A multi-dimensional single disease quality control method and system
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHAN DONG MSUN HEALTH TECH GRP CO LTD
- Filing Date
- 2026-03-27
- Publication Date
- 2026-06-12
Smart Images
Figure CN122201682A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of medical quality control technology, and in particular to a multi-dimensional single-disease quality control method and system. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] With the deep integration of medical informatics and artificial intelligence, single-disease quality control, as a core means to improve medical quality, is increasingly widely used in clinical diagnosis and treatment. Its core objective is to standardize diagnostic and treatment behaviors, reduce medical risks, and improve data quality through standardized rule verification.
[0004] Current methods for quality control of single diseases typically use a single model to control quality data across all dimensions. This can easily lead to omissions of key quality control nodes, resulting in low accuracy in quality control of single diseases. Summary of the Invention
[0005] To address the aforementioned problems, this invention proposes a multi-dimensional single-disease quality control method and system, which improves the accuracy and efficiency of single-disease quality control.
[0006] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a multi-dimensional single-disease quality control method is proposed, including: Acquire single-disease diagnosis and treatment data and quality control instructions; According to the quality control instructions, corresponding types of quality control information are extracted from the diagnosis and treatment data of single diseases; each type of quality control information includes multiple dimensions of quality control indicators. For each type of quality control information, the quality control indicators of each extracted dimension are verified according to the quality control rules to obtain the quality control conclusions for each dimension. The quality control conclusions of all dimensions corresponding to each type of quality control information are summarized to obtain the quality control results of single-disease diagnosis and treatment data.
[0007] Furthermore, single-disease diagnosis and treatment data includes medical order texts, test results, and medical records.
[0008] Furthermore, multiple parallel branches are used to extract various types of quality control information from single-disease diagnosis and treatment data in parallel.
[0009] Furthermore, the quality control indicators extracted from each of the multiple parallel branches are formatted in a unified manner.
[0010] Furthermore, each branch is equipped with an independent switch, and quality control instructions can be obtained by acquiring the status of the independent switch.
[0011] Furthermore, the quality control conclusions for all dimensions corresponding to each type of quality control information are summarized to generate a preliminary quality control report; The preliminary quality control report is standardized to obtain the quality control results of single-disease diagnosis and treatment data.
[0012] Secondly, a multi-dimensional single-disease quality control system is proposed, including: The data access module is used to acquire single-disease diagnosis and treatment data and quality control instructions; The quality control information extraction module is used to extract corresponding types of quality control information from single-disease diagnosis and treatment data according to quality control instructions; each type of quality control information includes multiple dimensions of quality control indicators. The rule verification and logic judgment module is used to verify the quality control indicators of each extracted dimension according to the quality control rules for each type of quality control information, and obtain the quality control conclusions of each dimension. The hybrid workflow scheduling module is used to summarize the quality control conclusions of all dimensions corresponding to each type of quality control information to obtain the quality control results of single disease diagnosis and treatment data.
[0013] Thirdly, a computer device is proposed, the device comprising: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the multi-dimensional single-disease quality control method proposed in the first aspect.
[0014] Fourthly, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program adapted to be loaded and executed by a processor, which is a multi-dimensional single-disease quality control method proposed in the first aspect.
[0015] Fifthly, a computer program product is proposed, which includes a computer program. When the computer program is executed by a processor, it implements a multi-dimensional single-disease quality control method proposed in the first aspect.
[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes a multi-dimensional single-disease quality control method and system. The method extracts corresponding quality control information from single-disease diagnosis and treatment data according to quality control instructions. Each type of quality control information includes multiple dimensions of quality control indicators. For each type of quality control information, the extracted quality control indicators of each dimension are verified according to quality control rules to obtain quality control conclusions for each dimension. The quality control conclusions of all dimensions corresponding to each type of quality control information are summarized to obtain the quality control results of single-disease diagnosis and treatment data. This ensures the comprehensiveness and accuracy of single-disease quality control and improves the efficiency of single-disease quality control.
