Intelligent interface-free data interaction system and method for assisting medical consultation

Abstract

The present invention discloses an intelligent interface-free data interaction system and method for auxiliary medical consultation, and relates to the field of data interaction processing. The present invention adjusts the parameters for data transmission without an interface, thereby providing an adjustment basis for subsequent adjustments to the amount of data transmitted, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission when the medical guidance robot to be optimized performs interface-free data transmission and sensitive data encryption, so that the medical guidance robot to be optimized is more efficient when performing interface-free data transmission; and then calculates the average growth rate and increased duration of patient information in the medical guidance robot to be optimized based on the future data volume set of the patient information, thereby providing an adjustment basis for subsequent adjustments to the amount of data transmitted, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission when the medical guidance robot to be optimized performs interface-free data transmission and sensitive data encryption.

Description

Technical Field

[0001] The present invention belongs to the field of data interaction processing, and in particular, relates to an intelligent interface-free data interaction system and method for assisting medical consultation. Background Art

[0002] The Chinese patent with announcement number CN115688760B discloses an intelligent medical guidance method, device, equipment and storage medium. First, multiple cluster centers need to be determined; these cluster centers are analyzed using a clustering algorithm to obtain clustering results; the similarity of the clustering results is calculated based on the registration information database to obtain multiple similarity calculation results; these similarity calculation results are sorted to filter out the top N results; the registration information is matched for the top N results to obtain corresponding N registration information; then, the patient information is classified and processed according to preset classification rules to determine the corresponding classification results; based on the classification results and the N registration information, path planning is performed through a preset path planning model to generate a target path and transmit it to the target terminal.

[0003] A Chinese patent with announcement number CN112035674B discloses a method, device, computer equipment and storage medium for obtaining guidance data. First, the main complaint information and user identity information sent by the receiving terminal are used to determine the user's consultation intention, and personalized consultation questions are generated and sent to the terminal; then, the terminal feeds back personalized replies based on the personalized consultation questions; based on the main complaint information, user identity information and personalized replies, the user's diagnostic path is obtained; finally, the user's guidance data is obtained based on the diagnostic path; the number of invalid dialogue rounds in the consultation can be reduced, and the efficiency of collecting guidance data can be improved.

[0004] The data generated by the current medical guide robots exist independently. The information obtained by patients after using the medical guide robots cannot be directly synchronized to the hospital's information system and electronic medical record system, resulting in the data not being fully utilized. Doctors are also required to conduct verbal inquiries when consulting patients, which increases the time of each consultation. Moreover, when the amount of patient data is large, if the optimal parameters for each data transmission cannot be determined, such as the amount of data transmitted each time and the number of threads allocated to data transmission and encryption of patient sensitive data, the transmission efficiency of each transmission of patient data to the hospital's information system and electronic medical record system will be low, making it impossible for the medical guide robots to synchronize data with the hospital's information system and electronic medical record system in a timely manner, resulting in the doctor being unable to obtain the patient's information from the system during the consultation. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes an intelligent interface-free data interaction system and method for auxiliary medical consultation to overcome the above-mentioned technical problems existing in the existing related art.

[0006] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0007] The present invention is an intelligent interface-free data interaction method for assisting medical consultation, comprising the following steps:

[0008] In view of the problems in the related art, the present invention proposes an intelligent interface-free data interaction system and method for auxiliary medical consultation to overcome the above-mentioned technical problems existing in the existing related art.

[0009] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0010] The present invention is an intelligent interface-free data interaction method for assisting medical consultation, comprising the following steps:

[0011] S1. Collect and preprocess the spoken and written information of multiple patients to obtain a second patient information data matrix and a third patient information data matrix; predict the amount of patient information data at a future time based on the amount of historical patient information data of the guidance robot to be optimized to obtain a set of future patient information data;

[0012] S2. Use the second patient information data matrix and the third patient information data matrix to build the final BERT model; calculate the average growth rate and the increased duration of the patient information in the guidance robot to be optimized according to the future data set of the patient information, and obtain the first average growth rate data and the first duration data;

[0013] S3. Cooperate with the final BERT model to set up the final total time-consuming mapping model by collecting patient information data and transmitting it to the information system and the electronic medical record system and counting the total transmission time, the initial transmission data volume for each data transmission without an interface, the initial transmission data volume for each data transmission without an interface, the number of threads allocated to data transmission and sensitive data encryption, the duration of the increase in patient data volume, and the average speed of the increase in data volume in each data volume statistical time period; then use the final total time-consuming mapping model and cooperate with the African vulture optimization algorithm to adjust the parameters of data transmission without an interface to obtain the final transmission data volume set, the final number of threads for data transmission, and the final number of threads for sensitive data encryption;

[0014] S4. In conjunction with the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption thread number set, and based on the first average growth rate data and the first duration data, adjust the transmission data volume, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission of the optimized medical guidance robot when performing interface-free data transmission and sensitive data encryption.

