Intelligent detection method and system of target drug

Abstract

The invention provides an intelligent detection method and system for a target drug. The method comprises the following steps: acquiring a current to-be-detected task; determining an operation process based on the current to-be-detected task; the operation process is displayed step by step through the step-by-step guide interface, and a user is prompted to execute corresponding operation; in response to the operation information of the user, executing the current to-be-detected task to detect the sample of the target drug, and pushing waiting prompt information to the user in the sample detection process; after the detection is completed, displaying a current detection result, storing the current detection result, and adding a whole process record of the current detection in a detection record; in response to the record viewing instruction of the user, the detailed information of the target detection record is searched and displayed from the detection record, so that standardization of target drug detection operation, transparency of the detection process and full-life-cycle management of the detection record are realized; the accuracy of the detection result, the efficiency of the detection work and the auditing performance of the detection process are improved.

Description

Technical Field

[0001] This invention relates to the field of pharmaceutical testing technology, and in particular to an intelligent detection method and system for a target drug. Background Technology

[0002] Drug testing is a crucial link in maintaining social security and public health, and is widely used in various fields. However, current testing methods have significant shortcomings and are no longer adequate for the high demands of modern testing in terms of efficiency and accuracy.

[0003] At the operational level, existing testing process guidelines are vague. Testing involves multiple steps, including sample processing and equipment debugging, but some equipment operation instructions are either too technical or overly simplified, lacking scenario-based guidance. This makes it easy for users to make testing errors due to confusion, omissions, or incorrect order of steps, resulting in sample waste and result deviations.

[0004] The testing process lacks a feedback mechanism. Target drug testing requires a certain reaction time, and complex samples take even longer. However, existing equipment only displays a vague status such as "testing in progress," without providing progress or estimated completion time. There are also no clear warnings when environmental abnormalities occur or user assistance is needed, which can easily lead to users accidentally interrupting the testing, causing testing failures or extended cycles.

[0005] Regarding record-keeping and traceability, the system is incomplete. The traditional model only stores the final test results, lacking core process information such as sample number, operation time, equipment parameters, and any abnormal situations. This "result-only" approach makes it impossible to reconstruct the entire process for subsequent review, auditing, and traceability, making it difficult to verify the reliability of the results and affecting the authority of the testing work.

[0006] In summary, the shortcomings of existing methods in terms of operational guidance, process feedback, and record traceability severely restrict the accuracy, efficiency, and standardization of testing. Summary of the Invention

[0007] This invention provides an intelligent detection method and system for target drugs, which improves the clarity and adaptability of operation instructions, enhances the real-time feedback capability of the detection process, and improves the completeness of detection records, thereby improving the accuracy, efficiency and standardization of detection work.

[0008] On one hand, the present invention provides an intelligent detection method for a target drug, comprising: With the detection equipment and monitoring terminal already connected, obtain the current task to be detected; Based on the current task to be detected, the operation process is determined; The operation process is displayed step by step through a guided interface, prompting the user to perform the corresponding operations. In response to the user's operation information, the system executes the current testing task to test the sample of the target drug, and pushes a waiting prompt message to the user during the sample testing process; Once the test is completed, display the test results, store the test results, and add a complete record of the test process to the test log. Responding to the user's record viewing command, it retrieves and displays detailed information about the target detection record from the detection records.

[0009] On the other hand, the present invention also provides an intelligent detection system for a target drug, comprising: The acquisition module is used to acquire the current task to be detected when the detection device and the monitoring terminal are connected. The determination module is used to determine the operation process based on the current task to be detected; The first display module is used to display the operation process step by step through a step-by-step guided interface and prompt the user to perform the corresponding operations; The execution module is used to respond to the user's operation information, execute the current test task to test the sample of the target drug, and push waiting prompt information to the user during the sample testing process; The second display module is used to display the detection results after the detection is completed, store the detection results, and add the full process record of the detection to the detection record. The search module is used to respond to the user's record viewing command, search for and display detailed information of the target detection record from the detection records.

[0010] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent detection method for the target drug as described in any of the above.

