CN115116572B - Medical data management system and method based on artificial intelligence - Google Patents
Medical data management system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN115116572B CN115116572B CN202211035876.0A CN202211035876A CN115116572B CN 115116572 B CN115116572 B CN 115116572B CN 202211035876 A CN202211035876 A CN 202211035876A CN 115116572 B CN115116572 B CN 115116572B
- Authority
- CN
- China
- Prior art keywords
- information data
- medical information
- medical
- user
- keywords
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a medical data management system and method based on artificial intelligence, and belongs to the technical field of medical information. The method comprises the steps of retrieving out a query word by acquiring a medical information text input by a user, further generating a plurality of medical information data packets, acquiring associated information data of each medical information data packet, and further narrowing the range between the closely associated medical information data packets to obtain interactive use information; then extracting the probability corresponding to each keyword in each medical information data packet through refinement, and continuously refining to obtain a medical information data target; through comparison and verification with historical data, the accuracy and the reliability of medical information data can be greatly improved, more scientific and effective reference and support are provided for medical schemes, and medical errors are reduced; the invention also provides a system which comprises a user using terminal, a medical information data receiving and transmitting module, a medical information data storage module and a medical information data processing module.
Description
Technical Field
The invention relates to the technical field of medical information, in particular to a medical data management system and method based on artificial intelligence.
Background
Wisdom medical treatment english is WIT120 for short, is the special medical noun that has recently emerged, through making the regional medical information platform of healthy archives, utilizes the most advanced internet of things technique, realizes the interdynamic between patient and medical staff, medical institution, medical equipment, reaches the informationization gradually. The technology of the internet of things is applied to the medical field, and limited medical resources can be shared by more people by means of a digital and visual mode. From the development of medical informatization, with the increasingly obvious development trend of the regionalization and the healthcare of medical and health care communities, the real-time tracking and monitoring of the physical sign information are carried out in the family through relevant terminal equipment such as a radio frequency instrument, and the real-time diagnosis and health reminding of a patient or a sub-health patient by a hospital can be realized through an effective internet of things, so that the occurrence and development of the patient are effectively reduced and controlled.
The problems of high medical cost, few channels, low coverage and the like are puzzled to the public due to the imperfection of the domestic public medical management system. In particular, medical problems represented by "a medical system with low efficiency, medical services with poor quality, and current situations of difficult and expensive medical visits" are the main focus of social attention. The problems that large hospitals are full of patients, community hospitals do not ask much fluid, the patient treatment procedure is complicated, and the like are caused by reasons of unsmooth medical information, bipolarization of medical resources, incomplete medical supervision mechanism and the like, and the problems become important factors influencing the social harmony development. How to enable patients to enjoy safe, convenient and high-quality diagnosis and treatment services by using shorter treatment waiting time and paying basic medical expenses, fundamentally solves the problems of difficult and expensive medical treatment and the like, and really achieves the purpose that healthy people become the key point of current research.
Disclosure of Invention
The present invention is directed to a medical data management system and method based on artificial intelligence, so as to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme:
a medical data management system based on artificial intelligence comprises a user use terminal, a medical information data receiving and sending module, a medical information data storage module and a medical information data processing module;
the user using terminal is used for acquiring a medical information text input by a user and sending a predefined instruction for the user to select; the medical information data transceiver module is used for searching for the query words of the medical information text; the medical information data storage module is used for storing various medical information data packets in historical medical data and calling the medical information data packets related to the doubtful words according to the doubtful words; the medical information data processing module is used for obtaining a final medical information data target through data analysis and processing according to the interactive use information among the medical information data packets and the keywords corresponding to each medical information data packet;
the medical information data packet is a treatment report which is effectively treated in a past case, and specifically comprises a sex condition, an age condition, a disease description condition, a treatment cycle condition, a treatment medicine condition and a treatment operation condition; meanwhile, the medical information data packets are also attached with marked disease category and disease characteristic, and the disease characteristic is a keyword corresponding to each medical information data packet;
the output end of the user using terminal is connected with the input end of the medical information data transceiving module; the output end of the medical information data transceiver module is connected with the input end of the medical information data storage module; the output end of the medical information data storage module is connected with the input end of the medical information data processing module;
the medical information text comprises a user-defined input information text and a system feedback information text; the system feedback information text is a keyword with the highest probability of being selected according to the keyword obtained after data processing is carried out on the medical information data processing module; the predefined instruction comprises a manual service instruction and a keyword corresponding to each medical information data packet;
the user-defined input information text comprises disease description, medicine name, body organ or operation name input by the user;
the user using terminal also comprises a user login unit, a user information encryption unit and a user information input unit; the user login unit is used for a user to log in by using a key; the user information encryption unit is used for encrypting the name of the user; the user information input unit is used for a user to perform user-defined input of information texts and selection of predefined instructions.
According to the technical scheme, the medical information data transceiving module is also used for receiving the medical information data target processed by the medical information data processing module and the keywords corresponding to the medical information data packet and sending the keywords to the user terminal; the keywords comprise query words formed by the keywords with the highest probability of being selected.
