Collaborative diagnosis method, device, equipment, system and program product

Abstract

The embodiment of the invention provides a collaborative diagnosis method. The method comprises the following steps: acquiring consultation information associated with a first object; then, based on the consultation information, a diagnosis party is triggered to carry out collaborative diagnosis on the consultation information to obtain a diagnosis suggestion, the diagnosis party comprises a second object and an intelligent agent, and the diagnosis suggestion is obtained based on interaction of the second object and the intelligent agent for the consultation information; determining an execution process indicated by the diagnosis suggestion; and triggering a diagnosis party to carry out cooperative judgment on diagnosis and treatment actions generated by the execution process so as to obtain a diagnosis conclusion. Therefore, a multi-party interactive collaborative diagnosis process is realized, deep analysis of difficult symptoms and personalized treatment scheme suggestions are provided through collaborative work of intelligent agents, the problems of single input limitation and limited information processing capability are solved, and the accuracy of the diagnosis process is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to collaborative diagnosis methods, devices, equipment, systems and program products. Background Art

[0002] Various diseases, especially some difficult and complicated diseases and chronic diseases, have atypical symptoms and imaging examinations. The diagnosis and treatment process often requires multidisciplinary collaboration, long-term follow-up observation, and multiple treatment adjustments, which puts great pressure on the medical system.

[0003] Generally, the disease diagnosis process can be the communication between doctors and patients, or the interaction between patients and intelligent agents; however, the one-to-one interaction process is less efficient and prone to diagnostic errors due to poor communication, affecting the accuracy of the diagnosis process. Summary of the invention

[0004] In view of this, the present application provides a collaborative diagnosis method, which can realize the collaborative diagnosis process and improve the accuracy of the diagnosis process.

[0005] According to a first aspect of an embodiment of the present application, a collaborative diagnosis method is provided, which can be applied to a system or program including a collaborative diagnosis function in a terminal device, and specifically includes:

[0006] Obtaining consultation information associated with the first object;

[0007] triggering a diagnostic party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnostic suggestions, the diagnostic party comprising a second object and an intelligent agent, the diagnostic suggestions being obtained based on the interaction between the second object and the intelligent agent with respect to the consultation information;

[0008] Determining the execution process of the diagnostic suggestion indication;

[0009] In response to the execution of the process, the diagnostic party is triggered to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion.

[0010] Optionally, in a possible implementation, triggering the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnosis suggestions includes:

[0011] Performing semantic recognition on the consultation information to obtain diagnostic evidence corresponding to the first object;

[0012] Triggering the diagnosing party to collect debate elements in the diagnostic evidence based on the diagnostic evidence;

[0013] In response to the second object and the intelligent agent performing a collaborative diagnosis on the debate element, the diagnosis suggestion is obtained.

[0014] Optionally, in a possible implementation manner, the performing semantic recognition on the consultation information to obtain diagnosis evidence corresponding to the first object includes:

[0015] Performing semantic recognition on the consultation information to obtain consultation semantic data, wherein the consultation semantic data is marked with a semantic object identifier;

[0016] Based on the semantic object identifier, the consultation semantic data is subjected to restricted natural speech understanding to obtain consultation semantic elements;

[0017] Generate diagnostic evidence corresponding to the first object according to the consultation semantic elements.

[0018] Optionally, in a possible implementation, in response to the second object and the agent performing collaborative diagnosis on the debate element to obtain the diagnosis suggestion, includes:

[0019] Obtaining a first suggestion obtained by the second object through diagnosis of the debate element, and a second suggestion obtained by the agent through diagnosis of the debate element;

[0020] Comparing the first suggestion and the second suggestion based on a preset dimension to obtain comparison information, wherein the preset dimension is determined based on an association relationship that has an impact in a diagnosis process;

[0021] If the comparison information indicates that the first suggestion and the second suggestion correspond to cooperation, the first suggestion and the second suggestion are summarized to obtain the diagnosis suggestion.

[0022] Optionally, in a possible implementation, the method further includes:

[0023] If the comparison information indicates that the first suggestion and the second suggestion correspond to conflicting suggestions, determining conflicting content;

[0024] Triggering the diagnosis party to perform at least one round of inquiry operation based on the conflict content to trigger a suggestion update process, wherein the suggestion update process is used to trigger the second object to update the first suggestion and / or trigger the agent to update the second suggestion;

[0025] The suggestion updating process is performed until the first suggestion and the second suggestion cooperate.

[0026] Optionally, in a possible implementation, the method further includes:

[0027] Counting the number of operations corresponding to the query operations associated with the conflicting content;

[0028] If the number of operations reaches the inquiry threshold, a stop instruction is output.

[0029] Optionally, in a possible implementation, the method further includes:

[0030] Determining a diagnostic dimension corresponding to the conflict content;

[0031] If the diagnostic dimension indicates a non-primary diagnosis, the diagnostic recommendation is determined according to the content of the primary diagnostic dimension.

[0032] Optionally, in a possible implementation, in response to the second object and the agent performing collaborative diagnosis on the debate element to obtain the diagnosis suggestion, includes:

[0033] determining a diagnosis cluster associated with the second object, and an agent cluster associated with the agent;

[0034] Obtaining a third suggestion obtained by diagnosing the debate element by the representative object in the diagnosis cluster;

[0035] Obtaining a fourth suggestion obtained by a representative intelligent agent in the intelligent agent cluster through diagnosis of the debate element;

[0036] A collaborative diagnosis is performed based on the third suggestion and the fourth suggestion to obtain the diagnosis suggestion.

[0037] Optionally, in a possible implementation, the obtaining of a fourth suggestion obtained by the representative agent in the agent cluster through diagnosis of the debate element includes:

[0038] Sending the debate elements to the agent cluster so that multiple agents in the agent cluster conduct consultation interaction based on the debate elements, wherein the consultation interaction process is performed with reference to consultation records and a knowledge database;

[0039] Obtain the fourth suggestion obtained by the agent cluster through the consultation interaction.

[0040] Optionally, in a possible implementation, the method further includes:

[0041] The diagnosis suggestion is sent to the agent cluster, so that a plurality of agents in the agent cluster associated with the diagnosis suggestion perform knowledge iteration based on the diagnosis suggestion.

[0042] Optionally, in a possible implementation manner, obtaining consultation information associated with the first object includes:

[0043] Obtaining medical record information associated with the first object;

[0044] Determine the preset data conditions and the data requirement conditions corresponding to the intelligent agent;

[0045] Matching the medical record information based on the preset data condition and the data requirement condition;

[0046] If the medical record information matches the preset data condition and the data requirement condition, the consultation information is generated based on the medical record information.

[0047] Optionally, in a possible implementation, the execution process includes an inspection process and a treatment process, and in response to the execution of the execution process, the diagnosis party is triggered to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion, including:

[0048] In response to the inspection process being carried out, triggering the diagnostic party to make a collaborative judgment on the detection actions generated by the inspection process to obtain an inspection conclusion;

[0049] triggering the treatment process based on the examination conclusion;

[0050] In response to the progress of the treatment process, the diagnostic party is triggered to make a collaborative judgment on the treatment actions generated by the treatment process to obtain the diagnosis conclusion.

[0051] Optionally, in a possible implementation manner, the method further includes:

[0052] Obtain the interaction data generated by the agent during the interaction process;

[0053] generating multimedia content based on the interaction data;

[0054] The multimedia content is presented in an interactive interface.

