CN113707296A - Medical treatment scheme data processing method, device, equipment and storage medium - Google Patents
Medical treatment scheme data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113707296A CN113707296A CN202110981896.6A CN202110981896A CN113707296A CN 113707296 A CN113707296 A CN 113707296A CN 202110981896 A CN202110981896 A CN 202110981896A CN 113707296 A CN113707296 A CN 113707296A
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- result
- feature
- scheme
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 28
- 238000004088 simulation Methods 0.000 claims abstract description 121
- 238000012545 processing Methods 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000013210 evaluation model Methods 0.000 claims abstract description 37
- 238000010606 normalization Methods 0.000 claims abstract description 30
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims description 124
- 238000000605 extraction Methods 0.000 claims description 53
- 238000004590 computer program Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 22
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract 1
- 229940079593 drug Drugs 0.000 description 13
- 239000003814 drug Substances 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 11
- 238000003062 neural network model Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012854 evaluation process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a medical scheme data processing method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring medical scheme data to be evaluated; obtaining medical characteristic data through dimension normalization processing; respectively inputting the medical characteristic data into a simulation evaluation model and a standard matching model; extracting dimension correlation characteristics through a simulation evaluation model to evaluate a final simulation result, and performing characteristic matching processing through a standard matching model to obtain a final standard result; carrying out variance processing on the final simulation result and the final standard result to obtain a variance result; and determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated. Therefore, the method and the device realize the result of rapidly and accurately evaluating the feasibility of the scheme, and greatly improve the efficiency of the feasibility analysis of the scheme. The invention is suitable for the field of artificial intelligence and can further promote the construction of intelligent medical treatment.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a medical scheme data processing method, a device, equipment and a storage medium.
Background
At present, in the evaluation process of feasibility analysis of medical administration schemes or feasibility analysis of medical pre-diagnosis schemes and other medical scheme data analysis feasibility, whether the scheme content is matched with a scheme guide or a compliance is involved, however, a plurality of factors exist in the scheme content, the scheme type span is large, scheme objects are various, the filled text content is inconsistent, and the evaluation method and the evaluation rule are diverse, so that the feasibility analysis of the scheme is mainly evaluated in a manual mode, in the existing technical scheme, the judgment is mainly based on subjective experiences of a plurality of experts, the subjective performance is high, and whether the practical implementation of the scheme is feasible or not is determined by manually checking the factors in the scheme such as the scheme steps, the price or the cost, and the like, and huge labor cost is consumed, therefore, the feasibility analysis investment cost of the existing scheme is large, and the evaluation period is long, the subjectivity is high, and the situation that a subsequent execution scheme has major problems due to manual misjudgment or omission easily occurs.
Disclosure of Invention
The invention provides a medical scheme data processing method, a medical scheme data processing device, computer equipment and a storage medium, which can accurately measure the evaluation result of whether the medical scheme data to be evaluated is feasible or not, and realize the quick and accurate evaluation of the feasibility result of the scheme without great subjectivity, energy and time input by manpower, thereby greatly improving the efficiency of the feasibility analysis of the scheme.
A medical protocol data processing method, comprising:
acquiring medical scheme data to be evaluated, and performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data;
inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively;
performing dimension correlation feature extraction on the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension correlation feature, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data;
carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result;
and determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result.
A medical protocol data processing apparatus comprising:
the normalizing module is used for acquiring the medical scheme data to be evaluated and performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data;
the input module is used for inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively;
the extraction module is used for extracting dimension associated features of the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension associated features, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data;
the variance module is used for carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result;
and the determining module is used for determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the medical protocol data processing method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned medical protocol data processing method.
The invention provides a medical scheme data processing method, a device, computer equipment and a storage medium, wherein the method comprises the steps of obtaining medical scheme data to be evaluated; performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data; inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively; performing dimension correlation feature extraction on the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension correlation feature, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data; carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result; and determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result, so that feasibility analysis can be automatically performed from a technical level and a cost level through a simulation evaluation model and a standard matching model to obtain a final simulation result and a final standard result, and the evaluation result of whether the medical scheme data to be evaluated is feasible can be accurately measured through the variance between the final simulation result and the final standard result, so that a large amount of subjectivity, energy and time are not required to be manually input, the result of rapidly and accurately evaluating the feasibility of the scheme is realized, and the efficiency of the feasibility analysis of the scheme is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a medical procedure data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of processing medical protocol data in accordance with an embodiment of the present invention;
FIG. 3 is a flowchart of step S10 of a medical protocol data processing method in an embodiment of the invention;
FIG. 4 is a flowchart of step S30 of a medical protocol data processing method in an embodiment of the invention;
FIG. 5 is a functional block diagram of a medical protocol data processing apparatus in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a computer device in an embodiment of 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 some, not all, embodiments of the present invention. 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.
