Scheduling method, confirmation method, device and product

Abstract

The embodiment of the invention provides a scheduling method, a confirmation method, a device and a product, and the method comprises the steps: obtaining voice recognition information according to an emergency voice request through a voice recognition model in response to the emergency voice request containing the emergency condition description audio of a patient and the positioning information of the patient, acquiring illness condition information matched with the emergency illness condition description audio according to the voice recognition information through an emergency illness matching model; acquiring medical institution information of at least one medical institution which has first-aid capability corresponding to the illness state information and is within a preset range with the positioning information; and determining a target medical institution in the at least one medical institution, and notifying the target medical institution to execute medical treatment preparation operation on the patient. By accurately matching the illness state information of the patient and the first-aid capability of the medical institution, the method disclosed by the invention can reasonably allocate medical resources, and unnecessary resource waste is avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of medical rescue technology, and in particular to a dispatching method, a confirmation method, a device and a product. Background Art

[0002] In the field of emergency medical rescue, traditional dispatch methods have many shortcomings, which often lead to low rescue efficiency, inaccurate information transmission and unreasonable resource allocation in practical applications. Specifically, the shortcomings of relevant technologies mainly include the following aspects:

[0003] Emergency medical dispatch in related technologies relies on manual phone calls, and manual questioning and recording of patient descriptions of their conditions. This process takes a long time, especially in emergency situations, where every second counts. Manual processing cannot quickly respond to patients' emergency requests, delaying precious treatment time.

[0004] When manually answering and recording the description of the patient or witness's condition, it is easy to have inaccurate information transmission. On the one hand, due to the tense or chaotic environment, the witness or patient may not be able to clearly describe the condition; on the other hand, the person answering the call may mishear or misunderstand during the recording process, resulting in distorted information. Such inaccurate information may lead to incorrect diagnosis and treatment measures, thus affecting the treatment effect of the patient.

[0005] When selecting a suitable medical institution, the method used in related technologies is usually based on the experience and subjective judgment of the dispatcher. This selection method lacks scientific basis and it is difficult to ensure that the most suitable medical institution can be found every time. Especially in emergency situations, if a hospital without corresponding emergency rescue capabilities is selected, the best time for treatment may be delayed, and even the patient's life safety may be endangered.

[0006] In an emergency, dispatchers need to handle multiple requests at the same time, which puts them under tremendous work pressure. Long hours of high-intensity work can easily lead to fatigue, which in turn affects dispatch efficiency and quality. In addition, when faced with complex and ever-changing emergency situations, it is difficult for dispatchers to make the best decision every time, which increases the difficulty of dispatch work. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the purpose of the present disclosure is to provide a scheduling method, a confirmation method, a device and a product to solve the problems in the related technology.

[0008] A first aspect of the present disclosure provides a dispatching method for emergency treatment, comprising:

[0009] In response to an emergency voice request including an audio describing an emergency condition of a patient and the patient's location information, a voice recognition model is used to obtain voice recognition information according to the emergency voice request, and an emergency disease matching model is used to obtain condition information matching the audio describing the emergency condition according to the voice recognition information;

[0010] Acquire medical institution information of at least one medical institution that has emergency rescue capabilities corresponding to the condition information and is within a predetermined range of the positioning information;

[0011] A target medical institution among the at least one medical institution is determined, and the target medical institution is notified to perform a medical treatment preparation operation for the patient.

[0012] In an embodiment of the first aspect, the obtaining medical institution information of at least one medical institution that has emergency rescue capabilities corresponding to the condition information and is within a predetermined range of the positioning information includes:

[0013] Determine, according to the medical institution address of the at least one medical institution and the positioning information, at least one medical institution that is within a preset range of the positioning information;

[0014] Among at least one medical institution within the preset range of the distance, at least one medical institution with the emergency rescue capability is matched, and corresponding medical institution information is obtained.

[0015] In an embodiment of the first aspect, determining a target medical institution among the at least one medical institution and notifying the target medical institution to perform a medical treatment operation on the patient includes:

[0016] Determine a recommended medical institution based on the at least one medical institution information and send it for confirmation;

[0017] In response to the confirmation about the recommended medical institution, taking the recommended medical institution as a target medical institution and notifying the target medical institution to perform a medical treatment preparation operation for the patient;

[0018] and / or, forming a first recommended medical institution set based on medical institution information of at least one medical institution;

[0019] In response to a medical institution designated by the user based on the first recommended medical institution list, the designated medical institution is used as the target medical institution, and the target medical institution is notified to perform a medical treatment preparation operation for the patient.

