Diagnosis department sorting method and device, electronic equipment and storage medium

Abstract

The invention provides a doctor-seeing department sorting method and device, electronic equipment and a storage medium, and relates to the technical field of data processing and intelligent medical treatment. The method comprises the following steps: acquiring treatment data of a historical patient as sample data, and training a large model based on the sample data to obtain a target large model; acquiring treatment information of the patient and a first position of the patient on a hospital map, and determining a target department of the patient needing treatment and a second position of the target department on the hospital map based on the treatment information; performing structured processing on the first position, the second position and the treatment information to obtain structured reference information; and sorting the target departments by the target large model based on the structured reference information, and outputting structured data of a department doctor seeing sequence. Therefore, according to the scheme, more accurate and quicker treatment navigation information can be provided for the patient, and the treatment efficiency of the patient and the service quality of a hospital are improved.

Description

Technical Field

[0001] The present disclosure relates to the fields of data processing and intelligent medical technology, and in particular to a method, device, electronic device and storage medium for sorting visiting departments. Background Art

[0002] Hospital intelligent navigation systems can provide patients with accurate and detailed navigation information, but existing technologies mostly rely on fixed map software to provide static guide maps or basic indoor instructions, lacking real-time positioning and personalized navigation. Although some attempts have been made to combine positioning services, they have not been effectively integrated into the entire medical process, such as registration, consultation, payment, testing, treatment, and medication collection. Summary of the invention

[0003] The present invention provides a method, device, electronic device and storage medium for sorting visiting departments, which are used to solve the problem of wasting time searching for departments due to large flow of patients and complex routes in hospitals.

[0004] To this end, an object of the present disclosure is to propose a method for sorting visiting departments.

[0005] The second objective of the present disclosure is to provide a device for sorting medical departments.

[0006] A third objective of the present disclosure is to provide an electronic device.

[0007] A fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0008] A fifth object of the present disclosure is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes a method for sorting visiting departments, including: obtaining historical patient visiting data as sample data, and performing structured processing on the sample data to obtain structured sample data; pre-configuring prompt words and output reference examples of a large model, and training the large model in combination with the structured sample data to obtain a target large model; obtaining visiting information of visiting patients and a first position of the visiting patients on a hospital map, and based on the visiting information, determining the destination department that the visiting patient needs to visit and the second position of the destination department on the hospital map; performing structured processing on the first position, the second position and the visiting information to obtain structured reference information; generating prompt words of the target large model based on the structured reference information, and inputting the prompt words into the target large model, and having the target large model sort the destination departments based on the prompt words, and outputting structured data of the department visiting sequence; feeding back the structured data to a client, and obtaining the department visiting sequence by parsing the structured data through the client.

[0010] According to one embodiment of the present disclosure, the first position, the second position and the medical information are structured to obtain structured reference information, including: obtaining the number of patients waiting for treatment in the target department and the execution time of the medical treatment items associated with the target department, and adding the number of patients waiting for treatment and the execution time to the medical information; using the first position, the second position and the medical information as sorting reference information, and structured processing the sorting reference information to obtain structured reference information.

[0011] According to one embodiment of the present disclosure, the generating of prompt words of the target large model based on the structured reference information includes: obtaining a prompt word generation template pre-configured for the target large model, and determining a filling position of each type of information in the structured reference information in the prompt word generation template; and writing each type of information in the structured reference information into the prompt word generation template according to the filling position to generate prompt words for the target large model.

[0012] According to one embodiment of the present disclosure, before the structuring processing of the sorting reference information to obtain the structured reference information, it also includes: acquiring the attribute information of the patient based on the medical information of the patient, wherein the attribute information includes at least the gender and age of the patient; using the attribute information of the patient as new reference information, and adding the attribute information to the sorting reference information.

[0013] According to one embodiment of the present disclosure, the target big model sorts the target departments based on the prompt words and outputs the structured data of the department visit sequence, including: the target big model sorts the target departments based on the prompt words to obtain the department visit sequence; and structures the department visit sequence based on a pre-configured output reference example to output the structured data of the department visit sequence.

[0014] According to one embodiment of the present disclosure, the department visit sequence is structured based on a preconfigured output reference example to output structured data of the department visit sequence, including: obtaining the department name and sorting number of the target department; for any target department i among the target departments that need to be visited, based on the sorting number of the target department, obtaining the target department that is arranged behind and adjacent to the target department i, and based on the target department i and the adjacent target department, generating path information of the target department i, wherein i is a natural number greater than or equal to 1; based on the output reference example, based on the department name, sorting number and path information of the target department i, generating the target information of the target department i, and sequentially combining the target information of each target department according to the sorting number of the target department to generate the structured data of the department visit sequence.

[0015] According to one embodiment of the present disclosure, the process of obtaining the first position of the patient on the hospital map includes: receiving a wireless access signal sent by a terminal device of the patient, and determining the first position of the terminal device on the hospital map based on the signal strength and local area network address of the wireless access signal.

[0016] According to one embodiment of the present disclosure, after the structured data is fed back to the client, it also includes: obtaining the node selection operation sent by the client; determining the destination department selected by the node selection operation, and taking the selected destination department as the navigation end point; obtaining the navigation starting point corresponding to the current patient; planning the path for the patient according to the navigation starting point and the navigation terminal, generating a navigation path corresponding to the node selection operation, and feeding back to the client.

[0017] According to one embodiment of the present disclosure, obtaining the navigation starting point currently corresponding to the patient includes: determining whether the patient has a previous destination department before the node selection operation; in response to the previous destination department not existing, determining the first position of the patient as the navigation starting point; in response to the previous destination department existing, determining the previous destination department as the navigation starting point.

[0018] According to one embodiment of the present disclosure, the obtaining of historical patient medical data as sample data and structuring the sample data to obtain structured sample data includes: obtaining historical patient medical data as sample data, wherein the sample data includes historical attribute information of the historical patient and historical department medical visit sequence; marking the department location, planned path and obstacles in the historical department medical visit sequence according to the hospital map to obtain department marking data; structuring the department marking data, the number of waiting people and execution time of the department, and the historical attribute information of the historical patient to obtain structured sample data.

[0019] According to one embodiment of the present disclosure, the method further includes: monitoring feedback information of the visiting patient, and in response to monitoring the feedback information, determining that the visiting patient is a sample patient for model optimization; based on the feedback information, determining the sample type of the sample patient; in response to the amount of the feedback information reaching a set value, using the visiting data of the sample patient as a model optimization sample, and fine-tuning the target large model based on the model optimization sample.