The medical scheme data processing method provided by the invention can be applied to the application environment shown in fig. 1, wherein a client (computer equipment or terminal) is communicated with a server through a network. The client (computer device or terminal) includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
In an embodiment, as shown in fig. 2, a medical treatment plan data processing method is provided, which mainly includes the following steps S10-S50:
and S10, acquiring the medical scheme data to be evaluated, and performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data.
Understandably, the medical plan data to be evaluated is plan information to be evaluated, and the medical plan data to be evaluated includes information related to various factors or dimensions of a plan, such as: in the medical field, the medical plan data to be evaluated includes information such as sex, age, disease type, department, hospital grade, doctor qualification grade, medication plan, medication list, medication price, and the like.
The dimension normalization processing process is a processing process of converting input information according to a format of structured data, performing standardized expansion on the converted structured data, and performing vector conversion to obtain normalized feature vector data, and the medical feature data is a feature vector set obtained after the data of each dimension is subjected to dimension normalization processing.
In an embodiment, as shown in fig. 3, in step S10, the acquiring medical plan data to be evaluated and performing dimension normalization processing on the medical plan data to be evaluated to obtain medical characteristic data includes:
and S101, performing structured data processing on the medical scheme data to be evaluated to obtain data to be processed.
Understandably, the structuring process is to convert the information of each dimension in the medical scheme data to be evaluated into a uniform structured data format which can be stored in a database, so as to obtain the data to be evaluated.
In an embodiment, in step S101, that is, performing structured data processing on the medical plan data to be evaluated to obtain data to be processed, the method includes:
and performing information filtering on the medical scheme data to be evaluated to obtain effective data.
Understandably, the information filtering is to delete the unstructured data in the scheme to be evaluated and delete the data of the disturbed dimensionality to obtain the valid data, for example: the privacy information including the patient, including name, photo, identification number, address, contact information and the like, is removed.
And carrying out structural data conversion on the effective data to obtain the data to be processed.
Understandably, the structured data is converted into a conversion process for converting the valid data into a storable unified predefined structured data format, for example: and the structured data format is a key-value format, so that the data to be processed is obtained.
According to the method, the effective data is obtained by filtering the information of the medical scheme data to be evaluated; and performing structured data conversion on the effective data to obtain the data to be processed, so that useful data can be screened out and converted into data in a structured format, and subsequent feasibility analysis is facilitated.
S102, normalizing each dimension data in the data to be processed to obtain a feature vector corresponding to each dimension data one by one.
Understandably, the normalization processing is a process of performing corresponding data extraction and normalization on each dimension data, and converting data of the same dimension data into a quantifiable feature vector.
In an embodiment, in the step S102, that is, performing normalization processing on each dimension data in the data to be processed to obtain a feature vector corresponding to each dimension data one to one, includes:
and acquiring a data type corresponding to each dimension data.
Understandably, the process of obtaining the data type corresponding to each of the dimension data may be to obtain a dimension attribute corresponding to each of the dimension data, where the dimension attribute represents a category name of the dimension data, search for a preset data type corresponding to each of the obtained dimension attributes, and obtain the data type corresponding to each of the found dimension attributes, so as to obtain the data type corresponding to each of the dimension data, where, for example, the data type includes a text type, a numerical type, a character type, and the like.
And performing corresponding data extraction and normalization processing on the dimensional data according to the data type corresponding to the dimensional data through a normalization model to obtain extraction results corresponding to the dimensional data one by one.
Understandably, the normalization model is a model for performing corresponding normalization processing on different input data types, and different data types correspond to different normalization processing procedures, such as: for the numeric type, the normalization processing process is to convert the values of all the numeric types into numeric values with uniform dimensions or ranges, for the text type, the normalization processing process is to perform processing processes of text abbreviation expansion on the text content, semantic extraction of keywords from the text context, labeling of each keyword, and the like, and the extraction result is to extract the key content from the dimensional data.
And performing vector conversion corresponding to the data type corresponding to the extraction result on each extraction result to obtain the feature vector corresponding to each extraction result.
Understandably, the vector conversion is a process of converting each extraction result into a feature vector of the same dimension, that is, converting the extraction result into a feature vector of a dimension corresponding to the extraction result according to a range in which each extraction result falls, for example, the vector conversion is completed by using one-hot coding conversion, the one-hot coding conversion is a technology of converting the structured data into the structured embedded data by using one-hot coding technology, the one-hot coding technology is a technology of allocating a vector value corresponding to one-to-one mapping of each type of information content in the structured data, that is, coding each type of information, and then converting the structured data into an array vector.
The invention realizes the purpose of acquiring the data type corresponding to each dimension data; inputting the data to be processed into a normalization model; performing corresponding data extraction and normalization processing on the dimensional data through the normalization model according to the data types corresponding to the dimensional data to obtain extraction results corresponding to the dimensional data one by one; and performing vector conversion corresponding to the data types corresponding to the extraction results on each extraction result to obtain the feature vectors corresponding to each extraction result, so that corresponding normalization processing can be performed according to different data types, different data types are converted into quantifiable feature vectors, and a data basis is provided for subsequent feasibility analysis.
And S103, carrying out vector combination on all the feature vectors to obtain the medical feature data.
Understandably, all the feature vectors are combined according to the format and the dimensionality of the central matrix, and parts with insufficient dimensionality or missing dimensionality are filled in a zero filling mode, so that a feature vector matrix is converged after filling is completed, and the feature vector matrix is recorded as the medical feature data.
The method and the device realize the structured data processing of the medical scheme data to be evaluated to obtain the data to be processed; normalizing each dimension data in the data to be processed to obtain a feature vector corresponding to each dimension data one by one; and carrying out vector combination on all the feature vectors to obtain the medical feature data, so that the data of each dimension can be automatically converted into the measurable feature vectors of uniform dimension, the subsequent feasibility analysis is facilitated, and the accuracy of the subsequent feasibility analysis is also improved.
And S20, inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively.
Understandably, the simulation evaluation model is a trained model for performing feasibility analysis results of a technical dimension and a cost dimension evaluation scheme on input data, and the standard matching model is a trained model for matching the input data to obtain a portrait category which is most matched with feature clusters of all dimensions of the input data, and obtaining a final standard result associated with the portrait category.
In one embodiment, before entering the medical feature data into the standard matching model, the method further comprises:
acquiring a feature vector sample set; the feature vector sample set comprises a plurality of feature vector samples; one of the feature vector samples corresponds to one of the sample portrait labels.
Understandably, the feature vector sample set is a set of the feature vector samples, the feature vector samples are feature vectors obtained by subjecting historically collected samples to dimensionality normalization processing, one feature vector sample corresponds to one sample portrait label, and the sample portrait label is a portrait category.
Inputting the feature vector samples into an initial neural network model containing initial parameters.
Understandably, the initial neural network model contains the initial parameters, the initial parameters may be preset parameters or parameters obtained by a transfer learning manner, and the transfer learning is a learning method for transferring a network structure and parameter values to the initial neural network model from a model related to a portrait in the same field or other fields.
And performing dimension association feature extraction on the feature vector sample through the initial neural network model, performing feature clustering according to the extracted dimension association feature, and obtaining an portrait type and a sample standard result associated with the portrait type.
Understandably, the dimension association features are features which are respectively embodied from a technical level and a cost level and are related to the association of each dimension, the dimension association features comprise technical dimension association features and cost dimension association features, the feature clustering method is a method for clustering the dimension association features among the dimensions by applying a K-means clustering algorithm, the sample standard result is a feature vector of each dimension formed by the mean value of each dimension in all feature vector samples corresponding to the same portrait category, and one portrait category corresponds to one sample standard result.
A loss value is determined based on the image type and the sample image tag.
Understandably, the portrait class and the sample portrait label are input into a loss function, from which the loss value is calculated, preferably a cross entropy (cross entropy) loss function.
And when the loss value does not reach the preset convergence condition, iteratively updating the initial parameters of the initial neural network model until the loss value reaches the preset convergence condition, and recording the converged initial neural network model as the standard matching model.
Understandably, the preset convergence condition may be a condition that the loss value is small and does not decrease again after 20000 times of calculation, that is, when the loss value is small and does not decrease again after 20000 times of calculation, stopping training, and recording the initial neural network model after convergence as the standard matching model; the preset convergence condition may also be a condition that the loss value is smaller than a set threshold, that is, when the loss value is smaller than the set threshold, the training is stopped, and the converged initial neural network model is recorded as the standard matching model, so that when the loss value does not reach the preset convergence condition, the initial parameters of the initial neural network model are continuously adjusted, and the initial parameters can be continuously drawn close to an accurate result, so that the recognition accuracy is higher and higher. Therefore, triage identification can be optimized, and accuracy and reliability of triage identification are improved.
S30, performing dimension correlation feature extraction on the medical characteristic data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical characteristic data based on the extracted dimension correlation feature, and performing feature matching processing on the medical characteristic data through the standard matching model to obtain a final standard result corresponding to the medical characteristic data.