[0020] In an embodiment of the first aspect, the method further includes: in response to a patient's request for help, obtaining the patient's location information and instructing the patient to describe the emergency condition to generate the emergency condition description audio;

[0021] Generate an emergency voice request based on the emergency condition description audio, and send the emergency voice request and the positioning information.

[0022] In an embodiment of the first aspect, the condition information includes: basic information of the patient and basic disease information matched according to the emergency condition description audio.

[0023] A second aspect of the present disclosure provides a method for confirming emergency medical treatment, which includes:

[0024] In a human-computer interaction interface, in response to a creation action of an emergency voice request, an emergency condition description audio is generated according to the emergency condition and an emergency voice request is sent; the emergency voice request is used to obtain medical institution information of at least one medical institution that has emergency capabilities corresponding to the condition information and is within a predetermined range from the patient's location information;

[0025] In response to a confirmation operation on a target medical institution among the at least one medical institution, confirmation information is sent.

[0026] In an embodiment of the second aspect, in response to a confirmation operation on a target medical institution among the at least one medical institution, sending confirmation information comprises:

[0027] In response to a confirmation operation of selecting the recommended medical institution as a target medical institution, sending confirmation information;

[0028] and / or,

[0029] In response to the modification operation of the recommended medical institution, a first recommended medical institution list is displayed; the first recommended medical institution list includes at least one medical institution sorted according to the relative distance between the first aid capability / corresponding medical institution and the positioning information;

[0030] In response to an operation of designating the recommended medical institution as a medical institution in the first recommended medical institution list, the recommended medical institution is modified to be a designated medical institution to obtain the target medical institution and sent.

[0031] A third aspect of the present disclosure provides a computer device, comprising:

[0032] Processor and memory;

[0033] The memory stores program instructions;

[0034] The processor is used to run the program instructions to execute any of the scheduling methods described above.

[0035] A fourth aspect of the present disclosure provides a computer-readable storage medium, wherein program instructions are stored, and the program instructions are executed to perform any of the scheduling methods described above.

[0036] A fifth aspect of the present disclosure provides a computer program product, which includes: program instructions for executing any of the scheduling methods described above.

[0037] The beneficial effects of the present disclosure are as follows: audio is converted into text information through a speech recognition model, which greatly shortens the time for information processing, and the text information obtained through speech recognition can be matched with an existing disease database through an emergency disease matching model, thereby accurately identifying the patient's condition information, so that rescue personnel can understand the patient's specific condition more quickly. By accurately matching the patient's condition information and the emergency rescue capabilities of the medical institution, the method of the present disclosure can determine the target medical institution through automated speech recognition and notify it to prepare for emergency rescue, ensuring that the patient can receive treatment immediately after arriving at the hospital. Compared with the method of manually accessing the phone and then processing and dispatching, it effectively improves the efficiency of emergency rescue. Moreover, it improves the reasonable allocation of emergency rescue resources and avoids unnecessary waste of emergency rescue resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a scheduling method in an embodiment of the present disclosure is shown.

[0039] Figure 2 A schematic diagram showing a process of obtaining medical institution information of at least one medical institution in a scheduling method in one embodiment of the present disclosure.

[0040] Figure 3 A schematic diagram of a process for determining a target medical institution among the at least one medical institution in a scheduling method in one embodiment of the present disclosure is shown.

[0041] Figure 4 A schematic diagram showing a flow chart of designating a target medical institution as a designated medical institution in a scheduling method in one embodiment of the present disclosure.

[0042] Figure 5 A schematic diagram showing the process of obtaining emergency voice request and positioning information in a dispatching method in one embodiment of the present disclosure.

[0043] Figure 6 A flowchart of a confirmation method in another embodiment of the present disclosure is shown.

[0044] Figure 7 A schematic flow chart showing a confirmation operation in response to a target medical institution among the at least one medical institution in a confirmation method in another embodiment of the present disclosure is shown.

[0045] Figure 8A schematic diagram showing the structure of a computer device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0046] The following is an explanation of the embodiments of the present disclosure by specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the information disclosed by the present disclosure. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in the present disclosure can also be modified or changed in various ways according to different viewpoints and application modules without departing from the spirit of the present disclosure. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0047] The following is a detailed description of the embodiments of the present disclosure with reference to the accompanying drawings so that those skilled in the art can easily implement the present disclosure. The present disclosure can be embodied in many different forms and is not limited to the embodiments described herein.