[0020] To achieve the above-mentioned purpose, the second embodiment of the present disclosure proposes a device for sorting visiting departments, including: a first processing module, used to obtain historical patient visiting data as sample data, and perform structured processing on the sample data to obtain structured sample data; a training module, used to pre-configure prompt words and output reference examples of a large model, and train the large model in combination with the structured sample data to obtain a target large model; a determination module, used to obtain the visiting information of the visiting patient and the first position of the visiting patient on the hospital map, and determine the target department that the visiting patient needs to visit based on the visiting information. room, and a second position of the target department on the hospital map; a second processing module, used to perform structured processing on the first position, the second position and the medical information to obtain structured reference information; a sorting module, used to generate prompt words of the target large model based on the structured reference information, and input the prompt words into the target large model, and the target large model sorts the target departments based on the prompt words, and outputs structured data of the department medical sequence; a parsing module, used to feed back the structured data to the client, and obtain the department medical sequence by parsing the structured data through the client.

[0021] According to one embodiment of the present disclosure, the second processing module is also used to: obtain the number of patients waiting to visit the target department and the execution time of the medical treatment items associated with the target department, and add the number of patients waiting to visit and the execution time to the medical information; use the first position and the second position and the medical information as sorting reference information, and perform structured processing on the sorting reference information to obtain structured reference information.

[0022] According to one embodiment of the present disclosure, the sorting module is further used to: obtain a prompt word generation template pre-configured for the target large model, and determine a filling position of each type of information in the structured reference information in the prompt word generation template; and write each type of information in the structured reference information into the prompt word generation template according to the filling position to generate prompt words for the target large model.

[0023] According to one embodiment of the present disclosure, the second processing module is further used to: obtain attribute information of the patient based on the patient's medical information, wherein the attribute information at least includes the gender and age of the patient; use the attribute information of the patient as new reference information, and add the attribute information to the sorting reference information.

[0024] According to one embodiment of the present disclosure, the sorting module is further used for: the target big model sorts the target departments based on the prompt words to obtain a department visit sequence; and structures the department visit sequence based on a pre-configured output reference example to output structured data of the department visit sequence.

[0025] According to one embodiment of the present disclosure, the sorting module is also used to: obtain the department name and sorting number of the target department; for any target department i among the target departments that need to be treated, based on the sorting number of the target department, obtain the target department that is arranged behind and adjacent to the target department i, and based on the target department i and the adjacent target department, generate the path information of the target department i, where i is a natural number greater than or equal to 1; based on the output reference example, based on the department name, sorting number and path information of the target department i, generate the target information of the target department i, and sequentially combine the target information of each target department according to the sorting number of the target department to generate structured data of the department visit sequence.

[0026] According to one embodiment of the present disclosure, the determination module is further used to: receive a wireless access signal sent by a terminal device of the patient, and determine a first position of the terminal device on the hospital map based on the signal strength and local area network address of the wireless access signal.

[0027] According to one embodiment of the present disclosure, the parsing module is also used to: obtain the node selection operation sent by the client; determine the destination department selected by the node selection operation, and use the selected destination department as the navigation end point; obtain the navigation starting point currently corresponding to the patient; plan the path for the patient based on the navigation starting point and the navigation terminal, generate a navigation path corresponding to the node selection operation, and feedback to the client.

[0028] According to one embodiment of the present disclosure, the parsing module is also used to: determine whether the patient has a previous destination department for treatment before the node selection operation; in response to the absence of the previous destination department for treatment, determine the first position of the patient as the navigation starting point; in response to the existence of the previous destination department for treatment, determine the previous destination department for treatment as the navigation starting point.

[0029] According to one embodiment of the present disclosure, the first processing module is further used to: obtain historical patient medical treatment data as sample data, wherein the sample data includes historical attribute information of the historical patients and historical department medical treatment sequences; mark the department locations, planned paths and obstacles in the historical department medical treatment sequences according to the hospital map to obtain department marking data; and perform structured processing on the department marking data, the number of waiting people and execution time of the department, and the historical attribute information of the historical patients to obtain structured sample data.

[0030] According to one embodiment of the present disclosure, the first processing module is further used to: monitor the feedback information of the patient, and in response to monitoring the feedback information, determine that the patient is a sample patient for model optimization; based on the feedback information, determine the sample type of the sample patient; in response to the amount of the feedback information reaching a set value, use the sample patient's visit data as a model optimization sample, and fine-tune the target large model based on the model optimization sample.

[0031] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the method for sorting visiting departments as described in the first aspect embodiment of the present disclosure.

[0032] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the method for sorting medical departments as described in the first aspect embodiment of the present disclosure.

[0033] To achieve the above-mentioned purpose, the fifth aspect of the present disclosure proposes a computer program product, including a computer program, which, when executed by a processor, is used to implement the method for sorting visiting departments as described in the first aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0035] Figure 1 A flowchart of a method for sorting visiting departments provided in an embodiment of the present disclosure;

[0036] Figure 2 A flowchart of another method for sorting visiting departments provided in an embodiment of the present disclosure;

[0037] Figure 3 A flowchart of another method for sorting visiting departments provided in an embodiment of the present disclosure;

[0038] Figure 4 A flowchart of another method for sorting visiting departments provided in an embodiment of the present disclosure;

[0039] Figure 5 An example flow chart of a training process of a target large model in a method for ranking visiting departments provided in an embodiment of the present disclosure;

[0040] Figure 6 An example diagram of an interaction for a patient to obtain a department visit sequence provided by an embodiment of the present disclosure;

[0041] Figure 7 A structural example diagram of a device for sorting visiting departments provided in an embodiment of the present disclosure;

[0042] Figure 8 This is a diagram showing an example structure of an electronic device provided in an embodiment of the present disclosure.

[0043] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0044] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0045] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0046] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the provisions of relevant laws and regulations.

[0047] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards.

[0048] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the relevant content of the solution.

[0049] Figure 1 This is an example flow chart of the method for sorting visiting departments provided in the embodiment of the present disclosure. Figure 1 As shown, the sorting methods for this visiting department include:

[0050] S101, obtaining historical patient medical data as sample data, and performing structured processing on the sample data to obtain structured sample data.

[0051] It should be noted that the execution subject of the method for sorting the visiting departments provided in the embodiment of the present disclosure is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc. The embodiment of the present disclosure is not specifically limited.

[0052] In some implementations, the medical treatment data of historical patients can be obtained based on the Hospital Information System (HIS). The medical treatment data of historical patients can be obtained from the HIS by sending a request message containing the identification information of historical patients to the HIS, and the medical treatment data can be used as sample data to train the large model. The medical treatment data includes but is not limited to: historical attribute information of historical patients and historical department medical treatment sequences.

[0053] Furthermore, the sample data may be subjected to structural processing to obtain structured sample data, wherein the format of the structured sample data may be JS key-value pair data (JavaScript Object Notation, JSON) or Extensible Markup Language (Extensible Markup Language, XML).

