Quality inspection method and device applied to medical record data, equipment and medium

Abstract

The invention provides a quality inspection method and device applied to medical record data, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent medical treatment, natural language processing and knowledge maps. According to the implementation scheme, the method comprises the steps of determining a plurality of medical items included in medical record data, wherein the medical items comprise at least one diagnosis item and at least one disposal item; obtaining a plurality of resource consumption records; determining at least one medical project associated with each resource consumption record based on the medical knowledge graph; calculating the sum of the resource consumption associated with each medical project; determining a main diagnosis item from the at least one diagnosis item and a main treatment item from the at least one treatment item based on the sum of the resource consumption of each medical item; and determining a quality inspection result for the medical record data based on the main diagnosis item, the main disposal item, the first diagnosis group and the first disposal group.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of smart medical care, natural language processing, and knowledge graph technology, and specifically to a quality inspection method, device, electronic device, computer-readable storage medium, and computer program product applied to medical record data. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] In order to facilitate the management of medical record data and medical resources, it is usually necessary to group a large amount of medical record data. The accuracy of medical record data grouping will directly affect the management and allocation efficiency of medical resources.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a quality inspection method, device, electronic device, computer-readable storage medium and computer program product for medical record data.

[0006] According to one aspect of the present disclosure, there is provided a quality inspection method for medical record data, wherein the medical record data includes a first diagnosis group and a first treatment group, and the method includes: determining a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item; obtaining a plurality of resource consumption records corresponding to the medical record data, wherein each resource consumption record in the plurality of resource consumption records includes a resource consumption item and a resource consumption amount; for each resource consumption record in the plurality of resource consumption records, determining at least one medical item associated with the resource consumption record from the plurality of medical items based on a medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and connecting edges between the multiple nodes, each of the multiple nodes corresponding to a resource consumption item or a medical item; for each medical item in the multiple medical items, calculating the sum of the resource consumption associated with the medical item; based on the sum of the resource consumption of each diagnostic item in the at least one diagnostic item, determining a main diagnostic item from the at least one diagnostic item; based on the sum of the resource consumption of each treatment item in the at least one treatment item, determining a main treatment item from the at least one treatment item; and determining a quality inspection result for the medical record data based on the main diagnostic item, the main treatment item, the first diagnostic group and the first treatment group.

[0007] According to one aspect of the present disclosure, there is provided a quality inspection device for medical record data, wherein the medical record data includes a first diagnosis group and a first treatment group, and the device includes: a first determination unit, configured to determine a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item; an acquisition unit, configured to acquire a plurality of resource consumption records corresponding to the medical record data, wherein each of the plurality of resource consumption records includes a resource consumption item and a resource consumption amount; a second determination unit, configured to determine, for each of the plurality of resource consumption records, at least one medical item associated with the resource consumption record from the plurality of medical items based on a medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and the plurality of A connecting edge between nodes, each of the multiple nodes corresponds to a resource consumption item or a medical item; a calculation unit, configured to calculate the sum of resource consumption associated with each medical item in the multiple medical items; a third determination unit, configured to determine a main diagnostic item from the at least one diagnostic item based on the sum of resource consumption of each diagnostic item in the at least one diagnostic item; a fourth determination unit, configured to determine a main treatment item from the at least one treatment item based on the sum of resource consumption of each treatment item in the at least one treatment item; and a quality inspection unit, configured to determine a quality inspection result for the medical record data based on the main diagnostic item, the main treatment item, the first diagnostic group and the first treatment group.

[0008] According to one aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned quality inspection method applied to medical record data.

[0009] According to one aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned quality inspection method applied to medical record data.

[0010] According to one aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program can implement the above-mentioned quality inspection method applied to medical record data when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, the accuracy of quality inspection of medical record data can be improved.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an exemplary embodiment of the present disclosure;

[0015] Figure 2 A flow chart of a quality inspection method applied to medical record data according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 3 A schematic diagram of a medical knowledge graph according to an exemplary embodiment of the present disclosure is shown;

[0017] Figure 4 A structural block diagram of a quality inspection device applied to medical record data according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0022] In order to facilitate the management of medical record data and medical resources, it is usually necessary to encode and group a large amount of medical record data, especially to add medical record front page codes based on ICD (International Classification of Diseases) coding rules, which is equivalent to obtaining the group information of the medical record data, and then manage it based on the DRG (Diagnosis Related Groups) tool.

[0023] In the related art, the group information of medical record data is usually checked based on preset rules, such as pre-configuring specific mutual exclusion rules between multiple groups, based on which to check whether the diagnosis or treatment groups contained in the medical record data to be inspected are mutually exclusive. This method only checks the medical records through simple rule matching, but fails to combine the complete medical record data and medical resource consumption information to check whether there are errors or omissions in the group information.

[0024] Based on this, the present disclosure provides a quality inspection method applied to medical record data, which first extracts diagnostic items and treatment items from the medical record data, and then determines the resource consumption records associated with each diagnostic item and treatment item based on the medical knowledge graph, and selects the main diagnostic items and main treatment items of the medical record data based on the total resource consumption, and then verifies whether the division of diagnostic groups and treatment groups is appropriate, so as to obtain more accurate quality inspection results for the medical record data.

[0025] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0026] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0027] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of a quality inspection method applied to medical record data.

[0028] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0029] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0030] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to send medical record data to be inspected. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0031] Client devices 101, 102, 103, 104, 105 and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various categories and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (eg, email applications), short message service (SMS) applications, and may use various communication protocols.

[0032] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0033] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0034] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0035] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0036] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0037] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different categories. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0038] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different categories of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0039] Figure 1The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0040] Figure 2 FIG. 2 shows a flow chart of a quality inspection method 200 applied to medical record data according to an exemplary embodiment of the present disclosure, wherein the medical record data includes a first diagnosis group and a first treatment group. Figure 2 As shown, the method 200 includes:

[0041] Step S201, determining a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item;

[0042] Step S202: Acquire multiple resource consumption records corresponding to the medical record data, each of the multiple resource consumption records including a resource consumption item and a resource consumption amount;

[0043] Step S203: for each resource consumption record in the plurality of resource consumption records, determining at least one medical project associated with the resource consumption record from the plurality of medical projects based on the medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and connecting edges between the plurality of nodes, and each of the plurality of nodes corresponds to a resource consumption project or a medical project;

[0044] Step S204: for each medical project among the multiple medical projects, calculating the total amount of resource consumption associated with the medical project;

[0045] Step S205, determining a main diagnostic item from the at least one diagnostic item based on the sum of resource consumption of each diagnostic item in the at least one diagnostic item;

[0046] Step S206, determining a main treatment project from the at least one treatment project based on the sum of resource consumption of each treatment project in the at least one treatment project; and

[0047] Step S207: Determine a quality inspection result for the medical record data based on the main diagnosis items, the main treatment items, the first diagnosis group, and the first treatment group.

[0048] By applying the method 200 as described above, it is possible to first extract multiple diagnostic items and treatment items from the medical record data, then obtain multiple resource consumption records corresponding to the medical record, determine the correspondence between the multiple resource consumption records and each diagnostic item and treatment item based on the medical knowledge graph, and more accurately select the main diagnostic items and main treatment items based on the total resource consumption corresponding to each diagnostic item and treatment item, and then check whether the division of diagnostic groups and treatment groups is appropriate, that is, to achieve accurate quality inspection of the medical record data. Therefore, it is possible to combine the complete medical record data and medical resource consumption information to check whether there are errors or omissions in the group information, and achieve more accurate and comprehensive quality inspection of medical record data.

[0049] In some examples, the diagnosis group information and the treatment group information may be coded information, such as ICD coding information indicating a disease diagnosis result and a medical treatment operation (such as a surgical operation and a non-surgical operation, etc.). In some examples, the first diagnosis group may correspond to the main diagnosis information on the front page of the medical record data, and the first treatment group may correspond to the main treatment information on the front page of the medical record data, such as main surgical information.

[0050] In some examples, multiple resource consumption records can be obtained based on medical expense detail information. For example, the resource consumption item in each resource consumption record can correspond to a charging item in a medical expense detail, and the resource consumption amount corresponds to the charging amount in the detail, or the resource consumption amount can be the corresponding resource consumption quantity in the detail, such as the quantity of medicine.

[0051] According to some embodiments, determining the multiple medical items included in the medical record data in step S201 includes: inputting the medical record data into a medical item extraction model to obtain multiple medical items output by the medical item extraction model, wherein the medical item extraction model is trained using sample medical record data labeled with medical items. Thus, the medical item extraction model can be used to extract medical item entities in the medical record data, thereby improving efficiency and accuracy.

[0052] In some examples, an initial medical project extraction model may be constructed based on a pre-trained natural language processing model. Specifically, for example, an entity extraction network may be added to the pre-trained language model to obtain an initial medical project extraction model. On the basis of fully utilizing the natural language understanding capabilities of the pre-trained language model, sample medical record data labeled with medical projects may be used to perform model optimization training, so that the trained medical project extraction model may have the ability to extract medical project entities from medical record data.

[0053] In some examples, on the basis of extracting medical project entities in medical record data, the attributes of the medical projects can be further extracted. For example, for diagnostic items indicating the diagnosis results of a disease, attributes such as time, cause, classification, stage, grade, whether it has occurred before, site of onset, frequency of onset, outcome time, and accompanying symptoms can be extracted to achieve more accurate and comprehensive medical record data quality inspection based on the extraction results.

[0054] In some examples, multiple medical items in the medical record data may be determined by other methods. For example, a medical item word library may be predefined, and regular matching is performed with text in the medical record data based on the preset content in the word library to obtain the medical items included in the medical record data.

[0055] Figure 3 A schematic diagram of a medical knowledge graph according to an exemplary embodiment of the present disclosure is shown. Figure 3 As shown, the medical knowledge graph contains two types of nodes, namely medical project nodes and resource consumption nodes, to indicate different entity contents respectively, and the connection edges between nodes can be used to indicate the relationship between entities. Specifically, the existence or non-existence of the connection edge between two nodes can indicate whether there is an association relationship between the entities corresponding to the two nodes, and the attribute information of the connection edge can be further configured to indicate the relationship type, relationship attributes and other information between the two nodes. For example, when medical project A is a diagnostic project (i.e., medical project A corresponds to a certain specific disease) and medical project C is a treatment project, the connection edge between node A and node C can indicate that treatment project C is a necessary means or a feasible means to treat the disease corresponding to diagnostic project A. For another example, when medical project B is a treatment project, the connection edge between node B and resource consumption node a can indicate that treatment project B will inevitably lead to resource consumption a. Furthermore, the connection edge between node B and resource consumption node a can also indicate the reasonable resource consumption of a, such as consumption threshold, consumption speed and other information.

[0056] By analyzing the prior knowledge of the relationship between medical items and resource consumption items contained in the medical knowledge graph, we can accurately determine the relationship between each medical item and the resource consumption record in the medical record data, and then accurately determine the main diagnosis items and main treatment items, so as to improve the accuracy of medical record data quality inspection.

[0057] According to some embodiments, in step S203, for each resource consumption record in the multiple resource consumption records, determining at least one medical project associated with the resource consumption record from the multiple medical projects based on the medical knowledge graph includes: searching the medical knowledge graph for a first node corresponding to the resource consumption project of the resource consumption record; for each medical project in the multiple medical projects, searching the medical knowledge graph for a second node corresponding to the medical project; and determining at least one medical project associated with the resource consumption record, wherein a connecting edge exists between the second node corresponding to each medical project associated with the resource consumption record and the first node. Thus, the connecting relationship indicated by the connecting edge in the medical knowledge graph can be used to determine the connecting relationship between the medical project and the resource consumption record, making full use of the prior knowledge in the graph and improving accuracy.

[0058] In some examples, it may be in response to determining that there is a connection edge that meets a preset condition between a resource consumption record and a node corresponding to a medical project, that is, determining that there is an association relationship between the resource consumption record and the medical project. The above preset condition may be configured according to actual needs, so that the association relationship between the resource consumption record and the medical project can be determined simply and efficiently.

[0059] In some examples, the existence of a connecting edge between the corresponding nodes of a medical project and a resource consumption record is a necessary but not sufficient condition for the association between the medical project and the resource consumption record, so as to combine more information to determine the association relationship between the resource consumption record and the medical project and improve the accuracy of medical record data quality inspection.

[0060] According to some embodiments, in step S203, for each resource consumption record in the multiple resource consumption records, determining at least one medical project associated with the resource consumption record from the multiple medical projects based on the medical knowledge graph includes: inputting the multiple resource consumption records and the multiple medical projects into a resource consumption analysis model, so that the resource consumption analysis model can determine at least one medical project associated with the resource consumption record based on the medical knowledge graph, wherein the resource consumption analysis model is trained using sample data annotated with the association relationship between resource consumption records and medical projects. Thus, the resource consumption analysis model can be used to determine the association relationship between medical projects and resource consumption records, further improving the efficiency and accuracy of medical record data quality inspection.

[0061] In some examples, an initial resource consumption analysis model may be constructed based on various types of neural network structures, and then trained using sample data labeled with the relationship between resource consumption records and medical items, so that the trained resource consumption analysis model can have the ability to determine the relationship between resource consumption records and medical items.

[0062] By executing steps S201 to S203, the resource consumption record associated with each medical project can be obtained, and then the total resource consumption of each medical project can be obtained.

[0063] In some examples, in step S205 and step S206, at least one diagnosis item and at least one treatment item may be sorted based on the sum of resource consumption, and a main diagnosis item and a main treatment item may be selected based on the sorting results.

[0064] In some examples, the sum of the numerical information or the proportion information of the resource consumption of each medical project can be visually displayed through the user interface, for example, through a visual chart such as a bar chart or a pie chart.

[0065] In some examples, when it is found that there are one or more resource consumption records that are not associated with any medical items in the medical record data, a quality inspection result may also be generated to indicate unreasonable resource consumption.

[0066] In some examples, determining the quality inspection results based on the main diagnostic items, the main treatment items, the first diagnostic group and the first treatment group in step S207 may include: determining whether there is a preset mapping relationship between the main diagnostic items and the first diagnostic group and determining whether there is a preset mapping relationship between the main treatment items and the first treatment items. When any judgment result is no, it can be determined that the quality inspection of the medical record data has failed, and the corresponding quality inspection result prompt information can be displayed through the user interface.

[0067] In actual application scenarios, medical record data may include multiple diagnosis groups, that is, other additional second diagnosis groups are included on the basis of the main first diagnosis group. For example, when the diagnosis group information is an ICD disease diagnosis code, the medical record data (such as the first page of the medical record) may include the main diagnosis code and multiple non-main diagnosis codes.

[0068] According to some embodiments, the medical record data further includes at least one second diagnostic group, and method 200 further includes: determining the diagnostic item corresponding to each second diagnostic group in the at least one second diagnostic group; and for each second diagnostic group in the at least one second diagnostic group, in response to determining that each resource consumption record in the plurality of resource consumption records is not associated with the diagnostic item corresponding to the second diagnostic group, determining that the quality inspection result for the medical record data is unqualified. Thus, it is possible to check whether there are redundant diagnostic groups based on the resource consumption records, thereby achieving more comprehensive and accurate quality inspection of medical record data.

[0069] In some examples, the medical record data may also include multiple treatment groups, that is, other additional second treatment groups are included on the basis of the main first diagnosis group. In this case, similar steps can be used to determine whether there are redundant treatment groups based on resource consumption records to improve the comprehensiveness of medical record data quality inspection.

[0070] According to some embodiments, the medical record data also includes medical test results, and method 200 further includes: in response to determining that the corresponding diagnostic items of each second diagnostic group in the at least one second diagnostic group are not associated with the medical test results, determining that the quality inspection result for the medical record data is unqualified. It can be understood that, generally speaking, there is a mapping relationship between medical test results of specific content and diagnostic items of a specific category. For example, when a medical test result is positive, it can be determined that there is a necessary mapping relationship between the medical test result and the specific disease diagnosis result. By judging whether there are missing diagnostic groups based on medical test results, a more comprehensive and accurate quality inspection of medical record data can be achieved.

[0071] According to some embodiments, method 200 further includes: for each diagnostic item in the at least one diagnostic item, determining a target diagnostic group corresponding to the diagnostic item; and in response to determining that the first diagnostic group and the at least one second diagnostic group do not include the target diagnostic group, determining that the quality inspection result for the medical record data is unqualified. By comparing and checking the diagnostic items and diagnostic groups included in the medical record data, it is possible to check whether there are erroneous or missing diagnostic groups, thereby achieving more comprehensive and accurate quality inspection of the medical record data.

[0072] In some examples, the division of diagnostic groups includes multiple levels. In one example, in response to determining that the first diagnostic group and the at least one second diagnostic group include a higher-level diagnostic group corresponding to the target diagnostic group, the corresponding quality inspection result is determined to indicate that the diagnostic group of the medical record data is too general and should be replaced with a more subordinate and accurate target diagnostic group. By comparing the superior and subordinate information based on the division of diagnostic groups, more accurate quality inspection of medical record data can be achieved.

[0073] It is understandable that when the medical record data includes multiple treatment groups, similar steps can also be used to compare and check the treatment items and treatment groups included in the medical record data to improve the comprehensiveness of the quality inspection of the medical record data.

[0074] In actual application scenarios, medical record data may contain multiple medical consultations. When conducting quality inspection of medical record data, it may be necessary to only inspect the contents of one or several of the visits.

[0075] According to some embodiments, method 200 further includes: determining the time information of each of the multiple medical items; and determining at least one target medical item from the multiple medical items based on the time information, wherein for each resource consumption record in the multiple resource consumption records, determining at least one medical item associated with the resource consumption record from the multiple medical items based on the medical knowledge graph includes: for each resource consumption record in the multiple resource consumption records, determining at least one target medical item associated with the resource consumption record from the at least one target medical item based on the medical knowledge graph. Thus, medical items can be sorted and screened based on time information to accurately identify the content of the medical consultation to be quality inspected, avoid interference from past history, and improve quality inspection accuracy.

[0076] In some examples, the medical record data explicitly records the diagnosis time, treatment time and other information corresponding to the medical items, so that the time information corresponding to each medical item can be extracted. The extraction process of the above time information can be implemented by using the entity extraction technology described above.

[0077] In some examples, the medical record data may record the diagnosis items and treatment items in a timeline order. In this case, the time information of each medical item may be the time sequence information of the medical item, so as to form a sequence containing multiple medical items based on the time sequence, based on which the target content to be inspected can be accurately identified.

[0078] In some examples, a verification rule corresponding to at least one of a diagnosis combination and a treatment group may be pre-configured, based on which a more comprehensive quality inspection of medical record data can be achieved.

[0079] In some examples, the verification rules include group refinement verification rules. As described above, the division of diagnosis groups or treatment groups can include multiple levels. When overly high-level groups are found in the medical record data, the corresponding quality inspection results can be determined to indicate that the group division of the medical record data is too general.

[0080] In some examples, the verification rule includes a group accompanying verification rule. Specifically, it can be to configure a necessary co-occurrence relationship between a specific group A and a specific group B, and when the medical record data only contains one of them, the corresponding quality inspection result is determined to indicate that the corresponding accompanying group is missing from the medical record data.

[0081] In some examples, the verification rule includes a group mutual exclusion verification rule. Specifically, a mutual exclusion relationship between a specific group C and a specific group D may be configured, and when the medical record data contains both of the above, a corresponding quality inspection result is determined to indicate that group mutual exclusion occurs in the medical record data.

[0082] In some examples, the verification rule includes a group merging verification rule. Specifically, the verification rule may be configured to indicate that when a specific group E and a specific group F co-occur, they need to be merged into group G, based on which the group information in the medical record data is quality checked.

[0083] As described above, the medical record data may include multiple diagnosis groups or multiple treatment groups, and may be specifically divided into main groups and additional groups. In this case, the verification rule may be for the division of the main group and the additional group. For example, the verification rule may be configured to indicate that a specific group H cannot be used as the main group, and based on this, the group information in the medical record data is quality checked.

[0084] Furthermore, in some examples, multiple diagnosis groups or multiple treatment groups in the medical record data may correspond to specific sorting information, such as sorting based on importance. In this case, the verification rule may be a sorting rule for multiple groups, based on which it is checked whether the sorting of the multiple groups in the medical record data is reasonable.

[0085] In some examples, the medical record data also includes necessary population characteristic information, such as gender and age information. In this case, the verification rules may include mutually exclusive verification rules for population characteristics and groups. For example, it may be a mutually exclusive relationship between the gender characteristics of the configuration population and the diagnostic group corresponding to a specific gender. For another example, it may also be a mutually exclusive relationship between the age characteristics of the configuration population and the diagnostic group corresponding to a specific age group.

[0086] By applying verification rules to check the group information of medical record data, more comprehensive and accurate quality inspection of medical record data can be achieved.

[0087] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0088] According to one aspect of the present disclosure, a quality inspection device applied to medical record data is also provided. Figure 4 FIG. 4 shows a structural block diagram of a quality inspection device 400 applied to medical record data according to an exemplary embodiment of the present disclosure, wherein the medical record data includes a first diagnosis group and a first treatment group. Figure 4 As shown, the device 400 includes:

[0089] A first determining unit 401 is configured to determine a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item;

[0090] An acquisition unit 402 is configured to acquire a plurality of resource consumption records corresponding to the medical record data, each of the plurality of resource consumption records including a resource consumption item and a resource consumption amount;

[0091] A second determining unit 403 is configured to determine, for each resource consumption record in the plurality of resource consumption records, at least one medical item associated with the resource consumption record from the plurality of medical items based on the medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and connecting edges between the plurality of nodes, and each of the plurality of nodes corresponds to a resource consumption item or a medical item;

[0092] A calculation unit 404 is configured to calculate, for each medical project among the plurality of medical projects, a sum of resource consumption amounts associated with the medical project;

[0093] A third determining unit 405 is configured to determine a main diagnostic item from the at least one diagnostic item based on the sum of resource consumption of each diagnostic item in the at least one diagnostic item;

[0094] A fourth determining unit 406 is configured to determine a main treatment project from the at least one treatment project based on a sum of resource consumption of each treatment project in the at least one treatment project; and

[0095] The quality inspection unit 407 is configured to determine a quality inspection result for the medical record data based on the main diagnosis items, the main treatment items, the first diagnosis group, and the first treatment group.

[0096] According to some embodiments, the first determination unit 401 is configured to: input the medical record data into a medical project extraction model to obtain multiple medical projects output by the medical project extraction model, wherein the medical project extraction model is trained using sample medical record data labeled with medical projects.

[0097] According to some embodiments, the second determination unit 403 is configured to: search for a first node corresponding to the resource consumption item of the resource consumption record from the medical knowledge graph; for each medical item among the multiple medical items, search for a second node corresponding to the medical item from the medical knowledge graph; and determine at least one medical item associated with the resource consumption record, wherein there is a connecting edge between the second node corresponding to each medical item associated with the resource consumption record and the first node.

[0098] According to some embodiments, the second determination unit 403 is configured to: input the multiple resource consumption records and the multiple medical projects into a resource consumption analysis model, so that the resource consumption analysis model can determine at least one medical project associated with the resource consumption record based on the medical knowledge graph, wherein the resource consumption analysis model is trained using sample data marked with the association relationship between resource consumption records and medical projects.

[0099] According to some embodiments, the medical record data also includes at least one second diagnostic group, and the device 400 also includes: a sixth determination unit, configured to determine the diagnostic items corresponding to each second diagnostic group in the at least one second diagnostic group, and the quality inspection unit 407 is also configured to, for each second diagnostic group in the at least one second diagnostic group, in response to determining that each resource consumption record in the multiple resource consumption records is not associated with the diagnostic items corresponding to the second diagnostic group, determine that the quality inspection result of the medical record data is unqualified.

[0100] According to some embodiments, the medical record data also includes medical test results, and the quality inspection unit 407 is further configured to: in response to determining that the corresponding diagnostic items of each second diagnostic group in the at least one second diagnostic group are not associated with the medical test results, determine that the quality inspection results for the medical record data are unqualified.

[0101] According to some embodiments, the device 400 also includes: a seventh determination unit, configured to determine, for each diagnostic item of the at least one diagnostic item, a target diagnostic group corresponding to the diagnostic item, and the quality inspection unit 407 is also configured to determine that the quality inspection result of the medical record data is unqualified in response to determining that the first diagnostic group and the at least one second diagnostic group do not include the target diagnostic group.

[0102] According to some embodiments, the device 400 also includes: an eighth determination unit, configured to determine the time information of each medical item among the multiple medical items; and a ninth determination unit, configured to determine at least one target medical item from the multiple medical items based on the time information, wherein the second determination unit 403 is configured to: for each resource consumption record among the multiple resource consumption records, determine at least one target medical item associated with the resource consumption record from the at least one target medical item based on the medical knowledge graph.

[0103] It should be understood that Figure 4 The operations of the various units of the quality inspection device 400 for medical record data shown in FIG. 4 can be similar to those of FIG. Figure 2 The steps in the quality inspection method 200 described above for medical record data correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the device 400 and the various units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0104] According to one aspect of the present disclosure, there is also provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned quality inspection method applied to medical record data.

[0105] According to one aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned quality inspection method applied to medical record data.

[0106] According to one aspect of the present disclosure, a computer program product is also provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned quality inspection method applied to medical record data.

[0107] refer to Figure 5, a block diagram of an electronic device 500 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0108] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0109] Multiple components in the device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 can be any type of device that can input information to the device 500. The input unit 506 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 507 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 can include but is not limited to a disk, an optical disk. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0110] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a quality inspection method applied to medical record data. For example, in some embodiments, the quality inspection method applied to medical record data may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the quality inspection method applied to medical record data described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the quality inspection method applied to medical record data in any other appropriate manner (eg, by means of firmware).

[0111] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0113] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0116] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0118] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples. Various elements in the embodiments or examples may be omitted or may be replaced by their equivalent elements. In addition, each step may be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that with the evolution of technology, many elements described herein may be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A quality inspection method for medical record data, wherein the medical record data includes a first diagnosis group and a first treatment group, the method comprising: determining a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item; Acquire a plurality of resource consumption records corresponding to the medical record data, each of the plurality of resource consumption records comprising a resource consumption item and a resource consumption amount; For each resource consumption record in the plurality of resource consumption records, determining at least one medical project associated with the resource consumption record from the plurality of medical projects based on the medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and connecting edges between the plurality of nodes, and each of the plurality of nodes corresponds to a resource consumption project or a medical project; For each medical project among the plurality of medical projects, calculating a sum of resource consumption amounts associated with the medical project; determining a main diagnostic item from the at least one diagnostic item based on a sum of resource consumption amounts of each diagnostic item in the at least one diagnostic item; determining a main treatment project from among the at least one treatment project based on a sum of resource consumption amounts of each of the at least one treatment project; and A quality inspection result for the medical record data is determined based on the main diagnosis items, the main treatment items, the first diagnosis group, and the first treatment group.

2. The method of claim 1, wherein: The step of determining, for each resource consumption record in the plurality of resource consumption records, at least one medical item associated with the resource consumption record from the plurality of medical items based on the medical knowledge graph comprises: Searching the medical knowledge graph for a first node corresponding to the resource consumption item of the resource consumption record; For each medical item in the plurality of medical items, searching the medical knowledge graph for a second node corresponding to the medical item; and At least one medical project associated with the resource consumption record is determined, wherein a connection edge exists between a second node corresponding to each medical project associated with the resource consumption record and the first node.

3. The method of claim 2, wherein: The step of determining, for each resource consumption record in the plurality of resource consumption records, at least one medical item associated with the resource consumption record from the plurality of medical items based on the medical knowledge graph comprises: The multiple resource consumption records and the multiple medical projects are input into a resource consumption analysis model so that the resource consumption analysis model can determine at least one medical project associated with the resource consumption record based on the medical knowledge graph, wherein the resource consumption analysis model is trained using sample data marked with the association relationship between resource consumption records and medical projects.

4. The method according to any one of claims 1 to 3, wherein: The medical record data further includes at least one second diagnosis group, and the method further includes: Determining a diagnostic item corresponding to each second diagnostic group in the at least one second diagnostic group; and For each second diagnosis group in the at least one second diagnosis group, in response to determining that each resource consumption record in the plurality of resource consumption records is not associated with a diagnosis item corresponding to the second diagnosis group, determining that a quality inspection result for the medical record data is unqualified.

5. The method of claim 4, wherein: The medical record data also includes medical test results, and the method further includes: In response to determining that the diagnostic items corresponding to each second diagnostic group in the at least one second diagnostic group are not associated with the medical test result, it is determined that the quality inspection result for the medical record data is unqualified.

6. The method according to claim 4 or 5, further comprising: For each of the at least one diagnostic item, Determine the target diagnostic group corresponding to the diagnostic item; as well as In response to determining that neither the first diagnosis group nor the at least one second diagnosis group includes the target diagnosis group, determining that the quality inspection result for the medical record data is unqualified.

7. The method according to any one of claims 1 to 6, wherein: The determining of the plurality of medical items included in the medical record data comprises: The medical record data is input into a medical item extraction model to obtain a plurality of medical items output by the medical item extraction model, wherein the medical item extraction model is trained using sample medical record data labeled with medical items.

8. The method according to any one of claims 1 to 7, further comprising: determining time information for each of the plurality of medical items; as well as determining at least one target medical project from the plurality of medical projects based on the time information, Wherein, for each resource consumption record in the multiple resource consumption records, determining at least one medical item associated with the resource consumption record from the multiple medical items based on the medical knowledge graph comprises: For each resource consumption record among the multiple resource consumption records, at least one target medical item associated with the resource consumption record is determined from the at least one target medical item based on the medical knowledge graph.

9. A quality inspection device for medical record data, the medical record data comprising a first diagnosis group and a first treatment group, the device comprising: A first determining unit is configured to determine a plurality of medical items included in the medical record data, wherein the plurality of medical items include at least one diagnosis item and at least one treatment item; an acquisition unit, configured to acquire a plurality of resource consumption records corresponding to the medical record data, each of the plurality of resource consumption records including a resource consumption item and a resource consumption amount; a second determining unit configured to determine, for each resource consumption record in the plurality of resource consumption records, at least one medical item associated with the resource consumption record from the plurality of medical items based on the medical knowledge graph, wherein the medical knowledge graph includes a plurality of nodes and connecting edges between the plurality of nodes, and each of the plurality of nodes corresponds to a resource consumption item or a medical item; a calculation unit configured to calculate, for each medical item in the plurality of medical items, a sum of resource consumption amounts associated with the medical item; a third determining unit configured to determine a main diagnostic item from the at least one diagnostic item based on a sum of resource consumption amounts of each diagnostic item in the at least one diagnostic item; a fourth determining unit configured to determine a main treatment project from among the at least one treatment project based on a sum of resource consumption amounts of each of the at least one treatment project; and The quality inspection unit is configured to determine a quality inspection result for the medical record data based on the main diagnosis items, the main treatment items, the first diagnosis group, and the first treatment group.

10. The device of claim 9, wherein: The second determining unit is configured to: Searching the medical knowledge graph for a first node corresponding to the resource consumption item of the resource consumption record; For each medical item in the plurality of medical items, searching the medical knowledge graph for a second node corresponding to the medical item; and At least one medical project associated with the resource consumption record is determined, wherein a connection edge exists between a second node corresponding to each medical project associated with the resource consumption record and the first node.

11. The device of claim 10, wherein: The second determining unit is configured to: The multiple resource consumption records and the multiple medical projects are input into a resource consumption analysis model so that the resource consumption analysis model can determine at least one medical project associated with the resource consumption record based on the medical knowledge graph, wherein the resource consumption analysis model is trained using sample data marked with the association relationship between resource consumption records and medical projects.

12. The device according to any one of claims 9 to 11, wherein: The medical record data further includes at least one second diagnosis group, and the device further includes: a sixth determining unit, configured to determine a diagnostic item corresponding to each second diagnostic group in the at least one second diagnostic group, The quality inspection unit is also configured to, for each second diagnostic group in the at least one second diagnostic group, determine that the quality inspection result of the medical record data is unqualified in response to determining that each resource consumption record in the multiple resource consumption records is not associated with the diagnostic item corresponding to the second diagnostic group.

13. The device of claim 12, wherein: The medical record data also includes medical test results, and the quality inspection unit is further configured to: In response to determining that the diagnostic items corresponding to each second diagnostic group in the at least one second diagnostic group are not associated with the medical test result, it is determined that the quality inspection result for the medical record data is unqualified.

14. The apparatus according to claim 12 or 13, further comprising: A seventh determining unit is configured to determine, for each diagnostic item in the at least one diagnostic item, a target diagnostic group corresponding to the diagnostic item, And the quality inspection unit is further configured to determine that the quality inspection result of the medical record data is unqualified in response to determining that the first diagnosis group and the at least one second diagnosis group do not include the target diagnosis group.

15. The device according to any one of claims 9 to 14, wherein: The first determining unit is configured to: The medical record data is input into a medical item extraction model to obtain a plurality of medical items output by the medical item extraction model, wherein the medical item extraction model is trained using sample medical record data labeled with medical items.

16. The apparatus according to any one of claims 9 to 15, further comprising: An eighth determining unit is configured to determine time information of each of the plurality of medical items; as well as a ninth determining unit configured to determine at least one target medical project from the plurality of medical projects based on the time information, Wherein, the second determining unit is configured to: For each resource consumption record among the multiple resource consumption records, at least one target medical item associated with the resource consumption record is determined from the at least one target medical item based on the medical knowledge graph.

17. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein: The computer program implements the method according to any one of claims 1 to 8 when executed by a processor.

Images