[0048] In the representations of the present disclosure, the reference terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" and the like mean that the specific features, structures, materials or characteristics represented in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials or characteristics represented may be combined in any one or a group of embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples represented in the present disclosure and the features of different embodiments or examples, unless they are mutually contradictory.

[0049] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the representation of the present disclosure, "a group" means two or more, unless otherwise clearly and specifically defined.

[0050] In order to clearly describe the present disclosure, components not related to the description are omitted, and the same reference numerals are given to the same or similar components throughout the specification.

[0051] Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" by placing other elements therebetween. In addition, when a device is said to "include" a certain component, unless otherwise stated, it does not exclude other components, but means that other components may be included.

[0052] Although the terms first, second, etc. are used to represent various elements in this article in some examples, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first interface and the second interface, etc. are represented. Moreover, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, modules, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or a group of other features, steps, operations, elements, modules, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Only when the combination of elements, functions, steps or operations is inherently mutually exclusive in some way, will there be an exception to this definition.

[0053] The technical terms used herein are only used to refer to specific embodiments and are not intended to limit the present disclosure. The singular form used herein also includes the plural form unless the sentence clearly indicates the contrary meaning. The meaning of "including" used in the specification is to specify specific characteristics, regions, integers, steps, operations, elements and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements and / or components.

[0054] Although not defined differently, all terms, including technical and scientific terms used herein, have the same meaning as those generally understood by those skilled in the art to which the present disclosure belongs. Terms defined in commonly used dictionaries are additionally interpreted as having meanings consistent with relevant technical literature and the message of the present disclosure, and shall not be overly interpreted as ideal or very formal meanings unless defined.

[0055] Emergency medical dispatch in related technologies relies on manual phone calls, and manual questioning and recording of patient descriptions of their conditions. This process takes a long time, especially in emergency situations, where every second counts. Manual processing cannot quickly respond to patients' emergency requests, delaying precious treatment time.

[0056] When selecting a suitable medical institution, the method used in related technologies is usually based on the experience and subjective judgment of the dispatcher. This selection method lacks scientific basis and it is difficult to ensure that the most suitable medical institution can be found every time. Especially in emergency situations, if a hospital without corresponding emergency rescue capabilities is selected, the best time for treatment may be delayed, and even the patient's life safety may be endangered.

[0057] In one embodiment of the present disclosure, a scheduling method for emergency treatment can be provided, which quickly converts the patient's condition description into text information through a speech recognition model, speeds up information processing, and uses an emergency disease matching model to accurately identify the patient's condition information. At the same time, the method can automatically screen out medical institutions that have corresponding emergency rescue capabilities and are close to the patient, ensuring that the patient can receive treatment as soon as possible, thereby optimizing the allocation of medical resources, avoiding waste of resources, and notifying the target medical institution in advance to prepare. In addition, this method improves the survival rate of patients, ensures that they are effectively treated within the golden rescue time, and at the same time reduces the workload of dispatchers, improves overall scheduling efficiency, simplifies the operating process, and enhances the user experience. In summary, the method of the present disclosure significantly improves the efficiency and effectiveness of emergency medical rescue.

[0058] In one example, after a patient dials an emergency number through a mobile terminal or a landline, after the emergency call is connected, the voice data containing the patient's emergency information is transferred to a server for processing to match the corresponding medical institution based on the patient's emergency information, thereby buying more precious treatment time for the patient and improving the efficiency and success rate of emergency treatment.

[0059] In an exemplary embodiment, Figure 1 FIG. 1 is a flow chart showing a scheduling method in an embodiment of the present disclosure. The scheduling method includes:

[0060] Step S100, in response to an emergency voice request containing an audio description of the patient's emergency condition and the patient's location information, obtain voice recognition information based on the emergency voice request through a voice recognition model, and obtain condition information matching the audio description of the emergency condition based on the voice recognition information through an emergency disease matching model.

[0061] Among them, in some embodiments, when a patient or witness dials an emergency rescue call via a landline or mobile phone, the call is connected to the emergency rescue dispatch center. The system of the dispatch center automatically starts recording or records when the call is answered by a dispatcher, and obtains the caller's location information (if it is a landline, it may be necessary to query the bound address through the address database; if it is a mobile phone, it can be located through GPS or base station). The system of the dispatch center uploads the recording file to the server. The server uses a pre-trained speech recognition model (such as an ASR model based on deep learning) to convert the recording file into text information. In some embodiments, the generated text information can be pre-processed to remove noise words and irrelevant information to ensure the clarity and accuracy of the text. Keywords and phrases related to the condition are extracted from the cleaned text information. Using the emergency disease matching model, the extracted key information is matched with a pre-established condition database. The database contains typical symptoms and descriptions of various common emergency diseases, and can also include the medical history of different patients. According to the matching results, the patient's condition information is determined, including possible disease types, severity, etc. Among them, when a patient needs emergency first aid, there are two situations. One is when the patient can still make a call by himself, the nature of the patient's injury and the patient can describe his symptoms (such as whether the consciousness is a little fuzzy, whether breathing is difficult, bleeding points, etc.), as well as any known medical conditions or drug allergies. Provide the location of the accident accurately, including street name, house number, nearby landmark buildings, etc., so that emergency personnel can quickly find the location. The emergency disease matching model first determines whether the patient is in a state of confusion. When the patient is conscious, the patient disease matching model extracts the symptoms in the patient's emergency condition description audio and matches it. Alternatively, the dispatcher can also determine the patient's state of consciousness. When the patient is conscious, the patient's emergency condition description audio is sent to the emergency disease matching model for further disease matching. The second situation is that the patient may not be able to make a call by himself, and the emergency call is made by a bystander. Since the call is made by a bystander, the patient's symptoms are described by the bystander, so the patient's injury point may be clearly visible or not. When the patient's injury point is clearly visible and the bystander's description is more detailed, the bystander's description information can be marked as credible information. When the patient's injury point is not obvious or does not exist, it is necessary to further judge the patient's injury or possible disease through the patient's posture. Therefore, when processing voice requests, the patient's posture can be used as reference information. For example, the user's current action described in the voice request, such as covering the chest or stomach, may correspond to the pain in that place, which helps to effectively reflect the location of the lesion.In addition, the caller may not be able to clearly describe the condition and the condition described may also contain errors. Therefore, the condition information determined by the emergency disease matching model may contain multiple diseases, causing the patient to have coma-like symptoms, which may be heart problems or brain problems. The credibility of the condition information can be determined according to the identity of the caller. For example, when the caller is a doctor, the information provided is the most credible, followed by other medical-related personnel, and the credibility of ordinary passers-by is the lowest. Therefore, the dispatcher can consult the caller information at the beginning, or extract the caller information from the voice request. In addition, if the patient's identity information can be obtained (for example, the caller is an acquaintance of the patient), the patient's medical history can be used to match the currently determined condition information to further determine the credibility of the condition information. The two credibility levels can complement each other or choose the most credible one. If the condition information is determined to be credible according to the credibility (for example, the credibility is higher than a certain threshold), the target hospital can be determined according to the condition information; if the condition information cannot be determined to be credible according to the credibility, it is processed according to the most credible condition information and matched in combination with the patient's medical history.

[0062] After obtaining the patient's condition information, Figure 1 In step S200, the medical institution information of at least one medical institution having emergency rescue capabilities corresponding to the condition information and being within a predetermined range of the positioning information is obtained.

[0063] In some embodiments, the emergency rescue capability requirements required by the corresponding medical institution are determined according to the condition information obtained by the emergency disease matching model in step S100. For example, the condition information may include the specific location of the disease attack, such as a heart attack usually requires a medical institution with cardiopulmonary resuscitation (CPR), defibrillator use, and acute coronary syndrome (ACS) processing capabilities. According to the emergency rescue capability requirements and the patient's location information (longitude, latitude or specific location), set query conditions, such as the type of emergency rescue capability, distance range, etc. Send a query request to the database containing medical institution information to obtain a list of qualified medical institutions. This information usually includes the name of the hospital, the address, the distance from the patient's location, whether it has the required emergency rescue capabilities, etc. In some embodiments, among the medical institutions that meet the emergency rescue capability requirements, they can be sorted according to the distance, and one or more medical institutions with the required emergency rescue capabilities closest to the patient are selected as the target rescue institutions.

[0064] After obtaining at least one medical institution that meets the emergency rescue capabilities and is within a preset distance, step S300 is used to determine a target medical institution among the at least one medical institution, and to notify the target medical institution to perform medical treatment preparation operations for the patient.