According to the technical scheme, the medical information data storage module is further used for storing associated information data among various medical information data packets, the associated information data are that when a user observes one medical information data packet in historical data, other medical information data packets are also observed, counting statistics is carried out on all the observed medical information data packets to obtain associated information data, for example, when the user observes the medical information data packet A, according to a certain piece of information of the medical information data packet A, the medical information data packets B, C and D are also observed, and then the associated information data of the medical information data packet A is 4;
the medical information data storage module also comprises a medical data management knowledge base and a medical information data calling unit; the medical data management knowledge base unit is used for storing various information; the medical information data calling unit is used for calling a required medical information data packet;
the output end of the medical information data calling unit is connected with the input end of the medical data management knowledge base unit.
According to the technical scheme, the medical information data processing module further comprises a verification unit, a prediction unit and an information updating unit; the verification unit is used for verifying the matching success rate of the search query words according to historical data; the prediction unit is used for predicting a user demand result to be processed; the information updating unit is used for updating the questioning words, the keywords, the medical information data packet and the matching success rate according to the using process of the user;
the output end of the verification unit is connected with the input end of the prediction unit; the output end of the prediction unit is connected with the input end of the information updating unit.
A medical data management method based on artificial intelligence comprises the following steps:
s1, a user uses a terminal to obtain a medical information text input by the user;
s2, searching for the query words of the acquired medical information text;
s3, retrieving information stored in a database according to the query words, and further generating a medical information data packet;
s4, further acquiring interactive use information among the medical information data packets, and further processing and analyzing to obtain the influence of each medical information data packet according to the interactive use information;
s5, obtaining keywords corresponding to the medical information data packet, further processing and analyzing according to the keywords to obtain the probability of the selected keywords, and further processing according to the probability of the selected keywords to obtain the corresponding trust degree of the medical information data packet;
s6, further processing, analyzing and determining a medical information data target according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet;
s7, setting a threshold value of the number of medical information data targets, recording the threshold value as Q, processing and analyzing according to the number of the medical information data packets processed in the step S3, and if the number of the obtained medical information data packets is more than or equal to Q, determining that the medical information data packets are the required medical information data targets; and if the number of the obtained medical information data packets is less than Q, further analyzing the success rate of searching for the matching of the query words, and further analyzing and processing to obtain the required medical information data target according to the matching success rate.
Further, in step S4, the calculation formula for further processing and analyzing the influence of each medical information data packet is as follows:
wherein, y x And (3) the associated information data representing any medical information data packet x, S (x) represents the influence of any medical information data packet x, and N represents the total number of the medical information data packets x.
Further, in step S5, the specific steps of further processing and analyzing to obtain the selected probability of the keyword are as follows:
s5-1, obtaining keywords corresponding to each medical information data packet, and generating a set of keywords contained in any medical information data packet, and recording the set as { I } 1 ,I 2 ,I 3 ...I j In which I 1 ,I 2 ,I 3 ...I j Represents any one of a plurality of keywords in the medical information data packet x;
s5-2, counting the number of all keywords appearing in all medical information data packets, recording as M, and further counting any keyword I i Number of occurrencesIs recorded as I' i And calculating the probability of selecting any keyword according to a formula as follows:
wherein, p (I) i ) Representing the probability of any keyword being selected.
Further, in step S6, the specific steps of further processing, analyzing and determining the medical information data target are as follows:
s6-1, obtaining the trust level of any medical information data packet x according to the number of all keywords in any medical information data packet, the number of the keywords and the keyword set corresponding to any medical information data packet, wherein the specific calculation formula is as follows:
wherein P (x) represents the trust degree of any medical information data packet, j is the total number of keywords contained in any medical information data packet, i represents the serial number of the keywords contained in any medical information data packet, j represents the serial number of the keywords contained in any medical information data packet, and,Representing the number of combinations of optional j different keywords in the keywords with the number of M to form a group;
s6-2, obtaining a label value of the medical information data packet through calculation according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet, wherein the formula is as follows:
L(x)=S(x)×P(x)
wherein, the influence S (x) of the medical information data packet is the result of the first screening; the trust degree P (x) corresponding to the medical information data packet is the result of the second screening; l (x) is the label value of the medical information data packet;
and S6-3, setting a label value threshold, recording the label value threshold as K, judging whether L (x) is greater than or equal to K, and if L (x) is greater than or equal to K, determining that the medical information data packet with L (x) greater than or equal to K is the determined medical information data target.
Further, the specific steps of finally obtaining the required medical information data target are as follows:
s7-1, setting the number Q of the medical information data targets, and if the number of the medical information data targets obtained in the step S6-3 is larger than or equal to Q, ending the execution operation to obtain the final required medical information data target; if the target number of the medical information data obtained in the step S6-3 is less than Q, continuing to execute the following steps;
s7-2, retrieving associated information data of the medical information data packet obtained when different questioning words are retrieved from the historical database and matching success rate after different questioning words are retrieved, simultaneously obtaining the average value and standard deviation of the associated information data of the medical information data packet, recording the average value as mu and recording the standard deviation as sigma;
s7-3, according to the average value, the standard deviation and the success rate, further obtaining a relation model which takes the number of medical information data packets as independent variables and the matched success rate after retrieval as dependent variables, and the relation model comprises the following steps:
wherein, P Y The matching success rate after any query word Y is retrieved is shown, and n is the number of medical information data packets obtained when any query word Y is retrieved;
s7-4, obtaining the average value of the matching success rate in the historical data, and recording the average value as phi if P is Y If the value is more than or equal to phi, executing the following step S7-5; if P Y If the value is less than phi, executing the following step S7-6;
s7-5, extracting the keywords with the maximum probability of being selected from the medical information data packets with the label values smaller than the threshold value, taking the keywords with the maximum probability as query words, and executing operation from the step S3 until the number of the obtained medical information data targets is larger than or equal to Q, namely, ending the execution operation, and obtaining the finally required medical information data targets;
and S7-6, the system enters a predefined mode, the predefined mode sends a preset instruction to the user using the terminal for the user to select, and the preset instruction comprises a manual service instruction and the keywords in the step S5.
Further, the specific working steps of the predefined mode are as follows:
s7-6-1, obtaining the keywords in the step S5, sorting the keywords in a descending order according to the selected probability of any keyword calculated in the step S5-2, and generating a sample set from the sorted result for a user to select;
and S7-6-2, sequentially selecting by the user according to the sequence of the keywords in the sample set, setting the number of the selected keywords of the user to be at least one, generating a user selection information set by the keywords selected by the user, sending an artificial service instruction in a predefined mode for the user to select after the user selects the keywords, and obtaining a final required medical information data target through artificial service.
Compared with the prior art, the invention has the following beneficial effects: in the medical data management system and method based on artificial intelligence, a query word is retrieved by acquiring a medical information text input by a user, a plurality of medical information data packets are further generated, associated information data of each medical information data packet is acquired, and further, the range is narrowed between closely associated medical information data packets to obtain interactive use information; then extracting the probability corresponding to each keyword in each medical information data packet through refinement, and continuously performing refinement processing to obtain a medical information data target; through comparison and verification with historical data, the accuracy and the reliability of medical information data can be greatly improved, more scientific and effective reference and support are provided for medical schemes, and medical errors are reduced; the invention also provides an artificial intelligence system which comprises a user using terminal, a medical information data receiving and sending module, a medical information data storage module and a medical information data processing module, wherein unmanned management is adopted in the implementation process, the generation, the processing and the distribution of data are realized by artificial intelligence, and meanwhile, the artificial service adopted by the invention depends on an AI big data intelligent simulation artificial mode.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an artificial intelligence based medical data management system of the present invention;
FIG. 2 is a schematic diagram illustrating the steps of a method for managing medical data based on artificial intelligence according to the present invention;
fig. 3 is a flow chart of a medical data management method based on artificial intelligence according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution:
as shown in fig. 1, the medical data management system based on artificial intelligence comprises a user terminal, a medical information data transceiver module, a medical information data storage module and a medical information data processing module;
the user using terminal is used for acquiring a medical information text input by a user and sending a predefined instruction for the user to select; the medical information data transceiver module is used for searching for the query words of the medical information text; the medical information data storage module is used for storing various medical information data packets in historical medical data and calling the medical information data packets related to the doubtful words according to the doubtful words; the medical information data processing module is used for obtaining final medical information through data analysis and processing according to the interactive use information among the medical information data packets and the keywords corresponding to each medical information data packet;
the output end of the user using terminal is connected with the input end of the medical information data transceiving module; the output end of the medical information data transceiving module is connected with the input end of the medical information data storage module; the output end of the medical information data storage module is connected with the input end of the medical information data processing module;
the medical information text comprises a user-defined input information text and a system feedback information text; the system feedback information text is a keyword with the highest probability of being selected according to the keyword obtained after data processing is carried out on the medical information data processing module; the predefined instruction comprises a manual service instruction and a keyword corresponding to each medical information data packet;
the user using terminal also comprises a user login unit, a user information encryption unit and a user information input unit; the user login unit is used for a user to log in by using a key; the user information encryption unit is used for encrypting the name of the user; the user information input unit is used for a user to perform user-defined input of information texts and selection of predefined instructions.
According to the technical scheme, the medical information data transceiving module is also used for receiving the medical information data target processed by the medical information data processing module and the keywords corresponding to the medical information data packet and sending the keywords to the user terminal; the keywords comprise query words formed by the keywords with the highest probability of being selected.
According to the technical scheme, the medical information data storage module is also used for storing associated information data among various medical information data packets, wherein the associated information data is obtained by counting and counting all observed medical information data packets when a user observes one medical information data packet in historical data and observes other medical information data packets;
the medical information data storage module also comprises a medical data management knowledge base and a medical information data calling unit; the medical data management knowledge base unit is used for storing various information; the medical information data calling unit is used for calling a required medical information data packet;
the output end of the medical information data calling unit is connected with the input end of the medical data management knowledge base unit.
According to the technical scheme, the medical information data processing module further comprises a verification unit, a prediction unit and an information updating unit; the verification unit is used for verifying the matching success rate of the search query words according to historical data; the prediction unit is used for predicting a user demand result to be processed; the information updating unit is used for updating the query words, the keywords, the medical information data packets and the matching success rate according to the using process of the user;
the output end of the verification unit is connected with the input end of the prediction unit; the output end of the prediction unit is connected with the input end of the information updating unit.
A medical data management method based on artificial intelligence comprises the following steps and specific procedures, as shown in figures 2 and 3:
s1, a user uses a terminal to obtain a medical information text input by the user;
s2, searching for the query words of the acquired medical information text;
s3, retrieving information stored in a database according to the query words, and further generating a medical information data packet;
s4, further acquiring interactive use information among the medical information data packets, and further processing and analyzing to obtain the influence of each medical information data packet according to the interactive use information;
s5, obtaining keywords corresponding to the medical information data packet, further processing and analyzing according to the keywords to obtain the probability of the selected keywords, and further processing according to the probability of the selected keywords to obtain the corresponding trust degree of the medical information data packet;
s6, further processing, analyzing and determining a medical information data target according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet;
s7, setting a threshold value of the number of medical information data targets, recording the threshold value as Q, processing and analyzing according to the number of the medical information data packets processed in the step S3, and if the number of the obtained medical information data packets is more than or equal to Q, determining that the medical information data packets are the required medical information data targets; and if the number of the obtained medical information data packets is less than Q, further analyzing the success rate of searching for the matching of the query words, and further analyzing and processing to obtain the required medical information data target according to the matching success rate.
Further, in step S4, the calculation formula for further processing and analyzing the influence of each medical information data packet is as follows:
wherein, y x And (3) the associated information data representing any medical information data packet x, S (x) represents the influence of any medical information data packet x, and N represents the total number of the medical information data packets x.
Further, in step S5, the specific steps of further processing and analyzing to obtain the selected probability of the keyword are as follows:
s5-1, obtaining keywords corresponding to each medical information data packet, and generating a set of keywords contained in any medical information data packet, and recording the set as { I 1 ,I 2 ,I 3 ...I j In which I 1 ,I 2 ,I 2 ...I j Represents any one of a plurality of keywords in the medical information data packet x;
s5-2, counting the number of all keywords appearing in all medical information data packets, recording the number as M, and further counting any keyword I i Number of occurrences, noted as I' i And calculating the probability of selecting any keyword according to a formula as follows:
wherein, p (I) i ) Representing the probability of any keyword being selected.
Further, in step S6, the specific steps of further processing, analyzing and determining the medical information data target are as follows:
s6-1, obtaining the trust level of any medical information data packet x according to the number of all keywords in any medical information data packet, the number of the keywords and the keyword set corresponding to any medical information data packet, wherein the specific calculation formula is as follows:
wherein P (x) represents the trust degree of any medical information data packet, j is the total number of keywords contained in any medical information data packet, i represents the serial number of the keywords contained in any medical information data packet, j represents the serial number of the keywords contained in any medical information data packet, and,Representing the number of combinations of j different keywords in the keywords with the number M to form a group;
s6-2, obtaining the label value of the medical information data packet through calculation according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet, wherein the formula is as follows:
L(x)=S(x)×P(x)
wherein, the influence S (x) of the medical information data packet is the result of the first screening; the trust degree P (x) corresponding to the medical information data packet is the result of the second screening; l (x) is the label value of the medical information data packet;
and S6-3, setting a label value threshold, recording the label value threshold as K, judging whether L (x) is greater than or equal to K, and if the L (x) is greater than or equal to K, determining that the medical information data packet with the L (x) greater than or equal to K is the determined medical information data target.
Further, the specific steps for finally obtaining the required medical information data target are as follows:
s7-1, setting the number Q of the medical information data targets, and if the number of the medical information data targets obtained in the step S6-3 is larger than or equal to Q, ending the execution operation to obtain the final required medical information data target; if the target number of the medical information data obtained in the step S6-3 is less than Q, continuing to execute the following steps;
s7-2, retrieving associated information data of the medical information data packet obtained when different query words are retrieved from a historical database and matching success rate after different query words are retrieved, simultaneously obtaining an average value and a standard deviation of the associated information data of the medical information data packet, recording the average value as mu and recording the standard deviation as sigma;
s7-3, according to the average value, the standard deviation and the success rate, further obtaining a relation model which takes the number of medical information data packets as independent variables and the matched success rate after retrieval as dependent variables, and the relation model comprises the following steps:
wherein, P Y The matching success rate after any query word Y is searched is shown, and n is the number of medical information data packets obtained during the search of any query word Y;
s7-4, obtaining the average value of the matching success rate in the historical data, and recording the average value as phi if P is Y If the value is larger than or equal to phi, executing the following step S7-5; if P Y If the value is less than phi, executing the following step S7-6;
s7-5, extracting the keywords with the maximum probability of being selected from the medical information data packets with the label values smaller than the threshold value, taking the keywords with the maximum probability as query words, and executing operation from the step S3 until the number of the obtained medical information data targets is larger than or equal to Q, namely, ending the execution operation, and obtaining the finally required medical information data targets;
and S7-6, the system enters a predefined mode, the predefined mode is used for sending a preset instruction to the user to select by the user, and the preset instruction comprises a manual service instruction and the keywords in the step S5.
Further, the specific working steps of the predefined mode are as follows:
s7-6-1, obtaining the keywords in the step S5, sorting the keywords in a descending order according to the selected probability of any keyword calculated in the step S5-2, and generating a sample set from the sorted result for a user to select;
and S7-6-2, sequentially selecting by the user according to the sequence of the keywords in the sample set, setting the number of the selected keywords of the user to be at least one, generating a user selection information set by the keywords selected by the user, sending an artificial service instruction in a predefined mode for the user to select after the user selection is finished, and obtaining a final required medical information data target through artificial service.
In this embodiment, the user inputs a customized medical information text such as "headache is frightening" on the user terminal;
searching for the interrogative words of headache and aversion to cold according to the medical information text input by the user;
according to the searched query words, the stored information of the data knowledge base is called to obtain medical information data packets A, B, C, D and E, wherein the associated information data of the medical information data packet A is 20, the associated information data of the medical information data packet B is 5, the associated information data of the medical information data packet C is 15, the associated information data of the medical information data packet D is 8, the associated information data of the medical information data packet E is 12, namely y A =20、y B =5、y C =15、y D =8.y E =12.n =60; substituting the data into the following equation:
wherein yx represents the associated information data of any medical information data packet x, S (x) represents the influence of any medical information data packet x, and N represents the total number of medical information data packets x;
the influence corresponding to each medical information data packet is obtained through calculation as follows:
S(A)=0.3333、S(B)=0.0833、S(C)=0.25、S(D)=0.1333、S(E)=0.2;
the method for acquiring the corresponding keywords of the medical information data packet comprises the following steps: aversion to cold, fever, headache, cough; and sequentially marking the keywords as I 1 、I 2 、I 3 、I 4 ;
The keyword generation sets corresponding to each medical information data packet are respectively as follows: a = { I 1 、I 2 、I 3 、I 4 }、B={I 1 、I 2 }、 C={I 2 、I 3 、1 4 }、D={I 2 、I 4 }、E={I 3 And M =12,i 1 =2、I 2 =4、I 3 =3、I 4 =3;
According to the calculation formula:
and calculating the probability of selecting any keyword by using the data: p (I) 1 )=0.1667、P(I 2 )=0.3333、P(I 3 )=0.25、 P(I 4 )=0.25;
According to the calculation formula:
substituting the data to calculate the trust of any medical information data packet:
according to the calculation formula:
L(x)=S(x)×P(x)
and (3) carrying out data calculation to obtain the label value of the medical information data packet: l (a) =0.0485, L (B) =0.0101, L (C) =0.0409, L (D) =0.0242, L (E) =0.05;
setting a label value threshold K =0.03, setting the number of medical information data objects Q =5; in the present embodiment, according to the history data feedback, the number Q =5 of the medical information data objects is an average value of the medical information data packets obtained at the time of history retrieval;
according to the threshold, if the medical information data packets A, C and E which are more than or equal to the threshold K are obtained and the number of the medical information data packets A, C and E is 3 and less than 5, further analyzing whether the retrieved questioning words are accurate or not, specifically as follows:
in the present embodiment, it is preferred that,σ 2 =27.6,n =5, according to the calculation formula:
the success rate of matching the questioning words of headache and aversion to cold is P obtained by substituting data for calculation Y =0.0252;
The average value phi =0.02 of the success rate of matching in the historical data is obtained Y =0.0252>Phi =0.02, then the query word is accurate, and the following steps are further carried out:
extracting the keywords with the maximum probability of being selected from the medical information data packets with the label values smaller than the threshold value, taking the keywords with the maximum probability as query words, starting to perform new screening until the number of the obtained medical information data targets is more than or equal to Q, namely finishing the execution operation, and obtaining the finally required medical information data target;
in this embodiment, the medical information data packets smaller than the threshold K are B and D, and include the keyword I 1 、I 2 、I 4 Probability of keywords being favoredThe largest keyword is "hot", and the keyword is used as a query word to start a new screening.
If the related information data of the medical information data packets A, B, C, D, E retrieved by the embodiment are respectively the related information data
y A =12、y B =8、y C =6、y D =15,y E =9,n =50; substituting the data into the following equation:
wherein, y x Representing the associated information data of any medical information data packet x, S (x) representing the influence of any medical information data packet x, and N representing the total number of the medical information data packets x;
according to the calculation formula:
L(x)=S(x)×P(x);
and (3) carrying out data calculation to obtain the label value of the medical information data packet: l (a) =0.0349, L (B) =0.0194, L (C) =0.0196, L (D) =0.0545, L (E) =0.0450;
according to the threshold K =0.03, the medical information data packets a, D, E greater than or equal to the threshold K are obtained, and the number is 3 and less than 5, and then whether the retrieved questioning words are accurate is further analyzed, specifically as follows:
in the present embodiment of the present invention,σ 2 =25,n =5, according to the calculation formula:
the success rate of matching the questioning words of headache and aversion to cold is P obtained by substituting data for calculation Y =0.0147,P Y If =0.0147 < Φ =0.02, it indicates that the query word is wrong, and the method further includes the following steps:
the system enters a predefined mode;
acquiring the probability of selecting all keywords, sequencing the keywords in a descending order, and generating a sample set from the sequenced results for a user to select;
and simultaneously, after the user selection is finished, sending a manual service instruction in a predefined mode for the user to select, and obtaining a final required medical information data target through manual service.
If the related information data of the medical information data packets A, B, C, D, E retrieved by the embodiment are respectively the related information data
y A =11、y B =13、y C =10、y D =9,y E =7,N=50;
Substituting the data into the following equation:
wherein, y x Representing the associated information data of any medical information data packet x, S (x) representing the influence of any medical information data packet x, and N representing the total number of the medical information data packets x;
according to the calculation formula:
L(x)=S(x)×P(x);
and (3) carrying out data calculation to obtain the label value of the medical information data packet: l (a) =0.0320, L (B) =0.0315, L (C) =0.0327, L (D) =0.0327, L (E) =0.0350;
and according to the threshold value K =0.03, the medical information data packets A, B, C, D and E which are more than or equal to the threshold value K are obtained, and the number is 5 or more, and the medical information data packets which are more than or equal to K are the determined medical information data target, and the execution is finished.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A medical data management method based on artificial intelligence is characterized by comprising the following steps:
s1, a user uses a terminal to obtain a medical information text input by the user;
s2, searching for the query words of the acquired medical information text;
s3, searching the information stored in the database according to the query words, and further generating a medical information data packet;
s4, further acquiring interactive use information among the medical information data packets, and further processing and analyzing to obtain the influence of each medical information data packet according to the interactive use information;
s5, obtaining keywords corresponding to the medical information data packet, further processing and analyzing the keywords according to the keywords to obtain the keyword selection probability, and further processing the keyword selection probability to obtain the corresponding trust degree of the medical information data packet;
s6, further processing, analyzing and determining a medical information data target according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet;
s7, setting a threshold value of the number of medical information data targets, recording the threshold value as Q, processing and analyzing according to the number of the medical information data packets processed in the step S3, and if the number of the obtained medical information data packets is more than or equal to Q, determining that the medical information data packets are the required medical information data targets; and if the number of the obtained medical information data packets is less than Q, further analyzing the success rate of searching for the matching of the query words, and further analyzing and processing to obtain the required medical information data target according to the matching success rate.
2. The method for managing medical data based on artificial intelligence as claimed in claim 1, wherein in step S4, the calculation formula for further processing and analyzing the influence of each medical information data packet is as follows:
wherein, y x And (3) the associated information data representing any medical information data packet x, S (x) represents the influence of any medical information data packet x, and N represents the total number of the medical information data packets x.
3. The artificial intelligence based medical data management method of claim 2, wherein in step S5, the specific steps of further processing and analyzing the selected probability of the keyword are as follows:
s5-1, obtaining keywords corresponding to each medical information data packet, and generating a set of keywords contained in any medical information data packet, and recording the set as { I 1 ,I 2 ,I 3 …I j In which I 1 ,I 2 ,I 3 …I j Represents any one of a plurality of keywords in the medical information data packet x;
s5-2, counting all medical information data packetsThe number of all the keywords appearing is marked as M, and any keyword I is further counted i Number of occurrences, denoted as I' i And calculating the probability of selecting any keyword according to a formula as follows:
wherein, P (I) i ) Representing the probability of any keyword being selected.
4. The artificial intelligence based medical data management method according to claim 3, wherein in step S6, the specific steps of further processing, analyzing and determining the medical information data target are as follows:
s6-1, obtaining the trust level of any medical information data packet x according to the number of all keywords in any medical information data packet, the number of the keywords and the keyword set corresponding to any medical information data packet, wherein the specific calculation formula is as follows:
wherein P (x) represents the trust level of any medical information data packet, j is the total number of keywords contained in any medical information data packet, i represents the keyword serial number contained in any medical information data packet, and,Representing the number of combinations of optional j different keywords in the keywords with the number of M to form a group;
s6-2, obtaining the label value of the medical information data packet through calculation according to the influence corresponding to the medical information data packet and the trust corresponding to the medical information data packet, wherein the formula is as follows:
L(x)=S(x)×P(x)
wherein, the influence S (x) of the medical information data packet is the result of the first screening; the trust level P (x) corresponding to the medical information data packet is the result of the second screening; l (x) is the label value of the medical information data packet;
and S6-3, setting a label value threshold, recording the label value threshold as K, judging whether L (x) is greater than or equal to K, and if L (x) is greater than or equal to K, determining that the medical information data packet with L (x) greater than or equal to K is the determined medical information data target.
5. The artificial intelligence based medical data management method according to claim 4, wherein the specific steps of finally obtaining the required medical information data object are as follows:
s7-1, setting the number Q of the medical information data targets, and if the number of the medical information data targets obtained in the step S6-3 is larger than or equal to Q, ending the execution operation to obtain the final required medical information data target; if the target number of the medical information data obtained in the step S6-3 is less than Q, continuing to execute the following steps;
s7-2, retrieving associated information data of the medical information data packet obtained when different query words are retrieved from a historical database and matching success rate after different query words are retrieved, simultaneously obtaining an average value and a standard deviation of the associated information data of the medical information data packet, recording the average value as mu and recording the standard deviation as sigma;
s7-3, according to the average value, the standard deviation and the success rate, further obtaining a relation model which takes the number of medical information data packets as independent variables and the matched success rate after retrieval as dependent variables, and the relation model comprises the following steps:
wherein, P Y The matching success rate after any query word Y is searched is shown, and n is the number of medical information data packets obtained during the search of any query word Y;
s7-4, obtaining the average value of the matching success rate in the historical data, and recording the average value as phi if P is Y If it is greater than or equal to phi, execution is performedThe following step S7-5; if P Y If the value is less than phi, executing the following step S7-6;
s7-5, extracting the keywords with the maximum probability of being selected from the medical information data packets with the label values smaller than the threshold value, taking the keywords with the maximum probability as query words, and executing operation from the step S3 until the number of the obtained medical information data targets is larger than or equal to Q, namely, ending the execution operation, and obtaining the finally required medical information data targets;
and S7-6, the system enters a predefined mode, the predefined mode is used for sending a preset instruction to the user to select by the user, and the preset instruction comprises a manual service instruction and the keywords in the step S5.
6. The artificial intelligence based medical data management method according to claim 5, wherein the predefined mode comprises the following specific working steps:
s7-6-1, obtaining the keywords in the step S5, sequencing the keywords according to the selection probability of any keyword calculated in the step S5-2 from big to small, and generating a sample set from the sequenced result for the user to select;
and S7-6-2, sequentially selecting by the user according to the sequence of the keywords in the sample set, setting the number of the selected keywords of the user to be at least one, generating a user selection information set by the keywords selected by the user, sending an artificial service instruction in a predefined mode for the user to select after the user selects the keywords, and obtaining a final required medical information data target through artificial service.
7. An artificial intelligence based medical data management system for performing an artificial intelligence based medical data management method according to any one of claims 1-6, characterized by: the system comprises a user using terminal, a medical information data transceiving module, a medical information data storage module and a medical information data processing module;
the user using terminal is used for acquiring a medical information text input by a user and sending a predefined instruction for the user to select; the medical information data transceiver module is used for searching for the query words of the medical information text; the medical information data storage module is used for storing various medical information data packets in historical medical data and calling the medical information data packets related to the doubtful words according to the doubtful words; the medical information data processing module is used for obtaining a final medical information data target through data analysis and processing according to interactive use information among the medical information data packets and keywords corresponding to each medical information data packet;
the output end of the user using terminal is connected with the input end of the medical information data transceiving module; the output end of the medical information data transceiver module is connected with the input end of the medical information data storage module; the output end of the medical information data storage module is connected with the input end of the medical information data processing module;
the medical information text comprises a user-defined input information text and a system feedback information text; the system feedback information text is a keyword with the highest probability of being selected according to the keyword obtained after data processing is carried out on the medical information data processing module; the predefined instruction comprises a manual service instruction and a keyword corresponding to each medical information data packet;
the user using terminal also comprises a user login unit, a user information encryption unit and a user information input unit; the user login unit is used for a user to log in by using a key; the user information encryption unit is used for encrypting the name of the user; the user information input unit is used for a user to perform self-defined information text input and predefined instruction selection.
8. The artificial intelligence based medical data management system of claim 7, wherein: the medical information data receiving and sending module is also used for receiving the medical information data target and the keywords corresponding to the medical information data packet processed by the medical information data processing module and sending the medical information data target and the keywords to the user terminal; the keywords comprise query words formed by the keywords with the maximum probability of being selected.
9. The artificial intelligence based medical data management system of claim 7, wherein: the medical information data storage module is also used for storing associated information data among various medical information data packets, wherein the associated information data is obtained by observing other medical information data packets when a user observes one medical information data packet in historical data and counting all the observed medical information data packets to obtain the associated information data;
the medical information data storage module also comprises a medical data management knowledge base and a medical information data calling unit; the medical data management knowledge base unit is used for storing various information; the medical information data calling unit is used for calling a required medical information data packet;
the output end of the medical information data calling unit is connected with the input end of the medical data management knowledge base unit.
10. The artificial intelligence based medical data management system of claim 7, wherein: the medical information data processing module also comprises a verification unit, a prediction unit and an information updating unit; the verification unit is used for verifying the matching success rate of the search query words according to historical data; the prediction unit is used for predicting a user demand result to be processed; the information updating unit is used for updating the query words, the keywords, the medical information data packets and the matching success rate according to the using process of the user;
the output end of the verification unit is connected with the input end of the prediction unit; the output end of the prediction unit is connected with the input end of the information updating unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211035876.0A CN115116572B (en) | 2022-08-27 | 2022-08-27 | Medical data management system and method based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211035876.0A CN115116572B (en) | 2022-08-27 | 2022-08-27 | Medical data management system and method based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115116572A CN115116572A (en) | 2022-09-27 |
CN115116572B true CN115116572B (en) | 2022-11-25 |
Family
ID=83335561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211035876.0A Active CN115116572B (en) | 2022-08-27 | 2022-08-27 | Medical data management system and method based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115116572B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111223533A (en) * | 2019-12-24 | 2020-06-02 | 深圳市联影医疗数据服务有限公司 | Medical data retrieval method and system |
CN112687402A (en) * | 2020-12-31 | 2021-04-20 | 招明香 | Intelligent medical internet big data processing method based on artificial intelligence and intelligent cloud service platform |
CN114334070A (en) * | 2022-01-05 | 2022-04-12 | 上海良方健康科技有限公司 | Auxiliary prescription system based on medical big data |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111708874B (en) * | 2020-08-24 | 2020-11-13 | 湖南大学 | Man-machine interaction question-answering method and system based on intelligent complex intention recognition |
US11322251B2 (en) * | 2020-10-07 | 2022-05-03 | National Guard Health Affairs | Hospital healthcare provider monitoring and verifyng device and system for patient care condition |
-
2022
- 2022-08-27 CN CN202211035876.0A patent/CN115116572B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111223533A (en) * | 2019-12-24 | 2020-06-02 | 深圳市联影医疗数据服务有限公司 | Medical data retrieval method and system |
CN112687402A (en) * | 2020-12-31 | 2021-04-20 | 招明香 | Intelligent medical internet big data processing method based on artificial intelligence and intelligent cloud service platform |
CN114334070A (en) * | 2022-01-05 | 2022-04-12 | 上海良方健康科技有限公司 | Auxiliary prescription system based on medical big data |
Also Published As
Publication number | Publication date |
---|---|
CN115116572A (en) | 2022-09-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Diagnosis and analysis of diabetic retinopathy based on electronic health records | |
WO2021179630A1 (en) | Complications risk prediction system, method, apparatus, and device, and medium | |
WO2023178971A1 (en) | Internet registration method, apparatus and device for seeking medical advice, and storage medium | |
CN112667799B (en) | Medical question-answering system construction method based on language model and entity matching | |
CN113724815B (en) | Information pushing method and device based on decision grouping model | |
CN111415760B (en) | Doctor recommendation method, doctor recommendation system, computer equipment and storage medium | |
CN113948168A (en) | Medical data evaluation practical application system and medical data evaluation practical application method | |
CN115116572B (en) | Medical data management system and method based on artificial intelligence | |
CN117542540A (en) | Infectious disease risk prediction method, infectious disease risk prediction device, electronic equipment and storage medium | |
CN110610766A (en) | Apparatus and storage medium for deriving probability of disease based on symptom feature weight | |
CN115525192A (en) | User-oriented quotation charging method and device, computer equipment and storage medium | |
CN114610748A (en) | Safe, rapid, accurate and effective medical disease data management system based on artificial intelligence and application | |
Jia et al. | Oncogpt: A medical conversational model tailored with oncology domain expertise on a large language model meta-ai (llama) | |
CN114822830B (en) | Inquiry interaction method and related device, electronic equipment and storage medium | |
CN113035346B (en) | Disease category assessment device and method based on medical knowledge graph | |
CN113744828B (en) | Medical record recommendation method, device, equipment and storage medium | |
Ilias et al. | A medical decision support system for the differential diagnosis based on medical information text mining | |
Cui et al. | Using Electronic Medical Records and Clinical Notes to Predict the Outcome of Opioid Treatment Program | |
González et al. | A recommendation system for electronic health records in the context of the HOPE project | |
WO2023133678A1 (en) | Method for predicting chemical reaction | |
CN112017064A (en) | Insurance application suggestion evaluation method and device suitable for assisted reproductive insurance | |
Farruggia et al. | A novel web service for mammography images indexing | |
CN114420242A (en) | Medical auxiliary information display method, system, equipment and medium based on voice input | |
Buntoro et al. | Text Mining in Healthcare for Disease Classification using Machine Learning Algorithm | |
Zhang et al. | Combining Reverse Temporal Attention Mechanism and Dynamic Similarity Analysis for Disease Prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |