Interaction information processing method applied to patient data interconnection system

Abstract

The embodiment of the invention discloses an interaction information processing method applied to a patient data interconnection system. A specific embodiment of the method comprises the steps that a nursing end detects a viewing operation acting on certain patient information and sends a patient information viewing request to an associated patient data storage system; sorting the patient information according to the currently acquired patient information corresponding to the patient information viewing request and the historical patient information list; according to the information content in the patient information list, determining the display position of the information sliding icon in the patient information monitoring interaction page when the patient information is loaded; in response to detecting that the information sliding icon moves to a set position of the patient information monitoring interaction page, loading and rendering the patient information content in the patient information list, and moving the information sliding icon to a display position. According to the embodiment, under the condition that the current display position is not changed, an efficient rolling loading and display mechanism of the current patient information can be realized.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of interaction information, and more particularly to an interaction information processing method applied to a patient data interconnection system. Background Art

[0002] In the daily care of patients admitted to the hospital, it is necessary to monitor the physical indicators of patients. Especially for patients with a history of diabetes, blood glucose monitoring is of utmost importance. The current work process is as follows: Use the portable scanning device of the nursing staff to scan the patient code worn by the patient, and perform process operations according to the nursing execution given on the scanning device. The process interface shows the items to be operated. Click and check to save. At this time, the scanning device will record the blood glucose measurement time. After the measurement is completed, a test report will be printed out, and the measured value will be handwritten. Then, the test report will be pasted on the test paste sheet and placed in a fixed location for use and storage. However, due to the dynamic loading of patient information, the information sliding icon often slides, which requires the nursing staff to repeatedly slide up and down to view in order to find the corresponding historical patient information. This sliding of the information sliding icon is likely to cause the nursing staff to miss important information and affect the subsequent care of patients. Summary of the Invention

[0003] This section of the present application is used to briefly introduce concepts that will be described in detail in the subsequent Detailed Description section. This section of the present application is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] Some embodiments of the present application propose an interaction information processing method, a computer device, and a computer-readable storage medium applied to a patient data interconnection system to solve one or more of the technical problems mentioned in the above Background Art section.

[0005] In a first aspect, some embodiments of the present application provide an interactive information processing method applied to a patient data interconnection system, the patient data interconnection system comprising: a nursing end and a patient data storage system, the method comprising: the nursing end detects a viewing operation on a certain patient information in a patient information monitoring interaction page, and sends a patient information viewing request to the associated patient data storage system; the nursing end sorts the patient information according to the currently acquired patient information corresponding to the patient information viewing request and the historical patient information list to obtain a patient information list, wherein the patient information list and the patient information correspond to the same patient user; the nursing end determines, according to the information content in the patient information list, a display position of an information sliding icon in the patient information monitoring interaction page when loading the patient information; in response to detecting that the information sliding icon moves to a set position on the patient information monitoring interaction page, the nursing end loads and renders the patient information content in the patient information list, and moves the information sliding icon to the display position to maintain the position of the currently displayed information in the patient information monitoring interaction page.

[0006] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0007] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0008] The above-mentioned various embodiments of the present application have the following beneficial effects: through the interactive information processing method applied to the patient data interconnection system of some embodiments of the present application, an efficient scrolling loading and display mechanism of the current patient information can be realized without changing the current display position. This can reduce the time required to consult patient information and reduce the omission of patient information. By optimizing the calculation mode of the dynamic position of the information sliding icon display, it can ensure that the position of the information sliding icon is stable in the case of high-frequency asynchronous loading of messages, avoid mutations and delays, reduce unnecessary component rendering, and significantly improve the page loading speed and response performance. Smooth maintenance of the current display position is achieved through animation. Further avoid sliding of the scrolling position to ensure the stability of nursing staff browsing the page. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In conjunction with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the embodiments of the present application will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0010] Figure 1 is a flowchart of some embodiments of an interactive information processing method applied to a patient data interconnection system according to the present application; Figure 2 is a schematic structural diagram of a computer device suitable for implementing some embodiments of the present application; Figure 3 is a schematic diagram of a scenario of a patient information monitoring and interaction page in an interactive information processing method applied to a patient data interconnection system according to the present application. Specific Embodiments

[0011] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not used to limit the protection scope of the present application.

[0012] In addition, it should be noted that for the sake of convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0013] It should be noted that the concepts such as "first" and "second" mentioned in the present application are only used to distinguish different devices, modules, or units, and are not used to limit the order of the functions executed by these devices, modules, or units or their interdependent relationships.

