A prescription review method, apparatus, device, and storage medium

Abstract

This invention discloses a prescription review method, apparatus, device, and storage medium. The method includes: preprocessing target prescription information to obtain target disease information and target drug information; when the target disease information and the target drug information are not in a preset prescription review database, converting the target disease information and the target drug indication information into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space; and determining the review result of the target prescription information based on the correlation between the target disease word vector and the target drug indication word vector. This invention solves the problem in the prior art of being unable to diagnose prescriptions not in the review database, enabling the review of prescriptions not in the database and improving the efficiency of prescription review.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data analysis, and particularly relate to a prescription auditing method, device, equipment and storage medium. BACKGROUND

[0002] A prescription refers to diagnostic information issued by a medical department for a patient's illness. Because the medical level of different medical departments is uneven, it is necessary to audit the prescription issued by the medical department. The existing technology usually audits the prescription according to a preset prescription auditing database, that is, the prescription auditing database has already stored the standard prescription corresponding to the illness, and when auditing the to-be-audited prescription, only needs to find the corresponding standard prescription in the prescription auditing database according to the illness in the to-be-audited prescription, and then compares the to-be-audited prescription with the standard prescription. However, with the continuous enrichment of prescription information, it cannot be guaranteed that the auditing database contains the corresponding standard prescription of the to-be-audited prescription, and therefore, it is necessary to improve the existing prescription auditing method to meet the increasing prescription auditing demand. SUMMARY

[0003] Embodiments of the present application provide a prescription auditing method, device, equipment and storage medium, which can audit the prescription not in the auditing database, and improve the efficiency of prescription auditing.

[0004] In a first aspect, embodiments of the present application provide a prescription auditing method, which comprises:

[0005] obtaining target illness information and target drug information by preprocessing target prescription information;

[0006] when the target illness information and the target drug information are not in a preset prescription auditing database, converting the target illness information and the target drug indication information into at least one target illness word vector and at least one target drug indication word vector in a preset medical word vector space, respectively;

[0007] determining an auditing result of the target prescription information according to the correlation between the target illness word vector and the target drug indication word vector.

[0008] In a second aspect, embodiments of the present application provide a prescription auditing device, which comprises:

[0009] a prescription information preprocessing module, configured to obtain target illness information and target drug information by preprocessing target prescription information;

[0010] The prescription information conversion module is used to convert the target disease information and the target drug indication information into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space when the target disease information and the target drug information are not in the preset prescription review database.

[0011] The prescription information review module is used to determine the review result of the target prescription information based on the correlation between the target disease word vector and the target drug indication word vector.

[0012] Thirdly, embodiments of the present invention provide a computer device, the computer device comprising:

[0013] One or more processors;

[0014] Memory, used to store one or more programs;

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the prescription review method described in any embodiment.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the prescription review method described in any embodiment.

[0017] The technical solution provided by this invention preprocesses target prescription information to obtain target disease information and target drug information. When the target disease information and the target drug information are not in a preset prescription review database, the target disease information and the target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space. Based on the correlation between the target disease word vector and the target drug indication word vector, the review result of the target prescription information is determined. This invention solves the problem in the prior art of being unable to diagnose prescriptions not in the review database, enabling the review of prescriptions not in the database and improving the efficiency of prescription review. Attached Figure Description

[0018] Figure 1 This is a flowchart of a prescription review method provided by an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of a prescription review method provided by an embodiment of the present invention;

[0020] Figure 3 This is a flowchart of a prescription review process provided by an embodiment of the present invention;

[0021] Figure 4This is a schematic diagram of the structure of a prescription review device provided in an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Figure 1 This is a flowchart of a prescription review method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where diagnostic prescriptions are reviewed. The method can be executed by a prescription review device, which can be implemented by software and / or hardware.

[0025] like Figure 1 As shown, the prescription review method includes the following steps:

[0026] S110. By preprocessing the target prescription information, target disease information and target drug information are obtained.

[0027] The target prescription information can be prescription information that requires prescription review, and may include the patient's symptoms and corresponding diagnoses. The target symptom information can be symptom information used for prescription review, such as fever, cold, cough, etc. The target drug information can be drug information that requires prescription review, such as drug number, drug name, indications, contraindications, etc.

[0028] Preprocessing can be an information processing method that removes abnormal information, extracts key information, or transforms the format of the target prescription information. Specifically, it can delete missing or abnormal data in the target prescription information and extract keywords to obtain the target disease information and target drug information.

[0029] Furthermore, the effectiveness of a prescription can be determined by analyzing the correspondence between symptoms and medications.

[0030] S120. When the target disease information and the target drug information are not in the preset prescription review database, the target disease information and the target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in the preset medical word vector space.

[0031] The preset prescription review database can be a pre-defined database for prescription review, containing a large amount of knowledge graph information such as symptoms, drug indications, and contraindications. When target symptom and drug information can be matched in the preset prescription review database, the symptom and drug information in the target symptom information can be reviewed according to the review list in the preset prescription review database. For example, when the symptom and drug information in the target symptom information successfully matches the whitelist in the review list, the target drug information can be determined to have passed the review; when the symptom and drug information in the target symptom information successfully matches the blacklist in the review list, the target drug information can be determined to have failed the review. When the target symptom and drug information cannot be matched in the preset prescription review database, the target symptom information cannot be reviewed through the preset prescription review database, and further processing of the target symptom and drug information is required to determine the review result.

[0032] The pre-defined medical word vector space can be a pre-defined vector space for medical terms. Within this space, target disease information and target drug indication information can be represented as word vectors, facilitating subsequent calculations of their correlations. Furthermore, the target disease information and target drug indication information can be input into a pre-trained information conversion model to obtain at least one target disease word vector and at least one target drug indication word vector within the pre-defined medical word vector space. The target disease word vector can be a word vector corresponding to the target disease information that is needed for prescription review; similarly, the target drug indication word vector can be a word vector corresponding to the target drug indication information that is needed for prescription review.

[0033] S130. Determine the review result of the target prescription information based on the correlation between the target symptom word vector and the target drug indication word vector.

[0034] The correlation can be the similarity between the word vectors of the target disease and the word vectors of the target drug indication. By analyzing the similarity between these two word vectors, it can be determined whether the drug in the target drug information is suitable for treating the disease in the target disease information, thereby determining the review result of the target prescription information. For example, the similarity value between the word vectors of the target disease and the word vectors of the target drug indication can be compared with a preset similarity review threshold. When the similarity value is greater than the preset similarity review threshold, the target prescription information can be determined to pass the review; when the similarity value is not greater than the preset similarity review threshold, the target prescription information can be determined to fail the review.

[0035] The technical solution provided by this invention preprocesses the target prescription information to obtain target disease information and target drug information. When the target disease information and target drug information are not in a preset prescription review database, the target disease information and target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space. Based on the correlation between the target disease word vector and the target drug indication word vector, the review result of the target prescription information is determined. This invention solves the problem in the prior art of being unable to diagnose prescriptions not in the review database, enabling the review of prescriptions not in the database and improving the efficiency of prescription review.

[0036] Figure 2 This is a flowchart of a prescription review method provided by an embodiment of the present invention. This embodiment of the present invention can be applied to scenarios where diagnostic prescriptions are reviewed. Based on the above embodiments, this embodiment further explains how to determine the review result of the target prescription information according to the correlation between the target disease word vector and the target drug indication word vector, and how to review the target prescription information when the target disease information and the target drug information are in a preset prescription review database. This device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0037] like Figure 2 As shown, the prescription review method includes the following steps:

[0038] S210. By preprocessing the target prescription information, target disease information and target drug information are obtained.

[0039] The target prescription information can be prescription information that requires prescription review, and may include the patient's symptoms and corresponding diagnoses. The target symptom information can be symptom information used for prescription review, such as fever, cold, cough, etc. The target drug information can be drug information that requires prescription review, such as drug number, drug name, indications, contraindications, etc.

[0040] Preprocessing can be an information processing method that removes abnormal information, extracts key information, or transforms the format of the target prescription information. Specifically, it can delete missing or abnormal data in the target prescription information and extract keywords to obtain the target disease information and target drug information.

[0041] Furthermore, the correspondence between symptoms and medications can be analyzed, or the validity of a prescription can be determined through prescription review standards.

[0042] S220. Determine whether the target disease information and the target drug information are in the preset prescription review database according to the preset judgment rules. If the target disease information and the target drug information are not in the preset prescription review database, execute steps S230, S240, S250 and S260; if the target disease information and the target drug information are in the preset prescription review database, execute step S270.

[0043] The preset judgment rule can be a preset rule used to determine whether the target disease information and target drug information are in the preset prescription review database. For example, it can match the target disease information and target drug information with the review list in the review database. If the target disease information and target drug information do not match the review list in the review database, it can be determined that the target disease information and target drug information are not in the preset prescription review database; if the target disease information and target drug information match the review list in the review database, it can be determined that the target disease information and target drug information are in the preset prescription review database.

[0044] S230. Input the target disease information and target drug indication information into a pre-trained target information conversion model to obtain at least one target disease word vector and at least one target drug indication word vector.

[0045] The target information conversion model can be a conversion model used to convert target disease information and target drug indication information into medical word vector format. Specifically, the target information conversion model can be obtained through pre-training, for example, using the word2vec algorithm. The target disease word vector can be the word vector corresponding to the target disease information that needs to be used for prescription review; the target drug indication word vector can be the word vector corresponding to the target drug indication information that needs to be used for prescription review. By inputting the target disease information and target drug indication information into the pre-trained target information conversion model, at least one target disease word vector and at least one target drug indication word vector can be obtained. Furthermore, by analyzing the similarity between the target disease word vector and the target drug indication word vector, the similarity between the target disease information and the target drug indication information can be reflected, thereby determining the prescription review status of the target prescription information.

[0046] S240. Calculate the word shift distance between the word vectors of each target disease and the word vectors of each target drug indication, and obtain at least one word shift distance.

[0047] Among them, word shift distance can be a parameter that reflects the similarity between the word vector of the target disease and the word vector of the target drug indication. The word shift distance can be obtained by calculating the cosine distance, Euclidean distance or Manhattan distance between the word vector of the target disease and the word vector of the target drug indication. The word shift distance is inversely proportional to the similarity, that is, the larger the word shift distance, the smaller the similarity between the word vector of the target disease and the word vector of the target drug indication.

[0048] S250. Based on the mapping relationship between the word shift distance and the similarity value, determine at least one corresponding similarity value, and take the maximum value among the at least one similarity value as the similarity value between the target disease information and the target drug indication information.

[0049] The mapping relationship can be a predefined correspondence between word-shift distance and similarity value. For example, when the cosine distance between the word vectors of each target disease and the word vectors of each target drug indication is used as the word-shift distance, the similarity value is equal to 1 minus the cosine distance. Based on the mapping relationship between word-shift distance and similarity value, at least one corresponding similarity value can be determined. Furthermore, the maximum value among at least one similarity value can be used as the similarity value between the target disease information and the target drug indication information. By using the maximum value among at least one similarity value as the similarity value between the target disease information and the target drug indication information, the similarity between the target disease information and the target drug indication information can be reflected to the greatest extent, avoiding a large number of prescriptions failing the review due to the selected similarity being too low, thus improving the review efficiency.

[0050] S260. Compare the similarity value with a preset similarity review threshold, and determine the review result of the target prescription information based on the comparison result of the similarity value and the preset similarity review threshold.

[0051] The preset similarity review threshold is a pre-defined threshold used to review similarity values. When the similarity value is greater than the preset threshold, it indicates that the target disease information and the target drug indication information have a strong similarity, and the target prescription information can pass the review. When the similarity value is less than the preset threshold, it indicates that the target disease information and the target drug indication information are not sufficiently similar, and the target prescription information cannot pass the review. Furthermore, medical professionals can adjust the preset similarity review threshold to ensure its effectiveness.

[0052] S270. When the target disease information and the target drug information are successfully matched with the preset prescription review whitelist in the preset prescription review list, the target prescription information is determined to have passed the review; when the target disease information and the target drug information are successfully matched with the preset prescription review blacklist in the preset prescription review list, the target prescription information is determined to have failed the review.

[0053] The preset prescription review whitelist can be a list of prescriptions that meet pre-defined review criteria. This whitelist includes disease information and corresponding medications that meet the review criteria. For example, it might include a disease and a list of medications that can treat that disease and have minimal side effects. When the target disease and medication information match the preset prescription review whitelist, the prescription is considered approved. The preset prescription review blacklist can be a list of prescriptions that do not meet the review criteria. This blacklist includes disease information and corresponding medications that do not meet the review criteria. For example, it might include a disease and a list of medications that can treat that disease but have a high efficacy, or medications that cannot be used to treat that disease. When the target disease and medication information match the preset prescription review blacklist, the prescription is considered rejected. Optionally, the target disease information can include multiple diseases and multiple drugs corresponding to multiple diseases. When one disease in the target disease information and the drug corresponding to that disease successfully match the preset prescription review whitelist, the target prescription information can be directly confirmed as approved. It is not necessary to review whether the remaining diseases in the target disease information and the drugs corresponding to the remaining diseases successfully match the preset prescription review whitelist.

[0054] In one optional implementation, the preset prescription review database can be updated based on the review results of the target prescription information. For example, when the target prescription information fails the review, the target disease information and target drug information in the target prescription information are added to the preset prescription review blacklist in the preset prescription review database; when the target prescription information passes the review, the target disease information and target drug information in the target prescription information are added to the preset prescription review whitelist in the preset prescription review database. By updating the preset prescription review database based on the review results of the target prescription information, when reviewing prescription information that is identical to the target prescription information, the prescription information can be directly reviewed through the updated preset prescription review database, thereby improving prescription review efficiency.

[0055] For example, Figure 3 This is a flowchart of a prescription review process provided by an embodiment of the present invention, such as... Figure 3 As shown, the prescription review workflow is as follows: First, the prescription information is preprocessed to obtain symptom information and drug information. Then, it is determined whether the symptom information and drug information are in the review database. If the symptom information and drug information are in the review database, the rationality of the prescription is determined according to the review list, and then the prescription information is determined to pass the review. If the symptom information and drug information are not in the review database, the symptom information and drug indication information are converted into symptom information word vectors and drug indication word vectors, respectively. Then, based on the word shift distance between the symptom information word vectors and drug indication word vectors, the similarity value between the symptom information and drug indication information is determined. The similarity value is compared with the preset similarity review threshold to determine the review result of the prescription information. Finally, the review database is updated according to the review result of the prescription information.

[0056] The technical solution provided in this invention preprocesses the target prescription information to obtain target disease information and target drug information. It then determines whether the target disease information and target drug information are in a preset prescription review database according to preset judgment rules. When the target disease information and target drug information are not in the preset prescription review database, the target disease information and target drug indication information are input into a pre-trained target information conversion model to obtain at least one target disease word vector and at least one target drug indication word vector. The word shift distance between each target disease word vector and each target drug indication word vector is calculated to obtain at least one word shift distance. Based on the mapping relationship between word shift distance and similarity value, at least one corresponding similarity value is determined, and the maximum value among the at least one similarity value is taken as the similarity value between the target disease information and the target drug indication information. When the target disease information and target drug information are in the preset prescription review database, if the target disease information and target drug information successfully match the preset prescription review whitelist in the preset prescription review list, the target prescription information is determined to have passed the review; if the target disease information and target drug information successfully match the preset prescription review blacklist in the preset prescription review list, the target prescription information is determined to have failed the review. The technical solution of this invention solves the problem in the prior art that prescriptions not in the review database cannot be diagnosed, and can review prescriptions not in the review database, thereby improving the efficiency of prescription review.

[0057] Figure 4 This is a schematic diagram of the structure of a prescription review device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios of reviewing diagnostic prescriptions. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0058] like Figure 4 As shown, the prescription review device includes: a prescription information preprocessing module 310, a prescription information conversion module 320, and a prescription information review module 330.

[0059] The prescription information preprocessing module 310 is used to preprocess the target prescription information to obtain target disease information and target drug information; the prescription information conversion module 320 is used to convert the target disease information and target drug indication information into at least one target disease word vector and at least one target drug indication word vector in the preset medical word vector space when the target disease information and target drug information are not in the preset prescription review database; the prescription information review module 330 is used to determine the review result of the target prescription information based on the correlation between the target disease word vector and the target drug indication word vector.

[0060] The technical solution provided by this invention preprocesses the target prescription information to obtain target disease information and target drug information. When the target disease information and target drug information are not in a preset prescription review database, the target disease information and target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space. Based on the correlation between the target disease word vector and the target drug indication word vector, the review result of the target prescription information is determined. This invention solves the problem in the prior art of being unable to diagnose prescriptions not in the review database, enabling the review of prescriptions not in the database and improving the efficiency of prescription review.

[0061] In one optional implementation, the prescription information preprocessing module 310 is specifically used to: determine the similarity value between the target disease information and the target drug indication information based on the word shift distance between the target disease word vector and the target drug indication word vector; compare the similarity value with a preset similarity review threshold; and determine the review result of the target prescription information based on the comparison result between the similarity value and the preset similarity review threshold.

[0062] In an optional implementation, the prescription information preprocessing module 310 is further configured to: calculate the word shift distance between each target symptom word vector and each target drug indication word vector to obtain at least one word shift distance; determine at least one corresponding similarity value based on the mapping relationship between word shift distance and similarity value; and take the maximum value among the at least one similarity value as the similarity value between the target symptom information and the target drug indication information.

[0063] In one optional implementation, the prescription information conversion module 320 is specifically used to: input the target disease information and the target drug indication information into a pre-trained target information conversion model to obtain at least one target disease word vector and at least one target drug indication word vector.

[0064] In an optional implementation, the prescription information review module 330 is further configured to: when the target symptom information and the target drug information are in the preset prescription review database, determine the review result of the target prescription information based on the matching result between the target symptom information and the target drug information and the preset prescription review list in the preset prescription review database.

[0065] In an optional implementation, the prescription information review module 330 is further configured to: determine that the target prescription information has passed review when the target symptom information and target drug information are successfully matched with the preset prescription review whitelist in the preset prescription review list; and determine that the target prescription information has failed review when the target symptom information and target drug information are successfully matched with the preset prescription review blacklist in the preset prescription review list.

[0066] In one optional implementation, the prescription review device further includes a database update module for updating a preset prescription review database based on the review results of the target prescription information.

[0067] The prescription review device provided in this embodiment of the invention can execute the prescription review method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0068] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 5 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 5 The computer device 12 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be configured within a prescription review device.

[0069] like Figure 5 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0070] Bus 18 can be one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0071] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0072] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0073] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0074] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 5 As not shown, it can be used in conjunction with computer device 12 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0075] Processing unit 16 executes various functional applications and data processing by running programs stored in system memory 28, such as implementing the prescription review method provided in this embodiment, which includes:

[0076] By preprocessing the target prescription information, target disease information and target drug information are obtained;

[0077] When the target disease information and the target drug information are not in the preset prescription review database, the target disease information and the target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in the preset medical word vector space.

[0078] The review result of the target prescription information is determined based on the correlation between the target disease word vector and the target drug indication word vector.

[0079] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the prescription review method as provided in any embodiment of the present invention, including:

[0080] By preprocessing the target prescription information, target disease information and target drug information are obtained;

[0081] When the target disease information and the target drug information are not in the preset prescription review database, the target disease information and the target drug indication information are respectively converted into at least one target disease word vector and at least one target drug indication word vector in the preset medical word vector space.

[0082] The review result of the target prescription information is determined based on the correlation between the target disease word vector and the target drug indication word vector.

[0083] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0084] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0085] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0086] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0087] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0088] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method of prescription review, characterized by, The method comprises: obtaining target disease information and target drug information by preprocessing target prescription information; when the target disease information and the target drug information are not in a preset prescription review database, converting the target disease information and target drug indication information into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space, respectively; calculating the word shift distance between each target disease word vector and each target drug indication word vector to obtain at least one word shift distance; determining at least one corresponding similarity value based on the mapping relationship between the word shift distance and the similarity value; wherein the mapping relationship includes: when the cosine distance between each target disease word vector and each target drug indication word vector is taken as the word shift distance, the similarity value is equal to 1 minus the cosine distance; taking the maximum value in the at least one similarity value as the similarity value of the target disease information and the target drug indication information; comparing the similarity value with a preset similarity review threshold, and determining the review result of the target prescription information according to the comparison result.

2. The method of claim 1, wherein, The method further comprises: when the target disease information and the target drug information are in the preset prescription review database, the method further comprises:

3. The method of claim 1, wherein, determining the review result of the target prescription information according to the matching result of the target disease information and the target drug information with a preset prescription review list in the preset prescription review database. The method further comprises:

4. The method of claim 3, wherein, updating the preset prescription review database according to the review result of the target prescription information. The device comprises: a prescription information preprocessing module for obtaining target disease information and target drug information by preprocessing target prescription information; 5. The method of claim 1, wherein, a prescription information conversion module for converting the target disease information and target drug indication information into at least one target disease word vector and at least one target drug indication word vector in a preset medical word vector space, respectively, when the target disease information and the target drug information are not in a preset prescription review database. ​ 6. A prescription review device, characterized by, ​ ​ ​ The prescription information auditing module is configured to calculate a word shift distance between each of the target disease word vector and each of the target drug indication word vector, and obtain at least one word shift distance; Based on a mapping relationship between the word shift distance and the similarity value, at least one corresponding similarity value is determined; wherein the mapping relationship comprises: when the cosine distance between each target disease word vector and each target drug indication word vector is taken as the word shift distance, the similarity value is equal to 1 minus the cosine distance; The maximum value in the at least one similarity value is taken as the similarity value of the target disease information and the target drug indication information; The similarity value is compared with a preset similarity auditing threshold, and an auditing result of the target prescription information is determined according to a comparison result.

7. A computer device, comprising: The computer device comprises: One or more processors; Memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the prescription auditing method as claimed in any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the prescription auditing method as claimed in any one of claims 1-5.

Images