Treatment information display method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a treatment information display method and device, computer equipment, a readable storage medium and a program product. And through a large language model, according to dialogue information between the treatment object and the inquiry intelligent agent and historical diagnosis and treatment report information, determining target abnormal description information with a first target feature and target historical diagnosis and treatment information with a second target feature, and displaying the target abnormal description information and the target historical diagnosis and treatment information according to a time sequence.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for displaying treatment information. Background Technology

[0002] In the context of patient treatment, the extent to which a doctor understands a patient's medical history is directly related to the effectiveness of treatment. Therefore, doctors need to obtain as comprehensive a patient's treatment information as possible. Currently, doctors typically determine this information through repeated manual questioning and review. However, this method is time-consuming, reducing the efficiency of information gathering.

[0003] Therefore, current methods of obtaining treatment information suffer from low efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for displaying treatment information that can improve the efficiency of obtaining the above-mentioned technical problems.

[0005] Firstly, this application provides a method for displaying treatment information, including:

[0006] Acquire dialogue information and historical medical reports; the dialogue information represents the dialogue between the patient and the intelligent diagnostic agent.

[0007] The dialogue information and the historical medical report information are input into a large language model; the large language model is used to obtain target abnormality description information and target historical medical report information corresponding to the treatment object based on the dialogue information and the historical medical report information; the target abnormality description information represents the abnormality description information with a first target feature in the dialogue information; the target historical medical report information represents the historical medical report information with a second target feature;

[0008] The abnormal description information of the target and the historical diagnosis and treatment information of the target are displayed in chronological order.

[0009] In one embodiment, the operation of acquiring the dialogue information includes:

[0010] In response to triggering information for the diagnostic agent, an initial question from a question set is output; the question set includes the initial question and one or more follow-up questions; the initial question represents a question related to the type of symptom.

[0011] Based on the treatment subject's response information to the initial question input, corresponding target follow-up questions are determined from the question set and output until a preset termination condition is met. Then, based on the initial question, each of the target follow-up questions, and each of the response information, the dialogue information is obtained.

[0012] In one embodiment, the operation of obtaining the historical medical report information includes:

[0013] The historical medical report information is obtained based on one or more of the first and second medical report information;

[0014] The first medical report information is extracted from the medical report image uploaded by the patient; the second medical report information is obtained by querying the local database based on the identifier corresponding to the patient.

[0015] In one embodiment, obtaining the target abnormality description information and target historical medical treatment information corresponding to the treatment subject based on the dialogue information and the historical medical report information includes:

[0016] By using a retrieval enhancement generation algorithm, external medical knowledge base information corresponding to the dialogue information and the historical medical report information is obtained;

[0017] Based on the external medical knowledge base information and the first target feature, the large language model extracts the symptom occurrence time, symptom description information and medical history description information from the dialogue information to obtain the target abnormal description information.

[0018] Based on the second target feature, the large language model extracts the historical treatment time, historical treatment type, and historical treatment result from the historical treatment report information to obtain the target historical treatment information.

[0019] In one embodiment, the target abnormality description information includes the symptom occurrence time and symptom description information; the target historical diagnosis and treatment information includes historical diagnosis and treatment time, historical diagnosis and treatment type, and historical diagnosis and treatment result;

[0020] The step of displaying the target anomaly description information and the target historical diagnosis and treatment information in chronological order includes:

[0021] For each time point, if there is a target symptom occurrence time that matches the time point, then the symptom description information corresponding to the target symptom occurrence time is displayed at the time point on the preset time axis.

[0022] If a target historical treatment time that matches the specified time point exists, then the historical treatment type and historical treatment result corresponding to the target historical treatment time are displayed at the specified time point on the preset time axis.

[0023] In one embodiment, a jump option corresponding to the target historical medical information is also included;

[0024] The method further includes:

[0025] In response to the trigger information for the jump option, the historical medical report information corresponding to the target historical medical information is displayed.

[0026] In one embodiment, a first window is further included; the first window is used to display structured information and the dialogue information; the structured information includes a chief complaint module and a medical history module; the chief complaint module is used to display the chief complaint information in the dialogue information; the medical history module is used to display the medical history information in the dialogue information;

[0027] The method further includes:

[0028] In response to the selection information of the field of the structured information in the first window, the text corresponding to the field in the dialog information is displayed.

[0029] In one embodiment, a second window is also included; the second window is used to display the historical medical report information based on the report type;

[0030] The method further includes:

[0031] In response to the trigger information for the target report type in the second window, the historical medical report information of each target report type is displayed.

[0032] Secondly, this application also provides a treatment information display device, comprising:

[0033] The acquisition module is used to acquire dialogue information and historical medical report information; the dialogue information represents the dialogue information between the treatment subject and the consultation intelligent agent;

[0034] An input module is used to input the dialogue information and the historical medical report information into a large language model; the large language model is used to obtain target abnormality description information and target historical medical report information corresponding to the treatment object based on the dialogue information and the historical medical report information; the target abnormality description information represents the abnormality description information with a first target feature in the dialogue information; the target historical medical report information represents the historical medical report information with a second target feature;

[0035] The display module is used to display the abnormal description information of the target and the historical diagnosis and treatment information of the target in chronological order.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the operation of the above-described method.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the operations of the above-described method.

[0038] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the operations of the above-described method.