Understandably, the medical characteristic data is subjected to the extraction of the dimension correlation characteristics through the simulation evaluation model, whether the medical characteristic data is feasible or not is evaluated from the technical dimension and the cost dimension, and a final simulation result is obtained, the final simulation result represents the evaluated values of the medical characteristic data on the technical level, the cost level and the comprehensive level respectively, the characteristic matching processing process is a processing process of performing similarity matching on data of each dimension in the medical characteristic data through a standard matching model, matching the portrait type which is the best matched with the medical characteristic data, acquiring a sample standard result associated with the portrait type from the standard matching model, and recording the sample standard result as a final standard result, and the final standard result comprises standard scores on a technical level, a cost level and a comprehensive level.
The dimension association features are features which are respectively embodied from a technical level and a cost level and are related to association of each dimension, the dimension association features comprise technical dimension association features and cost dimension association features, the technical dimension association features are features related to association between each dimension related to the technology in the medical feature data, and the cost dimension association features are features related to association between each dimension related to the cost in the medical feature data, such as: the medical characteristic data comprises dimension data of sex, age, medication category, hospital, medication physician, medication scheme, medication expense and the like, the technical dimension correlation characteristic is a correlation characteristic among the sex, the age, the medication category, the medication physician, the medication scheme and the like, and the cost dimension correlation characteristic is a correlation characteristic among the hospital, the medication category, the medication expense, the medication scheme and the like.
In an embodiment, as shown in fig. 4, in the step S30, the performing, by the simulation evaluation model, dimension related feature extraction on the medical feature data, and evaluating, based on the extracted dimension related feature, a final simulation result corresponding to the medical feature data includes:
s301, weighting each feature vector in the medical feature data through the simulation evaluation model to obtain weighted data.
Understandably, the weighting process is a process of giving a corresponding weight according to the condition of each dimension, and multiplying each feature vector in the medical feature data by the corresponding weight, so that the weighted data corresponding to the medical feature data can be obtained.
S302, extracting technical dimension association characteristics of the weighted data through the simulation evaluation model, and evaluating a technical simulation result according to the extracted technical dimension association characteristics.
Understandably, the technical dimension correlation characteristic is a characteristic related to correlation among all dimensions related to technology in medical characteristic data, the process of evaluating according to the extracted technical dimension correlation characteristic is that technical dimension extraction is carried out on the weighted data, a scheme portrait label is obtained by clustering the data after the technical dimension extraction, technical up-and-down correlation identification corresponding to the scheme portrait label is carried out through a scheme evaluation sub-model corresponding to the scheme portrait label, and an evaluation process of a technical simulation result is obtained, wherein the technical simulation result shows whether the medical scheme data to be evaluated corresponding to the medical characteristic data is feasible in the technical level.
In an embodiment, in the step S302, that is, performing the technical dimension association feature extraction on the weighted data through the simulation evaluation model, and evaluating a technical simulation result according to the extracted technical dimension association feature includes:
performing technical dimension extraction on the weighted data to obtain a technical characteristic vector matrix; the technical feature vector matrix includes a scheme type vector, a scheme scene vector, a scheme object vector, and a plurality of scheme content vectors.
Understandably, the technology dimension extraction is a process of extracting data of a technology-related dimension, the scheme type vector is a vector of a type to which a scheme belongs, the scheme scene vector is a vector corresponding to a name of an application scene of the scheme, the scheme object vector is a vector of an object oriented in the scheme, and the scheme content vector is a vector corresponding to a key entity and an action in the scheme content.
And clustering the scheme type vector, the scheme object vector and the scheme scene vector to obtain a scheme portrait label.
Understandably, the clustering process is a process of imaging the scheme type vector, the scheme object vector and the scheme scene vector in a K-means clustering manner, so as to determine a scheme portrait label, wherein the scheme portrait label comprises various technically divided categories of schemes.
And acquiring a scheme evaluation sub-model corresponding to the scheme portrait label.
And performing technical up-down association identification corresponding to the scheme portrait label on all the scheme content vectors through the obtained scheme evaluation submodel to obtain the technical simulation result.
Understandably, the technical context association is identified as the sequence of the feature vectors and the identification process of the related association relationship, so as to obtain the technical simulation result of whether the technical execution is in compliance or reasonable.
The method and the device realize that the scheme portrait label is obtained through clustering, whether the technology simulation result is feasible or not is evaluated through the corresponding scheme evaluation sub-model and the technology context correlation identification technology, and the accuracy of scheme feasibility analysis can be improved.
