WO2019136807A1 - Medical data relationship image acquisition method and apparatus, terminal device and storage medium - Google Patents

Abstract

Disclosed are a medical data relationship image acquisition method and apparatus, a terminal device and a storage medium. The medical data relationship image acquisition method comprises: acquiring at least one piece of target medical data; carrying out association analysis on the target medical data using an Apriori algorithm to acquire a degree of medical data relationship; and carrying out chart transformation on the degree of medical data relationship using an E-charts tool to acquire a medical data relationship image. The medical data relationship image acquisition method can enable a user to intuitively see a relationship between a disease characteristic and a symptom characteristic, thus facilitating the user understanding his/her possible disease condition according to his/her symptoms.

Description

Medical data relationship image acquisition method, device, terminal device and storage medium

This patent application is based on the Chinese Patent Application No. 201810031265.6 filed on January 12, 2018, entitled "Medical Data Relation Image Acquisition Method, Apparatus, Terminal Equipment and Storage Medium", and requires priority.

Technical field

The present application relates to the field of data processing, and in particular, to a method, an apparatus, a terminal device, and a storage medium for acquiring a medical data relationship image.

Background technique

The identification of the current disease is usually determined by the doctor according to the patient's symptoms, depends on the doctor's professional and experience, and can not enable the user to know his or her health according to his or her symptoms. When the user queries the medical website, the medical data such as symptoms, diseases and treatments provided on the medical website are displayed independently, and the relationship between the various medical data (ie, the degree of relationship) is not provided, so that the user cannot base the medical data according to the medical data. Keep abreast of your health status.

Summary of the invention

The embodiment of the present application provides a medical data relationship image acquisition method, device, terminal device and storage medium to solve the problem of traditional medical data independent display.

In a first aspect, an embodiment of the present application provides a method for acquiring a medical data relationship image, including:

Obtaining at least one target medical data;

Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.

In a second aspect, the embodiment of the present application provides a medical data relationship image acquiring apparatus, including:

a target medical data acquisition module, configured to acquire at least one target medical data;

a medical data relationship obtaining module, configured to perform correlation analysis on the target medical data by using an Apriori algorithm, and obtain a medical data relationship degree;

The medical data relation image obtaining module is configured to perform a graph conversion on the medical data relationship degree by using an E-charts tool to obtain a medical data relationship image.

In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, where the processor executes the computer The following steps are implemented when reading the instruction:

Obtaining at least one target medical data;

Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.

In a fourth aspect, an embodiment of the present application provides a computer readable medium storing computer readable instructions, where the computer readable instructions are executed by a processor to implement the following steps:

Obtaining at least one target medical data;

Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.

In the medical data relation image acquisition method, device, terminal device and storage medium provided by the embodiments of the present application, at least one target medical data is first acquired, and then the Apriori algorithm is used to perform correlation analysis on the target medical data, and the medical data relationship degree is obtained. To help users judge the probability of illness and prevent it in time. Finally, the E-charts tool is used to graphically convert the relationship between medical data and obtain medical data relationship images so that users can visually see the relationship between disease characteristics and symptom characteristics, which helps users to understand their possible diseases according to their own symptoms. The condition.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings may also be obtained from those of ordinary skill in the art based on these drawings without the inventive labor.

1 is a flowchart of a medical data relationship image acquisition method provided in Embodiment 1.

FIG. 2 is a specific schematic diagram of step S10 of FIG. 1.

FIG. 3 is a specific schematic diagram of step S12 of FIG. 2.

FIG. 4 is a specific schematic diagram of step S20 of FIG. 1.

FIG. 5 is a specific schematic diagram of step S30 of FIG. 1.

6 is a schematic block diagram of a medical data relation image acquiring device provided in Embodiment 2.

FIG. 7 is a schematic diagram of a terminal device provided in Embodiment 4.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

Example 1

FIG. 1 is a flow chart showing a method of acquiring a medical data relationship image in the present embodiment. The medical data relation image acquisition method can quickly collect a large amount of medical data from the network to perform relationship analysis based on the collected medical data. The medical data relationship image acquisition method can be specifically applied to the medical knowledge base management system, which is used for analyzing the relationship characteristics of the symptoms input by the user, and recommending a list of suspected disease characteristics for the user, which can effectively assist the user to understand. Self-health status. As shown in FIG. 1, the medical data relationship image acquisition method includes the following steps:

S10: Acquire at least one target medical data.

Among them, the target medical data is data for performing model training. The target medical data includes, but is not limited to, medical data such as symptom characteristics, disease characteristics, and the like in the present embodiment. In this embodiment, the target medical data is acquired for subsequent model training.