[0065] Among them, in some embodiments, the current status of each medical institution can be further evaluated based on the medical institution information obtained in step S200, such as the number of available beds, whether the emergency equipment is intact, whether there are sufficient medical staff and other factors. Considering the distance, emergency capacity and current load, select the most suitable medical institution as the target rescue agency. If there are multiple qualified medical institutions, additional factors such as their professional expertise and historical treatment success rate can also be considered. For example: Evaluate the status information of medical institutions A and B, and confirm that Hospital A currently has vacant beds, complete emergency equipment and sufficient medical staff, while Hospital B is closer but the current load is larger. After comprehensive consideration, medical institution A is selected as the target rescue agency.

[0066] After determining the target medical institution, create a notification message containing the patient's basic information (such as name, age, gender), description of the condition, estimated time of arrival, etc. Send the notification message to the relevant person in charge of the target medical institution through various means such as phone, text message, and dedicated medical communication system to ensure that the information is received and processed in a timely manner. Notify the hospital emergency department to prepare necessary emergency equipment, such as defibrillators, oxygen cylinders, emergency drugs, etc. Arrange doctors and nurses with corresponding emergency capabilities to be on standby.

[0067] Optional, Figure 2 The example is a flowchart of obtaining medical institution information of at least one medical institution that has emergency rescue capabilities corresponding to the condition information and is within a predetermined range of the location information, including:

[0068] Step S210, determining at least one medical institution within a preset range of the positioning information according to the medical institution address of the at least one medical institution and the positioning information;

[0069] Step S220, matching at least one medical institution with the emergency rescue capability among at least one medical institution within the preset range of the distance, and acquiring corresponding medical institution information.

[0070] Specifically, in some embodiments, the patient's location information is obtained from the location of the patient's emergency call, which usually includes the patient's latitude and longitude coordinates, as well as specific coordinate points. The location information of all available medical institutions is read from the database, and the location information also includes latitude and longitude coordinates. Use a suitable algorithm (such as Haversine formula or Vincenty formula) to calculate the distance between each medical institution and the patient's current location. According to the actual situation, a reasonable distance threshold is set as a preset range, such as 5 kilometers, 10 kilometers, etc. All medical institutions are sorted according to the distance, and those medical institutions whose distance is less than or equal to the preset range are obtained. According to the condition information (such as "suspected heart attack" and "high" severity) provided by the emergency disease matching model in step 100, the required emergency rescue capability requirements are determined. For example, a heart attack usually requires a medical institution with cardiopulmonary resuscitation (CPR), defibrillator use, and acute coronary syndrome (ACS) processing capabilities. From the medical institutions screened out in step S210, medical institutions with the required emergency rescue capabilities are further screened out. For example, which of medical institutions A, B, and C have the above-mentioned emergency rescue capabilities. Obtain detailed information of successfully matched medical institutions from the database, including hospital name, address, contact number, emergency response capabilities, etc.

[0071] In some embodiments, existing geographic information system (GIS) services and APIs can also be used to implement the screening and matching of medical institutions. The advantage of this approach is that it can utilize the powerful functions provided by existing map service providers (such as Google Maps API, Baidu Maps API, etc.), simplify the development process and improve the reliability and accuracy of the system.

[0072] Optional, Figure 3 The example is a flowchart of determining a target medical institution among the at least one medical institution and notifying the target medical institution to perform a medical treatment operation on the patient, which specifically includes:

[0073] Step S311, determining a recommended medical institution based on the at least one medical institution information and sending it for confirmation;

[0074] Step S312, in response to the confirmation of the recommended medical institution, taking the recommended medical institution as a target medical institution, and notifying the target medical institution to perform a medical treatment preparation operation for the patient.

[0075] Specifically, in some embodiments, based on the medical institution information screened out in step S200, the current status of each medical institution is further evaluated, such as the number of available beds, whether the emergency equipment is intact, whether there are sufficient medical staff, and other factors. Considering the distance, emergency capacity and current load, the recommended medical institution is determined. Create a message containing the basic information of the recommended medical institution (such as name, address, contact information, emergency capacity, etc.), and attach the basic information of the patient (such as name, age, description of the condition). Send the information of the recommended medical institution to the dispatch center or relevant decision makers for confirmation. The dispatch center or the patient confirms whether the recommended medical institution is suitable. Once the recommended medical institution is confirmed, the server will send a notification to the medical institution to inform it that it is ready to receive the patient and provide treatment.