[0039] The aforementioned treatment information display method, apparatus, computer equipment, computer-readable storage medium, and computer program product, through a large language model, determine the target anomaly description information with a first target feature and the target historical treatment information with a second target feature from the dialogue information between the treatment subject and the consultation intelligent agent, as well as historical medical report information, based on the dialogue information between the treatment subject and the consultation intelligent agent. The target anomaly description information and target historical treatment information are then displayed in chronological order. Compared to the traditional method of determining treatment information through repeated manual questioning and review, this application uses a consultation intelligent agent to conduct a pre-consultation with the treatment subject to obtain dialogue information. By combining the dialogue information and historical medical reports with a large language model, the target anomaly description information and target historical treatment information with corresponding features from the dialogue information and historical medical reports are extracted. These target anomaly description information and target historical treatment information are then displayed in chronological order. By observing the displayed information, the development and severity of the treatment subject's condition can be quickly obtained, improving the efficiency of obtaining treatment information for the treatment subject. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the disclosed drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating a treatment information display method in one embodiment.

[0042] Figure 2 This is a flowchart illustrating a treatment information display method in another embodiment.

[0043] Figure 3 This is a structural block diagram of a treatment information display device in one embodiment.

[0044] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0047] In related technologies, in outpatient settings, doctors learn about patients' conditions by asking questions and reading reports they bring. When there are many reports and the conditions are complex, doctors need to ask questions and review them repeatedly to understand the progression of the patient's condition. This consumes a lot of time, reduces the efficiency of consultation, increases the burden on doctors, and lengthens the patient's visit.

[0048] Based on this, this application uses a diagnostic intelligence agent to conduct a pre-diagnosis with the patient to obtain dialogue information. By combining the dialogue information and historical medical reports with a large language model, target anomaly description information and target historical medical information with corresponding characteristics are extracted from the dialogue information and historical medical reports. The target anomaly description information and target historical medical information are displayed in chronological order. By observing the displayed information, the patient's disease progression and severity can be quickly obtained, thus improving the efficiency of obtaining treatment information for the patient.

[0049] In one embodiment, such as Figure 1 As shown, a method for displaying treatment information is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and implemented through the interaction between the terminal and the server, including the following operations S202 to S206.

[0050] in:

[0051] Operation S202 obtains dialogue information and historical medical report information; the above dialogue information represents the dialogue information between the treatment subject and the consultation intelligent agent.

[0052] The terminal can be a computer device used by doctors to analyze and display patient conditions. The terminal connects to a diagnostic intelligent agent. This agent can be a generative large language model used to engage in dialogue with the patient regarding any abnormalities they experience (such as discomfort or symptoms). The patient can interact with the intelligent agent, generating dialogue information between them. The terminal can then access this dialogue information.

[0053] In addition, the terminal can also access the patient's historical medical reports. These reports can be information on a series of medical procedures performed by the patient within a historical period. For example, reports on various medical examinations the patient underwent during a historical period.

[0054] In operation S204, the above-mentioned dialogue information and the above-mentioned historical medical report information are input into the large language model; the above-mentioned large language model is used to obtain the target abnormality description information and target historical medical information corresponding to the above-mentioned treatment object based on the above-mentioned dialogue information and the above-mentioned historical medical report information; the above-mentioned target abnormality description information represents the abnormality description information with the first target feature in the above-mentioned dialogue information; the above-mentioned target historical medical information represents the historical medical information with the second target feature in the above-mentioned historical medical report information.

[0055] The terminal is pre-configured with a large language model. This model can be used to summarize the acquired dialogue information and historical medical report information. For example, based on the input dialogue information and historical medical report information, the large language model summarizes the information and extracts key information that meets certain conditions. For instance, the large language model extracts abnormal description information with a first target feature from the dialogue information as target abnormal description information, which can be obtained by summarizing the abnormal description information with the first target feature from the dialogue information. The large language model also extracts historical medical information with a second target feature from the target historical medical information as target historical medical information. The first target feature can be a feature that reflects the patient's condition, symptoms, and medical history; the second target feature can be a feature that reflects the type, location, conclusion, and time of the patient's medical treatment.

[0056] Operation S206 displays the above-mentioned target anomaly description information and the above-mentioned target historical diagnosis and treatment information in chronological order.

[0057] The terminal can display the extracted target anomaly description information and the aforementioned target historical medical information. Specifically, the terminal can display the target anomaly description information and the aforementioned target historical medical information in chronological order. For example, the terminal can display a timeline on a designated display page. Based on the time points corresponding to the occurrence of the target anomaly description information and the aforementioned target historical medical information, the terminal displays the corresponding target anomaly description information and target historical medical information at the corresponding time points on the timeline, forming an information display in chronological order, showing the progression of the patient's condition. For example, it can show on which day the patient developed what symptoms, and on which day the patient underwent what medical examinations.

[0058] In the aforementioned method for displaying treatment information, a large language model is used to determine the target anomaly description information with a first target feature and the target historical treatment information with a second target feature from the dialogue information between the treatment subject and the consultation agent, as well as historical medical report information. These target anomaly description information and target historical treatment information are then displayed in chronological order. Compared to the traditional method of determining treatment information through repeated manual inquiries and reviews, this application uses a consultation agent to conduct a pre-consultation with the treatment subject to obtain dialogue information. A large language model is then used to combine the dialogue information and historical medical reports to extract the target anomaly description information and target historical treatment information with corresponding features from both the dialogue information and the historical medical reports. These target anomaly description information and target historical treatment information are then displayed in chronological order. By observing the displayed information, the course and severity of the treatment subject's condition can be quickly obtained, thus improving the efficiency of obtaining treatment information for the treatment subject.