[0014] It should be noted that the modifications of "one" and "multiple" mentioned in the present application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0015] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0016] The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0017] Refer to Figure 1, which shows the flow 100 of some embodiments of the interactive information processing method applied to the patient data interconnection system according to the present application. The interactive information processing method applied to the patient data interconnection system, the above patient data interconnection system includes: a nursing end and a patient data storage system, and includes the following steps: Step 101, the nursing end detects a viewing operation on a certain patient information in the patient information monitoring interactive page, and sends a patient information viewing request to the associated patient data storage system.

[0018] In some embodiments, the nursing end detects a viewing operation on a certain patient information in the patient information monitoring interactive page, and sends a patient information viewing request to the associated patient data storage system. The patient information monitoring interactive page may refer to an interactive page that displays various patient information. The nursing staff can click on the control of a certain patient information in the patient information monitoring interactive page to view the detailed patient information. If the patient only needs to be observed, the patient information may include, but is not limited to: indicators such as blood glucose value, blood pressure, body temperature, heart rate, blood lipid, etc. If the patient also needs various medication care, the patient information may also include: glucose (Glu) measurement, whether the urinary catheter is indwelling, whether oxygen is inhaled, etc. The nursing end has a display and a processor. The display is used to display the patient information monitoring interactive page. The processor can be used to send and receive information and give instruction feedback. For example, after the nursing end detects a viewing operation (click operation) of the nursing staff on a certain patient information in the patient information monitoring interactive page, it sends a patient information viewing request to the associated patient data storage system. The patient information viewing request may represent a request to view the detailed patient information of the patient user corresponding to the patient information. Since the nursing end is a portable terminal, in order to prevent the nursing end from getting stuck due to storing too much patient information, the various historical examination information (various disease information and physical sign information) of the patient is stored in the patient data storage system. The patient information viewing request includes the identifier of the corresponding patient user.

[0019] It should be noted that the nursing terminal can refer to the terminal managed and operated by nursing staff. For example, the nursing terminal can be the terminal operated and managed by nurses. The patient data storage system can be used to collect / store the patient information of each patient. The patient information can include: patient name, patient age, patient weight, patient disease information, patient physical sign information, and the collection time corresponding to each index. For example, for the collection of patient information, a portable patient information detection device can be used to detect the physical sign data of the patient user. After that, the detection time, detection value, and comparison value can all be recorded in the patient data storage system. There is an information report corresponding to the patient data storage system. For example, if it is predicted that the change in the patient's blood glucose value is large, fluctuating greatly, but there are no obvious symptoms, a warning will be given, and a prompt message will be given in the portable detection device and the system, considering the occurrence of acute risks and chronic complications, especially the risks of macrovascular complications and neuropathy, reminding the nursing terminal to confirm again and recording it in the patient data storage system for doctors (with permissions) to view. Especially for previous diabetic patients who need to be monitored closely, they are tested 4 times a day. The comparison and evaluation of the blood glucose values of such patients over multiple days will also be recorded in the system to provide data support for risk prevention. For example, the portable patient information detection device can refer to a portable multi-functional vital sign monitoring device, including: an electrode vest, an airbag vest, electrode patches, and a cuff host. The cuff host can be fixed on the arm like a cuff and is provided with a power supply, a display screen, operation buttons, a blood pressure detection airbag, an air pump, and a control system. The air pump is controlled by the control system to inflate the blood pressure detection airbag regularly so that the control system can obtain blood pressure information regularly. The electrode patches can be fixed on the electrode vest, and the electrode patches can transmit electrical signals to the cuff host. The airbag vest is located outside the electrode vest and can be fixed to the electrode vest to inflate the airbag inside the airbag vest according to the contact situation of the visible electrode patches so that the electrode patches on the electrode vest can be in closer contact with the skin.

[0020] It should be noted that in the patient information monitoring and interaction page, the patient information is usually arranged in chronological order, and the latest patient information is often arranged at the front. Generally, the nursing staff can scroll up the scroll bar to display the patient information in the visible area. In some application scenarios, the patient information can also be arranged in reverse order. At this time, the nursing staff can scroll down the scroll bar to display the patient information in the visible area.

[0021] Step 102, the above-mentioned nursing terminal sorts the patient information according to the patient information corresponding to the current patient information viewing request and the historical patient information list to obtain a patient information list.