[0054] S102, pre-configure the prompt words and output reference examples of the large model, and train the large model in combination with the structured sample data to obtain the target large model.

[0055] In some implementations, the big model is trained by pre-configuring the prompt words and output reference examples of the big model, and inputting the prompt words, output reference examples, and structured sample data into the big model, so that the big model can understand maps, path planning, and sorting, and output a predicted department visit sequence that conforms to the output reference examples.

[0056] Optionally, the combined structured sample data can be divided into a training set and a validation set, and the training set can be used to train the large model to obtain a predicted department visit sequence. Then, the historical department visit sequence and the predicted department visit sequence in the validation set can be used to adjust the model's hyperparameters to improve the model's accuracy and obtain the target large model.

[0057] S103, obtaining the patient's medical information and the patient's first position on the hospital map, and based on the medical information, determining the destination department that the patient needs to visit and the destination department's second position on the hospital map.

[0058] Optionally, a request message including identification information of the patient is sent to the HIS to obtain the patient's medical information from the HIS, wherein the medical information includes but is not limited to: medical process, medical node information, and the like.

[0059] In some implementations, the location of the terminal device of the patient can be determined and used as the first location. Optionally, the first location can be determined based on the signal strength of a wireless signal. The wireless signal can be a wireless Fidelity (WIFI) signal.

[0060] Optionally, the first position of the terminal device is calculated by determining the signal strength of the wireless access signal of the terminal device at different access points and the local area network address, and according to the signal strength and the local area network address.

[0061] In some implementations, the consultation node information includes but is not limited to: the patient's medical treatment items, the destination department, the name of the destination department, etc. That is, the consultation node information can be obtained from the patient's consultation information, and the destination department that the patient needs to visit can be obtained from the consultation node information.

[0062] In some implementations, a hospital map may be obtained based on the HIS, and the second location of the target department may be determined from the hospital map according to identification information of the target department, wherein the identification information may be the name of the target department.

[0063] S104, performing structured processing on the first location, the second location and the medical consultation information to obtain structured reference information.

[0064] Optionally, the formats of the first location, the second location and the medical consultation information may be converted to structured reference information, wherein the format of the structured reference information may be JSON or XML.

[0065] S105, generating prompt words of the target macro model based on the structured reference information and inputting them into the target macro model, and the target macro model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence.

[0066] In some implementations, a prompt word template is obtained, and based on the prompt word template and the structured reference information, prompt words of the target large model are generated. The structured reference information can be filled into the prompt word template to obtain the prompt word.

[0067] Furthermore, the prompt word is input into the target large model, and the target large model can obtain the sorting reference information from the prompt word, and sort the target department according to the first position, the second position, the number of patients waiting for treatment and the execution time in the sorting reference information to obtain the sorting result of the target department, that is, the department visit sequence. Among them, the department visit sequence includes the department name and sorting number of the target department. For example, the target departments include Department A, Department B, Department C, and Department D, then the department visit sequence is Department B, sequence number 1, Department D, sequence number 2, Department C, sequence number 3, Department A, sequence number 4. In other words, patients can be treated in the order of Department B1, Department D, Department C, and Department A.

[0068] Furthermore, after obtaining the department visit sequence, structured data of the department visit sequence can be obtained by performing structured processing on the department visit sequence, and the target large model outputs the structured data of the department visit sequence.

[0069] S106, feeding back the structured data to the client, and obtaining the department visit sequence by parsing the structured data through the client.

[0070] In some implementations, after determining the structured data of the department visit sequence, the target big model can feed back the structured data to the client, that is, feed back the structured data to the terminal device of the visiting patient.

[0071] Furthermore, by parsing the structured data, the client can obtain the department visit sequence, and the patients can receive emergency treatment according to the department visit sequence to improve the patients' medical treatment efficiency and the hospital's service quality.

[0072] Optionally, in order to facilitate the efficiency of patients, after parsing the department visit sequence, voice prompt information, text guidance information, etc. can be generated according to the department visit sequence, so that patients can receive treatment according to the department visit sequence.

[0073] In the method for sorting visiting departments provided in the embodiment of the present disclosure, a target large model capable of sorting departments is pre-trained, and the visiting information of the visiting patient and the first position of the visiting patient are obtained, and the destination department required by the visiting patient is determined from the visiting information. The second position of the destination department is further determined, and the prompt words of the target large model are determined according to the first position, the second position and the visiting information, and the destination departments are sorted according to the prompt words to obtain structured data of the department visiting sequence. The client further parses the structured data to obtain the department visiting sequence, so that the visiting patient can visit the department according to the department visiting sequence, and the coverage of the visiting process by positioning and navigation services can be achieved, and more accurate and fast visiting navigation information can be provided to the visiting patient, thereby improving the patient's visiting efficiency and the service quality of the hospital. At the same time, the hospital's information level can be improved, and the digitalization and intelligentization of medical services can be promoted.

[0074] Figure 2 This is an example flow chart of the method for sorting visiting departments provided in the embodiment of the present disclosure. Figure 2 As shown, the sorting methods for this visiting department include:

[0075] S201, obtaining historical patient consultation data as sample data, and performing structured processing on the sample data to obtain structured sample data.

[0076] S202, pre-configure the prompt words and output reference examples of the large model, and train the large model in combination with the structured sample data to obtain the target large model.

[0077] S203, obtaining the patient's medical information and the patient's first position on the hospital map, and based on the medical information, determining the destination department that the patient needs to visit and the destination department's second position on the hospital map.

[0078] The relevant contents of step S201 to step S203 can be found in the above embodiment and will not be repeated here.

[0079] S204: Structural processing is performed on the first location, the second location and the medical consultation information to obtain structured reference information.

[0080] In some implementations, in order to improve the applicability of structured reference information, the number of patients waiting for treatment in the target department and the execution time of the medical treatment items associated with the target department can be obtained, and the number of patients waiting for treatment and the execution time can be added to the medical information. The first position, the second position and the medical information can be used as sorting reference information, and the sorting reference information can be structured to obtain structured reference information.

[0081] Optionally, the number of patients waiting for the target department and the execution time of the diagnosis and treatment items associated with the target department are obtained from the HIS. Optionally, the execution time of the diagnosis and treatment items associated with the target department can also be calculated based on the number of patients waiting for the target department and the historical diagnosis and treatment time.

[0082] In some implementations, in order to make the sorting reference information more referenceable and provide a more personalized department visit sequence for the patients, the attribute information of the patients can also be used as the sorting reference information.

[0083] That is, according to the patient's medical information, the patient's attribute information is obtained, wherein the attribute information at least includes the patient's gender and age. For example, the attribute information of patient A is female, 60 years old. Furthermore, the attribute information of the patient is used as the new reference information, and the attribute information is added to the sorting reference information, so that the department visit sequence output by the target large model is more personalized.

[0084] S205, obtaining a prompt word generation template pre-configured in the target large model, and determining a filling position of each type of information in the structured reference information in the prompt word generation template.

[0085] S206, writing each type of information in the structured reference information into the prompt word generation template according to the filling position to generate prompt words of the target large model.

[0086] In some implementations, in order to improve the efficiency and accuracy of prompt word generation so that the model can clarify instruction information, a template can be generated based on the prompt words to generate prompt words for the target large model.

[0087] Optionally, a pre-configured prompt word generation template is obtained, and according to the prompt word generation template, the position where the structured reference information needs to be filled in the prompt word generation template is determined, that is, the filling position in the prompt word generation template is determined. Further, the structured reference information is filled in the prompt word generation template according to the filling position to obtain the prompt words of the target large model.

[0088] For example, the prompt word generation template is "Please combine the following conditions to generate a department visit sequence for the patient: patient information: XXX, department information: XXX", then the patient A, female, 60 years old, Department A: distance 20, number of patients waiting for treatment 5, execution time 30 minutes, Department B: distance 30, number of patients waiting for treatment 20, execution time 15 minutes, Department C: distance 25, number of patients waiting for treatment 10, execution time 45 minutes in the structured reference information can be filled into the above prompt word generation template, and the prompt words of the target large model are obtained as follows:

[0089] Please combine the following conditions and factors to generate a department visit sequence for the patient:

[0090] Patient information: Patient A, female, age 60 years old;

[0091] Department information: Department A, distance 20, number of patients waiting for treatment 5, execution time 30 minutes; Department B, distance 30, number of patients waiting for treatment 20, execution time 15 minutes; Department C, distance 25, number of patients waiting for treatment 10, execution time 45 minutes.

[0092] S207, input the prompt words into the target big model, and the target big model sorts the target departments based on the prompt words, and outputs structured data of the department visit sequence.

[0093] S208, feeding back the structured data to the client, and obtaining the department visit sequence by parsing the structured data through the client.

[0094] The relevant contents of step S207 to step S208 can be found in the above embodiment and will not be repeated here.

[0095] In the method for sorting the visiting departments provided in the embodiment of the present disclosure, a target large model capable of sorting the departments is pre-trained, and the visiting information of the visiting patients and the first position of the visiting patients are obtained, and the visiting node information is determined from the visiting information, so as to determine the destination department required by the visiting patients according to the visiting node information. The second position of the destination department, as well as the number of waiting patients and the execution time of each destination department are further determined, and the first position and the second position, the number of waiting patients and the execution time are used as sorting reference information, and the structured reference information corresponding to the sorting reference information is determined. Then, according to the prompt words, a template and structured reference information are generated, and the prompt words of the target large model can be generated, and the destination departments are sorted according to the prompt words to obtain the structured data of the department visit sequence. The client further parses the structured data to obtain the department visit sequence, so that the visiting patients can visit the department according to the department visit sequence, and the coverage of the location and navigation services on the visit process can be achieved, and more accurate and fast visit navigation information can be provided to the visiting patients, thereby improving the patient's visit efficiency and the service quality of the hospital. At the same time, it can improve the hospital's information level and promote the digitalization and intelligentization of medical services.

[0096] Figure 3 This is an example flow chart of the method for sorting visiting departments provided in the embodiment of the present disclosure. Figure 3 As shown, the sorting methods for this visiting department include:

[0097] S301, obtaining the medical information of the patient and the first position of the patient on the hospital map.

[0098] S302, obtaining consultation node information based on the consultation information, and determining the destination department that the patient needs to visit and the diagnosis and treatment items associated with the destination department according to the consultation node information.

[0099] S303, obtaining the second position of the target department on the hospital map and the number of patients waiting for consultation, as well as the execution time of the diagnosis and treatment items associated with the target department.

[0100] S304: Using the first position and the second position, the number of patients waiting for treatment and the execution time as sorting reference information, and performing structured processing on the sorting reference information to obtain structured reference information.

[0101] S305: Generate prompt words of the target macro model based on the structured reference information and input them into the target macro model.

[0102] The relevant contents of step S301 to step S305 can be found in the above embodiment and will not be repeated here.

[0103] S306, the target large model sorts the target departments based on the prompt words to obtain the department visit sequence.

[0104] In some implementations, the target big model can determine the distance between the target departments, the number of patients waiting, the execution time, and the attribute information of the patients from the prompt words. The target big model uses the above information as a sorting reference factor to sort the target departments and obtain the department visit sequence.

[0105] Optionally, a weight may be assigned to each ranking reference factor, and based on the weight of the ranking reference factor, the ranking score of the target department is calculated, and the target department is ranked based on the ranking score to obtain a department visit sequence. The target departments may be ranked according to the ranking score, with the larger the ranking score, the higher the ranking. For example, if the ranking score of Department A is 0.311, the ranking score of Department B is 0.54, and the ranking score of Department C is 0.37, then the department visit sequence is Department B, Department C, and Department A.

[0106] S307 , performing structured processing on the department visit sequence based on a pre-configured output reference example to output structured data of the department visit sequence.

[0107] In some implementations, in order to improve data processing efficiency, enhance data reliability and integrity, and thereby improve data availability, data may be structured to obtain structured data.

[0108] Optionally, the department visit sequence may be structured according to a pre-configured output reference example to obtain structured data of the department visit sequence, so as to improve the consistency and accuracy of the data and avoid errors in the data transmission process.

[0109] Optionally, the department name and sorting number of the target department are obtained from the department visit sequence. The sorting number is the number of the target department in the department visit sequence. Taking the above example, the department visit sequence is Department B, Department C, and Department A, then the sorting number of Department B is 1, the sorting number of Department C is 2, and the sorting number of Department A is 3.

[0110] Furthermore, for any destination department i among the destination departments that need to be treated, based on the sorting sequence number of the destination department, the destination department that is behind and adjacent to the destination department i is obtained, and based on the destination department i and the adjacent destination departments, the path information of the destination department i is generated, where i is a natural number greater than or equal to 1.

[0111] Furthermore, based on the output reference example, the target information of the target department i can be generated based on the department name, sorting number and path information of the target department i, and the target information of each target department can be sequentially combined according to the sorting number of the target department to generate structured data of the department visit sequence.

[0112] For example, based on the above example, the structured data of the department visit sequence is as follows: Department name: Department B, sequence number: 1, path: first position -> Department B;

[0113] Department name: Department C, sequence number: 2, path: Department B->Department C;

[0114] Department name: Department A, serial number: 3, path: Department C->Department N.