[0059] In one embodiment, the dialogue information acquisition operation includes: in response to triggering information for the consultation agent, outputting an initial question from a question set; the question set includes the initial question and one or more follow-up questions; the initial question represents a question about the type of symptom; based on the treatment subject's answer information based on the initial question input, determining and outputting corresponding target follow-up questions from the question set, until a preset termination condition is met, and obtaining the dialogue information based on the initial question, each of the target follow-up questions, and each of the answer information.

[0060] In this embodiment, the terminal acquires dialogue information with the patient through a diagnostic agent. The terminal can pre-set a question set, which includes multiple questions, each addressing different types of abnormalities in the patient, such as questions about symptom types or symptom duration. These questions can be stored in a tree structure, with each initial question corresponding to one or more follow-up questions. Based on the patient's response, the terminal outputs follow-up questions matching the response. The terminal can then engage in dialogue with the patient through the diagnostic agent using an initial question-follow-up question approach.

[0061] The terminal responds to trigger information from the consultation agent. For example, if the patient clicks on a displayed consultation agent dialogue option, the terminal can output an initial question from the question set through the consultation agent. For instance, the consultation agent might output a question about the type of symptom, and the patient could input corresponding answers based on the initial question, such as what symptoms they currently have. The terminal can then use the consultation agent, based on the answers, to determine and output target follow-up questions that match the answers from the various follow-up questions corresponding to the initial question in the question set. For example, based on the answers about symptoms, the consultation agent might output follow-up questions such as "How long have the symptoms lasted?"

[0062] The aforementioned follow-up questioning can continue for multiple rounds. That is, the diagnostic agent can repeatedly receive answer information, determine target follow-up questions based on the answer information, output the target follow-up questions, and receive answer information, until a preset termination condition is met. At this point, the terminal obtains the aforementioned dialogue information based on the initial question, each of the target follow-up questions, and each of the answer information. The preset termination condition includes the diagnostic agent determining that no follow-up questioning is needed, the absence of a matching target follow-up question in the question set within a preset number of inquiries, and the reaching of the preset number of inquiries.

[0063] Specifically, after a patient requests a consultation, before the consultation officially begins, the terminal guides the patient and the consultation agent to interact. The consultation agent can collect basic information about the patient's condition. For example, the consultation agent can set some initial questions, such as "Where do you feel unwell?" or "What symptoms do you have?" The consultation agent asks questions to the patient through text and voice broadcasts. The patient can answer the questions by entering text, clicking options, uploading pictures, or using voice input. The consultation agent can then ask follow-up questions based on the medical knowledge base, the question set, and the patient's responses. For example, if the patient replies that they have a cough, the consultation agent will continue by asking, "How long have you been coughing?" The consultation agent connects to the patient's device via the network, and the patient accesses it through an application or webpage. After the consultation agent finishes asking questions, it can save all the dialogue information with the patient.

[0064] Through this embodiment, the terminal can collect dialogue information before the consultation through the consultation agent, so that the terminal can understand the patient's condition based on the dialogue information, thereby improving the efficiency of treatment information collection.

[0065] In one embodiment, the operation of obtaining historical medical report information includes: obtaining the aforementioned historical medical report information based on one or more of first medical report information and second medical report information; wherein the aforementioned first medical report information is extracted based on the medical report image uploaded by the aforementioned patient; and the aforementioned second medical report information is obtained by querying a local database based on the identifier corresponding to the aforementioned patient.

[0066] In this embodiment, the aforementioned historical medical report information may include multiple sources. For example, reports corresponding to medical treatment performed by the patient at institutions other than the terminal's location can be obtained by the patient uploading them to the terminal. The terminal can acquire the uploaded medical report image and extract medical report information with a second target feature from the image as the first medical report information. If the patient has undergone medical treatment at the terminal's location, the patient's medical report at that institution can be stored in a local database. The local database stores various medical report information stored according to the patient's corresponding identifier. The terminal can query the local database based on the patient's identifier to obtain the medical report information corresponding to that identifier, which serves as the second medical report information for the patient in the local database. Thus, the terminal can obtain the aforementioned historical medical report information based on one or more of the first and second medical report information. For example, if the terminal only receives the medical report image uploaded by the patient, the first medical report information is used as the historical medical report information; if the terminal only finds the medical report information of the patient in the local database, the second medical report is used as the historical medical report information; if the terminal receives the medical report image uploaded by the patient and finds the medical report information of the patient in the local database, the first medical report information and the second medical report information are integrated to obtain the historical medical report information.

[0067] Specifically, for medical reports originating outside the institution where the terminal is located, patients can upload these reports (paper or electronic) to the terminal. For example, patients can save the medical report to their photo album by taking a picture or screenshot using their image acquisition device, and then upload the saved report to the terminal's information collection module from an application or webpage. The upload can be in image format. The terminal performs image processing on the uploaded image through the information collection module, including rotation, correction, and cropping, to ensure that the information can be correctly recognized. For example, if the patient rotated the report by 90° when taking the picture, the terminal will correct it through the information collection module. Then, the terminal will recognize the processed image, using Optical Character Recognition (OCR) technology and a large visual model to read the text in the medical report and obtain the text content corresponding to each report.

[0068] If the patient receives medical treatment at the institution where the terminal is located, the terminal can search for the patient's medical records in the local database based on the patient's unique identification code (identifier). If the patient has previously received treatment at that institution, the terminal can obtain the patient's medical report, treatment records, and other materials to obtain the second medical report information.

[0069] Through this embodiment, the terminal can obtain the patient's historical medical report information in multiple ways, thereby improving the comprehensiveness of obtaining historical medical report information.