And S303, extracting cost dimension correlation characteristics of the weighted data through the simulation evaluation model, and evaluating a cost simulation result according to the extracted cost dimension correlation characteristics.
Understandably, the cost dimension correlation characteristic is a characteristic related to the correlation among all dimensions related to the cost in the medical characteristic data, and the process of evaluating according to the extracted cost dimension correlation characteristic is to perform cost dimension extraction on the weighted data to obtain a cost characteristic vector matrix; performing compliance identification on the cost characteristic vector matrix to obtain a first compliance result; performing cost dimension correlation feature extraction on the cost feature vector matrix, and performing cost evaluation according to the extracted cost dimension correlation feature to obtain a second compliance result; and determining the cost simulation result based on the first compliance result and the second compliance result, wherein the cost simulation result indicates whether the medical scheme data to be evaluated corresponding to the medical feature data is feasible in a cost level.
In an embodiment, in step S303, that is, the performing, by the simulation evaluation model, cost dimension associated feature extraction on the weighted data, and evaluating a cost simulation result according to the extracted cost dimension associated feature includes:
carrying out cost dimension extraction on the weighted data to obtain a cost characteristic vector matrix; the cost feature vector includes a cost item vector and a cost vector corresponding to the cost item vector.
Understandably, the cost dimension extraction is a process of extracting data of a dimension related to cost, the cost item vectors are vectors each corresponding to a name of each item or required material or material, and the cost expense vector is a vector of expense or price corresponding to the cost item vector.
And performing compliance identification on all the cost item vectors and all the cost expense vectors to obtain a first compliance result.
Understandably, the compliance identification process is a process of querying a compliance fee range corresponding to the cost item vector, judging whether the cost item vector corresponding to the cost item vector falls into the corresponding compliance fee range, thereby obtaining a compliance identification result of the cost item vector, and merging the compliance identification results of all the cost item vectors into the first compliance result.
And extracting cost dimension correlation characteristics of all the cost item vectors, and performing cost evaluation according to the extracted cost dimension correlation characteristics to obtain a second compliance result.
Understandably, the process of extracting the cost dimension association features is a process of extracting the association between the cost item vectors, and the cost evaluation is an evaluation process of evaluating whether the association between the cost item vectors conforms to coexistence or the same category, so as to judge whether all the cost item vectors are in compliance or not, and obtain the second compliance result, where the second compliance result represents a result of whether the coexistence or the same category of relationship between the cost item vectors is in compliance or not.
And determining the cost simulation result according to the first compliance result and the second qualified result.
Understandably, determining whether the cost simulation result is in compliance by combining whether both the first compliance result and the second compliance result are results of compliance, and determining that the cost simulation result is not in compliance as long as either one of the first compliance result and the second compliance result is not in compliance.
According to the invention, cost dimension extraction is carried out on the weighted data to obtain a cost characteristic vector matrix; the cost feature vector comprises a cost item vector and a cost expense vector corresponding to the cost item vector; performing compliance identification on all the cost item vectors and all the cost expense vectors to obtain a first compliance result; extracting cost dimension correlation characteristics of all the cost item vectors, and performing cost evaluation according to the extracted cost dimension correlation characteristics to obtain a second compliance result; and determining the cost simulation result according to the first compliance result and the second qualified result, so that the cost simulation result can be comprehensively output according to the first compliance result and the second compliance result estimated by cost by a compliance identification and cost dimension correlation feature extraction method, the feasibility of the scheme is analyzed from a cost level, and the accuracy and the reliability of the feasibility analysis of the scheme are improved.
S304, determining a comprehensive simulation result according to the technical simulation result and the cost simulation result.
Understandably, whether the comprehensive simulation result is in compliance is judged by combining whether the technical simulation result and the cost simulation result are both in compliance, and the comprehensive simulation result is determined to be in non-compliance as long as any one of the technical simulation result and the cost simulation result is in non-compliance.
S305, recording the technical simulation result, the cost simulation result and the comprehensive simulation result as the final simulation result.
According to the medical characteristic data weighting method and device, weighting processing is carried out on each characteristic vector in the medical characteristic data through the simulation evaluation model, and weighting data are obtained; performing technical dimension association feature extraction on the weighted data through the simulation evaluation model, and evaluating a technical simulation result according to the extracted technical dimension association feature; performing cost dimension correlation characteristic extraction on the weighted data through the simulation evaluation model, and evaluating a cost simulation result according to the extracted cost dimension correlation characteristic; determining a comprehensive simulation result according to the technical simulation result and the cost simulation result; and recording the technical simulation result, the cost simulation result and the comprehensive simulation result as the final simulation result, so that the technical simulation result and the cost simulation result are automatically evaluated through the processing processes of weighting processing, technical dimension correlation feature extraction and cost dimension correlation feature extraction, and the comprehensive simulation result is finally determined, so that the final simulation result is output, and the feasibility analysis of the scheme is scientifically and objectively evaluated.
In an embodiment, the step S30, in which the performing the feature matching process on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data includes:
preprocessing the medical characteristic data through an input layer in the standard matching model to obtain data to be matched; understandably, the standard matching model is a trained neural network model, the standard matching model comprises an output layer, a hidden layer and an output layer, and the preprocessing is to screen out the data to be matched from the medical characteristic data.
Carrying out feature matching processing and deviation identification on the data to be matched through a hidden layer in the standard matching model to obtain a matched feature vector group; classifying the matched feature vector group through an output layer in the standard matching model to obtain a technical standard result and a cost standard result; determining a comprehensive standard result according to the technical standard result and the cost standard result; and recording the technical standard result, the cost standard result and the comprehensive standard result as the final standard result.
Therefore, the characteristic matching processing and the deviation recognition are carried out through the standard matching model, the final standard result can be automatically matched, the measuring standard is provided for the subsequent scheme feasibility analysis, the final standard result is used as the reference for analysis, and the accuracy of the scheme feasibility analysis is improved.
And S40, performing variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result.
Understandably, the variance processing is a processing procedure of calculating a variance value between the final simulation result and the final standard result by using a variance formula, and after the variance processing, the variance result is obtained, and the variance result represents a difference range between the final simulation result and the final standard result.
Wherein the variance result is:
wherein X is the final simulation result; μ is the final standard result; n is the number of samples, and is preferably a fixed value of 1.
And S50, determining a feasibility assessment result corresponding to the medical scheme data to be assessed based on the variance result.
Understandably, the value of the variance result is judged to fall into which preset variance range, the preset variance range is divided into three intervals, the variance range is determined to be superior within [0,0.15], the variance range is determined to be good between (0.15,0.5), the variance range larger than 0.5 is determined to be poor, so that the feasibility evaluation result corresponding to the medical scheme data to be evaluated can be obtained, and the feasibility evaluation result shows the feasibility analysis result of the corresponding medical scheme data to be evaluated.
The invention realizes the purpose of acquiring the data of the medical scheme to be evaluated; performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data; inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively; performing dimension correlation feature extraction on the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension correlation feature, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data; carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result; and determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result, so that feasibility analysis can be automatically performed from a technical level and a cost level through a simulation evaluation model and a standard matching model to obtain a final simulation result and a final standard result, and the evaluation result of whether the medical scheme data to be evaluated is feasible can be accurately measured through the variance between the final simulation result and the final standard result, so that a large amount of subjectivity, energy and time are not required to be manually input, the result of rapidly and accurately evaluating the feasibility of the scheme is realized, and the efficiency of the feasibility analysis of the scheme is greatly improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, a medical treatment plan data processing device is provided, and the medical treatment plan data processing device corresponds to the medical treatment plan data processing method in the above embodiment one to one. As shown in fig. 5, the medical plan data processing apparatus includes a normalization module 11, an input module 12, an extraction module 13, a variance module 14, and a determination module 15. The functional modules are explained in detail as follows:
the normalizing module 11 is configured to obtain medical scheme data to be evaluated, and perform dimension normalizing processing on the medical scheme data to be evaluated to obtain medical feature data;
the input module 12 is used for inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively;
the extraction module 13 is configured to perform dimension correlation feature extraction on the medical feature data through the simulation evaluation model, evaluate a final simulation result corresponding to the medical feature data based on the extracted dimension correlation feature, and perform feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data;
a variance module 14, configured to perform variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result;
and the determining module 15 is configured to determine a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result.
For specific limitations of the medical plan data processing apparatus, reference may be made to the above limitations of the medical plan data processing method, which are not described herein again. The various modules in the medical protocol data processing apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a client or a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a readable storage medium and an internal memory. The readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the readable storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a medical protocol data processing method.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the medical plan data processing method in the above embodiments is implemented.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the medical protocol data processing method in the above-described embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A medical protocol data processing method, comprising:
acquiring medical scheme data to be evaluated, and performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data;
inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively;
performing dimension correlation feature extraction on the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension correlation feature, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data;
carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result;
and determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result.
2. The medical plan data processing method according to claim 1, wherein the performing dimension normalization processing on the medical plan data to be evaluated to obtain medical characteristic data includes:
carrying out structured data processing on the medical scheme data to be evaluated to obtain data to be processed;
normalizing each dimension data in the data to be processed to obtain a feature vector corresponding to each dimension data one by one;
and carrying out vector combination on all the feature vectors to obtain the medical feature data.