[0055] According to a second aspect of an embodiment of the present application, there is provided a collaborative diagnosis device, including:

[0056] An acquisition unit, configured to acquire consultation information associated with the first object;

[0057] A diagnosis unit, configured to trigger a diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, wherein the diagnosis party includes a second object and an agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the agent with respect to the consultation information;

[0058] The diagnostic unit is further used to determine the execution process of the diagnostic suggestion indication;

[0059] The diagnosis unit is also used to trigger the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process in response to the execution of the execution process to obtain a diagnosis conclusion.

[0060] Optionally, in a possible implementation, the diagnosis unit is used to perform semantic recognition on the consultation information to obtain diagnosis evidence corresponding to the first object when the diagnosis party is triggered to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnosis advice; based on the diagnosis evidence, the diagnosis party is triggered to collect debate elements in the diagnosis evidence; and in response to the second object and the agent performing collaborative diagnosis on the debate elements, obtain the diagnosis advice.

[0061] Optionally, in a possible implementation, the diagnosis unit is used to perform semantic recognition on the consultation information to obtain consultation semantic data when performing semantic recognition on the consultation information to obtain diagnostic evidence corresponding to the first object, and the consultation semantic data is marked with a semantic object identifier; perform restricted natural speech understanding on the consultation semantic data based on the semantic object identifier to obtain consultation semantic elements; and generate diagnostic evidence corresponding to the first object based on the consultation semantic elements.

[0062] Optionally, in a possible implementation, the diagnosis unit is used to obtain a first suggestion obtained by the second object for diagnosing the debate element and a second suggestion obtained by the agent for diagnosing the debate element in response to the second object and the agent performing a collaborative diagnosis on the debate element to obtain the diagnosis suggestion; compare the first suggestion and the second suggestion based on a preset dimension to obtain comparison information, wherein the preset dimension is determined based on a correlation relationship that has an impact in the diagnosis process; if the comparison information indicates that the suggestions corresponding to the first suggestion and the second suggestion cooperate, the first suggestion and the second suggestion are summarized to obtain the diagnosis suggestion.

[0063] Optionally, in a possible implementation, the diagnosis unit is further used to determine the conflict content if the comparison information indicates that the suggestions corresponding to the first suggestion and the second suggestion conflict; trigger the diagnosis party to perform at least one round of inquiry operations based on the conflict content to trigger a suggestion update process, the suggestion update process is used to trigger the second object to update the first suggestion, and / or trigger the agent to update the second suggestion; execute the suggestion update process until the first suggestion and the second suggestion cooperate.

[0064] Optionally, in a possible implementation, the diagnosis unit is further configured to count the number of operations corresponding to the query operation associated with the conflicting content; if the number of operations reaches a query threshold, a stop instruction is output.

[0065] Optionally, in a possible implementation, the diagnostic unit is further used to determine a diagnostic dimension corresponding to the conflicting content; if the diagnostic dimension indicates a non-primary diagnosis, the diagnostic suggestion is determined according to the content of the primary diagnostic dimension.

[0066] Optionally, in a possible implementation, the diagnosis unit is used to determine the diagnosis cluster associated with the second object and the agent cluster associated with the agent when the diagnosis suggestion is obtained in response to the second object and the agent performing a collaborative diagnosis on the debate element; obtain a third suggestion obtained by the representative object in the diagnosis cluster performing a diagnosis on the debate element; obtain a fourth suggestion obtained by the representative agent in the agent cluster performing a diagnosis on the debate element; and perform a collaborative diagnosis based on the third suggestion and the fourth suggestion to obtain the diagnosis suggestion.

[0067] Optionally, in a possible implementation, the diagnosis unit is used to send the debate element to the agent cluster when obtaining the fourth suggestion obtained by the representative agent in the agent cluster for diagnosing the debate element, so that multiple agents in the agent cluster conduct consultation interaction based on the debate element, and the consultation interaction process is performed with reference to the consultation record and the knowledge database; and obtain the fourth suggestion obtained by the agent cluster after the consultation interaction.

[0068] Optionally, in a possible implementation, the diagnosis unit is further used to send the diagnosis suggestion to the agent cluster, so that multiple agents in the agent cluster associated with the diagnosis suggestion perform knowledge iteration based on the diagnosis suggestion.

[0069] Optionally, in a possible implementation, the acquisition unit is used to acquire medical record information associated with the first object when acquiring consultation information associated with the first object; determine preset data conditions and data requirement conditions corresponding to the intelligent agent; match the medical record information based on the preset data conditions and the data requirement conditions; if the medical record information matches the preset data conditions and the data requirement conditions, generate the consultation information based on the medical record information.

[0070] Optionally, in a possible implementation, the diagnostic unit is used to trigger the diagnostic party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process in response to the execution of the execution process to obtain a diagnosis conclusion; in response to the implementation of the inspection process, trigger the diagnostic party to make a collaborative judgment on the detection actions generated by the inspection process to obtain an inspection conclusion; trigger the treatment process based on the inspection conclusion; and in response to the implementation of the treatment process, trigger the diagnostic party to make a collaborative judgment on the treatment actions generated by the treatment process to obtain the diagnosis conclusion.

[0071] Optionally, in a possible implementation, it is characterized in that the diagnostic unit is also used to obtain interaction data generated by the intelligent agent during the interaction process; generate multimedia content based on the interaction data; and present the multimedia content in the interaction interface.

[0072] According to a third aspect of an embodiment of the present application, there is provided a collaborative diagnosis device, including an input-output component and a processor;

[0073] The input and output components are used to obtain consultation information;

[0074] The processor is used to output a diagnosis conclusion corresponding to the consultation information obtained by the input-output component by executing the collaborative diagnosis method as described in the first aspect or any one of the first aspects.

[0075] According to a fourth aspect of an embodiment of the present application, there is provided a collaborative diagnosis system, including an interactive client and a server;

[0076] The interactive client is used to obtain consultation information and send the consultation information to the server, and to display the collaborative diagnosis results output by the server;

[0077] The server is used to output the diagnosis conclusion corresponding to the consultation information obtained by the interactive client by executing the collaborative diagnosis method described in the first aspect or any one of the first aspects.

[0078] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, comprising: a computer program, wherein when the computer program is executed by a processor, the collaborative diagnosis method described in the first aspect or any one of the first aspects is implemented.

[0079] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0080] By obtaining the consultation information associated with the first object; then triggering the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, the diagnosis party includes a second object and an intelligent agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the intelligent agent for the consultation information; and determining the execution process indicated by the diagnosis suggestion; and then in response to the execution process, triggering the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion. In this way, a collaborative diagnosis process of multi-party interaction is realized, and through the collaborative work of intelligent agents, an in-depth analysis of difficult symptoms and personalized treatment plan suggestions are provided to overcome the problems of single input limitations and limited information processing capabilities, thereby improving the accuracy of the diagnosis process. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0082] Figure 1 A network architecture diagram for the collaborative diagnosis system;

[0083] Figure 2 A process architecture diagram of collaborative diagnosis provided in an embodiment of the present application;

[0084] Figure 3 A flowchart of a collaborative diagnosis method provided in an embodiment of the present application;

[0085] Figure 4 A flowchart of another collaborative diagnosis method provided in an embodiment of the present application;

[0086] Figure 5 A technical architecture diagram of a collaborative diagnosis method provided in an embodiment of the present application;

[0087] Figure 6 A schematic diagram of a scenario of a collaborative diagnosis method provided in an embodiment of the present application;

[0088] Figure 7 A schematic diagram of another scenario of a collaborative diagnosis method provided in an embodiment of the present application;

[0089] Figure 8 A schematic diagram of the structure of a collaborative diagnosis device provided in an embodiment of the present application;

[0090] Fig. 9 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0091] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0092] It should be understood that the collaborative diagnosis method provided in the present application can be applied to a system or program containing a collaborative diagnosis function in a terminal device, such as a smart medical application. Specifically, the collaborative diagnosis system can be run on Figure 1 In the network architecture shown in Figure 1 As shown in FIG. 1 , it is a network architecture diagram of the collaborative diagnosis system. As can be seen from the figure, the collaborative diagnosis system can provide a collaborative diagnosis process with multiple information sources, that is, the consultation information is determined through the acquisition operation on the terminal side, and then sent to the server for multi-party consultation diagnosis; it can be understood that Figure 1 A variety of terminal devices are shown in FIG. 1 . The terminal devices may be computer devices. In actual scenarios, more or fewer types of terminal devices may participate in the collaborative diagnosis process. The specific number and type depend on the actual scenario and are not limited here. In addition, Figure 1 One server is shown in the figure, but in actual scenarios, multiple servers may be involved, especially in scenarios with multidisciplinary outputs. The specific number of servers depends on the actual scenario.

[0093] In this embodiment, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected through wired or wireless communication, and the terminal and the server can be connected to form a blockchain network, which is not limited in this application.

[0094] It can be understood that the above-mentioned collaborative diagnosis system can run on a personal mobile terminal, for example, as an application such as smart medical care, it can also run on a server, and it can also run on a third-party device to provide collaborative diagnosis to obtain collaborative diagnosis processing results of the information source; the specific collaborative diagnosis system can be run in the above-mentioned device in the form of a program, or it can be run as a system component in the above-mentioned device, and it can also be run as a cloud service program. The specific operation mode depends on the actual scenario and is not limited here.

[0095] With social development and population aging, the incidence of various diseases has increased year by year, especially some difficult and complicated diseases and chronic diseases, whose symptoms and imaging examinations are atypical. The diagnosis and treatment process often requires multidisciplinary collaboration and long-term follow-up observation, as well as multi-plan adjustment of treatment, which puts great pressure on the medical system.

[0096] Generally, the diagnosis process of a disease can be the communication between doctors and patients, or the interaction between patients and intelligent agents; however, the one-to-one interaction process is less efficient and prone to diagnostic errors due to poor communication, which affects the accuracy of the diagnostic process. In addition, for the diagnosis process of the machine consultation system, it lacks a targeted platform, that is, there is a lack of consultation platforms specifically for complex or rare and difficult diseases, resulting in low consultation quality for these diseases. And it has a single input limitation, that is, some automated diagnostic systems may only rely on a single test result as input for judgment, without considering multiple aspects of information, and can only be used for initial screening. And the ability to assist clinical practice is limited. Current technology cannot enable automated systems to completely replace medical experts, and there is still a risk of misdiagnosis and missed diagnosis.

[0097] In order to solve the above problems, this application proposes a collaborative diagnosis method, which is applied to Figure 2 In the collaborative diagnosis process framework shown in Figure 2 As shown, a process architecture diagram of collaborative diagnosis provided in an embodiment of the present application is provided. Through a debate-style interactive process involving three parties (doctor, patient, and intelligent agent), the intelligent agents corresponding to the professional fields configured on the server side are triggered to collaborate with each other, and multiple agents provide in-depth analysis and personalized treatment suggestions for difficult diagnoses. Multi-party consultations are conducted through the collection of patient medical records, and a debate-style execution method is adopted in the diagnosis and treatment process to obtain a diagnosis conclusion of multi-party cooperation, thereby improving the comprehensiveness and accuracy of the diagnosis and reducing the risk of personal bias and staff shortage.

[0098] It is understandable that the collaborative diagnosis method provided in the present application can be written as a program to serve as a processing logic in a hardware system, or as a collaborative diagnosis device to implement the above processing logic in an integrated or external manner. As an implementation method, the collaborative diagnosis device obtains the consultation information associated with the first object; then triggers the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, the diagnosis party includes a second object and an intelligent agent, and the diagnosis suggestion is based on the interaction between the second object and the intelligent agent for the consultation information; and determines the execution process indicated by the diagnosis suggestion; and then, in response to the execution process, triggers the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion. Thereby, a collaborative diagnosis process of multi-party interaction is realized, and through the collaborative work of intelligent agents, an in-depth analysis of difficult symptoms and personalized treatment plan suggestions are provided to overcome the problems of single input limitations and limited information processing capabilities, thereby improving the accuracy of the diagnosis process.

[0099] In combination with the above process architecture, the collaborative diagnosis method in this application is introduced below. Figure 3 , Figure 3 A flowchart of a collaborative diagnosis method provided in an embodiment of the present application, the embodiment of the present application at least includes the following steps:

[0100] 301. Obtain consultation information associated with a first object.

[0101] In this embodiment, the first object is the object that needs to be diagnosed and treated, which can be a patient, a patient's medical record, or a terminal that sends medical records and consultation information, etc. The patient is used as an example for explanation here. Correspondingly, the second object is the object that provides diagnosis and treatment, which can be a doctor, or a terminal associated with a doctor; and the intelligent agent is an artificial intelligence model trained based on diagnosis and treatment big data, which can generate corresponding inspection, diagnosis, and treatment suggestions in response to the input of medical record information. Its specific form can be a software algorithm, such as a smart doctor in a terminal application, or it can be encapsulated in specific hardware, such as the algorithm logic of a diagnosis and treatment robot. The specific form depends on the actual scenario, and this number is not limited.

[0102] In addition, the consultation information is a collection of medical treatment and preliminary diagnosis information based on the patient's medical record; specifically, the consultation information can be obtained through the interaction between the first object and the second object, that is, the communication record between the doctor and the patient; it can also be obtained through the interaction between the first object and the intelligent agent, that is, the diagnosis and treatment process of the intelligent agent conducting multiple rounds of dialogue with the patient; it can also be a combination of the above two situations.

[0103] Therefore, the diagnosis scenario of this embodiment is a debate-style multi-party consultation scenario; specifically, for this debate-style consultation scenario, it can be adopted Figure 4 The execution flow shown is Figure 4 A flowchart of another collaborative diagnosis method provided for an embodiment of the present application; the overall process of this scenario includes a preparation process (consultation preparation stage) 401, a diagnosis process (diagnosis debate stage) 402, an examination process (examination debate stage) 403, and a treatment process (treatment debate stage) 404, that is, starting from inputting the clinical data of a patient to be consulted, the patient's disease diagnosis, the patient's examination plan, and the patient's treatment plan are clarified in turn. The number of consultation preparation discussion rounds, the preparation time for each round of consultation, the total number of rounds of each debate link, and the time for each round of debate are set for each stage / node. If the limit is exceeded, it will automatically enter the next node to ensure the smoothness and standardization of the overall consultation discussion process, and lay the foundation for the formulation of process specifications for debate-type human-machine joint consultations.

[0104] exist Figure 4 In the consultation preparation stage shown, in order to ensure the smooth progress of the debate process, it is necessary to collect consultation-related information and judge its completeness, that is, first obtain the medical record information associated with the first object; then determine the preset data conditions and the data requirement conditions corresponding to the intelligent agent, where the preset data conditions are conditions indicating the integrity and availability of the data, such as whether the description of the condition is complete, whether the preliminary examination parameters are credible, etc., and the data requirement conditions are the support of the intelligent agent for the medical record information; then match the medical record information based on the preset data conditions and the data requirement conditions; if the medical record information matches the preset data conditions and the data requirement conditions, generate consultation information based on the medical record information.

[0105] Therefore, for the above-mentioned consultation preparation process, the preset data conditions (also known as system setting conditions) can be judged, that is, to ensure that all necessary preconditions have been met, including the completeness of patient data, the availability of preliminary diagnosis results, etc. And to judge whether the data requirement conditions are met, which can include agent decision conditions and consultation resource preset conditions. The agent decision conditions are used to ensure that all decision support tools and auxiliary systems have provided necessary information, including whether the patient's information in various dimensions can support the agent to make decisions; if the agent decision conditions are not met, a supplementary information reminder is given, through supplementary medical record data, system input or doctor report, etc.; and for the consultation resource preset condition judgment: according to the information given by the agent, it is judged whether the patient can make a consultation decision to decide the next action. For the judgment of starting the diagnostic consultation process, that is, once the above conditions are met, the consultation process can be started, which usually involves multiple doctors or experts discussing the condition together and formulating the best diagnosis and treatment plan.

[0106] In addition, for Figure 4In the diagnostic debate stage, step 402, the intelligent agent first makes diagnostic suggestions, which are given by either the consulting intelligent agent or the doctor, and the diagnostic suggestions are given in the form of natural language interaction; then the diagnostic suggestions are judged, that is, based on the suggestions given by the doctor and the intelligent agent, it is judged whether the suggestions of each party are "conflicting" or "cooperative", and then different processing procedures are continued; then cooperative conflict processing is performed: if multiple parties suggest cooperation (i.e. unity), the diagnostic process is judged, and if a diagnostic conclusion has been obtained or the process rounds have been exceeded, the diagnosis is terminated; if the suggestions of multiple parties conflict, evidence is supplemented according to the conflict, and the diagnostic process is entered again until a diagnostic conclusion is obtained or the process rounds have been exceeded, then the diagnosis is terminated; for the diagnosis conclusion judgment, that is, the diagnosis conclusion gives a conclusion on whether an examination is needed, if so, the examination process is entered, otherwise the treatment process is entered.

[0107] Furthermore, for Figure 4 In the examination debate stage, i.e., step 403, experts and agents from various disciplines discuss whether the primary diagnosis is clear, whether the accompanying diagnosis and secondary diagnosis are missing, and whether there are any diagnoses that affect the evaluation of subsequent treatment methods; for the treatment debate stage, i.e., step 404, experts and agents from various disciplines express their specialist opinions on whether there are indications and contraindications for surgical treatment, interventional treatment, radiofrequency ablation, radiotherapy, chemotherapy, targeted therapy, immunotherapy, and conservative treatment.

[0108] It can be seen that the debate-style human-opportunity diagnosis scenario process provided in this embodiment, by designing a debate-style interactive process that allows doctors, patients and intelligent agents to participate, strengthens multi-party communication and understanding in the decision-making process and reduces personal bias and misunderstanding in diagnosis.

[0109] 302. Triggering a diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnosis suggestions, the diagnosis party including a second object and an intelligent agent, and the diagnosis suggestions are obtained based on the interaction between the second object and the intelligent agent with respect to the consultation information.

[0110] In this embodiment, collaborative diagnosis is Figure 4 In the description of the diagnostic process 402, the collaborative process is that either the consulting intelligent agent or the doctor gives diagnostic suggestions, and the diagnostic suggestions are given in the form of natural language interaction; then the diagnostic suggestions are judged, that is, based on the suggestions given by the doctors and the intelligent agents, it is judged whether the suggestions of each party are "conflicting" or "cooperative", and then different processing flows are continued; in addition, the diagnostic party in this embodiment is a collection of second objects and intelligent agents, which can specifically be one or more second objects, and one or more intelligent agents. The specific forms of the second objects and intelligent agents refer to the description in step 301, which will not be repeated here.

[0111] Specifically, in scenarios where doctors give advice, the intelligent agent can directly review the doctor's advice, thereby saving data processing time. That is, the doctor's advice is provided through the professional knowledge and data analysis capabilities of multiple agents, assisting the doctor in making more accurate and comprehensive medical decisions.

[0112] In addition, for scenarios where the intelligent agent gives advice, doctors can directly review the advice given by the intelligent agent, thereby saving data processing time. That is, the intelligent agent can help simplify and speed up the diagnosis process, alleviate the workload of doctors, and improve the efficiency of diagnosis and treatment.

[0113] Furthermore, in scenarios where doctors and agents jointly give advice, it is necessary to determine whether the advice from each party is "conflicting" or "cooperative" and then proceed with different processing procedures. By adopting a debate-style framework, the decision-making basis of different agents can be displayed, providing doctors and patients with a more transparent decision-making process and logic, and enhancing interpretability.

[0114] Specifically, for the judgment process in the debate, that is, the review process, conflicts in suggestions may occur, and separate suggestions may also have conflicts in suggestions; at this time, a suggestion judgment execution process is required. For conflicting scenarios, if the comparison information indicates that the suggestions corresponding to the first suggestion and the second suggestion conflict, the conflict content is determined; then the diagnosis party is triggered to perform at least one round of inquiry operations based on the conflict content to trigger a suggestion update process. The suggestion update process is used to trigger the second object to update the first suggestion, and / or trigger the intelligent agent to update the second suggestion. The update process is to supplement evidence based on the conflict and re-enter the diagnosis process; execute the suggestion update process until the first suggestion and the second suggestion cooperate.

[0115] Optionally, in order to avoid falling into a loop update and save diagnostic time, a stop condition can be set, that is, the number of operations corresponding to the query operations associated with the conflicting content is counted; if the number of operations reaches the query threshold, a stop instruction is output.

[0116] It can be understood that the collaborative diagnosis process in the above-mentioned different scenarios can all be carried out based on the semantic recognition of the consultation information, that is, firstly, semantic recognition is performed on the consultation information to obtain the diagnostic evidence corresponding to the first object; then, based on the diagnostic evidence, the diagnostic party is triggered to collect the debate elements in the diagnostic evidence; and then, in response to the second object and the intelligent agent, a collaborative diagnosis is performed on the debate elements to obtain diagnostic suggestions. Through the process of semantic recognition, the direct text or voice interaction between the intelligent agent and each object is facilitated, thereby improving communication efficiency.

[0117] Optionally, the above-mentioned semantic recognition process can be performed using restricted natural speech understanding, that is, firstly semantic recognition is performed on the consultation information to obtain consultation semantic data, and the consultation semantic data is marked with semantic object identifiers, that is, object separation is performed; then, based on the semantic object identifier, restricted natural speech understanding is performed on the consultation semantic data to obtain consultation semantic elements; and then diagnostic evidence corresponding to the first object is generated based on the consultation semantic elements. Performing semantic recognition through restricted natural speech understanding can improve the recognition accuracy of medical-related language.

[0118] In one possible scenario, the above-mentioned diagnostic debate stage can be conducted based on multiple dimensions, that is, the diagnostic debate stage divides the discussion of diagnosis into three dimensions: primary diagnosis, concomitant diagnosis, and secondary diagnosis, to ensure that the diagnostic discussion is comprehensive and accurate. That is, first obtain the first suggestion obtained by the second object for the diagnosis of the debate element, and the second suggestion obtained by the intelligent agent for the diagnosis of the debate element; then compare the first suggestion and the second suggestion based on the preset dimension to obtain comparison information, and the preset dimension (primary diagnosis, concomitant diagnosis, secondary diagnosis) is determined based on the correlation relationship that affects the diagnosis process; if the comparison information indicates that the first suggestion and the second suggestion correspond to the suggestion cooperation, then summarize the first suggestion and the second suggestion to obtain a diagnostic suggestion. Through multi-dimensional diagnostic considerations, the accuracy of disease diagnosis can be improved.

[0119] Optionally, due to the multi-dimensional configuration, when making conflict judgments, the unified part of the main diagnosis can be output first, that is, the diagnostic dimension corresponding to the conflicting content is determined; if the diagnostic dimension indicates a non-main diagnosis, the diagnostic recommendation is determined according to the content of the main diagnostic dimension, thereby avoiding delaying the patient's treatment time.

[0120] Therefore, combined with the above-mentioned collaborative diagnosis process based on semantic recognition, Figure 5 The interaction architecture shown, Figure 5 A technical architecture diagram of a collaborative diagnosis method provided for an embodiment of the present application; the figure shows a multi-agent human-computer interactive consultation technology framework for doctors, patients, and intelligent agents. For each round of human-computer debate interaction, the doctor and the patient first interact with the intelligent agent through voice, and after completing voice recognition and role separation, the dialogue content of each role is output; the restricted natural language understanding (natural language understanding optimized for specific fields of consultation scenarios) module performs consultation semantic understanding and debate element (key consultation elements) recognition on the consultation content, and outputs key information of doctor-patient consultation; the intelligent consultation decision-making module, after receiving the doctor-patient consultation information, integrates the multi-agent diagnosis suggestions and outputs a phased diagnosis and treatment plan; the restricted natural language generation module will perform debate strategy integration and language generation according to the consultation context and the phased diagnosis and treatment plan, and form a consultation dialogue response based on the large language generation model; after voice synthesis, a dialogue is conducted with the doctor.

[0121] Specifically, the restricted natural language understanding module and the restricted natural language generation module can be used to realize the above-mentioned restricted natural language understanding process. The restricted natural language understanding module completes the semantic understanding of doctors / patients in the consultation process and identifies the elements of consultation debate to obtain the key information of consultation for the restricted scenario of human-opportunity consultation. The restricted natural language generation module uses the language big model to integrate the debate strategy and other key information of consultation, generates natural speech, and outputs the consultation response for each round.

[0122] In addition, the output module of collaborative diagnosis is the intelligent consultation decision-making module, which uses the key information of doctor / patient consultation and the diagnostic suggestions given by multiple agents to generate and classify consultation evidence, mine debate elements, and judge debate negotiation strategies. It outputs conclusions such as disease diagnosis, examination recommendations, and treatment plans, or determines whether further debate and consultation is needed.

[0123] It can be seen from the human-computer interactive consultation technology architecture that it adopts a multi-agent system, where each agent corresponds to a professional field and collaborates with each other to integrate multi-faceted information and support more comprehensive diagnostic analysis.

[0124] Combined with the description in the above human-computer interactive consultation technical architecture, the suggestions output by the intelligent agent in this embodiment can be suggestions output by multiple intelligent agents in a coordinated manner. Figure 6 As shown, Figure 6 A scenario diagram of a collaborative diagnosis method provided in an embodiment of the present application; the figure shows the consultation decision-making process of multi-agent collaboration, that is, multiple agents work together to provide in-depth analysis of difficult symptoms and personalized treatment plan recommendations to overcome the problems of single input limitations and limited information processing capabilities. At the same time, the debate-style decision-making process can combine the professional opinions and computing capabilities of doctors, and to a certain extent, it can also reduce the risks caused by insufficient manpower.

[0125] Specifically, for the multi-agent collaborative consultation decision-making process, first determine the diagnosis cluster associated with the second object and the agent cluster associated with the agent; then obtain the third suggestion obtained by the representative object in the diagnosis cluster for the diagnosis of the debate element; and obtain the fourth suggestion obtained by the representative agent in the agent cluster for the diagnosis of the debate element; then perform collaborative diagnosis based on the third suggestion and the fourth suggestion to obtain a diagnosis suggestion.

[0126] Optionally, the intelligent agent cluster can refer to external data and historical data to output recommendations, that is, by sending debate elements to the intelligent agent cluster so that multiple agents in the intelligent agent cluster conduct consultation interaction based on the debate elements, and the consultation interaction process is carried out with reference to consultation records and knowledge databases; thereby obtaining the fourth recommendation obtained by the intelligent agent cluster after consultation interaction, thereby improving the effectiveness of the recommendation.

[0127] In addition, multi-agent diagnosis suggestions are completed by the medical consultation self-organization and self-learning module, that is, when sending diagnosis suggestions to the agent cluster, multiple agents in the agent cluster associated with the diagnosis suggestions perform knowledge iteration based on the diagnosis suggestions. That is, when a consultation request is received, the single-agent diagnosis conclusion is obtained from each agent, and organized learning is performed to output multi-agent diagnosis suggestions; single agents include image agents, medical record agents, literature agents, knowledge agents, etc., and the agents initiate data requests to the platform or hospital system according to data requirements to complete diagnostic reasoning.

[0128] Specifically, for the above-mentioned multi-agent consultation decision-making process, in the consultation decision, the multi-agent proposes and optimizes its diagnostic suggestions through a decision support framework, including the following steps:

[0129] 1. Initialize the decision support environment:

[0130] 1. Information distribution and synchronization: The central diagnosis agent is responsible for synchronizing the status of all agents and ensuring that they all have full access to the information contained in the consultation request.

[0131] 2. Data acquisition instructions are issued: For consultation tasks, the central diagnosis agent assigns data collection instructions to each agent, requiring them to obtain relevant data from specific data sources.

[0132] 2. Independent diagnostic analysis:

[0133] 1. Generation of preliminary reasoning results: Each agent uses its own data set to independently run its algorithm model to form an initial diagnostic hypothesis or conclusion.

[0134] 2. Result submission: The diagnostic conclusion is submitted to the central diagnostic agent, which is responsible for coordinating and summarizing the preliminary reasoning outputs of each agent.

[0135] 3. Start the decision optimization process:

[0136] 1. Establishment of decision-making organization framework: The central diagnostic agent establishes a decision-making organization framework, within which all agents can submit and discuss their respective diagnostic conclusions, and question or support each other.

[0137] 2. Diagnostic suggestion competition: Agents make the most powerful diagnostic suggestions based on their respective decision weights and confidence levels, and closely observe the opinions of other agents to adjust their conclusions in a timely manner.

[0138] 4. Form final decision recommendations:

[0139] 1. System evaluation and comparison: The central diagnostic agent compares and evaluates the reasoning results of each agent, considering their relative importance and reliability.

[0140] 2. Consensus decision making: Through a series of decision rules or protocols, the agents reach a consensus and form a common and stable decision proposal as the output of the consultation.

[0141] 5. System feedback and model iteration:

[0142] 1. Multi-agent decision recommendation output: The final consensus decision is presented to doctors and patients, and waits for the effect evaluation after actual application.

[0143] 2. Decision result feedback learning: Once the evaluation results of the decision effect are collected, the entire system will self-learn and adapt according to the successful diagnosis use cases, continuously adjust the key decision parameters of the intelligent agent, and optimize future decision performance.

[0144] Through this series of technical steps and decision support links, the consultation decision method enables multiple agents to imitate the expert group consultation while combining advanced computing methods to improve the accuracy and efficiency of diagnosis.

[0145] It can be seen that the consultation decision-making process of multi-agent collaboration is completed by the medical consultation self-organization and self-learning module. When a consultation request is received, the single-agent diagnosis conclusion is obtained from each agent, and organized learning is carried out to output multi-agent diagnosis suggestions; single agents include image agents, medical record agents, literature agents, knowledge agents, etc., and the agents initiate data requests to the platform or hospital system according to data requirements to complete diagnostic reasoning.

[0146] 303. Determine the execution process of the diagnostic suggestion instructions.

[0147] In this embodiment, the execution process of the diagnosis suggestion indication may include at least one of the treatment process and the inspection process, that is, only the treatment process or the inspection process may be executed, or both may be executed. Figure 4 The execution flow shown is an example and is not limiting.

[0148] Specifically, for the examination process, it is the examination / debate stage; for the treatment process, it is the treatment debate stage, that is, each debate stage can adopt the collaborative execution process of step 302. After each debate stage is modularized, the consultation is carried out according to the same judgment conditions of the diagnosis process. These steps ensure the smooth progress of the consultation process, and also ensure that the patient can get the most accurate and effective medical services.

[0149] 304. In response to the execution of the process, the diagnosis party is triggered to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion.

[0150] In this embodiment, when the execution process is the inspection process, that is, the inspection and debate stage, experts and agents from various disciplines focus on whether the primary diagnosis is clear, whether the accompanying diagnosis and secondary diagnosis are missing, and whether there are any diagnoses that affect the evaluation of subsequent treatment methods.

[0151] In addition, when the execution process is the inspection process, that is, in the treatment debate stage, experts and agents from various disciplines will express their specialist opinions on whether there are indications and contraindications for surgical treatment, interventional treatment, radiofrequency ablation, radiotherapy, chemotherapy, targeted therapy, immunotherapy, and conservative treatment. The process ensures that experts and agents from various disciplines actively share and collaborate in the debate process, achieving sufficient interactive discussions and collisions of ideas.

[0152] Specifically, for the flow of the inspection process and the treatment process, in response to the inspection process, the diagnosis party is triggered to make a collaborative judgment on the detection action generated by the inspection process to obtain the inspection conclusion; then the treatment process is triggered based on the inspection conclusion; next, in response to the treatment process, the diagnosis party is triggered to make a collaborative judgment on the treatment action generated by the treatment process to obtain the diagnosis conclusion. Among them, for the specific debate execution process, that is, the inspection suggestion judgment, that is, based on the inspection suggestions given by the doctor and the intelligent agent, it is judged whether the inspection suggestions of each party are "conflicting" or "cooperative", and then different processing processes are continued; then cooperative conflict processing is performed: if the inspection suggestions of multiple parties are cooperative (i.e. unified), the treatment process is judged, and if the diagnosis conclusion has been obtained or the process round has been exceeded, the inspection is terminated; if the suggestions of multiple parties conflict, evidence is supplemented according to the conflict, and the inspection process is entered again until the inspection conclusion is obtained or the process round has been exceeded, then the inspection is terminated. As for the judgment of treatment recommendations, that is, based on the examination recommendations given by doctors and intelligent agents, it is determined whether the examination recommendations of each party are "conflicting" or "cooperative", and then different processing procedures are continued; then cooperative conflict processing is carried out: if the examination recommendations of multiple parties are cooperative (that is, unified), the diagnosis conclusion is output.

[0153] In a possible scenario, the interaction process between the above-mentioned intelligent agent and doctors and patients can be displayed using an interface, such as a smart medical consultation platform; that is, first obtain the interaction data generated by the intelligent agent during the interaction process; then generate multimedia content based on the interaction data, such as voice, text, image or animation, etc.; and present the multimedia content in the interactive interface. Figure 7 In the scenario shown, Figure 7A scene diagram of another collaborative diagnosis method provided for an embodiment of the present application; doctors and patients interact with intelligent agents through voice, and after completing voice recognition and role separation, the dialogue content of each role is output. This can trigger the natural language understanding module to conduct consultation semantic understanding and debate elements on the consultation content, and output key information of the doctor-patient consultation; the intelligent consultation decision module, after receiving the doctor-patient consultation information, integrates the multi-agent diagnosis suggestions and outputs a phased diagnosis and treatment plan; the natural language generation module will perform debate strategy integration and language generation based on the consultation context and the phased diagnosis and treatment plan, and form a consultation dialogue response based on the large language generation model; after voice synthesis, a dialogue is conducted with the doctor.

[0154] This embodiment enhances the quality of medical decision-making through a debate-style interactive process involving three parties (doctors, patients, and agents), mutual collaboration among agents corresponding to professional fields, and a process in which multiple agents provide in-depth analysis of difficult diagnoses and personalized treatment recommendations. That is, through the professional knowledge and data analysis capabilities of multiple agents, doctors are assisted in making more accurate and comprehensive medical decisions. Real-time collaboration and data fusion are achieved, that is, agents can share information and reasoning results on a real-time basis, conduct efficient data fusion and collaborative analysis, and strengthen the process of formulating diagnosis and treatment plans. Patient participation is also improved, that is, the debate-style interaction mode gives patients the opportunity to better understand their health conditions and treatment options, and improves their sense of participation and satisfaction when making decisions. Resource efficiency is improved, that is, agents can help simplify and accelerate the diagnosis process, relieve the workload of doctors, and improve the efficiency of diagnosis and treatment. The risk of misdiagnosis and missed diagnosis is also reduced, that is, by combining the knowledge and analytical power of multiple agents, the risk of misdiagnosis and missed diagnosis that may be caused by relying on the judgment of a single doctor can be reduced. It is also explainable and transparent, that is, the debate-style framework can display the decision-making basis of different agents, provide doctors and patients with a more transparent decision-making process and logic, and enhance explainability.

[0155] In combination with the above embodiments, it can be known that by obtaining the consultation information associated with the first object; then triggering the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, the diagnosis party includes a second object and an intelligent agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the intelligent agent for the consultation information; and determining the execution process indicated by the diagnosis suggestion; and then in response to the execution process, triggering the diagnosis party to perform collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion. In this way, a collaborative diagnosis process of multi-party interaction is realized, and through the collaborative work of intelligent agents, an in-depth analysis of difficult symptoms and personalized treatment plan suggestions are provided to overcome the problems of single input limitations and limited information processing capabilities, thereby improving the accuracy of the diagnosis process.

[0156] In order to better implement the above solution of the embodiment of the present application, the following also provides related devices for implementing the above solution. Figure 8 , Figure 8 The schematic diagram of the structure of a collaborative diagnosis device provided in an embodiment of the present application is as follows. The collaborative diagnosis device 800 includes:

[0157] An acquisition unit 801 is used to acquire consultation information associated with a first object;

[0158] A diagnosis unit 802 is used to trigger a diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, wherein the diagnosis party includes a second object and an agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the agent with respect to the consultation information;

[0159] The diagnosis unit 802 is further used to determine the execution process of the diagnosis suggestion indication;

[0160] The diagnosis unit 802 is further configured to trigger the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process in response to the execution of the execution process, so as to obtain a diagnosis conclusion.

[0161] Optionally, in a possible implementation, the diagnosis unit 802 is used to perform semantic recognition on the consultation information to obtain diagnostic evidence corresponding to the first object when the diagnosis party is triggered to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnostic suggestions; based on the diagnosis evidence, the diagnosis party is triggered to collect debate elements in the diagnosis evidence; and in response to the second object and the agent performing collaborative diagnosis on the debate elements, obtain the diagnostic suggestions.

[0162] Optionally, in a possible implementation, the diagnosis unit 802 is used to perform semantic recognition on the consultation information to obtain consultation semantic data when performing semantic recognition on the consultation information to obtain diagnostic evidence corresponding to the first object, and the consultation semantic data is marked with a semantic object identifier; perform restricted natural speech understanding on the consultation semantic data based on the semantic object identifier to obtain consultation semantic elements; and generate diagnostic evidence corresponding to the first object based on the consultation semantic elements.

[0163] Optionally, in a possible implementation, the diagnosis unit 802 is used to obtain a first suggestion obtained by the second object for diagnosing the debate element and a second suggestion obtained by the agent for diagnosing the debate element in response to the second object and the agent performing a collaborative diagnosis on the debate element to obtain the diagnosis suggestion; compare the first suggestion and the second suggestion based on a preset dimension to obtain comparison information, wherein the preset dimension is determined based on a correlation relationship that has an impact on the diagnosis process; if the comparison information indicates that the suggestions corresponding to the first suggestion and the second suggestion cooperate, the first suggestion and the second suggestion are summarized to obtain the diagnosis suggestion.

[0164] Optionally, in a possible implementation, the diagnosis unit 802 is further used to determine the conflict content if the comparison information indicates that the suggestions corresponding to the first suggestion and the second suggestion conflict; trigger the diagnosis party to perform at least one round of inquiry operations based on the conflict content to trigger a suggestion update process, the suggestion update process is used to trigger the second object to update the first suggestion, and / or trigger the agent to update the second suggestion; execute the suggestion update process until the first suggestion and the second suggestion cooperate.

[0165] Optionally, in a possible implementation, the diagnosis unit 802 is further configured to count the number of operations corresponding to the query operation associated with the conflicting content; if the number of operations reaches a query threshold, a stop instruction is output.

[0166] Optionally, in a possible implementation, the diagnosis unit 802 is further used to determine a diagnosis dimension corresponding to the conflicting content; if the diagnosis dimension indicates a non-primary diagnosis, the diagnosis suggestion is determined according to the content of the primary diagnosis dimension.

[0167] Optionally, in a possible implementation, the diagnosis unit 802 is used to determine the diagnosis cluster associated with the second object and the agent cluster associated with the agent when the diagnosis suggestion is obtained in response to the second object and the agent performing a collaborative diagnosis on the debate element; obtain a third suggestion obtained by the representative object in the diagnosis cluster performing a diagnosis on the debate element; obtain a fourth suggestion obtained by the representative agent in the agent cluster performing a diagnosis on the debate element; and perform a collaborative diagnosis based on the third suggestion and the fourth suggestion to obtain the diagnosis suggestion.

[0168] Optionally, in a possible implementation, the diagnosis unit 802 is used to send the debate element to the agent cluster when obtaining the fourth suggestion obtained by the representative agent in the agent cluster for diagnosing the debate element, so that multiple agents in the agent cluster conduct consultation interaction based on the debate element, and the consultation interaction process is performed with reference to the consultation record and the knowledge database; and obtain the fourth suggestion obtained by the agent cluster after the consultation interaction.

[0169] Optionally, in a possible implementation, the diagnosis unit 802 is further used to send the diagnosis suggestion to the agent cluster, so that multiple agents in the agent cluster associated with the diagnosis suggestion perform knowledge iteration based on the diagnosis suggestion.

[0170] Optionally, in a possible implementation, the acquisition unit 801 is used to obtain medical record information associated with the first object when obtaining consultation information associated with the first object; determine preset data conditions and data requirement conditions corresponding to the agent; match the medical record information based on the preset data conditions and the data requirement conditions; if the medical record information matches the preset data conditions and the data requirement conditions, generate the consultation information based on the medical record information.

[0171] Optionally, in a possible implementation, the diagnostic unit 802 is used to trigger the diagnostic party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process in response to the execution of the execution process to obtain a diagnosis conclusion; in response to the implementation of the inspection process, trigger the diagnostic party to make a collaborative judgment on the detection actions generated by the inspection process to obtain an inspection conclusion; trigger the treatment process based on the inspection conclusion; in response to the implementation of the treatment process, trigger the diagnostic party to make a collaborative judgment on the treatment actions generated by the treatment process to obtain the diagnosis conclusion.

[0172] Optionally, in a possible implementation, it is characterized in that the diagnostic unit 802 is also used to obtain interaction data generated by the intelligent agent during the interaction process; generate multimedia content based on the interaction data; and present the multimedia content in the interaction interface.

[0173] By obtaining the consultation information associated with the first object; then triggering the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, the diagnosis party includes a second object and an intelligent agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the intelligent agent for the consultation information; and determining the execution process indicated by the diagnosis suggestion; and then in response to the execution process, triggering the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion. In this way, a collaborative diagnosis process of multi-party interaction is realized, and through the collaborative work of intelligent agents, an in-depth analysis of difficult symptoms and personalized treatment plan suggestions are provided to overcome the problems of single input limitations and limited information processing capabilities, thereby improving the accuracy of the diagnosis process.

[0174] The collaborative diagnosis device provided in this embodiment belongs to the same application concept as the method provided in the above embodiments of this application, can execute the collaborative diagnosis method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the collaborative diagnosis method. For technical details not fully described in this embodiment, please refer to the specific processing content of the collaborative diagnosis method provided in the above embodiments of this application, and will not be repeated here.

[0175] The functions implemented by the above acquisition unit 801 and diagnosis unit 802 may be implemented by the same or different processors, respectively, and are not limited in the embodiment of the present application.

[0176] It should be understood that each unit in the above device can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the unit in the device can be implemented in the form of a hardware circuit, and the functions of some or all units can be realized by designing the hardware circuit. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all units above are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of some or all units above. All units of the above device can be implemented in the form of a processor calling software, or in the form of a hardware circuit, or in the form of a processor calling software, and the remaining part can be implemented in the form of a hardware circuit.

[0177] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0178] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0179] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0180] The embodiment of the present application also provides a collaborative diagnosis device; the collaborative diagnosis device includes a processor and an input-output component. The input-output component is used to obtain consultation information;

[0181] The processor is used to output the diagnosis conclusion corresponding to the consultation information obtained by the input-output component by executing any one of the collaborative diagnosis methods in the above embodiments.

[0182] The above-mentioned interface circuit can be any interface circuit that can realize the data communication function, for example, it can be a USB interface circuit, a Type-C interface circuit, a serial port circuit, a PCIE circuit, etc.

[0183] Optionally, the embodiment of the present application further provides a system, wherein the interactive client is used to obtain consultation information and send the consultation information to the server, and to display the collaborative diagnosis result output by the server;

[0184] The server is used to output the diagnosis conclusion corresponding to the consultation information obtained by the interactive client by executing the collaborative diagnosis method described in any one of the above embodiments.

[0185] Another embodiment of the present application also provides a collaborative diagnosis device, see Fig. 9 As shown, the device includes:

[0186] Memory 900 and processor 910;

[0187] The memory 900 is connected to the processor 910 and is used to store programs;

[0188] The processor 910 is used to implement the collaborative diagnosis method disclosed in any of the above embodiments by running the program stored in the memory 900.

[0189] Specifically, the collaborative diagnosis device may further include: a bus, a communication interface 920 , an input device 930 and an output device 940 .

[0190] The processor 910, the memory 900, the communication interface 920, the input device 930 and the output device 940 are connected to each other via a bus.

[0191] A bus may include a pathway that transfers information between components of a computer system.

[0192] The processor 910 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0193] The processor 910 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0194] The memory 900 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 900 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0195] The input device 930 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0196] Output device 940 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0197] The communication interface 920 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0198] The processor 910 executes the program stored in the memory 900 and calls other devices, which can be used to implement each step of any collaborative diagnosis method provided in the above embodiments of the present application.