[0011] The intelligent detection method and system for target drugs provided by this invention accurately acquires the task to be tested based on the connection between the detection equipment and the monitoring terminal. It determines the appropriate operation process based on the characteristics of the task and provides visual and scenario-based operation guidance through a step-by-step guided interface, effectively standardizing user operation behavior and avoiding operational errors caused by unclear processes. By pushing waiting prompts in real time during the detection process, it fills the gaps in feedback during the detection process, reducing the risk of user error interrupting the detection. After the detection is completed, it synchronously stores the final results and the entire process record, and supports quick querying of detailed information of the target record based on user commands, constructing a complete detection traceability system. In this way, it achieves standardization of target drug detection operations, transparency of the detection process, and full lifecycle management of detection records, improving the accuracy of detection results, the efficiency of detection work, and the auditability of the detection process, providing reliable technical support for the standardized implementation of target drug detection work. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0013] Figure 1 This is a flowchart illustrating the intelligent detection method for the target drug provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the intelligent detection system for the target drug provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0015] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0016] Figure 1 This is a flowchart illustrating the intelligent detection method for the target drug provided in an embodiment of the present invention.

[0017] like Figure 1 As shown, the intelligent detection method for the target drug provided in this embodiment of the invention mainly includes the following steps: 101. With the testing equipment and monitoring terminal already connected, obtain the current task to be tested; 102. Based on the current task to be detected, determine the operation process; 103. The operation process is displayed step by step through a step-by-step guided interface, and the user is prompted to perform the corresponding operations; 104. In response to the user's operation information, execute the current testing task to test the sample of the target drug, and push a waiting prompt message to the user during the sample testing process; 105. After the test is completed, display the test results and store them, and add a full process record of the test to the test record. 106. Respond to the user's record viewing command, find and display the detailed information of the target detection record from the detection record.

[0018] In a specific implementation process, the connection status between the detection device and the monitoring terminal establishes a communication link between them. This link can be wired or wireless, such as via Bluetooth, Wi-Fi, or USB. Its primary purpose is to ensure the reliability of the detection device and prevent operational interruptions due to connection failures. Obtaining the current task to be detected can be done by manually entering the task number or by automatically identifying the task information through scanning a QR code or barcode. The aim is to clarify the detection target and initiate subsequent processes.

[0019] Furthermore, the process of determining the operation procedure based on the current task to be tested can be to generate an appropriate operation sequence according to the specific parameters of the task. This can be achieved by matching the task type with a preset rule base to generate the procedure, or by manually configuring the task steps. The main purpose is to enable the operation guide to accurately match the testing needs of different target drugs.

[0020] Specifically, the step-by-step guided interface can present the operation process in a combination of text and images, or guide users to complete the operation step by step through voice prompts. The purpose is to provide scenario-based operation guidance and reduce the possibility of confusion or omission of steps.

[0021] In addition, the process of pushing waiting prompts to users can display the detection progress through a progress bar or indicate the estimated completion time through a countdown. The purpose is to eliminate the uncertainty of users while waiting and avoid misoperation caused by missing information.

[0022] After the test is completed, the process of storing the entire process record can be done by using a structured data table to save the test process information, or by recording the operation details through a log file. The purpose is to build a complete data chain to provide a basis for subsequent review and traceability.

[0023] The intelligent detection method for target drugs in this embodiment accurately acquires the task to be tested based on the connection between the detection equipment and the monitoring terminal. It determines an appropriate operation process based on the task characteristics and provides visual and scenario-based operation guidance through a step-by-step guided interface, effectively standardizing user operation behavior and avoiding operational errors caused by unclear processes. By pushing waiting prompts in real time during the detection process, it fills the gaps in feedback during the detection process, reducing the risk of user error interrupting the detection. After the detection is completed, it synchronously stores the final results and the entire process record, and supports quick querying of detailed information of the target record based on user commands, constructing a complete detection traceability system. In this way, it achieves standardization of target drug detection operations, transparency of the detection process, and full lifecycle management of detection records, improving the accuracy of detection results, the efficiency of detection work, and the auditability of the detection process, providing reliable technical support for the standardized implementation of target drug detection work.

[0024] In some embodiments, the implementation process of determining the operation flow based on the current task to be detected is as follows: The current task to be detected is parsed using a natural language processing model to obtain task parameters; the task parameters are mapped and matched with a preset task knowledge base to obtain matching results; the matching results include sample preprocessing requirements, instrument calibration steps, and data comparison rules; the sample preprocessing requirements, instrument calibration steps, and data comparison rules are combined to generate a task feature vector; based on the task feature vector and the preset operation flow knowledge base, a trained decision tree model is used to match the sequence of detection steps to form the operation flow.

