CN116469503A

CN116469503A - Health data processing method and server based on big data

Info

Publication number: CN116469503A
Application number: CN202310374247.9A
Authority: CN
Inventors: 徐丽丽; 姜小清; 于勇; 邱智泉
Original assignee: Eastern Hepatobiliary Surgery Hospital Third Affiliated Hospital Of Naval Medical University
Current assignee: Eastern Hepatobiliary Surgery Hospital Third Affiliated Hospital Of Naval Medical University
Priority date: 2023-04-06
Filing date: 2023-04-06
Publication date: 2023-07-21
Anticipated expiration: 2043-04-06
Also published as: CN116469503B

Abstract

According to the health data processing method and the server based on the big data, global matching of the target comparison health description information and the quasi-marking electronic medical record is guaranteed through the text semantic representation carrier of the quasi-marking electronic medical record and the historical electronic medical record, matching of the health description information in the target comparison health description information and the health description information in the quasi-marking electronic medical record is guaranteed based on the health description commonality coefficient between the quasi-marking electronic medical record and the historical electronic medical record, and therefore the number of the health description information, the spatial distribution of the health description items, the health description item types and the like in the target comparison health description information and the quasi-marking electronic medical record are matched. Therefore, global matching and detailed matching of the target comparison health description information and the electronic medical record to be marked can be ensured, correlation between the target comparison health description information and the electronic medical record to be marked is improved, and accurate marking is carried out.

Description

Health data processing method and server based on big data

Technical Field

The application relates to the field of data processing, in particular to a health data processing method and a server based on big data.

Background

Along with the promotion of the internet medical treatment, the information islands of medical data of different systems are slowly broken, and meanwhile, a large amount of medical health data arrangement work is brought. For example, in the archiving process of medical health data (such as electronic medical records), in order to facilitate the subsequent user to quickly read the health data, to improve the efficiency, relevant marks need to be performed in the health data, for example, highlighting text content to be focused, annotating information in dimensions to be focused, and the like. It will be appreciated that if health data is marked one by manual means, the efficiency of data processing is greatly limited, which is detrimental to effective use and occupies medical resources. Then, automatic and accurate marking of medical health data is a technical problem to be solved.

Disclosure of Invention

The invention aims to provide a health data processing method and a server based on big data so as to solve the problems.

The implementation manner of the embodiment of the application is as follows:

in a first aspect, an embodiment of the present application provides a health data processing method based on big data, applied to a data processing server, where the method includes:

Responding to the data processing instruction, and acquiring a quasi-marked electronic medical record and a historical electronic medical record;

acquiring health description information in the quasi-marked electronic medical record and health description information in the historical electronic medical record;

determining a health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description information in the quasi-marked electronic medical record and the health description information in the historical electronic medical record;

determining a text semantic representation carrier of the electronic medical record to be marked and a text semantic representation carrier of the historical electronic medical record;

determining a first characterization carrier commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on a text semantic characterization carrier of the quasi-marked electronic medical record and a text semantic characterization carrier of the historical electronic medical record;

determining a medical record commonality coefficient between the quasi-marked electronic medical record and the historical electronic medical record based on the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record and the first characterization carrier commonality coefficient;

and determining target comparison health description information from the historical electronic medical record based on a medical record commonality coefficient between the quasi-marked electronic medical record and the historical electronic medical record so as to mark the quasi-marked electronic medical record based on the target comparison health description information.

Optionally, the health description information in the pseudo-mark electronic medical record includes a first health description text obtained by parsing the pseudo-mark electronic medical record, and the health description information in the history electronic medical record includes a second health description text obtained by parsing the history electronic medical record;

the method for determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description information in the quasi-marked electronic medical record and the health description information in the historical electronic medical record comprises the following steps:

determining a first number statistical result of target health description items in the pseudo-tagging electronic medical record based on the first health description text;

determining a second number of statistical results for the target health description item in the historical electronic medical record based on the second health description text;

determining a summation result and a difference result of target health description items in the quasi-marked electronic medical record and the historical electronic medical record based on the first number statistical result and the second number statistical result;

determining a health description item commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on a summation result and a difference result of the target health description item in the quasi-marked electronic medical record and the historical electronic medical record;

And determining the health description commonality coefficients of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficients of the quasi-marked electronic medical record and the historical electronic medical record.

Optionally, obtaining the health description information in the pseudo-tagging electronic medical record and the health description information in the historical electronic medical record includes:

performing health description item identification operation on the quasi-marked electronic medical record and the historical electronic medical record respectively to determine a first health description text included in the quasi-marked electronic medical record and a second health description text included in the historical electronic medical record;

based on the first health description text and the second health description text, determining a health description item type corresponding to each text unit in the pseudo-mark electronic medical record and a health description item type corresponding to each text unit in the history electronic medical record;

disassembling the quasi-marked electronic medical record into P first paragraphs and disassembling the historical electronic medical record into P second paragraphs, wherein the P first paragraphs and the P second paragraphs are mapped one by one, and P is more than or equal to 1;

determining a first health description item type corresponding to each text unit in each first paragraph based on the health description item type corresponding to each text unit in the electronic medical record to be marked, and taking the first health description item type corresponding to each text unit in each first paragraph as health description information in the electronic medical record to be marked;

And determining a second health description item type corresponding to each text unit in each second paragraph based on the health description item type corresponding to each text unit in the historical electronic medical record, and taking the second health description item type corresponding to each text unit in each second paragraph as health description information in the historical electronic medical record.

Optionally, determining the health description commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record based on the health description information in the pseudo-marking electronic medical record and the health description information in the history electronic medical record includes:

determining a health description item type commonality coefficient between each first paragraph and a corresponding second paragraph based on the first health description item type corresponding to each text unit in each first paragraph and the second health description item type corresponding to each text unit in each second paragraph;

determining the health description item type commonality coefficient of the quasi-marked electronic medical record and the history electronic medical record based on the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph;

and determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item type commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record.

Optionally, the first health description item type includes a first target health description item type, the second health description item type includes the second target health description item type, the first paragraph includes a first selected paragraph, the second paragraph includes a second selected paragraph, the first selected paragraph corresponds to the second selected paragraph, text units in the first selected paragraph belong to the first target health description item type, and text units in the second selected paragraph belong to the second target health description item type;

wherein determining the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph comprises:

determining a count of the number of identical health description item types of the first target health description item type and the second target health description item type;

determining a number sum result of the first target health description item type and the health description item type of the second target health description item type;

determining a health description item type commonality coefficient for the first selected paragraph and the second selected paragraph based on a count of the number of identical health description item types of the first target health description item type and the second target health description item type, and a sum of the number of health description item types of the first target health description item type and the second target health description item type;

The first health description text comprises a first number of statistical results of the target health description items included in the pseudo-tagging electronic medical record, and the second health description text comprises a second number of statistical results of the target health description items included in the pseudo-tagging electronic medical record;

wherein determining the health description commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record based on the health description item type commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record comprises:

determining a health description item commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on a summation result and a difference result of target health description items in the quasi-marked electronic medical record and the historical electronic medical record;

and determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficient and the health description item type commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record.

Optionally, the quasi-marked electronic medical record includes a first quasi-marked electronic medical record and a second quasi-marked electronic medical record, a medical record common coefficient between the first quasi-marked electronic medical record and the historical electronic medical record is a first medical record common coefficient, and a medical record common coefficient between the second quasi-marked electronic medical record and the historical electronic medical record is a second medical record common coefficient;

wherein determining target control health description information from the historical electronic medical record based on medical record commonality coefficients between the pseudo-tagging electronic medical record and the historical electronic medical record comprises:

respectively acquiring text semantic representation carriers of the first quasi-marked electronic medical record and the second quasi-marked electronic medical record;

determining a second characterization carrier commonality coefficient between the first pseudo-mark electronic medical record and the second pseudo-mark electronic medical record based on the text semantic characterization carriers of the first pseudo-mark electronic medical record and the second pseudo-mark electronic medical record;

and determining target comparison health description information of the first to-be-marked electronic medical record from the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient and the second characterization carrier commonality coefficient.

Optionally, determining the target control health description information of the first pseudo-marking electronic medical record from the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient and the second characterization carrier commonality coefficient includes:

determining a coefficient of involvement of the second pseudo-marking electronic medical record on the first pseudo-marking electronic medical record based on the second medical record coefficient of commonality and the second characterization carrier coefficient of commonality;

determining a correlation coefficient of the first pseudo-marked electronic medical record and the historical electronic medical record based on the involvement coefficient of the second pseudo-marked electronic medical record on the first pseudo-marked electronic medical record and the first medical record commonality coefficient;

and determining target comparison health description information of the first quasi-marked electronic medical record from the historical electronic medical record based on the correlation coefficient of the first quasi-marked electronic medical record and the historical electronic medical record.

Optionally, marking the electronic medical record to be marked based on the target control health description information includes:

performing text paragraph association on the target comparison health description information and the electronic medical record to be marked to obtain a text paragraph association result;

Marking the electronic medical record to be marked through the target comparison health description information based on the text paragraph association result to obtain a basic marking text;

text adjustment is carried out on the basic mark text through a mark adjustment network so as to realize marking of the electronic medical record to be marked;

before text adjustment is performed on the basic mark text through a mark adjustment network to realize marking of the quasi-marked electronic medical record, the method further comprises the following steps:

acquiring a target mark electronic medical record template;

performing text enhancement processing on the health description item of the target marked electronic medical record template to obtain an enhanced marked electronic medical record template;

loading the enhanced marked electronic medical record template to a to-be-debugged marked adjustment network to obtain an adjustment marked electronic medical record template;

determining an error between the adjustment marked electronic medical record template and the target marked electronic medical record template;

and optimizing the network configuration variables of the to-be-debugged mark adjusting network through the errors so as to optimize the to-be-debugged mark adjusting network into the mark adjusting network.

Optionally, the pseudo-marking electronic medical record includes a first pseudo-marking electronic medical record and a second pseudo-marking electronic medical record, and the obtaining the pseudo-marking electronic medical record and the history electronic medical record in response to the data processing instruction includes: acquiring a first to-be-marked electronic medical record, a second to-be-marked electronic medical record and a historical electronic medical record;

The method further comprises the steps of:

acquiring a first medical record commonality coefficient between the first quasi-marked electronic medical record and the historical electronic medical record;

acquiring a second medical record commonality coefficient between the second quasi-marked electronic medical record and the historical electronic medical record;

determining a second characterization carrier commonality coefficient between the first pseudo-mark electronic medical record and the second pseudo-mark electronic medical record based on the first pseudo-mark electronic medical record and the text semantic characterization carrier of the second pseudo-mark electronic medical record;

and determining target comparison health description information of the first quasi-marked electronic medical record from the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient and the second characterization carrier commonality coefficient so as to mark the first quasi-marked electronic medical record based on the target comparison health description information.

In a second aspect, embodiments of the present application provide a data processing server, including a memory and a processor, the memory storing a computer program, the processor implementing the above method when running the computer program.

In the following description, other features will be partially set forth. Upon review of the ensuing disclosure and the accompanying figures, those skilled in the art will in part discover these features or will be able to ascertain them through production or use thereof. The features of the present application may be implemented and obtained by practicing or using the various aspects of the methods, tools, and combinations that are set forth in the detailed examples described below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

The methods, systems, and/or programs in the accompanying drawings will be described further in terms of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein reference numerals represent similar mechanisms throughout the several views of the drawings.

Fig. 1 is a schematic illustration of an application scenario shown according to some embodiments of the present application.

FIG. 2 is a schematic diagram of hardware and software components in a data processing server, according to some embodiments of the present application.

Fig. 3 is a flow chart illustrating a big data based health data processing method according to some embodiments of the present application.

FIG. 4 is a schematic diagram of a data processing apparatus according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.

In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application may be practiced without these details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

These and other features, together with the functions, acts, and combinations of parts and economies of manufacture of the related elements of structure, all of which form part of this application, may become more apparent upon consideration of the following description with reference to the accompanying drawings. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the figures are not to scale.

The flowcharts are used in this application to describe implementations performed by systems according to embodiments of the present application. It should be clearly understood that the execution of the flowcharts may be performed out of order. Rather, these implementations may be performed in reverse order or concurrently. Additionally, at least one other execution may be added to the flowchart. One or more of the executions may be deleted from the flowchart.

Fig. 1 is a schematic illustration of a scenario according to some embodiments of the present application, including a data processing server 100 and a medical data uploading terminal 300 communicatively connected to each other via a network 200.

In some embodiments, please refer to fig. 2, which is a schematic diagram of an architecture of a data processing server 100, the data processing server 100 includes a data processing device 110, a memory 120, a processor 130 and a communication unit 140. The memory 120, the processor 130, and the communication unit 140 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The data processing device 110 includes at least one software functional module that may be stored in the memory 120 in the form of software or firmware (firmware) or cured in an Operating System (OS) of the data processing server 100. The processor 130 is configured to execute executable modules stored in the memory 120, such as software functional modules and computer programs included in the data processing device 110.

The Memory 120 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 120 is used for storing a program, and the processor 130 executes the program after receiving an execution instruction. The communication unit 140 is used for establishing a communication connection between the data processing server 100 and the medical data uploading terminal 300 through a network, and for transceiving data through the network.

The processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also Digital Signal Processors (DSPs)), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It is to be understood that the architecture shown in fig. 2 is illustrative only, and that data processing server 100 may also include more or fewer components than shown in fig. 2, or have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.

Fig. 3 is a flowchart of a big data based health data processing method according to some embodiments of the present application, which is applied to the data processing server 100 in fig. 1, and may specifically include the following steps 110 to 170. On the basis of the following steps, alternative embodiments will be described, which should be understood as examples and should not be interpreted as essential features for implementing the present solution.

Step 110, in response to the data processing instruction, obtaining the pseudo-marked electronic medical record and the historical electronic medical record.

The electronic medical record to be marked is an electronic medical record which needs to be marked with medical record content in real time, for example, the operation of highlighting or annotating the content which needs to be focused on is performed, and the history electronic medical record is an electronic medical record which has been marked with medical record content. That is, the matching degree between the history electronic medical record and the quasi-marked electronic medical record is evaluated through the marked content and the global content of the history electronic medical record, and if the matching condition is satisfied, the content of the quasi-marked electronic medical record is marked according to the marked content of the history electronic medical record, for example, highlighting or annotating the corresponding notice item in the corresponding health description item, for example, annotating the corresponding notice item in the corresponding position.

The number of the electronic medical records to be marked is one or more, and the number of the historical electronic medical records is one or more.

And step 120, acquiring the health description information in the quasi-marked electronic medical record and the health description information in the historical electronic medical record.

As an implementation manner, the health description information in the electronic medical record to be marked may include the target health description item, the type of the target health description item, the distribution condition and the number statistics of the target health description item in the electronic medical record to be marked, and other contents associated with the target health description item, which may be acquired in the electronic medical record to be marked, which are obtained by parsing the electronic medical record to be marked. The target health description items can be health indexes, nursing histories, user conditions and the like, one or more target health description items can be provided, and the actual content of the target health description items is configured based on actual application.

And 130, determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description information in the quasi-marked electronic medical record and the health description information in the historical electronic medical record.

As one embodiment, the health description commonality coefficient of the pseudo-tag electronic medical record and the history electronic medical record is, for example, a commonality coefficient (a value describing the degree of similarity) of the target health description items included in the pseudo-tag electronic medical record and the history electronic medical record, and the health description commonality coefficient includes, for example, a number commonality coefficient, a type commonality coefficient, a distribution information commonality coefficient, and the like of the target health description items. If the number of the historical electronic medical records is P, the health description commonality coefficient between the quasi-marked electronic medical records and the plurality of the historical electronic medical records can be represented by a table T, for example, T= { T11, T12 … … T1n … … T1P }, and T1n is the health description commonality coefficient of the first quasi-marked electronic medical record and the nth historical electronic medical record, wherein n is more than or equal to 1 and less than or equal to P.

And 140, determining a text semantic representation carrier of the electronic medical record to be marked and a text semantic representation carrier of the historical electronic medical record.

As an implementation manner, the quasi-marking electronic medical record and the history electronic medical record are subjected to representation carrier mining based on the quasi-debugging marking adjusting network, so that a text semantic representation carrier capable of representing the quasi-marking electronic medical record and a text semantic representation carrier capable of representing the history electronic medical record are obtained, wherein the text semantic representation carrier is a carrier such as a feature vector, a matrix, a tensor and the like, in other words, the text semantic representation carrier is text semantic feature information of the electronic medical record (quasi-marking electronic medical record or history electronic medical record). The architecture of the proposed debug flag tuning network may be any feasible machine learning algorithm, such as BERT, transformr, CNN, DNN, LSTM, etc.

Step 150, determining a first characterization carrier commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the text semantic characterization carrier of the quasi-marked electronic medical record and the text semantic characterization carrier of the historical electronic medical record.

As an implementation mode, a characterization carrier commonality coefficient between a text semantic characterization carrier of the electronic medical record to be marked and a text semantic characterization carrier of the historical electronic medical record is obtained, the characterization carrier commonality coefficient is determined to be a first characterization carrier commonality coefficient, and the larger the numerical value of the first characterization carrier commonality coefficient is, the higher the association degree between the electronic medical record to be marked and the historical electronic medical record is represented. Optionally, the corresponding commonality coefficient is obtained based on calculating the euclidean distance between the text semantic representation carrier of the pseudo-tagging electronic medical record and the text semantic representation carrier of the historical electronic medical record.

If the text semantic representation carrier of the electronic medical record to be marked is Mu, and the text semantic representation carrier of the history electronic medical record is Mv, the commonality coefficient of the text semantic representation carrier of the electronic medical record to be marked and the representation carrier of the text semantic representation carrier of the history electronic medical record is mu.Mv, and u is not more than the number of the electronic medical records to be marked. If the number of the historical electronic medical records is P, the first characterization carrier commonality coefficient of the quasi-marked electronic medical records and the plurality of the historical electronic medical records can be represented by a table R, for example, R= { R11, R12 … … R1n … … R1P }, R1n is the characterization carrier commonality coefficient between the first quasi-marked electronic medical record and the nth historical electronic medical record, and n is more than or equal to 1 and less than or equal to P.

Step 160, determining a medical record commonality coefficient between the pseudo-tag electronic medical record and the historical electronic medical record based on the health description commonality coefficient of the pseudo-tag electronic medical record and the historical electronic medical record and the first characterization carrier commonality coefficient.

As one implementation mode, the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record is summed with the first characterization carrier commonality coefficient, the sum result is used as the medical record commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record, or the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record is integrated with the first characterization carrier commonality coefficient, and the integrated result is used as the medical record commonality coefficient between the quasi-marked electronic medical record and the historical electronic medical record.

Based on the medical record commonality coefficient determined in the above process, taking the correlation of the commonality coefficient of the global of the quasi-marked electronic medical record and the historical electronic medical record into consideration according to the first characterization carrier commonality coefficient, and taking the matching condition of the quasi-marked electronic medical record and the health data details in the historical electronic medical record into consideration according to the health description commonality coefficient. If the number of the historical electronic medical records is P, the medical record commonality coefficient between the to-be-marked electronic medical record and the plurality of the historical electronic medical records can be represented by a table Y, for example, Y= { Y11, Y12 … … Y1n … … Y1P }, and Y1n is the medical record commonality coefficient of the first to-be-marked electronic medical record and the nth historical electronic medical record, and n is more than or equal to 1 and less than or equal to P.

The medical record commonality coefficient table Y of the quasi-marked electronic medical record and each history electronic medical record can be obtained by calculation based on the health description commonality coefficient table T of the quasi-marked electronic medical record and each history electronic medical record and the characterization carrier commonality coefficient table R of the quasi-marked electronic medical record and each history electronic medical record, and specifically, y=t·r.

And 170, determining target comparison health description information from the historical electronic medical record based on the medical record commonality coefficient between the quasi-marked electronic medical record and the historical electronic medical record so as to mark the quasi-marked electronic medical record based on the target comparison health description information.

As an implementation manner, based on the medical record commonality coefficients of the to-be-marked electronic medical record and each history electronic medical record, the target comparison health description information is determined in each history electronic medical record, for example, the history electronic medical record corresponding to the maximum value of the medical record commonality coefficient can be determined in the medical record commonality coefficient table Y, and the history electronic medical record is determined as the target comparison health description information of the to-be-marked electronic medical record.

It should be noted that if the number of the electronic medical records to be marked is 2, the dimension of the health description common coefficient table T of the electronic medical records to be marked and each history electronic medical record and the dimension of the characterization carrier common coefficient table R of the electronic medical records to be marked and each history electronic medical record are increased from one dimension to two dimensions.

In the above process of the embodiment of the application, in the process of determining the target comparison health description information for the quasi-marking electronic medical record, a global matching basis between the target comparison health description information and the quasi-marking electronic medical record is ensured through the text semantic representation carrier of the quasi-marking electronic medical record and the history electronic medical record, and meanwhile, the matching of the health description information in the target comparison health description information and the health description information in the quasi-marking electronic medical record is ensured through the health description commonality coefficient between the quasi-marking electronic medical record and the history electronic medical record, so that the matching of the target comparison health description information and details in the quasi-marking electronic medical record is ensured. In summary, the embodiment of the application can ensure the matching degree of the target comparison health description information and the electronic medical record to be marked in the global and local directions, so that the relevance between the target comparison health description information and the electronic medical record to be marked is higher, and the marking accuracy is more reliable in the process of marking the electronic medical record to be marked based on the target comparison health description information.

As one embodiment, after determining the target control health description information of the electronic medical record to be marked, the electronic medical record to be marked is marked based on the following manner: and carrying out text paragraph association on the target comparison health description information and the electronic medical record to be marked to obtain a text paragraph association result. Text paragraph association is, for example, to align the titles (including main title, sub-title) of the individual health description items; and marking the quasi-marked electronic medical record according to the target comparison health description information based on the text paragraph association result to obtain a basic marked text.

The basic mark text obtained in the process may have inconsistent text expression modes of health description items, such as different text words and different text lengths, and after the basic mark text is obtained based on the inconsistent text expression modes, text adjustment is performed on the basic mark text according to the debugged mark adjustment network, so that marking of the electronic medical record to be marked is facilitated. Before text adjustment is carried out on the basic mark text according to the debugged mark adjustment network to mark the electronic medical record to be marked, the debugging of the mark adjustment network is carried out based on the following mode: acquiring a target mark electronic medical record template; the health description item text enhancement processing is carried out on the target marked electronic medical record template to obtain an enhanced marked electronic medical record template, for example, disturbance noise is injected into the health description item text on the basis of Random Noise Injection to obtain a new text, so that the network has robustness to the noise, and of course, in other modes, the method can be realized by using methods such as EDA, AEDA, masked Language Model and the like, and the method is not particularly limited; loading the enhanced marked electronic medical record template into a to-be-debugged marked adjustment network to obtain an adjustment marked electronic medical record template; determining an error between the adjustment marked electronic medical record template and the target marked electronic medical record template; and optimizing the network configuration variables of the to-be-debugged mark adjusting network through errors to optimize the to-be-debugged mark adjusting network into the mark adjusting network.

Returning to the description of the process for determining the coefficient of commonality of health descriptions, the health description information in the electronic medical record to be marked may include a first health description text parsed from the electronic medical record to be marked, and the health description information in the electronic medical record to be historic may include a second health description text parsed from the electronic medical record to be historic. The first health description text comprises the statistics of the number of the target health description items in the electronic medical record to be marked, and the second health description text comprises the statistics of the number of the target health description items in the historical electronic medical record.

As one embodiment, the text recognition may be performed on the pseudo-tag electronic medical record or the history electronic medical record based on the target health description item recognition operator, where the first health description text or the second health description text is determined. .

The determination of the health description commonality coefficient may specifically include;

step 210, determining a first number statistics of the target health description items in the electronic medical record to be marked based on the first health description text.

Step 220, determining a second number of statistics of the target health description items in the historical electronic medical record based on the second health description text.

Step 230, determining a sum result and a difference result of the target health description items in the electronic medical record to be marked and the historical electronic medical record based on the first number of statistical results and the second number of statistical results.

Step 240, determining the commonality coefficient of the health description items of the quasi-marked electronic medical record and the historical electronic medical record based on the summation result and the difference result of the target health description items in the quasi-marked electronic medical record and the historical electronic medical record.

As an embodiment, the health description term commonality coefficient Q between the pseudo-tagging electronic medical record and the nth history electronic medical record may be:

Q＝E/D

E＝Sum

d=1+d-value i

The Sum is the summation result of the target health description items in the quasi-marked electronic medical record and the historical electronic medical record, and the D-value is the difference result of the target health description items in the quasi-marked electronic medical record and the historical electronic medical record.

Step 250, determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record.

As one embodiment, the health description term commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record is determined as the medical record commonality coefficient between the pseudo-marking electronic medical record and the history electronic medical record, that is, the health description term commonality coefficient table of the pseudo-marking electronic medical record and the history electronic medical record is determined as the health description commonality coefficient table between the pseudo-marking electronic medical record and the history electronic medical record.

Based on the above, the embodiment of the application ensures that the target contrast health description information is globally matched with the electronic medical record to be marked based on the characteristic carrier commonality coefficient of the electronic medical record, and simultaneously ensures that the target contrast health description information is the same as the number of the target health description items in the electronic medical record to be marked, so that the target health description items in the electronic medical record to be marked comprise corresponding health description items in the target contrast health description information in the process of marking the electronic medical record to be marked based on the target contrast health description information, and the marking is more accurate.

The determining process of the health description information specifically may include:

step 310, performing a health description item identification operation on the pseudo-marked electronic medical record and the historical electronic medical record respectively to determine a first health description text included in the pseudo-marked electronic medical record and a second health description text included in the historical electronic medical record.

The first health description text may include target health description items existing in the electronic medical record to be marked and distribution conditions (such as paragraph distribution conditions) of each target health description item in the electronic medical record to be marked, and the second health description text includes target health description items existing in the electronic medical record to be marked and distribution conditions of each target health description item in the electronic medical record to be marked, and one electronic medical record to be marked or the electronic medical record to be marked may have a plurality of target health description items, and each target health description item may correspond to a different health description item type.

As one implementation mode, the identification of the quasi-marked electronic medical record is based on the debugged health description item identification operator, and the target health description items and the distribution situation of the target health description items are identified in the quasi-marked electronic medical record or the historical electronic medical record.

Step 320, determining a health description item type corresponding to each text unit in the electronic medical record to be marked and a health description item type corresponding to each text unit in the historical electronic medical record based on the first health description text and the second health description text.

As one implementation mode, if the distribution situation of each target health description item is identified in the to-be-marked electronic medical record or the history electronic medical record, each text unit in the to-be-marked electronic medical record or the history electronic medical record also carries corresponding indication information. If the target health description items of the three health description item types I, II and III are identified in the electronic medical record to be marked, a text unit in the electronic medical record to be marked is one of the three health description item types I, II and III or is other invalid text. The same idea is referred to for the obtaining mode of the text unit corresponding to the health description item type of each text unit in the history electronic medical record.

Step 330, disassemble the quasi-marked electronic medical record into P first paragraphs, and disassemble the history electronic medical record into P second paragraphs, the P first paragraphs and the P second paragraphs are mapped one by one, and P is more than or equal to 1.

The disassembly process is not limited, and all that is required is to map each text paragraph in the electronic medical record to each text paragraph in the history electronic medical record one by one.

Step 340, determining a first health description item type corresponding to each text unit in each first paragraph based on the health description item type corresponding to each text unit in the electronic medical record to be marked, and using the first health description item type corresponding to each text unit in each first paragraph as health description information in the electronic medical record to be marked.

As one embodiment, the first health description item type A corresponding to each text unit in each first paragraph can be collected ⁿ _x Health description information as a pseudo-mark electronic medical record, wherein A ⁿ _x And carrying indication information of the health description item types included in the paragraph, wherein x is not greater than the number of the to-be-marked electronic medical records, n is not greater than the number of first paragraphs in the x-th to-be-marked electronic medical records, for example, one first paragraph A has text units corresponding to the three health description item types I, II and III, and then the first health description item type Anx of the first paragraph A comprises the three health description item types I, II and III.

And step 350, determining a second health description item type corresponding to each text unit in each second paragraph based on the health description item type corresponding to each text unit in the history electronic medical record, and taking the second health description item type corresponding to each text unit in each second paragraph as health description information in the history electronic medical record.

As one embodiment, the second health description item type A corresponding to each text unit in each second paragraph can be collected ⁿ _y A is health description information of the quasi-marked electronic medical record ⁿ _y And carrying indication information of the health description item types included in the paragraph, wherein y is not more than the number of the electronic medical records to be marked, n is not more than the number of the first paragraph in the y-th electronic medical record to be marked, for example, a second paragraph contains text units corresponding to the three health description item types IV, V and VI, and the second health description item type of the second paragraph comprises the three health description item types IV, V and VI.

In one embodiment, after the first health description item type corresponding to each text unit in each first paragraph and the second health description item type corresponding to each text unit in each second paragraph are obtained, health description information in the quasi-marking electronic medical record and the historical electronic medical record is determined based on the first health description item type in each first paragraph and the second health description item type in each second paragraph. As one embodiment, the text unit indication information type commonality coefficient between each first paragraph and the corresponding second paragraph is collected based on the first health description item type in each first paragraph and the second health description item type in each second paragraph, and the health description commonality coefficient between the quasi-marked electronic medical record and the historical electronic medical record is determined based on the text unit indication information type commonality coefficient corresponding to each first paragraph. For example, the text unit indication information type commonality coefficients of each first paragraph and the corresponding second paragraph are added to determine the health description commonality coefficient between the pseudo-marking electronic medical record and the historical electronic medical record. The text unit indication information type (i.e. the health description item type indication information corresponding to the text unit, such as label information) common coefficient of the first paragraph and the corresponding second paragraph can adopt the number of the text units which are consistent with the first paragraph and the second paragraph indication information, and the common coefficient of the text unit indication information type of the first paragraph and the corresponding second paragraph is determined based on the proportion of the number of the text units which are consistent with the first paragraph and the second paragraph indication information and the total number of the text units of the first paragraph or the second paragraph.

For the determination of the health description commonality coefficient, another embodiment is proposed, which may specifically include:

step 410, determining a health description item type commonality coefficient between each first paragraph and the corresponding second paragraph based on the first health description item type corresponding to each text unit in each first paragraph and the second health description item type corresponding to each text unit in each second paragraph.

As one embodiment, the first health description item type corresponding to each text unit in each first paragraph is determined, i.e. the statistics Z (a ⁿ _x ) Determining a second health description item type corresponding to each text unit in each second paragraph, i.e. counting the number statistics Z (A ⁿ _y ). As one embodiment, if the first health description item type comprises a first target health description item type, the second health description item type comprises a second target health description item type, the first paragraph of the x-th pseudo-mark electronic medical record comprises a first selected paragraph, the y-th history electronic medical record second paragraph comprises a second selected paragraph, the first selected paragraph corresponds to the second selected paragraph, and the text units in the first selected paragraph correspond to the first target health description item type A ⁿ _x Text elements in the second selected paragraph correspond to the second target health description item type A ⁿ _y N is the order flag of the paragraph corresponding to the first selected paragraph or the second selected paragraph. Z (A) ⁿ _x ) And Z (A) ⁿ _y ) Representing the total number of solution sets.

The process of determining the health description item type commonality coefficient for the first selected paragraph and the second selected paragraph may be determining a count of the number of the same health description item types of the first target health description item type and the second target health description item type; determining the sum result of the numbers of the health description item types of the first target health description item type and the second target health description item type; a health description item type commonality coefficient for the first selected paragraph and the second selected paragraph is then determined based on the count of the number of the same health description item types of the first target health description item type and the second target health description item type, and the sum of the number of the health description item types of the first target health description item type and the second target health description item type.

The process of determining the health description item type commonality coefficient of the first selected passage and the second selected passage is, for example, determining a number sum result Z (a ⁿ _x ) And Z (A) ⁿ _y ) The method comprises the steps of carrying out a first treatment on the surface of the Based on the first target health description item type Z (A ⁿ _x ) And a second target health description item type Z (A ⁿ _y ) The number statistics Z (A) ⁿ _x ∩A ⁿ _y ) The result of the sum of the number of health description item types of the first target health description item type and the second target health description item type (Z (a) ⁿ _x )+Z(A ⁿ _y ) A health description item type commonality coefficient of the first selected paragraph and the second selected paragraph is obtained.

The health description item type commonality coefficient F of the first selected paragraph and the second selected paragraph is:

F＝Z(A ⁿ _x ∩A ⁿ _y )÷(Z(A ⁿ _x )+Z(A ⁿ _y ))

as an embodiment, the health description item type commonality coefficient F of each first paragraph and the corresponding second paragraph may be obtained based on the health description item type commonality coefficient determination manner of the first selected paragraph and the second selected paragraph.

Step 420, determining the health description item type commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record based on the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph.

As an implementation manner, the health description item type commonality coefficients of the first paragraphs and the corresponding second paragraphs can be added to obtain the health description item type commonality coefficients of the pseudo-marked electronic medical record and the historical electronic medical record.

Step 430, determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item type commonality coefficients of the quasi-marked electronic medical record and the historical electronic medical record.

As an implementation manner, the health description item type commonality coefficient of the quasi-marked electronic medical record and the history electronic medical record can be determined as the health description commonality coefficient of the quasi-marked electronic medical record and the history electronic medical record, that is, the health description commonality coefficient of the quasi-marked electronic medical record and the history electronic medical record is determined as the health description commonality coefficient table between the quasi-marked electronic medical record and the history electronic medical record.

As an implementation manner, the first health description text analyzed in the electronic medical record to be marked may include a first number of statistics of the target health description items in the electronic medical record to be marked, and the second health description text identifying the operation in the electronic medical record to be marked may include a second number of statistics of the target health description items in the electronic medical record to be marked.

The obtaining of the health description commonality coefficient can also be implemented by the following modes, which specifically include:

step 510, determining a health description item type commonality coefficient between each first paragraph and the corresponding second paragraph based on the first health description item type corresponding to each text unit in each first paragraph and the second health description item type corresponding to each text unit in each second paragraph.

Step 520, determining the health description item type commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record based on the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph.

Step 530, determining a sum result and a difference result of the target health description items in the electronic medical record to be marked and the historical electronic medical record based on the first number of statistical results and the second number of statistical results.

Step 540, determining the commonality coefficient of the health description items of the quasi-marked electronic medical record and the historical electronic medical record based on the summation result and the difference result of the target health description items in the quasi-marked electronic medical record and the historical electronic medical record.

Step 550, determining the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficient and the health description item type commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record.

As one implementation mode, the health description item type commonality coefficient and the health description item commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record are summed to obtain the health description commonality coefficient of the quasi-marked electronic medical record and the historical electronic medical record. .

Based on the process, the global matching of the target control health description information and the to-be-marked electronic medical record is ensured based on the characterization carrier commonality coefficient of the electronic medical record, the matching of the number of the target control health description information and the number of the target health description items in the to-be-marked electronic medical record is ensured, and the spatial distribution matching of the target control health description information and the health description information in the target health description items is ensured.

As an implementation manner, the quasi-marked electronic medical record includes a first quasi-marked electronic medical record and a second quasi-marked electronic medical record (for example, electronic medical records of different stages of the same user generally have higher similarity), a medical record common coefficient between the first quasi-marked electronic medical record and the historical electronic medical record can be a first medical record common coefficient, and a medical record common coefficient between the second quasi-marked electronic medical record and the historical electronic medical record can be a second medical record common coefficient. In the conventional thinking, if the first quasi-marking electronic medical record and the second quasi-marking electronic medical record are marked, the comparison health description information needs to be determined for the first quasi-marking electronic medical record and the second quasi-marking electronic medical record respectively, and in the method provided by the embodiment of the application, the acquisition process of the target comparison health description information includes:

step 610, obtaining text semantic representation carriers of the first pseudo-marking electronic medical record and the second pseudo-marking electronic medical record respectively.

As an implementation mode, the first quasi-marked electronic medical record and the second quasi-marked electronic medical record are subjected to representation carrier mining based on the quasi-debugging mark adjusting network, and a text semantic representation carrier for representing the overall situation of the first quasi-marked electronic medical record and a text semantic representation carrier for representing the overall situation of the second quasi-marked electronic medical record are obtained.

Step 620, determining a second characterization carrier commonality coefficient between the first and second electronic medical records based on the textual semantic characterization carriers of the first and second electronic medical records.

As an implementation manner, a common coefficient between the text semantic representation carrier of the first to-be-marked electronic medical record and the text semantic representation carrier of the second to-be-marked electronic medical record can be determined to be the second representation carrier common coefficient.

As one implementation mode, after the characterization carrier commonality coefficients of the first quasi-marked electronic medical record and the second quasi-marked electronic medical record are obtained, the target comparison health description information of the first quasi-marked electronic medical record is determined in the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient and the second characterization carrier commonality coefficient.

As one embodiment, determining the target control health description information of the first pseudo-marking electronic medical record from the historical electronic medical records based on the first medical record commonality coefficient, the second medical record commonality coefficient, and the second characterization carrier commonality coefficient, includes:

step 630, determining a coefficient of involvement of the second pseudo-marking electronic medical record on the first pseudo-marking electronic medical record based on the second medical record commonality coefficient and the second characterization carrier commonality coefficient.

As one implementation mode, the second characterization carrier commonality coefficient of the second quasi-marked electronic medical record and the first quasi-marked electronic medical record and the second medical record commonality coefficient of the second quasi-marked electronic medical record and the historical electronic medical record are summed to obtain the involvement coefficient of the second quasi-marked electronic medical record relative to the first quasi-marked electronic medical record.

Step 640, determining a correlation coefficient of the first pseudo-marked electronic medical record and the historical electronic medical record based on the coefficient of involvement of the second pseudo-marked electronic medical record on the first pseudo-marked electronic medical record and the first medical record commonality coefficient.

As one implementation mode, the coefficient of involvement of the second quasi-marked electronic medical record on the first quasi-marked electronic medical record and the coefficient of commonality of the first quasi-marked electronic medical record and the first medical record of the historical electronic medical record are summed to obtain the related coefficient of the first quasi-marked electronic medical record and the historical electronic medical record.

Step 650, determining the target control health description information of the first pseudo-marking electronic medical record in the history electronic medical record based on the correlation coefficient of the first pseudo-marking electronic medical record and the history electronic medical record.

As one implementation mode, the method is used for determining the correlation coefficient of the first quasi-marked electronic medical record and the plurality of historical electronic medical records, and then acquiring the historical electronic medical record corresponding to the maximum correlation coefficient from the plurality of correlation coefficients as the target comparison health description information of the first quasi-marked electronic medical record.

The correlation coefficient of the first quasi-marked electronic medical record and the historical electronic medical record takes the matching influence of the text characteristics of the electronic medical record in the first quasi-marked electronic medical record and the historical electronic medical record and the second quasi-marked electronic medical record on the first quasi-marked electronic medical record into consideration.

As an implementation manner, after the medical record correlation coefficients of the to-be-marked electronic medical record and each history electronic medical record are determined based on the above process, the history electronic medical record corresponding to the maximum value of the medical record correlation coefficients can be determined as the target comparison health description information of the to-be-marked electronic medical record.

Based on the method of the embodiment of the application, the similar target comparison health description information can be determined for each quasi-marked electronic medical record in the medical record combination, and marking of each quasi-marked electronic medical record in the medical record combination based on the target comparison health description information can ensure that the marking content deviation is within a controllable range.

The embodiment of the application also provides another health data processing method based on big data, which specifically comprises the following steps: .

Step 710, obtaining a first pseudo-marking electronic medical record, a second pseudo-marking electronic medical record and a history electronic medical record.

Step 720, obtaining a first medical record commonality coefficient between the first pseudo-marked electronic medical record and the historical electronic medical record.

The first medical record commonality coefficient is a characterization carrier commonality coefficient between the first pseudo-marked electronic medical record and the historical electronic medical record, or a commonality coefficient of the rest and the electronic medical record text associated based on the characterization carrier commonality coefficient between the first pseudo-marked electronic medical record and the historical electronic medical record, such as a commonality coefficient determined based on the health description commonality coefficient between the first pseudo-marked electronic medical record and the historical electronic medical record and the characterization carrier commonality coefficient.

The process of determining the commonality coefficient of the characterization carrier between the first to-be-marked electronic medical record and the historical electronic medical record is, for example, determining a text semantic characterization carrier of the first to-be-marked electronic medical record and a text semantic characterization carrier of the historical electronic medical record; and then determining the commonality coefficients of the representation carriers of the first quasi-marked electronic medical record and the historical electronic medical record based on the text semantic representation carrier of the first quasi-marked electronic medical record and the text semantic representation carrier of the historical electronic medical record. The process of determining the health description commonality coefficient between the first quasi-marked electronic medical record and the historical electronic medical record is, for example, that a first health description text is identified in the first quasi-marked electronic medical record, and a second health description text is identified in the historical electronic medical record; then determining a first number statistical result of the target health description items in the first to-be-marked electronic medical record based on the first health description text; determining a second number statistical result of the target health description items in the historical electronic medical record based on the second health description text; then, based on the first number statistical result and the second number statistical result, determining a summation result and a difference result of target health description items in the first to-be-marked electronic medical record and the historical electronic medical record; then determining a health description item commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record based on a summation result and a difference result of the target health description items in the first quasi-marked electronic medical record and the historical electronic medical record; and finally, determining the health description commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record.

Alternatively, the determining the health description commonality coefficient between the first to-be-marked electronic medical record and the history electronic medical record may further determine the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph based on a first health description item type corresponding to each text unit in each first paragraph and a second health description item type corresponding to each text unit in each second paragraph; determining the health description item type commonality coefficient of the first quasi-marked electronic medical record and the history electronic medical record based on the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph; and then determining the health description commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record based on the health description item type commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record.

Or, determining the health description commonality coefficient between the first to-be-marked electronic medical record and the historical electronic medical record may be based on a first health description item type corresponding to each text unit in each first paragraph and a second health description item type corresponding to each text unit in each second paragraph, and determining the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph; determining the health description item type commonality coefficient of the first quasi-marked electronic medical record and the history electronic medical record based on the health description item type commonality coefficient between each first paragraph and the corresponding second paragraph; then, based on the first number statistical result and the second number statistical result, determining a summation result and a difference result of target health description items in the first to-be-marked electronic medical record and the historical electronic medical record; then determining a health description item commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record based on a summation result and a difference result of the target health description items in the first quasi-marked electronic medical record and the historical electronic medical record; and finally, determining the health description commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record based on the health description item commonality coefficient and the health description item type commonality coefficient of the first quasi-marked electronic medical record and the historical electronic medical record.

Step 730, obtaining a second medical record commonality coefficient between the second pseudo-marked electronic medical record and the historical electronic medical record.

The second medical record commonality coefficient may be a characterization carrier commonality coefficient between the second pseudo-tag electronic medical record and the historical electronic medical record, or a commonality coefficient of the rest and the electronic medical record text associated determined based on the characterization carrier commonality coefficient between the second pseudo-tag electronic medical record and the historical electronic medical record, such as a commonality coefficient determined based on the health description commonality coefficient and the characterization carrier commonality coefficient between the second pseudo-tag electronic medical record and the historical electronic medical record. The determining of the health description commonality coefficient and the characterization carrier commonality coefficient between the second pseudo-tag electronic medical record and the historical electronic medical record may refer to the determining of the health description commonality coefficient and the characterization carrier commonality coefficient between the first pseudo-tag electronic medical record and the historical electronic medical record.

Step 740, respectively obtaining the text semantic representation carrier of the first pseudo-marking electronic medical record and the second pseudo-marking electronic medical record.

Step 750, determining a second characterization carrier commonality coefficient between the first and second electronic medical records based on the text semantic characterization carriers of the first and second electronic medical records.

Step 760, determining target control health description information of the first electronic medical record to be marked in the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient and the second characterization carrier commonality coefficient, so as to mark the first electronic medical record to be marked based on the target control health description information.

In summary, the method provided by the embodiment of the application ensures the global matching of the target comparison health description information and the quasi-marking electronic medical record through the text semantic representation carrier of the quasi-marking electronic medical record and the history electronic medical record, and ensures the matching of the health description information in the target comparison health description information and the health description information in the quasi-marking electronic medical record based on the health description commonality coefficient between the quasi-marking electronic medical record and the history electronic medical record, so that the number of the health description information in the target comparison health description information and the quasi-marking electronic medical record, the spatial distribution of the health description items, the health description item types and the like are matched. Therefore, global matching and detailed matching of the target comparison health description information and the electronic medical record to be marked can be ensured, correlation between the target comparison health description information and the electronic medical record to be marked is improved, and accurate marking is carried out.

Referring to fig. 4, a functional block diagram of a data processing apparatus 110 according to an embodiment of the present invention is provided, where the data processing apparatus 110 may be used to execute a health data processing method based on big data, and the data processing apparatus 110 includes:

a medical record obtaining module 111, configured to obtain a pseudo-marked electronic medical record and a history electronic medical record in response to the data processing instruction;

an information obtaining module 112, configured to obtain health description information in the electronic medical record to be marked and health description information in the historical electronic medical record;

a first commonality determining module 113, configured to determine a health description commonality coefficient of the pseudo-marking electronic medical record and the history electronic medical record based on the health description information in the pseudo-marking electronic medical record and the health description information in the history electronic medical record;

a carrier mining module 114 for determining a text semantic representation carrier of the electronic medical record to be marked and a text semantic representation carrier of the historical electronic medical record;

a second commonality determining module 115, configured to determine a first commonality coefficient of the pseudo-marking electronic medical record and the historical electronic medical record based on the text semantic representation carrier of the pseudo-marking electronic medical record and the text semantic representation carrier of the historical electronic medical record;

A third commonality determining module 116, configured to determine a medical record commonality coefficient between the pseudo-tag electronic medical record and the history electronic medical record based on the health description commonality coefficient of the pseudo-tag electronic medical record and the history electronic medical record and the first characterization carrier commonality coefficient;

the target determining module 117 is configured to determine target control health description information from the historical electronic medical record based on a medical record commonality coefficient between the pseudo-marking electronic medical record and the historical electronic medical record, so as to mark the pseudo-marking electronic medical record based on the target control health description information.

Since in the above embodiments, the detailed description has been made of the health data processing method based on big data provided in the embodiments of the present invention, and the principle of the data processing apparatus 110 is the same as that of the method, the execution principle of each module of the data processing apparatus 110 will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners as well. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an internet of things data server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

It is to be understood that the terminology which does not make a noun interpretation with respect to the above description is not to be interpreted as a noun interpretation, and that the skilled person can unambiguously ascertain the meaning to which it refers from the above disclosure. The foregoing of the disclosure of the embodiments of the present application will be apparent to and complete with respect to those skilled in the art. It should be appreciated that the process of deriving and analyzing technical terms not explained based on the above disclosure by those skilled in the art is based on what is described in the present application, and thus the above is not an inventive judgment of the overall scheme.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

It should also be appreciated that in the foregoing description of the embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one of the embodiments of the invention. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.

Claims

1. A health data processing method based on big data, characterized by being applied to a data processing server, the method comprising:

2. The method of claim 1, wherein the health description information in the pseudo-tagging electronic medical record includes a first health description text parsed from the pseudo-tagging electronic medical record, and the health description information in the history electronic medical record includes a second health description text parsed from the history electronic medical record;

3. The method of claim 1, wherein obtaining the health description information in the pseudo-tagging electronic medical record and the health description information in the historical electronic medical record comprises:

4. The method of claim 3, wherein determining a health description commonality coefficient for the pseudo-tagging electronic medical record and the historical electronic medical record based on the health description information in the pseudo-tagging electronic medical record and the health description information in the historical electronic medical record comprises:

5. The method of claim 4, wherein the first health description item type comprises a first target health description item type, the second health description item type comprises the second target health description item type, the first paragraph comprises a first selected paragraph, the second paragraph comprises a second selected paragraph, the first selected paragraph corresponds to the second selected paragraph, text units in the first selected paragraph belong to the first target health description item type, and text units in the second selected paragraph belong to the second target health description item type;

6. The method of claim 1, wherein the pseudo-marking electronic medical record comprises a first pseudo-marking electronic medical record and a second pseudo-marking electronic medical record, a medical record co-occurrence coefficient between the first pseudo-marking electronic medical record and the historical electronic medical record being a first medical record co-occurrence coefficient, and a medical record co-occurrence coefficient between the second pseudo-marking electronic medical record and the historical electronic medical record being a second medical record co-occurrence coefficient;

7. The method of claim 6, wherein determining target control health description information for the first simulated electronic medical record from the historical electronic medical record based on the first medical record commonality coefficient, the second medical record commonality coefficient, and the second characterization carrier commonality coefficient comprises:

8. The method of any one of claims 1-7, wherein marking the electronic medical record to be marked based on the target control health description information comprises:

acquiring a target mark electronic medical record template;

9. The method of claim 1, wherein the pseudo-marking electronic medical record comprises a first pseudo-marking electronic medical record and a second pseudo-marking electronic medical record, the obtaining the pseudo-marking electronic medical record and the history electronic medical record in response to the data processing instructions comprising: acquiring a first to-be-marked electronic medical record, a second to-be-marked electronic medical record and a historical electronic medical record;

the method further comprises the steps of:

10. A data processing server comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the method of any one of claims 1 to 9.