[0015] When the hospital is equipped with a guide robot, patients who come to the hospital can have a verbal conversation with the guide robot, and what is collected at this time is the patient's voice information; when the hospital is not equipped with a guide robot, patients who come to the hospital can fill in their information by scanning the WeChat code, and what is collected at this time is the patient's text information; therefore, this solution collects the oral and text information of multiple patients to provide a data basis for the subsequent construction of the final BERT model for extracting sensitive information from patient information; since voice information is often mixed with various noises, it is necessary to preprocess the input patient voice information so that the performance of the subsequent constructed final BERT model will be better; by constructing the final BERT model, before the subsequent data transmission through the interface-free method, an extraction model tool is provided to extract sensitive information from the patient information for encryption processing; by adjusting the parameters for data transmission without an interface, it is necessary to optimize the guide robot in the future. It provides a basis for adjusting the amount of data transmitted each time when performing interfaceless data transmission and sensitive data encryption, the number of data transmission threads and the number of sensitive data encryption threads, so that the guidance robot to be optimized is more efficient when performing interfaceless data transmission; by predicting the amount of patient information data in the guidance robot to be optimized at future moments, it provides a data basis for the subsequent calculation of the average growth rate of the amount of patient information data and the duration of data growth in the guidance robot to be optimized; since the average growth rate and the increase duration of patient information have a great influence on the efficiency of interfaceless data transmission, therefore, by calculating the average growth rate and the increase duration of patient information in the guidance robot to be optimized according to the future data volume set of patient information, it provides a basis for adjustment when adjusting the amount of data transmitted each time when performing interfaceless data transmission and sensitive data encryption, the number of data transmission threads and the number of sensitive data encryption threads in the guidance robot to be optimized.

[0016] Preferably, the S1 comprises the following steps:

[0017] S11, setting multiple field types that can reflect basic patient information to obtain a patient information field type set;

[0018] When equipped with a medical guide robot, in conjunction with the patient information field type set, the medical guide robot collects spoken information of multiple patients to obtain a first patient information data matrix; otherwise, in conjunction with the patient information field type set and using WeChat code scanning to collect text information filled in by multiple patients, a second patient information data matrix is ​​obtained;

[0019] According to the patient historical information data volume of the guidance robot to be optimized, the patient information data volume at the future moment is predicted to obtain the patient information future data volume set;

[0020] S12, performing denoising processing on each patient information data in the first patient information data matrix to obtain a processed patient information data matrix;

[0021] A pre-trained and tested Transformer model is used to perform speech-to-text operations on each patient's spoken information in the processed patient information data matrix to obtain a third patient information data matrix.

[0022] The patient information field types include name, gender, age, date of birth, ID number, contact information, current medical history, past medical history, surgical history, allergy history, height, weight, blood pressure, whether there are patients with similar diseases in the family, living habits, diet, smoking and drinking, etc.; by denoising each patient information data in the first patient information data matrix, the acquired patient's spoken information is clearer, which is convenient for subsequent speech-to-text operations.

[0023] Preferably, in S11, predicting the amount of patient information data at a future time according to the amount of patient historical information data of the medical guidance robot to be optimized, and obtaining a set of patient information future data includes the following steps:

[0024] S111, setting the to-be-optimized medical guidance robot and a plurality of historical data collection time points to obtain a historical data collection time point set; collecting data of the to-be-optimized medical guidance robot at each data collection time point according to the historical data collection time point set to obtain a patient information data set; obtaining the data volume of the patient information data at each time point in the patient information data set to obtain a patient information historical data volume set;

[0025] S112. Set multiple future data prediction time points to obtain a future data prediction time point set; predict the data volume of patient information at future moments in combination with the future data prediction time point set, the historical data collection time point set, and the patient information historical data volume set to obtain a future patient information data volume set.

