Object detection method, apparatus, device, storage medium, and program product

Abstract

The present disclosure provides an object detection method, device, equipment storage medium and program product, relates to the technical field of computers, and particularly relates to the technical field of AI medical treatment. The specific implementation scheme is as follows: a first medical entity group is determined, the first medical entity group includes a first diagnosis item entity and a first consumable item entity; according to the first medical entity group, a first diagnosis item entity category and a first consumable item entity category are determined; and a candidate diagnosis and treatment path combined with the first medical entity group is detected to obtain a first diagnosis and treatment relationship detection result, two end nodes of the candidate diagnosis and treatment path represent the first diagnosis item entity category and the first consumable item entity category respectively.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computers, in particular to the technical field of AI medical treatment, and specifically to an object detection method, device, equipment, storage medium and program product. BACKGROUND

[0002] The diagnosis-treatment relationship (the relationship between diagnosis and treatment) is related to the quality of medical services. How to detect the rationality of the diagnosis-treatment relationship becomes a problem to be solved. SUMMARY

[0003] The present disclosure provides an object detection method, device, equipment, storage medium and program product.

[0004] According to an aspect of the present disclosure, an object detection method is provided, comprising: determining a first medical entity group, the first medical entity group comprising a first diagnosis item entity and a first consumable item entity; determining a first diagnosis item entity category and a first consumable item entity category according to the first medical entity group; and detecting a candidate diagnosis-treatment path combining the first medical entity group to obtain a first diagnosis-treatment relationship detection result, two end nodes of the candidate diagnosis-treatment path representing the first diagnosis item entity category and the first consumable item entity category respectively.

[0005] According to another aspect of the present disclosure, an object detection device is provided, comprising: a first medical entity group determination module, a category determination module and a detection module. The first medical entity group determination module is configured to determine a first medical entity group, the first medical entity group comprising a first diagnosis item entity and a first consumable item entity; the category determination module is configured to determine a first diagnosis item entity category and a first consumable item entity category according to the first medical entity group; and the detection module is configured to detect a candidate diagnosis-treatment path combining the first medical entity group to obtain a first diagnosis-treatment relationship detection result, two end nodes of the candidate diagnosis-treatment path representing the first diagnosis item entity category and the first consumable item entity category respectively.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory connected with the at least one processor in communication. Wherein the memory stores instructions executable 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 execute the method of the embodiments of the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, the computer instructions being used to enable the computer to execute the method of the embodiments of the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the object detection method according to the embodiments of the present disclosure.

[0009] It should be understood that the contents described in this part are not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0011] Figure 1 A system architecture diagram of the object detection method and device according to an embodiment of the present disclosure is schematically shown;

[0012] Figure 2 A flowchart of the object detection method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A schematic diagram of the object detection method according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 4 A schematic diagram of obtaining a first diagnosis-treatment relationship detection result according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A schematic diagram of the object detection method according to another embodiment of the present disclosure is schematically shown;

[0016] Figure 6 A block diagram of the object detection device according to an embodiment of the present disclosure is schematically shown;

[0017] Figure 7 A block diagram of an electronic device that can implement the object detection method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0019] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the terms "comprises", "comprising", "includes", "including" and the like are specifically intended to be open-ended and to mean that other features, steps, operations, and / or components can be added.

[0020] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art unless otherwise defined herein. It should be noted that the terms used herein are to be interpreted as having a meaning that is consistent with the context of the specification, and should not be interpreted in an idealized or overly formal way.

[0021] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should generally be interpreted that the meaning of the expression is the same as "at least one of A, at least one of B, and at least one of C, etc.", unless otherwise defined herein.

[0022] In recent years, with the rapid development of medical insurance, the amount of medical-related expenses is huge, the amount of services is also increasing, and the trend of population aging is becoming more and more significant. At the same time, due to the current medical payment method is a post-payment system, under this system, if simply according to the consumables to settle and pay, the medical institutions will appear excessive diagnosis and treatment behavior, leading to the difficulty of controlling medical-related service costs and the problem of insufficient fairness of medical resources, ultimately leading to a series of unreasonable medical cost growth, therefore, reasonable control of medical expenses is needed.

[0023] In order to solve the above problems, the payment method and supervision means are constantly optimized, which is conducive to standardizing the service behavior of medical institutions, promoting reasonable diagnosis and treatment, controlling the unreasonable rise of medical expenses, and enhancing the cost control consciousness of medical institutions and improving service efficiency.

[0024] How to detect the rationality of diagnosis and treatment relationship is one of the problems faced by current medical cost control: due to the complexity and professionalism of medical services, the rationality of diagnosis and treatment relationship is detected by expert manual review, which introduces too many human factors and may lead to subjective review.

