CN116959750B

CN116959750B - Data analysis method, device, electronic equipment and medium

Info

Publication number: CN116959750B
Application number: CN202311221749.4A
Authority: CN
Inventors: 周志欢; 张海坡; 冯丹; 李欣强; 孙海丽
Original assignee: Beijing Excellent Future International Pharmaceutical Technology Development Co ltd
Current assignee: Beijing Excellent Future International Pharmaceutical Technology Development Co ltd
Priority date: 2023-09-21
Filing date: 2023-09-21
Publication date: 2023-12-19
Anticipated expiration: 2043-09-21
Also published as: CN116959750A

Abstract

The application relates to a data analysis method, a device, electronic equipment and a medium, and relates to the field of data analysis. The method has the effect of comprehensively analyzing the test data.

Description

Data analysis method, device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of data analysis technologies, and in particular, to a data analysis method, apparatus, electronic device, and medium.

Background

At present, after the research and development of the new medicine are finished, in order to ensure the safety of users after the new medicine is marketed, clinical tests are generally used for testing the safety and the curative effect of the new medicine, and research and development staff analyze according to test data generated by the clinical tests, so that the purposes of defining the safety and the curative effect of the new medicine are achieved. However, the test data are relatively large and complex, so that the research and development personnel are relatively inconvenient to analyze, and the analysis result is incomplete, so that how to analyze the test data more comprehensively, efficiently and accurately becomes a problem.

Disclosure of Invention

In order to more fully analyze test data, the application provides a data analysis method, a data analysis device, electronic equipment and a medium.

In a first aspect, the present application provides a method for data analysis, which adopts the following technical scheme:

a method of data analysis, comprising:

obtaining test data of a new drug, wherein the test data corresponds to a data type, the test data comprises control group data and test group data, the control group data comprises control data of a plurality of control persons, and the test group data comprises test data of a plurality of subjects;

determining at least one variation data type based on the control group data and the test group data;

if so, determining the number of the subjects corresponding to each first target data type and the total number of the tested subjects;

judging whether at least one first target data type exists in the at least one change data type or not based on a first preset data type, wherein the first target data type is a data type which does not belong to the first preset data type;

Judging whether each first target data type belongs to a first output data type or not based on the number and the tested total number, wherein data corresponding to the first output data type represents the influence of the new drug on the subject;

outputting data corresponding to a second target data type and data corresponding to the first preset data type, wherein the second target data type is a first target data type belonging to the first output data type.

By adopting the technical proposal, the test data is data generated in the clinical test process, the test data corresponds to data types, and in order to eliminate the influence of irrelevant variables on test results in the clinical test process, a control group and a test group are usually arranged, namely, the data generated in the clinical test comprises test group data and control group data, namely, the test data comprises control group data and test group data, the change data types are data types corresponding to data with larger phase difference in the control group data and the test group data, the test data is acquired, the follow-up determination of at least one change data type from the test group data and the control group data is facilitated, the first preset data type is the data type which is set in advance, the data type which is the ideal use corresponding to new drugs has influence on the body is based on the first preset data type, judging whether at least one data type which does not belong to a first preset data type exists in the at least one data type, namely, a first target data type, so as to achieve the effect of judging whether other medicinal effects possibly belonging to a new medicament exist, when the first target data type exists, indicating that the new medicament possibly exists other medicinal effects, determining the number of subjects corresponding to each first target data type and the total number of tested persons as the target subjects corresponding to the first target data type, so as to judge whether the first target data type belongs to a first output data type according to the number and the total number of tested persons, thereby achieving the effect of judging whether the data corresponding to the first target data type is caused by the new medicament, wherein the second target data type is the first target data type belonging to the first output data type, and outputting data corresponding to the second target data type and data corresponding to the first preset data type, so that the effect of analyzing the test data more comprehensively is achieved.

In another possible implementation, the test data includes vital sign data and response data, and the obtaining test data of a new drug includes:

acquiring video information in a ward and vital sign data acquired by a vital sign acquisition unit;

and carrying out feature analysis on the video information to obtain the response data.

By adopting the technical scheme, the test data comprise vital sign data of the subject and response data generated after the subject takes the new medicine, and the follow-up characteristic analysis of the video information is facilitated by acquiring the video information in a ward to obtain the response data and acquire the vital sign data acquired by the vital sign acquisition device, so that the effect of acquiring the test data is achieved.

In another possible implementation, the determining at least one change data type based on the control group data and the test group data includes:

acquiring the generation time corresponding to the control group data and the test group data respectively;

generating a plurality of test curves corresponding to the plurality of subjects respectively based on the test group data and the generation time corresponding to the test group data, and generating a plurality of control curves corresponding to the plurality of control persons respectively based on the control group data and the generation time corresponding to the control group data;

Calculating the test change rate corresponding to each test curve and the control change rate corresponding to each control curve;

the test change rate and the comparison change rate with the same data type are subjected to difference to obtain a plurality of difference values;

and if a target difference value reaching a preset difference value exists in the plurality of difference values, determining that the data type corresponding to the target difference value is a change data type.

By adopting the technical scheme, multiple test curves and multiple comparison curves are respectively generated according to the generation time, and the test change rate of each test curve and the comparison change rate of each comparison curve are calculated, so that the test change rate and the comparison change rate of the same data type are conveniently differenced to obtain multiple differences, the preset differences are preset differences, the difference representing the larger difference between the test change rate and the comparison change rate is a standard which reaches the preset differences, and when the target differences exist in the multiple differences, the difference representing the larger difference between the test change rate and the comparison change rate corresponding to the target differences can be determined, and therefore the effect of determining the change data type corresponding to the target differences can be achieved.

In another possible implementation manner, the number of the tested headcount is different, and the corresponding preset ratio is different, and the determining whether the first target data type belongs to the first output data type based on the number and the tested headcount includes:

determining a target preset ratio corresponding to the tested total number of people;

determining a quantity ratio based on the quantity and the total number of people tested;

if the quantity ratio reaches the target preset ratio, determining that a first target data type corresponding to the quantity belongs to a first output data type;

if the target preset ratio is not reached, determining that the first target data type corresponding to the number does not belong to the first output data type.

By adopting the technical scheme, the preset ratio is a preset quantity ratio, the preset ratio is a standard which corresponds to the preset quantity and indicates that the data type possibly belongs to the application of the new medicine, the tested total number is different, the corresponding preset ratio is different, the target preset ratio which corresponds to the current tested total number is determined, and the quantity ratio is determined according to the quantity and the tested total number, so that whether the first target data type belongs to the first output data type can be judged according to the target preset ratio and the quantity ratio, specifically, when the quantity ratio reaches the target preset ratio, the first target data type of the new medicine reaches the standard which possibly belongs to the application of the new medicine, therefore, the first target data type can be determined to belong to the first output data type, and when the target preset ratio is not reached, the first target data type cannot reach the standard which possibly belongs to the application of the new medicine, therefore, the first target data type cannot be determined to the first output data type, and therefore, the effect of judging whether the first target data type belongs to the first output data type is reached or not is achieved.

In another possible implementation manner, the other medicines are medicines with at least one component in the new medicine, the number of the other medicines is at least two, the number of the second target data types is at least two, and the outputting of the data corresponding to the second target data types includes:

acquiring first component information and second component information, wherein the first component information comprises the composition components of the new medicine, the second component information comprises the composition components of at least two other medicines, and the composition information of each other medicine is different;

calculating the similarity between the at least two other medicines and the new medicine respectively based on the first component information and the second component information;

based on the similarity, ordering the at least two other medicines to obtain a first ordering result;

acquiring a third target data type, wherein the third target data type comprises a second output data type and a second preset data type, the second output data type is a first output data type corresponding to the at least two other medicines, and the second preset data type is a first preset data type corresponding to the at least two other medicines;

And outputting data corresponding to at least two second target data types respectively based on the third target data type and the first sorting result.

By adopting the technical scheme, other medicines are medicines with at least one component in the new medicine, the number of the other medicines is at least two, the component information of each other medicine is different, namely the types of each other medicine are different, the first component information and the second component information are acquired so as to be convenient for calculating the similarity between the other medicines and the new medicine according to the first component information and the second component information, the effect generated by the medicines is determined by the component information of the medicines, therefore, the similarity between the other medicines and the new medicine is calculated according to the first component information and the second component information, thereby being convenient for defining the possible effect of the new medicine according to the similarity, the third target data type is a data type comprising a second output data type and a second preset data type, namely, the third target data type is all data types corresponding to at least two other medicines, so that the third target data type is acquired, the data corresponding to at least two second target data types respectively can be conveniently output according to the third target data type and the first sorting result, and as the first sorting result is the sorting result of the at least two other medicines according to the respectively corresponding similarity, namely, the most probable influence data type of the new medicine can be known by combining the first sorting result and the third target data type, namely, the output sequence of the at least two second target data types is defined, the data corresponding to the at least two second target data types respectively is output according to the third target data type and the first sorting result, so that a developer can more clearly know the second target data type which is most probable to the influence data type of the new medicine, thereby achieving the effect of being convenient for research and development personnel to analyze the data.

In another possible implementation manner, the first component information and the second component information further include ratio information corresponding to a plurality of components, respectively, and the calculating the similarity between the at least two other medicines and the new medicine based on the first component information and the second component information includes:

acquiring a first weight and a second weight, wherein the first weight is the weight of the new medicine, and the second weight is the weight of the other medicines;

determining the content of each of the plurality of first components based on the first weight and the proportion information corresponding to each of the plurality of first components, and determining the content of each of the plurality of second components based on the second weight and the proportion information corresponding to each of the plurality of second components, wherein the first component is a component corresponding to the new drug, and the second component is a component corresponding to the at least two other drugs;

determining the same component quantity, the first total component quantity, the second total component quantity and the same component type corresponding to the at least two other medicines respectively based on the plurality of first components and the plurality of second components, and judging whether the first total component quantity is the same as the second total component quantity or not to obtain a judging result, wherein the first total component quantity is the total component quantity of the new medicine, and the second total component quantity is the total component quantity corresponding to the at least two other medicines respectively;

And calculating the similarity between each other medicine and the new medicine based on the judging result, the same component quantity, the second total component quantity, the first same component content and the second same component content, wherein the first same component content is the component content of the same component in the new medicine, and the second same component content is the component content of the same component in each other medicine.

By adopting the technical scheme, the first component information and the second component information respectively comprise the proportion information corresponding to the multiple components, and the weights of the components are different even though the proportion information of the components is the same, so that the drug effect is different, namely the component content of the components influences the drug effect of the drug, the first weight and the second weight are required to be obtained, the component content corresponding to the multiple first components is determined according to the first weight and the proportion information corresponding to the multiple first components, and the component content corresponding to the multiple second components is determined according to the second weight and the proportion information corresponding to the multiple second components, so that the similarity of at least two drugs and new drugs is conveniently calculated.

In another possible implementation manner, the outputting, based on the third target data type and the first ordering result, data corresponding to at least two second target data types respectively includes:

searching each second target data type in the third target data types, and determining a target medicine corresponding to each second target data type, wherein at least one second target data type exists in the third target data types corresponding to the target medicine;

acquiring the medicine quantity of the target medicine;

sequencing the at least two second target data types according to the medicine quantity to obtain a second sequencing result;

judging whether a fourth target data type exists in the at least two second target data types, wherein the fourth target data type is the second target data type with the same medicine quantity;

if the data exists, sorting the fourth target data type based on the first sorting result, obtaining a third sorting result based on the second sorting result, and outputting the data respectively corresponding to the at least two second target data types based on the third sorting result;

and if the data type does not exist, outputting the data corresponding to the at least two second target data types respectively based on the second sorting result.

By adopting the technical scheme, the third target data type is all the data types corresponding to at least two other medicines, namely, the greater the possibility that the second target data type possibly affects a subject in a new medicine is indicated, therefore, the medicine quantity of the target medicines can be obtained, the second ordering result is obtained by ordering the at least two second target data types according to the medicine quantity, the fourth target data type is the second target data type with the same medicine quantity, the second target data type can be ordered according to the medicine quantity, the more the medicine quantity corresponding to the second target data type indicates, the more the second target data type can exert the influence effect corresponding to the second target data type in the explanation, namely, the greater the possibility that the second target data type possibly affects a subject in a new medicine is indicated, the fourth target data type is the second target data type which is the same in medicine quantity, the fourth target data type is the second target data type with the same medicine quantity, the fourth target data type is the second target data type with the second target data type can be ordered according to the medicine quantity, the fourth target data type can not be determined, the fourth target type can be further analyzed according to the second ordering result, and the second data type can be judged whether the second ordering result is more the second target type can not be ordered according to the second target type is more than the second target type, the second ordering result can be judged, the higher the similarity is, the greater the possibility that the effect of other medicines corresponding to the similarity exists in the new medicine is indicated, so that the fourth target data type can be ordered according to the first ordering result, the third ordering result is obtained by combining the second ordering result, the effect of obtaining a comprehensive and accurate ordering result is achieved, and the data of at least two second target data types are output according to the third ordering result, so that the effect of analyzing the test data by research personnel is achieved more conveniently. And when the second target data type which cannot be determined in the sequence is not existed in the second sequencing result, the data which are respectively used by at least two second target data types can be directly output according to the second sequencing result, so that the effect of more facilitating the research and development personnel to analyze the test data is achieved.

In a second aspect, the present application provides a device for data analysis, which adopts the following technical scheme:

an apparatus for data analysis, comprising:

the acquisition module is used for acquiring test data of a new drug, wherein the test data corresponds to a data type, the test data comprises control group data and test group data, the control group data comprises control data of a plurality of control persons, and the test group data comprises test data of a plurality of subjects;

a first determination module for determining at least one type of variation data based on the control group data and the test group data;

the first judging module is used for judging whether at least one first target data type exists in the at least one change data type or not based on a first preset data type, wherein the first target data type is a data type which does not belong to the first preset data type;

the second determining module is used for determining the number of the subjects corresponding to each first target data type and the total number of the tested subjects when the first target data type exists;

the second judging module is used for judging whether each first target data type belongs to a first output data type or not based on the number and the tested total number, and the data corresponding to the first output data type represents the influence of the new medicine on the subject;

The output module is used for outputting data corresponding to a second target data type and data corresponding to the first preset data type, wherein the second target data type is a first target data type belonging to the first output data type.

By adopting the technical scheme, the test data are data generated in the clinical test process, the test data correspond to data types, the influence of irrelevant variables on test results is eliminated in the clinical test process, a control group and a test group are often arranged, namely, the data generated in the clinical test comprise test group data and control group data, namely, the test data comprise control group data and test group data, the change data types are data types corresponding to data with larger phase difference in the control group data and the test group data, the first acquisition module acquires the test data, the subsequent first determination module is convenient to determine at least one change data type from the test group data and the control group data, the first preset data type is a data type which is set in advance, the first determination module is a data type which is influenced by an ideal application corresponding to a new drug, the first determination module determines whether at least one data type which does not belong to the first preset data type exists in the data types, namely, the first target data type is a first target data type, thereby achieving the effect of judging whether other drugs possibly exist or not, when the first target type corresponds to the first target type is present, the first target type is the first target type which can cause the new drug, the first data corresponding to the first target type is convenient to output the first target type, the first data is determined by the first determination module, the first determination module determines whether the total number of the first target type of the data corresponds to the first target type and the first target type is convenient to judge whether the first target type, the second target data type is a first target data type belonging to the first output data type, and the data corresponding to the second target data type and the data corresponding to the first preset data type are output through the output module, so that the effect of analyzing the test data more comprehensively is achieved.

In another possible implementation manner, the obtaining module is specifically configured to, when obtaining test data of a new drug:

In another possible implementation manner, the first determining module is specifically configured to, when determining at least one change data type based on the control group data and the test group data:

In another possible implementation manner, the second determining module is specifically configured to, when determining, based on the number and the total number of people under test, whether the first target data type belongs to a first output data type:

In another possible implementation manner, the output module is specifically configured to, when outputting data corresponding to the second target data type:

In another possible implementation manner, the output module is specifically configured to, when calculating the similarity between the at least two other medicines and the new medicine based on the first component information and the second component information:

acquiring a first weight and a second weight, wherein the first weight is the weight of the new medicine, and the second weight is the weight respectively corresponding to the at least two other medicines;

determining the content of each of the plurality of first components based on the first weight and the proportion information corresponding to each of the plurality of first components, and determining the content of each of the plurality of second components based on the second weight and the proportion information corresponding to each of the plurality of second components, wherein the first component is a component corresponding to the new drug, and the second component is a component corresponding to each of the at least two other drugs;

In another possible implementation manner, the output module is specifically configured to, when outputting data corresponding to at least two second target data types respectively based on the third target data type and the first ordering result:

acquiring the medicine quantity of the target medicine;

In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:

an electronic device, the electronic device comprising:

At least one processor;

a memory;

at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a method of data analysis is performed as shown in any one of the possible implementations according to the first aspect.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

a computer readable storage medium, which when executed in a computer causes the computer to perform the method of data analysis of any of the first aspects.

In summary, the present application includes at least one of the following beneficial technical effects:

1. the test data is data generated in the clinical test process, the test data corresponds to data types, the influence of irrelevant variables on test results is eliminated in the clinical test process, a control group and a test group are usually arranged, namely, the data generated in the clinical test comprises test group data and control group data, namely, the test data comprises control group data and test group data, the change data types are data types corresponding to data with larger phase difference in the control group data and the test group data, the test data is acquired, at least one change data type is conveniently determined from the test group data and the control group data, the first preset data type is a data type which is set in advance, the data type which influences the body for ideal purposes corresponding to new drugs is judged, based on the first preset data type, whether at least one data type which does not belong to the first preset data type exists in the data generated in the clinical test is judged, namely, the first target data type is judged, when the first target data type exists, the new drugs possibly exist, the new drugs are indicated to be the data types corresponding to the first target type, the first target type is convenient to determine whether the total data corresponding to the first target type is judged, the total data quantity of the total data of the first target type is judged, the total quantity of the total data of the first target type and the total data is judged whether the first target type of the total quantity of the first target type is reached, outputting data corresponding to the second target data type and data corresponding to the first preset data type, so as to achieve the effect of analyzing the test data more comprehensively;

2. The third target data type is all data types corresponding to at least two other medicines, the third target data type of the target medicine is at least one second target data type, each second target data type is searched in the third target data type, and the target medicine corresponding to each second target data type is determined, so that the second target data types can be ordered according to the target medicine, the more the medicine corresponding to the second target data type is, the greater the possibility that the influence effect corresponding to the second target data type can be exerted in the medicine is described, namely the greater the possibility that the second target data type possibly affects the subject in a new medicine is described, therefore, the number of the target medicine can be obtained, the at least two second target data types are ordered according to the medicine number, the second ordering result is obtained, the fourth target data type is the second target data type with the same medicine number, as the condition that the second target data type with the same number exists in the at least two second target data types is convenient to analyze, the fourth target data type can not be more accurately analyzed, the second target data type can not be determined according to the ordering result is more than the second ordering result, the second data type can be more easily determined, the second ordering result can be further is more than the second ordering result is more can be judged according to the at least the second ordering result, the second ordering result can be more, the second data type can be more easily be judged according to the second ordering data can be more than the second object type is more than the second ordering data type is more than the second target data type is more, the higher the possibility that the effect of other medicines corresponding to the similarity exists in the new medicine is, the fourth target data type can be ordered according to the first ordering result, the third ordering result is obtained by combining the second ordering result, the effect of obtaining a comprehensive and accurate ordering result is achieved, and the data of at least two second target data types are output according to the third ordering result, so that the effect of analyzing test data by research and development personnel is achieved more conveniently. And when the second target data type which cannot be determined in the sequence is not existed in the second sequencing result, the data which are respectively used by at least two second target data types can be directly output according to the second sequencing result, so that the effect of more facilitating the research and development personnel to analyze the test data is achieved.

Drawings

FIG. 1 is a flow chart of a method of data analysis in an embodiment of the present application.

Fig. 2 is a schematic structural diagram of an apparatus for data analysis in an embodiment of the present application.

Fig. 3 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

The present application is described in further detail below in conjunction with figures 1-3.

Modifications of the embodiments which do not creatively contribute to the invention may be made by the person skilled in the art after reading the present specification, but are protected by patent laws as long as they are within the scope of the present application.

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments that a subject of ordinary skill in the art would obtain without inventive effort based on the embodiments herein fall within the scope of protection of the present application.

In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.

Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.

The embodiment of the application provides a data analysis method, which is executed by electronic equipment, wherein the electronic equipment can be a server or terminal equipment, and the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server for providing cloud computing service. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., and the terminal device and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein, and as shown in fig. 1, the method includes: step S101, step S102, step S103, step S104, step S105, and step S106, wherein,

step S101, test data of a new drug are obtained.

The test data corresponds to a data type, and the test data comprises control group data and test group data, wherein the control group data comprises control data of a plurality of control persons, and the test group data comprises test data of a plurality of subjects.

For the embodiment of the present application, the test data of the new drug is data generated by a clinical test, the test data corresponds to data types such as heart rate, respiratory rate, blood pressure, and the like, the test data of a control group is test data of a control person who does not take any drug or takes a placebo, the test group data is test data of a subject who takes the new drug, in the embodiment of the present application, a plurality of control persons are included in the control group, and a plurality of subjects are included in the test group. And the test data of the new medicine is acquired, so that the subsequent analysis of the test data is facilitated.

Step S102, determining at least one change data type based on the control group data and the test group data.

For the embodiments of the present application, the data type of the change is different in the corresponding data change in the control group data and the test group data, for example, the cough frequency change is different in the control group and the test group.

Step S103, based on the first preset data type, judging whether at least one first target data type exists in at least one changed data type.

The first target data type is a data type which does not belong to a first preset data type.

For the embodiment of the present application, the first preset data type is a data type set in advance, and is a data type that affects the body for the ideal use corresponding to the new drug, and if the ideal use of the new drug is to treat cough, the first preset data type may be the cough frequency. In the embodiment of the present application, the number of the first preset data types may be at least two, and the number of the first preset data types is related to the ideal use of the new drug. The first target data type is a data type not belonging to the first preset data type, and at least one kind of change data is assumed to be: cough frequency and sleep duration, i.e. the first target data type is sleep duration.

In this embodiment of the present application, the manner of determining whether at least one first target data type exists in at least one type of change data according to the first preset data type may be to compare each type of change data with the first preset data type, so as to screen out the first target data type.

Step S104, if the first target data type exists, determining the number of the subjects corresponding to each first target data type and the total number of the tested subjects.

For the embodiments herein, when present, it is illustrated that the new drug may have an effect on the first target data type, and the number of subjects corresponding to each first target data type and the total number of subjects are determined, so as to facilitate a subsequent determination of whether the new drug has a greater likelihood of having an effect on the first target data type. Taking step S103 as an example, assume that the number of target subjects corresponding to the sleep time period is 18, and the total number of tested persons is 20.

Step S105, based on the number and the tested population, judging whether each first target data type belongs to the first output data type.

Wherein, the data corresponding to the first output data type characterizes the influence of the new drug on the subject.

For the embodiment of the application, the output data is other data caused by other unknown purposes except for the ideal purpose of the drug, and whether the first target data type belongs to the output data is judged according to the number and the total number of tested people, so that whether the new drug has a larger possibility of affecting the first target data type is determined.

Step S106, outputting the data corresponding to the second target data type and the data corresponding to the first preset data type.

Wherein the second target data type is a first target data type belonging to the first output data type.

For the embodiment of the present application, the second target data type is a first target data type belonging to the first output data type, that is, the second target data type is a data type possibly belonging to data corresponding to an effect caused by the new drug, and the data corresponding to the second target data type and the data corresponding to the first preset data type are output, so that a doctor can more comprehensively understand the effect possibly generated by the new drug.

In the embodiment of the application, the data corresponding to the second target data type and the data corresponding to the first preset data type can be respectively and specifically marked, so that a doctor can know the test condition more clearly. Specifically, the data corresponding to the second target data type may be marked with yellow, and the first preset data type may be marked with red.

Further, in the embodiment of the present application, the data may be output to a mobile device corresponding to a doctor, or the data may be output to a public display screen, so that each doctor may view the data, which is not limited herein.

In one possible implementation manner of the embodiment of the present application, step S101 includes step S1011 (not shown in the figure) and step S1012 (not shown in the figure) when acquiring test data of a new drug, wherein,

and step S1011, acquiring video information in a ward and vital sign data acquired by a vital sign acquisition unit.

For the embodiment of the application, the test data includes vital sign data and response data, the vital sign data is body data inside the body of the subject, such as heart rate, blood pressure, respiratory rate and the like, and the response data is response data outside the body, such as cough frequency, toilet frequency and the like, generated after the subject takes the new medicine. In this application embodiment, install image acquisition device in the ward that the subject resided, every subject position department is provided with the bed curtain, when operation such as the subject needs the change of clothes, can be used to shelter from image acquisition device to protect privacy. In this embodiment of the present application, the image capturing device may be a camera.

Further, in the embodiment of the present application, after the bed curtain is used by the subject, the bed curtain may not be pulled to the preset position in time, so that the situation that the image acquisition device acquires the subject is affected, therefore, when the condition that the bed curtain is not at the preset position is detected, the duration of the time that the bed curtain is not at the preset position is acquired, and when the duration of the time reaches the preset duration, a prompt message is output to remind the subject to pull the bed curtain to the preset position.

Step S1012, performing feature analysis on the video information to obtain reaction data.

For the embodiment of the application, when the response data of the number of times of toilet is determined, when the position of the subject in the video information is detected, the current time is obtained, and the number of times of toilet corresponding to the subject is added by one, so that the number of times of toilet corresponding to the subject is obtained.

In this embodiment of the present application, a plurality of sensors may be disposed in a ward, for example, a sensor is disposed at a toilet, and when a subject uses a toilet, the subject uses the sensor to transmit his own toilet condition to an electronic device, so that the electronic device can obtain the toilet condition of the subject, i.e. achieve the effect of obtaining test data.

In one possible implementation manner of the embodiment of the present application, step S102 includes step S1021 (not shown in the figure), step S1022 (not shown in the figure), step S1023 (not shown in the figure), step S1024 (not shown in the figure), and step S1025 (not shown in the figure) when determining at least one type of change data based on the control group data and the test group data, wherein,

step S1021, obtaining generation time corresponding to the control group data and the test group data respectively.

For the embodiments of the present application, the time of generation is the time of data generation, i.e., the time of data generation for the data type by the subject as well as the control. And acquiring the corresponding generation time of the control group data and the test group data respectively so as to facilitate the subsequent generation of a corresponding curve according to the generation time.

Step S1022, generating a plurality of test curves corresponding to the plurality of subjects based on the test group data and the generation time corresponding to the test group data, and generating a plurality of control curves corresponding to the plurality of control persons based on the control group data and the generation time corresponding to the control group data.

Step S1023, calculating the test change rate corresponding to each test curve and the control change rate corresponding to each control curve.

For the embodiment of the present application, assuming that the test curve is a cough frequency curve, the manner of calculating the cough frequency change rate may be to select a plurality of groups of cough frequency data and generation times corresponding to the cough frequency data from the cough frequency curve, obtain a plurality of initial test change rates according to the plurality of groups of cough frequency data and the generation times corresponding to the cough frequency data, average the plurality of initial test change rates to obtain the test change rate corresponding to the cough frequency curve, where the calculation manner of the comparison change rate is the same as that of the test change rate, and will not be described herein. In the embodiment of the application, the more the number of the groups of the selected data and the data generation time is, the more accurate the calculated change rate is. 1

Step S1024, the test change rate and the comparison change rate with the same data type are differenced to obtain a plurality of differences.

For the embodiment of the application, assuming that the data type is cough frequency change and sleep duration, the test change rate of the data type is cough frequency change is differentiated from the comparison change rate to obtain a difference value corresponding to the cough change frequency, and the test change rate of the data type is sleep duration is differentiated from the comparison change rate to obtain a difference value corresponding to the sleep duration. So that the type of the change data can be determined according to the difference value.

In step S1025, if a target difference value reaching the preset difference value exists in the plurality of difference values, it is determined that the data type corresponding to the target difference value is a changed data type.

For the embodiment of the application, the preset difference is a difference set in advance, and is used for indicating a standard with larger difference between the test change rate and the comparison change rate, the target difference is a difference reaching the preset difference, and when the target difference exists in the plurality of differences, the fact that the test change rate corresponding to the target difference is larger than the comparison change rate is indicated, so that the data type corresponding to the target difference can be determined to be the change data type, and the effect of determining the change data type is achieved.

In one possible implementation manner of the embodiment of the present application, step S105 includes step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), and step S1054 (not shown in the figure) when determining whether the first target data type belongs to the first output data type based on the number and the total number of people tested, wherein,

step S1051, determining a target preset ratio corresponding to the tested population.

For the embodiment of the present application, the preset ratio is a preset number ratio, the preset ratio is a standard corresponding to the preset number and indicating that the data type may belong to the application of the new drug, the total number of tested people is different, and the corresponding preset ratio is different, for example: the number of the tested population is 4, the corresponding preset ratio is 0.75, the number of the tested population is 20, the corresponding preset ratio is 0.8, and the target preset ratio corresponding to the current tested population is determined, so that whether the first target data type belongs to the first output data type or not can be judged according to the target preset ratio. Assume that the current total number of people to be tested is 20, i.e., the target preset ratio is 0.8.

Step S1052, determining the quantity ratio based on the quantity and the tested population.

For the embodiment of the present application, the number may be divided by the total number of the tested persons, so as to obtain a number ratio, and taking step S104 as an example, it may be determined that the number ratio corresponding to the sleep duration is 0.9.

In step S1053, if the number ratio reaches the target preset ratio, it is determined that the first target data type corresponding to the target subject belongs to the first output data type.

In step S1054, if the target preset ratio is not reached, it is determined that the first target data type corresponding to the target subject does not belong to the first output data type.

For the embodiment of the present application, taking step S1051 and step S1052 as examples, the number ratio corresponding to the sleep duration is 0.9 and reaches the preset ratio of 0.8, so it may be determined that the sleep duration belongs to the first output data type. When the target preset ratio is not reached, the first target data type of the new drug is not reached to the standard possibly belonging to the new drug application, so that the first target data type can be determined not to belong to the first output data type, and the effect of judging whether the first target data type belongs to the first output data type is achieved.

In one possible implementation manner of the embodiment of the present application, step S106 includes, when outputting data corresponding to the second target data type: step S1061 (not shown), step S1062 (not shown), step S1063 (not shown), step S1064 (not shown), and step S1065 (not shown), wherein,

in step S1061, the first component information and the second component information are acquired.

Wherein the first component information includes a constituent component of the new drug, the second component information includes a constituent component of at least two other drugs, and the constituent information of each other drug is different.

For the embodiment of the application, the other medicines are medicines with at least one component in the new medicine, the number of the other medicines is at least two, and the component information of each other medicine is different, namely the types of each other medicine are different, and the first component information and the second component information are acquired, so that the similarity between the other medicines and the new medicine can be calculated according to the first component information and the second component information.

In step S1062, the similarity between the other medicines and the new medicine is calculated based on the first component information and the second component information.

Step S1063, sorting at least two other medicines based on the similarity to obtain a first sorting result.

For the embodiment of the application, the effect generated by the medicine is determined by the component information of the medicine, so that the similarity between other medicines and the new medicine is calculated according to the first component information and the second component information, and the possible effect of the new medicine is conveniently determined according to the similarity. Assuming that the new medicine is medicine a, the other medicines are medicine B, medicine C and medicine D, and the similarity corresponding to medicine B, medicine C and medicine D is calculated to be 19%, 25% and 59%, respectively, so that the first sorting result is medicine D, medicine C and medicine B.

In step S1064, a third target data type is acquired.

The third target data type comprises a second output data type and a second preset data type, the second output data type is a first output data type corresponding to at least two other medicines, and the second preset data type is a first preset data type corresponding to at least two other medicines.

For the embodiment of the present application, the third target data type is a data type including the second output data type and the second preset data type, that is, the third target data type is all data types corresponding to at least two other medicines, so that the third target data type is obtained, and it is convenient to output data corresponding to at least two second target data types respectively according to the third target data type and the first ordering result. Assume that the third target data type corresponding to the medicine D is type a, type b, and type D, and the third target data type corresponding to the medicine C is type a, type C, and type e.

Step S1065, outputting data corresponding to the at least two second target data types based on the third target data type and the first ordering result.

For the embodiment of the application, the first sorting result is a sorting result of at least two other medicines according to respective corresponding similarities, the first sorting result is a positive sorting result, that is, the more the sorting is forward, the higher the corresponding similarities are, the second target data type is a possible influence type of a new medicine on a subject, and when the second target data type is the same as the data type of the other medicines with the more forward sorting, the greater the possibility that the second target data type belongs to the influence type of the new medicine on the subject is indicated, therefore, according to the third target data type and the first sorting result, at least two second target data types respectively corresponding and data are output, so that a researcher can know the second target data type most likely to belong to the influence data type of the new medicine more clearly, thereby achieving the effect of facilitating the research and development of analyzing the data.

Taking step S1064 as an example, assuming that at least two second target data types are type a, type c, and type d, the type a, the type c, and the type d may be output according to the order of the type a, the type d, and the type c.

In one possible implementation manner of the embodiment of the present application, step S1062 includes step S10621 (not shown in the figure), step S10622 (not shown in the figure), step S10623 (not shown in the figure), and step S10624 (not shown in the figure) when calculating the similarity between other medicines and the new medicine based on the first component information and the second component information, where,

in step S10621, the first weight and the second weight are acquired.

The first weight is the weight of the new medicine, and the second weight is the weight corresponding to the other medicines respectively.

Step S10622, determining the component contents of each of the plurality of first components based on the first weight and the ratio information of each of the plurality of first components, and determining the component contents of each of the plurality of second components based on the second weight and the ratio information of each of the plurality of second components.

Wherein the first component is a component corresponding to the new medicine, and the second component is a component corresponding to at least two other medicines respectively.

For the embodiment of the application, the first component information and the second component information respectively further include proportion information corresponding to a plurality of components, and because the weights of the medicines are different, even though the proportion information of the components is the same, the weights corresponding to the components are different, so that the medicine effects are different, that is, the component contents of the components affect the medicine effects, the first weight and the second weight need to be obtained, the component contents corresponding to the plurality of first components are determined according to the first weight and the proportion information corresponding to the plurality of first components, and the component contents corresponding to the plurality of second components are determined according to the second weight and the proportion information corresponding to the plurality of second components, so that the similarity of at least two medicines and new medicines is calculated conveniently.

Assuming that the components of the new medicine A are a, B, c and d, the corresponding proportion information is 0.5, 0.2, 0.1 and 0.2 in sequence, the weight of the new medicine A is 0.5g (g), the component content of the new medicine A is calculated to be 0.25g, 0.1g, 0.05g and 0.1g in sequence, the component content of the medicine B is a, B, e, f and g, the corresponding proportion information is 0.5, 0.1, 0.2, 0.1 and 0.1 in sequence, the weight of the medicine B is 0.1g, and the component content of the medicine B is calculated to be 0.05g, 0.01g, 0.02g and 0.01g in sequence.

Step S10623, determining the same component number, the first total component number, the second total component number, and the same component type corresponding to at least two other medicines based on the plurality of first components and the plurality of second components, and determining whether the first total component number is the same as the second total component number, to obtain a determination result.

The first total component quantity is the total component quantity of the new medicine, and the second total component quantity is the total component quantity respectively corresponding to at least two other medicines.

For the embodiment of the present application, taking step S10622 as an example, the same component number of the new drug a and the drug is 2, the first total component number is 4, the second total component number is 5, and the same component types are a and b, and the determination result is that the first total component number is different from the second total component number.

In step S10624, the similarity between at least two other medicines and the new medicine is calculated based on the determination result, the same component amounts, the second total component amounts, the first same component content, and the second same component content.

Wherein the first identical component content is the component content of the identical component in the new medicine, and the second identical component content is the component content of the identical component in each other medicine.

For the embodiment of the application, since the components and the component content of the medicine are all factors affecting the efficacy of the medicine, the similarity between at least two other medicines and the new medicine can be calculated according to the judgment result, the same component quantity, the second total component quantity, the first same component content and the second same component content, so that the effect of calculating the similarity between at least two other medicines and the new medicine is achieved.

In the embodiment of the present application, the manner of calculating the similarity may be preferably: the judgment results correspond to judgment values, when the judgment results are different, the corresponding judgment values are 0, when the judgment results are the same, the corresponding judgment values are 1, the judgment results have corresponding weights, the judgment values and the judgment results have corresponding weights to multiply to obtain the similarity of the judgment results, and the weight corresponding to the judgment results is assumed to be 0.4. Taking step S10622 as an example, the similarity of the determination result is 0, and the same component number and the second total component number are divided to obtain a component number ratio, where the component number ratio corresponds to a weight, and multiplying the component number ratio by the corresponding weight to obtain the component number similarity, where in the embodiment of the present application, the weight of the component number ratio is 0.4. Taking step S10622 as an example, the component number similarity is 16%. In the embodiment of the present application, the residual weight is 0.2, taking step S10622 as an example, the number of the same components is 2, that is, the sub weight is 0.1, the first same component content with the same composition component is compared with the second same component content, and the large weight and the small weight are determined, where the component content of the large weight is more than the component content of the small weight, the small weight with the same composition component is divided from the large weight, that is, the weight ratio corresponding to each same composition component is obtained, the weight ratios corresponding to the same composition components are added, that is, the total weight ratio is obtained, the total weight ratio is multiplied by the sub weight, that is, the weight similarity is obtained, taking step S10622 as an example, the component content of a in the new medicine a is 0.25g, the component content of B is 0.1g, the component content of a in the medicine B is 0.05g, the component content of B is 0.01g, that is the weight ratio corresponding to a is 0.2, the weight ratio corresponding to B is 0.1, the weight ratio corresponding to B is 0.3, and the total weight ratio corresponding to the new medicine a is 0.3, that is obtained, and the total weight ratio is 0.3.3. Finally, the similarity of the judging result, the similarity of the component quantity and the weight similarity are added to obtain the similarity of other medicines and new medicines, and the step S10622 is taken as an example to obtain the similarity of the medicine B and the new medicine A as 19%.

In one possible implementation manner of the embodiment of the present application, step S1065 includes step S10651 (not shown in the figure), step S10652 (not shown in the figure), step S10653 (not shown in the figure), step S10654 (not shown in the figure), step S10655 (not shown in the figure) and step S10656 (not shown in the figure) when outputting data corresponding to at least two second target data types respectively based on the third target data type and the first ordering result,

in step S10651, each second target data type is searched in the third target data type, and the target drug corresponding to each second target data type is determined.

Wherein, at least one second target data type exists in the third target data type corresponding to the target medicine.

For the embodiment of the application, the third target data type is all data types corresponding to at least two other medicines, at least one second target data type exists in the third target data types of the target medicines, each second target data type is searched in the third target data types, and the target medicine corresponding to each second target data type is determined, so that the second target data types can be ordered according to the target medicines.

In step S10652, the number of target medicines is acquired.

Step S10653, sorting at least two second target data types according to the number of the medicines to obtain a second sorting result.

For the embodiment of the application, the more the number of medicines corresponding to the second target data type is, the greater the possibility that the influence effect corresponding to the second target data type can be exerted in the medicines is, namely the greater the possibility that the second target data type may influence the subject in a new medicine is, so that the number of medicines of the target medicines can be obtained, and at least two second target data types are ordered according to the number of medicines, so that a second ordering result is obtained. Assume that the second target data type is type a, type b, type e, and type f. Taking step S1064 as an example, the number of medicines corresponding to type a is 2, the number of medicines corresponding to type b is 1, the number of medicines corresponding to type e is 1, and the number of medicines corresponding to type f is 0. That is, the second sorting result may be type a, type b, type e and type f, wherein, since the types b and e correspond to the same number of medicines respectively, that is, the sorting of the types b and e may be replaced at will.

In step S10654, it is determined whether the fourth target data type exists in the at least two second target data types.

The fourth target data type is the second target data type with the same medicine quantity.

For the embodiment of the present application, the fourth target data type is the second target data type with the same drug number, and since the second target data type with the same drug number exists in the at least two second target data types, as shown in the example in step S10653, when the fourth target data type exists, the ordering of the fourth target data type cannot be determined, so that it is required to determine whether the fourth target data type exists in the at least two second target data types, so that further operations are performed according to the determination result, so that the data respectively corresponding to the output at least two second target data types can be more convenient for the researchers to analyze.

Step S10655, if so, sorting the fourth target data type based on the first sorting result, obtaining a third sorting result based on the second sorting result, and outputting data corresponding to at least two second target data types respectively based on the third sorting result.

For the embodiment of the present application, when the first ordering result is the ordering result of other medicines according to the similarity, the higher the similarity is, the greater the likelihood that the new medicine has the effect of other medicines corresponding to the similarity is, so the fourth target data type can be ordered according to the first ordering result, taking step S1063 as an example, the first ordering result is medicine D, medicine C and medicine B, taking step S10653 as an example, the fourth target data type is type B and type e, and since the other medicines corresponding to type B are medicine D and the other medicines corresponding to type e are medicine C, the ordering result of type B and type e can be type B and type e, and the third ordering result can be obtained by combining the second ordering result, thereby achieving the effect of obtaining a relatively comprehensive and accurate ordering result. Taking step S10653 as an example, the third sorting result is type a, type b, type e, and type f. And outputting data of at least two second target data types according to the third sorting result, so that the effect of more facilitating the research and development personnel to analyze the test data is achieved.

And step S10656, if the data does not exist, outputting the data corresponding to the at least two second target data types respectively based on the second sorting result.

For the embodiment of the application, when the second target data type which cannot be determined in the sequence is not present in the second sequencing result, the data which are respectively used for at least two second target data types can be directly output according to the second sequencing result, so that the effect of more facilitating the research and development personnel to analyze the test data is achieved.

The above embodiment describes a method of data analysis from the perspective of a method flow, and the following embodiment describes an apparatus 20 for data analysis from the perspective of a virtual module or virtual unit, as described in detail below.

An embodiment of the present application provides a device 20 for data analysis, as shown in fig. 2, where the device 20 for data analysis may specifically include:

the acquisition module 201 is configured to acquire test data of a new drug, where the test data corresponds to a data type, and the test data includes control group data and test group data, the control group data includes control data of a plurality of control persons, and the test group data includes test data of a plurality of subjects;

a first determining module 202 for determining at least one type of variation data based on the control group data and the test group data;

A first determining module 203, configured to determine, based on a first preset data type, whether at least one first target data type exists in the at least one changed data type, where the first target data type is a data type that does not belong to the first preset data type;

a second determining module 204, configured to determine, when present, a number of subjects and a total number of subjects corresponding to each first target data type;

the second judging module 205 is configured to judge, based on the number and the total number of people under test, whether each first target data type belongs to a first output data type, where data corresponding to the first output data type represents an influence of a new drug on a subject;

the output module 206 is configured to output data corresponding to a second target data type and data corresponding to a first preset data type, where the second target data type is a first target data type that belongs to the first output data type.

By adopting the above technical scheme, the test data is data generated in the clinical test process, the test data corresponds to data types, and in the clinical test process, a control group and a test group are often arranged, namely, the data generated in the clinical test includes test group data and control group data, namely, the test data includes control group data and test group data, the change data types are data types corresponding to data with larger phase difference in the control group data and the test group data, the first acquisition module 201 acquires the test data, the subsequent first determination module 202 is convenient to determine at least one change data type from the test group data and the control group data, the first preset data type is a data type which is set in advance, the data type which is influenced by an ideal application corresponding to a new drug is generated on a body, the first determination module 203 determines whether at least one data type which does not belong to the first preset data type exists in the first preset data type based on the first preset data type, namely, the first target data type is used for determining whether other drug effect possibly exists or not, when the first data type corresponds to the first drug effect possibly exists, the first data corresponding to the first target type is displayed by the first acquisition module 201, the first determination module determines whether the first data corresponding to the first target type is convenient to output the first target type and the total number of drug effect and the first target type is reached, the first determination module is convenient to determine whether the first target type reaches the total number of the first data type and the first target type reaches the first target type and the first target type is different corresponding to the first target type and the first target type corresponding data type and the first target type is determined by the first preset data type, the second target data type is a first target data type belonging to the first output data type, and the output module 206 outputs data corresponding to the second target data type and data corresponding to the first preset data type, so that the effect of more comprehensively analyzing the test data is achieved.

In one possible implementation manner of this embodiment of the present application, when the obtaining module 201 obtains test data of a new drug, the obtaining module is specifically configured to:

and carrying out feature analysis on the video information to obtain reaction data.

In one possible implementation manner of the embodiment of the present application, the first determining module 202 is specifically configured to, when determining at least one type of change data based on the control group data and the test group data:

obtaining corresponding generation time of control group data and test group data respectively;

generating a plurality of test curves corresponding to a plurality of subjects respectively based on the test group data and the generation time corresponding to the test group data, and generating a plurality of comparison curves corresponding to a plurality of comparison persons respectively based on the comparison group data and the generation time corresponding to the comparison group data;

if a target difference value reaching a preset difference value exists in the plurality of difference values, determining that the data type corresponding to the target difference value is a change data type.

In one possible implementation manner of this embodiment of the present application, when the second determining module 205 determines, based on the number and the total number of people under test, whether the first target data type belongs to the first output data type, the second determining module is specifically configured to:

determining a target preset ratio corresponding to the total number of the tested people;

if the number ratio reaches a target preset ratio, determining that a first target data type corresponding to the number belongs to a first output data type;

In one possible implementation manner of this embodiment of the present application, when outputting data corresponding to the second target data type, the output module 206 is specifically configured to:

acquiring first component information and second component information, wherein the first component information comprises the components of the new medicine, the second component information comprises the components of at least two other medicines, and the component information of each other medicine is different;

calculating the similarity between at least two other medicines and the new medicine respectively based on the first component information and the second component information;

ordering at least two other medicines based on the similarity to obtain a first ordering result;

Acquiring a third target data type, wherein the third target data type comprises a second output data type and a second preset data type, the second output data type is a first output data type corresponding to at least two other medicines, and the second preset data type is a first preset data type corresponding to at least two other medicines;

and outputting data corresponding to at least two second target data types respectively based on the third target data type and the first ordering result.

In one possible implementation manner of the embodiment of the present application, when calculating the similarity between at least two other medicines and the new medicine based on the first component information and the second component information, the output module 206 is specifically configured to:

acquiring a first weight and a second weight, wherein the first weight is the weight of a new medicine, and the second weight is the weight respectively corresponding to at least two other medicines;

determining the content of each of the plurality of first components based on the first weight and the proportion information corresponding to each of the plurality of first components, and determining the content of each of the plurality of second components based on the second weight and the proportion information corresponding to each of the plurality of second components, wherein the first component is a component corresponding to a new medicine, and the second component is a component corresponding to at least two other medicines;

Based on a plurality of first composition components and a plurality of second composition components, determining the same component quantity, the first total component quantity, the second total component quantity and the same component type which are respectively corresponding to at least two other medicines, judging whether the first total component quantity is the same as the second total component quantity, and obtaining a judging result, wherein the first total component quantity is the total component quantity of the new medicine, and the second total component quantity is the total component quantity respectively corresponding to at least two other medicines;

In one possible implementation manner of the embodiment of the present application, when outputting data corresponding to at least two second target data types respectively based on the third target data type and the first ordering result, the output module 206 is specifically configured to:

Acquiring the medicine quantity of a target medicine;

sequencing at least two second target data types according to the number of the medicines to obtain a second sequencing result;

judging whether a fourth target data type exists in at least two second target data types, wherein the fourth target data type is the second target data type with the same medicine quantity;

if the data exists, sorting the fourth target data type based on the first sorting result, obtaining a third sorting result based on the second sorting result, and outputting data corresponding to at least two second target data types respectively based on the third sorting result;

and if the data does not exist, outputting the data corresponding to at least two second target data types respectively based on the second sorting result.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In an embodiment of the present application, as shown in fig. 3, an electronic device 30 shown in fig. 3 includes: a processor 301 and a memory 303. Wherein the processor 301 is coupled to the memory 303, such as via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 is not limited to the embodiment of the present application.

The processor 301 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 301 may also be a combination for performing computing functions, e.g., comprising at least one microprocessor combination, a combination of a DSP and a microprocessor, etc.

Bus 302 may include a path to transfer information between the components. Bus 302 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect Standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. Bus 302 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 3, but not only one bus or type of bus.

The Memory 303 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

The memory 303 is used for storing application program codes for executing the present application and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement what is shown in the foregoing method embodiments.

Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. But may also be a server or the like. The electronic device shown in fig. 3 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments herein.

The present application provides a computer readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above. Compared with the related technology, in the embodiment of the application, the test data is data generated in the clinical test process, the test data corresponds to a data type, in addition, in the clinical test process, in order to eliminate the influence of an irrelevant variable on a test result, a control group and a test group are often arranged, namely, the data generated in the clinical test comprises test group data and control group data, namely, the test data comprises control group data and test group data, the change data type is the data type corresponding to the data with larger phase difference in the control group data and the test group data, the test data is acquired, the follow-up determination of at least one change data type from the test group data and the control group data is facilitated, the first preset data type is the data type which is set in advance, is the data type which is influenced by an ideal application corresponding to a new drug, based on the first preset data type, whether at least one data type which does not belong to the first preset data type exists in the at least one data type is judged, namely, the first target data type is reached, so that when the first target data type exists, the new drug effect possibly belongs to a new drug is judged, the first target type can exist, the first target type can be the data corresponding to the first target type is obtained, the first target type is conveniently, the first target type is judged, the number is reached, the number of the first target type is reached, the first target type is corresponding to the first target type and the first target type is convenient, the number is the first target type, the number is the first type and the target type and the first type is reached, and the first target type is the first type is the target type is and the first type is corresponding the first type data type is and the first type data type is corresponding needs is, and outputting data corresponding to the second target data type and data corresponding to the first preset data type, so that the effect of analyzing the test data more comprehensively is achieved.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

The foregoing is only a partial embodiment of the present application and it should be noted that, for a person of ordinary skill in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method of data analysis, comprising:

obtaining test data of a new drug, wherein the test data corresponds to a data type, the test data comprises control group data and test group data, the control group data comprises control data of a plurality of control persons, and the test group data comprises test data of a plurality of subjects; the data types include heart rate, respiratory rate, blood pressure;

Determining at least one variation data type based on the control group data and the test group data; the change data type is used for referring to the data types with different data change conditions corresponding to the control group data and the experimental group data;

judging whether at least one first target data type exists in the at least one change data type or not based on a first preset data type; the first preset data type is used for referring to the data type which is corresponding to the new medicine and has an ideal purpose and affects the body; the first target data type is used for referring to data types except the first preset data type in the data types corresponding to the test data;

outputting data corresponding to a second target data type and data corresponding to the first preset data type, wherein the second target data type is a first target data type belonging to the first output data type;

Wherein the outputting the data corresponding to the second target data type includes:

acquiring first component information and second component information, wherein the first component information comprises the composition components of the new medicine, the second component information comprises the composition components of at least two other medicines, and the composition information of each other medicine is different; the other medicines are medicines with at least one component in the new medicine, the number of the other medicines is at least two, and the number of the second target data types is at least two;

2. A method of data analysis according to claim 1, wherein the test data includes vital sign data and response data, and the obtaining test data for a new drug comprises:

3. The method of claim 1, wherein said determining at least one type of variation data based on said control data and said test data comprises:

4. The method of claim 1, wherein the number of population to be tested is different and the corresponding preset ratio is different, and the determining whether the first target data type belongs to the first output data type based on the number and the number of population to be tested includes:

5. The method according to claim 1, wherein the first component information and the second component information further include ratio information corresponding to a plurality of components, respectively, and the calculating the similarity between the at least two other medicines and the new medicine based on the first component information and the second component information includes:

6. The method according to claim 1, wherein outputting data corresponding to at least two second target data types based on the third target data type and the first sorting result, respectively, comprises:

acquiring the medicine quantity of the target medicine;

7. An apparatus for data analysis, comprising:

the acquisition module is used for acquiring test data of a new drug, wherein the test data corresponds to a data type, the test data comprises control group data and test group data, the control group data comprises control data of a plurality of control persons, and the test group data comprises test data of a plurality of subjects; the data types include heart rate, respiratory rate, blood pressure;

a first determination module for determining at least one type of variation data based on the control group data and the test group data; the change data type is used for referring to the data types with different data change conditions corresponding to the control group data and the experimental group data;

The first judging module is used for judging whether at least one first target data type exists in the at least one change data type or not based on a first preset data type; the first preset data type is used for referring to the data type which is corresponding to the new medicine and has an ideal purpose and affects the body; the first target data type is used for referring to data types except the first preset data type in the data types corresponding to the test data;

the output module is used for outputting data corresponding to a second target data type and data corresponding to the first preset data type, wherein the second target data type is a first target data type belonging to the first output data type;

the output module is specifically configured to, when outputting data corresponding to the second target data type:

8. An electronic device, comprising:

at least one processor;

a memory;

at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a method of performing data analysis according to any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed in a computer, causes the computer to perform the method of data analysis according to any of claims 1-6.