[0022] In some embodiments, the above-mentioned care terminal views the patient information corresponding to the above-mentioned patient information viewing request based on the currently obtained patient information and the historical patient information list, sorts the patient information, and obtains the patient information list. Among them, the historical patient information list corresponds to the same patient user as the above-mentioned patient information. The historical patient information list can represent various detection information of the patient user in history. The historical patient information may include: the historical physical sign information of the patient user and the historical disease detection information. The historical physical sign information of the patient user may refer to the physical sign information corresponding to the historical time point. The historical disease detection information may refer to the disease information detected by the patient user at the historical time point (for example, it may include: disease name, symptoms, medication information, etc.). For example, the sorting can be set according to actual needs, such as in chronological order or reverse order, etc.

[0023] It should be noted that after the care terminal sends a patient information viewing request to the patient data storage system, the patient data storage system will feedback the corresponding detailed patient information and the patient information list to the care terminal.

[0024] Step 103, the above-mentioned care terminal determines the display position of the information sliding icon on the above-mentioned patient information monitoring interaction page when loading the patient information according to the information content in the patient information list.

[0025] In some embodiments, the above-mentioned care terminal determines the display position of the information sliding icon on the above-mentioned patient information monitoring interaction page when loading the patient information according to the information content in the patient information list. If the patient information is displayed on the patient information monitoring interaction page, the (starting) position where the information sliding icon is located is the display position. For example, there is no restriction on the information sliding icon, and it can be a common scroll bar or sliding cursor in the existing patient information monitoring interaction page.

[0026] In an actual application scenario, the above-mentioned care terminal can determine the display position of the information sliding icon on the above-mentioned patient information monitoring interaction page when loading the patient information through the following steps: The first step is to determine the content height of the previous patient information and the content height of the above-mentioned patient information according to the information content in the above-mentioned patient information list. For example, the total content height of the previous patient information (patient information list) (as Figure 3 illustrated) can be determined as the content height of the previous patient information. Figure 3Displays an example diagram of a patient information monitoring interaction page, showing "Patient Information 1". "Patient Information 1" can refer to historical patient information, which can include: disease information and physical sign information. "Disease information" and "physical sign information" can be displayed in the form of controls. The "information sliding icon" can be a "slider bar". "Patient Information 1" can refer to the height of the display area of "Patient Information 1". The "overflow area" indicates that the "patient information" is hidden. The "total content height" can refer to the "total height" of the obtained patient information list.

[0027] Among them, the above-mentioned first step can include the following sub-steps: Sub-step 1: Compare the total height of the element content of the patient information list in the above-mentioned patient information list with the height of the visible area in the above-mentioned patient information monitoring interaction page to obtain a first comparison result.

[0028] Sub-step 2: Determine the content height of the previous patient information through the first comparison result.

[0029] For example, the execution subject can compare and analyze the total height of the element content of the patient information in the patient information list with the height of the visible area in the patient information monitoring interaction page. Determine the content height of the previous patient information according to the comparison result. If the total height of the element content of the patient information in the patient information list is less than the height of the visible area, the height of the visible area can be determined as the content height of the previous patient information. If the total height of the element content is greater than the height of the visible area, the total height of the element content can be determined as the content height of the previous patient information.

[0030] Sub-step 3: Compare the total height of the content of the above-mentioned patient information in the above-mentioned patient information list with the height of the visible area in the above-mentioned patient information monitoring interaction page to obtain a second comparison result.

[0031] Sub-step 4: Determine the content height of the above-mentioned patient information through the second comparison result.

[0032] For example, the total height of the element content of the patient information in the patient information list can be compared and analyzed with the height of the visible area in the patient information monitoring interaction page. Determine the content height of the patient information according to the comparison result. Similarly, if the total content height of the patient information is less than the height of the visible area, the height of the visible area can be determined as the content height of the patient information. If the total content height of the patient information is greater than the height of the visible area, the total content height can be determined as the content height of the patient information.

[0033] The second step: Determine the content height difference between the content height of the previous patient information and the content height of the above-mentioned patient information.

[0034] Step 3: Determine the display position of the information sliding icon on the patient information monitoring interaction page when loading the patient information according to the above height difference.

[0035] Step 104: In response to detecting that the information sliding icon moves to the set position on the patient information monitoring interaction page, the nursing end loads and renders the patient information content in the patient information list, and moves the information sliding icon to the display position, keeping the position of the currently displayed information on the patient information monitoring interaction page.

