CN112885460A - Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium - Google Patents

Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium Download PDF

Info

Publication number
CN112885460A
CN112885460A CN202110184623.9A CN202110184623A CN112885460A CN 112885460 A CN112885460 A CN 112885460A CN 202110184623 A CN202110184623 A CN 202110184623A CN 112885460 A CN112885460 A CN 112885460A
Authority
CN
China
Prior art keywords
information
cold
case
standard
tuple
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.)
Pending
Application number
CN202110184623.9A
Other languages
Chinese (zh)
Inventor
严冬松
任书恒
武建华
谢勇君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinan University
Original Assignee
Jinan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jinan University filed Critical Jinan University
Priority to CN202110184623.9A priority Critical patent/CN112885460A/en
Publication of CN112885460A publication Critical patent/CN112885460A/en
Pending legal-status Critical Current

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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/237—Lexical tools
    • G06F40/247—Thesauruses; Synonyms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • 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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a case reasoning-based cold syndrome type judging method, a computer device and a computer readable storage medium, wherein the method comprises the following steps: acquiring cold case information; judging whether the cold case information is effective or not, if so, carrying out tuple classification processing on the cold case information to obtain all information tuples corresponding to the cold case information; calculating the similarity of each information tuple and the corresponding standard information tuple in the standard case by adopting a weighted Euclidean distance similarity algorithm; carrying out weighted summation on the similarity corresponding to all the information tuples to obtain the membership degree of the standard case; and confirming the cold syndrome result corresponding to the cold case information according to the membership degree. The computer apparatus includes a controller for implementing the above method when executing a computer program stored in a memory. The computer-readable storage medium has stored thereon a computer program which, when executed by a controller, implements the above-described method. The invention can effectively provide assistance for intelligent traditional Chinese medicine diagnosis.

Description

Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium
Technical Field
The invention relates to the technical field of health monitoring, in particular to a cold syndrome type judging method, a computer device applying the cold syndrome type judging method and a computer readable storage medium applying the cold syndrome type judging method.
Background
The common cold is a common and frequent disease caused by acute upper respiratory tract viral infection by pathogenic wind or virus, and is clinically manifested as nasal obstruction, sneezing, watery nasal discharge, fever, cough, headache and the like. In traditional Chinese medicine, cold syndromes are classified into wind-cold type cold, wind-heat type cold, summer-heat and damp type cold, influenza (influenza) and other syndromes. The different cold syndromes are different from each other in the symptoms of cold, tongue condition and pulse condition.
At present, in the field of cold syndrome judgment, most of the cold syndrome judgment depends on manual judgment, and professional traditional Chinese medical doctors carry out comprehensive treatment by using 'eight principles of four diagnosis' on the basis of syndrome differentiation according to symptoms, signs, tongue condition and pulse condition of patients and the like. This method requires a professional physician to make the diagnosis, which requires a lot of time and labor.
Based on the consideration, the simulated traditional Chinese medicine physician accurately diagnoses the cold on line, effectively provides auxiliary support for intelligent traditional Chinese medicine decision diagnosis, and has very high value and significance.
Disclosure of Invention
The first purpose of the invention is to provide a cold syndrome type judging method based on case-based reasoning, which can effectively provide auxiliary support for intelligent Chinese medicine decision diagnosis.
A second object of the present invention is to provide a computer device that can effectively provide auxiliary support for intelligent chinese medical decision diagnosis.
It is a third object of the present invention to provide a computer readable storage medium that can effectively provide auxiliary support for intelligent TCM decision diagnosis.
In order to achieve the first object, the method for evaluating cold syndrome type based on case-based reasoning provided by the invention comprises the following steps: acquiring cold case information; judging whether the cold case information is effective or not, if so, carrying out tuple classification processing on the cold case information to obtain all information tuples corresponding to the cold case information; calculating the similarity of each information tuple and a standard information tuple corresponding to a standard case in a standard case library by adopting a weighted Euclidean distance similarity algorithm; carrying out weighted summation on the similarity corresponding to all the information tuples to obtain the membership of the cold case information corresponding to all the standard cases; and confirming the cold syndrome result corresponding to the cold case information according to the membership degree.
According to the scheme, the cold syndrome type evaluation method carries out tuple classification on the cold case information, and calculates the similarity between each information tuple and the corresponding standard information tuple in the standard case, so that the membership degree of the standard case is obtained, and the cold syndrome type result corresponding to the cold case information is finally determined, so that auxiliary support can be effectively provided for intelligent traditional Chinese medicine decision diagnosis.
In a further scheme, after the step of confirming the cold syndrome corresponding to the cold case information according to the membership degree, the method further comprises the following steps: and judging whether the cold syndrome result is reliable or not, if so, judging whether a case with the same information as the cold case exists in the standard case library, and if not, adding the cold case information and the cold syndrome result to the standard case library.
Therefore, when the result of judging the cold syndrome is correct, whether the case with the same information as the cold case exists in the standard disease case library or not is judged, and if the case with the same information does not exist in the standard disease case library, the standard case in the standard disease case library is expanded by adding the cold case, so that the accuracy of judging the cold syndrome is improved.
In a further scheme, after the step of confirming the cold syndrome corresponding to the cold case information according to the membership degree, the method further comprises the following steps: and acquiring the judgment accuracy of the information of the cold cases in the preset time period, and adjusting the standard cases in the standard case library according to the judgment accuracy.
In a further aspect, the evaluation accuracy is obtained by the following formula: and alpha is the number of input cases in the first preset time period with correct judgment/the number of input cases in the first preset time period is multiplied by 100%.
Therefore, the accuracy of the current algorithm can be determined by calculating the judgment accuracy of all standard cold case information in the preset time period in the standard library so as to adjust the standard cases.
In a further scheme, the step of adjusting the standard cases in the standard case library according to the judgment accuracy comprises the following steps: judging whether the judging accuracy rate meets the expectation, if so, obtaining the matching rate and the correct matching rate of the current standard case; and if the product of the matching rate and the correct matching rate is smaller than a preset threshold value, deleting the current standard case from the standard library.
In a further embodiment, the matching rate of the current standard case is obtained by the following formula: beta is equal to the matching times of the current standard case in the second preset time period/all the matching times of the cold syndrome types of the current standard case in the second preset time period multiplied by 100 percent; the correct matching rate of the current standard case is obtained by the following formula: and gamma is the number of times that the current standard case in the second preset time period is judged to be correct/the matching number of times of the current standard case in the second preset time period is multiplied by 100%.
Therefore, the matching rate and the correct matching rate of the current standard case are obtained through calculation, and the cold cases with lower product of the matching rate and the correct matching rate in the standard library are eliminated based on the jungle rule, so that the matching efficiency of the judgment algorithm is improved.
In a further aspect, the step of obtaining cold case information includes: and if the acquired cold case information is natural language information, performing word segmentation processing and synonym replacement processing on the natural language information.
Therefore, considering that data input by a user are mostly natural language, and have a certain difference with professional Chinese medicine word description, the judgment of a case is not facilitated, and therefore, the natural language information is subjected to word segmentation processing and synonym replacement processing and is converted into a standard cold information term, so that the system can conveniently carry out recognition and judgment.
In a further aspect, the step of determining whether the cold case information is valid includes: and if the cold case information comprises the related information of at least one tuple, the cold case information is considered to be effective.
Therefore, in order to reduce unnecessary calculation, the cold syndrome type evaluation processing is further performed when the cold case information is valid. When judging whether the cold case information is effective or not, if the cold case information contains the related information of at least one tuple, the cold case information is considered to be effective, and further processing can be carried out.
In order to achieve the second objective of the present invention, the present invention provides a computer device including a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the steps of the cold syndrome type evaluation method.
In order to achieve the third object of the present invention, the present invention provides a computer readable storage medium, on which a computer program is stored, the computer program, when being executed by a controller, implementing the steps of the cold syndrome type evaluation method described above.
Drawings
FIG. 1 is a flowchart of an embodiment of a cold syndrome evaluation method of the present invention.
FIG. 2 is a flowchart illustrating the steps of adjusting the standard cases in the standard case library according to the evaluation accuracy in the method for evaluating cold syndrome according to the present invention.
The invention is further explained with reference to the drawings and the embodiments.
Detailed Description
The cold syndrome type evaluation method based on case-based reasoning is applied to an application program of an intelligent terminal and is used for carrying out cold syndrome type evaluation according to input cold case information. The intelligent terminal includes: desktop computer, cell-phone, intelligent terminal such as panel computer. The invention also provides a computer device which comprises a controller, wherein the controller is used for realizing the steps of the cold syndrome type judging method when executing the computer program stored in the memory. The invention also provides a computer readable storage medium, on which a computer program is stored, wherein the computer program realizes the steps of the cold syndrome type judging method when being executed by the controller.
The embodiment of the cold syndrome evaluation method comprises the following steps:
the case reasoning-based cold syndrome type evaluation method is applied to an application program of an intelligent terminal and is used for carrying out cold syndrome type evaluation according to input cold case information.
As shown in fig. 1, when the method for evaluating cold syndrome based on case-based reasoning works, step S1 is first executed to obtain information of cold cases. When the user needs to judge the syndrome type of the cold case, the information of the cold case needs to be input, and the user can input the information through an information input interface of the intelligent terminal.
The cold case information input by the user may be in standard terms or in natural language. In this embodiment, the step of obtaining the information of the cold case includes: and if the acquired cold case information is natural language information, performing word segmentation processing and synonym replacement processing on the natural language information. Considering that data input by a user is mostly natural language, and has a certain difference with professional Chinese medicine word description, the judgment of a case is not facilitated, therefore, word segmentation processing and synonym replacement processing are carried out on natural language information, and the natural language information is converted into standard cold information terms, so that the system can carry out recognition judgment. The word segmentation processing and the synonym replacement processing for the natural language information are well known to those skilled in the art and will not be described herein. In the present embodiment, when the word segmentation processing is performed on the natural language information, the description of the symptoms of the cold, tongue manifestation, pulse manifestation, and the like involved in the word segmentation processing is removed by irrelevant information, for example, information irrelevant to the symptoms, such as name, sex, and the like. When the word is segmented, the terms in the input information are segmented according to the symptom terms of inspection, smell, inquiry, cutting and the like in the traditional Chinese medicine. When the synonym is replaced, the abnormal expression in the input information is replaced by the common traditional Chinese medicine expression in the standard disease case library, for example, chilliness is replaced by aversion to cold, throat itching is replaced by throat itching, belly pulling is replaced by diarrhea and the like.
After the cold case information is acquired, step S2 is executed to determine whether the cold case information is valid. In order to reduce unnecessary calculation and error input, the cold syndrome type evaluation processing is further carried out when the cold case information is effective. In this embodiment, the step of determining whether the cold case information is valid includes: and if the cold case information comprises the related information of at least one tuple, the cold case information is considered to be effective. If there is information related to at least one information tuple in the cold case information, it is considered that there is a description related to the cold symptom in the cold case information, and further determination processing is required, and therefore, it is confirmed that the cold case information is valid. The information tuples comprise hope information tuples, smell information tuples, question information tuples and tangent information tuples, each information tuple is correspondingly provided with respective related description of cold symptoms, and the information tuples can be set according to cold symptom terms in traditional Chinese medicine.
If it is confirmed that the cold case information is invalid, it is considered that no further determination processing is necessary for the cold case information, and the process returns to step S1 to continue to acquire the cold case information. If the cold case information is confirmed to be valid, step S3 is executed to perform tuple classification processing on the cold case information to obtain all information tuples corresponding to the cold case information. The information of the cold case comprises the related information of at least one information tuple in the hope information tuple, the smell information tuple, the question information tuple and the contact information tuple, and in order to analyze the cold symptom more accurately, the information of the cold case needs to be subjected to tuple classification processing, and the information of the cold case comprising the related information of the information tuples is confirmed. For example, the information of the cold case information after word segmentation and synonym replacement is as follows: nasal obstruction, pharyngalgia, cough, dry throat, chilly and heavy sensation, hoarseness, thin and white tongue coating and floating and tense pulse, and after tuple classification, the thin and white tongue coating is classified into inspection information tuples; classifying hoarseness into an audible information tuple; classifying nasal obstruction, pharyngalgia, cough, dry throat, and aversion to cold into inquiry information tuple; the pulse is classified into groups of pulse-wise and pulse-wise information.
In addition, the descriptions of the cold information degree involved in the information tuple are all descriptions in the Chinese medicine language, and most descriptions in the Chinese medicine language are fuzzy quantity, namely, so-called qualitative variable. For example, it often manifests as "suffering" or "not suffering, not suffering", coughing, not coughing, chills, slight aversion to wind, little sweating, and the like. The system needs to convert the qualitative variable into a quantitative variable, and the obtained quantitative value is the weight of the cold information (i.e. the element of the information tuple) and is used for calculating the subsequent similarity. For the transformation of variables, the system will follow the cold information degree quantization table:
information degree of cold Quantized values
Has no or no disease 0
Micro, somewhat, light and few 0.3
General, moderate, and sometimes 0.7
Severe, severe and profuse 1.0
After all information tuples corresponding to the cold case information are obtained, step S4 is executed, and the similarity between each information tuple and the standard information tuple corresponding to the standard case in the standard case library is calculated by using a weighted euclidean distance similarity algorithm. The weighted euclidean distance similarity algorithm is well known to those skilled in the art and will not be described herein. In this embodiment, the method for calculating the similarity between each information tuple and the corresponding standard information tuple in the standard case is as follows:
Figure BDA0002942549310000061
wherein, in formula (1): lsimRepresenting the similarity of the prospect information tuple in the input case and the prospect information tuple in the standard case, LsRepresenting the expected information tuple in the standard case, LtRepresenting expected information tuples in the input case, h representing ordinal number of elements in the expected information tuples in the input case, n representing total number of the expected information tuple elements in the input case, lhWeight, l, representing the element of the prospect tupleshValues, l, representing the h-th transformed quantitative element of the expected information tuple in the standard casethRepresenting the values of the h-th transformed quantitative elements of the expected information tuples in the input case. In formula (2): ssimRepresenting the similarity of the audible information tuple in the input case and the audible information tuple in the standard case, SsRepresenting a tuple of audible information in a standard case, StRepresenting the tuple of the WeChat information in the input case, h representing the ordinal number of the elements in the tuple of WeChat information in the input case, n representing the total number of the elements in the tuple of WeChat information in the input case, shWeight, s, representing an element of an audible information tupleshValues, s, representing the h-th transformed quantitative elements of the audible information tuples in the standard casethRepresenting the values of the h-th transformed quantitative elements of the tuple of smell information in the input case. q. q.ssimRepresenting the similarity of the query information tuple in the input case and the query information tuple in the standard case, QsRepresenting a tuple of intermediate information, Q, of a standard casetRepresenting the query information tuple in the input case, h representing the ordinal number of the elements in the query information tuple in the input case, n representing the total number of the query information tuple elements in the input case, qhWeight, q, representing the element of the question information tupleshValues representing the h-th transformed quantitative element of the intermediate information tuple in the standard case, qthRepresenting the values of the h-th transformed quantitative element of the inter-information tuple in the input case. f. ofsimRepresenting the similarity of the tangent information tuple in the input case and the tangent information tuple in the standard case, FsRepresents the cut information tuple in the standard case,Ftrepresenting tangent information tuple in input case, h representing ordinal number of elements in tangent information tuple in input case, n representing total number of elements in tangent information tuple in input case, fhWeight, f, representing the element of the tangent tuple of informationshValues of h-th transformed quantitative elements, f, representing tangent tuples of information in standard casesthRepresenting the values of the h-th transformed quantitative elements of the tangent tuple of information in the input case.
After the similarity between each information tuple and the corresponding standard information tuple in the standard case is calculated, step S5 is executed to perform weighted summation on the similarities corresponding to all the information tuples to obtain the membership of the cold case information corresponding to all the standard cases. The degree of membership of the standard case is obtained by the following formula: w ═ lsim·wl+ssim·ws+qsim·wq+fsim·wfWherein w isl、ws、wqAnd wfThe similarity weight of the hope information tuple, the similarity weight of the smell information tuple, the similarity weight of the question information tuple and the similarity weight of the cutting information tuple are respectively. In this embodiment, the similarity weight of the expected information tuple, the similarity weight of the smell information tuple, the similarity weight of the question information tuple, and the similarity weight of the tangent information tuple are determined according to the number of elements of each information element ancestor in the cold case information, and the similarity weight of each information tuple is equal to the number of elements of the information element ancestor divided by the total number of elements in the cold case information. By obtaining the membership of the standard case, the degree of approximation of the input cold case to the standard case can be confirmed.
After the membership degree of the standard case is obtained, step S6 is executed to confirm the cold syndrome result corresponding to the cold case information according to the membership degree. By obtaining the membership degree of the standard case, the approximation degree of the input cold case and the standard case can be confirmed, and the standard case with the maximum membership degree is selected as the judgment result of the input cold case. When a standard disease case library in the system is established, information needs to be extracted from a single cold case to construct an information tuple of the cold case, wherein the information tuple of the standard case specifically comprises a hope information tuple and a hearing information tupleAt least one of an information tuple, a question information tuple, a cut information tuple, and a correct cold diagnosis result tuple. The five information tuples of the standard cold cases are expressed as C ═ (L, S, Q, F and R), wherein the hope information tuple L ═ (L)1,l2,l3...ln) The information obtained by 'inspection' in the traditional Chinese medicine diagnosis of the cold specifically comprises spirit, color, shape, state, tongue condition and the like; the tuple of the news information S ═ S (S)1,s2,s3...sn) The method is used for diagnosing information, such as sound, smell and the like, obtained by smelling in the cold in the traditional Chinese medicine; ask the information tuple Q ═ (Q)1,q2,q3...qn) The information obtained by 'asking' in the process of diagnosing the cold in the traditional Chinese medicine specifically comprises cold and heat, sweat, pain, aversion to stool, diet and the like; the tangent information tuple F ═ F1,f2,f3...fn) The information obtained by cutting in the traditional Chinese medicine cold specifically comprises information such as pulse conditions, description and the like; cold diagnosis result tuple R ═ R (R)1,r2,r3,r4) Specifically, the types include wind-cold syndrome, wind-heat syndrome, summer-heat-dampness syndrome and seasonal common cold syndrome. Each standard case corresponds to a cold syndrome type, so that the cold syndrome type result corresponding to the information of the cold case can be confirmed after the standard case is confirmed.
After the cold syndrome result corresponding to the cold case information is confirmed, step S7 is executed to determine whether the cold syndrome result is reliable. And when judging whether the cold syndrome result is reliable or not, judging whether the membership degree is greater than or equal to a preset membership degree or not, and if so, confirming that the cold syndrome result is reliable, namely, the cold syndrome result is correct. And the preset membership degree is set according to the experimental data.
If the result of the cold syndrome is confirmed to be reliable, step S8 is executed to determine whether the standard case library has the same case as the cold case information. When the result of the cold syndrome is judged to be correct, in order to expand the standard cases of the standard library, the information of the cold cases with correct cold syndrome results needs to be stored as the standard cases. In the storage process, in order to avoid the duplication of the stored standard cases, whether the cases with the same information as the cold cases exist in the standard case library or not needs to be judged. When judging whether a case with the same information as the cold case exists in the standard case library, comparing an information tuple corresponding to the cold case information with a standard information tuple of the standard case, and confirming that the case with the same information as the cold case exists in the standard case library when elements in the information tuple are all the same as elements in the standard information tuple.
If it is determined that the standard case base does not have the same case as the cold case information, step S9 is executed to add the cold case information and the cold syndrome result to the standard case base. The information of the cold cases and the cold syndrome results are added to the standard disease case library, so that the standard cases of the standard disease case library are increased, and the accuracy of judging the cold syndrome is improved. If it is confirmed that the case identical to the cold case information exists in the standard case library, it is considered that the currently input cold case information does not need to be stored.
After the cold case information and the cold syndrome result are added to the standard case library, or when the cold syndrome result is determined to be unreliable, or when it is determined that a case identical to the cold case information exists in the standard case library, the step S10 is executed, the judgment accuracy of the cold case information in the preset time period is obtained, and the standard case in the standard case library is adjusted according to the judgment accuracy. By obtaining the judgment accuracy of the information of the cold cases in the preset time period, the accuracy of the current algorithm can be determined so as to adjust the standard cases. In this embodiment, the evaluation accuracy is obtained by the following formula: and alpha is the number of input cases in the first preset time period with correct judgment/the number of input cases in the first preset time period is multiplied by 100%. The first preset time period can be set according to actual needs. For example, if the number of input cold case information pieces in a certain time zone, which is 90 pieces of input cold case information pieces for which the correctness of the cold syndrome result is confirmed, is 100, the evaluation accuracy α is 90/100 × 100%, which is 90%.
Referring to fig. 2, in the present embodiment, when the standard case in the standard case library is adjusted according to the judgment accuracy, step S91 is executed first to judge whether the judgment accuracy meets the expectation. And when judging whether the judgment accuracy rate accords with the expectation or not, judging whether the judgment accuracy rate is greater than or equal to a preset accuracy rate or not, and if so, considering that the judgment accuracy rate accords with the expectation. The preset accuracy can be set according to experimental data, and preferably, the preset accuracy is 90%.
If the judgment accuracy is determined to meet the expectation, step S92 is executed to obtain the matching rate and the correct matching rate of the current standard case. Wherein, the matching rate of the current standard case is obtained by the following formula: and beta is the matching frequency of the current standard case in the second preset time period/all the matching frequencies of the cold syndrome types of the current standard case in the second preset time period multiplied by 100%. The correct matching rate of the current standard case is obtained by the following formula: and gamma is the number of times that the current standard case in the second preset time period is judged to be correct/the matching number of times of the current standard case in the second preset time period is multiplied by 100%. The utilization rate of each standard case in the standard case library can be determined by calculating the matching rate and the correct matching rate of each standard case in a second preset time period, and the second preset time can be set according to actual needs.
After the matching rate and the correct matching rate of the current standard case are obtained, step S93 is executed to determine whether the product of the matching rate and the correct matching rate is smaller than a preset threshold. Wherein, the preset threshold value can be set according to experimental data. The product of the matching rate and the correct matching rate can reflect the matched probability of the current standard case in the standard case library, and if the product of the matching rate and the correct matching rate is smaller than a preset threshold value, the probability of the current standard case is considered to be smaller.
When the product of the matching rate and the correct matching rate is less than the preset threshold, step S94 is executed to delete the current standard case from the standard library. And if the product of the matching rate and the correct matching rate is smaller than a preset threshold value, the current standard case is considered to be deleted from the standard library, so that the accuracy of the case in the standard library is improved, and the matching correct rate of the cold case information is improved. And when the product of the matching rate and the correct matching rate is determined to be greater than or equal to the preset threshold, the current standard case is considered to accord with the standard of the standard library without adjustment.
Of course, the cold syndrome types in the above embodiments are only four cold syndrome types by way of example, but it should be understood by those skilled in the art that if the cold syndrome types are divided in more detail, the number of the cold syndrome types may be specifically set as required.
The embodiment of the computer device comprises:
the computer device of the embodiment comprises a controller, and the steps in the cold syndrome type evaluation method embodiment are realized when the controller executes a computer program.
For example, a computer program may be partitioned into one or more modules, which are stored in a memory and executed by a controller to implement the present invention. One or more of the modules may be a sequence of computer program instruction segments for describing the execution of a computer program in a computer device that is capable of performing certain functions.
The computer device may include, but is not limited to, a controller, a memory. Those skilled in the art will appreciate that the computer apparatus may include more or fewer components, or combine certain components, or different components, e.g., the computer apparatus may also include input-output devices, network access devices, buses, etc.
For example, the controller may be a Central Processing Unit (CPU), other general purpose controller, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, and so on. The general controller may be a microcontroller or the controller may be any conventional controller or the like. The controller is the control center of the computer device and connects the various parts of the entire computer device using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the controller may implement various functions of the computer apparatus by executing or otherwise executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. For example, the memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (e.g., a sound receiving function, a sound-to-text function, etc.), and the like; the storage data area may store data (e.g., audio data, text data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Computer-readable storage medium embodiments:
the modules integrated by the computer apparatus of the above embodiments, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, all or part of the processes in the cold syndrome type evaluation method embodiment may also be completed by instructing related hardware through a computer program, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a controller, the steps of the cold syndrome type evaluation method embodiment may be realized. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The storage medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
Therefore, the cold syndrome type evaluation method provided by the invention can be used for carrying out tuple classification on the cold case information and calculating the similarity between each information tuple and the corresponding standard information tuple in the standard case so as to obtain the membership degree of the standard case and finally determine the cold syndrome type result corresponding to the cold case information, thereby effectively providing auxiliary support for intelligent traditional Chinese medicine decision diagnosis. In addition, the accuracy of the current algorithm can be determined by calculating the judgment accuracy of all standard cold case information in the standard library in a preset time period so as to adjust the standard cases. When the standard case is adjusted, the matching rate and the correct matching rate of the current standard case are obtained through calculation, and the cold cases with lower product of the matching rate and the correct matching rate in the standard library are eliminated based on the jungle rule, so that the matching efficiency of the evaluation algorithm is improved.
It should be noted that the above is only a preferred embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept also fall within the protection scope of the present invention.

Claims (10)

1. A cold syndrome type judging method based on case reasoning is characterized in that: the method comprises the following steps:
acquiring cold case information;
judging whether the cold case information is effective or not, if so, carrying out tuple classification processing on the cold case information to obtain all information tuples corresponding to the cold case information;
calculating the similarity of each information tuple and a standard information tuple corresponding to a standard case in a standard case library by adopting a weighted Euclidean distance similarity algorithm;
carrying out weighted summation on the similarity corresponding to all the information tuples to obtain the membership of the cold case information corresponding to all the standard cases;
and confirming a cold syndrome result corresponding to the cold case information according to the membership degree.
2. The cold syndrome type evaluation method according to claim 1, wherein:
after the step of confirming the cold syndrome corresponding to the cold case information according to the membership degree, the method further comprises the following steps:
and judging whether the cold syndrome result is reliable or not, if so, judging whether a case with the same information as the cold case exists in the standard case library, and if not, adding the cold case information and the cold syndrome result to the standard case library.
3. The cold syndrome type evaluation method according to claim 1, wherein:
after the step of confirming the cold syndrome corresponding to the cold case information according to the membership degree, the method further comprises the following steps:
and acquiring the judgment accuracy of the information of the cold cases in a preset time period, and adjusting the standard cases in the standard case library according to the judgment accuracy.
4. The cold syndrome type evaluation method according to claim 3, wherein:
the evaluation accuracy is obtained by the following formula:
and alpha is the number of input cases in the first preset time period with correct judgment/the number of input cases in the first preset time period is multiplied by 100%.
5. The cold syndrome type evaluation method according to claim 3, wherein:
the step of adjusting the standard cases in the standard case library according to the judgment accuracy comprises the following steps:
judging whether the judgment accuracy rate meets the expectation, if so, acquiring the matching rate and the correct matching rate of the current standard case;
and if the product of the matching rate and the correct matching rate is smaller than a preset threshold value, deleting the current standard case from the standard library.
6. The cold syndrome type evaluation method according to claim 5, wherein:
the matching rate of the current standard case is obtained by the following formula: beta is equal to the matching times of the current standard case in the second preset time period/all the matching times of the cold syndrome types of the current standard case in the second preset time period multiplied by 100 percent;
the correct matching rate of the current standard case is obtained by the following formula: and gamma is the number of times that the current standard case in the second preset time period is judged to be correct/the matching number of times of the current standard case in the second preset time period is multiplied by 100%.
7. The cold syndrome type evaluation method according to any one of claims 1 to 6, wherein:
the step of obtaining cold case information comprises:
and if the acquired cold case information is natural language information, performing word segmentation processing and synonym replacement processing on the natural language information.
8. The cold syndrome type evaluation method according to any one of claims 1 to 6, wherein:
the step of judging whether the cold case information is valid includes:
and if the cold case information comprises the related information of at least one information tuple, the cold case information is considered to be effective.
9. A computer device comprising a processor and a memory, wherein: the memory stores a computer program which, when executed by the processor, implements the steps of the cold syndrome evaluation method of any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a controller, implements the steps of the cold syndrome evaluation method of any one of claims 1 to 8.
CN202110184623.9A 2021-02-10 2021-02-10 Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium Pending CN112885460A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110184623.9A CN112885460A (en) 2021-02-10 2021-02-10 Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110184623.9A CN112885460A (en) 2021-02-10 2021-02-10 Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN112885460A true CN112885460A (en) 2021-06-01

Family

ID=76057490

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110184623.9A Pending CN112885460A (en) 2021-02-10 2021-02-10 Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN112885460A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107958007A (en) * 2016-10-18 2018-04-24 浙江格林蓝德信息技术有限公司 Case information search method and device
CN110364263A (en) * 2019-06-17 2019-10-22 上海交通大学 Therapeutic scheme recommended method and system based on expert authority in conjunction with case reliability
CN110517785A (en) * 2019-08-28 2019-11-29 北京百度网讯科技有限公司 Lookup method, device and the equipment of similar case
CN111091907A (en) * 2019-11-15 2020-05-01 合肥工业大学 Health medical knowledge retrieval method and system based on similar case library

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107958007A (en) * 2016-10-18 2018-04-24 浙江格林蓝德信息技术有限公司 Case information search method and device
CN110364263A (en) * 2019-06-17 2019-10-22 上海交通大学 Therapeutic scheme recommended method and system based on expert authority in conjunction with case reliability
CN110517785A (en) * 2019-08-28 2019-11-29 北京百度网讯科技有限公司 Lookup method, device and the equipment of similar case
CN111091907A (en) * 2019-11-15 2020-05-01 合肥工业大学 Health medical knowledge retrieval method and system based on similar case library

Similar Documents

Publication Publication Date Title
CN108509484B (en) Classifier construction and intelligent question and answer method, device, terminal and readable storage medium
CN110739034A (en) method for DRGs grouping of case data
WO2021073263A1 (en) Disease suffering risk prediction method and device
CN112183026A (en) ICD (interface control document) encoding method and device, electronic device and storage medium
CN111627510A (en) Method, system and equipment for automatically reporting infection cases and readable storage medium
CN107480426B (en) Self-iteration medical record file clustering analysis system
CN111177375A (en) Electronic document classification method and device
CN112214515A (en) Data automatic matching method and device, electronic equipment and storage medium
Bashir et al. Systematic comparison of machine learning algorithms to develop and validate predictive models for periodontitis
WO2021174923A1 (en) Concept word sequence generation method, apparatus, computer device, and storage medium
CN112885460A (en) Case reasoning-based cold syndrome type judging method, computer device and computer readable storage medium
WO2023124837A1 (en) Inquiry processing method and apparatus, device, and storage medium
US11437122B2 (en) Electronic methods and systems for microorganism characterization
Liao et al. A machine learning‐based risk scoring system for infertility considering different age groups
WO2021120528A1 (en) Automatic report interpretation method and system
WO2021184579A1 (en) Intelligent selection method and apparatus employing multiple solutions, computer device, and storage medium
CN113539520A (en) Method, device, computer equipment and storage medium for implementing inquiry session
CN114662588B (en) Method, system, equipment and storage medium for automatically updating model
CN113139498A (en) Medical bill code matching method and device
CN112489038A (en) Fuzzy model breast cancer diagnosis method based on fuzzy clustering and generalized least square method
US20200303033A1 (en) System and method for data curation
Fund Comparing association rules and deep neural networks on medical data
WO2023185082A1 (en) Training method and training device for language representation model
CN114996452B (en) Method, system and storage medium for generating medical insurance limited payment text logical expression
Lloyd-Williams Case studies in the data mining approach to health information analysis

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