severity of their conditions, the order of rounds for multiple patients waiting for rounds is determined to be 11-16. At this point, the location data and condition data of patient 11 are sent to the patient who was rounded first.

[0090] As can be seen, in this embodiment, by combining the database of patients to be rounded, the doctor's location data collected by the badge recorder, and the audio data, the progress of the ward round is determined, and the doctor's current ward round node is grasped, avoiding delays or deviations in progress judgment. Then, based on the ward round progress and the preset ward round order, patients to be rounded can be screened, which can narrow down the scope of the ward round and achieve dynamic locking of the patients to be rounded. Furthermore, by combining the doctor's location, the location of the patients to be rounded, and the severity of their conditions, the ward round order is optimized, which can plan the optimal route and prioritize the timely treatment of critically ill patients, taking into account both the rationality of the path and the priority of treatment. Finally, the location and condition information of the next patient are sent to the badge recorder in the determined order, allowing the doctor to obtain key information in advance and reducing the time spent on information retrieval. The overall ward round process is intelligently scheduled, thereby significantly improving the efficiency of doctors' ward rounds.

[0091] In one possible implementation, the method further includes: processing the received audio data collected by the nameplate recorder to obtain the dialogue text between the ward-checking user and the user to be checked; extracting the dialogue text using a named entity recognition model to obtain an entity dataset; processing the entity dataset using a summary generation model to obtain ward-check summary information; and filling the dialogue text, the entity dataset, and the ward-check summary information into a ward-check record template to obtain a ward-check record for the user to be checked.

[0092] Specifically, the audio data collected by the badge recorder is processed through speech recognition and transcription to obtain the dialogue text. The process involves correcting colloquial expressions, adapting to medical dialects, and standardizing medical terminology. This maps colloquial expressions, abbreviations, and slang used in clinical ward rounds to national standard medical terminology, resulting in standardized ward round dialogue texts. .

[0093] Then, based on the finely tuned clinical medical-specific NER (Named Entity Recognition) model, the normalized text is processed. Sequence labeling was performed to extract core medical entities and diagnosis-treatment relationships. The model adopted a BERT-BiLSTM-CRF architecture, and the optimal decoding formula for the label sequence of the CRF layer is as follows: ; in, The optimal label sequence output by the model; The set of all possible label sequences; The output of the BiLSTM layer Each character corresponds to a label. The probability of launch; The labels learned by the CRF layer To tag The transition probability; The total length of characters in the normalized text.

[0094] Using the above model, core medical entities during ward rounds are extracted, including: patient complaints, physical examination results, diagnostic conclusions, changes in medical orders, medication regimens, follow-up requests, and health education content. Simultaneously, the timestamps and speaker information corresponding to each entity are labeled, constructing a structured entity dataset. .

[0095] Based on the extracted entity dataset, a summary generation model is used to extract the core diagnostic and treatment decisions, key concerns of both doctors and patients, and matters requiring follow-up during ward rounds, generating ward round summary information. .

[0096] At the same time, it can monitor compliant image acquisition streams. It associates and annotates with timestamps, dialogue text, and medical entities. For example, the images in the physical examination process are labeled with the entity "physical examination results", thus achieving temporal alignment between audio / video and text information.

[0097] Finally, the structured entity dataset can be generated based on the corresponding ward round record template in the medical record writing standard template library. The entity content is automatically filled into the corresponding field positions in the template. At the same time, based on natural language generation technology, it completes coherent sentences that conform to the medical record writing standards, and generates complete electronic ward round record documents, progress record update paragraphs, and medical order change summaries that meet clinical requirements.

[0098] For the generated electronic documents, multi-dimensional compliance checks are performed, including: verification of the completeness of required fields to ensure that there are no missing fields such as patient basic information, ward round time, attending physician, diagnosis conclusion, and medical order content; verification of the standardization of medical terminology to ensure that the terminology used in the document conforms to the national standard for medical terminology; verification of the consistency of diagnosis and treatment logic to compare the logical consistency between the patient's previous medical records, preoperative diagnosis and the conclusion of this ward round to avoid information contradictions; and verification of the desensitization of privacy information to ensure that there is no unnecessary leakage of patient privacy information in the document.

[0099] For any missing or abnormal items found during compliance checks, corresponding prompts and suggestions for completion are generated and simultaneously pushed to the client device of the visiting user for doctors to confirm and modify.

[0100] As can be seen in this example, by processing the audio data collected by the name tag recorder to generate dialogue text, then using the named entity recognition model to extract key entities and the summary generation model to generate a ward round summary, and finally automatically filling it into the ward round record template to form a complete ward round record, it is possible to achieve automatic transcription of voice information, intelligent extraction of key information and rapid generation of structured medical records during ward rounds, saving doctors the tedious operation of manual data entry, reducing the time spent on supplementary record entry after ward rounds, and improving the overall efficiency of ward rounds.

[0101] Please see Figure 9 , Figure 9 This is a schematic diagram of a ward round device based on a name tag recorder system provided in an embodiment of this application, as shown below. Figure 9 As shown, the ward round device 900 based on the name tag recorder system includes: The first processing unit 901 is used to determine the ward round progress of the ward round based on the database of ward round users, the location data of the ward round users collected by the name tag recorder, and the audio data. The second processing unit 902 is used to determine multiple users to be checked based on the check-up progress of the users and the preset check-up order; The third processing unit 903 is used to determine the ward round order of the multiple ward round users based on the location data of the ward round user, the location data of the multiple ward round users and the severity of their illness; The fourth processing unit 904 is used to send the location data and medical condition data of the next patient to be checked to the name tag recorder based on the ward round order and the database of patients to be checked.

[0102] In one possible implementation, in determining the ward round progress of a user based on a database of users to be ward rounds, location data of users being ward rounds collected by the badge recorder, and audio data, the first processing unit 901 is specifically used to: determine the matching probability between the user being ward rounds and the plurality of users to be ward rounds based on the database of users to be ward rounds, and location data of users being ward rounds collected by the badge recorder; and determine the ward round progress based on the matching probability.

[0103] In one possible implementation, regarding determining the matching probability between a ward-round user and multiple ward-round users based on a database of ward-round users and the location and audio data of ward-round users collected by the name tag recorder, the first processing unit 901 is specifically configured to: determine the location and voiceprint data of multiple ward-round users based on the database of ward-round users; determine the location matching probability between the ward-round user and the multiple ward-round users based on the location data of the multiple ward-round users and the location data of the ward-round user; determine the audio matching probability between the ward-round user and the multiple ward-round users based on the voiceprint and medical condition data of the multiple ward-round users and the audio data of the ward-round user; perform speech recognition on the audio data of the ward-round user to obtain text data; determine the text matching probability between the ward-round user and the multiple ward-round users based on the medical condition data of the multiple ward-round users and the text data; and determine the matching probability based on the location matching probability, the audio matching probability, and the text matching probability.

[0104] In one possible implementation, the first processing unit 901 is further configured to: determine the predicted matching probability between the ward-checking user and the plurality of ward-checking users based on the ward-checking progress; for each ward-checking user, calculate a first product of the predicted matching probability, the location matching probability, the audio matching probability, and the text matching probability between the ward-checking user and each ward-checking user; and normalize the first product to obtain the matching probability between the ward-checking user and each of the plurality of ward-checking users.

[0105] In one possible implementation, regarding determining the ward round order of multiple patients to be ward-rounded based on the location data of the ward-rounding user, a preset ward round number, the location data of the multiple patients to be ward-rounded, and their disease severity, the third processing unit 903 is specifically configured to: determine the distance between the ward-rounding user and the multiple patients to be ward-rounded based on the location data of the ward-rounding user and the location data of the multiple patients to be ward-rounded; obtain a score for each patient to be ward-rounded based on the preset ward round number of each patient to be ward-rounded, the distance between each patient to be ward-rounded and the ward-rounding user, and the disease severity of each patient to be ward-rounded; and obtain the ward round order of the multiple patients to be ward-rounded by sorting the scores of each patient to be ward-rounded in descending order.

[0106] In one possible implementation, regarding obtaining a score for each patient to be examined based on a preset ward round number, the distance between each patient to be examined and the ward round user, and the severity of each patient's condition, the third processing unit 903 is specifically configured to: obtain a second product of a first weight and the reciprocal of the preset ward round number of each patient to be examined; obtain a third product of the second weight and the reciprocal of the distance between each patient to be examined and the ward round user; obtain a fourth product of the third weight and the severity of each patient's condition; and obtain the sum of the second product, the third product, and the fourth product, where the sum is the score of each patient to be examined; wherein the sum of the first weight, the second weight, and the third weight is 1.

[0107] In one possible implementation, the third processing unit 903 is further configured to: process the received audio data collected by the nameplate recorder to obtain the dialogue text between the ward-checking user and the user to be checked; extract the dialogue text using a named entity recognition model to obtain an entity dataset; process the entity dataset using a summary generation model to obtain ward-check summary information; and fill the dialogue text, the entity dataset, and the ward-check summary information into a ward-check record template to obtain a ward-check record for the user to be checked.

[0108] It is worth noting that the specific functional implementation of the ward round device 900 based on the name tag recorder system is described above. Figure 3The description of the ward round method based on the name tag recorder system illustrates that, for example, the first processing unit 901 is used to execute the relevant content of S301, the second processing unit 902 is used to execute the relevant content of S302, the third processing unit 903 is used to execute the relevant content of S303, and the fourth processing unit 904 is used to execute the relevant content of S304. Each unit or module in the ward round device 900 based on the name tag recorder system can be individually or entirely merged into one or more other units or modules, or some of the units or modules can be further divided into multiple functionally smaller units or modules. This achieves the same operation without affecting the technical effect of the embodiments of the present invention. The above-mentioned units or modules are divided according to logical functions. In practical applications, the function of one unit (or module) is implemented by multiple units (or modules), or the function of multiple units (or modules) is implemented by one unit (or module).

[0109] Based on the description of the above method embodiments and related device embodiments, please refer to... Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer provided in an embodiment of this application. Figure 10 The computer 1000 shown includes a processor 1001, a memory 1002, a communication interface 1003, and a bus 1004. The processor 1001, memory 1002, and communication interface 1003 are interconnected via the bus 1004.

[0110] Optionally, the memory 1002 can be ROM, static storage device, dynamic storage device, or RAM.

[0111] Memory 1002 can store executable program code. When the executable program code stored in memory 1002 is executed by processor 1001, processor 1001 and communication interface 1003 are used for execution. Figure 3 The various steps of the ward round method based on the name tag recorder system in the illustrated embodiment.

[0112] The processor 1001 employs a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), GPU, or one or more integrated circuits to execute relevant programs to perform the ward round method based on the badge recorder system of the method embodiments of this application.

[0113] The processor 1001 can also be an integrated circuit chip with signal processing capabilities. In implementation, each step of the room-checking method based on the badge recorder system of this application can be completed through the integrated logic circuits in the hardware of the processor 1001 or through software instructions. Optionally, the processor 1001 can be a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor is a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. Optional software modules are located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 1002. Processor 1001 reads the information in memory 1002 and, in conjunction with its hardware, performs the functions required by the modules included in the ward round device 900 based on the name badge recorder system according to the embodiments of this application, or performs the ward round method based on the name badge recorder system according to the method embodiments of this application.

[0114] The communication interface 1003 uses transceiver-related devices such as, but not limited to, transceivers.

[0115] Bus 1004 may include a pathway for transmitting information between various components of computer 1000 (e.g., memory 1002, processor 1001, communication interface 1003).

[0116] It should be noted that, although Figure 10 The computer 1000 shown only illustrates the memory, processor, and communication interface. However, those skilled in the art should understand that in specific implementations, the computer 1000 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that the computer 1000 may also include hardware devices for implementing other additional functions. Moreover, those skilled in the art should understand that the computer 1000 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 10 All the devices shown.

[0117] This application provides a computer-readable storage medium storing a computer program for electronic data exchange. The computer program includes execution instructions for performing some or all of the steps of any of the ward round methods based on a badge recorder system as described in the above embodiments of the ward round method based on a badge recorder system. The computer includes an electronic client device.

[0118] This application provides a computer program product, which includes a computer program operable to enable the computer to perform some or all of the steps of any of the ward round methods based on a name tag recorder system described in the above method embodiments. The computer program product may be a software installation package.

[0119] It should be noted that, for the sake of simplicity, each of the aforementioned embodiments of the ward round method based on the name tag recorder system is described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to this application.

[0120] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of a ward round method, computer, storage medium, and program product based on a name tag recorder system. The descriptions of the embodiments above are only for the purpose of helping to understand the method and its core ideas of this application. At the same time, for those skilled in the art, based on the ideas of a ward round method, computer, storage medium, and program product based on a name tag recorder system of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

[0121] This application is described with reference to flowchart illustrations and / or block diagrams of methods, hardware products, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0122] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The functions specified in one or more boxes. Memory may include: flash drives, read-only memory (ROM), random access memory (RAM), hard disks or optical disks, etc.

[0123] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0124] Those skilled in the art will understand that all or part of the steps in the various methods of any of the above-described ward round method embodiments based on a name tag recorder system can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk, or an optical disk, etc.

[0125] It is understood that any product that is controlled or configured to execute the processing method described in the flowchart of an embodiment of a ward round method based on a name tag recorder system of this application, such as the device and computer program product of the above flowchart, falls within the scope of the related products described in this application.

[0126] Obviously, those skilled in the art can make various modifications and variations to the room-checking method, computer, storage medium, and program product based on the name badge recorder system provided in this application without departing from the spirit and scope of this application. Therefore, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A ward round method based on a name tag recorder system, characterized in that, A server for a name badge recorder system, wherein the server of the name badge recorder system communicates with the name badge recorders of the name badge recorder system, the method comprising: The ward round progress of the ward round is determined based on the database of ward round users, the location data of the ward round users collected by the name tag recorder, and the audio data. Based on the room-checking progress of the users and the preset room-checking order, multiple users to be checked are identified; The ward round order of the multiple patients to be ward rounded is determined based on the location data of the patients being ward rounded, the location data of the multiple patients to be ward rounded, and the severity of their illnesses. Based on the ward round order and the database of patients to be ward rounded, the location data and medical condition data of the next patient to be ward rounded are sent to the name tag recorder.

2. The method of claim 1, wherein, The step of determining the ward round progress of a user based on the database of users to be rounded, the location data of the users being rounded collected by the name tag recorder, and the audio data includes: Based on the database of users to be checked, as well as the location data and audio data of the users to be checked collected by the name tag recorder, the matching probability between the user to be checked and the multiple users to be checked is determined. The progress of ward rounds is determined based on the matching probability.

3. The method of claim 2, wherein, The step of determining the matching probability between the ward visit user and the multiple ward visit users based on the database of users to be visited, as well as the location data and audio data of the ward visit users collected by the badge recorder, includes: Based on the database of users to be checked, determine the location data and voiceprint data of multiple users to be checked; Based on the location data of the multiple users to be checked and the location data of the user checking, the probability of location matching between the user checking and the multiple users to be checked is determined; Based on the voiceprint data and medical condition data of the multiple patients to be examined, as well as the audio data of the patients to be examined, the probability of audio matching between the patients to be examined and the multiple patients to be examined is determined. The audio data of the users making the ward rounds is subjected to speech recognition to obtain text data; Based on the medical condition data of the multiple patients to be visited and the text data, the text matching probability between the patient to be visited and the multiple patients to be visited is determined; The matching probability is determined based on the location matching probability, the audio matching probability, and the text matching probability.

4. The method as described in claim 3, characterized in that, The method further includes: Based on the progress of the ward rounds, determine the predicted matching probability between the ward round user and the multiple ward round users; For each user to be checked, calculate the first product of the predicted matching probability, the location matching probability, the audio matching probability, and the text matching probability between the user to be checked and each user to be checked. The first product is normalized to obtain the matching probability between the user being checked and each of the multiple users to be checked.

5. The method of claim 1, wherein, The step of determining the ward round order of the multiple patients to be ward rounded based on the location data of the ward round patient, the preset ward round sequence number, the location data of the multiple patients to be ward rounded, and the severity of their illness includes: Based on the location data of the user being checked and the location data of the multiple users to be checked, the distance between the user being checked and the multiple users to be checked is determined; A score is obtained for each patient to be examined based on the preset ward round number, the distance between each patient to be examined and the patient being examined, and the severity of each patient's condition. The room inspection order of the multiple users to be inspected is obtained by sorting each user's score from largest to smallest.

6. The method of claim 5, wherein, The process of obtaining a score for each patient based on their preset ward round number, the distance between each patient and the ward round attendant, and the severity of their condition includes: Obtain the second product of the first weight and the reciprocal of the preset ward inspection number of each user to be inspected; Obtain the third product of the second weight and the reciprocal of the distance between each user to be checked and the user being checked; Obtain the product of the third weight and the severity of the illness of each patient to be examined; Obtain the sum of the second product, the third product, and the fourth product, where the sum is the score of each user to be checked. The sum of the first weight, the second weight, and the third weight is 1.

7. The method according to any one of claims 1 to 6, wherein The method further includes: The audio data collected by the name tag recorder is processed to obtain the dialogue text between the ward-checking user and the user to be checked. The dialogue text is extracted using a named entity recognition model to obtain an entity dataset; The entity dataset is processed by a summary generation model to obtain ward round summary information; By filling the dialogue text, the entity dataset, and the ward round summary information into the ward round record template, a ward round record for the user to be ward round is obtained.

8. An electronic device, comprising: The device includes: The system includes a memory, a processor, and executable program code stored in the memory and executable on the processor, wherein the processor executes the executable program code to perform the steps of the ward round method based on the name badge recorder system as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores executable program code, which includes execution instructions for performing the steps of the ward round method based on the name badge recorder system as described in any one of claims 1-7.

10. A computer program product, characterised in that, The computer program product includes a computer program that causes a computer to perform the steps of the ward round method based on the name badge recorder system as described in any one of claims 1-7.

Images