Interrogation request distribution processing method and device, equipment and medium

Abstract

The invention relates to the field of medical data management, and discloses an inquiry request distribution processing method and device, equipment and a medium, and the method comprises the steps: obtaining an inquiry request queue inputted into a target data processor, and dividing the inquiry request queue into a first type of inquiry requests from an upstream processor and a second type of inquiry requests from an external data node; calculating the cost amount required for processing the first type of inquiry requests and the second type of inquiry requests; querying resource bearing capacity balances of the target data processor and a downstream processor of the target data processor; the first type of inquiry requests are distributed to the target data processor according to the bearing capacity balance and the cost amount, the second type of inquiry requests are distributed in the target data processor and the downstream processor, the requests to be responded are classified according to sources, and the requests to be responded from different sources are distributed in corresponding modes, so that the inquiry efficiency is improved. Multiple times of downward distribution in the tree processor cluster are avoided, and the processor receiving the inquiry request initially and the user sending the inquiry request can be traced conveniently.

Description

Technical Field

[0001] The present application relates to the field of medical data management, and in particular to a method, device, equipment and medium for allocating and processing consultation requests. Background Art

[0002] With the booming development of intelligent medical consultation, users have begun to accept inputting medical consultation requests to trained AI agents to obtain corresponding diagnostic suggestions. Some of these AI agents are configured in a distributed manner in some or all processors of a tree processor cluster.

[0003] The existing tree-shaped processor cluster has a clear hierarchical structure. The upstream processor can distribute the received consultation requests to the downstream processor to improve the processing speed of batch consultation requests. However, for the multi-level tree-shaped processor cluster, after multiple downward distributions, there will be a problem of difficulty in tracing the consultation requests and diagnosis suggestions, that is, it is difficult to determine the processor that initially received the consultation request and the user who issued the consultation request. In addition, too many downward distributions will also leak the user's privacy, which has a certain risk of information leakage. Summary of the invention

[0004] The embodiment of the present invention provides a method, apparatus, device and medium for distributing and processing a consultation request, aiming to avoid multiple downward allocations in a tree-shaped processor cluster, so as to facilitate tracing back the processor that initially receives the consultation request and the user that issues the consultation request.

[0005] In a first aspect, an embodiment of the present invention provides a method for allocating and processing medical consultation requests, comprising:

[0006] Obtaining a medical consultation request queue input into a target data processor, wherein the waiting medical consultation request queue includes a batch of waiting medical consultation requests, and the target data processor is at least one processor in a tree-like processor cluster;

[0007] The unanswered consultation requests are divided into the first type of consultation requests and the second type of consultation requests, wherein the first type of consultation requests are consultation requests sent by the upstream processor of the target data processor to the target data processor, and the second type of consultation requests are consultation requests sent by the data node outside the tree processor cluster to the target processor;

[0008] Calculating a first resource cost amount required to process a first type of medical consultation request and a second resource cost amount required to process a second type of medical consultation request;

[0009] Querying a first resource carrying capacity balance of a target data processor and a second resource carrying capacity balance of a downstream processor of the target data processor;

[0010] Allocating at least part of the first-category medical consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first-category medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed;

[0011] The second type of medical consultation requests are distributed among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

[0012] In some implementations, allocating the second type of medical consultation request among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount includes:

[0013] Determine a current third resource carrying capacity balance of the target data processor according to the first resource carrying capacity balance and the first resource cost amount;

[0014] The second type of medical consultation requests are distributed among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost.

[0015] In some implementations, allocating the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance, and the second resource cost includes:

[0016] When the balance of the third resource carrying capacity is greater than the first balance threshold, selecting a first sub-inquiry request from the second type of inquiry request and allocating it to the target data processor according to the balance of the third resource carrying capacity;

[0017] Determine the sub-bearing capacity balances corresponding to the plurality of downstream processors and the matching consultation type according to the second resource bearing capacity balance;

[0018] The remaining second sub-query requests in the second type of query request are allocated to each downstream processor according to the sub-load balance of each downstream processor and the matching query type.

[0019] In some implementations, allocating remaining second sub-query requests in the second type of query request to each downstream processor according to the sub-capacity balance of each downstream processor and the matching query type includes:

[0020] Sort each downstream processor according to the corresponding sub-capacity balance;

[0021] Matching the inquiry request type of the second sub-inquiry request with the matching inquiry type of the downstream processor, and determining at least one server to be selected from the downstream processor;

[0022] The second sub-query requests with the same type of the consultation request are successively allocated to each of the servers to be selected according to the sorting result.

[0023] In some implementations, the second sub-inquiry requests of the same inquiry request type are successively allocated to each of the candidate servers according to the sorting result, including:

[0024] Allocating at least one second sub-query request to the first candidate server until the sub-bearing capacity balance of the first candidate server is less than a second balance threshold;

[0025] The remaining second sub-query requests are allocated to the second candidate server ranked after the first candidate server until the sub-load balance of the first candidate server is less than the third balance threshold.

[0026] In some implementations, allocating the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance, and the second resource cost amount further includes:

[0027] When the third resource carrying capacity balance is less than or equal to the first balance threshold, determining sub-carrying capacity balances corresponding to the plurality of downstream processors and matching consultation types respectively according to the second resource carrying capacity balance;

[0028] The second type of consultation request is allocated to each downstream processor according to the sub-capacity balance of each downstream processor and the matching consultation type.

[0029] In some embodiments, the method further comprises:

[0030] Sending the unallocated first-category consultation requests back to the upstream server;

[0031] or,

[0032] Establish a candidate consultation queue, and temporarily store some unassigned first-category consultation requests in the candidate consultation queue;

[0033] The real-time resource carrying capacity balance of the target data processor is periodically monitored, and when the real-time resource carrying capacity balance is greater than a fourth balance threshold, at least part of the first type of consultation requests temporarily stored in the candidate consultation queue is allocated to the target data processor.

[0034] In a second aspect, an embodiment of the present invention further provides a medical consultation request allocation processing device, comprising:

[0035] A request receiving module, used for obtaining a consultation request queue input into a target data processor, wherein the consultation request queue to be answered includes a batch of consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster;

[0036] A consultation classification module is used to classify the consultation requests to be answered into first-class consultation requests and second-class consultation requests, wherein the first-class consultation requests are consultation requests sent by the upstream processor of the target data processor to the target data processor, and the second-class consultation requests are consultation requests sent by the data node outside the tree processor cluster to the target processor;

[0037] A cost calculation module, used for calculating a first resource cost amount required for processing a first type of medical consultation request and a second resource cost amount required for processing a second type of medical consultation request;

[0038] A balance query module, used to query the first resource carrying capacity balance of the target data processor and the second resource carrying capacity balance of the downstream processor of the target data processor;

[0039] A first allocation module, configured to allocate at least part of the first type of medical consultation requests to a target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first type of medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed;

[0040] The second allocation module is used to allocate the second type of medical consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount and the second resource cost amount.

[0041] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising a memory and a processor;

[0042] Memory for storing computer programs;

[0043] A processor is used to execute a computer program and implement any one of the methods for allocating and processing medical consultation requests provided in the embodiments of this specification when executing the computer program.

[0044] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements any one of the consultation request allocation and processing methods provided in the embodiments of this specification.

[0045] An embodiment of the present invention provides a method, apparatus, computer device and computer-readable storage medium for allocating and processing medical consultation requests, wherein the method for allocating and processing medical consultation requests comprises: obtaining a medical consultation request queue input into a target data processor, wherein the medical consultation request queue to be answered comprises a batch of medical consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster; dividing the medical consultation requests to be answered into a first category of medical consultation requests and a second category of medical consultation requests, wherein the first category of medical consultation requests are medical consultation requests sent by an upstream processor of the target data processor to the target data processor, and the second category of medical consultation requests are medical consultation requests sent by a data node outside the tree-like processor cluster to the target processor; calculating a first resource cost amount required to process the first category of medical consultation requests and a second resource cost amount required to process the second category of medical consultation requests; querying the first resource carrying capacity surplus of the target data processor the balance of the first resource carrying capacity and the balance of the second resource carrying capacity of the downstream processor of the target data processor; allocating at least part of the first type of consultation requests to the target data processor according to the balance of the first resource carrying capacity and the first resource cost amount, so that the target data processor processes the first type of consultation requests and feeds back the processing results to the upstream processor after the processing is completed; allocating the second type of consultation requests among the target data processor and the downstream processor according to the balance of the first resource carrying capacity, the balance of the second resource carrying capacity, the first resource cost amount and the second resource cost amount, classifying the pending requests received by the target data processor according to their sources, and allocating the pending requests from different sources in a corresponding manner, thereby avoiding multiple downward allocations in the tree-shaped processor cluster, facilitating the tracing of the processor that initially receives the consultation request and the user who issues the consultation request, and improving information security. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 It is a schematic diagram of the steps of a method for allocating and processing medical consultation requests provided by one embodiment of the present invention;

[0048] Figure 2 A schematic diagram of the structure of a tree-like processor cluster provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of allocating first-category medical consultation requests and second-category medical consultation requests to a target data processor in a tree-like processor cluster provided by an embodiment of the present invention;

[0050] Figure 4 yes Figure 1 A flowchart of steps for allocating the second type of medical consultation requests in the medical consultation request allocation processing method;

[0051] Figure 5 yes Figure 4 A flowchart of steps for allocating the second type of medical consultation requests based on the third resource carrying capacity balance in the allocation of the second type of medical consultation requests;

[0052] Figure 6 A schematic diagram of the module structure of a medical consultation request allocation and processing device provided by an embodiment of the present invention;

[0053] Figure 7 A schematic block diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0056] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0057] It should be further understood that the term “and / or” used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] With the booming development of intelligent medical consultation, users have begun to accept inputting medical consultation requests to trained AI agents to obtain corresponding diagnostic suggestions. Some of these AI agents are configured in a distributed manner in some or all processors of a tree processor cluster.

[0059] The existing tree-shaped processor cluster has a clear hierarchical structure. The upstream processor can distribute the received consultation requests to the downstream processor to improve the processing speed of batch consultation requests. However, for the multi-level tree-shaped processor cluster, after multiple downward distributions, there will be a problem of difficulty in tracing the consultation requests and diagnosis suggestions, that is, it is difficult to determine the processor that initially received the consultation request and the user who issued the consultation request. In addition, too many downward distributions will also leak the user's privacy, which has a certain risk of information leakage.

[0060] Based on this, the embodiment of the present invention provides a method, device, computer equipment and computer-readable storage medium for distributing and processing medical consultation requests, aiming to avoid multiple downward allocations in a tree-shaped processor cluster, so as to facilitate tracing back to the processor that initially received the medical consultation request and the user who issued the medical consultation request. The medical consultation request distribution and processing method can be applied to the target data processor in the tree-shaped processor cluster and / or the control terminal connected to the target data processor in communication, and the control terminal can be a computer, an intelligent robot, an independent manager or a manager cluster and other electronic devices, which are not limited here.

[0061] In this embodiment, the method for distributing and processing medical consultation requests is described by taking the application of the method for distributing and processing medical consultation requests to a control terminal connected to a target data processing communication as an example, but the method for distributing and processing medical consultation requests is not limited to being applied to a control terminal connected to a target data processing communication.

[0062] Some implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings. The following embodiments and features in the embodiments may be combined with each other unless there is any conflict.

[0063] See also Figure 1 , Figure 1 The present invention provides a flowchart showing the steps of a method for allocating and processing medical consultation requests, which specifically includes the following steps 1 to 7.

[0064] Step S1, obtaining a consultation request queue input into a target data processor, wherein the consultation request queue to be answered includes a batch of consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster.

[0065] Specifically, the target data processor of the control terminal executing the method establishes a consultation request queue corresponding to the target data processor, so as to temporarily store and arrange the consultation requests to be answered input to the target data processor through the consultation request queue.

[0066] See also Figure 2 , Figure 2 A schematic diagram of the structure of a tree-like processor cluster provided by an embodiment of the present invention.

[0067] It should be noted that the trained AI agent or other response model is distributedly configured in some or all processors in the tree-like processor cluster, and the target data processor is a processor configured with an AI agent or other response model. The target data processor can respond to the input consultation request to be answered through the configured AI agent or response model to generate a processing result corresponding to the consultation request to be answered.

[0068] The tree-shaped processor cluster has a clear hierarchical structure, and a communication connection is formed between the upstream and downstream processors. The relatively upstream processor can assign the received consultation requests to the relatively downstream processor. The user can send a consultation request to any processor in the tree-shaped processor cluster. Therefore, for the target data processor, the consultation requests it receives to be answered include both consultation requests sent directly to itself by the user and consultation requests sent by the user to the upstream processor and assigned downward by the upstream processor.

[0069] For example, Figure 2 In the figure, the tree-like processor cluster includes processor A1, processor B1, processor B2, processor C1, processor C2, processor C3, and processor C4. Taking processor B1 as the target data processor as an example, processor A1 is the upstream processor of the target data processor, and processor C1, processor C2, processor C3, and processor C4 are the downstream processors of the target data processor.

[0070] Step S2, classify the inquiry requests to be answered into first-category inquiry requests and second-category inquiry requests, wherein the first-category inquiry requests are inquiry requests sent by the upstream processor of the target data processor to the target data processor, and the second-category inquiry requests are inquiry requests sent by the data nodes outside the tree-like processor cluster to the target processor.

[0071] Exemplarily, the data node outside the tree-shaped processor cluster may refer to an operation terminal used by a user, and the user may send a consultation request to the target processor by operating the operation terminal.

[0072] Specifically, based on the source of the unanswered request, including the user directly operating the corresponding operation terminal to send it to the target data processor, and the downward distribution by the upstream processor, the unanswered consultation requests can be divided into first-category consultation requests and second-category consultation requests according to the source of the unanswered request.

[0073] Specifically, the number of the first-category medical consultation requests is not limited, and can be 0 (ie, no first-category medical consultation requests) or at least one, and the same is true for the second-category medical consultation requests.

[0074] Step S3: Calculate the first resource cost required for processing the first type of medical consultation requests and the second resource cost required for processing the second type of medical consultation requests.

[0075] It should be noted that the first resource cost refers to the estimated memory usage for processing all first-category medical consultation requests, and the second resource cost refers to the estimated memory usage for processing all second-category medical consultation requests. Specifically, based on the AI ​​agent or other response model, some or all processors in the tree-like processor cluster are distributedly configured. When these processors respond to and process the first and second-category medical consultation requests, they need to occupy certain resources from the processor memory for processing.

[0076] It should be understood that, considering that the models of different processor configurations in the tree-like processor cluster are not necessarily the same, and the memory occupied by them for responding to the same consultation request is not necessarily the same, the first resource cost required to process the first type of consultation request can be calculated by averaging the memory occupied by at least part of the processors in the tree-like processor cluster to obtain the first resource cost, and the calculation of the second resource cost is similar.

[0077] Step S4: query the first resource carrying capacity balance of the target data processor and the second resource carrying capacity balance of the downstream processor of the target data processor.

[0078] Specifically, the first resource carrying capacity balance is the remaining memory amount of the target data processor that can be occupied for response processing in the current state, and the second resource carrying capacity balance is the remaining memory amount of the downstream processor that can be occupied for response processing in the current state.

[0079] The query of the second resource carrying capacity balance may be performed by the target data processor sending a query request to the downstream processor, so that the downstream processor calculates the second resource carrying capacity balance and feeds back the balance to the target data processor.

[0080] Step S5: allocate at least part of the first type of medical consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first type of medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed.

[0081] See also Figure 3 , Figure 3 A schematic diagram of allocating first-category medical consultation requests and second-category medical consultation requests to a target data processor in a tree-like processor cluster provided by an embodiment of the present invention.

[0082] Specifically, when the balance of the first resource carrying capacity is greater than or equal to the first resource cost, all first-class medical consultation requests are allocated to the target data processor, and when the balance of the first resource carrying capacity is less than the first resource cost, a part of the first-class medical consultation requests are first allocated to the target data processor, and the other part of the first-class medical consultation requests are not allocated for the time being.

[0083] It should be understood that based on the first type of inquiry request being an inquiry request sent by the upstream processor of the target data processor to the target data processor, the response processing of the first type of inquiry request is limited to the target data processor, and is not further allocated to the downstream processor. This can avoid multiple downward allocations in the tree-shaped processor cluster, facilitate the tracing of the processor that initially received the inquiry request and the user who issued the inquiry request, and improve information security.

[0084] In some embodiments, the method further comprises:

[0085] The unassigned portion of the first-class consultation requests is sent back to the upstream server.

[0086] It should be understood that when the balance of the first resource carrying capacity is less than the first resource cost, there may be a situation where the target data processor cannot fully respond to and process all first-class consultation requests. For the unallocated first-class consultation requests, the control terminal executing this method can instruct the target data processor to return them to the upstream server for queueing and temporary storage or to be re-queued by the upstream server.

[0087] In some embodiments, the method further comprises:

[0088] Establish a candidate consultation queue, and temporarily store some unassigned first-category consultation requests in the candidate consultation queue;

[0089] The real-time resource carrying capacity balance of the target data processor is periodically monitored, and when the real-time resource carrying capacity balance is greater than a fourth balance threshold, at least part of the first type of consultation requests temporarily stored in the candidate consultation queue is allocated to the target data processor.

[0090] Specifically, a candidate consultation queue is established inside or outside the target data processor, and some of the unallocated first-category consultation requests are temporarily stored in the candidate consultation queue. If the real-time resource carrying capacity balance of the target data processor is greater than the fourth balance threshold, indicating that the memory of the target data processor can be used to process new consultation requests, the real-time resource carrying capacity balance of the target data processor can be periodically monitored, and at least some of the first-category consultation requests temporarily stored in the candidate consultation queue can be allocated to the target data processor according to the real-time resource carrying capacity balance.

[0091] Step S6: Allocate the second type of medical consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

[0092] See also Figure 4 , Figure 4 yes Figure 1A flowchart showing the steps of allocating the second type of medical consultation requests in the medical consultation request allocation processing method.

[0093] like Figure 4 As shown, in some implementations, in step S6, the second type of medical consultation request is allocated among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount, including steps S61-S62:

[0094] Step S61, determining a current third resource carrying capacity balance of the target data processor according to the first resource carrying capacity balance and the first resource cost;

[0095] Step S62: Allocate the second type of medical consultation requests among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost.

[0096] Specifically, the first resource carrying capacity balance and the first resource cost amount may be used to determine: the third resource carrying capacity balance remaining in the target data processor after at least part of the first type of medical consultation requests are allocated to the target data processor in step S5.

[0097] Then, based on the size of the third resource carrying capacity balance, different strategies can be adopted to allocate the second type of consultation requests according to the second resource carrying capacity balance and the second resource cost. This can be to allocate part of the second type of consultation requests to the downstream processor and allocate part of the second type of consultation requests to the target data processor; or all of the second type of consultation requests can be allocated to the downstream processor.

[0098] See also Figure 5 , Figure 5 yes Figure 4 A flowchart showing the steps of allocating the second type of medical consultation requests based on the remaining amount of the third resource carrying capacity in the allocation of the second type of medical consultation requests.

[0099] like Figure 5 As shown, in some implementations, in step S62, the second type of consultation request is allocated among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost, including:

[0100] Step S621: when the balance of the third resource carrying capacity is greater than the first balance threshold, selecting a first sub-inquiry request from the second type of inquiry request and allocating it to a target data processor according to the balance of the third resource carrying capacity;

[0101] Step S622: Determine sub-bearing capacity balances corresponding to the plurality of downstream processors and matching consultation types according to the second resource bearing capacity balance;

[0102] Step S623: Allocate the remaining second sub-query requests in the second type of inquiry request to each downstream processor according to the sub-bearing capacity balance of each downstream processor and the matching inquiry type.

[0103] Specifically, the third resource carrying capacity refers to the available memory resources of the target data processor after the first type of medical consultation request is allocated. If the balance of the third resource carrying capacity is greater than the first balance threshold, indicating that there are still available memory resources, the first sub-inquiry request in the second type of medical consultation request can be allocated to the target data processor according to the available memory resources.

[0104] Among them, the second type of medical consultation request can be divided into a first sub-medical consultation request and the remaining second sub-medical consultation requests, and the number of the first sub-medical consultation requests matches the third resource carrying capacity.

[0105] After that, the sub-bearing capacity balances and matching inquiry types corresponding to the multiple downstream processors are determined according to the second resource bearing capacity balance, and the second sub-inquiry request is allocated to each downstream processor according to the sub-bearing capacity balance and matching inquiry type of each downstream processor.

[0106] It should be understood that the first balance threshold can be flexibly adjusted according to demand, and illustratively, the first balance threshold is 0. Alternatively, a higher first balance threshold can be set to ensure that the target data processor has sufficient free available memory resources to avoid downtime of the target data processor.

[0107] In some implementations, step S623 allocates the remaining second sub-query requests in the second type of inquiry request to each downstream processor according to the sub-load balance of each downstream processor and the matching inquiry type, including:

[0108] Sort each downstream processor according to the corresponding sub-capacity balance;

[0109] Matching the inquiry request type of the second sub-inquiry request with the matching inquiry type of the downstream processor, and determining at least one server to be selected from the downstream processor;

[0110] The second sub-query requests with the same type of the consultation request are successively allocated to each of the servers to be selected according to the sorting result.

[0111] Specifically, the sub-capacity balance refers to the capacity balance of the downstream processor, and the matching consultation type refers to the department type (such as surgery, dermatology, urology, etc.) to which the AI ​​agent or response model configured in the capacity balance is adapted, and the adapted department type can be confirmed based on the response log of the downstream processor.

[0112] Specifically, the target data processor may be communicatively connected to one, two or more downstream processors, and the server to be selected refers to a downstream processor whose consultation type matches the consultation request type of the second sub-consultation request.

[0113] In some implementations, the second sub-inquiry requests of the same inquiry request type are successively allocated to each of the candidate servers according to the sorting result, including:

[0114] Allocating at least one second sub-query request to the first candidate server until the sub-bearing capacity balance of the first candidate server is less than a second balance threshold;

[0115] The remaining second sub-query requests are allocated to the second candidate server ranked after the first candidate server until the sub-load balance of the first candidate server is less than the third balance threshold.

[0116] Specifically, the selected servers include at least a first selected server and a second selected server ranked after the first selected server. Furthermore, the selected servers also include a third selected server ranked after the first selected server and the second selected server, and so on. The remaining second sub-consultation requests can be further assigned to the third selected server.

[0117] Through the above steps, the second sub-medical inquiry requests of the same medical inquiry request type can be distributed in descending order according to the sub-load balance of the candidate servers.

[0118] The above steps are performed respectively for the second sub-inquiry requests of different inquiry request types, and the second sub-inquiry requests of different inquiry request types can be allocated to the downstream server of the target data processor.

[0119] like Figure 5 As shown, in some implementations, step S62 allocates the second type of consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost, and further includes:

[0120] Step S624: when the third resource carrying capacity balance is less than or equal to the first balance threshold, determining sub-carrying capacity balances corresponding to the plurality of downstream processors and matching consultation types according to the second resource carrying capacity balance;

[0121] Step S625: Allocate the second type of consultation request to each downstream processor according to the sub-bearing capacity balance of each downstream processor and the matching consultation type.

[0122] It should be noted that when the third resource carrying capacity balance is less than or equal to the first balance threshold, indicating that the target data processor has no spare available memory resources, all second-category consultation requests are allocated to the target data processor.

[0123] It should be understood that the specific step of allocating the second type of medical inquiry request to each downstream processor in step S625 can refer to the specific step of allocating the second sub-medical inquiry request to each downstream processor in step S623, which will not be repeated here.

[0124] In summary, an embodiment of the present invention provides a method, apparatus, computer device and computer-readable storage medium for allocating and processing medical consultation requests, wherein the method for allocating and processing medical consultation requests includes: obtaining a medical consultation request queue input into a target data processor, wherein the queue of medical consultation requests to be answered includes a batch of medical consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster; dividing the medical consultation requests to be answered into a first category of medical consultation requests and a second category of medical consultation requests, wherein the first category of medical consultation requests are medical consultation requests sent by an upstream processor of the target data processor to the target data processor, and the second category of medical consultation requests are medical consultation requests sent by a data node outside the tree-like processor cluster to the target processor; calculating a first resource cost amount required to process the first category of medical consultation requests and a second resource cost amount required to process the second category of medical consultation requests; querying the first resource carrying capacity of the target data processor The method comprises the following steps: according to the first resource carrying capacity balance and the second resource cost amount balance of the downstream processor of the target data processor; allocating at least part of the first type of consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost amount, so that the target data processor processes the first type of consultation requests and feeds back the processing results to the upstream processor after the processing is completed; allocating the second type of consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount and the second resource cost amount, and classifying the pending requests received by the target data processor according to their sources, and allocating the pending requests from different sources in a corresponding manner, thereby avoiding multiple downward allocations in the tree-shaped processor cluster, facilitating the tracing of the processor that initially receives the consultation request and the user who issues the consultation request, and improving information security.

[0125] The embodiment of the present invention also provides a medical consultation request allocation processing device, Figure 6 A schematic diagram of the module structure of a medical consultation request allocation processing device provided by an embodiment of the present invention, such as Figure 6 As shown, the medical consultation request allocation processing device 700 includes:

[0126] The request receiving module 701 is used to obtain a medical consultation request queue input into a target data processor, wherein the medical consultation request queue to be answered includes a batch of medical consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster;

[0127] A consultation classification module 702 is used to classify the consultation requests to be answered into first-class consultation requests and second-class consultation requests, wherein the first-class consultation requests are consultation requests sent by the upstream processor of the target data processor to the target data processor, and the second-class consultation requests are consultation requests sent by the data node outside the tree processor cluster to the target processor;

[0128] A cost calculation module 703 is used to calculate a first resource cost amount required to process a first type of medical consultation request and a second resource cost amount required to process a second type of medical consultation request;

[0129] A balance query module 704, configured to query a first resource carrying capacity balance of a target data processor and a second resource carrying capacity balance of a downstream processor of the target data processor;

[0130] A first allocation module 705 is used to allocate at least part of the first type of medical consultation requests to a target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first type of medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed;

[0131] The second allocation module 706 is configured to allocate the second type of medical consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

[0132] In some implementations, the second allocation module 706 allocates the second type of medical consultation request among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount, including:

[0133] Determine a current third resource carrying capacity balance of the target data processor according to the first resource carrying capacity balance and the first resource cost amount;

[0134] The second type of medical consultation requests are distributed among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost.

[0135] In some implementations, the second allocation module 706 allocates the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance, and the second resource cost, including:

[0136] When the balance of the third resource carrying capacity is greater than the first balance threshold, selecting a first sub-inquiry request from the second type of inquiry request and allocating it to the target data processor according to the balance of the third resource carrying capacity;

[0137] Determine the sub-bearing capacity balances corresponding to the plurality of downstream processors and the matching consultation type according to the second resource bearing capacity balance;

[0138] The remaining second sub-query requests in the second type of query request are allocated to each downstream processor according to the sub-load balance of each downstream processor and the matching query type.

[0139] In some implementations, the second allocation module 706 allocates the remaining second sub-query requests in the second type of inquiry request to each downstream processor according to the sub-load balance of each downstream processor and the matching inquiry type, including:

[0140] Sort each downstream processor according to the corresponding sub-capacity balance;

[0141] Matching the inquiry request type of the second sub-inquiry request with the matching inquiry type of the downstream processor, and determining at least one server to be selected from the downstream processor;

[0142] The second sub-query requests with the same type of the consultation request are successively allocated to each of the servers to be selected according to the sorting result.

[0143] In some implementations, the second allocation module 706 allocates the second sub-inquiry requests of the same inquiry request type to each of the candidate servers in sequence according to the sorting result, including:

[0144] Allocating at least one second sub-query request to the first candidate server until the sub-bearing capacity balance of the first candidate server is less than a second balance threshold;

[0145] The remaining second sub-query requests are allocated to the second candidate server ranked after the first candidate server until the sub-load balance of the first candidate server is less than the third balance threshold.

[0146] In some implementations, the second allocation module 706 allocates the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost, and further includes:

[0147] When the third resource carrying capacity balance is less than or equal to the first balance threshold, determining sub-carrying capacity balances corresponding to the plurality of downstream processors and matching consultation types respectively according to the second resource carrying capacity balance;

[0148] The second type of consultation request is allocated to each downstream processor according to the sub-capacity balance of each downstream processor and the matching consultation type.

[0149] In some implementations, the first allocation module 705 is further configured to:

[0150] Sending the unallocated first-category consultation requests back to the upstream server;

[0151] or,

[0152] Establish a candidate consultation queue, and temporarily store some unassigned first-category consultation requests in the candidate consultation queue;

[0153] The real-time resource carrying capacity balance of the target data processor is periodically monitored, and when the real-time resource carrying capacity balance is greater than a fourth balance threshold, at least part of the first type of consultation requests temporarily stored in the candidate consultation queue is allocated to the target data processor.

[0154] The embodiment of the present invention also provides a computer device, see Figure 7 , Figure 7 A schematic block diagram of the structure of a computer device provided in an embodiment of the present invention.

[0155] like Figure 7 As shown, the computer device 800 includes a processor 801 and a memory 802 , and the processor 801 and the memory 802 are connected via a bus 803 , such as an I2C (Inter-integrated Circuit) bus.

[0156] Specifically, the processor 801 is used to provide computing and control capabilities to support the operation of the entire computer device. The processor 801 can be a central processing unit (CPU), and the processor 801 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0157] Specifically, the memory 802 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0158] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the embodiment of the present invention, and does not constitute a limitation on the computer device to which the embodiment of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] The processor is used to run the computer program stored in the memory, and implement any one of the medical consultation request allocation processing methods provided by the embodiments of the present invention when executing the computer program.

[0160] In some implementations, the processor 801 is configured to run a computer program stored in the memory 802, and implement the following steps when executing the computer program:

[0161] Obtaining a medical consultation request queue input into a target data processor, wherein the waiting medical consultation request queue includes a batch of waiting medical consultation requests, and the target data processor is at least one processor in a tree-like processor cluster;

[0162] The unanswered consultation requests are divided into the first type of consultation requests and the second type of consultation requests, wherein the first type of consultation requests are consultation requests sent by the upstream processor of the target data processor to the target data processor, and the second type of consultation requests are consultation requests sent by the data node outside the tree processor cluster to the target processor;

[0163] Calculating a first resource cost amount required to process a first type of medical consultation request and a second resource cost amount required to process a second type of medical consultation request;

[0164] Querying a first resource carrying capacity balance of a target data processor and a second resource carrying capacity balance of a downstream processor of the target data processor;

[0165] Allocating at least part of the first-category medical consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first-category medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed;

[0166] The second type of medical consultation requests are distributed among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

[0167] In some implementations, the processor 801 distributes the second type of medical consultation request among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount, including:

[0168] Determine a current third resource carrying capacity balance of the target data processor according to the first resource carrying capacity balance and the first resource cost amount;

[0169] The second type of medical consultation requests are distributed among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost.

[0170] In some implementations, the processor 801 distributes the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance, and the second resource cost, including:

[0171] When the balance of the third resource carrying capacity is greater than the first balance threshold, selecting a first sub-inquiry request from the second type of inquiry request and allocating it to the target data processor according to the balance of the third resource carrying capacity;

[0172] Determine the sub-bearing capacity balances corresponding to the plurality of downstream processors and the matching consultation type according to the second resource bearing capacity balance;

[0173] The remaining second sub-query requests in the second type of query request are allocated to each downstream processor according to the sub-load balance of each downstream processor and the matching query type.

[0174] In some implementations, the processor 801 distributes the remaining second sub-query requests in the second type of inquiry request to each downstream processor according to the sub-load balance of each downstream processor and the matching inquiry type, including:

[0175] Sort each downstream processor according to the corresponding sub-capacity balance;

[0176] Matching the inquiry request type of the second sub-inquiry request with the matching inquiry type of the downstream processor, and determining at least one server to be selected from the downstream processor;

[0177] The second sub-query requests with the same type of the consultation request are successively allocated to each of the servers to be selected according to the sorting result.

[0178] In some implementations, the processor 801 sequentially distributes the second sub-inquiry requests of the same inquiry request type to each of the candidate servers according to the sorting result, including:

[0179] Allocating at least one second sub-query request to the first candidate server until the sub-bearing capacity balance of the first candidate server is less than a second balance threshold;

[0180] The remaining second sub-query requests are allocated to the second candidate server ranked after the first candidate server until the sub-load balance of the first candidate server is less than the third balance threshold.

[0181] In some implementations, the processor 801 allocates the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance, and the second resource cost, further comprising:

[0182] When the third resource carrying capacity balance is less than or equal to the first balance threshold, determining sub-carrying capacity balances corresponding to the plurality of downstream processors and matching consultation types respectively according to the second resource carrying capacity balance;

[0183] The second type of consultation request is allocated to each downstream processor according to the sub-capacity balance of each downstream processor and the matching consultation type.

[0184] In some implementations, the processor 801 is further configured to:

[0185] Sending the unallocated first-category consultation requests back to the upstream server;

[0186] or,

[0187] Establish a candidate consultation queue, and temporarily store some unassigned first-category consultation requests in the candidate consultation queue;

[0188] The real-time resource carrying capacity balance of the target data processor is periodically monitored, and when the real-time resource carrying capacity balance is greater than a fourth balance threshold, at least part of the first type of consultation requests temporarily stored in the candidate consultation queue is allocated to the target data processor.

[0189] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the computer device described above can refer to the corresponding process in the aforementioned animal identification method embodiment, and will not be repeated here.

[0190] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by one or more processors to implement the steps of any consultation request allocation processing method provided in the embodiments of this specification.

[0191] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0192] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0193] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0194] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for allocating and processing medical consultation requests, characterized in that: The method comprises: Acquire a medical consultation request queue input into a target data processor, wherein the medical consultation request queue to be answered includes a batch of medical consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster; The unanswered consultation requests are divided into a first type of consultation requests and a second type of consultation requests, wherein the first type of consultation requests are consultation requests sent by an upstream processor of the target data processor to the target data processor, and the second type of consultation requests are consultation requests sent by a data node outside the tree processor cluster to the target processor; Calculating a first resource cost amount required to process the first type of medical consultation requests and a second resource cost amount required to process the second type of medical consultation requests; Querying a first resource carrying capacity balance of the target data processor and a second resource carrying capacity balance of a downstream processor of the target data processor; allocating at least part of the first type of medical consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first type of medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed; The second type of medical consultation requests are distributed among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

2. The method for distributing and processing medical consultation requests according to claim 1, wherein: Allocating the second type of medical consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount includes: Determine a current third resource carrying capacity balance of the target data processor according to the first resource carrying capacity balance and the first resource cost; The second type of medical consultation requests are distributed among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost.

3. The method for distributing and processing medical consultation requests according to claim 2, wherein: The allocating the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost includes: When the third resource carrying capacity balance is greater than the first balance threshold, selecting a first sub-inquiry request from the second type of inquiry request and allocating it to the target data processor according to the third resource carrying capacity balance; Determine the sub-bearing capacity balances corresponding to the plurality of downstream processors and the matching inquiry type according to the second resource bearing capacity balance; The remaining second sub-query requests in the second-type query request are allocated to each of the downstream processors according to the sub-load balance of each of the downstream processors and the matching query type.

4. The method for distributing and processing medical consultation requests according to claim 3, wherein: The allocating the remaining second sub-query requests in the second-category inquiry request to each of the downstream processors according to the sub-bearing capacity balance of each of the downstream processors and the matching inquiry type includes: sorting the downstream processors according to the corresponding sub-capacity balances; Matching the inquiry request type of the second sub-inquiry request with the matching inquiry type of the downstream processor, and determining at least one server to be selected from the downstream processor; The second sub-query requests with the same type of consultation request are successively allocated to the to-be-selected servers according to the sorting result.

5. The method for distributing and processing medical consultation requests according to claim 5, wherein: The step of allocating the second sub-query requests of the same type to the respective servers to be selected in sequence according to the sorting result includes: Allocating at least one of the second sub-query requests to a first candidate server until the sub-bearing capacity balance of the first candidate server is less than the second balance threshold; The remaining second sub-query requests are allocated to a second candidate server ranked after the first candidate server until the sub-bearing capacity balance of the first candidate server is less than the third balance threshold.

6. The method for distributing and processing medical consultation requests according to claim 2, wherein: The allocating the second type of medical consultation request among the target data processor and the downstream processor based on the third resource carrying capacity balance, the second resource carrying capacity balance and the second resource cost amount further includes: When the third resource carrying capacity balance is less than or equal to the first balance threshold, determining sub-carrier capacity balances and matching consultation types respectively corresponding to the plurality of downstream processors according to the second resource carrying capacity balance; The second type of consultation requests are allocated to each of the downstream processors according to the sub-capacity balance of each of the downstream processors and the matching consultation type.

7. The method for distributing and processing medical consultation requests according to claim 1, wherein: The method further comprises: Sending the unallocated part of the first-category medical consultation requests back to the upstream server; or, Establishing a candidate consultation queue, and temporarily storing the unassigned part of the first-category consultation requests in the candidate consultation queue; The real-time resource carrying capacity balance of the target data processor is periodically monitored, and when the real-time resource carrying capacity balance is greater than a fourth balance threshold, at least part of the first type of consultation requests temporarily stored in the candidate consultation queue are allocated to the target data processor.

8. A medical consultation request allocation processing device, characterized in that: include: A request receiving module, used for acquiring a consultation request queue input into a target data processor, wherein the consultation request queue to be answered includes a batch of consultation requests to be answered, and the target data processor is at least one processor in a tree-like processor cluster; A consultation classification module, used for classifying the to-be-answered consultation requests into a first type of consultation requests and a second type of consultation requests, wherein the first type of consultation requests are consultation requests sent by an upstream processor of the target data processor to the target data processor, and the second type of consultation requests are consultation requests sent by a data node outside the tree-like processor cluster to the target processor; A cost calculation module, used for calculating a first resource cost amount required for processing the first type of medical consultation request and a second resource cost amount required for processing the second type of medical consultation request; A balance query module, used to query the first resource carrying capacity balance of the target data processor and the second resource carrying capacity balance of the downstream processor of the target data processor; A first allocation module, configured to allocate at least part of the first type of medical consultation requests to the target data processor according to the first resource carrying capacity balance and the first resource cost, so that the target data processor processes the first type of medical consultation requests and feeds back the processing results to the upstream processor after the processing is completed; A second allocation module is configured to allocate the second type of medical consultation requests among the target data processor and the downstream processor according to the first resource carrying capacity balance, the second resource carrying capacity balance, the first resource cost amount, and the second resource cost amount.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the medical consultation request allocation processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the medical consultation request allocation processing method according to any one of claims 1 to 7.

Images