[0076] Optional, Figure 4 An example is a flowchart that designates a target medical institution as a designated medical institution, including:

[0077] Step S321, forming a first recommended medical institution set based on medical institution information of at least one medical institution;

[0078] Step S322, in response to the medical institution designated by the user based on the first recommended medical institution list, the designated medical institution is used as the target medical institution, and the target medical institution is notified to perform medical treatment preparation operations for the patient.

[0079] Specifically, in some embodiments, all medical institution information that may receive patients is obtained from a database or other source, and this information may include but is not limited to the name, location, current occupancy rate, treatment capacity of specific diseases, etc. of the hospital. For each medical institution, its ability to receive patients is evaluated, including the distance from the patient's location, whether there are enough beds, whether there are professional departments that specialize in treating the diseases required by patients, etc. According to the analysis results, medical institutions that meet the conditions are selected to form a first set of recommended medical institutions. The medical institutions in this set should be the most likely to provide the best treatment effect for patients. The first set of recommended medical institutions is presented to users (such as operators of emergency centers or family members of patients) for their selection. The user selects one of the medical institutions as the hospital that finally accepts the patient based on his own judgment. Once the user specifies a medical institution, the server sets the medical institution as the target medical institution and sends a notification to it, allowing the medical institution to start preparing to receive patients.

[0080] Optional, Figure 5 The example is a flowchart of obtaining emergency voice request and location information. Figure 5 In the example, the scheduling method further includes:

[0081] Step S400, in response to the patient's call for help, obtaining the patient's location information and instructing the patient to describe the emergency condition to generate the emergency condition description audio;

[0082] Step S500, generating an emergency voice request based on the emergency condition description audio, and sending the emergency voice request and the positioning information.

[0083] Specifically, in some embodiments, when a patient's call for help is detected (such as pressing an emergency button, using a mobile phone application to send an SOS signal, etc.), the server automatically responds or the dispatcher connects the call. The GPS function of the patient's mobile device (such as a smart phone) is used to obtain the patient's current location information. If the patient's device does not have a GPS function, the location can be estimated through a base station or other means. The server or dispatcher guides the patient or nearby personnel to describe the current emergency situation through voice prompts, including but not limited to key information such as symptoms, duration, and previous medical history. During the patient's description, the phone is recorded and an audio file describing the emergency condition is generated. If the patient is unable to describe the situation (such as coma), the recording may contain ambient sound or other people's descriptions.

[0084] The server converts the emergency condition description audio into a voice request format, which may be achieved by attaching the audio file to the request, or transcribing it into text information using a speech recognition model. The generated emergency voice request is sent to the emergency center or the nearest medical institution along with the patient's location information, such as a phone call, text message, dedicated emergency service application, etc. After sending the request, wait for the emergency center's confirmation and next instructions, while continuing to monitor the patient's condition and update the emergency center if necessary.

[0085] Optionally, the medical condition information includes: basic information of the patient and basic disease information matched according to the audio description of the emergency condition.

[0086] Specifically, in some embodiments, the basic information of the patient may include: identity information: name, gender, age, ID number (in some cases), contact information, etc. Or a summary of the health record: including important medical history such as allergies, chronic diseases, previous surgical records, blood type, etc. And emergency contacts: information about family or friends who can be contacted in an emergency. When necessary, insurance information may also be included: medical insurance coverage, insurance company contact information, etc. Among them, basic disease information can be obtained through symptom descriptions, such as: symptoms described by the patient in an emergency, such as chest pain, difficulty breathing, confusion, etc. Onset time: the time when the patient first noticed the symptoms. Symptom progression: how the symptoms change over time, whether they worsen or ease. Through the information in the emergency condition description audio, the emergency disease matching model is used to preliminarily determine the type of disease that may be involved, and preliminary treatment recommendations are given based on the existing information before professional medical personnel arrive.

[0087] The matching process through the emergency disease matching model includes: extracting relevant symptom keywords from the text information converted from audio. Comparing the extracted symptoms with common diseases in the system's internal or external medical database. Generating a list of possible diseases and corresponding probability assessments based on the matching results. Integrating the patient's basic information with the basic disease information to form a complete medical report.