[0017] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application.
[0019] Figure 1 This is a flowchart of a multi-dimensional single-disease quality control method proposed in an embodiment of the present invention; Figure 2 This is a flowchart of the large model-code collaboration process proposed in an embodiment of the present invention. Detailed Implementation
[0020] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0021] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0023] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.
[0024] It should be noted that all data acquisition is conducted in accordance with laws and regulations and with user consent, and the data is used legally.
[0025] First, the application scenarios of the multi-dimensional single-disease quality control method proposed in the embodiments of the present invention will be described.
[0026] This invention proposes a multi-dimensional single-disease quality control method, which is applied to the single-disease quality control application scenario.
[0027] With the deep integration of medical informatics and artificial intelligence, single-disease quality control, as a core means to improve medical quality, is increasingly widely used in clinical diagnosis and treatment. Its core objective is to standardize diagnostic and treatment behaviors, reduce medical risks, and improve data quality through standardized rule verification.
[0028] Existing single-disease quality control methods have the following shortcomings: (1) Inaccurate extraction of unstructured data: The existing pure code quality control system relies on fixed regular expressions and keyword matching, which cannot parse the ambiguous expressions in medical records. The information extraction accuracy is only about 50%, which can easily lead to missed judgments in quality control. (2) The risk of AI hallucination is prominent: a single large model quality control system is directly used for logical judgment and result output, which is prone to "hallucination quality control conclusions". The hallucination rate exceeds 60%, resulting in inaccurate quality control results and failing to meet the seriousness requirements of medical quality control; (3) Conflict between workflow efficiency and standardization: Traditional linear workflows verify multi-dimensional quality control indicators in sequence, with a single case processing time exceeding 200 seconds, resulting in low efficiency; pure parallel workflows are prone to missing key quality control nodes, leading to insufficient standardization. (4) High implementation cost: Existing systems require professional developers to maintain the rule base and workflow, and the adaptation cycle for different single diseases (such as community-acquired pneumonia and acute exacerbation of COPD) is long and costly.
[0029] Therefore, there is an urgent need for a single-disease quality control method that can balance the accuracy of information extraction, the reliability of results, the efficiency of workflow, and the ease of implementation, in order to solve the pain points of existing technologies.
[0030] To address the technical challenges of current single-disease quality control methods, this invention proposes a multi-dimensional single-disease quality control method. Through a collaborative architecture of "large model-defined purpose + code logic judgment," it improves the accuracy of unstructured data extraction while reducing the risk of AI illusions. A hybrid workflow of "linear main process + parallel branches" is employed, with visualization and external on / off control implemented on the Dify platform. This ensures both the standardization of single-disease quality control (the linear main process does not omit core nodes) and improves processing efficiency (parallel branches synchronously verify multi-dimensional indicators). In the parallel branches of the hybrid workflow, a structured prompt word architecture is designed to limit the output of the large model, while an adaptation unit is constructed between the large model output and the code logic to resolve verification failures caused by format incompatibility. In the result output stage of the hybrid workflow, unified structured specifications and label encoding are implemented to achieve seamless integration of quality control results with the hospital's quality control system, improving the executability of the results.
[0031] like Figures 1-2 As shown in the embodiment of the present invention, a multi-dimensional single-disease quality control method includes: Acquire single-disease diagnosis and treatment data and quality control instructions; According to the quality control instructions, corresponding types of quality control information are extracted from the diagnosis and treatment data of single diseases; each type of quality control information includes multiple dimensions of quality control indicators. For each type of quality control information, the quality control indicators of each extracted dimension are verified according to the quality control rules to obtain the quality control conclusions for each dimension. The quality control conclusions of all dimensions corresponding to each type of quality control information are summarized to obtain the quality control results of single-disease diagnosis and treatment data.
[0032] This invention proposes a multi-dimensional single-disease quality control method. Based on quality control instructions, corresponding types of quality control information are extracted from single-disease diagnosis and treatment data. Each type of quality control information includes multiple dimensions of quality control indicators. For each type of quality control information, the extracted quality control indicators of each dimension are verified according to quality control rules to obtain quality control conclusions for each dimension. The quality control conclusions of all dimensions corresponding to each type of quality control information are summarized to obtain the quality control results of the single-disease diagnosis and treatment data. This method ensures the comprehensiveness and accuracy of single-disease quality control and improves its efficiency.
[0033] In some embodiments, single-disease diagnosis and treatment data includes medical order texts, test results, and medical records.
[0034] Single-disease diagnosis and treatment data can be extracted from the hospital's HIS / EMR / LIS system. After the single-disease diagnosis and treatment data is extracted, it is first standardized to conform to the data format of subsequent data analysis. The standardized data format is automatically verified to ensure compliance through JSON Schema to avoid interruption of the single-disease quality control process due to data format disorder.
[0035] In some embodiments, multiple parallel branches are used to extract multiple types of quality control information from single-disease diagnosis and treatment data in parallel.
[0036] Among them, the quality control indicators extracted from each of the multiple parallel branches have a unified format.
[0037] In this embodiment of the invention, a separate large model is set up for each of the multiple parallel branches to extract multi-dimensional quality control indicators.
[0038] Large models can be either the medical vertical model MsunGPT-14B or Qwen3-30B-A3B, with independent model invocation instances allocated according to the parallel branch dimension.
[0039] The core of each branch is "structured prompt words + standardized output". That is, each branch has a dedicated prompt word template to limit the large model to extract quality control indicators of the corresponding dimension from the single disease diagnosis and treatment data, so as to avoid the output divergence. The output of the large model strictly follows the preset JSON format to ensure that the extraction results of different parallel branches are in a uniform format. The quality control information output by the large model is filtered and calibrated to filter low confidence fields and calibrate terms and units, thereby providing clean data for subsequent rule verification.
[0040] In this embodiment of the invention, a rule verification module is also set in each branch. The rule verification module sets up quality control rules in multiple dimensions. The quality control rules in multiple dimensions can perform corresponding rule verification on the quality control indicators of multiple dimensions extracted from the branch, thereby obtaining the quality control conclusions of each dimension of the branch.
[0041] To ensure that the quality control indicators extracted from each branch are compatible with the code logic, this embodiment of the invention first performs JSON cleaning and type validation on the quality control indicators extracted from each branch. JSON cleaning removes redundant formats from the quality control indicators and calibrates escape characters; type validation ensures that the quality control indicators are of a code-recognizable type such as a list / dictionary.
[0042] The quality control indicators for each dimension, after being cleaned and validated by JSON, are mapped to the rule validation module of the corresponding branch. The rule validation module calls the quality control rules for multiple dimensions stored in itself to perform rule validation on each quality control indicator input to the module, and finally outputs the quality control conclusion for the corresponding dimension.
[0043] The method proposed in this invention performs single-disease quality control in a fixed order of "acquiring single-disease diagnosis and treatment data - extracting quality control information - verifying quality control rules - outputting results", thereby ensuring that no core nodes of single-disease quality control are omitted.
[0044] The quality control of a single disease is divided into several parallel branches, and the extraction of quality control information and rule verification of each type are performed simultaneously. This greatly shortens the overall processing time of the quality control process for a single disease and ensures the accuracy of quality control for each type.
[0045] In this embodiment of the invention, each branch is also equipped with an independent switch. By controlling the independent switch, the branch can be individually invoked, enabled, or disabled. By obtaining the status of the independent switch, quality control instructions can be obtained.
[0046] The embodiments of the present invention can obtain one quality control instruction or obtain multiple quality control instructions simultaneously. When multiple quality control instructions are obtained, multiple types of quality control are performed on single disease diagnosis and treatment data in parallel to improve quality control efficiency.
[0047] In this embodiment of the invention, after obtaining the quality control conclusions for each dimension corresponding to each type of quality control information, the quality control conclusions for all dimensions corresponding to each type of quality control information are summarized, abnormal quality control conclusions are filtered out, and a preliminary quality control report is generated. The preliminary quality control report is standardized to obtain standardized quality control results for single-disease diagnosis and treatment data.
[0048] The standardization process for preliminary quality control reports includes: extracting conclusions and supporting evidence from quality control conclusions across various dimensions, generating structured data in the form of "Conclusions & Supporting Evidence", determining the code for the corresponding quality control result based on "Conclusions & Supporting Evidence", then constructing standardized quality control results for this type of single-disease diagnosis and treatment data from the conclusions, supporting evidence, and codes corresponding to the quality control conclusions across all dimensions of this type of quality control information, and outputting the quality control results in a standardized JSON format.
[0049] The codes include 1, 2, 3 and 4; 1 represents a complete evaluation, 2 represents an incomplete evaluation, 3 represents no valid information, and 4 represents partial missing / error.
[0050] The single-disease quality control method proposed in this invention will be described in detail using the following CAP quality control example.
[0051] Among them, CAP quality control includes 7 types, such as CURB-65 score and critical care assessment.
[0052] First, a "linear main process + 7 parallel branches" approach for CAP quality control was built based on the Dify platform: Linear main workflow: Acquisition of single-disease diagnosis and treatment data — Extraction of quality control information — Validation of quality control rules — Output of results; Parallel branch configuration: Branch 1: CURB-65 score; Branch 2: Severe Illness Assessment; ... Quality control process for CURB-65 scoring type: (1) Structured prompt word template (branch-specific) # Raw parameters (unstructured text) for workflow input input_params = { } Task: Extract the five dimensions of information required for the CURB-65 score from the following three diagnostic data parameters texts. Based solely on the text content, mark "not extracted" if not mentioned. In case of information conflicts, prioritize "test results > medical records > medical orders".
[0053] Parameter text: 1. Present Illness: {Medical Order Text} 2. Laboratory Results: {Test Result Text} 3. Physical examination: {Medical record text} The 5 dimensions to be extracted (output strictly according to this format, without any extra content): { "Disorders of consciousness": "Yes / No", # Fill in "Yes" when the text contains explicit descriptions such as "irritability, drowsiness, coma, disorientation", and fill in "No" when the patient is described as being conscious or not. "BUN": "Value in mmol / L / Not extracted", # Units are required, such as "8.2mmol / L". If no specific value is available, enter "Not extracted". "Respiratory Rate": "Number of breaths / minute / Not retrieved", # e.g., "28 breaths / minute", if no specific value is found, enter "Not retrieved"; "Blood pressure": "Systolic pressure / Diastolic pressure mmHg / Not retrieved", # e.g., "100 / 70 mmHg", if no specific value is available, enter "Not retrieved"; "Age": "Number in years / Not retrieved" # Specific numerical value is required (e.g., "70 years old"). For vague descriptions such as "elderly", fill in "Not retrieved".
[0054] } (2) The code logic adapts to the core code and performs rule-based evaluation on the quality control index data of five dimensions: "disorder of consciousness", "urea nitrogen", "respiratory rate", "blood pressure" and "age".
[0055] import json import re def clean_platform_input(raw_input): "Core objective: Clean the JSON output from large models and resolve format compatibility issues." cleaned_str = str(raw_input).replace("\\\\", "\\").replace("\\n", "").replace("'", '"') cleaned_str = re.sub(r'(?<=[{\s])(\w+)(?=\s*:)', r'"\1"', cleaned_str) cleaned_str = re.sub(r'\s+', ' ', cleaned_str).strip() try: return json.loads(cleaned_str) except json.JSONDecodeError: return {} def main(llm_extracted_data) ->dict: llm_data = clean_platform_input(llm_extracted_data) ALL_DIMENSIONS = ["Disorder of consciousness", "BUN", "Respiratory rate", "Blood pressure", "Age"] valid_score = 0 extracted_dimensions = [] missing_dimensions = [] error_dimensions = [] def process_dimension(dim_name, data_key, judge_func): """Processing a single dimension: validating validity, calculating scores, and categorizing records""" value = llm_data.get(data_key, "") is_valid, score, desc = judge_func(value) if is_valid: nonlocal valid_score valid_score += score extracted_dimensions.append(f"{dim_name}:{desc}") elif "Not retrieved" in desc: missing_dimensions.append(f"{dim_name}:{desc}") elif "Format error" in desc: error_dimensions.append(f"{dim_name}:{desc}"); # Dimension 1: Impaired Consciousness (Present = 1 point, Absent = 0 points) process_dimension("Disorder of consciousness", "Disorder of consciousness", lambda v: (True, 1, "Yes (Needs attention)") if v == "Yes" else (True, 0, "None (Normal)") if v == "None" else (False, 0, "No valid information was extracted")); # Dimension 2: Blood Urea Nitrogen (>7 mmol / L = 1 point, ≤7 = 0 points) process_dimension("urea nitrogen", "urea nitrogen", lambda v: (False, 0, "No valid information extracted") if not v or "mmol / L" not inv else (False, 0, f"Incorrect format (Input: {v})") if not v.replace("mmol / L", "").strip().replace(".", "", 1).isdigit() else (True, 1, f"{v}(Note)") if float(v.replace("mmol / L", ""))>7 else (True, 0, f"{v}(normal)")) # Dimension 3: Respiratory rate (≥30 breaths / min = 1 point, <30 = 0 points) process_dimension("breathing rate", "breathing rate") lambda v: (False, 0, "No valid information extracted") if not v or "times / minute" not in velse (False, 0, f"Incorrect format (Input: {v})") if not v.replace("times / minute", "").strip().isdigit() else (True, 1, f"{v}(Note)") if int(v.replace("times / minute", ""))>= 30 else (True, 0, f"{v}(normal)")) # Dimension 4: Blood Pressure (Systolic blood pressure <90 or diastolic blood pressure ≤60 = 1 point) process_dimension("blood pressure", "blood pressure", lambda v: (False, 0, "No valid information extracted") if (not v or " / " not in v or "mmHg" not in v) else (False, 0, f"Incorrect format (Input: {v})") if len(v.replace("mmHg", "").split(" / ")) != 2 or not all(x.strip().isdigit() for x in v.replace("mmHg", "").split(" / ")) else (lambda sys, dia: (True, 1, f"{v}(Needs attention)") if (sys<90 or dia<= 60)else (True, 0, f"{v}(Normal)")) (int(v.replace("mmHg", "").split(" / ")[0]), int(v.replace("mmHg", "").split(" / ")[1]))) # Dimension 5: Age (≥65 years old = 1 point, <65 years old = 0 points) process_dimension("age", "age", lambda v: (False, 0, "No valid information retrieved") if not v or "age" not in velse (False, 0, f"Incorrect format (input: {v})") if not v.replace("years", "").strip().isdigit() else (True, 1, f"{v} (Note: This needs attention)) if int(v.replace("age", ""))>= 65 else (True, 0, f"{v}(normal)")) # Status determination (1 = complete evaluation, 3 = no valid information, 4 = partial missing / error) actual_missing = len(missing_dimensions) + len(error_dimensions) label_1, curb65_content = "", "" if actual_missing == len(ALL_DIMENSIONS): label_1 = "3" curb65_content = "No CURB-65 related information was extracted". elif actual_missing>0: label_1 = "4" basis = f"Valid extraction:\n{chr(10).join(extracted_dimensions) ifextracted_dimensions else 'none'}\nUnextracted:\n{chr(10).join(missing_dimensions)if missing_dimensions else 'none'}\nIncorrect format:\n{chr(10).join(error_dimensions)if error_dimensions else 'none'}" curb65_content = f"Unable to fully evaluate &{basis}" else: label_1 = "1" curb65_content = f"CURB-65 score {valid_score} & details:\n{chr(10).join(extracted_dimensions)}" return { "result": json.dumps({"CURB-65": curb65_content, "label_1": label_1},ensure_ascii=False) } The quality control conclusions for each dimension are summarized and output as follows: { "CURB-65": "Unable to fully assess & effectively extract: Consciousness disturbance: None (normal) Blood urea nitrogen: 4.7 mmol / L (normal) Respiratory rate: 22 breaths / min (normal) Not extracted: Age: No valid information extracted Format error: Blood pressure: Format error (input: abc)", "label_1": "4"}.
[0056] Following the above procedure, desensitization data from 500 CAP patients were tested, and the following results were obtained: Linear main process standardization: 100% (no core nodes omitted); Overall processing time: 23 seconds per case on average (88% shorter than a purely linear workflow); The time for a single call to the CURB-65 scoring branch of CAP is 4 seconds per case. System integration and matching rate: 100%; AI illusion rate: 3.1%; CURB-65 rating dimension extraction accuracy: 98%; code logic parsing success rate: 100%.
[0057] This invention proposes a multi-dimensional single-disease quality control method, centered on a hybrid workflow of "linear main process + parallel branches," integrating innovative features such as structured prompts, code adaptation, and Dify visual management to achieve the following effects: (1) Balancing standardization and efficiency: The linear main process ensures that no core quality control nodes are missed (100% standardization), while the parallel branches make the average processing time for a single case ≤15 seconds, which is more than 80% shorter than that of a pure linear process; (2) High extraction accuracy: The structured prompt words limit the output of the large model, and the information extraction accuracy of each branch is ≥98%, while the AI illusion rate is ≤5%; (3) High flexibility: Dify visual setup + external switch control, the processing time of calling a branch alone is reduced by 73%, the overall computing power consumption is reduced by 80%, and it is suitable for quality control needs in multiple scenarios such as special projects, routine projects and emergency situations; (4) Good format compatibility: The code logic adaptation unit achieves 100% conversion of the large model output to the code format, with no parsing errors; (5) High efficiency in integration: Standardized output and label encoding facilitate integration with other systems, and the integration cycle can be shortened from 15 days to 3 days; (6) Low implementation cost: Dify visual configuration does not require professional development, and the workflow setup cycle for a single disease is ≤4 hours.
[0058] This invention also proposes a multi-dimensional single-disease quality control system, including: The data access module is used to acquire single-disease diagnosis and treatment data and quality control instructions; The quality control information extraction module is used to extract corresponding types of quality control information from single-disease diagnosis and treatment data according to quality control instructions; each type of quality control information includes multiple dimensions of quality control indicators. The rule verification and logic judgment module is used to verify the quality control indicators of each extracted dimension according to the quality control rules for each type of quality control information, and obtain the quality control conclusions of each dimension. The hybrid workflow scheduling module is used to summarize the quality control conclusions of all dimensions corresponding to each type of quality control information to obtain the quality control results of single disease diagnosis and treatment data.
[0059] It should be noted that the multi-dimensional single-disease quality control system provided in the above embodiments is only illustrated by the division of the above functional modules when performing single-disease quality control. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the multi-dimensional single-disease quality control system and the multi-dimensional single-disease quality control method embodiment provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0060] The present invention also discloses a computer device, the device comprising: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements a multi-dimensional single-disease quality control method disclosed in the embodiments of the present invention.
[0061] The computer device can be a portable mobile terminal, such as a smartphone, tablet, laptop, or desktop computer. Typically, a computer device includes a processor and memory.
[0062] A processor may include one or more processing cores, such as a core processor or a core processor. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor may also include a main processor and coprocessors. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0063] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory are used to store at least one computer program, which is executed by a processor to implement the intelligent vehicle control method provided in the method embodiments of this application.
[0064] In some embodiments, the computer device may also optionally include: a peripheral device interface and at least one peripheral device. The processor, memory, and peripheral device interface can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of: radio frequency circuitry, a display screen, a camera assembly, audio circuitry, and a power supply.
[0065] Peripheral device interfaces can be used to connect at least one I / O (Input / Output) related peripheral device to the processor and memory. In some embodiments, the processor, memory, and peripheral device interface are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor, memory, and peripheral device interface can be implemented on separate chips or circuit boards, which is not limited in this embodiment.
[0066] Radio frequency (RF) circuits are used to receive and transmit RF signals, also known as electromagnetic signals. RF circuits communicate with communication networks and other communication devices via electromagnetic signals. RF circuits convert electrical signals into electromagnetic signals for transmission, or convert received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit can communicate with other terminals through at least one wireless communication protocol. These wireless communication protocols include, but are not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.
[0067] The present invention also discloses a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed by a processor to disclose a multi-dimensional single-disease quality control method according to an embodiment of the present invention.
[0068] The present invention also discloses a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a multi-dimensional single-disease quality control method disclosed in the embodiments of the present invention.
[0069] The method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.
[0070] Those skilled in the art will recognize that the units and algorithm steps described in conjunction with the embodiments herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0071] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.
Claims
1. A multi-dimensional quality control method for a single disease, characterized in that, include: Acquire single-disease diagnosis and treatment data and quality control instructions; According to the quality control instructions, corresponding types of quality control information are extracted from the diagnosis and treatment data of single diseases; each type of quality control information includes multiple dimensions of quality control indicators. For each type of quality control information, the quality control indicators of each extracted dimension are verified according to the quality control rules to obtain the quality control conclusions for each dimension. The quality control conclusions of all dimensions corresponding to each type of quality control information are summarized to obtain the quality control results of single-disease diagnosis and treatment data.
2. The multi-dimensional single-disease quality control method as described in claim 1, characterized in that, Single-disease diagnosis and treatment data includes medical order texts, test results, and medical records.
3. The multi-dimensional single-disease quality control method as described in claim 1, characterized in that, Multiple parallel branches are used to extract various types of quality control information from single-disease diagnosis and treatment data in parallel.
4. The multi-dimensional single-disease quality control method as described in claim 3, characterized in that, The quality control indicators extracted from each of the multiple parallel branches have a unified format.
5. The multi-dimensional single-disease quality control method as described in claim 3, characterized in that, Each branch is equipped with an independent switch, and quality control instructions are obtained by acquiring the status of the independent switch.
6. The multi-dimensional single-disease quality control method as described in claim 1, characterized in that, Summarize the quality control conclusions of all dimensions corresponding to each type of quality control information to generate a preliminary quality control report; The preliminary quality control report is standardized to obtain the quality control results of single-disease diagnosis and treatment data.
7. A multi-dimensional single-disease quality control system, characterized in that, include: The data access module is used to acquire single-disease diagnosis and treatment data and quality control instructions; The quality control information extraction module is used to extract corresponding types of quality control information from single-disease diagnosis and treatment data according to quality control instructions; each type of quality control information includes multiple dimensions of quality control indicators. The rule verification and logic judgment module is used to verify the quality control indicators of each extracted dimension according to the quality control rules for each type of quality control information, and obtain the quality control conclusions of each dimension. The hybrid workflow scheduling module is used to summarize the quality control conclusions of all dimensions corresponding to each type of quality control information to obtain the quality control results of single disease diagnosis and treatment data.
8. An electronic device, characterized in that, The device includes: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements a multi-dimensional single-disease quality control method according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed by a processor to provide a multi-dimensional single-disease quality control method according to any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements a multi-dimensional single-disease quality control method as described in any one of claims 1-6.