[0036] In some embodiments, in response to detecting that the information sliding icon moves to the set position on the patient information monitoring interaction page, the nursing end loads and renders the patient information content in the patient information list, and moves the information sliding icon to the display position, keeping the position of the currently displayed information on the patient information monitoring interaction page. Among them, the set position can be set according to actual needs, such as Figure 3 the top or bottom of the visible area in the patient information monitoring interaction page as shown. That is, after calculating the display position of the information sliding icon on the patient information monitoring interaction page, the information sliding icon will move and stay at this display position, and at the same time, the patient information monitoring interaction page will not slide.

[0037] In some embodiments, to ensure the smooth movement of the information sliding icon, the properties can be set through Cascading Style Sheets (CSS). For example, the property of scroll-behavior can be set to smooth, and the keyframes animation property can be used to set an animation transition effect for the sliding element from 0% to 100% within 1 s. Among them, scroll-behavior is a property in CSS used to control the behavior of an element when scrolling to a specified position. Keyframes is a technology in CSS used to define the style changes at a certain stage during an animation. That is, according to the pre-set smooth properties and animation properties in the Cascading Style Sheets, the execution entity can smoothly move the information sliding icon to the display position within the set time.

[0038] In an actual application scenario, the nursing end can load and render the patient information content in the patient information list through the following steps, and move the information sliding icon to the display position, keeping the position of the currently displayed information on the patient information monitoring interaction page: Step 1: In response to detecting that the information sliding icon moves to the first preset position on the patient information monitoring interaction page according to the above viewing operation, render the patient information content in the patient information list.

[0039] In the second step, in response to detecting the above information, slide the icon to the second preset position on the above patient information monitoring interaction page, move the above information slide icon to the above display position, and keep the currently displayed information in the position on the above patient information monitoring interaction page, where the above first preset position is less than or equal to the above second preset position, the above first preset position is the position of a set number of pixels from one end of the visible area in the above patient information monitoring interaction page, the above second preset position is one end of the above visible area, and one end of the above visible area is the top or the bottom.

[0040] Among them, the first preset position and the second preset position can be set according to actual needs. For example, the first preset position can be the position of a set number of pixels (such as 600px) from one end of the visible area in the patient information monitoring interaction page; and the second preset position can be one end of the visible area. Among them, one end of the visible area is usually the top or the bottom. That is to say, the information slide icon usually passes through the first preset position first and then through the second preset position. In this way, when the patient information monitoring interaction page detects a patient information viewing operation and the information slide icon reaches the first preset position of the patient information monitoring interaction page, the execution entity can send a patient information viewing request to the patient data storage system and perform patient information content loading and rendering.

[0041] Furthermore, in response to receiving the disease problem information of the corresponding target patient user sent by the above nursing end, the above patient data storage system performs feature extraction processing on the above disease problem information to obtain a disease problem feature information set.

[0042] In some embodiments, the patient data storage system, in response to receiving the disease problem information corresponding to the target patient user sent by the nursing terminal, performs feature extraction processing on the disease problem information to obtain a disease problem feature information set. Among them, the target patient user is the patient user corresponding to a certain patient information in the patient information monitoring and interaction page. The disease problem information can represent the disease consultation information or the disease problem text consultation information submitted by the nursing staff corresponding to the target patient user. For example, the disease problem information can be sliced, and corresponding disease problem keywords can be found from each phrase obtained from the slice as the disease problem feature information set. For another example, the disease problem information can be subjected to feature extraction processing through a rule-based method / a machine learning-based method / a deep learning-based method / a hybrid model / a multimodal model to obtain a disease problem feature information set. For example, the rule-based method can include: 1. Keyword extraction: Extract keywords in the question through predefined rules or dictionaries; 2. Syntactic analysis: Use syntactic structures (such as dependency syntactic analysis) to extract the main body and modifiers of the question. For example, the machine learning-based method can include: 1. Traditional classifiers: such as SVM, random forest, etc., combined with manual features (such as part-of-speech, syntactic features) for classification; 2. Conditional random field (CRF): Used for sequence labeling tasks, such as named entity recognition. The deep learning-based method can include: 1. CNN: Extract local features, suitable for short text classification; 2. RNN / LSTM / GRU: Process sequence data and capture context information; 3. Transformer: Capture long-distance dependencies through self-attention mechanisms, and pre-trained models such as BERT and GPT are often used for question understanding; 4. Pre-trained language models: such as BERT, RoBERTa, XLNet, etc., extract question features through fine-tuning. The hybrid model can include: 1. Combining rules and statistics: such as using TF-IDF to extract keywords after rule filtering. 2. Combining deep learning and traditional methods: such as inputting the features extracted by BERT into a traditional classifier. The multimodal model can include: Combining text and image: such as VL-BERT, UNITER, to process multimodal data.