[0115] S308, feeding back the structured data to the client, and obtaining the department visit sequence by parsing the structured data through the client.

[0116] The relevant contents of step S308 can be found in the above embodiment and will not be repeated here.

[0117] In the method for sorting the visiting departments provided in the embodiment of the present disclosure, by obtaining the visiting information of the visiting patient and the first position of the visiting patient, and determining the visiting node information from the visiting information, the destination department required by the visiting patient is determined according to the visiting node information. The second position of the destination department, as well as the number of waiting patients and the execution time of each destination department are further determined, and the first position and the second position, the number of waiting patients and the execution time are used as sorting reference information to determine the prompt words of the target large model according to the sorting reference information, and the target large model sorts the destination department according to the prompt words to obtain the department visiting sequence, and then the department visiting sequence is structured to obtain structured data. The client further parses the structured data to obtain the department visiting sequence, so that the visiting patient can visit the department according to the department visiting sequence, and the coverage of the visiting process by positioning and navigation services can be achieved, and more accurate and fast visiting navigation information can be provided to the visiting patient, thereby improving the patient's visiting efficiency and the service quality of the hospital. At the same time, the information level of the hospital can be improved, and the digitalization and intelligentization of medical services can be promoted.

[0118] Figure 4 This is an example flow chart of the method for sorting visiting departments provided in the embodiment of the present disclosure. Figure 4 As shown, the sorting methods for this visiting department include:

[0119] S401, obtaining the medical information of the patient.

[0120] The relevant contents of step S401 can be found in the above embodiment and will not be described again here.

[0121] S402, receiving a wireless access signal sent by a terminal device of a visiting patient, and determining a first position of the terminal device on a hospital map according to a signal strength and a local area network address of the wireless access signal.

[0122] In some implementations, a wireless access signal sent by a terminal device may be received by a wireless access point (AP), and the wireless access signal may be processed to determine the signal strength and local area network address of the wireless access signal. The first position of the terminal device on the hospital map may then be determined based on the signal strength and the local area network address. Positioning of terminal devices based on wireless signals is applicable to a variety of scenarios, and can also be flexibly configured and adjusted according to actual needs to optimize the positioning effect. Among them, the local area network address may be a media access control address (MAC).

[0123] It is understandable that during the transmission of wireless network signals, the signal strength detected by the signal receiver can reflect the distance between the transmitting device and the receiver. Specifically, a weaker signal usually means a longer distance, while a stronger signal means a closer distance. The LAN address provides the physical location information of the wireless access point for precise positioning.

[0124] That is to say, the approximate location range of the terminal device provided by the signal strength can be used, combined with the physical location information provided by the local area network address, to determine the precise first location.

[0125] Optionally, in order to improve the accuracy and stability of the data, the wireless access signal may be preprocessed, including operations such as noise removal and filtering.

[0126] S403, obtaining consultation node information based on the consultation information, and determining the destination department that the patient needs to visit and the diagnosis and treatment items associated with the destination department according to the consultation node information.

[0127] S404, obtaining the second position of the target department on the hospital map and the number of patients waiting for consultation, as well as the execution time of the diagnosis and treatment items associated with the target department.

[0128] S405, taking the first position and the second position, the number of patients waiting for treatment and the execution time as sorting reference information, and performing structured processing on the sorting reference information to obtain structured reference information.

[0129] S406, generating prompt words of the target macro model based on the structured reference information and inputting them into the target macro model, and the target macro model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence.

[0130] S407, feeding back the structured data to the client, and obtaining the department visit sequence by parsing the structured data through the client.

[0131] The relevant contents of step S403 to step S407 can be found in the above embodiment and will not be repeated here.

[0132] In some implementations, in order to accurately guide patients to see a doctor according to the department's visit sequence and improve the patient's visit efficiency, after the structured data is fed back, the patient can choose the starting point and end point of the visit by himself to generate a corresponding navigation path according to the department's visit sequence.

[0133] Optionally, the client determines the node selection operation of the visiting patient on the client to obtain the node selection operation sent by the client, and determines the target department selected by the node selection operation, and uses the selected target department as the navigation end point.

[0134] Furthermore, the navigation starting point corresponding to the patient can be obtained according to the patient's location, so as to guide the patient from the starting point to the end point for treatment. That is to say, it is determined whether the patient has a previous treatment destination department before the node selection operation. In response to the absence of the previous treatment destination department, the first position of the patient is determined as the navigation starting point; in response to the existence of the previous treatment destination department, the previous treatment destination department is determined as the navigation starting point.

[0135] Furthermore, when the navigation starting point and the navigation terminal are determined, the path planning for the patient can be carried out according to the navigation starting point and the navigation terminal, and the navigation path corresponding to the node selection operation can be generated and fed back to the client so that the patient can receive treatment according to the planned navigation path.

[0136] In the method for sorting the visiting departments provided in the embodiment of the present disclosure, the visiting information of the visiting patient is obtained, and the first position of the visiting patient is determined according to the wireless access signal of the terminal device, and the visiting node information is determined from the visiting information, so as to determine the destination department required by the visiting patient according to the visiting node information. The second position of the destination department, as well as the number of waiting patients and the execution time of each destination department are further determined, and the first position and the second position, the number of waiting patients and the execution time are used as sorting reference information to determine the prompt words of the target large model according to the sorting reference information, and the destination departments are sorted according to the prompt words to obtain the structured data of the department visit sequence. The client further parses the structured data to obtain the department visit sequence, so that the visiting patient can visit the department according to the department visit sequence, and the coverage of the location and navigation service to the visit process can be achieved, and more accurate and fast visit navigation information can be provided to the visiting patient, so as to improve the patient's visit efficiency and the service quality of the hospital. At the same time, the information level of the hospital can be improved, and the digitalization and intelligentization of medical services can be promoted.

[0137] Based on the above embodiments, the embodiments of the present disclosure can explain the training process of the target large model, such as Figure 5 As shown, the training process of the target large model includes:

[0138] S501, obtaining historical patient consultation data as sample data, wherein the sample data includes historical attribute information of historical patients and historical department consultation sequences.

[0139] In some implementations, historical patient medical data can be obtained from HIS by obtaining the attribute information of historical patients who have visited the hospital as historical attribute information, and the order in which historical patients visited different departments as the historical department visit sequence, and then using the historical attribute information and the historical department visit sequence as sample data.

[0140] S502: annotate department locations, planned paths, and obstacles in the historical department visit sequence according to the hospital map to obtain department annotation data.

[0141] In some implementations, a hospital map is obtained, wherein the hospital map includes layout information such as locations of various departments, corridors, stairs, elevators, etc. Optionally, the hospital map may be determined based on a wireless access signal.

[0142] Furthermore, coordinate points are determined for each department in the historical department visit sequence based on the hospital map, and the name of the department is marked. Based on the historical department visit sequence, the path of the historical patient from one department to the next is determined, and the path is marked on the hospital map. Based on the hospital map, obstacles that may hinder the movement of patients, such as walls, fixed equipment, etc., are identified, and the obstacles are marked on the hospital map. By integrating the data of department location, planned path, and obstacle marking, department marking data can be obtained.

[0143] S503, structure the department labeling data, the number of waiting people and execution time of the department, and the historical attribute information of historical patients to obtain structured sample data.

[0144] In some implementations, structured sample data can be obtained by obtaining the number of waiting people and execution time of each department included in the historical department visit sequence from HIS, and structuring the department label data, the number of waiting people, execution time, and historical attribute information of the department. The format of the structured sample data can be JSON or XML.

[0145] S504, pre-configure the prompt words and output reference examples of the large model, and train the large model in combination with the structured sample data to obtain the target large model.

[0146] In some implementations, the big model is trained by pre-configuring the prompt words and output reference examples of the big model, and inputting the prompt words, output reference examples, and structured sample data into the big model, so that the big model can understand maps, path planning, and sorting, and output a predicted department visit sequence that conforms to the output reference examples.

[0147] Optionally, the combined structured sample data can be divided into a training set and a validation set, and the training set can be used to train the large model to obtain a predicted department visit sequence. Then, the historical department visit sequence and the predicted department visit sequence in the validation set can be used to adjust the model's hyperparameters to improve the model's accuracy and obtain the target large model.

[0148] In some implementations, in order to improve the accuracy of the target large model and make the target large model output a more reasonable department visit sequence, the target large model can also be fine-tuned. Optionally, the target large model can be fine-tuned based on the feedback information of the patient who visits the department visit sequence output by the target large model.

[0149] In some implementations, the patient's feedback information is monitored, and in response to the monitored feedback information, the patient is determined as a sample patient for model optimization. That is, after the patient's visit according to the department's visit sequence is completed, the patient can be guided to evaluate the visit, and the evaluation information is used as feedback information to fine-tune the target large model.

[0150] Optionally, the sample type of the sample patient can be determined based on the feedback information. That is, the patient associated with the feedback information can be used as the sample patient, and the sample type of the sample patient can be clarified by determining the attribute information of the sample patient, so as to fine-tune the target large model according to different sample types. For example, the sample type can be divided according to age, and the sample type can also be divided according to the condition.

[0151] In some implementations, a large amount of feedback information is collected to fine-tune the model using the visit data of the visit patients associated with the feedback information. That is, in response to the amount of feedback information reaching a set value, the visit data of the sample patients is used as a model optimization sample, and the target large model is fine-tuned based on the model optimization sample.

[0152] In the method for sorting visiting departments provided in the embodiment of the present disclosure, sample data is obtained and the historical visiting sequence of the department in the sample data is annotated using a hospital map to obtain department annotation data. Structured sample data is obtained by structuring the department annotation data, historical attribute information of historical patients, and the like, and the large model is trained using the structured sample data to obtain the target large model, which enables the target large model to perform accurate path planning and sorting. Fine-tuning the target large model according to the patient's feedback information can improve the model performance and improve the quality of the model in sorting departments.

[0153] Figure 6 The diagram shows an interactive diagram of a patient obtaining a department visit sequence. Figure 6In the system, the intelligent outpatient medical assistant provides the patient with a department visit sequence. The patient logs in to the intelligent outpatient medical assistant through a terminal device, that is, a mobile phone. When the patient logs in to the intelligent outpatient medical assistant, the intelligent outpatient medical assistant can determine the first location of the patient based on the wireless access signal sent by the mobile phone. The intelligent outpatient medical assistant can obtain the patient's medical information by accessing the Hospital Information System (HIS), and determine the target department that the patient needs to visit and the medical treatment items associated with the target department based on the medical information. By obtaining the second location of the target department on the hospital map and the number of patients waiting for the visit, as well as the execution time of the medical treatment items associated with the target department, the target department is sorted using the target large model to obtain the department visit sequence, and the department visit sequence is structured to obtain structured data and fed back to the mobile phone. The mobile phone can obtain the department visit sequence by parsing the structured data.

[0154] Corresponding to the sorting methods of medical departments provided in the above-mentioned embodiments, an embodiment of the present disclosure further provides a sorting device for medical departments. Since the sorting device for medical departments provided in the embodiment of the present disclosure corresponds to the sorting methods of medical departments provided in the above-mentioned embodiments, the implementation methods of the above-mentioned sorting methods for medical departments are also applicable to the sorting device for medical departments provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0155] Figure 7 This is a structural example diagram of a device for sorting visiting departments provided in an embodiment of the present disclosure. Figure 7 As shown, the device for sorting visiting departments includes: a first processing module 701, a training module 702, a determination module 703, a second processing module 704, a sorting module 705 and a parsing module 706.

[0156] The first processing module 701 is used to obtain historical patient visit data as sample data, and perform structured processing on the sample data to obtain structured sample data;

[0157] A training module 702 is used to pre-configure the prompt words and output reference examples of the large model, and train the large model in combination with the structured sample data to obtain a target large model;

[0158] The determination module 703 is used to obtain the medical information of the patient and the first position of the patient on the hospital map, and determine the target department that the patient needs to visit and the second position of the target department on the hospital map based on the medical information;

[0159] A second processing module 704 is used to perform structured processing on the first position, the second position and the medical consultation information to obtain structured reference information;

[0160] A sorting module 705 is used to generate prompt words of the target macro model based on the structured reference information, and input the prompt words into the target macro model, so that the target macro model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence;

[0161] The parsing module 706 is used to feed back the structured data to the client, and parse the structured data through the client to obtain the department visit sequence.

[0162] According to one embodiment of the present disclosure, the second processing module 704 is also used to: obtain the number of patients waiting for treatment in the target department and the execution time of the medical treatment items associated with the target department, and add the number of patients waiting for treatment and the execution time to the medical information; use the first position and the second position and the medical information as sorting reference information, and perform structured processing on the sorting reference information to obtain structured reference information.

[0163] According to one embodiment of the present disclosure, the sorting module 705 is further used to: obtain a prompt word generation template pre-configured for the target large model, and determine a filling position of each type of information in the structured reference information in the prompt word generation template; and write each type of information in the structured reference information into the prompt word generation template according to the filling position to generate prompt words for the target large model.

[0164] According to one embodiment of the present disclosure, the second processing module 704 is further used to: obtain attribute information of the patient based on the medical information of the patient, wherein the attribute information at least includes the gender and age of the patient; use the attribute information of the patient as new reference information, and add the attribute information to the sorting reference information.

[0165] According to one embodiment of the present disclosure, the sorting module 705 is also used for: the target big model sorts the target departments based on the prompt words to obtain a department visit sequence; and structures the department visit sequence based on a pre-configured output reference example to output structured data of the department visit sequence.

[0166] According to one embodiment of the present disclosure, the sorting module 705 is also used to: obtain the department name and sorting number of the target department; for any target department i among the target departments that need to be treated, based on the sorting number of the target department, obtain the target department that is arranged behind and adjacent to the target department i, and based on the target department i and the adjacent target department, generate the path information of the target department i, where i is a natural number greater than or equal to 1; based on the output reference example, based on the department name, sorting number and path information of the target department i, generate the target information of the target department i, and sequentially combine the target information of each target department according to the sorting number of the target department to generate structured data of the department visit sequence.

[0167] According to one embodiment of the present disclosure, the determination module 703 is further used to: receive a wireless access signal sent by a terminal device of the patient, and determine a first position of the terminal device on the hospital map based on the signal strength and local area network address of the wireless access signal.

[0168] According to one embodiment of the present disclosure, the parsing module 706 is also used to: obtain the node selection operation sent by the client; determine the target department selected by the node selection operation, and use the selected target department as the navigation end point; obtain the navigation starting point corresponding to the current patient; plan the path for the patient according to the navigation starting point and the navigation terminal, generate a navigation path corresponding to the node selection operation, and feedback to the client.

[0169] According to one embodiment of the present disclosure, the parsing module 706 is also used to: determine whether the patient has a previous destination department before the node selection operation; in response to the absence of the previous destination department, determine the first position of the patient as the navigation starting point; in response to the existence of the previous destination department, determine the previous destination department as the navigation starting point.

[0170] According to one embodiment of the present disclosure, the first processing module 701 is further used to: obtain historical patient medical treatment data as sample data, wherein the sample data includes historical attribute information of the historical patients and historical department medical treatment sequences; mark the department locations, planned paths and obstacles in the historical department medical treatment sequences according to the hospital map to obtain department marking data; and perform structured processing on the department marking data, the number of waiting people and execution time of the department, and the historical attribute information of the historical patients to obtain structured sample data.

[0171] According to one embodiment of the present disclosure, the first processing module 701 is further used to: monitor the feedback information of the patient, and in response to monitoring the feedback information, determine that the patient is a sample patient for model optimization; based on the feedback information, determine the sample type of the sample patient; in response to the amount of the feedback information reaching a set value, use the patient's visit data as a model optimization sample, and fine-tune the target large model based on the model optimization sample.

[0172] In the device for sorting medical departments provided in the embodiment of the present disclosure, a target large model capable of sorting departments is pre-trained, and the medical information of the patients and the first position of the patients are obtained, and the target department required by the patients is determined from the medical information. The second position of the target department is further determined, and the prompt words of the target large model are determined according to the first position, the second position and the medical information, and the target departments are sorted according to the prompt words to obtain structured data of the department medical sequence. The client further parses the structured data to obtain the department medical sequence, so that the patients can be treated according to the department medical sequence, and the coverage of the medical process by positioning and navigation services can be achieved, and more accurate and fast medical navigation information can be provided to the patients, thereby improving the patient's medical efficiency and the service quality of the hospital. At the same time, the hospital's information level can be improved, and the digitalization and intelligentization of medical services can be promoted.

[0173] Figure 8 This is a diagram showing an example of the structure of an electronic device provided in an embodiment of the present disclosure. Figure 8 As shown, the electronic device 800 may include: a transceiver 801 , a processor 802 , and a memory 803 .

[0174] The processor 802 executes the computer execution instructions stored in the memory, so that the processor 802 executes the scheme in the above embodiment. The processor 802 can be a general-purpose processor, including a central processing unit CPU, a network processor (network processor, NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0175] The memory 803 is connected to the processor 802 via a system bus and implements communication therebetween. The memory 803 is used to store computer program instructions.

[0176] The transceiver 801 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0177] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0178] The electronic device provided in the embodiments of the present disclosure may be the terminal device of the above embodiments.

[0179] The disclosed embodiment also provides a chip for running instructions, which is used to execute the technical solution of the method for sorting visiting departments in the above embodiment.

[0180] The present disclosure also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the method for sorting visiting departments in the above embodiment.

[0181] The embodiments of the present disclosure also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the method for sorting visiting departments in the above embodiment.

[0182] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0183] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for sorting visiting departments, characterized in that: include: Acquire historical patient visit data as sample data, and perform structured processing on the sample data to obtain structured sample data; Pre-configuring the prompt words and output reference examples of the large model, and training the large model in combination with the structured sample data to obtain a target large model; Obtaining the medical information of the patient and the first position of the patient on the hospital map, and determining the target department that the patient needs to visit and the second position of the target department on the hospital map based on the medical information; Performing structured processing on the first location, the second location and the medical consultation information to obtain structured reference information; Generate prompt words of the target large model based on the structured reference information, and input them into the target large model, so that the target large model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence; The structured data is fed back to the client, and the client parses the structured data to obtain the department visit sequence.

2. The method according to claim 1, characterized in that The step of performing structural processing on the first location, the second location and the medical consultation information to obtain structured reference information includes: Obtain the number of patients waiting for the target department and the execution time of the diagnosis and treatment items associated with the target department, and add the number of patients waiting for the diagnosis and treatment and the execution time to the medical information; The first position, the second position and the medical consultation information are used as sorting reference information, and the sorting reference information is structured to obtain structured reference information.

3. The method according to claim 2, characterized in that The step of generating the prompt words of the target large model based on the structured reference information includes: Acquire a prompt word generation template pre-configured in the target large model, and determine a filling position of each type of information in the structured reference information in the prompt word generation template; According to the filling position, each type of information in the structured reference information is written into the prompt word generation template to generate the prompt words of the target large model.

4. The method according to claim 2, characterized in that: Before the structuring of the sorting reference information to obtain the structured reference information, the method further includes: Acquire attribute information of the patient according to the patient's medical information, wherein the attribute information at least includes the gender and age of the patient; The attribute information of the patient is used as new reference information, and the attribute information is added to the sorting reference information.

5. The method according to any one of claims 1 to 4, characterized in that The target large model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence, including: The target large model sorts the target departments based on the prompt words to obtain a department visit sequence; The department visit sequence is structured based on a preconfigured output reference example to output structured data of the department visit sequence.

6. The method according to claim 5, characterized in that The step of performing structured processing on the department visit sequence based on a preconfigured output reference example to output structured data of the department visit sequence includes: Obtain the department name and sorting number of the target department; For any target department i among the target departments that need to be treated, based on the sorting sequence number of the target department, obtain the target department that is arranged behind and adjacent to the target department i, and based on the target department i and the adjacent target department, generate the path information of the target department i, where i is a natural number greater than or equal to 1; Based on the output reference example, based on the department name, sorting number and path information of the target department i, the target information of the target department i is generated, and the target information of each target department is sequentially combined according to the sorting number of the target department to generate structured data of the department visit sequence.

7. The method according to any one of claims 1 to 4, characterized in that The process of obtaining the first position of the patient on the hospital map includes: A wireless access signal sent by a terminal device of the patient is received, and a first position of the terminal device on a hospital map is determined according to a signal strength and a local area network address of the wireless access signal.

8. The method according to any one of claims 1 to 4, characterized in that After feeding back the structured data to the client, the method further includes: Obtaining a node selection operation sent by the client; Determine the target department selected by the node selection operation, and use the selected target department as the navigation end point; Obtain the navigation starting point currently corresponding to the patient; According to the navigation starting point and the navigation terminal, a path is planned for the patient, a navigation path corresponding to the node selection operation is generated, and feedback is given to the client.

9. The method according to claim 8, characterized in that The obtaining of the navigation starting point currently corresponding to the patient includes: Determine whether the patient has visited a previous department before the node selection operation; In response to the absence of the previous destination department, determining the first location of the patient as the navigation starting point; In response to the existence of the previous destination department, the previous destination department is determined as the navigation starting point.

10. The method according to claim 1, characterized in that The obtaining of historical patient visit data as sample data and performing structured processing on the sample data to obtain structured sample data includes: Acquire historical patient consultation data as sample data, wherein the sample data includes historical attribute information of the historical patient and historical department consultation sequence; According to the hospital map, the department locations, planned paths and obstacles in the historical department visit sequence are marked to obtain department marking data; The department labeling data, the number of waiting people and execution time of the department, and the historical attribute information of the historical patients are structured to obtain structured sample data.

11. The method according to claim 10, characterized in that The method further comprises: Monitoring feedback information of the patient, and determining the patient as a sample patient for model optimization in response to monitoring the feedback information; Based on the feedback information, determining the sample type of the sample patient; In response to the amount of the feedback information reaching a set value, the medical data of the sample patient is used as a model optimization sample, and the target large model is fine-tuned based on the model optimization sample.

12. A device for sorting visiting departments, characterized in that: include: A first processing module is used to obtain historical patient visit data as sample data, and perform structured processing on the sample data to obtain structured sample data; A training module, used for pre-configuring the prompt words and outputting reference examples of the large model, and training the large model in combination with the structured sample data to obtain a target large model; A determination module, used to obtain the medical information of the patient and the first position of the patient on the hospital map, and determine the target department that the patient needs to visit and the second position of the target department on the hospital map based on the medical information; a second processing module, configured to perform structured processing on the first position, the second position and the medical consultation information to obtain structured reference information; A sorting module, used to generate prompt words of the target large model based on the structured reference information, and input the prompt words into the target large model, so that the target large model sorts the target departments based on the prompt words and outputs structured data of the department visit sequence; The parsing module is used to feed back the structured data to the client, and parse the structured data through the client to obtain the department visit sequence.

13. The device according to claim 12, characterized in that The second processing module is further used for: Obtain the number of patients waiting for the target department and the execution time of the diagnosis and treatment items associated with the target department, and add the number of patients waiting for the diagnosis and treatment and the execution time to the medical information; The first position, the second position and the medical consultation information are used as sorting reference information, and the sorting reference information is structured to obtain structured reference information.

14. The device according to claim 13, characterized in that The sorting module is further used for: Acquire a prompt word generation template pre-configured in the target large model, and determine a filling position of each type of information in the structured reference information in the prompt word generation template; According to the filling position, each type of information in the structured reference information is written into the prompt word generation template to generate the prompt words of the target large model.

15. The device according to claim 13, characterized in that The second processing module is further used for: Acquire attribute information of the patient according to the patient's medical information, wherein the attribute information at least includes the gender and age of the patient; The attribute information of the patient is used as new reference information, and the attribute information is added to the sorting reference information.

16. The device according to any one of claims 12 to 15, characterized in that The sorting module is further used for: The target large model sorts the target departments based on the prompt words to obtain a department visit sequence; The department visit sequence is structured based on a preconfigured output reference example to output structured data of the department visit sequence.

17. The device according to claim 16, characterized in that The sorting module is further used for: Obtain the department name and sorting number of the target department; For any target department i among the target departments that need to be treated, based on the sorting sequence number of the target department, obtain the target department that is arranged behind and adjacent to the target department i, and based on the target department i and the adjacent target department, generate the path information of the target department i, where i is a natural number greater than or equal to 1; Based on the output reference example, based on the department name, sorting number and path information of the target department i, the target information of the target department i is generated, and the target information of each target department is sequentially combined according to the sorting number of the target department to generate structured data of the department visit sequence.

18. The device according to any one of claims 12 to 15, characterized in that The determining module is further used for: A wireless access signal sent by a terminal device of the patient is received, and a first position of the terminal device on a hospital map is determined according to a signal strength and a local area network address of the wireless access signal.

19. The device according to any one of claims 12 to 15, characterized in that The parsing module is also used for: Obtaining a node selection operation sent by the client; Determine the target department selected by the node selection operation, and use the selected target department as the navigation end point; Obtain the navigation starting point currently corresponding to the patient; According to the navigation starting point and the navigation terminal, a path is planned for the patient, a navigation path corresponding to the node selection operation is generated, and feedback is given to the client.

20. The device according to claim 19, characterized in that The parsing module is also used for: Determine whether the patient has visited a previous department before the node selection operation; In response to the absence of the previous destination department, determining the first location of the patient as the navigation starting point; In response to the existence of the previous destination department, the previous destination department is determined as the navigation starting point.

21. The device according to claim 12, characterized in that The first processing module is further used for: Acquire historical patient visit data as sample data, wherein the sample data includes historical attribute information of the historical patient and historical department visit sequence; According to the hospital map, the department locations, planned paths and obstacles in the historical department visit sequence are marked to obtain department marking data; The department labeling data, the number of waiting people and execution time of the department, and the historical attribute information of the historical patients are structured to obtain structured sample data.

22. The device according to claim 21, characterized in that The first processing module is further used for: Monitoring feedback information of the patient, and determining the patient as a sample patient for model optimization in response to monitoring the feedback information; Based on the feedback information, determining the sample type of the sample patient; In response to the amount of the feedback information reaching a set value, the medical data of the sample patient is used as a model optimization sample, and the target large model is fine-tuned based on the model optimization sample.

23. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 11.

24. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 11 when executed by a processor.

25. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 11 when being executed by a processor.

Images