[0025] Specifically, natural language processing models can be implemented using deep learning-based language models (such as BERT or GPT) to accurately capture task requirements and avoid subjective errors from human interpretation. The task knowledge base can be understood as a database storing rules and parameters related to various target drug detection methods. It can be constructed using relational or graph databases to provide basic data support for dynamic matching. In practical applications, the task feature vector is a quantitative representation composed of multi-dimensional information such as sample preprocessing requirements, instrument calibration steps, and data comparison rules. It can be generated using vector space models or embedding techniques to compress task characteristics and facilitate efficient handling of complex dependencies. Furthermore, the decision tree model is a rule-based learning algorithm that can be implemented using CART or ID3 algorithms. Its purpose is to dynamically generate the optimal sequence of steps based on the inherent patterns of the task feature vector.

[0026] Specifically, this method first uses a natural language processing model to parse the detection task, transforming the unstructured task description into structured task parameters to ensure accurate capture of task requirements. Next, these task parameters are mapped and matched with rules and parameters in a task knowledge base, automatically associating sample preprocessing requirements, instrument calibration steps, and data comparison rules, rather than relying on fixed process templates, thus achieving precise alignment between task requirements and specific detection requirements. Subsequently, the matching results are combined to generate a task feature vector for quantified compression of multi-dimensional information. Finally, based on the task feature vector and the operation process knowledge base, a trained decision tree model is used to match the detection step sequence, combining historical data and rule constraints to dynamically generate an operation process that conforms to the detection logic and adapts to the characteristics of real-time tasks.

[0027] In some embodiments, based on task feature vectors and a pre-defined operation process knowledge base, using a trained decision tree model to match detection step sequences to form an operation process may include: Input the task feature vector into the trained decision tree model to obtain the identifier of the detection step sequence; Based on the identifier of the detection step sequence, retrieve the corresponding detection step sequence template from the operation process knowledge base; Based on the task parameters, the detection step sequence template is optimized and adjusted to generate an operation flow; The optimization adjustments include rearranging the order of steps, skipping steps, or inserting exception handling steps, and the adjustments are based on real-time sensor data and historical execution success rates.

[0028] Specifically, the task feature vector refers to a vector expression that integrates key information such as sample preprocessing requirements, instrument calibration steps, and data comparison rules. It can be extracted and constructed using various machine learning algorithms to ensure that the decision tree model can accurately match the preset step sequence. The detection step sequence template can be understood as a standardized process framework stored in the operation process knowledge base. It is retrieved through a unique identifier and aims to provide a basic blueprint for subsequent optimization. Optimization and adjustment refers to the process of dynamically modifying the detection step sequence template. This can involve rearranging the step order to adapt to the urgency of different tasks, skipping steps to eliminate redundant operations, or inserting anomaly handling steps to address potential risks, all aimed at improving the flexibility and robustness of the process.

[0029] In detail, firstly, the task feature vector is input into the trained decision tree model, which outputs identifiers for the detection step sequence based on the key information of the task feature vector. Next, the corresponding detection step sequence template is retrieved from the operation procedure knowledge base based on the identifier. Subsequently, the template is optimized and adjusted in conjunction with task parameters to generate the final operation procedure. During the optimization and adjustment process, real-time sensor data is used to reflect the current device status and environmental changes, while historical execution success rates provide empirical statistical basis, thereby enabling dynamic rearrangement of step order, skipping of inefficient steps, and insertion of abnormal handling steps. This improves the adaptability of the operation procedure and enhances the stability and efficiency of the detection process.

[0030] In some embodiments, the present invention further proposes a method for optimizing and adjusting the generation process of the detection step sequence template according to task parameters, including the following: Based on task parameters, real-time sensor data, and historical detection records, the execution urgency and risk coefficient of each step in the detection step sequence template are calculated. Based on the urgency of execution, risk coefficient, and preset process constraint rules, the detection step sequence template is optimized and adjusted to generate an operation process; the optimization and adjustment include at least one of rearranging the execution order of steps, replacing specific steps, and inserting anomaly handling steps.

[0031] Specifically, execution urgency refers to the degree to which a certain detection step needs to be completed in the current task scenario. It can be determined by analyzing information such as time constraints and sample characteristics in the task parameters. In practical applications, a weighted scoring model or a machine learning prediction model can be used to ensure that high-priority steps are executed in a timely manner.

