CN112259226A

CN112259226A - Intelligent medical condition monitoring method and system based on big data and medical cloud platform

Info

Publication number: CN112259226A
Application number: CN202011150250.5A
Authority: CN
Inventors: 周玉娟
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-04-19
Filing date: 2020-04-19
Publication date: 2021-01-22
Also published as: CN111540421B; CN111540421A; CN112259225A

Abstract

The embodiment of the disclosure provides a smart medical condition monitoring method and system based on big data and a medical cloud platform. Therefore, the big data behavior characteristics of the medical information recommendation list of the patient user can be effectively mined and refined, so that the illness state of the patient user is monitored in a targeted manner, and subsequent further information recommendation is facilitated.

Description

Intelligent medical condition monitoring method and system based on big data and medical cloud platform

Technical Field

The disclosure relates to the technical field of big data and intelligent medical treatment, in particular to a method and a system for monitoring the condition of an illness of intelligent medical treatment based on big data and a medical cloud platform.

Background

With the rapid development of intelligent medical treatment and internet technology, information recommendation based on intelligent medical treatment can help a patient user to more specifically search information related to the intention of the patient user. The inventor of the application finds that for each patient user, the medical case history situation of the patient user may arouse the requirement of the patient user on medical information search, and particularly due to the advantages of rapid development of the internet, privacy, convenience and the like, the internet intelligent medical treatment is gradually becoming an efficient channel for the patient user to obtain medical recommendation information.

When a patient user receives medical recommendation information, a series of user behaviors are usually generated, the user behaviors may reflect behavior activities of the patient user for the condition of the patient's condition in detail, and how to effectively mine and refine big data of the user behaviors is performed, so that the condition of the patient user is monitored in a targeted manner, and subsequent further information recommendation is facilitated, which is a technical problem to be solved in the field.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, an object of the present disclosure is to provide a method and a system for monitoring an illness state of smart medical treatment based on big data, and a medical cloud platform, which can effectively mine and refine big data behavior characteristics of a medical information recommendation list of a patient user, so as to monitor an illness state of the patient user in a targeted manner, and facilitate subsequent further information recommendation.

In a first aspect, the present disclosure provides a big data-based intelligent medical condition monitoring method applied to a big data medical cloud platform in communication connection with a plurality of intelligent medical service terminals, the method including:

acquiring a medical information recommendation list with browsing time length exceeding preset time length of the intelligent medical service terminal, and extracting big data behavior characteristics of the medical information recommendation list, wherein the medical information recommendation list is an information list recommended by the intelligent medical service terminal after browsing corresponding medical record information and performing intention search on a target, and the corresponding medical record information comprises medical record information of a patient user of the intelligent medical service terminal and associated medical record information associated with the medical record information;

tracking and identifying each browsing behavior node in the big data behavior characteristics to obtain a tracking and identifying result, wherein the tracking and identifying result comprises disease type association characteristics of each browsing behavior node in the big data behavior characteristics and association degrees corresponding to each browsing behavior node in a disease text range of the corresponding medical record information, and each browsing behavior node corresponds to a browsing behavior record;

and generating a medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal according to the tracking identification result, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt.

In a possible implementation manner of the first aspect, the step of extracting big data behavior features of the medical information recommendation list includes:

extracting matching key information records in the medical information recommendation list according to a preset browsing behavior matching rule sequence and extracting matching feature vectors in the matching key information records;

acquiring a behavior parameter set and a content parameter set corresponding to each matched feature vector, wherein the content parameter set comprises content item information and content duration information, and the content duration information is used for representing time sequence information in a behavior parameter identification process;

acquiring a browsing target positioning sequence corresponding to the medical information recommendation list according to the content parameter set, wherein the browsing target positioning sequence is a browsing target positioning sequence of a current first recommendation information unit and a second recommendation information unit in the medical information recommendation list, and the second recommendation information unit is an auxiliary information recommendation unit of the first recommendation information unit;

comparing the parameter serial number of each behavior parameter in the behavior parameter set with the browsing target positioning sequence to obtain a comparison result, wherein the comparison result indicates that the behavior parameter is located in the first recommendation information unit or the second recommendation information unit;

and extracting big data behavior characteristics of the medical information recommendation list according to the comparison result.

In a possible implementation manner of the first aspect, the step of extracting big data behavior features of the medical information recommendation list according to the comparison result includes:

constructing a target behavior parameter set to be synthesized according to the behavior parameter set;

selecting corresponding target feature expression information from the content parameter set according to the behavior parameter set, and acquiring behavior parameters in the first recommendation information unit and the second recommendation information unit from the target behavior parameter set;

when the behavior parameters are located in a current first recommendation information unit, determining corresponding first behavior parameters to be synthesized in a behavior parameter set according to the positions of the behavior parameters, determining corresponding second behavior parameters to be synthesized in the content parameter set, synthesizing a parameter vector of the first behavior parameters to be synthesized in the behavior parameter set and a parameter vector of the second behavior parameters to be synthesized in the content parameter set to obtain a first synthesized parameter vector, and then updating the parameter vector of the behavior parameters in the target behavior parameter set to be the first synthesized parameter vector;

when the behavior parameters are located in a current second recommendation information unit, determining corresponding first behavior parameters to be synthesized and corresponding third behavior parameters to be synthesized in the behavior parameter set according to the positions of the behavior parameters, synthesizing parameter vectors of the first behavior parameters to be synthesized in the behavior parameter set and parameter vectors of the third behavior parameters to be synthesized in the target feature expression information to obtain second synthesized parameter vectors, and then updating the parameter vectors of the behavior parameters in the target behavior parameter set to be the second synthesized parameter vectors;

and extracting the characteristic information of the behavior parameter updated to the first synthetic parameter vector or the second synthetic parameter vector, and summarizing to obtain the big data behavior characteristic of the medical information recommendation list.

In a possible implementation manner of the first aspect, the tracking and identifying each browsing behavior node in the big data behavior feature to obtain a tracking and identifying result includes:

tracking and identifying each browsing behavior node in the big data behavior characteristics to respectively obtain at least one tracking track record queue;

extracting behavior persistence characteristics and behavior flow characteristics of the browsing behavior nodes on the at least one trace record queue, wherein the behavior flow characteristics are used for describing behavior change trends in the trace record queue;

and obtaining the disease type association characteristics of the browsing behavior nodes and the association degrees corresponding to the browsing behavior nodes within a disease text range according to the behavior persistence characteristics and the behavior flow direction characteristics of the browsing behavior nodes.

In a possible implementation manner of the first aspect, the step of obtaining a disease type associated feature of the browsing behavior node and an association degree corresponding to the browsing behavior node within a disease text range according to the behavior persistence feature and the behavior flow direction feature of the browsing behavior node includes:

respectively carrying out nearest neighbor classification calculation on the behavior persistence characteristics and the behavior flow direction characteristics of the browsing behavior nodes to obtain a first nearest neighbor classification result;

based on the nearest neighbor classification result matched with the behavior persistence feature in the first nearest neighbor classification result, positioning in the nearest neighbor classification result of a preset disease type associated feature library to obtain a first positioning result matched with the behavior persistence feature;

based on the nearest neighbor classification result matched with the behavior flow direction feature in the first nearest neighbor classification result, positioning in the nearest neighbor classification result of the preset disease type associated feature library to obtain a second positioning result matched with the behavior flow direction feature;

acquiring the same positioning result in the first positioning result and the second positioning result, taking the same positioning result as a primary positioning result, calculating the position difference between each positioning result included in the primary positioning result and the browsing behavior node, and synthesizing the positioning result included in the primary positioning result according to the calculated position difference to obtain a target positioning result;

acquiring a disease type associated feature node of each positioning result in the target positioning result, and respectively performing behavior persistence feature extraction and behavior flow direction feature extraction on each acquired disease type associated feature node;

for each disease type associated feature node, respectively performing nearest neighbor classification calculation on the behavior persistence feature and the behavior flow direction feature of the disease type associated feature node to obtain a nearest neighbor classification result of the disease type associated feature node;

and acquiring the node position of the disease type associated feature node in the positioning result, and associating the nearest neighbor classification result of the disease type associated feature node based on the identification information of the positioning result and the node position of the disease type associated feature node to obtain the disease type associated feature of the browsing behavior node and the association degree corresponding to the browsing behavior node.

In a possible implementation manner of the first aspect, the step of generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to the tracking identification result, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt includes:

aiming at the disease type correlation characteristics of each browsing behavior node in the tracking identification result, inputting the disease type correlation characteristics into a medical condition behavior monitoring model corresponding to a corresponding browsing behavior record, extracting monitoring characteristic vectors of a plurality of different monitoring object units of the medical condition behavior monitoring model, and combining the monitoring characteristic vectors of the plurality of different monitoring object units to generate the monitoring characteristic vectors of the disease type correlation characteristics;

calculating the confidence degree that each feature vector part in the monitoring feature vectors of the disease type associated features is an offset feature vector part according to the association degree corresponding to each browsing behavior node, and calculating the offset label type of each feature vector part when each feature vector part is the offset feature vector part, wherein the offset feature vector part is used for indicating that the feature vector part and the feature vector corresponding to the disease text range of the corresponding medical record information have reverse features, and the offset label type is used for indicating the medical information type corresponding to the feature vector part when the feature vector part is the offset feature vector part;

and generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to the offset label type of each feature vector part when the feature vector part is the offset feature vector part, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt.

In a possible implementation manner of the first aspect, offset functions corresponding to intervals with different degrees of association are preconfigured in the big data medical cloud platform, and the larger the offset function is, the more obvious the situation of representing reverse features is;

the step of calculating the confidence degree that each feature vector part in the monitoring feature vectors of the disease type associated features is an offset feature vector part according to the association degree corresponding to each browsing behavior node, and the offset label type of each feature vector part when the feature vector part is the offset feature vector part, includes:

determining an offset function of each browsing behavior node according to the association degree interval where the association degree corresponding to each browsing behavior node is located;

calculating the confidence coefficient that each feature vector part in the monitoring feature vectors of the disease type associated features is the offset feature vector part according to the offset function of each browsing behavior node, wherein the confidence coefficient is obtained according to the product of the matrix output value of each feature vector part in the monitoring feature vectors and the offset function;

and determining the characteristic vector part with the confidence coefficient higher than the preset confidence coefficient threshold value as an offset characteristic vector part, and determining the offset label type of each offset characteristic vector part according to the offset label matched with the offset direction and the offset quantity of each offset characteristic vector part.

In a possible implementation manner of the first aspect, the step of generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to an offset tag type of each feature vector part when the feature vector part is an offset feature vector part includes:

and taking the offset label type of each characteristic vector part as a medical illness state behavior monitoring item when the characteristic vector part is the offset characteristic vector part, and taking each medical illness state behavior monitoring item as a medical illness state behavior monitoring result corresponding to a patient user of the intelligent medical service terminal.

In a possible implementation manner of the first aspect, the method further includes:

and recording the medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal generated each time into a medical record disease behavior monitoring database included in the corresponding medical record information.

In a second aspect, the disclosed embodiment further provides a big data-based intelligent medical condition monitoring device applied to a big data medical cloud platform in communication connection with a plurality of intelligent medical service terminals, where the device includes:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring a medical information recommendation list of which the browsing time length of the intelligent medical service terminal exceeds a preset time length and extracting big data behavior characteristics of the medical information recommendation list, the medical information recommendation list is an information list recommended by the intelligent medical service terminal after the intelligent medical service terminal browses corresponding medical record information and then performs intention search on a target, and the corresponding medical record information comprises medical record information of a patient user of the intelligent medical service terminal and associated medical record information associated with the medical record information;

the tracking identification module is used for tracking and identifying each browsing behavior node in the big data behavior characteristics to obtain a tracking identification result, the tracking identification result comprises the disease type associated characteristics of each browsing behavior node in the big data behavior characteristics and the association degree corresponding to each browsing behavior node in the disease text range of the corresponding medical record information, and each browsing behavior node corresponds to a browsing behavior record;

and the generating module is used for generating a medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal according to the tracking identification result, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt.

In a third aspect, an embodiment of the present disclosure further provides a smart medical condition monitoring system based on big data, where the smart medical condition monitoring system based on big data includes a big data medical cloud platform and a plurality of smart medical service terminals communicatively connected to the big data medical cloud platform;

the big data medical cloud platform is used for acquiring a medical information recommendation list of which the browsing time of the intelligent medical service terminal exceeds a preset time, and extracting big data behavior characteristics of the medical information recommendation list, wherein the medical information recommendation list is an information list recommended by the intelligent medical service terminal after the intelligent medical service terminal browses corresponding medical record information and then performs intention search on a target, and the corresponding medical record information comprises medical record information of a patient user of the intelligent medical service terminal and associated medical record information associated with the medical record information;

the big data medical cloud platform is used for tracking and identifying each browsing behavior node in the big data behavior characteristics to obtain a tracking and identifying result, the tracking and identifying result comprises disease type associated characteristics of each browsing behavior node in the big data behavior characteristics and an association degree corresponding to each browsing behavior node in a disease text range of the corresponding medical record information, and each browsing behavior node corresponds to a browsing behavior record;

the big data medical cloud platform is used for generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to the tracking identification result, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt.

In a fourth aspect, an embodiment of the present disclosure further provides a big data medical cloud platform, where the big data medical cloud platform includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected by a bus system, the network interface is used for being communicatively connected to at least one smart medical service terminal, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to execute the big data-based smart medical condition monitoring method in the first aspect or any one of possible designs in the first aspect.

In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having instructions stored therein, which when executed, cause a computer to perform the big data based intelligent medical condition monitoring method according to the first aspect or any one of the possible designs of the first aspect.

Based on any one of the above aspects, the medical information recommendation list with the browsing time length exceeding the preset time length is obtained, the big data behavior characteristics of the medical information recommendation list are extracted, each browsing behavior node in the big data behavior characteristics is tracked and identified to obtain a tracking identification result, a medical illness state behavior monitoring result corresponding to a patient user of the intelligent medical service terminal is generated according to the tracking identification result, and the medical illness state behavior monitoring result is pushed to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt. Therefore, the big data behavior characteristics of the medical information recommendation list of the patient user can be effectively mined and refined, so that the illness state of the patient user is monitored in a targeted manner, and subsequent further information recommendation is facilitated.

Drawings

To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present disclosure and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings may be obtained from the drawings without inventive effort.

Fig. 1 is a schematic view of an application scenario of an intelligent medical condition monitoring system based on big data according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart illustrating a method for intelligent medical condition monitoring based on big data according to an embodiment of the present disclosure;

FIG. 3 is a functional block diagram of an intelligent medical condition monitoring device based on big data according to an embodiment of the present disclosure;

fig. 4 is a block diagram illustrating a structure of a big data medical cloud platform for implementing the big data-based intelligent medical condition monitoring method according to the embodiment of the present disclosure.

Detailed Description

The present disclosure is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the device embodiments or the system embodiments.

FIG. 1 is an interactive schematic diagram of a big data based intelligent medical condition monitoring system 10 according to an embodiment of the present disclosure. The big data based intelligent medical condition monitoring system 10 may include a big data medical cloud platform 100 and an intelligent medical service terminal 200 communicatively connected to the big data medical cloud platform 100. The big data based intelligent medical condition monitoring system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the big data based intelligent medical condition monitoring system 10 may include only one of the components shown in fig. 1 or may include other components.

In this embodiment, the smart medical services terminal 200 may include a mobile device, a tablet computer, a laptop computer, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home devices may include control devices of smart electrical devices, smart monitoring devices, smart televisions, smart cameras, and the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant, a gaming device, and the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like.

In this embodiment, the internet of things cloud big data medical cloud platform 100 and the smart medical service terminal 200 in the big data based smart medical condition monitoring system 10 may cooperatively perform the big data based smart medical condition monitoring method described in the following method embodiment, and the detailed description of the following method embodiment may be referred to in the steps of executing the big data medical cloud platform 100 and the smart medical service terminal 200.

To solve the technical problem in the background art, fig. 2 is a schematic flow chart of a big data based intelligent medical condition monitoring method according to an embodiment of the present disclosure, which can be executed by the big data medical cloud platform 100 shown in fig. 1, and the big data based intelligent medical condition monitoring method is described in detail below.

Step S110, acquiring a medical information recommendation list whose browsing duration exceeds a preset duration from the smart medical service terminal 200, and extracting big data behavior characteristics of the medical information recommendation list.

And step S120, tracking and identifying each browsing behavior node in the big data behavior characteristics to obtain a tracking and identifying result.

Step S130, generating a medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal 200 according to the tracking identification result, and pushing the medical condition behavior monitoring result to the medical staff terminal corresponding to the intelligent medical service terminal 200 for monitoring information prompt.

In this embodiment, the medical information recommendation list may specifically be an information list recommended by the intelligent medical service terminal 200 after browsing corresponding medical record information and then intending to search for a target, and the corresponding medical record information may include medical record information of a patient user of the intelligent medical service terminal 200 and associated medical record information associated with the medical record information. The related medical record information related to the medical record information may refer to medical record information generated by a patient user of the medical record information at other related medical institutions.

In this embodiment, the medical record may be a record of the medical activities of the patient user, such as examination, diagnosis, treatment, etc., of the occurrence, development, and outcome of the disease of the patient user by the relevant medical staff during the medical treatment. For example, the medical records may be written in a prescribed format and requirement by summarizing, sorting, and comprehensively analyzing the collected data, and the medical records may be recorded in the big data medical cloud platform 100 by medical staff, and a patient user may access the big data medical cloud platform 100 through a medical service terminal to view medical records at any time.

In the process of viewing medical cases, a patient user may have various information search intentions, information search is performed based on a related intention search target, at this time, user behavior big data related to the patient user can be obtained, a user behavior big data sample in which behavior frequency is arranged is formed according to the user behavior big data of the related intention search target, and a medical information recommendation list for the patient user can be generated by performing information mining.

In this embodiment, the tracking identification result may include a disease type association characteristic of each browsing behavior node and an association degree corresponding to each browsing behavior node in the big data behavior characteristics within the disease text range of the corresponding medical record information, where each browsing behavior node corresponds to one browsing behavior record. For example, the disease text range may refer to a text range corresponding to a disease category selected in medical record information, and the browsing behavior record may refer to a record generated each time a browsing behavior is initiated.

Based on the above steps, in this embodiment, a medical information recommendation list with a browsing duration exceeding a preset duration is obtained by the smart medical service terminal 200, big data behavior characteristics of the medical information recommendation list are extracted, then, each browsing behavior node in the big data behavior characteristics is tracked and identified to obtain a tracking identification result, then, a medical condition behavior monitoring result corresponding to a patient user of the smart medical service terminal 200 is generated according to the tracking identification result, and the medical condition behavior monitoring result is pushed to a medical staff terminal corresponding to the smart medical service terminal 200 for monitoring information prompt. Therefore, the big data behavior characteristics of the medical information recommendation list of the patient user can be effectively mined and refined, so that the illness state of the patient user is monitored in a targeted manner, and subsequent further information recommendation is facilitated.

In a possible implementation manner, regarding to step S110, in the process of obtaining the medical information recommendation list whose browsing duration of the intelligent medical service terminal 200 exceeds the preset duration, the following exemplary sub-steps may be specifically implemented, which are described in detail below.

And the substep S111, obtaining the user behavior big data of the related intention search target browsed by the intelligent medical service terminal 200 after accessing the medical record, and forming a user behavior big data sample in a mode of arrangement according to the behavior frequency according to the user behavior big data of the related intention search target.

And a substep S112, processing the user behavior big data sample into a plurality of user behavior big data sub-samples of a query intention decision tree which is divided by related intention search targets according to different query intents in advance, calculating query word frequency characteristics of a plurality of query words contained in each user behavior big data sub-sample, and taking the query word frequency characteristics as the query intention characteristics of the corresponding user behavior big data sub-sample.

And a substep S113, taking the query intention characteristics as the query intention characteristics of the user behavior requirements mapped by the corresponding user behavior big data subsample, generating the query intention characteristics of each user behavior requirement, and generating the information recommendation thermodynamic diagram of the intelligent medical service terminal 200 according to the query intention characteristics of each user behavior requirement.

In sub-step S114, a medical information recommendation list of the intelligent medical service terminal 200 is generated based on the information recommendation thermodynamic diagram.

The patient user may be in various information searching intentions in the process of viewing medical cases, information searching is carried out on the basis of the related intention searching target, at the moment, the user behavior big data related to the patient user can be obtained, and a user behavior big data sample in which the behavior frequency is arranged is formed according to the user behavior big data of the related intention searching target.

The action frequency may refer to the number of times of repetition of the search action generated by the patient user, or the duration, and may be used to indicate the attention degree of the patient user for a certain search target content.

The query term may refer to a series of keywords, such as input or clicked keywords, generated by the patient user based on a certain search target content.

Therefore, the large data of the user behaviors of the target can be effectively mined and extracted based on the related intentions of the patient user, and medical information recommendation can be provided for the patient user more specifically.

In one possible implementation manner, regarding step S112, considering that there may be many query intentions mixed in the big data sample of the user behavior, step S112 may be specifically implemented by the following exemplary sub-steps for facilitating the accurate recommendation, which will be described in detail below.

(1) And presetting a query intention decision tree divided according to different query intentions.

(2) And respectively processing the user behavior big data samples according to each query intention decision tree divided according to different query intentions to correspondingly obtain a plurality of intention decision object sequences.

(3) One of the plurality of intended decision object sequences is selected as a first decision object sequence, and a main decision object of the first decision object sequence is identified and used as a reference main decision object.

(4) And for other second intention decision object sequences except the first decision object sequence, respectively setting main decision objects of each second intention decision object sequence, and calculating item interaction information of a decision intention related item corresponding to any one main decision object in the main decision objects of each second intention decision object sequence and a decision intention related item corresponding to each reference main decision object of the first decision object sequence.

The item interaction information may refer to information generated by information interaction between items related to decision intentions, such as information generated in the process of transferring from one item to another item.

(5) Any one main decision object is configured to be a reference main decision object which enables the project interaction information to be closest to the main decision object of the first decision object sequence, the main decision object of each second intention decision object sequence in the rest intention decision object sequences is configured to be a corresponding reference main decision object, the rest intention decision object sequences are respectively reconfigured and distributed according to the first decision object sequence according to the configuration result, and a plurality of configured intention decision object sequences are obtained by combining the configuration result with the first decision object sequence.

(6) And calculating the behavior interaction information and the behavior frequency of each decision object sequence in the plurality of configured intention decision object sequences.

(7) And dividing the user behavior big data samples according to the behavior interaction information and the behavior frequency of each decision object sequence in the configured plurality of intention decision object sequences to obtain a plurality of user behavior big data sub-samples.

In a possible implementation manner, still referring to step S112, in the process of calculating the query word frequency characteristics of the plurality of query words included in each user behavior big data sub-sample, the following exemplary sub-steps can be specifically implemented, which are described in detail below.

(8) And calculating the repetition degree of a plurality of query words contained in each user behavior big data sub-sample to the corresponding user behavior big data sub-sample to obtain corresponding word frequency reversal frequency information.

In this embodiment, term frequency-reversal frequency information (TF-IDF) may be used to indicate the repetition degree of the query term for each corresponding user behavior big data subsample. In detail, the importance of the query term is increased in proportion to the number of times the query term appears in the corresponding big data subsample of the user behavior, so that the importance of the query term can be used as a measure or rating of the degree of correlation between the big data subsample of the user behavior and the query of the user.

(8) And extracting a characteristic vector from the word frequency reversal frequency to obtain the query word frequency characteristics of a plurality of query words contained in each user behavior big data subsample.

In one possible implementation, step S113 may be specifically implemented by the following exemplary sub-steps, which are described in detail below.

(1) And obtaining the query intention hotspot distribution of each user behavior demand output in each query intention decision tree according to the query intention characteristics of each user behavior demand, and dividing the query intention hotspot distribution to obtain a plurality of query intention hotspot units.

(2) And performing intention mining processing on the plurality of query intention hotspot units according to the intention mining script corresponding to each query intention decision tree to obtain the intention mining results corresponding to the plurality of query intention hotspot units.

In this embodiment, the intent mining result may include an intent test confidence of the query intent hotspot unit under the corresponding query intent decision tree.

(3) And determining a graph connection relationship between the query intent hotspot units in each query intent decision tree according to the respective intent mining results corresponding to the query intent hotspot units, and generating an information recommendation thermodynamic diagram of the intelligent medical service terminal 200 according to the determined graph connection relationship between the query intent hotspot units in each query intent decision tree.

In a possible implementation manner, still referring to step S110, in the process of obtaining the big data behavior feature of the medical information recommendation list, the following exemplary sub-steps may be implemented in detail, which will be described in detail below.

And a substep S115, extracting matching key information records in the medical information recommendation list and extracting matching feature vectors in the matching key information records according to a preset browsing behavior matching rule sequence.

And a substep S116, acquiring a behavior parameter set and a content parameter set corresponding to each matched feature vector, wherein the content parameter set comprises content item information and content duration information, and the content duration information is used for representing time sequence information in the behavior parameter identification process.

And a substep S117, obtaining a browsing target positioning sequence corresponding to the medical information recommendation list according to the content parameter set, wherein the browsing target positioning sequence is a browsing target positioning sequence of a current first recommendation information unit and a current second recommendation information unit in the medical information recommendation list, and the second recommendation information unit is an auxiliary information recommendation unit of the first recommendation information unit.

And a substep S118, comparing the parameter serial number of each behavior parameter in the behavior parameter set with the browsing target positioning sequence to obtain a comparison result, wherein the comparison result indicates that the behavior parameter is located in the first recommendation information unit or the second recommendation information unit.

And a substep S119, extracting big data behavior characteristics of the medical information recommendation list according to the comparison result.

For example, in one possible example, the present embodiment may construct a target behavior parameter set to be synthesized according to the behavior parameter set, then select corresponding target feature expression information from the content parameter set according to the behavior parameter set, and obtain behavior parameters located in the first recommendation information unit and the second recommendation information unit from the target behavior parameter set.

For example, when the behavior parameter is located in the current first recommendation information unit, a corresponding first behavior parameter to be synthesized is determined in the behavior parameter set according to the position of the behavior parameter, a corresponding second behavior parameter to be synthesized is determined in the content parameter set, a parameter vector of the first behavior parameter to be synthesized in the behavior parameter set and a parameter vector of the second behavior parameter to be synthesized in the content parameter set are synthesized to obtain a first synthesized parameter vector, and then the parameter vector of the behavior parameter in the target behavior parameter set is updated to be the first synthesized parameter vector.

For another example, when the behavior parameter is located in the current second recommendation information unit, a corresponding first behavior parameter to be synthesized is determined in the behavior parameter set according to the position of the behavior parameter, a corresponding third behavior parameter to be synthesized is determined in the target feature expression information, a parameter vector of the first behavior parameter to be synthesized in the behavior parameter set and a parameter vector of the third behavior parameter to be synthesized in the target feature expression information are synthesized to obtain a second synthesized parameter vector, and then the parameter vector of the behavior parameter in the target behavior parameter set is updated to be the second synthesized parameter vector.

Therefore, the characteristic information of the behavior parameter updated to the first synthetic parameter vector or the second synthetic parameter vector can be extracted and summarized to obtain the big data behavior characteristic of the medical information recommendation list.

In a possible implementation manner, still referring to step S110, in the process of performing tracking identification on each browsing behavior node in the big data behavior feature to obtain a tracking identification result, the following exemplary sub-steps may be specifically implemented, which is described in detail below.

And a substep S111, tracking and identifying each browsing behavior node in the big data behavior characteristics to respectively obtain at least one tracking track record queue.

And a substep S112, extracting behavior persistence characteristics and behavior flow characteristics of the browsing behavior nodes on at least one trace record queue, wherein the behavior flow characteristics are used for describing behavior change trends in the trace record queue.

And a substep S113, obtaining disease type association characteristics of the browsing behavior nodes and association degrees corresponding to the browsing behavior nodes in the disease text range according to the behavior persistence characteristics and the behavior flow direction characteristics of the browsing behavior nodes.

For example, in sub-step S113, it can be embodied by the following exemplary sub-steps, which are described in detail below.

(1) And respectively carrying out nearest neighbor classification calculation on the behavior persistence characteristics and the behavior flow direction characteristics of the browsing behavior nodes to obtain a first nearest neighbor classification result.

(2) And positioning in the nearest neighbor classification result of the preset disease type associated feature library based on the nearest neighbor classification result matched with the behavior persistence feature in the first nearest neighbor classification result to obtain a first positioning result matched with the behavior persistence feature.

(3) And positioning in the nearest neighbor classification result of the preset disease type associated feature library based on the nearest neighbor classification result matched with the behavior flow direction feature in the first nearest neighbor classification result to obtain a second positioning result matched with the behavior flow direction feature.

(4) And acquiring the same positioning result in the first positioning result and the second positioning result, taking the same positioning result as a primary positioning result, calculating the position difference between each positioning result included in the primary positioning result and the browsing behavior node, and synthesizing the positioning result included in the primary positioning result according to the calculated position difference to obtain a target positioning result.

(5) And acquiring a disease type associated feature node of each positioning result in the target positioning result, and respectively performing behavior persistence feature extraction and behavior flow direction feature extraction on each acquired disease type associated feature node.

(6) And for each disease type associated feature node, respectively carrying out nearest neighbor classification calculation on the behavior persistence feature and the behavior flow direction feature of the disease type associated feature node to obtain a nearest neighbor classification result of the disease type associated feature node.

(7) And acquiring the node position of the disease type associated feature node in the positioning result, and associating the nearest neighbor classification result of the disease type associated feature node based on the identification information of the positioning result and the node position of the disease type associated feature node to obtain the disease type associated feature of the browsing behavior node and the association degree corresponding to the browsing behavior node.

In one possible implementation, step S130 may be implemented by the following exemplary sub-steps, which are described in detail below.

And the substep S131 is to input the disease type correlation characteristics of each browsing behavior node in the tracking and identifying result into the medical condition behavior monitoring model corresponding to the corresponding browsing behavior record, extract the monitoring characteristic vectors of a plurality of different monitoring object units of the medical condition behavior monitoring model, and combine the monitoring characteristic vectors of the plurality of different monitoring object units to generate the monitoring characteristic vector of the disease type correlation characteristics.

And a substep S132 of calculating the confidence degree that each feature vector part in the monitoring feature vectors of the disease type associated features is the offset feature vector part according to the association degree corresponding to each browsing behavior node, and the offset label type of each feature vector part when the feature vector part is the offset feature vector part.

In this embodiment, the offset feature vector part is used to indicate that the feature vector part and the feature vector corresponding to the disease text range of the corresponding medical record information have a reverse feature, and the offset tag type is used to indicate the medical information type corresponding to the feature vector part having a reverse feature when the feature vector part is the offset feature vector part.

For example, offset functions corresponding to different relevance intervals may be configured in advance in the big data medical cloud platform 100, and the larger the offset function is, the more obvious the reverse characteristic situation is.

Therefore, the offset function of each browsing behavior node can be determined according to the association degree interval where the association degree corresponding to each browsing behavior node is located, and then the confidence degree that each feature vector part in the monitoring feature vector of the disease type association features is the offset feature vector part is calculated according to the offset function of each browsing behavior node.

As one possible example, the confidence level may be obtained by multiplying the matrix output value of each feature vector portion in the monitored feature vector by the offset function.

Then, the feature vector parts with the confidence degrees higher than the preset confidence degree threshold value can be determined as offset feature vector parts, and the offset tag type of each offset feature vector part is determined according to the offset tags matched with the offset direction and the offset quantity of each offset feature vector part.

And a substep S133, generating a medical condition behavior monitoring result corresponding to the patient user of the smart medical service terminal 200 according to the offset tag type of each feature vector part when the feature vector part is the offset feature vector part, and pushing the medical condition behavior monitoring result to the medical staff terminal corresponding to the smart medical service terminal 200 for monitoring information prompt.

For example, when each feature vector part is an offset feature vector part, the offset tag type of the feature vector part may be used as a medical condition behavior monitoring item, and each medical condition behavior monitoring item may be used as a medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal 200.

On the basis, in this embodiment, in order to facilitate subsequent data tracing, the big-data medical cloud platform 100 may further record the medical condition behavior monitoring result corresponding to the patient user of the smart medical service terminal 200 generated each time into a medical record disease behavior monitoring database included in the corresponding medical record information.

Fig. 3 is a schematic diagram of functional modules of a smart medical condition monitoring apparatus 300 based on big data according to an embodiment of the present disclosure, in this embodiment, the smart medical condition monitoring apparatus 300 based on big data may be divided into functional modules according to an embodiment of a method executed by the big data medical cloud platform 100, that is, the following functional modules corresponding to the smart medical condition monitoring apparatus 300 based on big data may be used to execute each embodiment of the method executed by the big data medical cloud platform 100. The big data based intelligent medical condition monitoring apparatus 300 may include an obtaining module 310, a tracking and identifying module 320, and a generating module 330, wherein the functions of the functional modules of the big data based intelligent medical condition monitoring apparatus 300 are described in detail below.

The obtaining module 310 is configured to obtain a medical information recommendation list of which the browsing time of the smart medical service terminal 200 exceeds a preset time, and extract big data behavior characteristics of the medical information recommendation list, where the medical information recommendation list is an information list recommended by the smart medical service terminal 200 after browsing corresponding medical record information and then performing an intention search on a target, and the corresponding medical record information includes medical record information of a patient user of the smart medical service terminal 200 and associated medical record information associated with the medical record information. The obtaining module 310 may be configured to perform the step S110, and the detailed implementation of the obtaining module 310 may refer to the detailed description of the step S110.

The tracking and identifying module 320 is configured to track and identify each browsing behavior node in the big data behavior feature to obtain a tracking and identifying result, where the tracking and identifying result includes a disease type association feature of each browsing behavior node in the big data behavior feature and an association degree corresponding to each browsing behavior node in a disease text range of corresponding medical record information, and each browsing behavior node corresponds to one browsing behavior record. The tracking identification module 320 may be configured to perform the step S120, and for a detailed implementation of the tracking identification module 320, reference may be made to the detailed description of the step S120.

The generating module 330 is configured to generate a medical condition behavior monitoring result corresponding to the patient user of the smart medical service terminal 200 according to the tracking identification result, and push the medical condition behavior monitoring result to a medical staff terminal corresponding to the smart medical service terminal 200 for monitoring information prompt. The generating module 330 may be configured to execute the step S130, and the detailed implementation of the generating module 330 may refer to the detailed description of the step S130.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the obtaining module 310 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the processing element of the apparatus calls and executes the functions of the obtaining module 310. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).

Fig. 4 shows a hardware structure diagram of a big data medical cloud platform 100 for implementing the above control device according to an embodiment of the present disclosure, and as shown in fig. 4, the big data medical cloud platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, the at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120 (for example, the obtaining module 310, the tracking identification module 320, and the generating module 330 included in the big-data-based smart medical condition monitoring apparatus 300 shown in fig. 3), so that the processor 110 may execute the big-data-based smart medical condition monitoring method according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected via the bus 130, and the processor 110 may be configured to control the transceiving action of the transceiver 140, so as to transceive data with the smart medical service terminal 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned various method embodiments executed by the big data medical cloud platform 100, which implement principles and technical effects similar to each other, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 4, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus 130 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus 130 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

In addition, the embodiment of the present disclosure also provides a readable storage medium, in which a computer executing instruction is stored, and when a processor executes the computer executing instruction, the above intelligent medical condition monitoring method based on big data is implemented.

The readable storage medium described above may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.

Claims

1. A big data-based intelligent medical condition monitoring method is applied to a big data medical cloud platform in communication connection with a plurality of intelligent medical service terminals, and comprises the following steps:

generating a medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal according to the tracking identification result, and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt;

recording medical condition behavior monitoring results corresponding to the patient user of the intelligent medical service terminal generated each time into a medical record disease behavior monitoring database included in the corresponding medical record information;

the step of obtaining the medical information recommendation list with the browsing time length of the intelligent medical service terminal exceeding the preset time length comprises the following steps:

acquiring user behavior big data of a related intention search target browsed by the intelligent medical service terminal after accessing a medical record, and forming a user behavior big data sample in a mode of arrangement according to behavior frequency according to the user behavior big data of the related intention search target;

processing the user behavior big data sample into a plurality of user behavior big data sub-samples of a query intention decision tree which is divided by the related intention search target according to different query intentions in advance, calculating query word frequency characteristics of a plurality of query words contained in each user behavior big data sub-sample, and taking the query word frequency characteristics as the query intention characteristics of the corresponding user behavior big data sub-sample;

taking the query intention characteristics as query intention characteristics of user behavior requirements mapped by corresponding user behavior big data subsamples, generating the query intention characteristics of each user behavior requirement, and generating an information recommendation thermodynamic diagram of the intelligent medical service terminal according to the query intention characteristics of each user behavior requirement;

and generating a medical information recommendation list of the intelligent medical service terminal according to the information recommendation thermodynamic diagram.

2. The intelligent big-data-based medical condition monitoring method according to claim 1, wherein the step of extracting big-data behavior features of the medical information recommendation list comprises:

3. The intelligent medical condition monitoring method based on big data as claimed in claim 2, wherein the step of extracting big data behavior features of the medical information recommendation list according to the comparison result comprises:

4. The intelligent medical condition monitoring method based on big data as claimed in claim 1, wherein the step of tracking and identifying each browsing behavior node in the big data behavior feature to obtain a tracking and identifying result comprises:

5. The intelligent medical condition monitoring method based on big data as claimed in claim 4, wherein the step of obtaining the disease type association feature and the association degree corresponding to the browsing behavior node within the disease text range according to the behavior persistence feature and the behavior flow direction feature of the browsing behavior node comprises:

6. The intelligent medical condition monitoring method based on big data according to any one of claims 1-5, wherein the step of generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to the tracking and identifying result and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt includes:

7. The intelligent medical condition monitoring method based on big data as claimed in claim 6, wherein the big data medical cloud platform is pre-configured with offset functions corresponding to different relevance intervals, and the larger the offset function is, the more obvious the reverse characteristic condition is;

8. The intelligent medical condition monitoring method based on big data of claim 7, wherein the step of generating the medical condition behavior monitoring result corresponding to the patient user of the intelligent medical service terminal according to the offset tag type of each feature vector part when the feature vector part is the offset feature vector part comprises:

9. The intelligent medical condition monitoring system based on big data is characterized by comprising a big data medical cloud platform and a plurality of intelligent medical service terminals in communication connection with the big data medical cloud platform;

the big data medical cloud platform is used for generating a medical condition behavior monitoring result corresponding to a patient user of the intelligent medical service terminal according to the tracking identification result and pushing the medical condition behavior monitoring result to a medical staff terminal corresponding to the intelligent medical service terminal for monitoring information prompt;

the big data medical cloud platform is used for recording medical condition behavior monitoring results generated each time and corresponding to the patient user of the intelligent medical service terminal into a medical record disease behavior monitoring database included in the corresponding medical record information;

the big data medical treatment cloud platform obtains the mode that wisdom medical service terminal browses the medical information recommendation list that duration exceeded and predetermine duration includes:

10. A big data medical cloud platform, comprising a processor, a machine-readable storage medium, and a network interface, wherein the machine-readable storage medium, the network interface, and the processor are connected via a bus system, the network interface is configured to be communicatively connected to at least one smart medical service terminal, the machine-readable storage medium is configured to store a program, instructions, or codes, and the processor is configured to execute the program, instructions, or codes in the machine-readable storage medium to perform the big data-based smart medical condition monitoring method according to any one of claims 1 to 9.