IVD detection process control method and system based on Json

Abstract

The invention belongs to the field of IVD detection, and discloses a Json-based IVD detection process control method and a Json-based IVD detection process control system, which directly read the parameter configuration and control process of an operator from a Json file, and easily adjust the input data, the processing process and the output result of an algorithm before field deployment according to different requirements and scenes without code modification and recompilation. Due to the flexibility and the configurability, the algorithm is easier to maintain, deploy and adapt to different scenes, and debugging by field personnel is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of IVD detection, and in particular to a Json-based IVD detection process control method and system. Background Art

[0002] In vitro diagnosis, or IVD (In Vitro Diagnosis), refers to a diagnostic method that obtains clinical diagnostic information by testing samples such as human body fluids, cells and tissues in vitro, and then determines the disease or body function. It plays an important role in disease prevention, diagnosis, and treatment. Currently, more than 80% of clinical disease diagnosis can be completed by IVD. It includes sample pre-treatment, multi-row rapid sample injection, multi-turn turntable sample barcode high-speed reading, etc., which are applied to automated test lines, test tube sorting, blood bag management, coagulation, immunity, urine, biochemistry, luminescence platforms, etc.

[0003] The IVD vision industry plays an important role in the field of medical diagnosis, especially when it comes to the processing and classification of blood types. The traditional manual blood bag blood typing method is labor-intensive, time-consuming, and prone to human errors. Existing machine vision-based solutions require code modification and compilation when deployed in different scenarios, which results in long preparatory work and is not conducive to maintenance and on-site debugging. Summary of the invention

[0004] The object of the present invention is to provide a Json-based IVD detection process control method and system.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The IVD detection process control system based on Json is characterized in that the process control Json is workflow, including a skeleton and a configuration file, and the workflow configuration file includes the following parameters: workflow name, inputs and outputs names, the number of processes executing the workflow, workflow content, etc.

[0007] The workflow defines the entire computing topology. An algorithm SDK is built by reading the workflow configuration file. The file content is a Json string that defines a complete Workflow topology.

[0008] The workflow content includes multiple Nodes or sub-workflows, and data dependencies are established between the multiple Nodes or sub-workflows through input and output fields.

[0009] Inputs defines all input names, namely input images and operator operating parameters.

[0010] outputs defines all output names, namely output images and operator operation results.

[0011] A Node is a computing unit that includes the following parameters: the thread ID that runs the Node object, the method type, the Node name, the input slots, and the output slots.

[0012] The process control system performs the following steps:

[0013] S1: Load the process control Json file;

[0014] S2: Load parameter configuration json file;

[0015] S3: Execute operator calls according to the process and pass corresponding input images and parameters;

[0016] S4: Save the operator output results and display them;

[0017] Compared with the prior art, the present invention has the beneficial effect of directly reading the operator's parameter configuration and control flow from the Json file, and easily adjusting the algorithm's input data, processing flow and output results before field deployment according to different needs and scenarios without modifying or recompiling the code. Such flexibility and configurability can make the algorithm easier to maintain, deploy and adapt to different scenarios, and facilitate debugging by field personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 An IVD detection flow chart of an embodiment of the present invention; DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1

[0021] like Figure 1As shown, the IVD detection process control system based on Json is characterized in that the process control Json is workflow, including a skeleton and a configuration file, and the workflow configuration file includes the following parameters: workflow name, inputs and outputs names, the number of processes executing the workflow, workflow content, etc.;

[0022] The workflow defines the entire computing topology. An algorithm SDK is built by reading the workflow configuration file. The file content is a Json string that defines a complete Workflow topology.

[0023] The workflow content includes multiple Nodes or sub-workflows, and data dependencies are established between the multiple Nodes or sub-workflows through input and output fields.

[0024] Inputs defines all input names, namely input images and operator operating parameters.

[0025] outputs defines all output names, namely output images and operator operation results.

[0026] A Node is a computing unit that includes the following parameters: the thread ID that runs the Node object, the method type, the Node name, the input slots, and the output slots.