[0032] The risk coefficient measures the probability that a particular detection step may result in an error or failure. It can be assessed by integrating information such as device status, environmental parameters, and failure rates from real-time sensor data and historical detection records. In practical applications, probabilistic statistical methods or risk assessment models trained on historical data can be used to identify and address potentially high-risk steps in advance.

[0033] In practical applications, process constraint rules refer to the restrictions that ensure that the adjustment of the testing steps conforms to the logical order and safety specifications. They can be implemented using expert system rule bases or formal verification methods, with the aim of ensuring that the adjusted operation process is both efficient and safe and reliable.

[0034] Specifically, this solution effectively addresses the lack of objective basis for operational process adjustments by introducing a quantitative calculation mechanism for execution urgency and risk coefficients, combined with dynamic optimization using process constraint rules. This improves the adaptability and reliability of the detection process. Task parameters define the specific requirements of the detection task, real-time sensor data captures environmental changes and equipment operating status, and historical detection records provide past execution success rates and duration data. These inputs collectively ensure that urgency and risk coefficients comprehensively reflect the urgency and potential risks of each step. Based on this, quantitative indicators drive process refactoring, process constraint rules ensure adjustments conform to logical order and safety standards, and urgency and risk coefficients serve as dynamic priority criteria, guiding step rearrangement, replacement, or insertion of exception handling. For example, high-urgency steps are prioritized through sequential rearrangement to reduce waiting time, and high-risk steps are reduced in probability of operational errors through replacement or insertion mechanisms, thereby generating an operational process more suited to real-time conditions. Finally, optimization adjustments include at least one of the following: sequential rearrangement of step execution, replacement of specific steps, and insertion of exception handling steps. Sequential rearrangement adapts to changes in urgency to improve efficiency, step replacement addresses high-risk aspects to enhance accuracy, and insertion of exception handling strengthens the process's fault tolerance.

[0035] The intelligent detection method for target drugs in this embodiment achieves scientific optimization and adjustment of the detection step sequence template. The generated operation process can not only adapt to changes in real-time task requirements, equipment status and historical execution data, but also effectively avoid operation delays and increased error rates caused by unreasonable step order or failure to handle high-risk links in a timely manner, thereby improving the efficiency and reliability of target drug detection.

[0036] In some embodiments, the present invention further proposes the following technical solution: Based on task parameters, real-time sensor data, and historical detection records, the execution urgency and risk coefficient of each step in the detection step sequence template are calculated, including: for each current step in the detection step sequence template, the following operations are performed: extracting static attributes of the current step from task parameters and a preset operation process knowledge base; the static attributes include step type, estimated time consumption, criticality level, and stability parameters of required materials; extracting equipment status parameters and environmental parameters related to the current step from real-time sensor data; querying historical execution success rates and average execution times corresponding to the current step and similar task parameters from historical detection records; and calculating the execution urgency and risk coefficient of the current step based on the static attributes, equipment status parameters, environmental parameters, historical execution success rates, and average execution times using a pre-trained urgency calculation model and risk coefficient calculation model.

[0037] Specifically, static attributes refer to a set of information that reflects the inherent characteristics of a detection step. These attributes can be implemented using multi-dimensional indicators such as step type, estimated time, criticality level, and stability parameters of required materials. Step type distinguishes different types of operations, such as sample processing or instrument calibration; estimated time quantifies the time range required to complete the step; criticality level measures the degree of impact of the step on the overall detection result; and the stability parameters of required materials assess the potential interference from external factors on the step's execution. The purpose of introducing these static attributes is to provide fundamental data support for subsequent calculations, ensuring that optimization adjustments have a reliable basis.

[0038] In practical applications, equipment status parameters refer to a set of data reflecting the current operating status of the testing equipment, which can be achieved using indicators such as instrument calibration accuracy and sensor sensitivity. Environmental parameters refer to external conditions affecting the testing process, such as changes in temperature and humidity or fluctuations in light intensity. The purpose of introducing this dynamic data is to capture changes in the testing scenario in real time, thereby improving the adaptability and accuracy of the calculation results. In addition, historical execution success rate and average execution time provide empirical references; the former reflects the reliability of the steps, while the latter is used to assess time pressure. Together, they enhance the scientific nature of optimization and adjustment.

[0039] In practical applications, firstly, for each current step in the detection step sequence template, static attributes are extracted from the task parameters and operation process knowledge base. These attributes define the inherent characteristics of the step, laying the foundation for subsequent calculations. Secondly, device status parameters and environmental parameters are extracted from real-time sensor data. This dynamic data reflects changes in the current operating environment in real time, enabling the calculation process to adapt to fluctuations in the actual detection scenario. Next, historical execution success rates and average execution times corresponding to the current step and similar task parameters are queried from historical detection records, ensuring a high degree of correlation between historical data and the current task. Finally, based on all extracted data, execution urgency and risk coefficient are output respectively through pre-trained urgency calculation models and risk coefficient calculation models, thereby supporting the dynamic optimization of the detection process.

[0040] In some embodiments, the present invention further proposes a method for optimizing and adjusting the generation process of the detection step sequence template, including the following: Based on the urgency and risk coefficient, calculate the comprehensive priority score for each step in the detection step sequence template; Construct a step dependency graph based on process constraint rules; Based on the combined priority score and step dependency graph, the topological sorting algorithm is used to generate the initial optimized sequence. A risk assessment is performed on the initial optimization sequence to obtain a comprehensive risk coefficient. When the comprehensive risk coefficient exceeds the first preset threshold, specific steps are replaced and / or anomaly handling steps are inserted for steps with risk coefficients exceeding the second preset threshold, thereby generating an operation flow.

[0041] Specifically, the comprehensive priority score refers to a value derived by quantifying and integrating execution urgency and risk coefficients, which can be implemented using methods such as weighted summation and normalization. A step dependency graph is a graphical structure that expresses the logical dependencies between steps, which can be implemented using data structures such as adjacency lists and adjacency matrices. Topological sorting is a sorting method for directed acyclic graphs, aiming to ensure that the order of steps conforms to logical dependencies while prioritizing high-urgency, low-risk steps.

[0042] In detail, the scheme first calculates the comprehensive priority score for each step based on execution urgency and risk coefficient. Next, it constructs a step dependency graph according to process constraint rules, parsing the implicit step order and logical relationships within the preset rules, and explicitly expressing the mandatory dependencies between steps to prevent invalid sequences. Then, based on the comprehensive priority score and step dependency graph, it uses a topological sorting algorithm to generate an initial optimized sequence. While satisfying the dependencies, the comprehensive priority score serves as the sorting driver, improving execution efficiency. Finally, it performs a risk assessment on the initial optimized sequence and dynamically adjusts it. By quantifying the overall process's comprehensive risk coefficient, it selectively replaces high-risk steps or inserts exception handling mechanisms when the risk exceeds a threshold, ensuring the final operation maintains low-risk characteristics in a dynamic environment.

[0043] The above solution, through optimization and adjustment of the detection step sequence template, solves the problem of process failure caused by ignoring step correlation and risk accumulation, and significantly enhances the stability and adaptability of the detection process.

[0044] In some embodiments, the present invention further proposes to display the operation process step by step through a step-by-step guided interface, including: obtaining the user's skill level and historical operation data; determining the level of detail of the guidance for each step of the operation process based on the user's skill level and historical operation data; and displaying the operation process on the step-by-step guided interface according to the level of detail of the guidance for each step and the order of the guidance for each step.

[0045] Specifically, user skill level refers to the system's quantitative assessment of a user's operational capabilities, which can be achieved through user self-assessment during registration, past performance on testing tasks, or simulation test results. Historical operation data can be understood as a record of a user's behavior in previous testing tasks, including information such as average operation time, error rate, and number of corrections, aiming to provide data support for personalized guidance. Guidance detail refers to the richness of the guidance content, which can be implemented in practice through concise, standard, and detailed modes, with the aim of adapting to the operational needs of different users.

[0046] In detail, this solution dynamically generates the level of detail for each step of the guidance based on the aforementioned data, such as assigning different guidance modes according to the user's skill level and historical error rate. This mechanism ensures that key steps provide sufficient warnings to low-skilled users, while simplifying redundant information for high-skilled users. On the step-by-step guidance interface, the personalized guidance content is presented strictly in the order of the operation logic, thereby ensuring that users receive consistent and appropriate visual and operational feedback during execution. This process not only enhances the accuracy of step execution but also optimizes the smoothness of interaction, fundamentally reducing the risk of detection errors caused by improper guidance.

[0047] The intelligent detection method for target drugs in this embodiment combines user-individualized data with task feature vectors, enabling the system to more accurately match the sequence of detection steps and generate an operation process adapted to the user's capabilities, thereby significantly improving detection efficiency and accuracy.