[0070] In one embodiment, obtaining target anomaly description information and target historical treatment information corresponding to the treatment subject based on the aforementioned dialogue information and the aforementioned historical treatment report information includes: obtaining external medical knowledge base information corresponding to the aforementioned dialogue information and the aforementioned historical treatment report information through a retrieval enhancement generation algorithm; extracting symptom occurrence time, symptom description information, and medical history description information from the aforementioned dialogue information using a large language model based on the aforementioned external medical knowledge base information and the first target feature to obtain the aforementioned target anomaly description information; and extracting historical treatment time, historical treatment type, and historical treatment result from the aforementioned historical treatment report information using a large language model based on the second target feature to obtain the aforementioned target historical treatment information.

[0071] In this embodiment, the terminal can extract abnormal description information and target historical medical information from dialogue information and historical medical report information based on the aforementioned first target feature and second target feature. To improve extraction accuracy, the terminal can also extract the target abnormal description information by combining a large language model with external knowledge. For example, the terminal can use a retrieval enhancement generation algorithm with a large language model to obtain external medical knowledge base information corresponding to the dialogue information and the aforementioned historical medical report information. Thus, the terminal can use the large language model, combined with the external medical knowledge base information and the first target feature, to extract the symptom occurrence time, symptom description information, and medical history description information from the dialogue information to obtain the aforementioned target abnormal description information. Here, the symptom occurrence time represents the time when the patient's symptoms appeared, the symptom description information represents the patient's description of the symptoms, and the medical history description information represents the patient's relevant medical history information.

[0072] The terminal can also extract historical treatment time, historical treatment type, and historical treatment result from historical medical reports by combining a large language model with the second target features, thus obtaining the aforementioned target historical medical information. The historical medical report information can be stored in a structured format; therefore, the terminal can use a large language model to extract the specific content from the structured parameters (such as time, title, and conclusion) in the historical medical report information to obtain the aforementioned historical treatment time, historical treatment type, and historical treatment result.

[0073] Specifically, the terminal utilizes a large language model for information extraction. The terminal can summarize and segment the aforementioned dialogue information. For example, through the large language model, it can extract the chief complaint, present illness, past medical history, surgical history, family history, and smoking history from the dialogue information. The chief complaint refers to a concise description of the main symptoms, signs, and their duration described by the patient during their visit; the present illness, past medical history, surgical history, family history, and smoking history can serve as medical history description information. The terminal can also extract key information through retrieval enhancement generation algorithms. For example, by using retrieval enhancement generation tools, external medical knowledge bases or documents can be introduced into the large language model. Combining the large language model with external knowledge, it can further extract key phrases from the above summary, such as the most important and obvious symptoms or signs in the chief complaint (symptom description information), and the duration of these symptoms or signs (symptom onset time).

[0074] For the collected historical medical reports, the terminal uses a large language model to extract key information such as time (historical treatment time), title (historical treatment type), institution, and conclusion (historical treatment result). The large language model then combines the extracted information into a single summary sentence. For example, "On XX date, a complete blood count was performed at XX institution. Results: White blood cells 6.8 × 10⁹ / L, Red blood cells 4.5 × 10⁹ / L." 12 / L, hemoglobin 135g / L, platelets 210×109 / L, neutrophil percentage 62%, lymphocyte percentage 30%, no obvious abnormalities observed. Based on the above summary, the large language model extracts key information and highlights it during the subsequent presentation.

[0075] After extracting various information items, the large language model can output them in a structured form. This structured output can be in JSON format. For example, for extracting dialogue information, the large language model outputs a JSON-formatted result: {"chief complaint": "...", "present illness": "...", "past medical history": "...", ...}; for medical reports, the large language model outputs a JSON-formatted result: {"date": "...", "title": "...", "institution": "...", ...}. Furthermore, the large language model can construct a reference relationship between the extracted key information and the original dialogue information. While outputting key information, the large language model provides the source of that key information in the original text, establishing a mapping relationship. For example, for the symptom description information extracted from the chief complaint, the large language model establishes a mapping relationship between this symptom description information and the source text in the dialogue information.

[0076] Through this embodiment, the terminal can summarize and extract key information from the above-mentioned dialogue information and historical medical report information using a large language model, thereby improving the efficiency of obtaining target abnormality description information and target historical medical information.

[0077] In one embodiment, displaying the target abnormality description information and the target historical diagnosis and treatment information in chronological order includes: for each time point, if there is a target symptom occurrence time that matches the time point, then displaying the symptom description information corresponding to the target symptom occurrence time at the time point on the preset time axis; if there is a target historical diagnosis and treatment time that matches the time point, then displaying the historical diagnosis and treatment type and historical diagnosis and treatment result corresponding to the target historical diagnosis and treatment time at the time point on the preset time axis.

[0078] In this embodiment, the extracted target abnormality description information includes the symptom occurrence time and symptom description information. The extracted target historical treatment information includes historical treatment time, historical treatment type, and historical treatment result. The terminal can display the extracted key information. The terminal can pre-set a preset timeline. The preset timeline includes multiple time points. For each time point, the terminal can detect whether there is a target symptom occurrence time matching that time point. If so, the terminal can determine to display the symptom description information corresponding to the target symptom occurrence time at that time point on the preset timeline. For example, it can display the symptom description information as a node at that time point.

[0079] For each time point, the terminal can detect whether a target historical treatment time exists that matches the time point. If it does, the terminal can determine to display the historical treatment type and results corresponding to the target historical treatment time at the aforementioned time point on the preset timeline. For example, this can be displayed as a node at the aforementioned time point.