S20: The Apriori algorithm is used to analyze the relevance of the target medical data to obtain the relationship of the medical data.

Among them, Apriori algorithm is a representative algorithm for association rule mining. Apriori algorithm is widely used in various industries, with less calculation, easy to understand, and can effectively mine the potential rules between data. The medical data relationship is used to reflect the degree of association between disease characteristics and symptom characteristics. Specifically, the Apriori algorithm is used to analyze the target medical data, and the N frequent items (N>1) are generated by continuous circulation until the frequent sets are obtained, so that the medical data relationship degree is obtained, and the user can quickly learn the health of the user. Situation, timely prevention.

S30: The E-charts tool is used to perform graph conversion on medical data relationship degree, and obtain medical data relationship image.

The medical data relation image refers to an image obtained by graphically converting the degree of medical data relationship. ECharts (Enterprise Charts) is a pure Javascript chart library that runs smoothly on PCs and mobile devices. It is compatible with most browsers. The underlying version relies on the lightweight Canvas library ZRender. Users provide intuitive, vivid, highly personalized data visualization charts. The Echarts tool can effectively improve the visualization of data and achieve higher interactivity.

In this embodiment, at least one target medical data is acquired first, and then the Apriori algorithm is used to perform correlation analysis on the target medical data, and the degree of medical data relationship is obtained to assist the user in judging the probability of disease and prevent it in time. Finally, the E-charts tool is used to convert the medical data relationship degree and obtain the medical data relationship image, so that the user can visually see the relationship between the data, assist the user in analysis and consultation, and improve work efficiency.

In a specific embodiment, as shown in FIG. 2, in step S10, at least one target medical data is acquired, which specifically includes the following steps:

S11: Get the target webpage address.

The target webpage address is a webpage address corresponding to the target medical data to be obtained in advance. For example: 39 health website. Support for obtaining target medical data based on the target web page address by obtaining the target web page address to enable subsequent crawling of the target medical data using the web crawler technology.

S12: The crawler tool is used to crawl the webpage corresponding to the target webpage address to obtain at least one original medical data.

Among them, the crawler tool is a tool for automatically crawling the webpage content corresponding to the webpage address according to certain rules, such as a Python crawler tool. Specifically, the crawler tool is used to crawl the webpage content corresponding to the webpage address to obtain at least one original medical data, and each of the original medical data includes an actual disease characteristic and a corresponding at least one symptom characteristic, such as a cold (actual disease characteristic). Corresponding to symptoms such as runny nose, headache and fever. In this embodiment, the crawler tool is used to crawl the webpage corresponding to the target webpage address, and no manual search is needed, which is beneficial to improving the efficiency of data collection.

In this embodiment, the crawler tool performs crawling data on the target webpage address in a periodic crawling manner, so that the original medical data is time-series, so that the target medical features acquired by the subsequent model training are also sequential.

S13: Perform data cleaning on at least one original medical data to obtain at least one target medical data.

Among them, data cleaning refers to the method of processing raw medical data according to certain rules to obtain pure target medical data. Target medical data refers to pure data processed in accordance with data cleaning rules. The data cleaning rules include, but are not limited to, removing duplicate data. Since each raw medical data contains actual disease characteristics and corresponding at least one symptom characteristic, when cleaning according to the data cleaning rule, two or more original medical data having the same disease characteristics and symptom characteristics can be combined into one. Raw medical data. In this embodiment, by performing data cleaning on the original medical data to obtain target medical data, the quality of the target medical data can be effectively improved, and the repeated original medical data is removed, so that when the target medical data is subsequently used for training, it is not necessary. Re-training the repeated raw medical data can effectively reduce the training time, save time and improve training efficiency.

In this embodiment, the target webpage address is obtained first, and then the webpage corresponding to the target webpage address is crawled by the crawler tool to obtain at least one original medical data, and no manual search is needed, which is beneficial to improving the efficiency of data collection. Finally, data cleaning is performed on at least one original medical data, and at least one target medical data is acquired, so that when the target medical data is used for training, the repeated data is not required to be retrained, thereby effectively reducing training time, saving time, and improving training efficiency. .

In a specific embodiment, as shown in FIG. 3, in step S12, the crawler tool is used to crawl the webpage corresponding to the target webpage address to obtain at least one original medical data, and the original medical data includes a disease characteristic and corresponding at least one symptom. Features include the following steps:

S121: Using a crawler tool, crawling at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, where each of the access addresses corresponds to a webpage.

In this embodiment, the depth-first algorithm can be used to start from the start page, and one link is tracked and tracked. After the line is processed, the next start page is transferred to continue tracking the link. The target webpage address corresponds to a target webpage, and the target webpage includes at least one accessing address linked to the starting page and the at least one starting page, and each accessing address corresponds to a visiting webpage. The crawler tool includes a web page extraction tool and a web page download tool. The webpage extraction tool is a tool for extracting an access address, and step S121 specifically uses a webpage extraction tool to crawl at least one access address linked by the target webpage address. The webpage downloading tool is a tool for downloading a webpage corresponding to an access address.

In this embodiment, the breadth-first algorithm can also be used to continuously crawl a new webpage address from the current page into the message queue to be downloaded, and stop executing the crawler task until the preset stop condition is satisfied. The breadth-first algorithm refers to inserting the link found by the newly downloaded webpage directly into the end of the queue to be crawled, that is, the web crawler first crawls all the webpages in the start page, and then selects one of the links. The webpage continues to crawl all pages linked in this page.

S122: Store at least one access address in a queue of pending messages.

Specifically, each access address crawled in step S121 is stored in the queue to be downloaded according to the chronological order of the crawling, so that when step S123 is performed, the crawling may be based on the webpage address in the message queue to be downloaded. Take data. The message queue to be downloaded processes the access address according to the advanced first-in-first method, so that the crawl access address and the original medical data can be crawled asynchronously based on the access address, which is beneficial to improving the efficiency of obtaining the original medical data.

Specifically, the webpage extraction tool in the crawler tool first grabs all the webpage content in the start page, and then selects at least one access address linked by the startpage, and continues to crawl the webpage of the visitor address link. In this embodiment, the start page is a target webpage address.

S123: The crawler tool is used to perform data extraction on the webpage corresponding to each access address in the message queue to obtain original medical data.

Specifically, the webpage downloading tool automatically downloads all the medical data in the webpage corresponding to the accessing address according to each access address of the message queue to be downloaded. In this embodiment, a plurality of webpage addresses including the original medical data are stored in the message queue to be downloaded, and the webpage downloading tool of the crawler tool sequentially obtains the accessing address from the to-be-downloaded message queue and downloads the webpage corresponding to the accessing address. Raw medical data. Specifically, the crawler tool obtains an access address from the head of the message queue to be downloaded and downloads the webpage corresponding to the access address, stores the downloaded original medical data in the database, and unregisters the corresponding webpage address in the message queue to be downloaded. Repeat the above steps until there is no access address in the message queue to be downloaded to get the original medical data in all web pages crawled by the crawler tool. In this embodiment, the webpage downloading tool in the crawler tool automatically crawls the webpage address including the original medical data from the Internet according to the crawler task set by the user, and does not need manual search, which is beneficial to improving data collection efficiency.

Raw medical data includes, but is not limited to, symptom characteristics and disease characteristics, and may also include a visiting department. In this embodiment, after the original medical data is acquired, the symptom table, the disease table, and the department table are also stored according to the identification fields of the original medical data (ie, the symptoms, the disease, and the visiting department). Then, the data in each table is labeled. For example, A1 (labeled code) represents the first symptom in the symptom database, ie A1 = runny nose, and A2 represents the second symptom in the symptom store, ie A2 = fever, B2 represents The second disease of the disease library is B2 = cold. Finally, each visit record is labeled with the above-mentioned label code, for example (runny nose, fever, cold) = (A1, A2, B2).

In this embodiment, the crawler tool is used to crawl at least one access address linked by the target webpage address according to the breadth-first algorithm or the depth-first algorithm, and the obtained access address is stored in the message queue to be downloaded, and then the crawler is used. The tool downloads the original medical data based on the access address obtained in the message queue to be downloaded, so that the original medical data downloaded by the access address is processed asynchronously, which is beneficial to improving the efficiency of obtaining the original medical data. In this embodiment, obtaining the original medical data asynchronously by using the webpage extraction tool and the webpage downloading tool is beneficial to improving the efficiency of acquiring the original medical data.

As shown in FIG. 4, in step S20, the Apriori algorithm is used to perform correlation analysis on the target medical data, and the degree of medical data relationship is obtained, which specifically includes the following steps:

S21: Acquire at least one first candidate set based on the target medical data, and determine a corresponding first support degree according to the number of occurrences of each first candidate set.

The first candidate set refers to a set generated based on the target medical data in the first cycle of the algorithm. The first support degree refers to the number of times each first candidate set appears in the target medical data. Specifically, the symptom feature and the disease feature in the medical record marked after the labeling code are input into the Apriori algorithm for analysis, and the first candidate set is obtained, and the corresponding first number is determined according to the number of occurrences of each first candidate set. Support. For example, the medical records obtained are as follows: (runny nose, fever, cold) = (A1, A2, B2), (runny nose, fever, headache, cold) = (A1, A2, A3, B2), then obtained The first candidate set is {A1}, {A2}, {A3}, {B2}, then {A1}, {A2}, {A3}, {B2}, the first support set corresponding to the first candidate set They are 2, 2, 1, and 2, respectively. Among them, runny nose, fever, headache, and cold are the target medical data in this embodiment.

S22: Select a first candidate set whose first support degree is greater than or equal to the preset support degree as the first frequent set.

The preset support degree may be preset by the user, or may be the minimum support degree selected by the first support degree generated in each round of the loop as the preset support degree. The first frequent set refers to a set of items corresponding to the first support set and having a first support degree greater than a preset support degree. Specifically, the first candidate set whose first support degree is greater than or equal to the preset support degree is selected as the first frequent set. In the example of step S21, if the preset support degree is 1, the first frequent set is {A1}. , {A2}, {A3}, {B2}; if the preset support is 2, the first frequent set is {A1}, {A2}, {B2}.

S23: Perform iterative processing on the first frequent set and the first candidate set according to the natural connection theorem and the pruning algorithm, and obtain the updated first candidate set, the updated first support degree, and the updated first frequent set until the updated first When a frequent set is an empty set, the medical data relationship is determined based on the first frequent set of the last update.

The updated first candidate set refers to the item set used to generate the updated first frequent set in the Kth iteration. The updated first support refers to the number of times each updated first candidate set appears in the target medical data. The natural connection theorem is the generated N-term set. If there are two N-item sets, when two N-items have N-1 items in the same set, the natural connection can be made. For example, there are two sets of 3 items: {A1, A2, B2} and {A1, A2, A3}. Since these two items are the same, they are naturally connected. They can be joined to generate a set of 4 items {A1, A2, A3, B2}. Another example is two sets of 3 items {A1, A2, B2} and {A1, A4, B1}. These two items are not connectable because they have no two identical elements. In this embodiment, the value of the parameter K is the same as the value of the parameter N.

As in the example of step S21, if the first candidate set is {A1}, {A2}, {A3}, {B2}, the first frequent set is {A1}, {A2}, {A3}, {B2}, then The updated first candidate set obtained according to the natural connection theorem is {A1, A2}, {A1, A3}, {A2, A3}, {A2, B2}, {A3, B2}, which corresponds to the updated first The support is 2, 1, 1, 2, 1.

The pruning algorithm refers to an algorithm that obtains a frequent set by judging whether the support degree is greater than a preset support degree. Specifically, if the preset support degree is 2, according to the pruning algorithm, if the first support degree updated at this time is greater than or equal to the preset support degree, the updated first support set corresponding to the first support level is used as an update. The first frequent set. For example, the updated first candidate set obtained according to the natural connection theorem is {A1, A2}, {A1, A3}, {A2, A3}, {A2, B2}, {A3, B2}, corresponding to the updated The first support degree is 2, 1, 1, 2, 1, according to the pruning algorithm, and the first frequent set updated at this time is {A1, A2}, {A2, B2}.

The iterative processing of the updated first candidate set and the updated first frequent set is continued according to the natural connection theorem and the pruning theorem until the updated first frequent set is an empty set.

The updated first frequent set is an empty set, that is, the updated first support degree is less than the preset support degree, and the first candidate set that is not updated may be used as the updated first frequent set, that is, the updated first frequent set. For an empty set, the iterative processing is aborted at this time.

The confidence of the subset corresponding to the first frequent set of the last update is calculated, and compared with the preset reliability to obtain the final strong association rule, and the support degree corresponding to the strong association rule is taken as the medical data relationship degree. Among them, the Confidence interval of a probability sample is its confidence, which is an interval estimate of a certain overall parameter of this sample, and support is support. In the example of step S21, the first frequent set of the last acquired update is {A1, A2}, {A2, B2}, and based on the first frequent set, their subset is obtained as {A1}, { A2}, {A1, A2}, {B2}, {A2, B2}, the rules obtained are as follows: A1->A2^B2 (indicating symptom A1, symptom A2 and disease B2 can be introduced), A2->A1 ^B2 (indicated by symptom A2, can give symptoms A1 and disease B2), A1^A2->B2 (expressed by symptom A1, A2 can launch disease B2), B2->A1^A2 (represented by disease B2, can be launched Symptoms A1, A2), A2^B2->A1 (indicating symptom A2 and disease B2, symptom A1 can be introduced). Then, according to the formula support(A∪B)/suport(A), the confidence of each rule is obtained separately. In this embodiment, the confidence level of each rule is support (A1, A2, B2) / support (A1) = 1, support (A1, A2, B2) / support (A2) = 1, support (A1, A2, B2) / support (A1, A2) = 1, support (A1, A2, B2) / support (B2) = 1, support (A1, A2, B2) / support (A2, B2) = 1. The confidence level corresponding to each rule is compared with the pre-set reliability, and the rule with greater than or equal to the pre-set reliability is selected as the strong association rule, and the confidence corresponding to the strong association rule is the medical data relationship degree. Among them, the pre-set reliability is pre-customized by the developer.

In this embodiment, the first candidate set is obtained according to the disease feature and the symptom feature, so that the first support degree is determined according to the number of occurrences of each first candidate set, and then the first support degree is greater than or equal to the pre-selection. The first candidate set of the support degree is set as the first frequent set, and the first frequent set and the first candidate set are iteratively processed according to the natural connection theorem and the pruning theorem, and the updated first candidate set and the updated first candidate set are obtained. The first support level and the updated first frequent set, until the updated first frequent set is an empty set, the medical data relationship degree is determined based on the first frequent set of the last update. The updated first frequent set is obtained by the natural connection theorem and the pruning theorem to reduce the amount of calculation and improve the acquisition efficiency of the medical data relationship.

In a specific embodiment, as shown in FIG. 5, in step S30, the E-charts tool is used to perform graph conversion on the medical data relationship degree, and the medical data relationship image is obtained, which specifically includes the following steps:

S31: Acquire a chart configuration request, and the chart configuration request includes a chart ID.

Among them, the chart ID is an identifier that can uniquely identify the chart conversion function corresponding to different chart types stored in the E-charts tool. The chart configuration request is a request by the user to make a relationship image. Specifically, after selecting the relationship image creation, the user displays all the chart types in the chart type configuration interface, and the user can determine the type of the relationship image to be selected through the chart type configuration request, and the operation process is simple and convenient, which is beneficial to improving the user experience.

S32: Obtain a chart conversion function corresponding to the chart ID in the E-charts tool.

Specifically, the chart conversion tool stores conversion functions corresponding to different types of charts, and each conversion function corresponds to a conversion function identifier, and the corresponding conversion function method can be called by the conversion function identifier. In this embodiment, the E-charts tool includes, but is not limited to, a pie chart, a histogram and a line chart, a bar chart, a column-linked pie chart, a line line chart, a scatter scatter chart, a pie pie chart, and a pie2 nested ring. The conversion function method corresponding to the chart type such as map map, parallel parallel coordinate, graph relation graph, and graphLes circle type relationship graph.

S33: Call the chart conversion function to perform chart conversion on the medical data relationship degree, and obtain a medical data relationship image.

Specifically, the chart conversion function in the E-charts tool is called to convert the medical data relationship degree, load the corresponding medical data relationship image, and display the medical data relationship image in the visualization area. In this embodiment, the E-charts tool obtains the medical data relationship degree and updates the relationship image in real time, so that the medical data relation image has the advantages of strong timing and high reliability.

In this embodiment, the chart configuration request is acquired, and the chart configuration request includes a chart ID to obtain a chart conversion function corresponding to the chart ID in the E-charts tool based on the chart ID, and finally, the chart conversion function is invoked to perform the medical data relationship degree. Chart conversion, access to medical data relationship images, so that users can more intuitively see the relationship between medical data, assist with agent analysis and consulting, and improve work efficiency.

It should be understood that the size of the sequence of the steps in the above embodiments does not mean that the order of execution is performed. The order of execution of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.

Example 2

Fig. 6 is a block diagram showing the principle of the medical data relation image acquiring apparatus corresponding to the medical data relation image obtaining method in the first embodiment. As shown in FIG. 6, the medical data relationship image acquisition device includes a target medical data acquisition module 10, a medical data relationship degree acquisition module 20, and a medical data relationship image acquisition module 30. The implementation functions of the target medical data acquisition module 10, the medical data relationship degree acquisition module 20, and the medical data relationship image acquisition module 30 correspond one-to-one with the steps corresponding to the medical data relationship image acquisition method in the embodiment. To avoid redundancy, the implementation The examples are not detailed one by one.

The target medical data obtaining module 10 is configured to acquire at least one target medical data.

The medical data relationship obtaining module 20 is configured to perform correlation analysis on the target medical data by using the Apriori algorithm, and obtain the medical data relationship degree.

The medical data relation image obtaining module 30 is configured to perform chart conversion on the medical data relationship degree by using the E-charts tool, and obtain a medical data relationship image.

Preferably, the target medical data acquisition module 10 includes a target webpage address acquisition unit 11, an original medical data acquisition unit 12, and a target medical data acquisition unit 13.

The target webpage address obtaining unit 11 is configured to obtain a target webpage address.

The original medical data obtaining unit 12 is configured to crawl the webpage corresponding to the target webpage address by using the crawler tool to obtain at least one original medical data.

The target medical data acquiring unit 13 is configured to perform data cleaning on the at least one original medical data to acquire at least one target medical data.

Preferably, the original medical data acquisition unit 12 includes an access address acquisition sub-unit 121, an access address storage sub-unit 122, and an original medical data acquisition sub-unit 123.

The access address obtaining sub-unit 121 is configured to use a crawler tool to crawl at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, where each of the access addresses corresponds to a webpage.

The access address storage sub-unit 122 stores at least one access address in the message queue to be downloaded.

The original medical data acquisition sub-unit 123 uses the crawler tool to perform data extraction on the webpage corresponding to each access address in the download message queue to obtain the original medical data.

Preferably, the medical data relationship degree obtaining module 20 includes a first candidate set and a first support degree obtaining unit 21, a first frequent set obtaining unit 22, and a medical data relationship degree acquiring unit 23.

The first candidate set and the first support obtaining unit 21 are configured to acquire at least one first candidate set based on the target medical data, and determine a corresponding first support according to the number of occurrences of each first candidate set.

The first frequent set obtaining unit 22 is configured to select a first candidate set whose first support degree is greater than or equal to the preset support degree as the first frequent set.

The medical data relationship obtaining unit 23 is configured to perform iterative processing on the first frequent set and the first candidate set according to the natural connection theorem and the pruning algorithm, and obtain the updated first candidate set, the updated first support degree, and the updated first A frequent set, until the updated first frequent set is an empty set, then the medical data relationship is determined based on the first frequent set of the last update.

Preferably, the medical data relation image acquisition module 30 includes a chart configuration request acquisition unit 31, a chart conversion function acquisition unit 32, and a medical data relationship image acquisition unit 33.

The chart configuration request obtaining unit 31 is configured to acquire a chart configuration request, and the chart configuration request includes a chart ID.

The chart conversion function acquisition unit 32 is configured to acquire a chart conversion function corresponding to the chart ID in the E-charts tool.

The medical data relation image obtaining unit 33 is configured to invoke a chart conversion function to perform chart conversion on the medical data relationship degree, and acquire a medical data relationship image.

Example 3

The embodiment provides a computer readable storage medium, where the computer readable storage medium is stored by the processor, and the medical data relationship image acquisition method in Embodiment 1 is implemented to avoid duplication. , no longer repeat them here. Alternatively, when the computer readable instructions are executed by the processor, the functions of the modules/units in the medical data relation image obtaining device in Embodiment 2 are implemented. To avoid repetition, details are not described herein again.

The computer readable storage medium can include any entity or device capable of carrying the computer readable instruction code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, a computer memory, a read only memory (ROM, Read-Only) Memory), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media.

Example 4

FIG. 7 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 7, the terminal device 70 of this embodiment includes a processor 71, a memory 72, and computer readable instructions 73 stored in the memory 72 and operable on the processor 71. When the processor 71 executes the computer readable instructions 73, the steps of the medical data relation image acquisition method in the above-described Embodiment 1 are implemented, such as steps S10 to S30 shown in FIG. Alternatively, when the processor 71 executes the computer readable instructions 73, the functions of the modules/units of the medical data relation image acquiring device in the second embodiment are implemented, for example, the target medical data acquiring module 10 and the medical data relationship acquiring module shown in FIG. 20 and medical data relate to the functionality of image acquisition module 30.

Illustratively, computer readable instructions 73 may be partitioned into one or more modules/units, one or more modules/units being stored in memory 72 and executed by processor 71 to complete the application. The one or more modules/units may be an instruction segment of a series of computer readable instructions 703 capable of performing a particular function for describing the execution of computer readable instructions 73 in the terminal device 70. For example, the computer readable instructions 73 may be divided into a target medical data acquisition module 10, a medical data relationship degree acquisition module 20, and a medical data relationship image acquisition module 30. The specific functions of the modules are as described in Embodiment 2, and are different here. A narrative.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The above-mentioned embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing embodiments. The technical solutions described in the examples are modified or equivalently replaced with some of the technical features; and the modifications or substitutions do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in Within the scope of protection of this application.

Claims (20)

1. A medical data relationship image acquisition method, comprising:

   Obtaining at least one target medical data;

   Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

   The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.
2. The method of acquiring a medical data relationship image according to claim 1, wherein the obtaining the at least one target medical data comprises:

   Get the landing page address;

   Using a crawler tool to crawl the webpage corresponding to the target webpage address to obtain at least one original medical data;

   Performing data cleaning on at least one of the original medical data to acquire at least one target medical data.
3. The medical data relationship image acquisition method according to claim 2, wherein the crawling tool crawls the webpage corresponding to the target webpage address to obtain at least one original medical data, including:

   Using a crawler tool, crawling at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, each of the access addresses corresponding to a webpage;

   Storing at least one of the access addresses in a queue of pending messages;

   And using the crawler tool to perform data extraction on the webpage corresponding to each of the access addresses in the to-be-processed message queue, to obtain the original medical data.
4. The medical data relationship image acquisition method according to claim 1, wherein the Apriori algorithm performs correlation analysis on the target medical data to obtain a medical data relationship degree, including:

   And acquiring, according to the target medical data, at least one first candidate set, and determining a corresponding first support degree according to the number of occurrences of each of the first candidate sets;

   Selecting the first candidate set whose first support degree is greater than or equal to the preset support degree as the first frequent set;

   And the first frequent set and the first candidate set are iteratively processed according to the natural connection theorem and the pruning algorithm, and the updated first candidate set, the updated first support degree, and the updated first frequent set are obtained until the update When the first frequent set is an empty set, the medical data relationship degree is determined based on the first frequent set of the last update.
5. The medical data relationship image acquisition method according to claim 1, wherein the medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image, including:

   Obtaining a chart configuration request; the chart configuration request includes a chart ID;

   Obtaining a chart conversion function corresponding to the chart ID in the E-charts tool;

   The chart conversion function is invoked to perform a chart conversion on the medical data relationship degree, and the medical data relationship image is acquired.
6. A medical data relationship image acquiring device, comprising:

   a target medical data acquisition module, configured to acquire at least one target medical data;

   a medical data relationship obtaining module, configured to perform correlation analysis on the target medical data by using an Apriori algorithm, and obtain a medical data relationship degree;

   The medical data relation image obtaining module is configured to perform chart conversion on the medical data relationship degree by using an E-charts tool to obtain a medical data relationship image.
7. The medical data relationship image acquisition apparatus according to claim 6, wherein the medical data relationship degree acquisition module includes

   a first candidate set and a first support obtaining unit, configured to acquire at least one first candidate set based on the target medical data, and determine a corresponding first support degree according to the number of occurrences of each of the first candidate set;

   a first frequent set obtaining unit, configured to select the first candidate set whose first support degree is greater than or equal to a preset support degree as the first frequent set;

   a medical data relationship obtaining unit, configured to iteratively process the first frequent set and the first candidate set according to a natural connection theorem and a pruning algorithm, to obtain an updated first candidate set, updated first support degree, and The updated first frequent set, until the updated first frequent set is an empty set, then determining the medical data relationship based on the first frequent set of the last update.
8. The medical data relationship image obtaining apparatus according to claim 6, wherein the medical data relation image obtaining module comprises:

   a chart configuration request obtaining unit, configured to acquire a chart configuration request; the chart configuration request includes a chart ID;

   a chart conversion function obtaining unit, configured to acquire a chart conversion function corresponding to the chart ID in the E-charts tool;

   The medical data relation image obtaining unit is configured to invoke the chart conversion function to perform chart conversion on the medical data relationship degree, and acquire the medical data relationship image.
9. The medical data relation image obtaining apparatus according to claim 6, wherein the target medical data acquiring module comprises:

   a target webpage address obtaining unit, configured to obtain a target webpage address;

   The original medical data obtaining unit is configured to crawl the webpage corresponding to the target webpage address by using a crawler tool to obtain at least one original medical data;

   The target medical data acquiring unit is configured to perform data cleaning on the at least one of the original medical data to acquire at least one target medical data.
10. The medical data relation image obtaining apparatus according to claim 6, wherein the original medical data acquiring unit comprises:

    An access address obtaining sub-unit, configured to: crawl the at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, where each of the access addresses corresponds to a webpage;

    An access address storage subunit, configured to store at least one of the access addresses in a queue of pending messages;

    The original medical data acquisition sub-unit is configured to perform data extraction on the webpage corresponding to each of the access addresses in the to-be-processed message queue by using a crawler tool to obtain the original medical data.
11. A terminal device comprising a memory, a processor, and computer readable instructions stored in the memory and operable on the processor, wherein the processor executes the computer readable instructions as follows step:

    Obtaining at least one target medical data;

    Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

    The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.
12. The terminal device according to claim 11, wherein the obtaining the at least one target medical data comprises:

    Get the landing page address;

    Using a crawler tool to crawl the webpage corresponding to the target webpage address to obtain at least one original medical data;

    Performing data cleaning on at least one of the original medical data to acquire at least one target medical data.
13. The terminal device according to claim 12, wherein the crawling tool crawls the webpage corresponding to the target webpage address to obtain at least one original medical data, including:

    Using a crawler tool, crawling at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, each of the access addresses corresponding to a webpage;

    Storing at least one of the access addresses in a queue of pending messages;

    And using the crawler tool to perform data extraction on the webpage corresponding to each of the access addresses in the to-be-processed message queue, to obtain the original medical data.
14. The terminal device according to claim 11, wherein the Apriori algorithm performs correlation analysis on the target medical data to obtain a medical data relationship degree, including:

    And acquiring, according to the target medical data, at least one first candidate set, and determining a corresponding first support degree according to the number of occurrences of each of the first candidate sets;

    Selecting the first candidate set whose first support degree is greater than or equal to the preset support degree as the first frequent set;

    And the first frequent set and the first candidate set are iteratively processed according to the natural connection theorem and the pruning algorithm, and the updated first candidate set, the updated first support degree, and the updated first frequent set are obtained until the update When the first frequent set is an empty set, the medical data relationship degree is determined based on the first frequent set of the last update.
15. The terminal device according to claim 11, wherein the medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image, including:

    Obtaining a chart configuration request; the chart configuration request includes a chart ID;

    Obtaining a chart conversion function corresponding to the chart ID in the E-charts tool;

    The chart conversion function is invoked to perform a chart conversion on the medical data relationship degree, and the medical data relationship image is acquired.
16. A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the following steps:

    Obtaining at least one target medical data;

    Performing correlation analysis on the target medical data by using the Apriori algorithm, and obtaining medical data relationship degree;

    The medical data relationship degree is graphically converted by using an E-charts tool to obtain a medical data relationship image.
17. The computer readable storage medium of claim 16, wherein the obtaining the at least one target medical data comprises:

    Get the landing page address;

    Using a crawler tool to crawl the webpage corresponding to the target webpage address to obtain at least one original medical data;

    Performing data cleaning on at least one of the original medical data to acquire at least one target medical data.
18. The computer readable storage medium according to claim 17, wherein the crawling tool crawls the webpage corresponding to the target webpage address to obtain at least one original medical data, including:

    Using a crawler tool, crawling at least one access address linked by the target webpage address according to a breadth-first algorithm or a depth-first algorithm, each of the access addresses corresponding to a webpage;

    Storing at least one of the access addresses in a queue of pending messages;

    And using the crawler tool to perform data extraction on the webpage corresponding to each of the access addresses in the to-be-processed message queue, to obtain the original medical data.
19. The computer readable storage medium according to claim 16, wherein the Apriori algorithm performs correlation analysis on the target medical data to obtain a medical data relationship degree, including:

    And acquiring, according to the target medical data, at least one first candidate set, and determining a corresponding first support degree according to the number of occurrences of each of the first candidate sets;

    Selecting the first candidate set whose first support degree is greater than or equal to the preset support degree as the first frequent set;

    And the first frequent set and the first candidate set are iteratively processed according to the natural connection theorem and the pruning algorithm, and the updated first candidate set, the updated first support degree, and the updated first frequent set are obtained until the update When the first frequent set is an empty set, the medical data relationship degree is determined based on the first frequent set of the last update.
20. The computer readable storage medium according to claim 16, wherein the graphical conversion of the medical data relationship degree by using an E-charts tool to obtain a medical data relationship image comprises:

    Obtaining a chart configuration request; the chart configuration request includes a chart ID;

    Obtaining a chart conversion function corresponding to the chart ID in the E-charts tool;

    The chart conversion function is invoked to perform a chart conversion on the medical data relationship degree, and the medical data relationship image is acquired.

Images