[0199] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the collaborative diagnosis method according to various embodiments of the present application described in any of the above-mentioned embodiments of this specification.

[0200] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0201] In addition, the embodiment of the present application may also be a storage medium on which a computer program is stored. The computer program is executed by a processor to execute the steps of the collaborative diagnosis method according to various embodiments of the present application described in any of the above embodiments of this specification, and specifically the following steps may be implemented:

[0202] Obtaining consultation information associated with the first object;

[0203] triggering a diagnostic party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnostic suggestions, the diagnostic party comprising a second object and an intelligent agent, the diagnostic suggestions being obtained based on the interaction between the second object and the intelligent agent with respect to the consultation information;

[0204] Determining the execution process of the diagnostic suggestion indication;

[0205] In response to the execution of the process, the diagnostic party is triggered to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion.

[0206] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0207] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0208] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0209] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0210] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0211] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0212] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0213] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0214] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0215] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0216] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A collaborative diagnosis method, characterized in that: include: Obtaining consultation information associated with the first object; triggering a diagnostic party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnostic suggestions, the diagnostic party comprising a second object and an intelligent agent, the diagnostic suggestions being obtained based on the interaction between the second object and the intelligent agent with respect to the consultation information; Determining the execution process of the diagnostic suggestion indication; In response to the execution of the process, the diagnostic party is triggered to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion.

2. The method according to claim 1, characterized in that The triggering of the diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain diagnosis suggestions includes: Performing semantic recognition on the consultation information to obtain diagnostic evidence corresponding to the first object; Triggering the diagnosing party to collect debate elements in the diagnostic evidence based on the diagnostic evidence; In response to the second object and the intelligent agent performing a collaborative diagnosis on the debate element, the diagnosis suggestion is obtained.

3. The method according to claim 2, characterized in that The performing semantic recognition on the consultation information to obtain diagnosis evidence corresponding to the first object includes: Performing semantic recognition on the consultation information to obtain consultation semantic data, wherein the consultation semantic data is marked with a semantic object identifier; Based on the semantic object identifier, the consultation semantic data is subjected to restricted natural speech understanding to obtain consultation semantic elements; Generate diagnostic evidence corresponding to the first object according to the consultation semantic elements.

4. The method according to claim 2, characterized in that: The step of obtaining the diagnosis suggestion in response to the second object and the intelligent agent performing collaborative diagnosis on the debate element comprises: Obtaining a first suggestion obtained by the second object through diagnosis of the debate element, and a second suggestion obtained by the agent through diagnosis of the debate element; Comparing the first suggestion and the second suggestion based on a preset dimension to obtain comparison information, wherein the preset dimension is determined based on an association relationship that has an impact in a diagnosis process; If the comparison information indicates that the first suggestion and the second suggestion correspond to cooperation, the first suggestion and the second suggestion are summarized to obtain the diagnosis suggestion.

5. The method according to claim 4, characterized in that The method further comprises: If the comparison information indicates that the first suggestion and the second suggestion correspond to conflicting suggestions, determining conflicting content; Triggering the diagnosis party to perform at least one round of inquiry operation based on the conflict content to trigger a suggestion update process, wherein the suggestion update process is used to trigger the second object to update the first suggestion and / or trigger the agent to update the second suggestion; The suggestion updating process is performed until the first suggestion and the second suggestion cooperate.

6. The method according to claim 5, characterized in that The method further comprises: Counting the number of operations corresponding to the query operations associated with the conflicting content; If the number of operations reaches the inquiry threshold, a stop instruction is output.

7. The method according to claim 6, characterized in that The method further comprises: Determining a diagnostic dimension corresponding to the conflict content; If the diagnostic dimension indicates a non-primary diagnosis, the diagnostic recommendation is determined according to the content of the primary diagnostic dimension.

8. The method according to claim 2, characterized in that: The step of obtaining the diagnosis suggestion in response to the second object and the intelligent agent performing collaborative diagnosis on the debate element comprises: determining a diagnosis cluster associated with the second object, and an agent cluster associated with the agent; Obtaining a third suggestion obtained by diagnosing the debate element by the representative object in the diagnosis cluster; Obtaining a fourth suggestion obtained by a representative intelligent agent in the intelligent agent cluster through diagnosis of the debate element; A collaborative diagnosis is performed based on the third suggestion and the fourth suggestion to obtain the diagnosis suggestion.

9. The method according to claim 8, characterized in that The obtaining of a fourth suggestion obtained by the representative agent in the agent cluster through diagnosis of the debate element comprises: Sending the debate elements to the agent cluster so that multiple agents in the agent cluster conduct consultation interaction based on the debate elements, wherein the consultation interaction process is performed with reference to consultation records and a knowledge database; Obtain the fourth suggestion obtained by the agent cluster through the consultation interaction.

10. The method according to claim 8, characterized in that The method further comprises: The diagnosis suggestion is sent to the agent cluster, so that a plurality of agents in the agent cluster associated with the diagnosis suggestion perform knowledge iteration based on the diagnosis suggestion.

11. The method according to claim 1, characterized in that The obtaining of consultation information associated with the first object includes: Obtaining medical record information associated with the first object; Determine the preset data conditions and the data requirement conditions corresponding to the intelligent agent; Matching the medical record information based on the preset data condition and the data requirement condition; If the medical record information matches the preset data condition and the data requirement condition, the consultation information is generated based on the medical record information.

12. The method according to claim 1, characterized in that The execution process includes an inspection process and a treatment process, and the response to the execution process triggers the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process to obtain a diagnosis conclusion, including: In response to the inspection process being carried out, triggering the diagnostic party to make a collaborative judgment on the detection actions generated by the inspection process to obtain an inspection conclusion; triggering the treatment process based on the examination conclusion; In response to the progress of the treatment process, the diagnostic party is triggered to make a collaborative judgment on the treatment actions generated by the treatment process to obtain the diagnosis conclusion.

13. The method according to any one of claims 1 to 12, characterized in that: The method further comprises: Obtain the interaction data generated by the agent during the interaction process; generating multimedia content based on the interaction data; The multimedia content is presented in an interactive interface.

14. A collaborative diagnostic device, characterized in that: include: An acquisition unit, configured to acquire consultation information associated with the first object; A diagnosis unit, configured to trigger a diagnosis party to perform collaborative diagnosis on the consultation information based on the consultation information to obtain a diagnosis suggestion, wherein the diagnosis party includes a second object and an agent, and the diagnosis suggestion is obtained based on the interaction between the second object and the agent with respect to the consultation information; The diagnostic unit is further used to determine the execution process of the diagnostic suggestion indication; The diagnosis unit is also used to trigger the diagnosis party to make a collaborative judgment on the diagnosis and treatment actions generated by the execution process in response to the execution of the execution process to obtain a diagnosis conclusion.

15. A collaborative diagnostic device comprising an input-output component and a processor; The input and output components are used to obtain consultation information; The processor is used to output a diagnosis conclusion corresponding to the consultation information obtained by the input and output component by executing the collaborative diagnosis method as described in any one of claims 1 to 13.

16. A collaborative diagnosis system, comprising an interactive client and a server; The interactive client is used to obtain consultation information and send the consultation information to the server, and to display the collaborative diagnosis results output by the server; The server is used to output the diagnosis conclusion corresponding to the consultation information obtained by the interactive client by executing the collaborative diagnosis method described in any one of claims 1 to 13.

17. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the collaborative diagnosis method according to any one of claims 1 to 13 is implemented.

Images