[0080] Specifically, the aforementioned preset timeline can be a disease progression timeline. After summarizing the dialogue information and treatment report information, the terminal can construct a timeline based on date information. The timeline includes multiple time points, each representing a node, and the nodes are ordered chronologically. The content of a node can include the date, title, institution, and key information of the treatment report information corresponding to that time point. The key information can be treatment behavior (target historical treatment information), such as "CT scan: lung nodule, diameter 5mm", "Prescription: Drug 1, 0.5g, bid"; or it can be a description of the disease (target abnormal description information), such as "persistent fever for 3 days, highest temperature 39℃". If the node is constructed from a treatment report, the terminal can add a one-sentence summary of the report below the node, such as: "Report Summary: Left ventricular apical regional non-compaction, left and right ventricular function within normal range". If the node is constructed from dialogue information, the node can display the symptom occurrence time node extracted by the large language model, such as "Date xx, first occurrence of headache".

[0081] The nodes at various points in time along the aforementioned timeline can be merged and deduplicated. Multiple events at the same point in time (such as "Routine Blood Test on Date 1" and "Pre-consultation Report on Date 1") are merged into a single node. Except for the date, the title and institution are transformed into multiple sub-items. The terminal expands the node by detecting trigger information, displaying the results of the sub-items. Furthermore, if the timeline spans a large period, such as one year, the terminal can display only the most recent timeframe; the displayed time range is adjustable.

[0082] Through this embodiment, the terminal can display the extracted abnormal description information and diagnosis and treatment report information in chronological order via a timeline, which improves the intuitiveness of obtaining treatment information.

[0083] In one embodiment, the method further includes: in response to triggering information for the aforementioned jump option, displaying historical medical report information corresponding to the aforementioned target historical medical information.

[0084] In this embodiment, the target historical medical information also has a corresponding jump option, which can be set at a node of the target historical medical information in a preset timeline. There is a correlation between the target historical medical information and its corresponding historical medical report information (which serves as the original text). When the terminal detects a trigger for the jump option, such as a click, the terminal can display the historical medical report information corresponding to the target historical medical information. For example, after the jump option is clicked, the terminal displays the historical medical report information corresponding to the target historical medical information in a new window.

[0085] Through this embodiment, the terminal can add jump options to display the extracted key information in association with the original diagnosis and treatment report information, thereby improving the efficiency of obtaining treatment information of the patient.

[0086] In one embodiment, the method further includes: in response to the selection information of the fields of the structured information in the first window, displaying the text corresponding to the fields in the dialog information.

[0087] In this embodiment, the terminal can also display a first window during the display process. This first window displays structured information and the aforementioned dialogue information. The structured information includes a chief complaint module and a medical history module; the chief complaint module displays the chief complaint information from the dialogue information; the medical history module displays the medical history information from the dialogue information. That is, the first window can simultaneously display structured information and the dialogue information as the original text. The terminal can use a large language model to split the dialogue information, such as splitting it into JSON-like results {“chief complaint”:“…”, “present illness”:“…”, “past medical history”:“…”,…}, etc. The structured information in the first window can include the display of the chief complaint module and the medical history module (such as displaying present illness, past medical history, etc.). The chief complaint module can display information extracted from the dialogue information, such as descriptions of symptoms or assessments of physical signs; the medical history module can display information extracted from the dialogue information, such as present illness, past medical history, allergy history, surgical history, etc.

[0088] The structured information and the aforementioned dialogue information can be linked. For example, when the terminal detects selection information for a field in the structured information in the first window, the terminal can display the text corresponding to that field in the original dialogue information, such as highlighting it.

[0089] Specifically, the terminal can simultaneously display both the original dialogue information and the structured information from the structured output. In the first window, the terminal displays key information such as the chief complaint, present illness, past medical history, allergy history, and surgical history within the structured information section. This key information can be extracted from the dialogue information using a large language model. The terminal utilizes the extracted key information and its citations in the original text to highlight key information fields in the structured output. Sentences in the original dialogue information that provide this information are also highlighted, and users can click on key information fields to jump to the corresponding sentences in the dialogue information.

[0090] Through this embodiment, the terminal can simultaneously display structured information and dialogue information as the original text through a first window, and can also highlight them in conjunction, thereby improving the efficiency of obtaining treatment information of the treatment subject.

[0091] In one embodiment, the method further includes: in response to the trigger information for the target report type in the second window, displaying the historical medical report information for each of the target report types.

[0092] In this embodiment, the terminal can also display a second window during the presentation. This second window is used to display historical medical report information based on report type. This historical medical report information can include various types of information. The terminal can detect whether there is trigger information for the target report type in the second window, such as whether there is click information for the target report type. If so, the terminal can display various historical medical report information of the target report type in the second window.

[0093] Specifically, the terminal can categorize collected historical medical reports through a second window. Categories can include laboratory reports, imaging reports, case reports, etc. The terminal can quickly view relevant reports within the corresponding categories. It also includes a search function, allowing for quick matching from report summaries using search fields.

[0094] Through this embodiment, the terminal can display various types of medical report information through a second window. By selecting the corresponding category, the medical report information can be viewed in the corresponding category, which improves the efficiency of obtaining treatment information of the patient.

[0095] In one exemplary embodiment, such as Figure 2 As shown, Figure 2 This is a flowchart illustrating a treatment information display method in another embodiment.

[0096] In this embodiment, the terminal can collect information.