[0025] Figure 1 The system architecture of the object detection method and device according to an embodiment of the disclosure is schematically shown. It should be noted that, Figure 1 The shown is only an example of the system architecture to which the embodiments of the disclosure can be applied, to help those skilled in the art understand the technical content of the disclosure, but does not mean that the embodiments of the disclosure cannot be used for other devices, systems, environments or scenarios.

[0026] like Figure 1 As shown, the system architecture 100 according to this embodiment may include clients 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between clients 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0027] Users can use clients 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on clients 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0028] Clients 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers. Clients 101, 102, and 103 in this embodiment of the disclosure can, for example, run applications.

[0029] Server 105 can be a server providing various services, such as a backend management server supporting websites browsed by users using clients 101, 102, and 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the clients. Alternatively, server 105 can also be a cloud server, meaning server 105 has cloud computing capabilities.

[0030] It should be noted that the object detection method provided in this embodiment can be executed by server 105. Correspondingly, the object detection device provided in this embodiment can be located in server 105. The image recognition method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with clients 101, 102, 103 and / or server 105. Correspondingly, the object detection device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with clients 101, 102, 103 and / or server 105.

[0031] In one example, server 105 can obtain historical medical information from users 101, 102, and 103 via network 104.

[0032] It should be understood that Figure 1The number of clients, networks and servers in the system is merely illustrative. Any number of clients, networks and servers can be provided as needed.

[0033] It should be noted that in the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solutions comply with relevant laws and regulations and do not violate public order and good customs.

[0034] In the technical solutions of the present disclosure, the authorization or consent of the user is obtained before the user personal information is acquired or collected.

[0035] The object detection method provided in the embodiments of the present disclosure will be described below in combination with the system architecture of Figure 1 and the object detection method according to the exemplary embodiments of the present disclosure is described with reference to Figures 2-5 The object detection method of the embodiments of the present disclosure can be performed by the server 105 shown in Figure 1 for example.

[0036] Figure 2 A flowchart of the object detection method according to an embodiment of the present disclosure is shown schematically.

[0037] As shown in Figure 2 the object detection method 200 of the embodiments of the present disclosure can include operations S210-S230 for example.

[0038] In operation S210, a first medical entity group is determined.

[0039] The first medical entity group can be understood as a group including at least two different categories of medical-related entities. The first medical entity group includes a first diagnosis item entity and a first consumable item entity.

[0040] Exemplarily, the first medical entity group can be stored in a database in a specific data structure of a binary group, and at this time, the first medical entity group includes two medical-related entities.

[0041] Exemplarily, the first diagnosis item entity can include a specific disease diagnosis, differential diagnosis, symptom, etc. For example, acute tonsillitis is a specific disease diagnosis, and differential hypertension or angina pectoris is a specific differential diagnosis, and headache is a specific symptom.

[0042] Exemplarily, the first consumable item entity can include a specific drug, surgery, examination, test and medical material, etc. For example, amoxicillin capsules are a specific drug, tumor surgery is a specific surgery, nuclear magnetic resonance examination is a specific examination, and a syringe is a specific medical material.

[0043] At operation S220, a first diagnosis item entity category and a first consumable item entity category are determined according to the first medical entity group.

[0044] The first diagnosis item entity category can be understood as a category to which a specific first diagnosis item entity belongs.

[0045] Exemplarily, the first diagnosis item entity can be divided into the three categories of disease diagnosis, differential diagnosis, and symptom as described above. For example, when the first diagnosis item entity is acute tonsillitis, the corresponding first diagnosis item entity category can be disease diagnosis.

[0046] Exemplarily, the first consumable item entity can be divided into the five categories of medicine, surgery, examination, laboratory test, and medical material as described above. For example, amoxicillin capsules are a specific first consumable item entity, and amoxicillin capsules belong to the category of medicine, so medicine is the first consumable item entity category of the first consumable item entity of amoxicillin capsules.

[0047] At operation S230, a candidate diagnosis and treatment path combined with the first medical entity group is detected to obtain a first diagnosis and treatment relationship detection result.

[0048] The two end nodes of the candidate diagnosis and treatment path represent the first diagnosis item entity category and the first consumable item entity category, respectively.

[0049] The candidate diagnosis and treatment path can be understood as a possible and reasonable diagnosis and treatment path. Exemplarily, the candidate diagnosis and treatment path can be determined in advance.

[0050] For example, when the first diagnosis item entity is acute tonsillitis and the first consumable item entity is amoxicillin capsules, the first medical entity group B1 is <amoxicillin capsules, acute tonsillitis>, which indicates that the use of amoxicillin capsules is caused by the disease of tonsillitis, i.e., there is a causal relationship between the two. The corresponding candidate diagnosis and treatment path may, for example, include medicine-disease diagnosis, medicine-examination-disease diagnosis, and medicine-symptom-disease diagnosis.

[0051] For the candidate diagnosis and treatment path of medicine-disease diagnosis, the candidate diagnosis and treatment path combined with the first medical entity group B1 is: amoxicillin capsules-acute tonsillitis.

