Auxiliary diagnosis model sharing method, system and sharing platform

Abstract

The invention relates to an auxiliary diagnosis model sharing method which is applied to a sharing platform of an auxiliary diagnosis model, the sharing platform is connected with at least one middleware, and the middleware is connected with at least one sample analyzer. The method comprises the following steps: in response to a release request of an auxiliary diagnosis model, generating a deployment identifier corresponding to the auxiliary diagnosis model; receiving a deployment request sent by the middleware; the deployment request comprises a target deployment identifier of a to-be-deployed target auxiliary diagnosis model; and according to the deployment request, sending a target auxiliary diagnosis model corresponding to the target deployment identifier to the middleware, so that the target auxiliary diagnosis model outputs a corresponding auxiliary diagnosis result based on detection data of a sample analyzer connected with the middleware. Therefore, the middleware can deploy the required target auxiliary diagnosis model from the sharing platform according to medical detection requirements, so that full sharing and reasonable utilization of medical resources are realized, an information barrier is broken, and convenience is provided for medical personnel.

Description

Methods, systems and platforms for sharing auxiliary diagnostic models Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method, system and platform for sharing auxiliary diagnostic models. Background Technology

[0002] With the rapid development of medical testing technology and the advancement of science and technology, the number of medical testing instruments and auxiliary diagnostic models deployed by various medical institutions is increasing daily. Therefore, how to fully share and rationally utilize medical resources is an urgent problem to be solved. Summary of the Invention

[0003] Therefore, it is necessary to provide an auxiliary diagnostic model sharing method, system, and sharing platform to address the aforementioned technical problems.

[0004] In a first aspect, this application provides a method for sharing auxiliary diagnostic models, applied to a sharing platform for auxiliary diagnostic models, wherein the sharing platform is connected to at least one middleware, and the middleware is connected to at least one sample analyzer; the method includes:

[0005] In response to a release request for an auxiliary diagnostic model, a deployment identifier corresponding to the auxiliary diagnostic model is generated; wherein the auxiliary diagnostic model is trained using detection data from at least one of the middlewares;

[0006] Receive a deployment request sent by the middleware; the deployment request includes a target deployment identifier for the target auxiliary diagnostic model to be deployed;

[0007] According to the deployment request, the target auxiliary diagnostic model corresponding to the target deployment identifier is sent to the middleware, so that the target auxiliary diagnostic model outputs the corresponding auxiliary diagnostic result based on the detection data of the sample analyzer connected to the middleware.

[0008] In one embodiment, the method further includes:

[0009] Based on the verification information bound to the middleware account, a target auxiliary diagnostic model recommended for the middleware is selected from the auxiliary diagnostic models; wherein, the verification information bound to the account includes instrument information of the bound instrument and / or information of the bound joint examination discipline.

[0010] In one embodiment, the step of selecting a target auxiliary diagnostic model recommended for the middleware from the auxiliary diagnostic models based on the verification information of the middleware's account binding includes:

[0011] Based on the verification information of the account binding of the middleware, candidate auxiliary diagnostic models are selected from the auxiliary diagnostic models;

[0012] The candidate auxiliary diagnostic models are sorted according to at least one of the middleware account's account attributes, the auxiliary diagnostic model's download information, usage information, and publisher information, and the target auxiliary diagnostic model is determined based on the sorting result; wherein, the account attributes include at least one of location information and time information; and the publisher information includes the identity information of the publisher of the auxiliary diagnostic model.

[0013] In one embodiment, the method further includes:

[0014] Based on the location information of the middleware account, disease warning information issued by the disease control center in the corresponding region is obtained, and the corresponding target auxiliary diagnostic model is selected from the auxiliary diagnostic model in combination with the disease warning information; wherein, the disease warning information includes at least one of endemic disease information and seasonal disease information.

[0015] In one embodiment, the method further includes:

[0016] In response to a request to view the model recommendation page, the model recommendation page is displayed; the model recommendation page includes a model recommendation area; the model recommendation area is used to display detailed information about the target auxiliary diagnostic model; the model recommendation area includes a copy option;

[0017] When a selection operation for the copy option is received, the deployment identifier of the target auxiliary diagnostic model is copied according to the copy option; the deployment identifier is used by the middleware to download and deploy the target auxiliary diagnostic model.

[0018] In one embodiment, the method further includes:

[0019] In response to a request to view the publishing page, the publishing page is displayed; the publishing page includes a model publishing area and a published model area.

[0020] The model publishing area includes an upload option; when the upload option is selected, the uploaded auxiliary diagnostic model is received according to the upload option, and the upload status corresponding to the auxiliary diagnostic model is displayed; the upload status indicates the current progress of the auxiliary diagnostic model during the upload process.

[0021] The published model area is used to display the published data of the published auxiliary diagnostic model; the published model area includes model setting options; when the model setting option is selected, the model attributes of the auxiliary diagnostic model are set according to the model setting option; the model attributes indicate parameters that describe and / or limit the features of the auxiliary diagnostic model.

[0022] Secondly, this application provides an auxiliary diagnostic model sharing system, comprising:

[0023] A sample analyzer is used to test a sample to obtain test data for the sample.

[0024] The middleware, connected to at least one sample analyzer, is used to acquire sample information and corresponding project test data from at least one of the sample analyzers, and to anonymize the sample information to obtain approved test data; the test data includes sample information after filtering out sensitive information and the project test data, and the test data is sent to the R&D platform;

[0025] A research and development platform, connected to at least one of the middleware, is used to train at least one auxiliary diagnostic model using the detection data from at least one of the middleware; and to publish the auxiliary diagnostic model to a sharing platform.

[0026] A sharing platform for executing the auxiliary diagnostic model sharing method described in any embodiment of this application;

[0027] The middleware is also connected to the shared platform and at least one of the sample analyzers, and is used to send a deployment request to the shared platform; the deployment request includes a deployment identifier of the target auxiliary diagnostic model to be deployed; receive and deploy the target auxiliary diagnostic model sent based on the deployment request; and in response to an auxiliary diagnostic request for a target sample, output the corresponding auxiliary diagnostic result based on the sample information and test results of the target sample through the target auxiliary diagnostic model.

[0028] In one embodiment, the R&D platform obtains a model release request and verifies the feature information of the auxiliary diagnostic model corresponding to the model release request;

[0029] The R&D platform publishes the auxiliary diagnostic model to the sharing platform, including:

[0030] If the auxiliary diagnostic model passes the verification, the R&D platform will publish the auxiliary diagnostic model to the sharing platform.

[0031] Thirdly, this application provides a sharing platform, which is connected to at least one middleware, and the middleware is connected to at least one sample analyzer; the sharing platform includes:

[0032] A processing module is configured to generate a deployment identifier corresponding to the auxiliary diagnostic model in response to a release request for the auxiliary diagnostic model; wherein the auxiliary diagnostic model is trained using detection data from at least one of the middlewares;

[0033] A transmission module is used to receive a deployment request sent by the middleware; the deployment request includes a target deployment identifier for the target auxiliary diagnostic model to be deployed;

[0034] The transmission module is used to send the target auxiliary diagnostic model corresponding to the target deployment identifier to the middleware according to the deployment request, so that the target auxiliary diagnostic model outputs the corresponding auxiliary diagnostic result based on the detection data of the sample analyzer connected to the middleware.

[0035] In the aforementioned method for sharing auxiliary diagnostic models, the sharing platform can respond to a deployment request for an auxiliary diagnostic model by generating a deployment identifier corresponding to the model. Based on the deployment identifier carried in the middleware's deployment request, the platform sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware. This enables unified management of auxiliary diagnostic models, allowing each middleware to deploy the required target auxiliary diagnostic model from the sharing platform according to medical testing needs. This achieves full sharing and rational utilization of medical resources, breaks down information barriers, and provides convenience for medical personnel. Attached Figure Description

[0036] Figure 1 is a schematic diagram of the structure of an auxiliary diagnostic model sharing system according to an exemplary embodiment;

[0037] Figure 2 is a schematic diagram of a middleware main page according to an exemplary embodiment;

[0038] Figure 3 is a flowchart illustrating an auxiliary diagnostic model sharing method according to an exemplary embodiment;

[0039] Figure 4 is a schematic diagram of a model recommendation page according to an exemplary embodiment;

[0040] Figure 5 is a schematic diagram of a model details page according to an exemplary embodiment;

[0041] Figure 6 is a schematic diagram of an author publishing page according to an exemplary embodiment;

[0042] Figure 7 is a schematic diagram of a project details page according to an exemplary embodiment;

[0043] Figure 8 is a schematic diagram of a model publishing page according to an exemplary embodiment;

[0044] Figure 9 is a schematic diagram of a data details page according to an exemplary embodiment;

[0045] Figure 10 is a flowchart illustrating an auxiliary diagnostic model sharing method according to an exemplary embodiment;

[0046] Figure 11 is a structural block diagram of a shared platform according to an exemplary embodiment;

[0047] Figure 12 is an internal structure diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "at least one" is used to indicate one or more; "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0050] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0051] In some embodiments, the assisted diagnostic model sharing method can be applied to an electronic device. The electronic device can be any mobile or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to a user. Exemplarily, the terminal can be an Internet of Things (IoT) terminal, such as a sensor device, a mobile phone (or "cellular" phone), and a computer with an IoT terminal, for example, a fixed, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted device. Portable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Alternatively, the terminal can also be a device from an unmanned aerial vehicle (UAV). Alternatively, the terminal can also be a vehicle-mounted device, such as a vehicle computer with wireless communication capabilities, or a wireless terminal connected to an external vehicle computer.

[0052] This application provides an auxiliary diagnostic model sharing system, including:

[0053] A sample analyzer is used to test a sample to obtain test data for the sample.

[0054] The middleware, connected to at least one sample analyzer, is used to acquire sample information and corresponding project test data from at least one of the sample analyzers, and to anonymize the sample information to obtain approved test data; the test data includes sample information after filtering out sensitive information and the project test data, and the test data is sent to the R&D platform;

[0055] A research and development platform, connected to at least one of the middleware, is used to train at least one auxiliary diagnostic model using the detection data from at least one of the middleware; and to publish the auxiliary diagnostic model to a sharing platform.

[0056] The shared platform is used to execute the auxiliary diagnostic model sharing method described in any embodiment of this application;

[0057] The middleware is also connected to the shared platform and at least one of the sample analyzers, and is used to send a deployment request to the shared platform; the deployment request includes a deployment identifier of the target auxiliary diagnostic model to be deployed; receive and deploy the target auxiliary diagnostic model sent based on the deployment request; and in response to an auxiliary diagnostic request for a target sample, output the corresponding auxiliary diagnostic result based on the sample information and test results of the target sample through the target auxiliary diagnostic model.

[0058] In this embodiment, the sample analyzer is applied in the medical or biochemical analysis field, and its function is to detect the sample to be tested, wherein the sample to be tested can be blood, urine, or other bodily fluids. The sample analyzer may include, but is not limited to, at least one of coagulation analyzers, hematology analyzers, biochemical analyzers, and immunoassay analyzers.

[0059] In this embodiment of the application, the sample information may include, but is not limited to, at least one of the target object's name, age, gender, identity information, address information, and historical diagnostic information.

[0060] In this application embodiment, sensitive information may include, but is not limited to, at least one of the target object's name, identity information, and address information.

[0061] In this embodiment, the detection data is used to indicate at least one historical data point; the detection data may include, but is not limited to, at least one of the following: sample information after filtering out sensitive information, item detection data, and sample warning information. For example, item detection data may indicate the sample's data for blood cell, immune, or coagulation tests.

[0062] In some embodiments, the R&D platform in the auxiliary diagnostic model sharing system trains at least one auxiliary diagnostic model using detection data from at least one middleware, and publishes the auxiliary diagnostic model to the sharing platform. Upon receiving a deployment request from the middleware, the sharing platform sends the target auxiliary diagnostic model corresponding to the deployment identifier carried in the deployment request to the middleware for deployment.

[0063] In some embodiments, the middleware in the auxiliary diagnostic model sharing system sends the approved detection data to the R&D platform; the detection data is used by the R&D platform to train the model to obtain at least one auxiliary diagnostic model; the middleware sends a deployment request to the sharing platform, downloads the corresponding target auxiliary diagnostic model through the deployment identifier carried in the deployment request, and deploys the target auxiliary diagnostic model; or, the middleware can manually upload the target auxiliary diagnostic model through the local upload option to achieve offline deployment of the target auxiliary diagnostic model.

[0064] In some embodiments, in response to an auxiliary diagnosis request for a target sample, the middleware inputs the sample information and test results of the target sample into the target auxiliary diagnosis model to obtain the auxiliary diagnosis result corresponding to the target sample.

[0065] In one embodiment, the middleware can be configured to automatically upload approved test data, eliminating the need to set up a data upload option in the navigation bar of the middleware's main page. Once the sample information has been anonymized and the test data is obtained, it will be automatically uploaded to the R&D platform.

[0066] In one embodiment, the middleware can download the approved testing data to local storage, and the R&D platform can then upload the approved testing data from the local storage.

[0067] In this embodiment, the middleware can upload detection data to the R&D platform in multiple ways, eliminating interference from network factors and meeting the need for real-time upload of detection data.

[0068] In some embodiments, as shown in FIG1, the auxiliary diagnostic model sharing system includes a sample analyzer, a sharing platform 110, middleware 120, and a research and development platform 130. The sample analyzer includes a hematology instrument, a coagulation instrument, and an immunoassay instrument. The research and development platform 130 is used to train at least one auxiliary diagnostic model using detection data from at least one middleware 120, and publish the auxiliary diagnostic model to the sharing platform 130. The sharing platform 130 obtains at least one auxiliary diagnostic model published by the research and development platform 130; obtains a deployment request sent by the middleware 120; the deployment request includes a deployment identifier of the target auxiliary diagnostic model to be deployed; and sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware 120 according to the deployment request. The middleware 120 is used to obtain sample information of multiple target objects and perform data anonymization on the sample information to obtain approved detection data; send the detection data to the research and development platform 130; send a deployment request to the sharing platform 130; and deploy the target auxiliary diagnostic model corresponding to the deployment identifier transmitted from the sharing platform 110. The middleware 120, sharing platform 110, and R&D platform 130 in the auxiliary diagnostic model sharing system can be applied to different electronic devices or servers; the middleware 120, sharing platform 110, and R&D platform 130 transmit data through wired or wireless connections.

[0069] In some embodiments, as shown in Figure 2, which is a schematic diagram of the middleware main page, the middleware responds to a main page viewing request by displaying the middleware main page. The middleware main page includes a sample list area, a sample information area, a test result area, and a navigation bar. The navigation bar includes data upload options. When a selection operation for the data upload option is received, the test data is uploaded to the R&D platform according to the data upload option.

[0070] In the aforementioned shared auxiliary diagnostic model system, the R&D platform acquires sample detection data from at least one middleware and trains at least one auxiliary diagnostic model based on this data. This enables unified management of the training process for auxiliary diagnostic models, ensuring the accuracy and reliability of each model. The middleware acquires information from multiple samples and performs data anonymization to obtain detection data, enabling unified management of the detection data used for training models on the R&D platform. Based on the deployment identifier carried in the deployment request, the middleware receives the target auxiliary diagnostic model corresponding to the deployment identifier from the shared platform and deploys it. This achieves unified management of auxiliary diagnostic models, allowing each middleware to deploy the required target auxiliary diagnostic model from the shared platform according to medical testing needs. This facilitates the full sharing and rational utilization of medical resources, breaks down information barriers, and provides convenience for medical personnel.

[0071] In some embodiments, as shown in FIG3, an auxiliary diagnostic model sharing method is provided, applied to an auxiliary diagnostic model sharing platform, wherein the sharing platform is connected to at least one middleware, and the middleware is connected to at least one sample analyzer; the method includes:

[0072] S301, in response to the release request of the auxiliary diagnostic model, a deployment identifier corresponding to the auxiliary diagnostic model is generated; wherein, the auxiliary diagnostic model is trained using detection data from at least one of the middlewares;

[0073] S302, Receive a deployment request sent by the middleware; the deployment request includes a target deployment identifier for the target auxiliary diagnostic model to be deployed;

[0074] S303, according to the deployment request, the target auxiliary diagnostic model corresponding to the target deployment identifier is sent to the middleware, so that the target auxiliary diagnostic model outputs the corresponding auxiliary diagnostic result based on the detection data of the sample analyzer connected to the middleware.

[0075] In this embodiment of the application, the auxiliary diagnostic model is used to indicate a model that assists in disease diagnosis by collecting patient test data (such as medical images, medical records, laboratory test results, etc.) and using algorithms such as machine learning and deep learning to analyze and process this data.

[0076] In this embodiment of the application, the deployment request is used to instruct a request to download and deploy the target auxiliary diagnostic model.

[0077] In some embodiments, the deployment identifier may include, but is not limited to, at least one of graphic identifiers, color identifiers, and string identifiers; wherein, the string identifier may include, but is not limited to, at least one of text identifiers, number identifiers, and letter identifiers.

[0078] In some embodiments, when the sharing platform receives a release request for an auxiliary diagnostic model, it generates a deployment identifier for the auxiliary diagnostic model to associate the auxiliary diagnostic model with the deployment identifier; there is a one-to-one correspondence between the auxiliary diagnostic model and the deployment identifier. When the sharing platform receives a deployment request from the middleware, it sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware according to the deployment identifier carried in the deployment request, so that the middleware can deploy the target auxiliary diagnostic model.

[0079] In the aforementioned method for sharing auxiliary diagnostic models, the sharing platform responds to the release request of the auxiliary diagnostic model by generating a deployment identifier corresponding to the model. Based on the deployment identifier carried in the middleware's deployment request, the platform sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware. This enables unified management of auxiliary diagnostic models, allowing each middleware to deploy the required target auxiliary diagnostic model from the sharing platform according to medical testing needs. This achieves full sharing and rational utilization of medical resources, breaks down information barriers, and provides convenience for medical personnel.

[0080] In some embodiments, the method further includes:

[0081] Based on the verification information bound to the middleware account, a target auxiliary diagnostic model recommended for the middleware is selected from the auxiliary diagnostic models; wherein, the verification information bound to the account includes instrument information of the bound instrument and / or information of the bound joint examination discipline.

[0082] Optionally, the instrument binding indicates the related instrument bound to the middleware; the bound instrument may include, but is not limited to, at least one of a sample analyzer, a blood cell analyzer, a flow cytometer, a chemiluminescence analyzer, and an enzyme immunoassay analyzer.

[0083] Optionally, the application of multiple testing disciplines or technologies bound to the middleware can be linked to the joint testing disciplines; the linked joint testing disciplines can include, but are not limited to, at least two of biochemistry, immunology, laboratory testing, microbiology and molecular diagnostics.

[0084] In some embodiments, the auxiliary diagnostic model includes a first auxiliary diagnostic model, a second auxiliary diagnostic model, and a third auxiliary diagnostic model; the first auxiliary diagnostic model is adapted to a coagulation analyzer, the second auxiliary diagnostic model is adapted to a biochemical analyzer, and the third auxiliary diagnostic model is adapted to a blood cell analyzer. If the first middleware-bound instrument includes a blood cell analyzer and a coagulation analyzer, then the first auxiliary diagnostic model and the third auxiliary diagnostic model are determined as the target auxiliary diagnostic models.

[0085] In some embodiments, the auxiliary diagnostic model includes a first auxiliary diagnostic model, a second auxiliary diagnostic model, and a third auxiliary diagnostic model; the first auxiliary diagnostic model is adapted to a biochemical and immunoassay analyzer, the second auxiliary diagnostic model is adapted to a biochemical analyzer, and the third auxiliary diagnostic model is adapted to an immunoassay analyzer. If the second middleware-bound instrument includes a biochemical and immunoassay analyzer, then the first auxiliary diagnostic model is determined as the target auxiliary diagnostic model.

[0086] In this embodiment, the verification information bound to the middleware account can be used to filter out and recommend target auxiliary diagnostic models that are more suitable for the middleware. On the one hand, this can reduce unnecessary time and cost consumption caused by downloading unsuitable auxiliary diagnostic models. On the other hand, it can make it easier for users to intuitively and quickly view and select the target auxiliary diagnostic models to be deployed, and also reduce the search time for users to find a more suitable target auxiliary diagnostic model among a large number of auxiliary diagnostic models, thereby improving the user experience.

[0087] In some embodiments, the step of selecting a target auxiliary diagnostic model recommended for the middleware from the auxiliary diagnostic models based on the verification information bound to the middleware's account includes:

[0088] Based on the verification information of the account binding of the middleware, candidate auxiliary diagnostic models are selected from the auxiliary diagnostic models;

[0089] The candidate auxiliary diagnostic models are sorted according to at least one of the middleware account's account attributes, the auxiliary diagnostic model's download information, usage information, and publisher information, and the target auxiliary diagnostic model is determined based on the sorting result; wherein, the account attributes include at least one of location information and time information; and the publisher information includes the identity information of the publisher of the auxiliary diagnostic model.

[0090] Optionally, the location information can indicate the geographical location of the middleware. For example, the location information could be province A, city B, district C; or, the location information could be (30°N, 45°E).

[0091] Optionally, the time information can indicate the current time of the middleware. For example, the time information is September 23rd, autumn.

[0092] Optionally, the download information may include, but is not limited to, at least one of the following: download volume, download rate, download status within a preset time range, and download curve. For example, the download information may be that the first auxiliary diagnostic model has downloaded 700 times.

[0093] Optionally, usage information may include, but is not limited to, at least one of the following: usage amount, usage rate, usage within a preset time range, and usage curve. For example, usage information could be that the usage rate of the second auxiliary diagnostic model is 50%.

[0094] In this embodiment, the publisher information may include, but is not limited to, the identity information of the publisher of the auxiliary diagnostic model. The identity information may include information used to characterize the publisher's academic research status.

[0095] Optionally, the identity information may include, but is not limited to, at least one of ordinary users, senior users, and authoritative users.

[0096] For example, the identity information could be that the publisher of A auxiliary diagnostic model can be an ordinary user with a low academic research status; or, the publisher of B auxiliary diagnostic model can be an authoritative user with a high academic research status.

[0097] In some embodiments, the sharing platform can sort the candidate auxiliary diagnostic models according to their usage from high to low, and determine the candidate auxiliary diagnostic model with the highest usage as the target auxiliary diagnostic model.

[0098] In some embodiments, the instrument bound to the middleware is a blood cell analyzer, and the sharing platform can select candidate auxiliary diagnostic models that are compatible with the blood cell analyzer from the auxiliary diagnostic models. The sharing platform selects alternative auxiliary diagnostic models from the candidate auxiliary diagnostic models based on at least one of the account attributes of the middleware account, the download information of the auxiliary diagnostic model, and the publisher information. The sharing platform sorts the alternative auxiliary diagnostic models according to their accuracy from high to low, and determines the alternative auxiliary diagnostic models with an accuracy greater than a second preset threshold as the target auxiliary diagnostic models.

[0099] This application employs multiple methods to select target auxiliary diagnostic models from among auxiliary diagnostic models, thereby meeting the auxiliary diagnostic needs in various scenarios. Compared to considering only the influence of a single factor, this approach allows for further selection of more suitable target auxiliary diagnostic models that are better adapted to the middleware, based on the initial screening of candidate auxiliary diagnostic models. This improves the accuracy of the target auxiliary diagnostic model and facilitates the auxiliary diagnosis of the selected test samples.

[0100] In some embodiments, the method further includes:

[0101] Based on the location information of the middleware account, disease warning information issued by the disease control center in the corresponding region is obtained, and the corresponding target auxiliary diagnostic model is selected from the auxiliary diagnostic model in combination with the disease warning information; wherein, the disease warning information includes at least one of endemic disease information and seasonal disease information.

[0102] In some embodiments, the timing of disease warning information acquisition is closely related to the method of acquisition, and different acquisition times can meet different warning and model selection needs. For example, the electronic device can acquire disease warning information at preset time intervals; the time interval may include, but is not limited to, 5 days, 1 week, and 1 month. Alternatively, in response to an account logging into the sharing platform, the electronic device automatically acquires disease warning information. Alternatively, in response to a request to view the model recommendation page, the model recommendation page is displayed and disease warning information is automatically acquired. Alternatively, the electronic device can acquire disease warning information in real time.

[0103] In some embodiments, if the disease warning information includes influenza information, a target auxiliary diagnostic model suitable for influenza can be selected from the auxiliary diagnostic models. Alternatively, if the middleware's location information is City C in Province B, and City C is currently in summer (June), and Z-specific diseases are prone to occur frequently in this region during the summer, the disease warning information may include Z-specific disease information, allowing a target auxiliary diagnostic model suitable for Z-specific diseases to be selected from the auxiliary diagnostic models.

[0104] In this embodiment of the application, by identifying the regional diseases that are prone to occur in the region where the middleware account is located or the seasonal diseases that are prone to occur in the current season, a specific target auxiliary diagnostic model can be further screened from the candidate auxiliary diagnostic models, thus providing convenience for users.

[0105] In some embodiments, the method further includes:

[0106] Based on at least one of the following: the verification information of the middleware's account binding, account attributes, the download information of the auxiliary diagnostic model, and the publisher information, a target auxiliary diagnostic model recommended for the middleware is selected from the auxiliary diagnostic models.

[0107] In some embodiments, the sharing platform may identify auxiliary diagnostic models with a usage rate higher than a first preset threshold as candidate auxiliary diagnostic models; the sharing platform may identify candidate auxiliary diagnostic models whose publisher is an authoritative user as target auxiliary diagnostic models and display them in descending order.

[0108] In this embodiment of the application, by considering the influence of various factors on the selection of target auxiliary diagnostic models, the target auxiliary diagnostic models that are compatible with the middleware can be selected comprehensively and accurately from the auxiliary diagnostic models, so as to improve the user experience and provide convenience for the auxiliary diagnosis of the selected test samples.

[0109] In some embodiments, the method further includes:

[0110] In response to a request to view the model recommendation page, the model recommendation page is displayed; the model recommendation page includes a model recommendation area; the model recommendation area is used to display detailed information about the target auxiliary diagnostic model; the model recommendation area includes a copy option;

[0111] When a selection operation for the copy option is received, the deployment identifier of the target auxiliary diagnostic model is copied according to the copy option; the deployment identifier is used by the middleware to download and deploy the target auxiliary diagnostic model.

[0112] In this embodiment of the application, the model recommendation area can be the entire area or a part of the model recommendation page.

[0113] In this embodiment of the application, the detailed information may include, but is not limited to, at least one of the following: model name, publishing organization, R&D personnel, deployment identifier, and model download volume.

[0114] Optionally, the issuing organization may include, but is not limited to, at least one of hospitals, laboratories, research institutes, companies, and schools.

[0115] In this embodiment, the display style of the copy option and the upload option, model settings option, local download option, upload sharing platform option, jump to more details option, model search option, view details option and local data upload option in the following embodiments can be any suitable form, color or text style.

[0116] In this embodiment of the application, the selection operation may include, but is not limited to, at least one of the following operations: clicking, long pressing, sliding, and dragging.

[0117] In one embodiment, to facilitate the management of auxiliary diagnostic models, each auxiliary diagnostic model's corresponding model recommendation area on the model recommendation page includes a first enable switch for the copy option. By selecting the copy option, the deployment identifier of the target auxiliary diagnostic model corresponding to the selected operation can be copied. For example, as shown in Figure 4, the copy option is displayed as a double-overlayed box, and the deployment identifier is a deployment code. When a user wants to select the Y auxiliary diagnostic model as the target auxiliary diagnostic model for deployment within the middleware, the sharing platform can click the first enable switch corresponding to the copy option of the Y auxiliary diagnostic model, and copy the deployment code of the Y auxiliary diagnostic model based on the click operation.

[0118] In some embodiments, the model recommendation page further includes a specified order selection area and / or a specified category selection area; the specified order selection area is used to specify the display order of the target auxiliary diagnostic models, and the specified category selection area is used to specify the category of the target auxiliary diagnostic models to be displayed.

[0119] In some embodiments, the model recommendation page also includes a model search option; when a selection operation for the model search option is received, the auxiliary diagnostic model is searched according to the model search option and the search results are displayed. For example, as shown in Figure 4, the ninth enable switch corresponding to the model search option is a long circular frame.

[0120] In one embodiment, as shown in Figure 4, the model recommendation area corresponding to each auxiliary diagnostic model on the model recommendation page may also include a "View Details" option. When the sharing platform receives a click on the "View Details" option, it redirects to the corresponding auxiliary diagnostic model's model details page, as shown in Figure 5. Figure 5 is a schematic diagram of the model details page. The model details page also includes a copy option and a local download option.

[0121] In this embodiment, the detailed information of the recommended target auxiliary diagnostic model can be intuitively determined through the model recommendation page, or the auxiliary diagnostic model can be searched for on the model recommendation page to find the target auxiliary diagnostic model. Furthermore, the deployment identifier of the target auxiliary diagnostic model can be copied using the deployment identifier copy option, facilitating the subsequent deployment of the target auxiliary diagnostic model corresponding to the deployment identifier by the middleware.

[0122] In some embodiments, the method further includes:

[0123] In response to a request to view the publishing page, the publishing page is displayed; the publishing page includes a model publishing area.

[0124] The model publishing area includes an upload option; when the upload option is selected, the uploaded auxiliary diagnostic model is received according to the upload option, and the upload status corresponding to the auxiliary diagnostic model is displayed; the upload status indicates the current progress of the auxiliary diagnostic model during the upload process.

[0125] In some embodiments, the auxiliary diagnostic model may include a certified auxiliary diagnostic model and a third-party model. A third-party model indicates a model that has not been trained using detection data from at least one middleware through the R&D platform, and / or whose feature information has not been verified; a certified auxiliary diagnostic model indicates a model whose feature information has been verified through the R&D platform and has passed the verification; wherein, the feature information may include at least one of detection data, training methods, and accuracy information.

[0126] In this embodiment of the application, the upload status may include, but is not limited to, at least one of the following: upload successful, pending review, review successful, pending publication, and publication successful.

[0127] In one embodiment, to facilitate model upload management, the model publishing area includes a second enable switch corresponding to the upload option. By selecting the second enable switch, an auxiliary diagnostic model or a third-party model can be uploaded from the local machine, and the upload status of the auxiliary diagnostic model or the third-party model can be displayed. For example, as shown in Figure 6, the upload option is displayed as a box. When the auxiliary diagnostic model is successfully uploaded, a background color is added to the display style corresponding to the successful upload status in the model publishing area, indicating that the auxiliary diagnostic model has been successfully uploaded and has entered the next status (pending review status).

[0128] In some embodiments, the publishing page also includes a published model area;

[0129] The published model area includes model setting options; when the selection operation of the model setting option is received, the model attributes of the auxiliary diagnostic model are set according to the model setting option; the model attributes indicate parameters that describe and / or limit the features of the auxiliary diagnostic model.

[0130] In some embodiments, the published model area can be used to display the publication data of each published auxiliary diagnostic model; the publication data may include, but is not limited to, at least one of the following: number of views, number of likes, number of uses, number of comments, and revenue.

[0131] In this embodiment of the application, the model attributes may include, but are not limited to, at least one of browsing attributes, comment attributes, and cost attributes.

[0132] In one embodiment, to facilitate the management of published auxiliary diagnostic models, the published model area for each auxiliary diagnostic model on the publishing page includes model settings options and a third enable switch for each model settings option. By selecting the third enable switch, settings can be configured for the published auxiliary diagnostic model. For example, as shown in Figure 6, the model settings options are displayed in a hexagonal ring. When an X auxiliary diagnostic model is uploaded, the model settings options in the published model area of ​​the X auxiliary diagnostic model can be clicked. In response to selecting a model settings option, model attributes such as whether the X auxiliary diagnostic model is viewable, whether it is chargeable, and the fee amount can be set.

[0133] In this embodiment, certified auxiliary diagnostic models and / or third-party models can be manually uploaded via the upload option in the model publishing area of ​​the author's publishing page. This ensures real-time model publishing regardless of network communication conditions, facilitating model uploads for users. Furthermore, the currently published data of an author's published auxiliary diagnostic models can be viewed intuitively in the published model area of ​​the author's publishing page; users can also freely and flexibly set model attributes, enabling publishers to manage their published auxiliary diagnostic models.

[0134] In some embodiments, the R&D platform publishes the assisted diagnostic model to a sharing platform, including:

[0135] The R&D platform obtains a model release request and verifies the feature information of the auxiliary diagnostic model corresponding to the model release request.

[0136] The R&D platform publishes the auxiliary diagnostic model to the sharing platform, including:

[0137] If the auxiliary diagnostic model passes the verification, the R&D platform will publish the auxiliary diagnostic model to the sharing platform.

[0138] In some embodiments, in response to a model release request, the R&D platform verifies whether the auxiliary diagnostic model to be released uses qualified detection data, the correct training method, and the accuracy information of the trained auxiliary diagnostic model. It determines that an auxiliary diagnostic model that meets a first condition is considered qualified; the first condition includes, but is not limited to, using qualified detection data, using the correct training method, and having an accuracy greater than a third preset threshold. If the auxiliary diagnostic model is qualified, the R&D platform releases the auxiliary diagnostic model to the sharing platform.

[0139] In this embodiment of the application, the correctness and rationality of the auxiliary diagnostic model are ensured by verifying whether the trained auxiliary diagnostic model is qualified, thereby reducing erroneous auxiliary diagnoses caused by the incorrect auxiliary diagnostic model and ensuring the accuracy of the identification results of the auxiliary diagnostic model.

[0140] In some embodiments, the R&D platform responds to a request to view a project details page and displays the project details page; the project details page includes a project statistics area and a data statistics area; the project statistics area is used to display the current status of each model; the status includes new creation, data selection, data processing, feature analysis, feature extraction, machine modeling, model evaluation, paper help, model release, and completion; the project statistics area includes a new project option; the data statistics area is used to display the time consumption curve and model training time of each of the auxiliary diagnostic models;

[0141] When a selection operation is received to choose the new project option, the detection data is selected according to the new project option to start training the model corresponding to the selection operation.

[0142] In one embodiment, to facilitate the management of the model training process, the project statistics area may include a fourth enable switch corresponding to the "Create a New Project" option. By selecting the fourth enable switch, an input event for model training can be created, and the current states of multiple models can be displayed simultaneously. For example, as shown in Figure 7, the display style of the "Create a New Project" option is a plus sign. When the first model completes data selection, a background color is added to the display style corresponding to the data selection state in the current state of the first model in the project statistics area, indicating that the first model has completed data selection and entered the next state (data processing state).

[0143] In this embodiment, the current status of model training and the training time of each auxiliary diagnostic model can be intuitively determined through the project details page, which facilitates the management of model training.

[0144] In some embodiments, the R&D platform responds to a request to view the model release page and displays the model release page; the model release page includes a model details area; the model details area is used to display detailed information of the auxiliary diagnostic model; the detailed information includes model identifier, modeling date, accuracy information, release status, and release date; the model details area includes local download options, upload to a sharing platform options, and jump to more details options;

[0145] When the local download option is selected, the auxiliary diagnostic model is downloaded to the local space according to the local download option.

[0146] When the selection operation of choosing the upload sharing platform option is received, the auxiliary diagnostic model is published to the sharing platform according to the upload sharing platform option;

[0147] When the user selects the option to jump to more details, the user is redirected to other details pages of the auxiliary diagnostic model according to the selected option.

[0148] In this embodiment of the application, the publishing status includes published status and pending publishing status.

[0149] In one embodiment, to facilitate unified management of trained auxiliary diagnostic models, the model details area of ​​each auxiliary diagnostic model on the model publishing page includes a fifth enable switch for the local download option, a sixth enable switch for the upload to the sharing platform option, and a seventh enable switch for the jump to more details option. Selecting the fifth enable switch downloads the trained auxiliary diagnostic model to the local storage; selecting the sixth enable switch publishes the trained auxiliary diagnostic model to the sharing platform; and selecting the seventh enable switch redirects to the more details page of the trained auxiliary diagnostic model. For example, as shown in Figure 8, the local download option is displayed as a downward arrow, the upload to the sharing platform option is displayed as an upward arrow within a cloud, and the jump to more details option is displayed as a left arrow. When a user wants to upload the trained auxiliary diagnostic model to the sharing platform, they can click the sixth enable switch corresponding to the upload to the sharing platform option; after the user selects the upload to the sharing platform option, the auxiliary diagnostic model is automatically published to the sharing platform.

[0150] In this embodiment, the model publishing page allows users to intuitively view the details of the currently trained auxiliary diagnostic model and choose whether to publish it to a shared platform or download it to their local space, thus meeting the management needs of the trained auxiliary diagnostic model.

[0151] In some embodiments, the R&D platform responds to a request to view a data details page and displays a data details page; the data details page includes a sample size statistics area and a sample classification statistics area; the sample size statistics area is used to display the sample size change curve within a preset time period; the sample classification statistics area is used to display the item classification information and instrument classification information of the test data; the data details page includes a local data upload option;

[0152] When the selection operation corresponding to the local data upload option is received, local sample information is received according to the local data upload option.

[0153] In this embodiment, the preset time can be any suitable duration. For example, the preset time can be one month, one week, or one day, etc.

[0154] In this embodiment, the project classification information indicates the classification information of the project source of the detection data.

[0155] For example, the test data includes data 1 to N; data 1 to i are from coagulation test; data i+1 to j are from biochemical test; data j+1 to N are from immune test; where N, i and j are all positive integers.

[0156] For example, as shown in Figure 9, based on the schematic diagram of the current sample details in the sample classification statistics area, it can be determined that 6% of the test data comes from C-reactive protein (CRP), 10% of the test data comes from serum amyloid A (SAA), 20% of the test data comes from complete blood cell count (CBC) and CRP, 28% of the test data comes from CBC and SAA, and 38% of the test data comes from CBC, differential leukocyte count (DIFF), and reticulocytes (RET).

[0157] In this embodiment of the application, the instrument classification information indicates the classification information of the middleware (Data Management System, DMS) source and / or instrument source of the detection data.

[0158] For example, the detection data includes data points 1 to M; data points 1 to i originate from a first type of instrument; data points i+1 to j originate from a second type of instrument; and data points j+1 to M originate from a third type of instrument; where M, i, and j are all positive integers. Alternatively, a first percentage of the detection data originates from a first middleware; a second percentage of the detection data originates from a second middleware; and a third percentage of the detection data originates from a third middleware; where the sum of the first, second, and third percentages is 100%.

[0159] For example, as shown in Figure 9, based on the schematic diagram of the proportion of instrument data in the sample classification statistics area, it can be determined that 6% of the detection data comes from the fifth instrument, 10% of the detection data comes from the fourth instrument, 20% of the detection data comes from the third instrument, 28% of the detection data comes from the second instrument, and 38% of the detection data comes from the first instrument.

[0160] In one embodiment, to facilitate uploading detection data when network communication is abnormal, the data details page includes an eighth enable switch corresponding to the local data upload option. By selecting the eighth enable switch, local sample information can be uploaded locally. The local sample information may include approved detection data downloaded from the middleware and unapproved sample information in the local space. For example, as shown in Figure 9, the local data upload option is displayed as an upward arrow. When a user wants to manually upload detection data, they can click the eighth enable switch corresponding to the local data upload option. After selecting the local data upload option, the user can select local sample information to upload to the R&D platform, and the R&D platform can automatically remove unapproved sample information from the local space.

[0161] In one embodiment, the data details page may further include data filtering options. When the R&D platform receives the tenth operation corresponding to the data filtering option, it receives the input event of the target time according to the data filtering option and displays the data details corresponding to the target time. For example, as shown in Figure 9, the display style of the data filtering option is a box; when a user wants to view the data details of the detection data between October 23, 2015 and October 29, 2015, they can click the tenth enable switch corresponding to the data filtering option. The time configuration option corresponding to the data filtering option will be switched to an active state, and the user can configure the target time of the data through input operations.

[0162] In this embodiment, the data details page allows for a direct view of sample size changes and classification information of the test data within a preset time period, facilitating the assessment of the reasonableness of the test data. Furthermore, the local data upload option allows for offline uploading of test data to meet the real-time data upload requirement. On the other hand, the data filtering option allows for free selection of the sample size changes and classification information of the test data within a target time period, satisfying the need for real-time viewing of data details.

[0163] The following provides specific examples in conjunction with any of the above embodiments:

[0164] Specific Example 1: Figure 10 illustrates an exemplary method for sharing auxiliary diagnostic models. As shown in Figure 10, the auxiliary diagnostic model sharing method is executed by an auxiliary diagnostic model sharing system, which includes middleware, a development platform, and a sharing platform. The auxiliary diagnostic model sharing method includes:

[0165] S1001, the middleware obtains sample information and project testing data of multiple target objects, and performs data anonymization on the sample information to obtain the approved testing data.

[0166] In one optional embodiment, the detection data includes at least sample information after filtering out sensitive information and project detection data.

[0167] S1002, the middleware sends the detection data to the R&D platform.

[0168] S1003, the R&D platform uses the detection data from at least one middleware to train at least one auxiliary diagnostic model.

[0169] S1004, the R&D platform will release the auxiliary diagnostic model to the sharing platform.

[0170] S1005, the sharing platform responds to the release request of at least one auxiliary diagnostic model sent by the R&D platform and generates a deployment identifier corresponding to the auxiliary diagnostic model.

[0171] S1006, the shared platform receives a middleware deployment request.

[0172] In one alternative embodiment, the deployment request includes a deployment identifier for the target auxiliary diagnostic model to be deployed.

[0173] S1007, the shared platform sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware based on the middleware's deployment request.

[0174] S1008, the middleware deployment transmits the deployment identifier corresponding to the target auxiliary diagnostic model from the shared platform.

[0175] In the aforementioned method for sharing auxiliary diagnostic models, the sharing platform can respond to a deployment request for an auxiliary diagnostic model by generating a deployment identifier corresponding to the model. Based on the deployment identifier carried in the middleware's deployment request, the platform sends the target auxiliary diagnostic model corresponding to the deployment identifier to the middleware. This enables unified management of auxiliary diagnostic models, allowing each middleware to deploy the required target auxiliary diagnostic model from the sharing platform according to medical testing needs. This achieves full sharing and rational utilization of medical resources, breaks down information barriers, and provides convenience for medical personnel.

[0176] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0177] Based on the same inventive concept, this application also provides a sharing platform for implementing the above-described method for sharing auxiliary diagnostic models. The solution provided by this sharing platform is similar to the implementation described in the above method; therefore, the specific limitations in one or more sharing platform embodiments provided below can be found in the limitations of the auxiliary diagnostic model sharing method described above, and will not be repeated here.

[0178] In some embodiments, as shown in FIG11, the shared platform is connected to at least one middleware, and the middleware is connected to at least one sample analyzer; the shared platform includes:

[0179] Processing module 10 is configured to generate a deployment identifier corresponding to the auxiliary diagnostic model in response to a release request for the auxiliary diagnostic model; wherein the auxiliary diagnostic model is trained using detection data from at least one of the middlewares;

[0180] Transmission module 20 is used to receive a deployment request sent by the middleware; the deployment request includes a target deployment identifier of the target auxiliary diagnostic model to be deployed;

[0181] The transmission module 20 is used to send the target auxiliary diagnostic model corresponding to the target deployment identifier to the middleware according to the deployment request, so that the target auxiliary diagnostic model outputs the corresponding auxiliary diagnostic result based on the detection data of the sample analyzer connected to the middleware.

[0182] In some embodiments, the platform further includes:

[0183] The recommendation module is used to filter out target auxiliary diagnostic models recommended for the middleware from the auxiliary diagnostic models based on the test information bound to the middleware's account; wherein, the test information bound to the account includes instrument information of the bound instrument and / or information of the bound joint examination discipline.

[0184] In some embodiments, the recommendation module includes:

[0185] The first filtering unit is used to filter candidate auxiliary diagnostic models from the auxiliary diagnostic models based on the verification information of the account binding of the middleware.

[0186] The second filtering unit is used to sort the candidate auxiliary diagnostic models according to at least one of the middleware account's account attributes, the auxiliary diagnostic model's download information, usage information, and publisher information, and to determine the target auxiliary diagnostic model according to the sorting result; wherein, the account attributes include at least one of location information and time information; and the publisher information includes the identity information of the publisher of the auxiliary diagnostic model.

[0187] In some embodiments, the recommendation module is configured to obtain disease warning information issued by the disease control center of the corresponding region based on the location information of the middleware account, and select a corresponding target auxiliary diagnostic model from the auxiliary diagnostic models in combination with the disease warning information; wherein, the disease warning information includes at least one of endemic disease information and seasonal disease information.

[0188] In some embodiments, the platform further includes:

[0189] The display module is used to respond to a request to view the model recommendation page and display the model recommendation page; the model recommendation page includes a model recommendation area; the model recommendation area is used to display detailed information about the target auxiliary diagnostic model; the model recommendation area includes a copy option;

[0190] The processing module 10 is configured to copy the deployment identifier of the target auxiliary diagnostic model according to the copy option when a selection operation for the copy option is received; the deployment identifier is used by the middleware to download and deploy the target auxiliary diagnostic model.

[0191] In some embodiments, the platform further includes:

[0192] The display module is used to display the publishing page in response to a request to view the publishing page; the publishing page includes a model publishing area; the model publishing area includes an upload option;

[0193] The processing module 10 is configured to receive the uploaded auxiliary diagnostic model according to the upload option when the upload option is selected, and display the upload status corresponding to the auxiliary diagnostic model; the upload status indicates the current progress of the auxiliary diagnostic model during the upload process.

[0194] In some embodiments, the publishing page further includes a published model area; the published model area includes model settings options;

[0195] The processing module 10 is configured to set the model attributes of the auxiliary diagnostic model according to the model setting option when the model setting option is selected; the model attributes indicate parameters that describe and / or limit the features of the auxiliary diagnostic model.

[0196] The sharing platform, R&D platform, and middleware in the aforementioned assisted diagnostic model sharing system can be implemented entirely or partially through software, hardware, or a combination thereof. The sharing platform, R&D platform, and middleware can be embedded in or independent of the processor in an electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each of the above modules. In one embodiment, an electronic device is provided, which can be a terminal, and its internal structure diagram can be as shown in Figure 12. The electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor of the electronic device provides computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the electronic device is used for wired or wireless communication with external terminals; wireless communication can be achieved through WIFI, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an assisted diagnostic model sharing method. The display screen of the electronic device can be an LCD screen or an e-ink screen. The input device of the electronic device can be a touch layer covering the display screen, or buttons, trackballs or touchpads set on the casing of the electronic device, or external keyboards, touchpads or mice, etc.

[0197] Those skilled in the art will understand that the structure shown in Figure 12 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0198] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0199] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and / or features involved in this application are all information, data and / or features authorized by the user or fully authorized by all parties.

[0200] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0201] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for sharing auxiliary diagnostic models, characterized in that, A shared platform for an auxiliary diagnostic model, the shared platform being connected to at least one middleware, and the middleware being connected to at least one sample analyzer; the method includes: generating a deployment identifier corresponding to the auxiliary diagnostic model in response to a deployment request for the auxiliary diagnostic model; wherein the auxiliary diagnostic model is trained using detection data from at least one of the middleware; receiving a deployment request sent by the middleware; the deployment request including a target deployment identifier for a target auxiliary diagnostic model to be deployed; and, according to the deployment request, sending the target auxiliary diagnostic model corresponding to the target deployment identifier to the middleware, so that the target auxiliary diagnostic model outputs a corresponding auxiliary diagnostic result based on the detection data from the sample analyzer connected to the middleware.

2. The method according to claim 1, characterized in that, The method further includes: selecting a target auxiliary diagnostic model recommended for the middleware from the auxiliary diagnostic models based on the inspection information bound to the middleware account; wherein the inspection information bound to the account includes instrument information of the bound instrument and / or information of the bound joint examination discipline.

3. The method according to claim 2, characterized in that, The step of selecting a target auxiliary diagnostic model recommended for the middleware from the auxiliary diagnostic models based on the verification information bound to the middleware's account includes: selecting candidate auxiliary diagnostic models from the auxiliary diagnostic models based on the verification information bound to the middleware's account; sorting the candidate auxiliary diagnostic models according to at least one of the middleware account's account attributes, the auxiliary diagnostic model's download information, usage information, and publisher information; and determining the target auxiliary diagnostic model based on the sorting result; wherein, the account attributes include at least one of location information and time information; and the publisher information includes the identity information of the publisher of the auxiliary diagnostic model.

4. The method according to claim 2, characterized in that, The method further includes: obtaining disease warning information issued by the disease control center of the corresponding region based on the location information of the middleware account, and selecting the corresponding target auxiliary diagnostic model from the auxiliary diagnostic model in combination with the disease warning information; wherein, the disease warning information includes at least one of endemic disease information and seasonal disease information.

5. The method according to claim 1, characterized in that, The method further includes: in response to a request to view a model recommendation page, displaying a model recommendation page; the model recommendation page includes a model recommendation area; the model recommendation area is used to display detailed information of the target auxiliary diagnostic model; the model recommendation area includes a copy option; when a selection operation of the copy option is received, the deployment identifier of the target auxiliary diagnostic model is copied according to the copy option; the deployment identifier is used by the middleware to download and deploy the target auxiliary diagnostic model.

6. The method according to claim 1, characterized in that, The method further includes: responding to a request to view the publishing page, displaying a publishing page; the publishing page includes a model publishing area; the model publishing area includes an upload option; when the upload option is selected, receiving the uploaded auxiliary diagnostic model according to the upload option, and displaying the upload status corresponding to the auxiliary diagnostic model; the upload status indicates the current progress of the auxiliary diagnostic model during the upload process.

7. The method according to claim 6, characterized in that, The publishing page also includes a published model area; the published model area includes model setting options; when the model setting option is selected, the model attributes of the auxiliary diagnostic model are set according to the model setting option; the model attributes indicate parameters that describe and / or limit the features of the auxiliary diagnostic model.

8. A shared system for auxiliary diagnostic models, characterized in that, include: A sample analyzer is used to test a sample to obtain test data for the sample. The middleware, connected to at least one sample analyzer, is used to acquire sample information and corresponding project test data from at least one of the sample analyzers, and to anonymize the sample information to obtain approved test data; the test data includes sample information after filtering out sensitive information and the project test data, and the test data is sent to the R&D platform; A research and development platform, connected to at least one of the middleware components, is used to train at least one auxiliary diagnostic model using detection data from the at least one middleware component; the auxiliary diagnostic model is published to a sharing platform; the sharing platform is used to execute the auxiliary diagnostic model sharing method as described in any one of claims 1 to 7; the middleware is also connected to the sharing platform and at least one of the sample analyzers, and is used to send a deployment request to the sharing platform; the deployment request includes a deployment identifier of the target auxiliary diagnostic model to be deployed; the platform receives and deploys the target auxiliary diagnostic model sent based on the deployment request; in response to an auxiliary diagnostic request for a target sample, the platform outputs a corresponding auxiliary diagnostic result based on the sample information and detection results of the target sample using the target auxiliary diagnostic model.

9. The system according to claim 8, characterized in that, The R&D platform obtains a model release request and verifies the feature information of the auxiliary diagnostic model corresponding to the model release request. The R&D platform publishes the auxiliary diagnostic model to the sharing platform, including: the R&D platform publishes the auxiliary diagnostic model to the sharing platform when the auxiliary diagnostic model passes the verification.

10. A sharing platform, characterized in that, The shared platform is connected to at least one middleware, and the middleware is connected to at least one sample analyzer. The shared platform includes: a processing module, configured to generate a deployment identifier corresponding to the auxiliary diagnostic model in response to a deployment request of the auxiliary diagnostic model; wherein the auxiliary diagnostic model is trained using detection data from at least one of the middleware; and a transmission module, configured to receive a deployment request sent by the middleware; the deployment request includes a target deployment identifier of the target auxiliary diagnostic model to be deployed; the transmission module is further configured to send the target auxiliary diagnostic model corresponding to the target deployment identifier to the middleware according to the deployment request, so that the target auxiliary diagnostic model outputs a corresponding auxiliary diagnostic result based on the detection data from the sample analyzer connected to the middleware.

Images