[0097] In this system, after a patient requests a consultation, before the consultation officially begins, the terminal guides the patient and the intelligent consultation agent to interact. The intelligent agent collects basic information about the patient's condition. For example, the intelligent agent can set initial questions such as "Where do you feel unwell?" or "What symptoms do you have?" The intelligent agent asks these questions to the patient through text and voice prompts. The patient can answer the questions by entering text, clicking options, uploading images, or using voice input. The intelligent agent can then ask follow-up questions based on a medical knowledge base, a question set, and the patient's responses. For example, if the patient replies that they have a cough, the intelligent agent might ask, "How long have you been coughing?" The intelligent agent connects to the patient's device via the network, and the patient accesses it through an application or webpage. After the intelligent agent finishes asking questions, it saves all the dialogue information with the patient.

[0098] The terminal also acquires historical medical reports. For medical reports from institutions outside the terminal's location, patients can upload these reports (paper or electronic) to the terminal. For example, patients can save the medical report to their photo album by taking a picture or screenshot using their image acquisition device, and then upload the saved report to the terminal's information collection module from an application or webpage. The upload can be in image format. The terminal performs image processing on the uploaded image through the information collection module, including rotation, correction, and cropping, to ensure that the information can be correctly recognized. For example, if the patient rotated the report by 90° when taking the picture, the terminal will correct it through the information collection module. Then, the terminal will recognize the processed image, using Optical Character Recognition (OCR) technology and a large visual model to read the text in the medical report and obtain the text content corresponding to each report.

[0099] For the medical reports of the institutions where the terminals are located, the terminals search for the medical records of the patients in the local database based on the unique identification code (identifier) ​​of the patients. If the patients have been treated at the institutions, the terminals obtain their medical reports, treatment records and other information to obtain the second medical report information.

[0100] The terminal utilizes a large language model for information summarization. It can summarize and segment the aforementioned dialogue information. For example, through the large language model, it can extract the chief complaint, present illness, past medical history, surgical history, family history, and smoking history from the dialogue information. The chief complaint refers to a concise description of the main symptoms, signs, and their duration described by the patient during their visit; the present illness, past medical history, surgical history, family history, and smoking history can serve as medical history description information. The terminal can also extract key information through retrieval enhancement generation algorithms. For example, by using retrieval enhancement generation tools, external medical knowledge bases or documents can be introduced into the large language model. Combining the large language model with external knowledge, it can further extract key phrases from the above summary, such as the most important and obvious symptoms or signs in the chief complaint (symptom description information), and the duration of these symptoms or signs (symptom onset time).

[0101] For the collected historical medical reports, the terminal uses a large language model to extract key information such as time (historical treatment time), title (historical treatment type), institution, and conclusion (historical treatment result). The large language model then combines the extracted information into a single summary sentence. For example, "On XX date, a complete blood count was performed at XX institution. Results: White blood cells 6.8 × 10⁹ / L, Red blood cells 4.5 × 10⁹ / L." 12 / L, hemoglobin 135g / L, platelets 210×109 / L, neutrophil percentage 62%, lymphocyte percentage 30%, no obvious abnormalities observed. Based on the above summary, the large language model extracts key information and highlights it during the subsequent presentation.

[0102] After extracting various information items, the large language model can output them in a structured form. This structured output can be in JSON format. For example, for extracting dialogue information, the large language model outputs a JSON-formatted result: {"chief complaint": "...", "present illness": "...", "past medical history": "...", ...}; for medical reports, the large language model outputs a JSON-formatted result: {"date": "...", "title": "...", "institution": "...", ...}. Furthermore, for dialogue information, the large language model can also extract key information and the citation relationships between key information and the original text. While outputting key information, the large language model provides the source of the key information in the original text, establishing a mapping relationship. For example, for the symptom description information extracted from the chief complaint, the large language model establishes a mapping relationship between this symptom description information and the source text in the dialogue information.

[0103] The terminal can also display patient symptoms. During this display, after summarizing the aforementioned dialogue and treatment report information, the terminal can construct a timeline based on date information. The timeline includes multiple time points, each representing a node, and the nodes are ordered chronologically. The content of each node can include the date, title, institution, and key information of the corresponding treatment report. Key information can be treatment behavior (target historical treatment information), such as "CT scan: lung nodule, diameter 5mm," or "Prescription: Drug 1, 0.5g, bid"; or it can be a description of the symptoms (target abnormal description information), such as "persistent fever for 3 days, highest temperature 39℃." If the node is constructed from a treatment report, the terminal can add a one-sentence summary of the report below the node, for example: "Report Summary: Left ventricular apical regional non-compaction, left and right ventricular function within normal range." The terminal can also add a jump option at the corresponding node in the treatment report, allowing users to view the original treatment report content. If the node is constructed from dialogue information, the node can display the symptom occurrence time point extracted by the large language model, such as "Date xx, first occurrence of headache."

[0104] The nodes at various points in time along the aforementioned timeline can be merged and deduplicated. Multiple events at the same point in time (such as "Routine Blood Test on Date 1" and "Pre-consultation Report on Date 1") are merged into a single node. Except for the date, the title and institution are transformed into multiple sub-items. The terminal expands the node by detecting trigger information, displaying the results of the sub-items. Furthermore, if the timeline spans a large period, such as one year, the terminal can display only the most recent timeframe; the displayed time range is adjustable.

[0105] The terminal can simultaneously display both the original dialogue information and the structured information from the structured output. Specifically, the terminal divides the structured information in the first window into blocks (such as the chief complaint module and medical history module mentioned above), displaying key information such as the chief complaint, present illness, past medical history, allergy history, and surgical history. This key information can be extracted from the dialogue information using a large language model. Utilizing the extracted key information and its citation relationships in the original text, the terminal highlights key information fields in the structured output. Sentences in the original dialogue information that provide this information are also highlighted, and clicking on a key information field allows users to jump to the corresponding sentence in the dialogue information.

[0106] The terminal can categorize collected historical medical reports through a second window. Categories can include laboratory reports, imaging reports, case reports, etc. Users can quickly access relevant reports within each category. A search function is also included, allowing for rapid matching from report summaries using search fields.

[0107] Through the above embodiments, the terminal completes the collection and organization of patient information before the consultation. On the doctor's terminal device, the patient's condition development and treatment are displayed in a timeline manner, which helps the doctor quickly understand the patient's condition, shortens the entire consultation time, and improves efficiency.

[0108] It should be understood that although the operations in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these operations are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these operations, and they can be executed in other orders. Moreover, at least some of the operations in the flowcharts of the embodiments described above may include multiple operations or multiple stages. These operations or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these operations or stages is not necessarily sequential, but can be performed alternately or in turn with other operations or at least some of the operations or stages in other operations. It is understood that the operations in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0109] Based on the same inventive concept, this application also provides a treatment information display device for implementing the treatment information display method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more treatment information display device embodiments provided below can be found in the limitations of the treatment information display method described above, and will not be repeated here.

[0110] In one exemplary embodiment, such as Figure 3 As shown, a treatment information display device is provided, including: an acquisition module 500, an input module 502, and a display module 504, wherein:

[0111] The acquisition module 500 is used to acquire dialogue information and historical medical report information; the dialogue information represents the dialogue information between the treatment subject and the consultation agent.

[0112] The input module 502 is used to input the above-mentioned dialogue information and the above-mentioned historical medical report information into the large language model; the above-mentioned large language model is used to obtain the target abnormality description information and target historical medical information corresponding to the above-mentioned treatment object based on the above-mentioned dialogue information and the above-mentioned historical medical report information; the above-mentioned target abnormality description information represents the abnormality description information with the first target feature in the above-mentioned dialogue information; the above-mentioned target historical medical information represents the historical medical information with the second target feature in the above-mentioned historical medical report information.

[0113] The display module 504 is used to display the above-mentioned target abnormality description information and the above-mentioned target historical diagnosis and treatment information in chronological order.

[0114] In one embodiment, the acquisition module 500 is configured to output an initial question from a question set in response to triggering information for the consultation agent; the question set includes the initial question and one or more follow-up questions; the initial question represents a question related to the type of symptom; based on the answer information of the treatment subject based on the initial question input, the corresponding target follow-up question is determined from the question set and output until a preset termination condition is met, and the dialogue information is obtained based on the initial question, each of the target follow-up questions and each of the answer information.

[0115] In one embodiment, the acquisition module 500 is used to obtain the historical medical report information based on one or more of the first medical report information and the second medical report information; wherein the first medical report information is extracted based on the medical report image uploaded by the treatment subject; and the second medical report information is obtained by querying the local database based on the identifier corresponding to the treatment subject.

[0116] In one embodiment, the input module 502 is used to obtain external medical knowledge base information corresponding to the dialogue information and the historical medical report information through a retrieval enhancement generation algorithm; extract the symptom occurrence time, symptom description information and medical history description information from the dialogue information through a large language model based on the external medical knowledge base information and the first target feature to obtain the target abnormal description information; and extract the historical treatment time, historical treatment type and historical treatment result from the historical medical report information through a large language model based on the second target feature to obtain the target historical medical information.

[0117] In one embodiment, the display module 504 is configured to, for each time point, if there is a target symptom occurrence time matching the time point, display symptom description information corresponding to the target symptom occurrence time at the time point on the preset time axis; if there is a target historical treatment time matching the time point, display the historical treatment type and historical treatment result corresponding to the target historical treatment time at the time point on the preset time axis.

[0118] In one embodiment, the device further includes a jump module, configured to display historical medical report information corresponding to the target historical medical information in response to triggering information for the jump option.

[0119] In one embodiment, the apparatus further includes a dialogue display module, configured to display the text corresponding to the fields in the dialogue information in response to the selection information of the fields in the first window for the structured information.

[0120] In one embodiment, the apparatus further includes a report display module, configured to display the historical medical report information of each of the target report types in response to the trigger information for the target report type in the second window.

[0121] Each module in the aforementioned treatment information display device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0122] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for displaying therapeutic information. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0123] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0124] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method for displaying treatment information.

[0125] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the treatment information display method described above.

[0126] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method for displaying treatment information.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0128] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0129] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0130] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for displaying treatment information, the method comprising: Obtain dialogue information and historical medical reports; The dialogue information represents the dialogue information between the treatment subject and the intelligent consultation agent; The dialogue information and the historical medical report information are input into a large language model; the large language model is used to obtain target abnormality description information and target historical medical report information corresponding to the treatment object based on the dialogue information and the historical medical report information; the target abnormality description information represents the abnormality description information with a first target feature in the dialogue information; the target historical medical report information represents the historical medical report information with a second target feature; The abnormal description information of the target and the historical diagnosis and treatment information of the target are displayed in chronological order.

2. The method according to claim 1, wherein the operation of acquiring the dialogue information includes: In response to the triggering information for the consultation agent, the initial question from the question set is output; The set of questions includes an initial question and one or more follow-up questions; The initial question characterizes the question in relation to the type of symptom; Based on the treatment subject's response information to the initial question input, corresponding target follow-up questions are determined from the question set and output until a preset termination condition is met. Then, based on the initial question, each target follow-up question, and each response information, the dialogue information is obtained.

3. The method according to claim 1, wherein the operation of obtaining the historical medical report information includes: The historical medical report information is obtained based on one or more of the first and second medical report information; The first medical report information is extracted from the medical report image uploaded by the patient; the second medical report information is obtained by querying the local database based on the identifier corresponding to the patient.

4. The method according to claim 1, wherein obtaining the target abnormality description information and target historical medical information corresponding to the treatment subject based on the dialogue information and the historical medical report information includes: By using a retrieval enhancement generation algorithm, external medical knowledge base information corresponding to the dialogue information and the historical medical report information is obtained; Based on the external medical knowledge base information and the first target feature, the large language model extracts the symptom occurrence time, symptom description information and medical history description information from the dialogue information to obtain the target abnormal description information. Based on the second target feature, the large language model extracts the historical treatment time, historical treatment type, and historical treatment result from the historical treatment report information to obtain the target historical treatment information.

5. The method according to claim 1, wherein the target abnormality description information includes symptom occurrence time and symptom description information; the target historical diagnosis and treatment information includes historical diagnosis and treatment time, historical diagnosis and treatment type, and historical diagnosis and treatment result; The step of displaying the target anomaly description information and the target historical diagnosis and treatment information in chronological order includes: For each time point, if there is a target symptom occurrence time that matches the time point, then the symptom description information corresponding to the target symptom occurrence time is displayed at the time point on the preset time axis. If a target historical treatment time that matches the specified time point exists, then the historical treatment type and historical treatment result corresponding to the target historical treatment time are displayed at the specified time point on the preset time axis.

6. The method according to claim 1, further comprising a jump option corresponding to the target historical medical information; The method further includes: In response to the trigger information for the jump option, the historical medical report information corresponding to the target historical medical information is displayed.

7. The method according to claim 1, further comprising a first window; the first window being used to display structured information and the dialogue information; the structured information including a chief complaint module and a medical history module; the chief complaint module being used to display the chief complaint information in the dialogue information; the medical history module being used to display the medical history information in the dialogue information; The method further includes: In response to the selection information of the field of the structured information in the first window, the text corresponding to the field in the dialog information is displayed.

8. The method according to any one of claims 1 to 7, further comprising a second window; the second window being used to display the historical medical report information based on the report type; The method further includes: In response to the trigger information for the target report type in the second window, the historical medical report information of each target report type is displayed.

9. A treatment information display device, the device comprising: The acquisition module is used to acquire dialogue information and historical medical report information; The dialogue information represents the dialogue information between the treatment subject and the intelligent consultation agent; An input module is used to input the dialogue information and the historical medical report information into a large language model; the large language model is used to obtain target abnormality description information and target historical medical report information corresponding to the treatment object based on the dialogue information and the historical medical report information; the target abnormality description information represents the abnormality description information with a first target feature in the dialogue information; the target historical medical report information represents the historical medical report information with a second target feature; The display module is used to display the abnormal description information of the target and the historical diagnosis and treatment information of the target in chronological order.

10. The apparatus according to claim 9, wherein the acquisition module is configured to: In response to triggering information for the diagnostic agent, an initial question from a question set is output; the question set includes the initial question and one or more follow-up questions; the initial question represents a question related to the type of symptom. Based on the treatment subject's response information to the initial question input, corresponding target follow-up questions are determined from the question set and output until a preset termination condition is met. Then, based on the initial question, each target follow-up question, and each response information, the dialogue information is obtained.

11. The apparatus according to claim 9, wherein the acquiring module is configured to: The historical medical report information is obtained based on one or more of the first and second medical report information; in, The first medical report information is extracted from the medical report image uploaded by the patient; the second medical report information is obtained by querying the local database based on the identifier corresponding to the patient.

12. The apparatus according to claim 9, wherein the input module is configured to: By using a retrieval enhancement generation algorithm, external medical knowledge base information corresponding to the dialogue information and the historical medical report information is obtained; Based on the external medical knowledge base information and the first target feature, the large language model extracts the symptom occurrence time, symptom description information and medical history description information from the dialogue information to obtain the target abnormal description information. Based on the second target feature, the large language model extracts the historical treatment time, historical treatment type, and historical treatment result from the historical treatment report information to obtain the target historical treatment information.

13. The apparatus according to claim 9, wherein the target abnormality description information includes symptom occurrence time and symptom description information; the target historical diagnosis and treatment information includes historical diagnosis and treatment time, historical diagnosis and treatment type, and historical diagnosis and treatment result; The display module is used for: For each time point, if there is a target symptom occurrence time that matches the time point, then the symptom description information corresponding to the target symptom occurrence time is displayed at the time point on the preset time axis. If a target historical treatment time that matches the specified time point exists, then the historical treatment type and historical treatment result corresponding to the target historical treatment time are displayed at the specified time point on the preset time axis.

14. The device according to claim 9, further comprising a jump option corresponding to the target historical medical information; The device further includes: Jump module, used for: In response to the trigger information for the jump option, the historical medical report information corresponding to the target historical medical information is displayed.

15. The apparatus according to claim 9, further comprising a first window; the first window being used to display structured information and the dialogue information; the structured information including a chief complaint module and a medical history module; the chief complaint module being used to display the chief complaint information in the dialogue information; the medical history module being used to display the medical history information in the dialogue information; The device further includes: The dialogue display module is used for: In response to the selection information of the field of the structured information in the first window, the text corresponding to the field in the dialog information is displayed.

16. The apparatus according to any one of claims 9 to 15, further comprising a second window; the second window being used to display the historical medical report information based on the report type; The device further includes: The report display module is used for: In response to the trigger information for the target report type in the second window, the historical medical report information of each target report type is displayed.

17. A computer device comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the operation of the method according to any one of claims 1 to 8.

18. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the operation of the method according to any one of claims 1 to 8.

19. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it performs the operation of the method according to any one of claims 1 to 8.

Images