[0027] The process control system performs the following steps:

[0028] S1: Load the process control Json file;

[0029] S2: Load parameter configuration json file;

[0030] S3: Execute operator calls according to the process and pass corresponding input images and parameters;

[0031] S4: Save the operator output results and display them.

[0032] Example 2

[0033] The process control Json (Workflow) defines the entire computing topology. An algorithm SDK is built by reading the Workflow configuration file. The file content is a Json string that defines a complete Workflow topology.

[0034] 1.1.1.Workflow skeleton structure

[0035] The following is an example workflow configuration:

[0036] Its backbone structure is as follows:

[0037]

[0038] (1) type=workflow indicates that the current node is a workflow. It is used to distinguish type=node nodes.

[0039] (2) unique_name defines the workflow name. It can be omitted by default and a unique name will be automatically generated internally.

[0040] (3)inputs / outputs defines all input and output names.

[0041] (4)thread_count defines the number of threads that execute the workflow (different threads perform different tasks).

[0042] (5) The workflow defines the structure of the entire topology, which consists of multiple Nodes or Workflow objects (sub-workflows). Data dependencies are established between nodes through the inputs and outputs fields.

[0043] Inputs / outputs definitions

[0044] Inputs defines all input names, usually input images and operator operation parameters. Outputs defines all output names (consisting of the unique_name of the corresponding Node or sub-workflow + "#" + variable name), usually output images and operator operation results. In addition, during the calculation process of the workflow, some intermediate methods may generate some intermediate outputs, and these intermediate fields may also become the input of other intermediate methods. For ease of use, these intermediate outputs can also be placed in the outputs field of the entire workflow.

[0045] Node definition

[0046] Node is a computing unit that encapsulates the configuration and definition of Method. Its backbone structure is as follows:

[0047]

[0048] (1) type=node indicates that the current node is a single Node of the Method type. It is used to distinguish type=workflow sub-workflow type nodes. For details, see 1.1.1 definition.

[0049] (2) thread_id represents the thread id that runs this Node object. Different Node objects can use different threads to execute in parallel to speed up the process.

[0050] (3)method_type: the name of the Method used by the current Node.

[0051] (4) unique_name is used to uniquely identify a MethodInstance object instance.

[0052] (5) inputs / outputs defines the input and output names of the Method, where the name in outputs is composed of the unique_name of the Node + "#" + the variable name.

[0053] Sub-workflow definition

[0054] In some complex business scenarios, we can represent a Node as a Workflow and implement Workflow nesting through the function of sub-Workflow.

[0055] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention in the form of a ring-shaped light source. Therefore, the embodiments should be considered exemplary and non-restrictive in every sense, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes within the meaning and range of equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0056] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. IVD detection process control system based on Json, It is characterized in that The process control Json is workflow, including the skeleton and configuration file. The workflow configuration file includes the following parameters: workflow name, input and output names, number of processes to execute the workflow, workflow content, etc. The workflow defines the entire computing topology. An algorithm SDK is built by reading the workflow configuration file. The file content is a Json string that defines a complete Workflow topology.

2. The IVD detection process control method based on Json according to claim 1, It is characterized in that The workflow content includes multiple Nodes or sub-workflows, and data dependencies are established between the multiple Nodes or sub-workflows through input and output fields.

3. The IVD detection process control system based on Json according to claim 1, It is characterized in that Inputs defines all input names, namely input images and operator operating parameters.

4. The IVD detection process control system based on Json according to claim 1, It is characterized in that outputs defines all output names, namely output images and operator operation results.

5. The IVD detection process control system based on Json according to claim 1, It is characterized in that A Node is a computing unit that includes the following parameters: the thread ID that runs the Node object, the method type, the Node name, the input slots, and the output slots. 6.IVD detection process control method based on Json, It is characterized in that The process control system according to any one of claims 1 to 5 performs the following steps: S1: Load the process control Json file; S2: Load parameter configuration json file; S3: Execute operator calls according to the process and pass corresponding input images and parameters; S4: Save the operator output results and display them.

Images