[0088] In another embodiment of the present disclosure, a method for confirming emergency medical treatment may be provided, wherein: Figure 6 The example is a flow chart of the confirmation method, which specifically includes:

[0089] Step A100, in response to the creation action of the emergency request, generating an emergency condition description audio according to the emergency condition and sending an emergency voice request on a human-computer interaction interface; the emergency voice request is used to obtain medical institution information of at least one medical institution that has emergency capabilities corresponding to the condition information and is within a predetermined range from the patient's location information;

[0090] Step A200, sending confirmation information in response to a confirmation operation on a target medical institution among the at least one medical institution.

[0091] Specifically, in some embodiments, the user triggers an emergency request through a specific application or an emergency button on a smart device (such as a smart phone, smart watch or other wearable device). The server can automatically guide or the dispatcher can guide the user to describe the current emergency condition, or it can automatically detect the user's physiological parameters (if supported by the device). This information will be used to generate an audio description of the emergency condition. Based on the information provided by the user or the results of automatic detection, the server generates a voice request containing the patient's basic information and current condition, and sends it to the emergency dispatch center through the network.

[0092] According to the patient's location information (usually obtained through GPS or other positioning technology), medical institutions within a certain range near the patient are screened out. Among these medical institutions, institutions with emergency treatment capabilities corresponding to the condition information are further screened out. Target medical institutions that meet the conditions are displayed to the user for selection. Or the automatically screened target medical institutions are directly displayed. The user's confirmation information is sent to the selected target medical institution to start the emergency treatment process.

[0093] Optional, Figure 7 The example is a flowchart of sending confirmation information in response to a confirmation operation on a target medical institution among the at least one medical institution, which includes:

[0094] In response to a confirmation operation of taking the recommended medical institution as a target medical institution, confirmation information is transmitted.

[0095] Specifically, in some embodiments, the server recommends a most suitable medical institution as the target medical institution based on the patient's condition information and geographical location information, and the user confirms the recommendation on the human-computer interaction interface, indicating that he agrees to go to the medical institution.

[0096] Optionally, when the user does not accept the target medical institution initially recommended by the system, the user may choose to modify the recommendation result and select a new target medical institution from an optimized and sorted list of first recommended medical institutions. Figure 7 As shown in:

[0097] In response to the modification operation of the recommended medical institution, a first recommended medical institution list is displayed; the first recommended medical institution list includes at least one medical institution sorted according to the relative distance between the first aid capability / corresponding medical institution and the positioning information;

[0098] In response to an operation of designating the recommended medical institution as a medical institution in the first recommended medical institution list, the recommended medical institution is modified to be a designated medical institution to obtain the target medical institution and sent.

[0099] Specifically, in some embodiments, after the user selects a medical institution as a new target medical institution in the first recommended medical institution list, the recommended medical institution is updated to the medical institution selected by the user. The server sends the updated confirmation information to the new target medical institution and notifies it that it is ready to receive patients. Through such a process, even if the initial recommendation may not be the best choice, the user has the opportunity to find an emergency service provider that is more suitable for him / her, thereby improving the emergency experience and service quality.

[0100] like Figure 8, which shows a schematic diagram of the structure of a computer device in one embodiment of the present disclosure.

[0101] The computer device 600 may be exemplified as a processing terminal, such as a server, a desktop computer, a laptop computer, a tablet computer, a smart phone, or other terminals.

[0102] The computer device 600 includes a bus 601, a processor 602, and a memory 603. The processor 602 and the memory 603 can communicate with each other through the bus 601. The memory 603 can store program instructions. The processor 602 implements the steps of the scheduling method or the determination method in the previous embodiment by running the program instructions in the memory 603, for example Figure 1 or Figure 6 .

[0103] The bus 601 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, although only one thick line is used in the figure, it does not mean that there is only one bus or one type of bus.

[0104] In some embodiments, the processor 602 may be implemented as a central processing unit (CPU), a microprocessing unit (MCU), a system on chip (System On Chip), or a field programmable logic array (FPGA). The memory 603 may include a volatile memory (Volatile Memory) for temporary storage of data when running a program, such as a random access memory (Random Access Memory, RAM).

[0105] The memory 603 may also include a non-volatile memory (non-volatile memory) for data storage, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state disk (SSD).

[0106] In some embodiments, the computer device 600 may further include a communicator 604. The communicator 604 is used to communicate with the outside. In a specific example, the communicator 604 may include one or a group of wired and / or wireless communication circuit modules. For example, the communicator 604 may include one or more of a wired network card, a USB module, a serial interface module, etc. The wireless communication protocols followed by the wireless communication module include: for example, near field communication (NFC) technology, infrared (IR) technology, Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time-Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Bluetooth (BT), Global Navigation Satellite System (GNSS), etc. One or more.

[0107] In an embodiment of the present disclosure, a computer-readable storage medium may be provided, storing program instructions, which implement the scheduling method or determination method in any of the previous embodiments when executed.

[0108] That is, the method steps in the above embodiments are implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or are implemented as computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded via a network and to be stored in a local recording medium, so that the method represented herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA).

[0109] The above embodiments are merely illustrative of the principles and effects of the present disclosure, and are not intended to limit the present disclosure. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present disclosure. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present disclosure shall still be covered by the protection scope of the present disclosure.

Claims

1. A dispatching method for emergency treatment, characterized in that: include: In response to an emergency voice request including an audio describing an emergency condition of a patient and the patient's location information, a voice recognition model is used to obtain voice recognition information according to the emergency voice request, and an emergency disease matching model is used to obtain condition information matching the audio describing the emergency condition according to the voice recognition information; Acquire medical institution information of at least one medical institution that has emergency rescue capabilities corresponding to the condition information and is within a predetermined range of the positioning information; A target medical institution among the at least one medical institution is determined, and the target medical institution is notified to perform a medical treatment preparation operation for the patient.

2. The scheduling method according to claim 1, characterized in that: The obtaining of medical institution information of at least one medical institution having emergency rescue capabilities corresponding to the condition information and being within a predetermined range of the positioning information includes: Determine, according to the medical institution address of the at least one medical institution and the positioning information, at least one medical institution that is within a preset range of the positioning information; Among at least one medical institution within the preset range of the distance, at least one medical institution with the emergency rescue capability is matched, and corresponding medical institution information is obtained.

3. The scheduling method according to claim 1, characterized in that: The step of determining a target medical institution among the at least one medical institution and notifying the target medical institution to perform a medical treatment operation on the patient includes: Determine a recommended medical institution based on the at least one medical institution information and send it for confirmation; In response to the confirmation about the recommended medical institution, taking the recommended medical institution as a target medical institution and notifying the target medical institution to perform a medical treatment preparation operation for the patient; and / or, forming a first recommended medical institution set based on medical institution information of at least one medical institution; In response to a medical institution designated by the user based on the first recommended medical institution list, the designated medical institution is used as the target medical institution, and the target medical institution is notified to perform a medical treatment preparation operation for the patient.

4. The scheduling method according to claim 1, characterized in that: Also includes: In response to the patient's call for help, obtaining the patient's location information and instructing the patient to describe the emergency condition to generate the emergency condition description audio; Generate an emergency voice request based on the emergency condition description audio, and send the emergency voice request and the positioning information.

5. The scheduling method according to claim 1, characterized in that: The medical condition information includes: basic information of the patient and basic disease information matched according to the audio of the emergency condition description.

6. A method for confirming emergency medical treatment, characterized in that: include: In a human-computer interaction interface, in response to a creation action of an emergency voice request, an emergency condition description audio is generated according to the emergency condition and an emergency voice request is sent; The first aid voice request is used to obtain medical institution information of at least one medical institution that has first aid capabilities corresponding to the condition information and is within a predetermined range from the patient's location information; In response to a confirmation operation on a target medical institution among the at least one medical institution, confirmation information is sent.

7. The confirmation method according to claim 6, characterized in that: The sending of confirmation information in response to the confirmation operation on the target medical institution among the at least one medical institution comprises: In response to a confirmation operation of selecting the recommended medical institution as a target medical institution, sending confirmation information; and / or, In response to the modification operation of the recommended medical institution, a first recommended medical institution list is displayed; the first recommended medical institution list includes at least one medical institution sorted according to the relative distance between the first aid capability / corresponding medical institution and the positioning information; In response to an operation of designating the recommended medical institution as a medical institution in the first recommended medical institution list, the recommended medical institution is modified to be a designated medical institution to obtain the target medical institution and sent.

8. A computer device, characterized in that: include: Processor and memory; The memory stores program instructions; The processor is used to run the program instructions to execute the scheduling method according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that: Program instructions are stored, and the program instructions are executed to perform the scheduling method according to any one of claims 1 to 5.

10. A computer program product, characterized in that include: Program instructions for executing the scheduling method according to any one of claims 1 to 5.

Images