[0043] Further, the patient data storage system performs the following retrieval steps according to the disease problem feature information set: The first retrieval step is to retrieve the reference disease problem fragment sequence corresponding to the above disease problem feature information set and the doctor-set disease problem fragment sequence from the preset disease problem knowledge base. Among them, the above disease problem knowledge base includes: a standard reference disease problem fragment database and a doctor-set disease problem fragment database. Among them, the reference disease problem fragment sequence corresponds to the standard reference disease problem fragment database. The doctor-set disease problem fragment sequence corresponds to the doctor-set disease problem fragment database. The disease problem knowledge base can be a question-and-answer knowledge base for various disease problems pre-constructed by combining technologies such as full-text retrieval, vector models, and large language models. For example, the intelligent knowledge base can store questions about disease symptoms, disease diagnosis, medical advice for diseases, etc. The standard reference disease problem fragment database can refer to the ElasticCloud database or the milvus vector database. The distributed search database can refer to the OpenSearch database or the Lucene vector database. For example, first, convert the above disease problem feature information into word vectors; then, the reference disease problem fragment with the highest similarity can be retrieved from the standard reference disease problem fragment database, so as to obtain the reference disease problem fragment sequence. The doctor-set disease problem fragment with the highest similarity can be retrieved from the doctor-set disease problem fragment database, so as to obtain the doctor-set disease problem fragment sequence. A disease problem fragment can refer to a problem fragment after slicing a specific problem. Multiple problem fragments form a complete problem. One disease problem type corresponds to one disease problem document type. The standard reference disease problem fragment database can refer to a database of various disease problem fragments constructed from medical standard textbooks. The doctor-set disease problem fragment database can refer to a database of disease problem fragments constructed by doctors after actual diagnosis and refinement and supplementation of various disease problems.

[0044] The second retrieval step is to determine whether the disease problem type corresponding to the above doctor-set disease problem fragment sequence is a common disease problem type. The common disease problem type can refer to common disease problem types. For example, the disease problem types can include: type I, type II, type III, type IV. "Type I" and "type II" can be set as common and common problem types. It should be noted that each disease problem fragment corresponds to a disease problem type. The disease problem types corresponding to each disease problem fragment can be the same or different.

[0045] Third retrieval step, in response to determining that the above-mentioned disease problem type is not a common disease problem type, determine whether there is a corresponding disease problem response text for the above-mentioned reference disease problem fragment sequence. For example, it can be determined whether there is a disease problem response text for the target disease problem condition in the reference disease problem fragment sequence. The target disease problem condition can be: there is only one disease problem response text in the standard reference disease problem fragment database that contains the most reference disease problem fragments. For example, the reference disease problem fragment sequence includes: reference disease problem fragment A, reference disease problem fragment B, reference disease problem fragment C, reference disease problem fragment D, reference disease problem fragment E; among them, there is a disease problem response text A in the standard reference disease problem fragment database that contains "reference disease problem fragment A, reference disease problem fragment B, reference disease problem fragment C, reference disease problem fragment D"; there is a disease problem response text B in the standard reference disease problem fragment database that contains "reference disease problem fragment C, reference disease problem fragment D, reference disease problem fragment E"; then the disease problem response text A meets the target disease problem condition.

[0046] Fourth retrieval step, in response to determining that there is a corresponding disease problem response text for the above-mentioned reference disease problem fragment sequence, generate disease problem response information corresponding to the above-mentioned disease problem feature information set according to the above-mentioned disease problem response text. For example, a preset number of disease problem fragments associated with the disease problem response text can be retrieved from the doctor-set disease problem fragment database. Then, the preset number of disease problem fragments can be combined into disease problem response information.

[0047] Among them, the above-mentioned fourth retrieval step may include the following sub-steps: The first sub-step, through the above-mentioned disease problem response text, retrieve a target number of disease problem fragments in the above-mentioned doctor-set disease problem fragment database as the target disease problem fragment group.