[0052] The object detection method of the embodiments of the present disclosure can efficiently detect the rationality of the diagnosis-treatment relationship by taking the existence of a causal relationship between the two entity elements (the first consumable item entity and the first diagnosis item entity) of the first medical entity group as the basis for judging the rationality of the diagnosis-treatment relationship after abstracting the medical scene. In addition, one first diagnosis item entity category can include multiple different first diagnosis item entities, and one first consumable item entity category can include multiple different first consumable item entities. Therefore, the candidate diagnosis-treatment path with two end nodes representing the first diagnosis item entity category and the first consumable item entity category can adapt to multiple first medical entity groups, has good migratability, and is more stable. In addition, the candidate diagnosis-treatment path of the first medical entity group is the possible actual diagnosis-treatment path of the first medical entity group. Therefore, the object detection method of the embodiments of the present disclosure has higher accuracy in detecting the diagnosis-treatment relationship.

[0053] Figure 3 An illustrative diagram of the object detection method 300 of the embodiments of the present disclosure is shown.

[0054] As shown in Figure 3 operation S310, the first medical entity group 302 can be determined according to the historical medical information 301, and the first medical entity group 302 includes the first diagnosis item entity and the first consumable item entity.

[0055] In operation S320, the first diagnosis item entity category 303 and the first consumable item entity category 304 are determined according to the first medical entity group 302.

[0056] In operation S330, the candidate diagnosis-treatment path combined with the first medical entity group 302 is detected to obtain the first diagnosis-treatment relationship detection result 306. The two end nodes of the candidate diagnosis-treatment path 305 represent the first diagnosis item entity type 303 and the first consumable item entity type 304, respectively.

[0057] Figure 4 An illustrative diagram of operation S430 according to an embodiment of the present disclosure is shown. The candidate diagnosis-treatment path can include at least one path unit, the first medical entity group can include at least one second medical entity group, and the two end nodes of the path unit can represent the diagnosis item entity category and / or the consumable item entity category.

[0058] The second medical entity group can be understood as a group including at least two medical-related entities.

[0059] For example, the second medical entity group can be stored in the database in the form of a binary tuple, and at this time, the second medical entity group includes two medical-related entities.

[0060] The “diagnosis and treatment path can include at least one path unit” can include the following three cases:

[0061] 1) The diagnosis and treatment path includes one path unit. For example, for the first medical entity group B1: <Amoxicillin Capsules-Acute Tonsillitis>, the first diagnosis entity DE1 is acute tonsillitis, and the first consumable entity CE1 is amoxicillin capsules. One of the candidate diagnosis and treatment paths P1 is “drug-disease diagnosis”. The candidate diagnosis and treatment path P1 includes one path unit PC1. The first medical entity group B1 includes a second medical entity group B11, which is <amoxicillin capsules-acute tonsillitis>.

[0062] 2) The diagnosis and treatment path includes two path units. For example, the first medical entity group B2: <Silicone Oil, Gastritis>, the first diagnosis entity DE2 is gastritis, the first diagnosis entity category DEC2 is disease diagnosis, the first consumable entity CE2 is silicone oil, and the first consumable entity category CEC2 is medical material. One of the candidate diagnosis and treatment paths P2 is disease diagnosis-examination-medical material. The first medical entity group B2: <silicone oil, gastritis> can be divided into two second medical entity groups B21, B22: <silicone oil, electronic gastroscopy> (second medical entity group B21), <electronic gastroscopy, gastritis> (second medical entity group B22).

[0063] For the candidate diagnosis and treatment path P2 of disease diagnosis-examination-medical material, two path units PC21, PC22 can be included: disease diagnosis-examination (path unit PC21), examination-medical material (path unit PC22).

[0064] 3) The diagnosis and treatment path includes more than two path units. For example, the first medical entity group B3: <Propofol, Pterygium of Both Eyes>, the first diagnosis entity DE3 is pterygium of both eyes, the first diagnosis entity category DEC3 is disease diagnosis, the first consumable entity CE3 is propofol, and the first consumable entity category CEC3 is medical material. One of the candidate diagnosis and treatment paths P3 is: drug-anesthesia-surgery-disease diagnosis. The first medical entity group B3: <propofol, pterygium of both eyes> can be divided into three second medical entity groups: <propofol, local intravenous anesthesia> (second medical entity group B31), <local intravenous anesthesia, pterygium excision surgery> (second medical entity group B32), and <pterygium excision surgery, pterygium of both eyes> (second medical entity group B33).

[0065] For the candidate treatment pathway P3 of drug-anesthesia-surgery-disease diagnosis, it can include three pathway units P31, P32 and P33: drug-anesthesia (pathway unit P31), anesthesia-surgery (pathway unit P32) and surgery-disease diagnosis (pathway unit P33).

[0066] The two entity elements of the second medical entity group can each include a diagnostic item entity and a consumable item entity, or each include two diagnostic item entities, or each include two consumable item entities.

[0067] According to another embodiment of this disclosure, the following specific example can be used to implement operation S430 in the object detection method, to detect the diagnosis and treatment path combined with the first medical entity group and obtain the detection result of the first diagnosis and treatment relationship.

[0068] like Figure 4 As shown, in operation S431, each path unit combined with the second medical entity group is detected to obtain the second diagnosis and treatment relationship detection result.

[0069] For example, in the example of the first medical entity group B3: <propofol, bilateral pterygium>, the path units combined with the second medical entity group are: propofol-local intravenous anesthesia (corresponding path unit P31), local intravenous anesthesia-pterygium excision surgery (corresponding path unit P32), and pterygium excision surgery-bilateral pterygium (corresponding path unit P33).

[0070] In operation S432, the first diagnosis and treatment relationship detection result is determined based on the second diagnosis and treatment relationship detection result.

[0071] For example, both the first and second diagnosis-treatment relationship detection results can include whether the detection passed or failed.

[0072] For example, the detection result of the first diagnosis-treatment relationship can be determined to be passed if every second diagnosis-treatment relationship detection result is passed. If any second diagnosis-treatment relationship detection result is failed, the detection result of the first diagnosis-treatment relationship can be determined to be failed.

[0073] Because medical knowledge is highly specialized, and the relationships between diagnostic and consumable entities are complex, the object detection method of this disclosure, by dividing the treatment path into at least one path unit, allows for finer-grained detection. Dividing complex treatment paths into at least one concise treatment unit improves object detection accuracy.

[0074] Figure 4Exemplarily, two second medical entity groups 401, 402 are shown, and it should be understood that the second medical entity group can be obtained according to the first medical entity group <first diagnosis item entity, first consumable item entity>. The first diagnosis item entity category 403, the diagnosis item entity category 404 can be determined according to the second medical entity group 401, and the consumable item entity category 405, the first consumable item entity category 406 can be determined according to the second medical entity group 402. The two end nodes of the path unit 407 are the first diagnosis item entity category 403 and the diagnosis item entity category 404 respectively, and the two end nodes of the path unit 408 are the consumable item entity category 405 and the first consumable item entity category 406 respectively.

[0075] In operation S431, the path unit combined with the second medical entity group 401 and the path unit combined with the second medical entity group 402 can be detected respectively to obtain the second diagnosis-treatment relationship detection result 409 and the second diagnosis-treatment relationship detection result 410.

[0076] In operation S432, the first diagnosis-treatment relationship detection result 411 can be obtained according to the second diagnosis-treatment relationship detection result 409 and the second diagnosis-treatment relationship detection result 410.

[0077] Exemplarily, according to the object detection method of the embodiment of the present disclosure, wherein the diagnosis-treatment path combined with the first medical entity group is detected to obtain the first diagnosis-treatment relationship detection result can include: detecting the candidate diagnosis-treatment path combined with the first medical entity group to obtain the first diagnosis-treatment relationship detection result according to at least one of the following: knowledge base, rule strategy, label strategy and neural network model.

[0078] The knowledge base can be understood as a special database for knowledge management, so as to facilitate the collection, arrangement and extraction of knowledge in the relevant field. For example, in the application scenario of the embodiment of the present disclosure, the knowledge base can include medical related books.

[0079] The detection according to the rule strategy can be understood as detecting according to the rules determined by the relevant professionals in advance. For example, a specific rule can be: a certain disease diagnosis uses a certain drug.

[0080] The detection according to the label strategy can be understood as detecting according to the label association of different entities. For example, the electronic gastroscopy examination, which is a consumable item entity, and the gastritis, which is a diagnosis item entity, both have the same label "stomach", so it can be considered that the electronic gastroscopy examination-gastritis has a causal relationship, that is, the detection passes.

[0081] The neural network model can be understood as a complex network structure formed by a large number of simple processing units (i.e., neurons) widely connected to each other.

[0082] Exemplarily, the neural network model can specifically include a convolutional neural network model (i.e., Convolutional Neural Networks, CNN for short). For example, a large number of first medical entity group sample data with detection result labels can be used to train the convolutional neural network model to obtain a target convolutional neural network model with accuracy up to standard, and new first medical entity groups can be input into the target convolutional neural network model to obtain detection results.

[0083] The object detection method of the embodiments of the present disclosure can automatically detect the rationality of the diagnosis and treatment relationship of the first medical entity group by at least one of the knowledge base, the rule strategy, the label strategy, and the neural network model, which is more objective and has higher accuracy.

[0084] Exemplarily, the candidate diagnosis and treatment path combined with the first medical entity group is detected according to at least one of the following: the knowledge base, the rule strategy, the label strategy, and the neural network model to obtain the first diagnosis and treatment relationship detection result. The path unit combined with the second medical entity group is detected according to at least one of the following: the knowledge base, the rule strategy, the label strategy, and the neural network model to obtain the second diagnosis and treatment relationship detection result. The first diagnosis and treatment relationship detection result is determined according to the second diagnosis and treatment relationship detection result.

[0085] For example, for the above-mentioned example of the first medical entity group B2: <Simethicone, Gastritis>, the candidate diagnosis and treatment path can include: drug-disease diagnosis, drug-examination-disease diagnosis, and drug-symptom-disease diagnosis.

[0086] For the candidate diagnosis and treatment path of drug-examination-disease diagnosis, the candidate path of Simethicone-electronic gastroscopy-gastritis combined with the first medical entity group can be detected according to at least one of the knowledge base, the rule strategy, the label strategy, and the neural network model, and the first diagnosis and treatment relationship detection result is detection pass. However, when the candidate path of Simethicone-head X-ray examination-gastritis combined with the first medical entity group is detected, since the current knowledge base, rule strategy, label strategy, and neural network model do not have the diagnosis and treatment relationship of head X-ray examination-gastritis, the first diagnosis and treatment relationship detection result of the candidate path of Simethicone-head X-ray examination-gastritis combined with the first medical entity group is detection fail. For the remaining candidate diagnosis and treatment paths, the detection of the candidate diagnosis and treatment path combined with the first medical entity group is similar to the above-mentioned example, which will not be described here.

[0087] Exemplarily, according to the object detection method of the embodiment of the present disclosure, the determining of the first diagnosis item entity category and the first consumable item entity category according to the first medical entity group can include: comparing the first diagnosis item entity with a diagnosis item category to obtain the first diagnosis item entity category; and comparing the first consumable item entity with a consumable item category to obtain the first consumable item entity category.

[0088] Exemplarily, the diagnosis item category and the consumable item category can be determined in advance. For example, it can be determined in advance that disease diagnosis, differential diagnosis and complication belong to the diagnosis item category, Chinese patent medicine, western medicine and traditional Chinese medicine belong to the medicine category, class B medical material and class C medical material belong to the medical material category, and comprehensive examination, radiological examination, pathological examination and nuclear medicine examination belong to the examination category.

[0089] For example, the historical medical information can be obtained from medical records, payment lists and the like. The payment list includes specific medicine information and also includes specific medicine information related information. For example, the payment list includes amoxicillin capsules and also includes the information that the amoxicillin capsules belong to western medicine. When the specific medicine amoxicillin capsules is obtained, the first consumable item entity category of the amoxicillin capsules can be determined as medicine according to the information that the amoxicillin capsules belong to western medicine, and western medicine is one of the above-mentioned medicine categories.

[0090] Exemplarily, the first diagnosis item entity category and the first consumable item entity category can also be determined according to the knowledge base, knowledge graph and the like.

[0091] The object detection method of the embodiment of the present disclosure can automatically determine the first diagnosis item entity category according to the specific first diagnosis item entity, and automatically determine the first consumable item entity category according to the specific first consumable item entity, and has higher detection efficiency of the rationality of the diagnosis and treatment relationship.

[0092] Exemplarily, according to the object detection method of the embodiment of the present disclosure, the determining of the first medical entity group can include: determining at least one first diagnosis item entity and at least one first consumable item entity according to historical medical information; and obtaining at least one first medical entity group according to the full combination of the first diagnosis item entity and the first consumable item entity.

[0093] Exemplarily, the historical medical information can be obtained according to a medical record, a payment list, and the like. For example, the medical record can include a specific first diagnosis item entity, and the payment list can include a specific first consumable item entity. In some cases, the medical record can include multiple different first diagnosis item entities, and the payment list can include multiple different first consumable item entities. For example, the medical record can include two different first diagnosis item entities of myopia and hordeolum, and the payment list can include two different first consumable item entities of optometry and levofloxacin hydrochloride eye drops. Thus, four first medical entity groups of <myopia, optometry>, <hordeolum, optometry>, <myopia, levofloxacin hydrochloride eye drops>, and <hordeolum, levofloxacin hydrochloride eye drops> can be obtained.

[0094] The object detection method of the embodiment of the present disclosure can perform full-quantity combination of the first diagnosis item entity and the first consumable item entity according to actual medical history information, and at least one first medical entity group obtained can cover all possible cases, so as to improve the object detection accuracy.

[0095] In the above example, only two first medical entity groups of <myopia, optometry> and <hordeolum, levofloxacin hydrochloride eye drops> have reasonable diagnosis and treatment relationships.

[0096] Exemplarily, the object detection method according to the embodiment of the present disclosure can further include: determining an evaluation result of the first diagnosis and treatment relationship detection result according to the diagnosis and treatment path, the evaluation result representing a confidence degree of the first diagnosis and treatment relationship detection result.

[0097] Due to the professionalism and complexity of medical treatment, even if a certain diagnosis and treatment path is determined, and the first diagnosis and treatment relationship detection result corresponding to the diagnosis and treatment path is detected to pass, it cannot be completely determined that the first diagnosis and treatment relationship detection result is correct. The evaluation result obtained by the object detection method of the embodiment of the present disclosure can evaluate the first diagnosis and treatment relationship detection result from the confidence degree of the first diagnosis and treatment relationship detection result, which can be used for reference by relevant personnel, for example, to improve the object detection accuracy.

[0098] Exemplarily, the object detection method according to the embodiment of the present disclosure, wherein the evaluation result can include: high correlation, medium correlation, and low correlation. Determining the evaluation result of the first diagnosis and treatment relationship detection result according to the diagnosis and treatment path can include one of the following.

[0099] In a case where the diagnosis and treatment path includes less than a first threshold number of path units, the evaluation result is determined to be high correlation.

[0100] In a case where the diagnosis and treatment path includes greater than or equal to the first threshold number and less than a second threshold number of path units, the evaluation result is determined to be medium correlation, wherein the second threshold is less than the first threshold.

[0101] In a case where the diagnosis and treatment path includes equal to or greater than the second threshold number of path units, the evaluation result is determined to be low correlation.

[0102] Exemplarily, the first threshold can be 2, and the second threshold can be 4.

[0103] The object detection method of the embodiments of the present disclosure detects each path unit of the diagnosis and treatment path. The second diagnosis and treatment relationship detection result of each path unit cannot ensure correctness. With the increase of the path units, the confidence of the first diagnosis and treatment relationship detection result determined according to the second diagnosis and treatment relationship detection result is reduced. Therefore, the object detection method of the embodiments of the present disclosure can evaluate the confidence of the first diagnosis and treatment relationship detection result with one of the three evaluation results of high correlation, medium correlation and low correlation, and has higher accuracy.

[0104] Exemplarily, the object detection method of the embodiments of the present disclosure can further include recording the first diagnosis and treatment relationship detection result and / or the second diagnosis and treatment relationship detection result as correlation information of detection failure.

[0105] For example, in a case where the first diagnosis and treatment relationship detection result is detection failure, the corresponding first medical entity group, the corresponding cost number information of the first consumable item entity of the first medical entity group can be recorded. In a case where the second diagnosis and treatment relationship detection result is detection failure, the corresponding second medical entity group, the corresponding cost number information of the consumable item entity of the second medical entity group can be recorded.

[0106] Figure 5 An illustrative diagram of an object detection method 500 according to another embodiment of the present disclosure is shown.

[0107] As shown in FIG. 5, in operation S510, at least one consumable item and at least one diagnosis item are determined according to historical medical information. Figure 5

[0108] For example, the consumable item can be determined according to the payment list 501, and the diagnosis item can be determined according to the medical record 502. In a case where the consumable item includes three: consumable item x, consumable item y, and consumable item z, and the diagnosis item includes two: diagnosis item m and diagnosis item n, six first medical entity groups can be obtained: first medical entity group xm, first medical entity group xn, first medical entity group ym, first medical entity group yn, first medical entity group zm, and first medical entity group zn.

[0109] In operation S520, a node is established. The node is used to represent the consumable item and the diagnosis item.

[0110] In operation S530, a diagnosis and treatment path is generated.

[0111] ​In operation S540, a diagnosis and treatment path is detected to obtain the first diagnosis and treatment relationship detection result 503. The "detecting a diagnosis and treatment path" can be understood as detecting a diagnosis and treatment path combined with the first medical entity group.

[0112] The object detection method 500 of the embodiment of the present disclosure is different from the object detection methods of other embodiments in that the object detection method 500 of the embodiment of the present disclosure further includes establishing a node and generating a diagnosis and treatment path.

[0113] Figure 6 A block diagram of an object detection apparatus according to an embodiment of the present disclosure is schematically shown.

[0114] As shown in Figure 6 The object detection apparatus 600 of the embodiment of the present disclosure includes, for example, a first medical entity group determination module 610, a category determination module 620, and a detection module 630.

[0115] The first medical entity group determination module 610 is configured to determine a first medical entity group, and the first medical entity group includes a first diagnosis item entity and a first consumable item entity. In an embodiment, the first medical entity group determination module 610 can be configured to perform operation S210 described above, and details are not repeated here.

[0116] The category determination module 620 is configured to determine a first diagnosis item entity category and a first consumable item entity category according to the first medical entity group. In an embodiment, the category determination module 620 can be configured to perform operation S220 described above, and details are not repeated here.

[0117] The detection module 630 is configured to detect a candidate diagnosis and treatment path combined with the first medical entity group to obtain a first diagnosis and treatment relationship detection result, and two end nodes of the candidate diagnosis and treatment path represent the first diagnosis item entity category and the first consumable item entity category, respectively. In an embodiment, the detection module 630 can be configured to perform operation S230 described above, and details are not repeated here.

[0118] According to the object detection apparatus of the embodiment of the present disclosure, the candidate diagnosis and treatment path includes at least one path unit, the first medical entity group includes at least one second medical entity group, two end nodes of the path unit represent a diagnosis item entity category and / or a consumable item entity category, and the detection module can include a second diagnosis and treatment relationship detection result determination submodule and a first diagnosis and treatment relationship detection result determination submodule.

[0119] The second diagnosis and treatment relationship detection result determination submodule can be configured to detect each path unit combined with the second medical entity group to obtain a second diagnosis and treatment relationship detection result.

[0120] The first diagnosis-treatment relationship detection result determination sub-module can be configured to determine the first diagnosis-treatment relationship detection result according to the second diagnosis-treatment relationship detection result.

[0121] The object detection apparatus according to the embodiments of the present disclosure, wherein the detection module can include a detection sub-module. The detection sub-module can be configured to detect the candidate diagnosis-treatment path combined with the first medical entity group according to at least one of the following: the knowledge base, the rule strategy, the label strategy, and the neural network model, to obtain the first diagnosis-treatment relationship detection result.

[0122] The object detection apparatus according to the embodiments of the present disclosure, wherein the category determination module can include a first comparison sub-module and a second comparison sub-module.

[0123] The first comparison sub-module can be configured to compare the first diagnosis item entity with the diagnosis item category to obtain the first diagnosis item entity category.

[0124] The second comparison sub-module can be configured to compare the first consumable item entity with the consumable item category to obtain the first consumable item entity category.

[0125] The object detection apparatus according to the embodiments of the present disclosure, wherein the first medical entity group determination module can include an entity determination sub-module and a first medical entity group determination sub-module.

[0126] The entity determination sub-module can be configured to determine at least one first diagnosis item entity and at least one first consumable item entity according to the historical medical information.

[0127] The first medical entity group determination sub-module can be configured to obtain at least one first medical entity group according to the full combination of the first diagnosis item entity and the first consumable item entity.

[0128] The object detection apparatus according to the embodiments of the present disclosure can further include an evaluation result determination module.

[0129] The evaluation result determination module can be configured to determine an evaluation result of the first diagnosis-treatment relationship detection result according to the candidate diagnosis-treatment path, the evaluation result representing the confidence of the first diagnosis-treatment relationship detection result.

[0130] The object detection apparatus according to the embodiments of the present disclosure, wherein the evaluation result can include high correlation, medium correlation, and low correlation; and the evaluation result determination module can include one of the following sub-modules: a first evaluation sub-module, a second evaluation sub-module, and a third evaluation sub-module.

[0131] The first evaluation sub-module can be configured to determine the evaluation result as high correlation when the candidate diagnosis-treatment path includes less than a first threshold number of path units.

[0132] The first evaluation submodule can be configured to determine the evaluation result as medium correlation when the candidate diagnosis and treatment path includes greater than or equal to a first threshold and less than a second threshold number of path units, wherein the second threshold is less than the first threshold.

[0133] The third evaluation submodule can be configured to determine the evaluation result as low correlation when the candidate diagnosis and treatment path includes greater than or equal to a second threshold number of path units.

[0134] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0135] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0136] As shown in Figure 7 The electronic device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the electronic device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0137] Various components in the electronic device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, and the like; an output unit 707, such as various types of displays, speakers, and the like; a storage unit 708, such as a magnetic disk, an optical disk, and the like; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0138] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the object detection method. For example, in some embodiments, the object detection method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the object detection method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the object detection method by any other appropriate means, such as by means of firmware.

[0139] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0140] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0141] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0142] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0143] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end 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), and the Internet.

[0144] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0145] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0146] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An object detection method, comprising: A first medical entity group is identified, which includes a first diagnostic item entity and a first consumable item entity; Based on the first medical entity group, determine the first diagnostic item entity category and the first consumable item entity category; Determine candidate treatment paths corresponding to the first medical entity group, wherein the two end nodes of the candidate treatment path respectively represent the first diagnostic item entity category and the first consumable item entity category; The candidate treatment paths are tested to obtain a first treatment relationship detection result, which indicates whether there is a causal relationship between the first diagnostic item entity and the first consumable item entity. The candidate treatment path includes at least one path unit, wherein the two end nodes of the path unit respectively represent the entity category of the diagnostic item and / or the entity category of the consumable item; the detection of the candidate treatment path to obtain the first treatment relationship detection result includes: Divide the first medical entity group into at least one second medical entity group; Identify at least one path unit corresponding to each of the at least one second medical entity group, and detect each path unit to obtain the second diagnosis-treatment relationship detection result; The first diagnosis-treatment relationship detection result is determined based on the second diagnosis-treatment relationship detection result.

2. The method according to claim 1, wherein, The step of detecting the candidate treatment paths to obtain the first treatment relationship detection result includes: The candidate treatment path is detected based on at least one of the following to obtain the first treatment relationship detection result: knowledge base, rule strategy, label strategy, and neural network model.

3. The method according to any one of claims 1 to 2, wherein, The step of determining the first diagnostic item entity category and the first consumable item entity category based on the first medical entity group includes: By comparing the first diagnostic item entity with the diagnostic item category, the first diagnostic item entity category is obtained; and By comparing the first consumable item entity with the consumable item category, the first consumable item entity category is obtained.

4. The method according to any one of claims 1 to 2, wherein, The determination of the first group of medical entities includes: Based on historical medical information, identify at least one entity for the first diagnostic item and at least one entity for the first consumable item; and Based on the full combination of the first diagnostic item entity and the first consumable item entity, at least one group of the first medical entities is obtained.

5. The method according to claim 1, further comprising: Based on the candidate treatment pathways, an evaluation result of the first treatment relationship detection result is determined, and the evaluation result represents the confidence level of the first treatment relationship detection result.

6. The method according to claim 5, wherein, The evaluation results include: high correlation, moderate correlation, and low correlation; the evaluation result of determining the first diagnosis-treatment relationship detection result based on the candidate diagnosis-treatment path includes one of the following: If the candidate treatment path includes fewer than a first threshold number of path units, the evaluation result is determined to be highly relevant. If the candidate treatment pathway includes a number of pathway units greater than or equal to the first threshold and less than the second threshold, the evaluation result is determined to be relevant, wherein the second threshold is less than the first threshold; and If the candidate treatment path includes more than or equal to the second threshold number of path units, the evaluation result is determined to be of low relevance.

7. An object detection device, comprising: The first medical entity group determination module is used to determine the first medical entity group, which includes a first diagnostic item entity and a first consumable item entity. The category determination module is used to determine the first diagnostic item entity category and the first consumable item entity category based on the first medical entity group; The candidate treatment path determination module is used to determine the candidate treatment path corresponding to the first medical entity group, wherein the two end nodes of the candidate treatment path respectively represent the first diagnostic item entity category and the first consumable item entity category; The detection module is used to detect the candidate treatment path and obtain a first treatment relationship detection result, wherein the first treatment relationship detection result characterizes whether there is a causal relationship between the first diagnostic item entity and the first consumable item entity; The candidate treatment path includes at least one path unit, wherein the two end nodes of the path unit respectively represent the entity category of the diagnostic item and / or the entity category of the consumable item; the detection module includes: A partitioning submodule is used to divide the first medical entity group into at least one second medical entity group; The second diagnosis-treatment relationship detection result determination submodule is used to determine at least one path unit corresponding to the at least one second medical entity group, and to detect each path unit to obtain the second diagnosis-treatment relationship detection result; The first diagnosis-treatment relationship detection result determination submodule is used to determine the first diagnosis-treatment relationship detection result based on the second diagnosis-treatment relationship detection result.

8. The apparatus according to claim 7, wherein, The detection module includes: The detection submodule is used to detect the candidate diagnosis and treatment path according to at least one of the following to obtain the first diagnosis and treatment relationship detection result: knowledge base, rule strategy, label strategy and neural network model.

9. The apparatus according to claim 7 or 8, wherein, The category determination module includes: The first comparison submodule is used to compare the first diagnostic item entity with the diagnostic item category to obtain the first diagnostic item entity category; and The second comparison submodule is used to compare the first consumable item entity with the consumable item category to obtain the first consumable item entity category.

10. The apparatus according to claim 7 or 8, wherein, The first medical entity group determination module includes: The entity determination submodule is used to determine at least one entity for the first diagnosis item and at least one entity for the first consumable item based on historical medical information; and The first medical entity group determination submodule is used to obtain at least one first medical entity group based on the full combination of the first diagnostic item entity and the first consumable item entity.

11. The apparatus according to claim 7, further comprising: The evaluation result determination module is used to determine the evaluation result of the first diagnosis-treatment relationship detection result based on the candidate diagnosis-treatment path, wherein the evaluation result characterizes the confidence level of the first diagnosis-treatment relationship detection result.

12. The apparatus according to claim 11, wherein, The evaluation results include: high correlation, medium correlation, and low correlation; the evaluation result determination module includes one of the following sub-modules: The first evaluation submodule is used to determine the evaluation result as highly relevant when the candidate treatment path includes fewer than a first threshold number of path units. The second evaluation submodule is configured to determine that the evaluation result is relevant when the candidate treatment path includes more than or equal to the first threshold and less than the second threshold number of path units, wherein the second threshold is less than the first threshold; and The third evaluation submodule is used to determine the evaluation result as low correlation when the candidate treatment path includes more than or equal to the second threshold number of path units.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images