3. The medical protocol data processing method of claim 2, wherein the performing structured data processing on the medical protocol data to be evaluated to obtain data to be processed comprises:
performing information filtering on the medical scheme data to be evaluated to obtain effective data;
and carrying out structural data conversion on the effective data to obtain the data to be processed.
4. The medical plan data processing method according to claim 2, wherein the normalizing each of the dimensional data in the data to be processed to obtain a feature vector corresponding to each of the dimensional data one to one includes:
acquiring a data type corresponding to each dimension data;
performing corresponding data extraction and normalization processing on the dimensional data through a normalization model according to the data types corresponding to the dimensional data to obtain extraction results corresponding to the dimensional data one by one;
and performing vector conversion corresponding to the data type corresponding to the extraction result on each extraction result to obtain the feature vector corresponding to each extraction result.
5. The medical plan data processing method according to claim 1, wherein the performing, by the simulation evaluation model, dimension-related feature extraction on the medical feature data, and evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension-related feature comprises:
weighting each feature vector in the medical feature data through the simulation evaluation model to obtain weighted data;
performing technical dimension association feature extraction on the weighted data through the simulation evaluation model, and evaluating a technical simulation result according to the extracted technical dimension association feature;
performing cost dimension correlation characteristic extraction on the weighted data through the simulation evaluation model, and evaluating a cost simulation result according to the extracted cost dimension correlation characteristic;
determining a comprehensive simulation result according to the technical simulation result and the cost simulation result;
and recording the technical simulation result, the cost simulation result and the comprehensive simulation result as the final simulation result.
6. The medical protocol data processing method according to claim 5, wherein the performing, by the simulation evaluation model, a technical dimension correlation feature extraction on the weighted data and evaluating a technical simulation result according to the extracted technical dimension correlation feature comprises:
performing technical dimension extraction on the weighted data to obtain a technical characteristic vector matrix; the technical feature vector matrix comprises a scheme type vector, a scheme scene vector, a scheme object vector and a plurality of scheme content vectors;
clustering the scheme type vector, the scheme object vector and the scheme scene vector to obtain a scheme portrait label;
acquiring a scheme evaluation sub-model corresponding to the scheme portrait label;
and performing technical up-down association identification corresponding to the scheme portrait label on all the scheme content vectors through the obtained scheme evaluation submodel to obtain the technical simulation result.
7. The medical procedure data processing method of claim 6, wherein said extracting cost dimension associated features from said weighted data by said simulation evaluation model and evaluating cost simulation results based on said extracted cost dimension associated features comprises:
carrying out cost dimension extraction on the weighted data to obtain a cost characteristic vector matrix; the cost feature vector comprises a cost item vector and a cost expense vector corresponding to the cost item vector;
performing compliance identification on all the cost item vectors and all the cost expense vectors to obtain a first compliance result;
extracting cost dimension correlation characteristics of all the cost item vectors, and performing cost evaluation according to the extracted cost dimension correlation characteristics to obtain a second compliance result;
and determining the cost simulation result according to the first compliance result and the second qualified result.
8. A medical protocol data processing apparatus, comprising:
the normalizing module is used for acquiring the medical scheme data to be evaluated and performing dimensionality normalization processing on the medical scheme data to be evaluated to obtain medical characteristic data;
the input module is used for inputting the medical characteristic data into a simulation evaluation model and a standard matching model respectively;
the extraction module is used for extracting dimension associated features of the medical feature data through the simulation evaluation model, evaluating a final simulation result corresponding to the medical feature data based on the extracted dimension associated features, and performing feature matching processing on the medical feature data through the standard matching model to obtain a final standard result corresponding to the medical feature data;
the variance module is used for carrying out variance processing on the final simulation result and the final standard result corresponding to the medical characteristic data to obtain a variance result;
and the determining module is used for determining a feasibility evaluation result corresponding to the medical scheme data to be evaluated based on the variance result.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the medical protocol data processing method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the medical plan data processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110981896.6A CN113707296B (en) | 2021-08-25 | 2021-08-25 | Medical scheme data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110981896.6A CN113707296B (en) | 2021-08-25 | 2021-08-25 | Medical scheme data processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113707296A true CN113707296A (en) | 2021-11-26 |
| CN113707296B CN113707296B (en) | 2024-04-02 |
Family
ID=78654693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110981896.6A Active CN113707296B (en) | 2021-08-25 | 2021-08-25 | Medical scheme data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113707296B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524464A (en) * | 2024-01-04 | 2024-02-06 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
| CN117558400A (en) * | 2024-01-12 | 2024-02-13 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6223074B1 (en) * | 1999-08-10 | 2001-04-24 | Thuris Corporation | Method and computer program product for assessing neurological conditions and treatments using evoked response potentials |
| CN111737975A (en) * | 2020-05-14 | 2020-10-02 | 平安科技（深圳）有限公司 | Text connotation quality evaluation method, device, equipment and storage medium |
| CN112035541A (en) * | 2020-08-28 | 2020-12-04 | 平安科技（深圳）有限公司 | Client image drawing method and device, computer readable storage medium and terminal equipment |
| CN112233810A (en) * | 2020-10-20 | 2021-01-15 | 武汉华大基因科技有限公司 | Treatment scheme comprehensive curative effect evaluation method based on real world clinical data |
| CN112259253A (en) * | 2020-11-13 | 2021-01-22 | 上海市第六人民医院 | Medical prescription auditing system and method |
| CN112950579A (en) * | 2021-02-26 | 2021-06-11 | 北京金山云网络技术有限公司 | Image quality evaluation method and device and electronic equipment |
-
2021
- 2021-08-25 CN CN202110981896.6A patent/CN113707296B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6223074B1 (en) * | 1999-08-10 | 2001-04-24 | Thuris Corporation | Method and computer program product for assessing neurological conditions and treatments using evoked response potentials |
| CN111737975A (en) * | 2020-05-14 | 2020-10-02 | 平安科技（深圳）有限公司 | Text connotation quality evaluation method, device, equipment and storage medium |
| CN112035541A (en) * | 2020-08-28 | 2020-12-04 | 平安科技（深圳）有限公司 | Client image drawing method and device, computer readable storage medium and terminal equipment |
| CN112233810A (en) * | 2020-10-20 | 2021-01-15 | 武汉华大基因科技有限公司 | Treatment scheme comprehensive curative effect evaluation method based on real world clinical data |
| CN112259253A (en) * | 2020-11-13 | 2021-01-22 | 上海市第六人民医院 | Medical prescription auditing system and method |
| CN112950579A (en) * | 2021-02-26 | 2021-06-11 | 北京金山云网络技术有限公司 | Image quality evaluation method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 周正阳等: "智慧医疗终端应用模型与仿真系统设计", 信息与电脑(理论版), no. 03, pages 112 - 116 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524464A (en) * | 2024-01-04 | 2024-02-06 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
| CN117524464B (en) * | 2024-01-04 | 2024-04-05 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
| CN117558400A (en) * | 2024-01-12 | 2024-02-13 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
| CN117558400B (en) * | 2024-01-12 | 2024-03-15 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113707296B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860674B (en) | Sample category identification method, sample category identification device, computer equipment and storage medium | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| WO2021121129A1 (en) | Method and apparatus for similar case detection, device, and storage medium | |
| CN108596630B (en) | Fraud transaction identification method, system and storage medium based on deep learning | |
| CN113707296B (en) | Medical scheme data processing method, device, equipment and storage medium | |
| CN111797629B (en) | Method and device for processing medical text data, computer equipment and storage medium | |
| CN109783785B (en) | Method and device for generating experiment detection report and computer equipment | |
| CN111291264A (en) | Access object prediction method and device based on machine learning and computer equipment | |
| CN112035611B (en) | Target user recommendation method, device, computer equipment and storage medium | |
| CN112395500A (en) | Content data recommendation method and device, computer equipment and storage medium | |
| CN112132776A (en) | Visual inspection method and system based on federal learning, storage medium and equipment | |
| CN110888911A (en) | Sample data processing method and device, computer equipment and storage medium | |
| CN113095408A (en) | Risk determination method and device and server | |
| CN111767192B (en) | Business data detection method, device, equipment and medium based on artificial intelligence | |
| CN112652386A (en) | Triage data processing method and device, computer equipment and storage medium | |
| CN114647713A (en) | Knowledge graph question-answering method, device and storage medium based on virtual confrontation | |
| CN109992778B (en) | Resume document distinguishing method and device based on machine learning | |
| CN112487284A (en) | Bank customer portrait generation method, equipment, storage medium and device | |
| CN112732423B (en) | Process migration method, device, equipment and medium | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN115222112A (en) | Behavior prediction method, behavior prediction model generation method and electronic equipment | |
| CN113627514A (en) | Data processing method and device of knowledge graph, electronic equipment and storage medium | |
| CN112528662A (en) | Entity category identification method, device, equipment and storage medium based on meta-learning | |
| CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
| CN111752985A (en) | Method, device and storage medium for generating main portrait |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220920 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |