An adverse reaction detection method, device, equipment and storage medium

Abstract

The application discloses an adverse reaction detection method, device and equipment and a storage medium. The method comprises the following steps: obtaining candidate detection data corresponding to a target quality control item, wherein the candidate detection data comprises image data, voice communication data and text communication data; performing optical character recognition processing on the candidate detection data to determine target detection data corresponding to the target quality control item; performing adverse reaction detection on the target detection data based on an adverse reaction matching strategy to determine target adverse reaction description data corresponding to the target quality control item and a target processing strategy corresponding to the target adverse reaction description data; and generating an adverse reaction detection report based on the target adverse reaction description data and the target processing strategy. The application can realize efficient detection of adverse reactions, reduce high labor costs, and avoid the problems of high adverse reaction detection missing and false reporting rates caused by negligence or non-uniform judgment standards.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for detecting adverse reactions. Background Technology

[0002] In the field of medical quality and safety monitoring, how to achieve accurate and efficient adverse reaction detection is a core technical challenge to ensure patient medication safety and improve the quality of medical services, which directly affects the reliability of clinical medication decisions and the ability to prevent medical disputes.

[0003] Currently, traditional adverse reaction detection methods generally rely on manual reading and interpretation of patient data from multiple sources. However, these methods are inefficient, costly, and prone to errors due to negligence or inconsistent judgment criteria, leading to high rates of missed and false positives and compromising the stability of test results. Summary of the Invention

[0004] This invention provides an adverse reaction detection method, apparatus, equipment, and storage medium to achieve efficient detection of adverse reactions. It can greatly improve the detection efficiency of adverse reactions, reduce high labor costs, and avoid the problems of high missed and false alarm rates in adverse reaction detection caused by negligence or inconsistent judgment standards, thereby ensuring the stability of detection results.

[0005] According to one aspect of the present invention, an adverse reaction detection method is provided, the method comprising: Obtain candidate test data corresponding to the target quality control item, wherein the candidate test data includes image data, voice communication data and text communication data; The candidate detection data are subjected to optical character recognition processing to determine the target detection data corresponding to the target quality control item; Based on the adverse reaction matching strategy, adverse reaction detection is performed on the target detection data to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. Based on the target adverse reaction description data and the target treatment strategy, an adverse reaction detection report is generated.

[0006] According to another aspect of the present invention, an adverse reaction detection device is provided, the device comprising: The candidate data acquisition module is used to acquire candidate test data corresponding to the target quality control project, wherein the candidate test data includes image data, voice communication data and text communication data; The target data acquisition module is used to perform optical character recognition processing on the candidate detection data to determine the target detection data corresponding to the target quality control item. The adverse reaction detection module is used to perform adverse reaction detection on the target detection data based on the adverse reaction matching strategy, and to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. The detection report generation module is used to generate an adverse reaction detection report based on the target adverse reaction description data and the target treatment strategy.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the adverse reaction detection method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the adverse reaction detection method according to any embodiment of the present invention.

[0009] The technical solution of this invention acquires candidate detection data corresponding to the target quality control item. This candidate detection data includes image data, voice communication data, and text communication data, ensuring comprehensive data acquisition, covering multi-dimensional data sources, and avoiding missed detections caused by a single data source. Optical character recognition (OCR) processing is performed on the candidate detection data to determine the target detection data corresponding to the target quality control item. This transforms unstructured data into structured data, providing data support for subsequent steps. Adverse reaction detection is performed on the target detection data based on an adverse reaction matching strategy to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data, reducing the false negative / false positive rate. Based on the target adverse reaction description data and the target processing strategy, an adverse reaction detection report is generated, facilitating rapid understanding of key information by the medical team. This invention achieves closed-loop management of the entire process from data acquisition to decision support through multimodal data integration, optical character recognition processing, adverse reaction matching strategies, and automated report generation. It can greatly improve the detection efficiency of adverse reactions, reduce high labor costs, and avoid the problems of high missed and false alarm rates in adverse reaction detection caused by negligence or inconsistent judgment standards, thereby ensuring the stability of detection results.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of an adverse reaction detection method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of an adverse reaction detection method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of an adverse reaction detection device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the adverse reaction detection method of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Example 1 Figure 1 This is a flowchart illustrating an adverse reaction detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving the detection of adverse reactions. The method can be executed by an adverse reaction detection device, which can be implemented in hardware and / or software. This adverse reaction detection device can be configured in an electronic device. For example... Figure 1 As shown, the method includes: S110. Obtain the candidate test data corresponding to the target quality control item, including image data, voice communication data and text communication data.

[0016] In this context, the target quality control project can refer to a specific monitoring project within the medical quality monitoring system that targets a particular medical behavior or outcome, such as "post-marketing adverse reaction monitoring of a certain anti-tumor drug." Its core objective is to assess the safety, effectiveness, and standardization of medical practices through systematic data collection and analysis, ultimately achieving quality improvement. The candidate detection data can refer to a multimodal dataset used for adverse reaction detection, including imaging data, voice communication data, and text communication data. Imaging data can refer to digitized human tissue information obtained through imaging technologies such as CT / MRI / PET, or uploaded image information, such as paper reports, examination forms, and prescriptions uploaded by patients. Voice communication data can refer to data such as recorded phone calls between doctors and patients, and voice recordings from remote consultations. Text communication data can refer to unstructured text data such as electronic medical records, online chat logs, and prescription texts.

[0017] Specifically, multimodal data, including image data, voice communication data, and text communication data, can be automatically and synchronously collected through medical information systems, electronic medical records, voice acquisition devices, and patient communication platforms (such as online consultation platforms). This allows for the rapid acquisition and coverage of multidimensional data sources, avoiding missed detections caused by a single data source.

[0018] For example, S110 may include: in response to a configuration operation on a target quality control item, determining the project configuration information corresponding to the target quality control item; and based on the project configuration information, obtaining the candidate test data corresponding to the target quality control item.

[0019] Among them, project configuration information can refer to the specific parameters and rule system set for the target testing task in the medical quality control project, covering core elements such as testing scope, time range, data source identification, screening conditions, and specific orders.

[0020] Specifically, it can respond to the configuration operations of quality control personnel on target quality control items through a configurable interface. It should be noted that the configurable interface can provide functions for creating / searching / viewing configuration information. The configuration information includes project name, pharmaceutical company name, drug name, quality control number, etc., and the configuration result is determined as the project configuration information corresponding to the target quality control project. It can realize dynamic adjustment of the testing range and improve the flexibility of adverse reaction detection. Based on the project configuration information, it can integrate data sources such as medical information systems, electronic medical records, voice, and patient self-service platforms through API gateways or database views to automatically obtain the candidate testing data corresponding to the target quality control project, reducing labor costs.

[0021] For example, based on project configuration information, obtaining candidate test data corresponding to the target quality control project includes: obtaining raw test data corresponding to the target quality control project based on project configuration information; performing preprocessing operations on the raw test data to obtain candidate test data corresponding to the target quality control project, wherein the preprocessing operation is at least one of data cleaning and data alignment.

[0022] Raw test data can refer to unprocessed initial medical data that comes directly from source systems such as imaging equipment, voice recordings, and electronic medical records, retaining the original format and content.

[0023] Specifically, based on the data source identifier (such as medical information system, electronic medical record database, voice gateway) in the project configuration information, data acquisition instructions can be dynamically generated through API interface or database query to obtain the original test data corresponding to the target quality control project; by performing at least one of the operations of data cleaning and data alignment on the original test data, the candidate test data corresponding to the target quality control project can be obtained, which can improve data quality and ensure the accuracy of subsequent analysis.

[0024] S120. Perform optical character recognition processing on the data to be tested to determine the target test data corresponding to the target quality control item.

[0025] Among them, target detection data can refer to structured data processed by OCR technology, specifically key information fields extracted from data such as images, voice, and text.

[0026] Specifically, by calling a high-performance OCR engine to perform optical character recognition multilingual processing on the selected detection data, the text extracted by OCR can be parsed into structured data according to fields (such as patient information, examination items, symptom descriptions), generating target detection data corresponding to the target quality control items, thereby improving data processing efficiency, reducing labor costs, and providing reliable data support for subsequent processing.

[0027] For example, S120 may include: performing optical character recognition processing on the selected detection data to generate plain text detection data; and performing data verification on the plain text detection data based on a preset rule engine to obtain target detection data corresponding to the target quality control item.

[0028] Plain text detection data can refer to machine-readable text data generated after structured transformation of multimodal data (image / speech / text) using OCR (Optical Character Recognition) technology. A preset rule engine can refer to pre-defined rules used to convert non-technical text into technical terminology.

[0029] Specifically, OCR technology can be used to process the selected detection data using optical character recognition. It can also be combined with technologies such as ASR and NLU. For example, for scanned copies of CT examination reports, the OCR engine will locate the text area (such as "examination findings" and "diagnosis"), recognize and extract the symptom descriptions (such as "lung shadow" and "elevated liver enzymes"). For voice data such as telephone recordings, it is first converted into preliminary text through ASR (automatic speech recognition), and then the OCR post-processing module corrects problems such as accent misrecognition and semantic ambiguity, finally generating plain text detection data. According to the preset rule engine, the plain text detection data is validated to obtain the target detection data corresponding to the target quality control items, thereby ensuring the accuracy, consistency and completeness of the target detection data.

[0030] S130. Based on the adverse reaction matching strategy, perform adverse reaction detection on the target detection data, and determine the target adverse reaction description data corresponding to the target quality control item and the target treatment strategy corresponding to the target adverse reaction description data.

[0031] Here, the adverse reaction matching strategy can refer to a rule system pre-built based on a medical knowledge base and machine learning model for adverse reaction matching. The target adverse reaction description data can refer to specific adverse reaction instances identified by the matching strategy. The target treatment strategy can refer to a clinical decision support plan developed based on the adverse reaction description.

[0032] Specifically, adverse reaction matching strategies can be pre-defined by a team of medical experts. These strategies may include keyword matching (such as "rash" or "nausea"), logical rules (such as "drug A + symptom B"), and time constraints (such as symptoms appearing within 24 hours of medication). Using a rule engine or a custom matching algorithm, combined with the adverse reaction matching strategy, adverse reaction detection is performed on the target detection data. The system automatically outputs the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. This can greatly improve the ability to identify adverse reactions and reduce labor costs.

[0033] S140. Generate an adverse reaction detection report based on the target adverse reaction description data and the target treatment strategy.

[0034] Among them, the adverse reaction detection report can refer to the formal documented output of the adverse reaction detection results.

[0035] Specifically, a preset report template can be used to automatically fill in fields such as patient information, symptom description, and treatment suggestions based on the target adverse reaction description data and target treatment strategy, thereby generating an adverse reaction detection report. This can provide a clear treatment path and reduce clinical decision-making time.

[0036] In this embodiment, candidate detection data corresponding to the target quality control items are acquired. This candidate detection data includes image data, voice communication data, and text communication data, ensuring comprehensive data acquisition, covering multi-dimensional data sources, and avoiding missed detections due to a single data source. Optical character recognition (OCR) processing is performed on the candidate detection data to determine the target detection data corresponding to the target quality control items. This transforms unstructured data into structured data, providing data support for subsequent steps. Adverse reaction detection is performed on the target detection data based on an adverse reaction matching strategy, determining the target adverse reaction description data corresponding to the target quality control items and the target processing strategy corresponding to the target adverse reaction description data, which can reduce the false negative / false positive rate. Based on the target adverse reaction description data and the target processing strategy, an adverse reaction detection report is generated, facilitating the medical team's rapid understanding of key information. This invention, through multimodal data integration, OCR processing, adverse reaction matching strategies, and automated report generation, achieves closed-loop management of the entire process from data acquisition to decision support. This can greatly improve the efficiency of adverse reaction detection, reduce high labor costs, and avoid the problems of high false negative and false positive rates in adverse reaction detection caused by negligence or inconsistent judgment standards, thereby ensuring the stability of detection results.

[0037] Example 2 Figure 2 This is a flowchart of an adverse reaction detection method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the step of "performing adverse reaction detection on target detection data based on an adverse reaction matching strategy, determining the target adverse reaction description data corresponding to the target quality control item, and the target processing strategy corresponding to the target adverse reaction description data." Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0038] See Figure 2 Another adverse reaction detection method provided in this embodiment specifically includes the following steps: S210. Obtain the candidate test data corresponding to the target quality control item, including image data, voice communication data and text communication data.

[0039] S220. Perform optical character recognition processing on the data to be tested to determine the target test data corresponding to the target quality control item.

[0040] S230. Based on the adverse reaction matching strategy, the target detection data is screened at multiple levels to determine the target adverse reaction description data corresponding to the target quality control item.

[0041] Specifically, target detection data can be screened at multiple levels based on adverse reaction matching strategies. For example, if keywords such as "rash," "nausea," and "dyspnea" appear in the detection data, the system immediately marks them as "potential adverse reaction signals" and continues to verify the time-causal relationship. If a patient experiences "dyspnea" within 3 hours of taking the medication, and there is a strong correlation between "drug A" and "acute allergic reaction" in the rule base, it is determined to be a "high-reliability adverse reaction." By determining the target adverse reaction description data corresponding to the target quality control item, the reliability of the target adverse reaction description data can be guaranteed.

[0042] For example, S230 may include: performing keyword matching on the target detection data to determine the potential adverse reaction description data corresponding to the target quality control item; performing contextual semantic analysis on the target detection data, and combining the potential adverse reaction description data to determine the adverse reaction symptom data and adverse reaction causal association data corresponding to the target quality control item; and determining the potential adverse reaction description data, adverse reaction symptom data, and adverse reaction causal association data as the target adverse reaction description data corresponding to the target quality control item.

[0043] Specifically, potential adverse reaction description data can refer to text fragments that may be adverse drug reactions, initially screened from target detection data through keyword matching. Adverse reaction symptom data can refer to specific symptom manifestations and quantitative indicators extracted from potential adverse reaction descriptions through contextual semantic analysis. Adverse reaction causal association data can refer to evidence of the causal relationship between symptoms and the drug.

[0044] Specifically, based on the adverse reaction matching strategy, a retrieval tool can be used to scan the target detection data for keywords and extract text to obtain potential adverse reaction description data corresponding to the target quality control items. Contextual semantic analysis of the target detection data, combined with the potential adverse reaction description data, verifies the causal relationship between symptoms and drugs, and determines the adverse reaction symptom data and adverse reaction causal relationship data corresponding to the target quality control items. The potential adverse reaction description data matched by keywords, the adverse reaction symptom data from contextual semantic analysis, and the adverse reaction causal relationship data are integrated into structured target adverse reaction description data, achieving accurate conversion from target detection data to target adverse reaction description data, and improving the efficiency and accuracy of adverse reaction detection.

[0045] S240. Based on the target adverse reaction description data, perform processing strategy matching to determine the target processing strategy corresponding to the adverse reaction description data.

[0046] Specifically, treatment strategies can be matched based on the target adverse reaction description data. This means the optimal treatment strategy is automatically matched to the adverse reaction description data, resulting in the target treatment strategy corresponding to the adverse reaction description data. Through precise matching of treatment strategies and adverse reaction descriptions, actionable tiered treatment recommendations are provided to clinicians, reducing decision-making time.

[0047] For example, S240 may include: determining the severity of the adverse reaction corresponding to the target quality control item based on the target adverse reaction description data; and matching the treatment strategy based on the severity of the adverse reaction to determine the target treatment strategy corresponding to the adverse reaction description data.

[0048] The severity of adverse reactions can refer to pre-set adverse reaction evaluation criteria.

[0049] Specifically, the symptom types (such as rash, elevated liver enzymes) and numerical indicators (such as white blood cell count 12.3 × 10⁻⁶) corresponding to the adverse reaction can be extracted from the target adverse reaction description data. 9 The severity of adverse reactions corresponding to target quality control items is determined by analyzing factors such as the duration of adverse reaction ( / L), time characteristics (e.g., symptoms appearing 3 hours after medication), and patient baseline information (e.g., age, underlying diseases). Treatment strategies are then matched based on the severity of adverse reactions to determine the target treatment strategy corresponding to the adverse reaction description data. This precise matching of treatment strategies with severity provides clinicians with actionable tiered treatment recommendations, reducing decision-making time and improving the efficiency of medical resource utilization.

[0050] S250. Generate an adverse reaction detection report based on the target adverse reaction description data and the target treatment strategy.

[0051] The technical solution of this embodiment uses a multi-level screening of target detection data based on an adverse reaction matching strategy to determine the target adverse reaction description data corresponding to the target quality control items, thereby achieving precise quantification of the severity of adverse reactions. Matching processing strategies based on the target adverse reaction description data helps improve the efficiency of medical resource utilization. This invention, through severity grading and processing strategy matching, achieves closed-loop management of the entire process from target adverse reaction description data to clinical decision support, improving the efficiency and accuracy of adverse reaction handling, strengthening the scientific rigor and compliance of clinical decision-making, and ultimately providing medical institutions with an intelligent and scalable adverse reaction detection and handling solution.

[0052] Example 3 Figure 3This is a schematic diagram of an adverse reaction detection device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a candidate data acquisition module 310, a target data acquisition module 320, an adverse reaction detection module 330, and a test report generation module 340; The candidate data acquisition module 310 is used to acquire candidate test data corresponding to the target quality control project, wherein the candidate test data includes image data, voice communication data and text communication data. The target data acquisition module 320 is used to perform optical character recognition processing on the candidate detection data to determine the target detection data corresponding to the target quality control item. The adverse reaction detection module 330 is used to perform adverse reaction detection on the target detection data based on the adverse reaction matching strategy, and to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. The test report generation module 340 is used to generate an adverse reaction test report based on the target adverse reaction description data and the target treatment strategy.

[0053] In this embodiment, candidate detection data corresponding to the target quality control item is acquired. This candidate detection data includes image data, voice communication data, and text communication data, ensuring comprehensive data acquisition, covering multi-dimensional data sources, and avoiding missed detections due to a single data source. Optical character recognition (OCR) processing is performed on the candidate detection data to determine the target detection data corresponding to the target quality control item. This transforms unstructured data into structured data, providing data support for subsequent steps. Adverse reaction detection is performed on the target detection data based on an adverse reaction matching strategy to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data, reducing the false negative / false positive rate. Based on the target adverse reaction description data and the target processing strategy, an adverse reaction detection report is generated, facilitating the medical team's rapid understanding of key information. This invention achieves closed-loop management of the entire process from data acquisition to decision support through multimodal data integration, optical character recognition processing, adverse reaction matching strategies, and automated report generation. It can greatly improve the detection efficiency of adverse reactions, reduce high labor costs, and avoid the problems of high missed and false alarm rates in adverse reaction detection caused by negligence or inconsistent judgment standards, thereby ensuring the stability of detection results.

[0054] Optionally, the candidate data acquisition module 310 includes: An information configuration unit is used to determine the project configuration information corresponding to the target quality control project in response to a configuration operation on the target quality control project. The data acquisition unit is used to acquire the candidate test data corresponding to the target quality control project based on the project configuration information.

[0055] Optionally, the data acquisition unit is specifically used for: acquiring the original test data corresponding to the target quality control project based on the project configuration information; performing preprocessing operations on the original test data to acquire the candidate test data corresponding to the target quality control project, wherein the preprocessing operation is at least one of data cleaning and data alignment.

[0056] Optionally, the target data acquisition module 320 is specifically used for: performing optical character recognition processing on the candidate detection data to generate plain text detection data; and performing data verification on the plain text detection data based on a preset rule engine to obtain the target detection data corresponding to the target quality control item.

[0057] Optionally, the adverse reaction detection module 330 includes: A multi-level screening unit is used to perform multi-level screening of the target detection data based on an adverse reaction matching strategy to determine the target adverse reaction description data corresponding to the target quality control item. The strategy matching unit is used to perform processing strategy matching based on the target adverse reaction description data to determine the target processing strategy corresponding to the adverse reaction description data.

[0058] Optionally, the multi-level screening unit is specifically used for: performing keyword matching on the target detection data to determine the potential adverse reaction description data corresponding to the target quality control item; performing contextual semantic analysis on the target detection data, and combining the potential adverse reaction description data to determine the adverse reaction symptom data and adverse reaction causal association data corresponding to the target quality control item; and determining the potential adverse reaction description data, the adverse reaction symptom data, and the adverse reaction causal association data as the target adverse reaction description data corresponding to the target quality control item.

[0059] Optionally, the strategy matching unit is specifically used to: determine the severity of the adverse reaction corresponding to the target quality control item based on the target adverse reaction description data; and perform processing strategy matching based on the severity of the adverse reaction to determine the target processing strategy corresponding to the adverse reaction description data.

[0060] The above-described device can perform the adverse reaction detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for performing the adverse reaction detection method.

[0061] Example 4 Figure 4This is a schematic diagram of an electronic device implementing the adverse reaction detection method of an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0062] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0063] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0064] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as adverse reaction detection methods.

[0065] In some embodiments, the adverse reaction detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the adverse reaction detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the adverse reaction detection method by any other suitable means (e.g., by means of firmware).

[0066] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0067] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0068] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0069] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0070] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0071] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0072] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0073] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0074] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting adverse reactions, characterized in that, include: Obtain candidate test data corresponding to the target quality control item, wherein the candidate test data includes image data, voice communication data and text communication data; The candidate detection data are subjected to optical character recognition processing to determine the target detection data corresponding to the target quality control item; Based on the adverse reaction matching strategy, adverse reaction detection is performed on the target detection data to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. Based on the target adverse reaction description data and the target treatment strategy, an adverse reaction detection report is generated.

2. The method according to claim 1, characterized in that, The acquisition of candidate test data corresponding to the target quality control item includes: In response to the configuration operation of the target quality control item, determine the project configuration information corresponding to the target quality control item; Based on the project configuration information, obtain the candidate testing data corresponding to the target quality control project.

3. The method according to claim 2, characterized in that, The step of obtaining the candidate testing data corresponding to the target quality control project based on the project configuration information includes: Based on the project configuration information, obtain the original test data corresponding to the target quality control project; The raw test data is preprocessed to obtain candidate test data corresponding to the target quality control item, wherein the preprocessing operation is at least one of data cleaning and data alignment.

4. The method according to claim 1, characterized in that, The step of performing optical character recognition processing on the candidate detection data to determine the target detection data corresponding to the target quality control item includes: The candidate detection data is processed by optical character recognition to generate plain text detection data; The plain text detection data is validated based on a preset rule engine to obtain the target detection data corresponding to the target quality control item.

5. The method according to claim 1, characterized in that, The step of performing adverse reaction detection on the target detection data based on the adverse reaction matching strategy, and determining the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data, includes: Based on the adverse reaction matching strategy, the target detection data is screened at multiple levels to determine the target adverse reaction description data corresponding to the target quality control item; Based on the target adverse reaction description data, a processing strategy is matched to determine the target processing strategy corresponding to the adverse reaction description data.

6. The method according to claim 5, characterized in that, The multi-level screening of the target detection data based on the adverse reaction matching strategy to determine the target adverse reaction description data corresponding to the target quality control item includes: Keyword matching is performed on the target detection data to determine the potential adverse reaction description data corresponding to the target quality control item; Contextual semantic analysis is performed on the target detection data, and combined with the potential adverse reaction description data, the adverse reaction symptom data and adverse reaction causal association data corresponding to the target quality control item are determined; The potential adverse reaction description data, the adverse reaction symptom data, and the adverse reaction causal association data are identified as the target adverse reaction description data corresponding to the target quality control item.

7. The method according to claim 5, characterized in that, The step of matching processing strategies based on the target adverse reaction description data to determine the target processing strategy corresponding to the adverse reaction description data includes: Based on the target adverse reaction description data, the severity of the adverse reaction corresponding to the target quality control item is determined; Based on the severity of the adverse reaction, a treatment strategy is matched to determine the target treatment strategy corresponding to the adverse reaction description data.

8. An adverse reaction detection device, characterized in that, include: The candidate data acquisition module is used to acquire candidate test data corresponding to the target quality control project, wherein the candidate test data includes image data, voice communication data and text communication data; The target data acquisition module is used to perform optical character recognition processing on the candidate detection data to determine the target detection data corresponding to the target quality control item. The adverse reaction detection module is used to perform adverse reaction detection on the target detection data based on the adverse reaction matching strategy, and to determine the target adverse reaction description data corresponding to the target quality control item and the target processing strategy corresponding to the target adverse reaction description data. The detection report generation module is used to generate an adverse reaction detection report based on the target adverse reaction description data and the target treatment strategy.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the adverse reaction detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the adverse reaction detection method according to any one of claims 1-7.

Images