Target data determination method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a method, device, electronic device and storage medium for determining target data. The method includes: obtaining multiple groups of to-be-processed data relative to each preset platform of the current symptom information; determining the medication evidence information corresponding to each group of to-be-processed data by associating the medication information in each group of to-be-processed data; processing the medication evidence information corresponding to each group of to-be-processed data to obtain the target to-be-processed medication evidence information corresponding to each medication evidence information; determining the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target to-be-processed medication association data in the target to-be-processed medication evidence information, solving the problem of low prescription efficiency when prescribing by consulting historical prescription data, and realizing the effect of comprehensively considering the medication association information of symptom information by preset platforms of different data sizes.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer processing technology, and more particularly to a method, device, electronic device and storage medium for determining target data. Background Art

[0002] As the information construction of the medical system becomes more and more perfect, the storage of drug prescription data for various diseases in the system is becoming more and more standardized and comprehensive. When prescribing a medicine for a certain disease, it is usually necessary to consult a large amount of historical drug prescription data, or combine personal subjective prescription experience to prescribe specific prescription information corresponding to the disease, which leads to low prescription efficiency. Summary of the invention

[0003] Embodiments of the present invention provide a target data determination method, device, electronic device and storage medium to improve the reliability of determining medication regularity information.

[0004] In a first aspect, an embodiment of the present invention provides a method for determining target data, the method comprising:

[0005] For each symptom information, multiple groups of to-be-processed data of the current symptom information relative to each preset platform are obtained; wherein each group of to-be-processed data includes multiple to-be-processed data, each group of to-be-processed data corresponds to a corresponding preset platform, and each to-be-processed data includes medication information corresponding to the current symptom information;

[0006] By performing association processing on the medication information in each group of data to be processed, at least one piece of medication association data corresponding to each group of data to be processed is obtained, and based on the at least one piece of medication association data, medication evidence information corresponding to each group of data to be processed is determined;

[0007] Based on a preset evidence processing algorithm, the medication evidence information corresponding to each group of data to be processed is processed to obtain target medication evidence information to be processed corresponding to each medication evidence information;

[0008] By analyzing and processing each target medication association data in the target medication evidence information, the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information are determined.

[0009] In a second aspect, an embodiment of the present invention further provides a target data determination device, the device comprising:

[0010] The module for acquiring data to be processed is used to acquire, for each symptom information, multiple groups of data to be processed of the current symptom information relative to each preset platform; wherein each group of data to be processed includes multiple data to be processed, each group of data to be processed corresponds to a corresponding preset platform, and each data to be processed includes medication information corresponding to the current symptom information;

[0011] a medication evidence information determination module, configured to obtain at least one medication association data corresponding to each group of data to be processed by performing association processing on the medication information in each group of data to be processed, and determine medication evidence information corresponding to each group of data to be processed based on the at least one medication association data;

[0012] A target medication evidence information determination module is used to process the medication evidence information corresponding to each group of data to be processed based on a preset evidence processing algorithm to obtain target medication evidence information corresponding to each medication evidence information;

[0013] The target medication evidence information determination module is used to determine the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target medication association data in the target medication evidence information.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the target data determination method as described in any one of the embodiments of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a target data determination method as described in any one of the embodiments of the present invention.

[0019] The technical solution of the embodiment of the present invention obtains multiple groups of to-be-processed data relative to each preset platform of the current symptom information; obtains the medication-related data corresponding to each group of to-be-processed data by associating the medication information in each group of to-be-processed data, and determines the medication evidence information corresponding to each group of to-be-processed data; processes the medication evidence information corresponding to each group of to-be-processed data to obtain the target to-be-processed medication evidence information corresponding to each medication evidence information; determines the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication-related data in the target medication evidence information by analyzing and processing each target to-be-processed medication-related data in the target to-be-processed medication evidence information, thereby solving the problem in the prior art of obtaining a reliable diagnosis of a disease by consulting a large amount of historical drug prescription data or combining personal subjective experience. There is a problem of low prescription efficiency in prescribing medicines for diseases. Based on the association rule algorithm, the pending data of each preset platform for the current disease information is processed respectively, and the medication association information corresponding to each preset platform is determined. Then, each group of medication association information is converted into corresponding medication evidence information by using the DS evidence theory. At the same time, each medication evidence information is weighted averaged to obtain the medication association information and the corresponding confidence in the final target evidence information. The credibility of the prescription scheme for the disease information of the preset platforms with different data sizes is comprehensively considered, and the reliability of the determination of medication association information is improved, so that the subsequent medication association information with higher confidence can provide a theoretical basis for the clinical rational medication and the interpretation of the medication mechanism, which is convenient for medical staff to prescribe reasonable prescriptions for the disease information. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a method for determining target data provided by Embodiment 1 of the present invention;

[0022] Figure 2 A flow chart of a method for determining target data provided by Embodiment 2 of the present invention;

[0023] Figure 3 A flowchart of a method for determining target data provided by Embodiment 3 of the present invention;

[0024] Figure 4 A structural block diagram of a target data determination device provided by Embodiment 4 of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0027] Figure 1 This is a flow chart of a target data determination method provided in the first embodiment of the present invention. This embodiment can be applied to the case of determining the medication rules for various diseases. This method can be executed by the target data determination device in the embodiment of the present invention. The device can be implemented in software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server. The device can be configured in a computing device. The target data determination method provided in this embodiment specifically includes the following steps:

[0028] S110 . For each symptom information, obtain multiple groups of to-be-processed data of the current symptom information relative to each preset platform.

[0029] Among them, the symptom information can be understood as disease information in the medical field. For example, in the medical field, colds, fevers, heart disease, diabetes, and hypertension can all be used as symptom information. The current symptom information can be understood as when it is necessary to obtain the symptom data associated with each symptom information, the symptom data associated with any symptom information can be processed as the symptom data for obtaining the current symptom information, that is, one of the symptom information in each symptom information can be described as the current symptom information. The preset platform can be understood as a preset, third-party platform, and optionally, it can be a hospital system platform or an Internet medical institution platform. The data to be processed can be understood as data associated with the symptom information, and optionally, it can be the detection data when diagnosing the symptom, such as the patient's body temperature, blood pressure and other data; it can also be the medication information used to treat the symptom information, such as, for fever symptoms, the data to be processed can be the medication information such as drug A, drug B, drug C, etc. used to treat fever symptoms. It should be noted that a group of pending data corresponding to the current symptom information can be obtained for each preset platform, each group of pending data includes multiple pending data, each group of pending data corresponds to the corresponding preset platform, and each pending data includes medication information corresponding to the current symptom information, and medication information can be understood as drug information used to treat symptom information. For example, in hospital platform A, the diagnosis sheets of patients with fever symptoms in the hospital can be obtained, and the corresponding symptoms on each diagnosis sheet can be associated with the prescription sheet for the symptom issued by the doctor, and the prescription sheet can contain at least one drug information prescribed by the doctor for the symptom, and then multiple prescription sheet data for fever symptoms in hospital A can be obtained, and the drug information corresponding to the fever symptoms in each prescription sheet can be used as a pending data, that is, multiple pending data can be obtained, and then the obtained multiple pending data can be used as a group of pending data.

[0030] It should be noted that a corresponding system can be developed based on the present technical solution, and then the corresponding data can be processed based on the system to determine the corresponding target data. The system can be connected to each preset platform using a data interface, and then the interface engine can be used to retrieve the prescription data for the current symptom information of each preset platform system, and then the medication information corresponding to the current symptom information is obtained, that is, the data to be processed is obtained. It can also be that when it is detected that the preset platform uploads a prescription for the patient with the current symptom information, it can be considered that the server has received the data information on the prescription, and these data information can be used as the data to be processed corresponding to the current symptom information, that is, it is considered that the data to be processed is obtained.

[0031] It should also be noted that, by obtaining the multiple groups of to-be-processed data corresponding to the current symptom information for each preset platform, the current symptom information can be predetermined so that the to-be-processed data corresponding to a certain symptom information can be analyzed and processed. A group of to-be-processed data corresponding to the current symptom information can be obtained from each preset platform, that is, multiple groups of to-be-processed data corresponding to each preset platform can be obtained.

[0032] Optionally, obtaining multiple sets of data to be processed relative to each preset platform of the current symptom information includes: determining the current symptom information, and retrieving at least one set of data to be processed corresponding to the current symptom information from each preset platform, to obtain multiple sets of data to be processed corresponding to each preset platform.

[0033] It should be noted that the current symptom information can be determined by technical personnel according to actual working conditions, and the current symptom information is not specifically limited here.

[0034] Specifically, when the current symptom information is determined, the interface can be used to retrieve the prescription corresponding to the current symptom information from the preset platform system, the algorithm can be used to extract the medication information on each prescription, the medication information on each prescription can be used as a piece of data to be processed, and then multiple pieces of data to be processed corresponding to the current symptom information can be obtained, and the obtained multiple pieces of data to be processed can be used as a group of data to be processed, and accordingly, multiple groups of data to be processed corresponding to each preset platform can be obtained on each preset platform.

[0035] S120, obtaining at least one piece of medication association data corresponding to each group of data to be processed by performing association processing on the medication information in each group of data to be processed, and determining medication evidence information corresponding to each group of data to be processed based on the at least one piece of medication association data.

[0036] Among them, the medication association data can be understood as the medication rule information when treating the disease information. For example, the medication information on the prescription 1 issued by the doctor corresponding to a certain disease can include drug A and drug B, and the medication information on the prescription 2 can include drug A, drug B, and drug D. When treating the disease, the condition that drug A is prescribed and drug B is also prescribed can be regarded as a medication rule information, that is, the condition that drug A is prescribed and drug B is also prescribed can be regarded as a medication association data; the condition that drug B is prescribed and drug A is also prescribed can also be regarded as a medication association data. Medication evidence information can be understood as data information in another form of representation for medication association data and the confidence corresponding to medication association data. Confidence refers to the degree of credibility used to characterize medication association data. For example, the condition that drug A is prescribed and drug B is also prescribed, this medication association data can be recorded as A=>B, and the confidence (A=>B) can be the ratio of the number of records containing both A and B in the prescription to the number of records containing A in the prescription. For example, A=>B can be used as medication-related data 1, and its confidence is 2 / 2=1. When drug B is prescribed, drug A is also prescribed, that is, B=>A can be used as medication-related data 2, and its confidence is 2 / 2=1. Then, the confidences corresponding to the two medication-related data can be processed using a normalization algorithm, so that confidence (A=>B)+confidence (B=>A)=1, and the corresponding medication evidence information is obtained. The medication evidence information may include information such as A=>B, confidence (A=>B)=0.5, B=>A, confidence (B=>A)=0.5, etc. Accordingly, the medication-related data in each preset platform corresponding to the current symptom information can be determined, and then the medication evidence information corresponding to each group of data to be processed can be determined.

[0037] It should be noted that when the medication information of each group of data to be processed is obtained, the association rule algorithm can be used to associate the medication information in any group of data to be processed. For example, the medication information can be combined according to the preset rules to obtain multiple medication information sets, and then the corresponding medication information in each medication information set can be associated, and the medication association data composed of at least one medication information can be obtained, that is, the medication association data corresponding to the group of data to be processed is obtained. Accordingly, the medication association data corresponding to each group of data to be processed can be obtained. And the normalization algorithm can be used to process the corresponding medication association data and the corresponding confidence in each group of data to be processed to determine the medication evidence information corresponding to each group of data to be processed.

[0038] Specifically, in order to comprehensively consider the medication-related data corresponding to the medication information in each preset platform with different amounts of data to be processed, the medication information in each preset platform can be processed separately to obtain the medication-related data corresponding to each group of data to be processed, and the medication-related data corresponding to each group of data to be processed can be processed using an algorithm to generate medication evidence information corresponding to each group of data to be processed.

[0039] It should be noted that the medication information in each group of data to be processed can be obtained by obtaining the medication information on each prescription corresponding to the current symptom information corresponding to the data to be processed. The prescription can contain the drug information prescribed by the doctor for the current symptom information, that is, the medication information. When determining the medication-related data corresponding to each group of data to be processed based on the medication information in each group of data to be processed, the drug information on the prescription can be processed, such as association processing, and a drug information set consisting of at least one drug information can be obtained, such as drug A can be used as a drug information set, and drug A and drug B can also be used as a drug information set, and then the medication-related data corresponding to each drug information in each drug information set can be determined. Optionally, each drug information can be represented by a corresponding drug name.

[0040] Optionally, the data to be processed is a prescription corresponding to the current disease information, and the medication information includes the name of the medicine. The association processing is performed on the medication information in each group of data to be processed to obtain at least one medication association data corresponding to each group of data to be processed, including: determining the name of the medicine in each prescription in each group of data to be processed to obtain a set of medicine names corresponding to each group of data to be processed; for each set of medicine names, determining the medication association data corresponding to each medicine name in the current medicine name set, and the confidence level corresponding to the medication association data.

[0041] Among them, the prescription can be understood as a data sheet of medication information issued for the symptom information, and the prescription can contain multiple medication information. The drug name can be understood as the drug name. The drug name set can be understood as a set consisting of drug names corresponding to one or more medication information, such as drug A, drug B and drug C can be used as a drug name set, and drug A can also be used as a drug name set.

[0042] It should be noted that an algorithm can be used to process each prescription, extract the drug name corresponding to the drug information in each prescription in each group of data to be processed, and then the algorithm can be used to determine the drug name set corresponding to each drug information in each group of data to be processed. The algorithm can be an association rule algorithm, optionally, it can be an Apriori algorithm, or it can be an FP-Growth algorithm. For example, for fever symptoms, a group of data to be processed corresponding to the preset platform A can include prescription 1, prescription 2, and prescription 3. Prescription 1 can include drug names such as drug A, drug B, and drug C, prescription 2 can include drug names such as drug A, drug B, and drug D, and prescription 3 can include drug names such as drug A and drug D. The Apriori algorithm can be used to obtain the K-item set corresponding to the drug name set, and K can be 1, 2, 3, .... The K-item set is used to indicate that there are drug names corresponding to K drug information in the drug name set. The drug name set information of 1-item set can be obtained, that is, there is a drug name corresponding to drug information in the set, for example, the drug name set can be four sets of 1-item sets, namely {drug A}, {drug B}, {drug C} and {drug D}. Each drug name in each set can be counted, and then the count value corresponding to each drug name can be obtained, for example, the count value of drug A is 3, the count value of drug B is 2, the count value of drug C is 1, and the count value of drug D is 2. The support of the medication information in the drug name set in this set of data to be processed can be determined according to the count value corresponding to the drug name in the drug name set. The support is used to characterize the degree of support of all medication information in the drug name set appearing simultaneously in this set of data to be processed. The support of {drug A} is the ratio of the count of drug orders for drug A to the total count of drug orders, which can be 3 / 3=1, the support of {drug B} is 2 / 3, the support of {drug C} is 1 / 3, and the support of {drug D} is 2 / 3. The support corresponding to each drug name set is compared with the preset minimum support threshold. If the minimum support is 2 / 3, the drug name set with a support greater than or equal to the minimum support meets the preset minimum support condition, and the output drug name set that meets the minimum support condition is {drug A}, {drug B}, and {drug D}. The algorithm can be used to self-connect the drug name set that meets the conditions to find the set information of the drug name set as a 2-item set, such as the 2-item set drug name set can be {drug A, drug B}, {drug A, drug D}, {drug B, drug D}.At this time, the support of {drug A, drug B} is calculated to be 2 / 3, the support of {drug A, drug D} is 2 / 3, and the support of {drug B, drug D} is 1 / 3. According to the preset minimum support condition, the two sets of {drug A, drug B} and {drug A, drug D} are obtained. Then, the algorithm is used to self-connect {drug A, drug B} and {drug A, drug D} to find the set information of the drug name set as a 3-item set. The 3-item set is {drug A, drug B, drug D}, and the support is 1 / 3, which does not meet the preset minimum support condition. At this time, it is found that the set of drug names in the 3-item set that meets the preset minimum support condition is empty, and the search ends. Finally, the drug name sets that meet the preset minimum support condition are {drug A}, {drug B}, {drug A, drug B}, and then the algorithm can be used to associate the drug name sets to obtain {drug A}->{drug B}, {drug B}->{drug A}, {drug A}->{drug A, drug B}, {drug B}->{drug A, drug B} and other drug association data. The confidence of each drug association data can be compared with the preset minimum confidence threshold. If the confidence of the drug association data is greater than or equal to the preset minimum confidence threshold, the preset minimum confidence condition is met and it can be used as output. For example, if the preset minimum confidence threshold is 2 / 3, the confidence of {drug A}->{drug B} is 2 / 3, the confidence of {drug B}->{drug A} is 2 / 3, the confidence of {drug A}->{drug A, drug B} is 2 / 3, and the confidence of {drug B}->{drug A, drug B} is 2 / 3, then the preset minimum confidence condition is met, and {drug A}->{drug B}, {drug B}->{drug A}, {drug A}->{drug A, drug B}, {drug B}->{drug A, drug B} can be output as the final medication association data. Accordingly, the medication association data in each group of data to be processed and the confidence corresponding to the medication association data can be obtained.

[0043] It should also be noted that in the process of using the association rule algorithm to determine the medication association data corresponding to the data to be processed, the preset minimum support threshold and the preset minimum confidence threshold can be determined by the technician according to the actual working situation, which can be understood by people in this technical field.

[0044] It should also be noted that if the obtained medication-related data is less than the preset threshold value of the number of associated data, it can be said that the obtained medication-related data does not meet the preset expected information, and the numerical values ​​of the preset minimum support threshold and the preset minimum confidence threshold can be adjusted accordingly; the amount of data to be processed can also be adjusted accordingly, such as increasing the amount of data; algorithms can also be used to check and process the data to be processed, such as checking whether the names of the drugs in the same category are consistent.

[0045] Specifically, the algorithm can be used to extract data features in each prescription in each group of data to be processed, and each data feature can be used as medication information to identify the name of the medicine corresponding to each medication information. Then, the Apriori algorithm can be used to calculate the set of medicine names that meets the preset minimum support condition, and then each medicine name set can be associated to obtain medication association data composed of at least one medicine name set that meets the preset minimum confidence condition, and then the confidence corresponding to each medication association data can be obtained.

[0046] It should be noted that each group of data to be processed may contain multiple medication-related data. In order to subsequently integrate the medication-related data in each group of data to be processed as a whole to obtain the final medication-related data, the medication-related data in each group of data to be processed may be processed into a unified format. Thus, a basic processing template data may be used to process each group of medication-related data, and then, based on the basic processing template data, the related data information after processing of each group of medication-related data may be obtained.

[0047] Optionally, determining the medication evidence information corresponding to each group of data to be processed based on the at least one medication-related data includes: obtaining basic fused data by fusing at least one medication-related data of each group of data to be processed; and determining the medication evidence information corresponding to the at least one medication-related data based on the basic fused data.

[0048] Among them, the basic fusion data can be understood as the basic template data used to process each group of medication-related data into a data volume of the same size.

[0049] It should be noted that the algorithm can be used to splice the medication-related data in each group of data to be processed, and the spliced ​​data of each medication-related data can be used as the basic fusion data. Optionally, it can be defined R i It can represent any medication-related data in the data to be processed, that is, the medication-related data in each medication-related data set, i is a natural number, which can be 1, 2, 3, ..., N. R' represents the medication-related data in the basic fusion data. The confidence calculation formula can be used R k It can be expressed as the kth medication association data, Conf(R k ) can be expressed as R k If the confidence Then R kThe confidence can be 0, that is, the missing medication-related data in each medication-related data set can be supplemented. For example, the medication-related data of group 1 can be [A, B, C], the medication-related data of group 2 can be [B, C, E], and the medication-related data of group 3 can be [D, E, A]. The algorithm can be used to splice the medication-related data, and at the same time, the medication-related data can be compared, so that the medication-related data in the final spliced ​​data only appears once, and then the [A, B, C, E, D] data can be obtained, and the data can be used as the basic fusion data. The algorithm can be used to compare the basic fusion data with the medication-related data in each group, and each group of medication-related data can be supplemented at the same time, that is, the missing medication-related data in each group of medication-related data can be supplemented. For example, the basic fusion data [A, B, C, E, D] can be compared with the medication-related data in each group according to the data order in the data set. For example, A is compared with the data in [A, B, C]. If [A, B, C] contains A, the comparison is successful, and the next data comparison operation is performed. B is successfully compared with the data in [A, B, C], C is successfully compared with the data in [A, B, C], and E is unsuccessful in comparing with the data in [A, B, C]. The comparison position of [A, B, C] can be supplemented with 0, that is, the medication-related data at this position is 0, and its confidence is also 0. If the comparison between D and the data in [A,B,C] is unsuccessful, the comparison position of [A,B,C] can be filled with 0, and then the processed [A,B,C,0,0] corresponding to the group of medication-related data can be output in the comparison order. Accordingly, after processing the medication-related data of group 2, [0,B,C,E,0] can be obtained, and the medication-related data of group 3 can be obtained [A,0,0,E,D].Furthermore, the confidence corresponding to the processed medication association data can be normalized by using an algorithm. For example, in the three groups of medication association data [A, B, C, 0, 0], [0, B, C, E, 0], and [A, 0, 0, E, D], the confidence of A can be 1, the confidence of B can be 0.4, the confidence of C can be 0.6, the confidence of E can be 1, and the confidence of D can be 0.4. The sum of the confidences of the medication association data in each group of data to be processed must meet a preset threshold. For example, the threshold can be 1, that is, the sum of the confidences of the medication association data can be equal to 1. Then, the confidence of A in [A, B, C, 0, 0] can be normalized after processing. The confidence of A is 0.5, the confidence of B can be 0.2 after processing, and the confidence of C can be 0.3 after processing. The processed confidence can be used as the confidence distribution for each medication-related data, and then the processed medication-related data and the corresponding confidence in each group of data to be processed can be obtained. Each group of processed medication-related data can be used as a medication evidence information, and then multiple medication evidence information can be obtained. That is to say, each group of data to be processed can have a corresponding medication evidence information, and the medication evidence information can include multiple medication-related data processed by the algorithm, and the data amount of the medication-related data in each medication evidence information is consistent.

[0050] Specifically, an algorithm can be used to splice each medication-related data in each group of data to be processed, that is, to fuse each medication-related data, obtain the data after splicing and fusion of all medication-related data, and obtain basic fusion data. Then, the medication-related data in each group of data to be processed can be compared based on the basic fusion data, and the missing medication-related data in each group of medication-related data can be filled. Optionally, 0 can be filled, and the confidence corresponding to the medication-related data that is 0 can also be 0. After obtaining the medication-related data set composed of each group of medication-related data after processing and updating, the confidence corresponding to each medication-related data can be normalized using a normalization algorithm. The processed confidence can be used as the confidence of each medication-related data in the medication-related data set, or each medication-related data set can be used as medication evidence information. Accordingly, multiple medication evidence information can be obtained.

[0051] S130. Process the medication evidence information corresponding to each group of data to be processed based on a preset evidence processing algorithm to obtain target medication evidence information to be processed corresponding to each medication evidence information.

[0052] Among them, the preset evidence processing algorithm can be understood as a preset algorithm for updating each medication evidence information and generating target medication evidence information to be processed corresponding to each medication evidence information. The target medication evidence information to be processed can be understood as the evidence information that is fused after the medication evidence information is updated and processed. For example, each medication evidence information can be updated and processed using an algorithm, and then the medication evidence information after each update can be fused and processed to generate a medication evidence information, which can be used as the target medication evidence information to be processed.

[0053] It should be noted that an algorithm can be used to assign corresponding weight values ​​to the medication evidence information corresponding to each group of data to be processed to obtain weighted updated medication evidence information. After obtaining the updated medication evidence information, each medication evidence information can be integrated and processed. For example, the medication-related data in each weighted updated medication evidence information and the confidence corresponding to the medication-related data can be integrated and calculated, and the correspondence of each medication-related data can be integrated into a new medication evidence information set. Correspondingly, the confidence corresponding to each medication-related data can be added and averaged to obtain a new medication evidence information set. The medication evidence information set can be used as a new medication evidence information, and the new medication evidence information can be used as the target medication evidence information to be processed.

[0054] Specifically, the algorithm can be used to assign corresponding weight values ​​to the medication evidence information corresponding to each group of data to be processed, so as to obtain weighted updated medication evidence information. Furthermore, the algorithm can be used to fuse each medication evidence information assigned with a corresponding weight value, so as to obtain the target medication evidence information to be processed after the weighted updated medication evidence information is fused.

[0055] S140, determining the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target medication association data in the target medication evidence information.

[0056] The target pending medication association data can be understood as the medication association data in the target pending medication evidence information. The target medication evidence information can be understood as the medication evidence information after the target pending medication evidence information is updated. The target medication association data can be understood as the medication association data in the target medication evidence information.

[0057] It should be noted that after obtaining the target medication evidence information to be processed after updating and fusion processing of each medication evidence information, the target medication evidence information to be processed can also be processed, such as updating processing, the confidence corresponding to the medication-related data in the target medication evidence information to be processed can be combined and updated by using an algorithm to obtain the confidence information of the new medication evidence information, and the medication evidence information can be used as the target medication evidence information. The medication-related information in the target medication evidence information can be used as the target medication-related data, and the confidence information after the algorithm update processing is the confidence corresponding to each target medication-related information.

[0058] Specifically, the confidence corresponding to the medication-related data in the target medication evidence information to be processed may be updated using an algorithm, and an updated target medication evidence information to be processed, namely, the target medication evidence information, may be obtained.

[0059] The technical solution of this embodiment obtains multiple groups of to-be-processed data relative to each preset platform for current symptom information; obtains medication-related data corresponding to each group of to-be-processed data by associating medication information in each group of to-be-processed data, and determines medication evidence information corresponding to each group of to-be-processed data; processes medication evidence information corresponding to each group of to-be-processed data to obtain target to-be-processed medication evidence information corresponding to each medication evidence information; determines target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication-related data in the target medication evidence information by analyzing and processing each target to-be-processed medication-related data in the target to-be-processed medication evidence information, thereby solving the problem in the prior art of making a diagnosis of a disease by consulting a large amount of historical drug prescription data or combining personal subjective experience. There is a problem of low prescription efficiency in issuing drug prescriptions. Based on the association rule algorithm, the pending data of each preset platform for the current disease information is processed separately to determine the drug association information corresponding to each preset platform, and then each group of drug association information is converted into corresponding drug evidence information using the DS evidence theory. At the same time, each drug evidence information is weighted averaged to obtain the drug association information and the corresponding confidence in the final target evidence information. The credibility of the prescription plan for the disease information of the preset platform with different data sizes is comprehensively considered, and the reliability of the determination of drug association information is improved, so that the drug association information with higher confidence can provide a theoretical basis for the clinical rational drug use and the explanation of the drug mechanism in the future, which is convenient for medical staff to issue reasonable prescriptions for the disease information.

[0060] Embodiment 2

[0061] Figure 2This is a flow chart of a target data determination method provided in the second embodiment of the present invention. Based on the above embodiment, S130 and S140 are further refined. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiment are not repeated here.

[0062] like Figure 2 As shown, the method specifically comprises the following steps:

[0063] S210 . For each symptom information, obtain multiple groups of to-be-processed data of the current symptom information relative to each preset platform.

[0064] S220, obtaining at least one piece of medication association data corresponding to each group of data to be processed by performing association processing on the medication information in each group of data to be processed, and determining medication evidence information corresponding to each group of data to be processed based on the at least one piece of medication association data.

[0065] S230. If the amount of the medication evidence information is greater than a preset threshold, then for each medication evidence information, determine the evidence distance value between the current medication evidence information and each medication evidence information based on the preset evidence algorithm, and determine the evidence distance matrix based on each evidence distance value.

[0066] Among them, the evidence distance value can be used to characterize the difference between two pieces of medication evidence information, and can also be used to characterize the difference in the determination of medication association information of the current disease information by two preset platforms under two pieces of medication evidence information. The larger the evidence distance value, the greater the difference, and vice versa, the smaller the evidence distance value, the smaller the difference. The evidence distance matrix refers to a matrix used to represent the distance relationship between any two pieces of medication evidence information. The distance between any one piece of medication evidence information and other pieces of medication evidence information can be determined based on the evidence distance matrix.

[0067] It should be noted that if the amount of medication evidence information is greater than the preset number threshold, optionally, the preset number threshold can be 2, that is, at this time the preset platform is greater than 2, and the data to be processed is greater than two groups, the evidence distance value between the current medication evidence information and each medication evidence information can be calculated based on the preset evidence algorithm.

[0068] It should also be noted that the distance algorithm can be used to process the medication association information in any two medication evidence information, and optionally, it can be a Jousselme distance algorithm or a Euclidean distance algorithm. For example, the Jousselme distance algorithm can be used as an example to introduce the technical solution, and the algorithm can be used to represent the medication association information in each medication evidence information as a vector in a high-dimensional space. The calculation method of the Jousselme distance can be Formula 1:

[0069]

[0070] in, Represented as medication evidence information m i , Represented as medication evidence information m j , d ij Medication evidence information i and medication evidence information j The distance value between Medication evidence information i and medication evidence information j The inner product of , i,j=1,2,…,n.

[0071] Furthermore, the distance value between each medication evidence information and other medication evidence information can be obtained, and each distance value information can be integrated and processed to generate each evidence distance value to determine the evidence distance matrix. The evidence distance matrix can be as follows:

[0072]

[0073] Specifically, the Jousselme distance algorithm may be used to calculate the evidence distance value between the current medication evidence information and each medication evidence information, and the generated evidence distance values ​​may be integrated to generate a corresponding evidence distance matrix.

[0074] S240: For each piece of medication evidence information, determine the average distance between the current medication evidence information and each piece of medication evidence information according to the evidence distance matrix.

[0075] The average distance can be understood as the average value of the distance between any medication evidence information and other medication evidence information.

[0076] Specifically, an algorithm may be used to retrieve the evidence distance value between the current medication evidence information and each medication evidence information. Further, optionally, Formula 2 may be used to calculate the average distance between the current medication evidence information and each medication evidence information.

[0077]

[0078] in, Represented as medication evidence information m i The corresponding average distance, n is the sum of the number of medication evidence information. For example, the average distance corresponding to the current medication evidence information can be the ratio of the sum of the evidence distance values ​​between the current medication evidence information and each medication evidence information to the sum of the number of remaining medication evidence information other than the current medication evidence information. Accordingly, the average distance corresponding to each medication evidence information can be determined.

[0079] S250: Determine target medication evidence information to be processed based on medication evidence information of each medication evidence information and the corresponding average distance.

[0080] It should be noted that the average distances corresponding to each medication evidence information can be compared using an algorithm to obtain a weight coefficient corresponding to the corresponding average distance. Each weight coefficient can be multiplied with the corresponding medication evidence information to obtain new medication evidence information, and multiple medication evidence information processed by the weight coefficient can be obtained. It should also be noted that the larger the average distance of the medication evidence information, the greater the difference between the medication evidence information and other medication evidence information, and accordingly, a smaller weight coefficient can be assigned to the medication evidence information. On the contrary, the larger the average distance of the medication evidence information, the smaller the difference between the medication evidence information and other medication evidence information, and accordingly, a larger weight coefficient can be assigned to the medication evidence information, and different weight coefficient values ​​can be assigned to each medication evidence information according to the size of the average distance.

[0081] Optionally, the target medication evidence information to be processed is determined based on the medication evidence information of each medication evidence information and the corresponding average distance, including: for each medication evidence information, according to the average distance of the current medication evidence information, determining the evidence weight value of the current medication evidence information; according to each medication evidence information and the corresponding evidence weight value, determining the target medication evidence information to be processed.

[0082] Among them, the evidence weight value can be understood as the weight information corresponding to the medication evidence information.

[0083] It should be noted that the average distance of the medication evidence information is inversely proportional to the evidence weight value of the medication evidence information. Optionally, Formula 3 can be used to assign a corresponding evidence weight value to each medication evidence information.

[0084]

[0085] Among them, w i Represented as medication evidence information m i The corresponding weight of evidence value.

[0086] Specifically, an algorithm can be used to fuse the evidence weight values ​​of each medication evidence information obtained with the medication-related data in the medication evidence information. For example, the corresponding medication evidence information can be weighted based on the evidence weight values ​​of each medication evidence information to obtain weighted medication evidence information corresponding to each medication evidence information. Furthermore, each weighted medication evidence information can be averaged. For example, a mathematical logic algorithm can be used to add each medication evidence information, and then the added data information is averaged, that is, the ratio of the data after the addition of each medication evidence information to the quantitative value corresponding to the medication evidence information is obtained to obtain a fused medication evidence information, which can be used as the target medication evidence information to be processed.

[0087] S260: self-combine the target medication evidence information to be processed to obtain the target evidence information and the confidence level of each target medication association data in the target evidence information.

[0088] It should be noted that in order to make the average evidence method have the convergence of combined medication association data, the averaged target medication evidence information can be combined with itself. Optionally, if there are n medication evidence information, the target medication evidence information needs to be self-combined n-1 times, n is a natural number, for example, if there are 2 medication evidence information, the target medication evidence information needs to be self-combined once, and if there are 5 medication evidence information, the target medication evidence information needs to be self-combined 4 times.

[0089] It should also be noted that if the amount of medication evidence information is less than the preset quantity threshold, each medication evidence information can be processed to obtain the target medication evidence information to be processed. For example, optionally, the preset quantity threshold is 2, that is, at this time there are 2 groups of to-be-processed data corresponding to the preset platform, corresponding to 2 pieces of medication evidence information, and the Murphy synthesis rule can be used to perform evidence fusion processing on these two pieces of medication evidence information, such as, the confidence corresponding to the medication association information in the two pieces of medication evidence information can be added and averaged accordingly, and a new piece of evidence information can be obtained after fusion, and the evidence information can be used as the target medication evidence information to be processed. Furthermore, the target medication evidence information to be processed can be self-combined once using an algorithm, and the algorithm can be a DS evidence synthesis algorithm, and a final piece of evidence information can be obtained, and the evidence information can be used as the target evidence information, and accordingly, each target medication association data and the corresponding confidence in the target evidence information are obtained.

[0090] It should also be noted that if the amount of medication evidence information is greater than the preset quantity threshold, the target medication evidence information to be processed is determined based on each medication evidence information and the corresponding evidence weight value. Optionally, the preset quantity threshold can be 2. Furthermore, the DS evidence synthesis algorithm can be used to self-combine the target medication evidence information to be processed. For example, Formula 4 can be used to self-combine the target medication association data and the corresponding confidence in the target medication evidence information to be processed.

[0091]

[0092] Among them, m i ' represents the target medication evidence information to be processed m i The medication evidence information generated after self-combination processing, A m , A n Represented as m i The target medication association data to be processed in, X represents m i 'The target medication association data to be processed, is represented as an empty set. For example, m i Target medication association data A to be processed m The corresponding confidence level is 0.99, m i After self-combination, the target medication association data A to be processed m The corresponding confidence level may be updated to 0.999, and the updated target pending medication evidence information may be obtained, and the target pending medication evidence information may be used as the target evidence information.

[0093] Specifically, the DS evidence synthesis algorithm can be used to perform self-combination processing on the target medication evidence information to be processed, and the processed target medication evidence information to be processed can be used as the target evidence information to obtain the target medication association data and the corresponding confidence in the final target evidence information.

[0094] The technical solution of this embodiment obtains multiple groups of to-be-processed data relative to each preset platform for current symptom information; obtains medication-related data corresponding to each group of to-be-processed data by associating medication information in each group of to-be-processed data, and determines medication evidence information corresponding to each group of to-be-processed data; processes medication evidence information corresponding to each group of to-be-processed data to obtain target to-be-processed medication evidence information corresponding to each medication evidence information; determines target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication-related data in the target medication evidence information by analyzing and processing each target to-be-processed medication-related data in the target to-be-processed medication evidence information, thereby solving the problem in the prior art of making a diagnosis of a disease by consulting a large amount of historical drug prescription data or combining personal subjective experience. There is a problem of low prescription efficiency in issuing drug prescriptions. Based on the association rule algorithm, the pending data of each preset platform for the current disease information is processed separately to determine the drug association information corresponding to each preset platform, and then each group of drug association information is converted into corresponding drug evidence information using the DS evidence theory. At the same time, each drug evidence information is weighted averaged to obtain the drug association information and the corresponding confidence in the final target evidence information. The credibility of the prescription plan for the disease information of the preset platform with different data sizes is comprehensively considered, and the reliability of the determination of drug association information is improved, so that the drug association information with higher confidence can provide a theoretical basis for the clinical rational drug use and the explanation of the drug mechanism in the future, which is convenient for medical staff to issue reasonable prescriptions for the disease information.

[0095] Embodiment 3

[0096] As an alternative embodiment of the above embodiment, Figure 3 This is a flowchart of a method for determining target data provided in Embodiment 3 of the present invention. For details, please refer to the following specific content.

[0097] For example, Figure 3 As shown, according to the specified disease information, the corresponding data set to be processed is obtained in each preset platform, that is, each preset platform corresponds to a set of data sets to be processed, and then the Apriori algorithm can be used to mine association rules for each set of data to be processed, and the minimum support and minimum confidence thresholds are set according to experience, and the medication association data set that meets the conditions is output. Each set of data sets to be processed corresponds to a medication association data set, and the medication association data set contains medication association data and confidence. If the output medication association data is not ideal, for example, the number of medication association data is less than the preset threshold, the input data and the minimum support and minimum confidence thresholds can be readjusted. The medication association data and the corresponding confidence in each medication association data set can be converted into evidence that conforms to the definition of DS evidence theory using an algorithm, and each medication association data set corresponds to a medication evidence information mi , the confidence in each medication association data set can be normalized to obtain the confidence distribution. Since the medication association data in different medication association data sets may be different, we can define Use the confidence calculation formula The missing medication-related data in each medication-related data set are supplemented. Furthermore, the average distance between each medication evidence information and other medication evidence information can be calculated. The distance between evidences is calculated using the Jousellme distance. i and m j The distance between them can be obtained as a distance matrix, which is as follows:

[0098]

[0099] Among them, i,j=1,2,…,n.

[0100] Further, medication evidence information i The average distance calculation formula to other medication evidence information is as follows:

[0101]

[0102] Furthermore, the evidence weight value corresponding to each medication evidence information can be calculated, evidence m i The corresponding weight w i The calculation formula is as follows:

[0103]

[0104] Furthermore, a new piece of evidence m may be obtained by weighted averaging all medication evidence information according to the evidence weight value corresponding to each piece of medication evidence information.

[0105] Furthermore, the DS evidence synthesis rule can be used to implement n-1 self-combinations on the new evidence m to obtain the final medication-related data and the corresponding confidence level. When the number of evidence n is 2, that is, there are 2 preset platforms corresponding to the data to be processed, each medication-related data set is obtained to correspond to a medication evidence information m i Afterwards, the medication evidence information can be fused according to Murphy's synthesis rule to obtain the final medication association data and the corresponding confidence level.

[0106] The technical solution of this embodiment obtains multiple groups of to-be-processed data relative to each preset platform for current symptom information; obtains medication-related data corresponding to each group of to-be-processed data by associating medication information in each group of to-be-processed data, and determines medication evidence information corresponding to each group of to-be-processed data; processes medication evidence information corresponding to each group of to-be-processed data to obtain target to-be-processed medication evidence information corresponding to each medication evidence information; determines target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication-related data in the target medication evidence information by analyzing and processing each target to-be-processed medication-related data in the target to-be-processed medication evidence information, thereby solving the problem in the prior art of making a diagnosis of a disease by consulting a large amount of historical drug prescription data or combining personal subjective experience. There is a problem of low prescription efficiency in issuing drug prescriptions. Based on the association rule algorithm, the pending data of each preset platform for the current disease information is processed separately to determine the drug association information corresponding to each preset platform, and then each group of drug association information is converted into corresponding drug evidence information using the DS evidence theory. At the same time, each drug evidence information is weighted averaged to obtain the drug association information and the corresponding confidence in the final target evidence information. The credibility of the prescription plan for the disease information of the preset platform with different data sizes is comprehensively considered, and the reliability of the determination of drug association information is improved, so that the drug association information with higher confidence can provide a theoretical basis for the clinical rational drug use and the explanation of the drug mechanism in the future, which is convenient for medical staff to issue reasonable prescriptions for the disease information.

[0107] Embodiment 4

[0108] Figure 4 This is a structural block diagram of a target data determination device provided in Embodiment 4 of the present invention. The device comprises: a to-be-processed data acquisition module 410 , a medication evidence information determination module 420 , a target to-be-processed medication evidence information determination module 430 , and a target medication evidence information determination module 440 .

[0109] The module for obtaining data to be processed 410 is used to obtain, for each symptom information, multiple groups of data to be processed of the current symptom information relative to each preset platform; each group of data to be processed includes multiple data to be processed, each group of data to be processed corresponds to a corresponding preset platform, and each data to be processed includes medication information corresponding to the current symptom information; the module for determining medication evidence information 420 is used to obtain at least one medication association data corresponding to each group of data to be processed by associating the medication information in each group of data to be processed, and determine, based on the at least one medication association data, Medication evidence information corresponding to each group of data to be processed; a target medication evidence information determination module 430, which is used to process the medication evidence information corresponding to each group of data to be processed based on a preset evidence processing algorithm to obtain target medication evidence information corresponding to each medication evidence information; a target medication evidence information determination module 440, which is used to determine the target medication evidence information corresponding to the current disease information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target medication association data in the target medication evidence information.

[0110] The technical solution of this embodiment obtains multiple groups of to-be-processed data relative to each preset platform for current symptom information; obtains medication-related data corresponding to each group of to-be-processed data by associating medication information in each group of to-be-processed data, and determines medication evidence information corresponding to each group of to-be-processed data; processes medication evidence information corresponding to each group of to-be-processed data to obtain target to-be-processed medication evidence information corresponding to each medication evidence information; determines target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication-related data in the target medication evidence information by analyzing and processing each target to-be-processed medication-related data in the target to-be-processed medication evidence information, thereby solving the problem in the prior art of making a diagnosis of a disease by consulting a large amount of historical drug prescription data or combining personal subjective experience. There is a problem of low prescription efficiency in issuing drug prescriptions. Based on the association rule algorithm, the pending data of each preset platform for the current disease information is processed separately to determine the drug association information corresponding to each preset platform, and then each group of drug association information is converted into corresponding drug evidence information using the DS evidence theory. At the same time, each drug evidence information is weighted averaged to obtain the drug association information and the corresponding confidence in the final target evidence information. The credibility of the prescription plan for the disease information of the preset platform with different data sizes is comprehensively considered, and the reliability of the determination of drug association information is improved, so that the drug association information with higher confidence can provide a theoretical basis for the clinical rational drug use and the explanation of the drug mechanism in the future, which is convenient for medical staff to issue reasonable prescriptions for the disease information.

[0111] On the basis of the above device, optionally, the to-be-processed data acquisition module 410 includes a group of to-be-processed data determination units.

[0112] The group of to-be-processed data determining unit is used to determine the current symptom information and retrieve at least one to-be-processed data corresponding to the current symptom information from each preset platform to obtain multiple groups of to-be-processed data corresponding to each preset platform.

[0113] On the basis of the above device, optionally, the medication evidence information determination module 420 includes: a medication association data determination unit and a medication evidence information determination unit.

[0114] The medication-related data determination unit is specifically used to determine the name of the medicine in each prescription in each group of data to be processed, and obtain a set of medicine names corresponding to each group of data to be processed; for each set of medicine names, determine the medication-related data corresponding to each medicine name in the current medicine name set, and the confidence level corresponding to the medication-related data.

[0115] The medication evidence information determination unit is specifically used to obtain basic fused data by fusing at least one medication-related data of each group of data to be processed; and determine medication evidence information corresponding to at least one medication-related data according to the basic fused data.

[0116] Based on the above device, optionally, the target medication evidence information determination module 430 includes a target medication evidence information determination unit. The target medication evidence information determination unit includes an evidence distance matrix determination subunit, an average distance determination subunit and a target medication evidence information determination subunit.

[0117] The evidence distance matrix determination subunit is used to determine the evidence distance value between the current medication evidence information and each medication evidence information based on the preset evidence algorithm if the amount of the medication evidence information is greater than a preset amount threshold, and determine the evidence distance matrix based on each evidence distance value.

[0118] The average distance determination subunit is used to determine, for each medication evidence information, the average distance between the current medication evidence information and each medication evidence information according to the evidence distance matrix.

[0119] The target medication evidence information to be processed determining subunit is used to determine the target medication evidence information to be processed based on the medication evidence information of each medication evidence information and the corresponding average distance.

[0120] Based on the above device, optionally, the target medication evidence information to be processed determining subunit includes a target medication evidence information to be processed determining first unit.

[0121] The first unit for determining the target medication evidence information to be processed is specifically used to determine the evidence weight value of the current medication evidence information according to the average distance of the current medication evidence information for each medication evidence information; and determine the target medication evidence information to be processed according to each medication evidence information and the corresponding evidence weight value.

[0122] Based on the above device, optionally, the target medication evidence information determination module 440 includes a target evidence information determination unit.

[0123] The target evidence information determination unit is used to perform self-combination processing on the target medication evidence information to be processed to obtain the target evidence information and the confidence of each target medication association data in the target evidence information.

[0124] The target data determination device provided in the embodiment of the present invention can execute the target data determination method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0125] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0126] Embodiment 5

[0127] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Figure 5 A block diagram of an exemplary electronic device 50 suitable for implementing exemplary embodiments of the present invention is shown. Figure 5 The electronic device 50 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0128] like Figure 5 As shown, the electronic device 50 is in the form of a general computing device. The components of the electronic device 50 may include but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 connecting different system components (including the system memory 502 and the processing unit 501).

[0129] Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0130] The electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0131] System memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 504 and / or cache memory 505. Electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 506 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, 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, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 503 via one or more data medium interfaces. The memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0132] A program / utility 508 having a set (at least one) of program modules 507 may be stored, for example, in the memory 502, such program modules 507 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 507 generally perform the functions and / or methods of the embodiments described herein.

[0133] The electronic device 50 may also communicate with one or more external devices 509 (e.g., keyboards, pointing devices, displays 510, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 50, and / or communicate with any device that enables the electronic device 50 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 511. Furthermore, the electronic device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 512. As shown, the network adapter 512 communicates with other modules of the electronic device 50 through the bus 503. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0134] The processing unit 501 executes various functional applications and data processing by running the programs stored in the system memory 502, such as implementing the target data determination method provided in the embodiment of the present invention.

[0135] Embodiment 6

[0136] Embodiment 6 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a target data determination method when executed by a computer processor. The method includes:

[0137] For each symptom information, multiple groups of to-be-processed data of the current symptom information relative to each preset platform are obtained; wherein each group of to-be-processed data includes multiple to-be-processed data, each group of to-be-processed data corresponds to a corresponding preset platform, and each to-be-processed data includes medication information corresponding to the current symptom information;

[0138] By performing association processing on the medication information in each group of data to be processed, at least one piece of medication association data corresponding to each group of data to be processed is obtained, and based on the at least one piece of medication association data, medication evidence information corresponding to each group of data to be processed is determined;

[0139] Based on a preset evidence processing algorithm, the medication evidence information corresponding to each group of data to be processed is processed to obtain target medication evidence information to be processed corresponding to each medication evidence information;

[0140] By analyzing and processing each target medication association data in the target medication evidence information, the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information are determined.

[0141] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0142] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0143] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0144] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0145] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining target data, characterized in that: include: For each symptom information, multiple groups of to-be-processed data of the current symptom information relative to each preset platform are obtained; wherein each group of to-be-processed data includes multiple to-be-processed data, each group of to-be-processed data corresponds to a corresponding preset platform, and each to-be-processed data includes medication information corresponding to the current symptom information; By performing association processing on the medication information in each group of data to be processed, at least one piece of medication association data corresponding to each group of data to be processed is obtained, and based on the at least one piece of medication association data, medication evidence information corresponding to each group of data to be processed is determined; Based on a preset evidence processing algorithm, the medication evidence information corresponding to each group of data to be processed is processed to obtain target medication evidence information to be processed corresponding to each medication evidence information; Determine the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target medication association data in the target medication evidence information; Wherein, determining the medication evidence information corresponding to each group of data to be processed according to the at least one medication association data includes: By fusing at least one piece of medication-related data of each group of data to be processed, basic fused data is obtained; Determining medication evidence information corresponding to at least one medication-related data according to the basic fusion data; The method of obtaining basic fused data by fusing at least one piece of medication-related data in each group of data to be processed includes: The medication-related data in each group of data to be processed are spliced ​​by using an algorithm, and the medication-related data are compared with each other, so that the medication-related data in the final spliced ​​data appears only once, thereby obtaining the basic fused data; wherein the basic fused data is used to process each group of medication-related data into basic template data with the same data volume; Wherein, determining medication evidence information corresponding to at least one medication association data according to the basic fusion data includes: Compare and process the medication-related data in each group of data to be processed based on the basic fusion data, and complete the missing medication-related data in each group of data to be processed to obtain processed medication-related data for each group of data to be processed; Normalizing the confidences corresponding to the medication-related data to obtain the confidences of the processed medication-related data in each group of data to be processed; Each group of data to be processed is used as a medication evidence information to obtain at least one medication evidence information; wherein each medication evidence information includes a plurality of medication-related data processed by an algorithm, and the data amount of the medication-related data in each medication evidence information is consistent.

2. The method according to claim 1, characterized in that The obtaining of the current disease information relative to multiple groups of to-be-processed data of each preset platform includes: The current symptom information is determined, and at least one to-be-processed data corresponding to the current symptom information is retrieved from each preset platform to obtain multiple groups of to-be-processed data corresponding to each preset platform.

3. The method according to claim 1, characterized in that The data to be processed is a prescription corresponding to the current symptom information, the medication information includes the name of the medicine, and the at least one medication association data corresponding to each group of data to be processed is obtained by performing association processing on the medication information in each group of data to be processed, including: Determine the name of the medicine in each prescription in each group of data to be processed, and obtain a set of medicine names corresponding to each group of data to be processed; For each drug name set, the medication association data corresponding to each drug name in the current drug name set and the confidence level corresponding to the medication association data are determined.

4. The method according to claim 1, characterized in that: The method of processing the medication evidence information corresponding to each group of data to be processed based on a preset evidence processing algorithm to obtain target medication evidence information to be processed corresponding to each medication evidence information includes: If the amount of the medication evidence information is greater than a preset amount threshold, then for each medication evidence information, based on the preset evidence processing algorithm, determine the evidence distance value between the current medication evidence information and each medication evidence information, and determine the evidence distance matrix based on each evidence distance value; For each medication evidence information, determining the average distance between the current medication evidence information and each medication evidence information according to the evidence distance matrix; Based on the medication evidence information of each medication evidence information and the corresponding average distance, the target medication evidence information to be processed is determined.

5. The method according to claim 4, characterized in that The determining of the target medication evidence information to be processed based on the medication evidence information of each medication evidence information and the corresponding average distance includes: For each piece of medication evidence information, determine the evidence weight value of the current medication evidence information according to the average distance of the current medication evidence information; According to each piece of medication evidence information and the corresponding evidence weight value, the target medication evidence information to be processed is determined.

6. The method according to claim 1, characterized in that The step of analyzing and processing each target medication association data in the target medication evidence information to be processed to determine the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information includes: The target medication evidence information to be processed is processed by self-combination to obtain the target medication evidence information and the confidence of each target medication association data in the target medication evidence information.

7. A target data determination device, characterized in that: include: The module for acquiring data to be processed is used to acquire, for each symptom information, multiple groups of data to be processed of the current symptom information relative to each preset platform; wherein each group of data to be processed includes multiple data to be processed, each group of data to be processed corresponds to a corresponding preset platform, and each data to be processed includes medication information corresponding to the current symptom information; a medication evidence information determination module, configured to obtain at least one medication association data corresponding to each group of data to be processed by performing association processing on the medication information in each group of data to be processed, and determine medication evidence information corresponding to each group of data to be processed based on the at least one medication association data; A target medication evidence information determination module is used to process the medication evidence information corresponding to each group of data to be processed based on a preset evidence processing algorithm to obtain target medication evidence information corresponding to each medication evidence information; a target medication evidence information determination module, configured to determine the target medication evidence information corresponding to the current symptom information and the confidence corresponding to each target medication association data in the target medication evidence information by analyzing and processing each target medication association data in the target medication evidence information; Wherein, the medication evidence information determination module includes: a medication association data determination unit and a medication evidence information determination unit; The medication evidence information determination unit is used to obtain basic fused data by fusing at least one medication-related data of each group of data to be processed; and determine medication evidence information corresponding to at least one medication-related data according to the basic fused data; The medication evidence information determination unit is specifically used to splice the medication-related data in each group of data to be processed using an algorithm, and compare the medication-related data to make the medication-related data in the final spliced ​​data appear only once, thereby obtaining the basic fusion data; wherein the basic fusion data is used to process each group of medication-related data into basic template data with the same data volume; Among them, the medication evidence information determination unit is specifically used to compare and process the medication-related data in each group of data to be processed based on the basic fusion data, and to complete the missing medication-related data in each group of data to be processed to obtain the processed medication-related data of each group of data to be processed; to normalize the confidence corresponding to each medication-related data to obtain the confidence of the processed medication-related data in each group of data to be processed; to take each group of data to be processed as a medication evidence information to obtain at least one medication evidence information; wherein, each medication evidence information includes multiple medication-related data processed by the algorithm, and the data amount of the medication-related data in each medication evidence information is consistent.

8. An electronic device, characterized in that: The device comprises: one or more processors; a storage device 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 target data determination method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the target data determination method as described in any one of claims 1 to 6 is implemented.

Images