[0048] This invention further proposes a method for determining the level of detail in the guidance for each step of the operation process based on the user's skill level and historical operation data, including: Based on user skill level, average operation time, error rate, and number of corrections, a predefined detail mapping table is used to assign a level of guidance detail to each step; the guidance detail levels include concise mode, standard mode, and detailed mode. In the concise mode, the guidance information only includes key operation points and minimized text prompts; in the standard mode, the guidance information includes standard operation instructions with both text and images; and in the detailed mode, the guidance information additionally includes video demonstrations and warnings about common errors.

[0049] Specifically, user skill level refers to the ability level comprehensively assessed based on a user's past testing experience, training records, and certification qualifications. This can be achieved using a tiered scoring system or a tag-based classification method. Average operation time refers to the average time required for a user to complete a specific testing step, which can be statistically analyzed using a real-time timing module or historical data analysis tools. Error rate refers to the frequency of errors made by the user during the execution of testing steps, which can be calculated using error capture algorithms or log analysis programs. Correction count refers to the number of times the user corrects an error after it is discovered, which can be obtained through behavior tracking systems or interaction record analysis. These indicators collectively construct a real-time quantitative evaluation system for user operational capabilities, aiming to accurately match the user's actual operational needs.

[0050] In practical applications, a detail mapping table is a standardized decision-making tool that transforms multi-dimensional dynamic data such as user skill level, average operation time, error rate, and number of corrections into specific guidance detail levels. It can be implemented using rule engines or machine learning models. Guidance detail levels are divided into concise mode, standard mode, and detailed mode. This hierarchical design covers the full spectrum of user capabilities, aiming to ensure that the guidance intensity at each step closely matches the user's actual needs.

[0051] In detail, this solution integrates dynamic data from multiple dimensions, including user skill level, historical operation time, error rate, and number of corrections, and combines this with a predefined detail mapping table to achieve precise allocation of guidance detail. Specifically, user skill level provides a basic capability benchmark, average operation time reflects operational proficiency, and error rate and number of corrections directly reflect operational accuracy and the learning curve. These dynamic data work together to avoid the problem of generalized guidance information. By assigning a guidance detail level to each step through a predefined detail mapping table, the inconsistency in allocation caused by subjective judgment during process execution is resolved, making the guidance strategy repeatable and objective. The concise mode provides only key operation points and minimal text prompts for highly skilled users, reducing interference through information simplification and improving the operational fluency of skilled users; the standard mode provides standard operation instructions combining text and graphics, offering clear guidance to intermediate-skilled users by combining visual and textual information, effectively reducing the risk of step confusion; the detailed mode additionally includes video demonstrations and common error warnings, using dynamic videos to enhance understanding of complex steps for users with low skill levels or high historical error rates, and preventing typical operational errors through error warnings.

[0052] In some embodiments, the present invention further proposes real-time monitoring of user operation behavior, including operation time interval, operation sequence conformity, and operation force. When the operation time interval exceeds a preset duration, it is determined as an operation delay. When the operation sequence is inconsistent with the step guidance sequence or the operation force exceeds the allowable range, it is determined as an operation error. When an operation delay or error is detected, an exception handling mechanism is triggered. The exception handling mechanism includes at least one of the following: displaying a warning prompt on the interface and highlighting the correct operation area; retrieving matching supplementary guidance content from the knowledge base based on the error type and the user's skill level; if the number of consecutive errors by the user reaches a threshold, automatically re-displaying the video demonstration of the current step and pausing the process until the user completes the correct operation.

[0053] Specifically, the operation time interval can be implemented using a timer module to reflect the user's response efficiency. Operation sequence conformity can be understood as the degree of matching between the user's actual operation steps and the system's preset step guidance sequence; this can be achieved through a sequence comparison algorithm to verify the accuracy of the step execution logic. Operation force refers to the magnitude of the force applied by the user during physical operation; this can be implemented using a pressure sensor or force feedback device to monitor the precision of the physical operation.

[0054] In detail, the system continuously collects data streams on operation time intervals, operation sequence compliance, and operation force, and analyzes them in real time. When data in any dimension exceeds a preset threshold, the system immediately triggers the corresponding anomaly detection logic. For example, when the operation time interval is too long, the system dynamically adjusts the sensitivity of the delay detection to ensure that it neither interferes with the user too frequently nor interrupts the process too quickly. For cases of incorrect operation sequence or inappropriate force, the system accurately identifies the problem by comparing it with the preset step guidance sequence and the device's safety range. Based on this, the anomaly handling mechanism selects an appropriate intervention method according to the severity of the problem and the user's historical performance. For example, for minor errors, the system may only correct them through interface prompts; while for continuous errors, the intervention intensity will be escalated, forcing the user to master the correct operation through video demonstrations, thereby ensuring the continuity of the detection process and the reliability of the results.

[0055] Based on the same general inventive concept, this invention also protects an intelligent detection system for a target drug. The intelligent detection system for a target drug provided by this invention will be described below. The intelligent detection system for a target drug described below and the intelligent detection method for a target drug described above can be referred to in correspondence.

[0056] Figure 2 This is a schematic diagram of the intelligent detection system for the target drug provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the intelligent detection system for the target drug in this embodiment includes an acquisition module 21, a determination module 22, a first display module 23, an execution module 24, a second display module 25, and a search module 26.

[0057] The acquisition module 21 is used to acquire the current task to be detected when the detection device and the monitoring terminal are connected. The determination module 22 is used to determine the operation process based on the current task to be detected; The first display module 23 is used to display the operation process step by step through a step-by-step guided interface and prompt the user to perform the corresponding operations. The execution module 24 is used to respond to the user's operation information, execute the current test task to test the sample of the target drug, and push waiting prompt information to the user during the sample testing process; The second display module 25 is used to display the current detection result after the detection is completed, store the current detection result, and add the full process record of the current detection to the detection record; The search module 26 is used to respond to the user's record viewing command, search for and display the detailed information of the target detection record from the detection record.

[0058] Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions stored in the memory 330 to execute an intelligent detection method for the target drug.

[0059] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0060] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the intelligent detection method for the target drug provided by the above methods.

[0061] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an intelligent detection method for the target drug provided by the methods described above.

[0062] It should be noted that all relevant information that may be involved in the various embodiments of the present invention is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is information that users actively provide or generate during the use of the product / service, as well as information obtained with user authorization.

[0063] The information processed by this invention may vary depending on the specific product / service scenario and should be based on the specific scenario in which the user uses the product / service. This may involve user account information, device information, or other related information. This invention will handle the relevant information and its processing with the utmost diligence.

[0064] This invention places great importance on the security of related information and has adopted reasonable and feasible security protection measures that comply with industry standards to protect related information and prevent unauthorized access, public disclosure, use, modification, damage or loss of related information.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent detection of a target drug, characterized in that, include: With the detection equipment and monitoring terminal already connected, obtain the current task to be detected; Based on the current task to be detected, the operation process is determined; The operation process is displayed step by step through a guided interface, prompting the user to perform the corresponding operations. In response to the user's operation information, the system executes the current testing task to test the sample of the target drug, and pushes a waiting prompt message to the user during the sample testing process; Once the test is completed, display the test results, store the test results, and add a complete record of the test process to the test log. Responding to the user's record viewing command, it retrieves and displays detailed information about the target detection record from the detection records.

2. The intelligent detection method for the target drug according to claim 1, characterized in that, Based on the current task to be detected, the operation process is determined, including: The task parameters are obtained by parsing the current task to be detected using a natural language processing model; The task parameters are mapped and matched with a preset task knowledge base to obtain matching results; the matching results include sample preprocessing requirements, instrument calibration steps and data comparison rules. The task feature vector is generated by combining sample preprocessing requirements, instrument calibration steps, and data comparison rules. Based on the task feature vector and the pre-set operation process knowledge base, the trained decision tree model is used to match the detection step sequence to form the operation process.

3. The intelligent detection method for the target drug according to claim 2, characterized in that, Based on task feature vectors and a pre-defined operation process knowledge base, a trained decision tree model is used to match and detect the sequence of steps to form an operation process, including: Input the task feature vector into the trained decision tree model to obtain the identifier of the detection step sequence; Based on the identifier of the detection step sequence, retrieve the corresponding detection step sequence template from the operation process knowledge base; Based on the task parameters, the detection step sequence template is optimized and adjusted to generate an operation flow; The optimization adjustments include rearranging the order of steps, skipping steps, or inserting exception handling steps, and the adjustments are based on real-time sensor data and historical execution success rates.

4. The intelligent detection method for the target drug according to claim 3, characterized in that, Based on the task parameters, the detection step sequence template is optimized and adjusted to generate an operation flow, including: Based on task parameters, real-time sensor data, and historical detection records, the execution urgency and risk coefficient of each step in the detection step sequence template are calculated. Based on the urgency of execution, risk coefficient, and preset process constraint rules, the detection step sequence template is optimized and adjusted to generate the operation process; wherein, the optimization and adjustment includes at least one of rearranging the execution order of steps, replacing specific steps, and inserting anomaly handling steps.

5. The intelligent detection method for the target drug according to claim 4, characterized in that, Based on task parameters, real-time sensor data, and historical detection records, the execution urgency and risk coefficient of each step in the detection step sequence template are calculated, including: For each current step in the detection step sequence template, perform the following operations: The static attributes of the current step are extracted from the task parameters and the preset operation process knowledge base; the static attributes include step type, estimated time, criticality level, and stability parameters of required materials. Extract the device status parameters and environmental parameters related to the current step from the real-time sensor data; From the historical detection records, query the historical execution success rate and average execution time corresponding to the parameters of the current step and similar tasks; Based on the static attributes, device status parameters, environmental parameters, historical execution success rate, and average execution time, the execution urgency and risk coefficient of the current step are calculated using a pre-trained urgency calculation model and risk coefficient calculation model, respectively.

6. The intelligent detection method for the target drug according to claim 4, characterized in that, Based on the urgency, risk factor, and preset process constraint rules, the detection step sequence template is optimized and adjusted to generate the operation process, including: Based on the execution urgency and risk coefficient, calculate the comprehensive priority score for each step in the detection step sequence template; Construct a step dependency graph based on the process constraint rules; Based on the comprehensive priority score and step dependency graph, an initial optimized sequence is generated using a topological sorting algorithm; A risk assessment is performed on the initial optimized sequence to obtain a comprehensive risk coefficient. When the comprehensive risk coefficient exceeds a first preset threshold, specific steps are replaced and / or anomaly handling steps are inserted for steps with risk coefficients exceeding a second preset threshold, thereby generating an operation flow.

7. The intelligent detection method for the target drug according to claim 2, characterized in that, The operation process is displayed step-by-step through a guided interface, including: Obtain user skill level and historical operation data; Based on the user's skill level and historical operation data, the level of detail in the guidance for each step of the operation process is determined. The step-by-step guided interface displays the operation process according to the level of detail and order of each step.

8. The intelligent detection method for the target drug according to claim 7, characterized in that, Based on the user's skill level and historical operation data, the level of detail in the guidance for each step of the operation process is determined, including: Based on the user's skill level, average operation time, error rate, and number of corrections, a guide detail level is assigned to each step through a predefined detail mapping table; the guide detail levels include concise mode, standard mode, and detailed mode; In the concise mode, the guidance information only includes key operation points and minimized text prompts; in the standard mode, the guidance information includes standard operation instructions with both text and images; and in the detailed mode, the guidance information additionally includes video demonstrations and warnings about common errors.

9. The intelligent detection method for the target drug according to claim 7, characterized in that, Also includes: Real-time monitoring of user actions, including operation time intervals, operation sequence compliance, and operation force; When the operation time interval exceeds the preset duration, it is judged as an operation delay; when the operation sequence is inconsistent with the step guidance sequence or the operation force exceeds the allowable range, it is judged as an operation error. When an operation delay or error is detected, an exception handling mechanism is triggered; wherein, the exception handling mechanism includes at least one of the following: popping up a warning prompt on the interface and highlighting the correct operation area; retrieving matching supplementary guidance content from the knowledge base based on the error type and the user's skill level; If a user makes a consecutive error to the threshold, the video demonstration of the current step will be automatically re-shown and the process will be paused until the user completes the operation correctly.

10. An intelligent detection system for a target drug, characterized in that, include: The acquisition module is used to acquire the current task to be detected when the detection device and the monitoring terminal are connected. The determination module is used to determine the operation process based on the current task to be detected; The first display module is used to display the operation process step by step through a step-by-step guided interface and prompt the user to perform the corresponding operations; The execution module is used to respond to the user's operation information, execute the current test task to test the sample of the target drug, and push waiting prompt information to the user during the sample testing process; The second display module is used to display the detection results after the detection is completed, store the detection results, and add the full process record of the detection to the detection record. The search module is used to respond to the user's record viewing command, search for and display detailed information of the target detection record from the detection records.

Images