[0048] The second sub-step, perform splicing processing on the above-mentioned target disease problem fragment group to obtain target disease problem information.

[0049] The third sub-step, input the above-mentioned target disease problem information into a pre-trained disease recognition model to generate disease problem response information corresponding to the above-mentioned target disease problem information. The disease recognition model can be a pre-trained disease intelligent question-answering model that takes the target disease problem information as input and the disease problem response information as output. For example, the disease recognition model can be a recurrent neural network (RNN), a gated recurrent unit (GRU), or a generative adversarial network (GAN). The disease problem response information can refer to the answer information for the target disease problem information.

[0050] Thus, through the pre-established dual-disease knowledge base, fragmentary retrieval is performed on the disease problem information; thereby, the accuracy of the response to the disease problem can be improved, which can help the nursing staff to further determine Furthermore, the disease recognition model can be obtained through the following steps of training: First, for each type of disease problem, the following processing steps are performed: 1. Obtain the disease problem data set corresponding to the above-mentioned disease problem type. The disease problem data may refer to various disease consultation questions raised by users for the above-mentioned disease problem type.

[0051] 2. Determine the initial disease recognition network corresponding to the above-mentioned disease problem type. For example, the type of the neural network model of the initial disease recognition network, as well as the model structure, various network layers, and loss function, etc., can be determined.

[0052] 3. Through the above-mentioned disease problem data set, model training is performed on the above-mentioned initial disease recognition network to obtain the second initial disease recognition network. For example, the initial disease recognition network may refer to a generative adversarial network (GAN) that has not been trained yet. The second initial disease recognition network may be a neural network model that has mastered more disease knowledge within the disease problem type after being trained on the disease problem data set. For example, the above-mentioned execution entity can use a model training method (e.g., backpropagation method) to perform model training on the initial disease recognition network to obtain the second initial disease recognition network.

[0053] 4. Through the pre-set disease problem enhanced sample set, the above-mentioned second initial disease recognition network is trained to obtain the third initial disease recognition network. Among them, the disease problem enhanced samples include: various problem supplementary features corresponding to the disease problems. Among them, the problem supplementary features may be the feature content corresponding to problem completion. The problem supplementary features may be features related to the retrieval of disease problem completion operations. For example, the problem supplementary features may be: disease problem time, disease problem prefix, the disease problem completion list corresponding to the disease problem prefix, and the disease problem completion association list corresponding to the disease problem prefix. The disease problem enhanced samples may be samples in the form of prompt information for enhancing the disease problem supplement ability of the model.

[0054] 5. In response to determining that the above-mentioned third initial disease recognition network reaches the training target, the third initial disease recognition network is determined as the disease recognition network that has completed training. Among them, the training target may be a pre-set expected target representing the automatic completion accuracy and completion efficiency of the third initial disease recognition network. For example, the training target may be that the automatic completion accuracy of the third initial disease recognition network is higher than 90%, and the accuracy of the problem response is higher than 95%.

[0055] Second, fuse the trained disease recognition networks into a disease recognition model. For example, the trained disease recognition networks can be combined into a trained disease recognition model.

[0056] Thus, through multiple trainings of the disease recognition model, the disease recognition model can learn more knowledge corpora within the disease problem types, and can also combine more problem completion features to predict more accurate answers to disease problems. Moreover, through multiple model tests and adaptive trainings, the disease recognition model can perform multiple sample learnings, and a disease recognition model with more accurate output disease responses can be obtained.

[0057] This application also provides a computer device 200. As Figure 2 shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203, and a communication interface 204. The processor 202, the memory 203, and the communication interface 204 communicate with each other through the bus 201. The computer device 200 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computer device 200.

[0058] The bus 201 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 2 only one line is shown in the figure, but it does not mean that there is only one bus or one type of bus. The bus 201 can include a path for transmitting information between various components of the computer device 200 (for example, the memory 203, the processor 202, the communication interface 204).

[0059] The processor 202 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0060] The memory 203 may include a volatile memory, such as a random access memory (RAM). The memory 203 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0061] The executable program code is stored in the memory 203, and the processor 202 executes the executable program code to implement the functions of the foregoing acquisition module, sampling module, determination module, and mixing module respectively, so as to implement the interactive information processing method applied to the patient data interconnection system. That is, the memory 203 stores instructions for executing the interactive information processing method applied to the patient data interconnection system described above.

[0062] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or communication networks.

[0063] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads the instructions stored on the memory through the data interface to execute the interactive information processing method applied to the patient data interconnection system described above.

[0064] An embodiment of the present application also provides a computer-readable storage medium. The above computer-readable storage medium may be any available medium that a computing device can store or a data storage device such as a data center that includes one or more available media. The above available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state drive), etc. The computer-readable storage medium includes instructions that direct the computing device to execute the interactive information processing method applied to the patient data interconnection system described above.

[0065] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0066] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. An interactive information processing method applied to a patient data interconnection system, characterized in that: The patient data interconnection system includes: a nursing end and a patient data storage system, including: The nursing end detects a viewing operation on a certain patient information in the patient information monitoring interactive page, and sends a patient information viewing request to the associated patient data storage system; The nursing end sorts the patient information according to the currently acquired patient information corresponding to the patient information viewing request and the historical patient information list to obtain the patient information list, wherein the historical patient information list and the patient information correspond to the same patient user; The nursing end determines, according to the information content in the patient information list, a display position of the information sliding icon in the patient information monitoring interactive page when the patient information is loaded; In response to detecting that the information sliding icon has moved to the set position of the patient information monitoring interaction page, the nursing end loads and renders the patient information content in the patient information list, and moves the information sliding icon to the display position, maintaining the position of the currently displayed information in the patient information monitoring interaction page.

2. The interactive information processing method applied to the patient data interconnection system according to claim 1, characterized in that: The step of determining, according to the information content in the patient information list, a display position of the information sliding icon in the patient information monitoring interactive page when the patient information is loaded, includes: According to the information content in the patient information list, determine the content height of the last patient information and the content height of the patient information; determining a content height difference between a content height of a previous patient information and a content height of the patient information; According to the content height difference, the display position of the information sliding icon in the patient information monitoring interaction page is determined when the patient information is loaded.

3. The interactive information processing method applied to the patient data interconnection system according to claim 2, characterized in that: The determining the content height of the last patient information and the content height of the patient information includes: Compare the total height of the element contents of the patient information list in the patient information list with the height of the visible area in the patient information monitoring interaction page to obtain a first comparison result; Determine the content height of the last patient information through the first comparison result; Comparing the total height of the content of the patient information in the patient information list with the height of the visible area in the patient information monitoring interaction page to obtain a second comparison result; The content height of the patient information is determined through the second comparison result.

4. The interactive information processing method applied to the patient data interconnection system according to claim 1, characterized in that: In response to detecting that the information sliding icon moves to a set position on the patient information monitoring interactive page, loading and rendering the patient information content in the patient information list, and moving the information sliding icon to the display position to maintain the position of the currently displayed information on the patient information monitoring interactive page, includes: In response to detecting, according to the viewing operation, that the information sliding icon moves to a first preset position of the patient information monitoring interactive page, rendering the patient information content in the patient information list; In response to detecting that the information sliding icon moves to the second preset position of the patient information monitoring interaction page, the information sliding icon is moved to the display position, and the position of the currently displayed information in the patient information monitoring interaction page is maintained, wherein the first preset position is less than or equal to the second preset position, the first preset position is a position set in pixels from one end of the visible area in the patient information monitoring interaction page, the second preset position is one end of the visible area, and one end of the visible area is the top or bottom.

5. The interactive information processing method applied to the patient data interconnection system according to claim 1, characterized in that: The method further comprises: The patient data storage system, in response to receiving the symptom problem information corresponding to the target patient user sent by the nursing end, performs feature extraction processing on the symptom problem information to obtain a symptom problem feature information set, wherein the target patient user is a patient user corresponding to a certain patient information in the patient information monitoring interaction page; The patient data storage system performs the following retrieval steps according to the disease problem characteristic information set: Retrieving a reference symptom problem segment sequence and a doctor-set symptom problem segment sequence corresponding to the symptom problem feature information set from a preset symptom problem knowledge base, wherein the symptom problem knowledge base includes: a standard reference symptom problem segment database and a doctor-set symptom problem segment database; Determine whether the symptom problem type corresponding to the symptom problem segment sequence set by the doctor is a common symptom problem type; In response to determining that the disease problem type is not a common disease problem type, determining whether the reference disease problem segment sequence has a corresponding disease problem answer text; In response to determining that the reference symptom question segment sequence has a corresponding symptom question answer text, symptom question answer information corresponding to the symptom question feature information set is generated based on the symptom question answer text.

6. A computer device, characterized in that: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images