[0026] Preferably, in S112, predicting the data volume of the patient information at the future moment in combination with the future data prediction time point set, the historical data collection time point set, and the patient information historical data volume set to obtain the patient information future data volume set includes the following steps:

[0027] S1121, constructing an initial SVM prediction model, a third training data ratio, and a test data ratio; dividing the patient information historical data set and the historical data collection time point set according to the third training data ratio and the test data ratio to obtain a patient information historical training data set, a historical data collection time point training set, a patient information historical test data set, a historical data collection time point test set, a patient information historical to-be-predicted data set, and a historical data collection time point to-be-predicted set;

[0028] S1122, setting a third training error threshold; inputting the patient information historical training data set and the historical data collection time point training set into the initial SVM prediction model for training; during the training process, when the training error is less than the third training error threshold, stopping the training to obtain a trained SVM prediction model; otherwise, continuing the training until the training error is less than the third training error threshold;

[0029] S1123, setting a third test accuracy threshold; inputting the patient information historical test data set and the historical data collection time point test set into the trained SVM prediction model for testing, and after the test is completed, obtaining the third test accuracy; when the third test accuracy is greater than or equal to the third test accuracy threshold, using the trained SVM prediction model as the final SVM prediction model; otherwise, returning to S422 to continue training the trained SVM prediction model until the third test accuracy is greater than or equal to the third test accuracy threshold;

[0030] S1124. In conjunction with the future data prediction time point set, the patient information historical data volume set to be predicted and the historical data collection time point set to be predicted are input into the final SVM prediction model for prediction to obtain the patient information future data volume set.

[0031] By training and testing the initial SVM prediction model using the patient information historical training data set, the historical data collection time point training set, the patient information historical test data set, and the historical data collection time point test set, the final SVM prediction model has a good prediction ability for the data volume of patient information in the guidance robot to be optimized.

[0032] Preferably, S2 comprises the following steps:

[0033] S21, merging the second patient information data matrix and the third patient information data matrix to obtain a merged patient information data matrix; and annotating the sensitive information part of each patient information data in the merged patient information data matrix to obtain an annotated data matrix;

[0034] Calculate the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot according to the future data volume set of the patient information, and obtain the first average growth rate data and the first duration data;

[0035] S22. Construct an initial BERT model; use the merged patient information data matrix and the labeled data matrix to train and test the initial BERT model to obtain a final BERT model.

[0036] By annotating the sensitive information in each patient information data in the merged patient information data matrix, training and test labels are provided for the subsequent construction of the final BERT model.

[0037] Preferably, in S21, calculating the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot according to the future data volume set of the patient information, and obtaining the first average growth rate data and the first duration data includes the following steps:

[0038] S211, merging the patient information future data set and the patient information historical data set to obtain a patient information comprehensive data set;

[0039] S212. Calculate the average growth rate and the increase duration of the patient information in the medical guidance robot to be optimized according to the comprehensive patient information data set, and obtain first average growth rate data and first duration data.

[0040] By calculating the average growth rate and increase duration of patient information in the guidance robot to be optimized, a basis is provided for setting the amount of data transmitted, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission when the guidance robot to be optimized performs interface-free data transmission and sensitive data encryption.

[0041] Preferably, the S22 comprises the following steps:

[0042] S221, setting a first training data ratio; performing data partitioning on the combined patient information data matrix and the labeled data matrix according to the first training data ratio to obtain a combined patient information training data matrix, a labeled training data matrix, a combined patient information test data matrix, and a labeled test data matrix;

[0043] S222, setting a first training error threshold; inputting the combined patient information training data matrix and the labeled training data matrix into the initial BERT model for training; during the training process, when the training error is less than the first training error threshold, stopping the training to obtain a trained BERT model; otherwise, continuing the training until the training error is less than the first training error threshold;

[0044] S223. Set a first test accuracy threshold; input the combined patient information test data matrix and the labeled test data matrix into the trained BERT model for testing; after the test is completed, obtain a first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy threshold, use the trained BERT model as the final BERT model; otherwise, return to S222 to continue training the trained BERT model until the first test accuracy is greater than or equal to the first test accuracy threshold.

[0045] By training and testing the initial BERT model using a merged patient information training data matrix, an annotated training data matrix, and a merged patient information test data matrix, an annotated test data matrix, respectively, the final BERT model has a more accurate ability to extract sensitive information from patient information.

[0046] Preferably, S3 comprises the following steps:

[0047] S31, setting multiple data volume statistical time periods from when the patient information data starts to increase to when the patient information data stops increasing, to obtain a data volume statistical time period set; evenly setting multiple time points of the same number in each data volume statistical time period in the data volume statistical time period set, to obtain a data volume collection time point matrix;

[0048] Calculate the duration of the increase in patient data volume according to the data volume collection time point matrix to obtain a duration data set;

[0049] S32, collecting data from the medical guidance robot or medical guidance system at each data collection time point according to the data volume collection time point matrix, to obtain a patient information data matrix; obtaining the data volume of the patient information data at each time point in the patient information data matrix, to obtain a patient information data volume matrix; calculating the average speed data of the data volume increase in each data volume statistical time period according to the patient information data volume matrix, to obtain a data volume average growth rate data set;

[0050] S33, setting the initial transmission data volume for each data transmission without an interface, obtaining an initial transmission data volume set, the number of threads allocated to data transmission and sensitive data encryption, and obtaining a data transmission initial thread number set and a sensitive data encryption initial thread number set respectively;

[0051] According to the patient information data volume matrix, a total time consumption data threshold for the transmission of patient information data in each data volume statistical time period is set to obtain a total time consumption threshold set; in conjunction with the final BERT model, the patient information data in the patient information data matrix is ​​transmitted to the information system and the electronic medical record system according to the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set, and the total transmission time consumption is calculated to obtain a total transmission time consumption data set;

[0052] S34, constructing a final total time consumption mapping model according to the total transmission time consumption data set, the initial transmission data volume set, the data transmission initial thread number set, the sensitive data encryption initial thread number set, the duration data set, and the data volume average growth rate data set;

[0053] S35. When there is a total transmission time consumption data in the total transmission time consumption data set that is greater than or equal to the total time consumption threshold corresponding to the corresponding total time consumption threshold set, the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period are adjusted until there is no total transmission time consumption data in the total transmission time consumption data set that is greater than or equal to the total time consumption threshold corresponding to the corresponding total time consumption threshold set, thereby obtaining a final transmission data volume set, a final number of threads for data transmission, and a final number of threads for sensitive data encryption;

[0054] Otherwise, there is no need to adjust the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period.

[0055] The period from the beginning of the increase of patient data in the medical guidance platform to the cessation of the increase of patient data is regarded as a statistical cycle, so that the statistical data is more complete; the average growth rate of patient data and the duration of growth have a great influence on the transmission volume of each transmission when the patient information is transmitted through no interface and the number of threads allocated to data transmission and data encryption. Therefore, this scheme calculates the average speed of data increase and the duration of data increase in each data volume statistical time period, which provides an adjustment basis for the subsequent iterative optimization of the transmission volume of each transmission when data is transmitted through no interface and the number of threads allocated to data transmission and data encryption.

[0056] Preferably, the S34 comprises the following steps:

[0057] S341. Construct an initial SVM classification model and set a second training data ratio; divide the total transmission time data set, the initial transmission data volume set, the initial number of threads for data transmission, the initial number of threads for sensitive data encryption, the duration data set, and the average data volume growth rate data set according to the second training data ratio to obtain a total transmission time training data set, an initial transmission data volume training set, an initial number of threads for data transmission, an initial number of threads for sensitive data encryption, a duration training data set, an average data volume growth rate training data set, a total transmission time test data set, an initial transmission data volume test set, an initial number of threads for data transmission, a test set for the initial number of threads for sensitive data encryption, a duration test data set, and an average data volume growth rate test data set;

[0058] S342, setting a second training error threshold; inputting the total transmission time training data set, the initial transmission data volume training set, the initial number of threads for data transmission training set, the initial number of threads for sensitive data encryption training set, the duration training data set, and the average data volume growth rate training data set into the initial SVM classification model for training; during the training process, when the training error is less than the second training error threshold, a trained SVM classification model is obtained; otherwise, the training is continued until the training error is less than the second training error threshold;

[0059] S343, set a second test accuracy threshold; input the total transmission time test data set, initial transmission data volume test set, data transmission initial thread number test set, sensitive data encryption initial thread number test set, duration test data set and data volume average growth rate test data set into the trained SVM classification model for testing; after the test is completed, obtain the second test accuracy; when the second test accuracy is greater than or equal to the second test accuracy threshold, use the trained SVM classification model as the final total time mapping model; otherwise, return to S342 to continue training the trained SVM classification model until the second test accuracy is greater than or equal to the second test accuracy threshold.

[0060] The initial SVM classification model is trained and tested using the total transmission time training data set, the initial transmission data volume training set, the initial number of data transmission threads training set, the initial number of sensitive data encryption threads training set, the duration training data set, the average data volume growth rate training data set, and the total transmission time test data set, the initial transmission data volume test set, the initial number of data transmission threads test set, the initial number of sensitive data encryption threads test set, the duration test data set, and the average data volume growth rate test data set, so that the final total time mapping model has a good mapping ability between the transmission data volume, the number of data transmission threads, the number of sensitive data encryption threads and the total transmission time data.

[0061] Preferably, adjusting the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period in S35 includes the following steps:

[0062] S351, constructing an African vulture population; setting the maximum number of iterations of the African vulture population to e 1 , the current number of iterations is e 2 ; The search space dimension of the African vulture population is 3-dimensional;

[0063] S352, setting the lower limit and upper limit of the value corresponding to the initial transmission data volume to be adjusted, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption to be adjusted, and obtaining the value interval of the initial transmission data volume to be adjusted, the value interval of the initial number of threads for data transmission to be adjusted, and the value interval of the initial number of threads for sensitive data encryption to be adjusted; setting the initial position of each African vulture in the African vulture population according to the value interval of the initial transmission data volume to be adjusted, the value interval of the initial number of threads for data transmission to be adjusted, and the value interval of the initial number of threads for sensitive data encryption to be adjusted, and obtaining an initial position matrix;

[0064] S354, constructing a fitness function of the African vulture population according to the total transmission time-consuming data set;

[0065] S355, start iteration, before iteration, the current number of iterations is e 2 Set to 1; calculate the first hunger rate during the first round of iteration and determine whether the current iteration process is in the mining stage or the survey stage based on the first hunger rate; and in the first round of iteration, cooperate with the final total time-consuming mapping model and use the fitness function of the African vulture population to calculate the fitness value of the initial position of each African vulture in the initial position matrix to obtain a first fitness value set; take the maximum fitness value in the first fitness value set and the corresponding initial position of the African vulture as the first global optimal fitness and the first global optimal position respectively; update the initial position of each African vulture in the initial position matrix according to the first global optimal fitness and the first global optimal position; after the update is completed, the current number of iterations e 2 Add 1 and enter the next iteration;

[0066] In each other round of iteration, the second hunger rate is calculated and it is determined whether the current iteration process is in the mining stage or the survey stage according to the second hunger rate; and the fitness value of the position of each African vulture updated in the previous round of iteration is calculated in conjunction with the final total time-consuming mapping model and the fitness function of the African vulture population to obtain a second fitness value set; the maximum fitness value in the second fitness value set and the corresponding initial position of the African vulture are used as the second global optimal fitness and the second global optimal position respectively; the position of each African vulture is updated according to the second global optimal fitness and the second global optimal position; after the update is completed, the current number of iterations is again calculated. e 2 Add 1 and enter the next iteration;

[0067] S356, when e 2 Greater than or equal to e 1 When , stop the iteration and get the final global optimal position; input the final global optimal position and the corresponding duration data and the average growth rate data of the data volume into the final total time consumption mapping model for mapping to get the adjusted total time consumption data; otherwise, continue to iterate until e 2 Greater than or equal to e 1 until the time;

[0068] S357. When the adjusted total time consumption data is less than the corresponding total time consumption threshold, the final global optimal position is used to replace the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set corresponding to the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set, to obtain the final transmission data volume set, the data transmission final thread number set, and the sensitive data encryption final thread number set;

[0069] Otherwise, return to S355 to continue iterating until the adjusted total time consumption data is less than the corresponding total time consumption threshold.

[0070] The African vulture optimization algorithm combines the two stages of exploration and development, which helps to both widely search the solution space during the search process and conduct a detailed search after finding a better area, thereby improving the global search capability and the local search capability; therefore, in this scheme, the African vulture optimization algorithm is used to perform multiple iterations of the data transmission amount of the guide robot during interface-free data transmission and the number of threads allocated to data transmission and data encryption, and the total time consumption data of data transmission is used as a measure of the quality of the found solution; therefore, as the iteration proceeds, the time consumption of the data transmission of the guide robot in each statistical cycle becomes smaller and smaller, indicating that the data transmission amount each time and the number of threads allocated to data transmission and data encryption obtained by the iteration are more in line with the current data transmission needs.

[0071] Preferably, S4 comprises the following steps:

[0072] S41, merging the duration data set and the data volume average growth rate data set to obtain a first merged data set; and then combining the first average growth rate data and the first duration data to obtain a second merged data set;

[0073] Calculating the Euclidean distance between each merged data in the second merged data set and the first merged data set to obtain a Euclidean distance data set;

[0074] S42. In conjunction with the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption final thread number set, the final transmission data volume, the final data transmission thread number, and the final sensitive data encryption thread number corresponding to the minimum Euclidean distance in the Euclidean distance data set are used as the transmission data volume, the data transmission thread number, and the sensitive data encryption thread number for each transmission of the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption; the guidance robot to be optimized transmits patient information data to the information system and the electronic medical record system through interface-free data transmission.

[0075] Since the corresponding average growth rate data and growth duration data of similar patient data volumes have similar data volumes transmitted without interfaces, the number of data transmission threads, and the number of sensitive data encryption threads, the Euclidean distance between each merged data in the second merged data set and the first merged data set is calculated to find the data in the first merged data set that is most similar to the second merged data set. The previously optimized data volumes transmitted without interfaces, the number of data transmission threads, and the number of sensitive data encryption threads corresponding to the most similar data are used as the data volumes transmitted without interfaces, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission of the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption. This ensures that the total time spent by the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption is minimized.

[0076] An intelligent interface-free data interaction system for auxiliary medical consultation includes a patient data collection module, a preprocessing module, a sensitive information extraction information model construction module, a first patient information data quantity feature calculation module, an interface-free transmission data setting collection module, a total time consumption mapping model construction module, a first interface-free transmission data adjustment module, a prediction module, a second patient information data quantity feature calculation module and a second interface-free transmission data adjustment module.

[0077] The present invention has the following beneficial effects:

[0078] 1. The present invention adjusts the parameters for data transmission without an interface, thereby providing an adjustment basis for the subsequent adjustment of the amount of data transmitted, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission when the guidance robot to be optimized performs interface-free data transmission and sensitive data encryption, so that the guidance robot to be optimized is more efficient when performing interface-free data transmission; then, the average growth rate and the increase duration of the patient information in the guidance robot to be optimized are calculated based on the future data volume set of the patient information, which provides a basis for the subsequent adjustment of the amount of data transmitted, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission when the guidance robot to be optimized performs interface-free data transmission and sensitive data encryption, thereby achieving efficient data synchronization between the guidance robot and the information system and the electronic medical record system.

[0079] 2. In the present invention, the African vulture optimization algorithm is used to perform multiple iterations to optimize the data transmission amount of the medical guide robot during interface-free data transmission and the number of threads allocated to data transmission and data encryption. As the iterations proceed, the time consumed by the medical guide robot for data transmission in each statistical cycle becomes shorter and shorter.

[0080] 3. In the present invention, the amount of data transmitted without an interface, the number of data transmission threads, and the number of sensitive data encryption threads that have been optimized for each time corresponding to the data that is most similar to the second merged data set are used as parameters for the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption, so that the total time consumed for interface-free data transmission and sensitive data encryption is minimized.

[0081] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0083] Figure 1 It is a flow chart of the intelligent data interaction method without interface for assisting medical consultation of the present invention;

[0084] Figure 2 The figure is a schematic diagram of the process of assisting the medical consultation according to the present invention. DETAILED DESCRIPTION

[0085] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0086] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0087] Embodiment 1

[0088] This embodiment is an intelligent method for data interaction without an interface for assisting medical consultation, comprising the following steps:

[0089] S1. Collect and preprocess the spoken and written information of multiple patients to obtain a second patient information data matrix and a third patient information data matrix; predict the amount of patient information data at a future time based on the amount of historical patient information data of the guidance robot to be optimized to obtain a set of future patient information data;

[0090] The S1 comprises the following steps:

[0091] S11. Set multiple field types that can reflect the basic information of the patient, and obtain a set of patient information field types. , a i Indicates the setting i Patient information field types, Indicates the total number of patient information field types that are set;

[0092] When equipped with a medical guidance robot, the patient information field type set , the medical guidance robot collects oral information of multiple patients to obtain a first patient information data matrix; otherwise, in accordance with the patient information field type set The text information filled in by multiple patients was collected by scanning the WeChat code to obtain the second patient information data matrix ; as follows, ;in, Indicates the collected i The patient's j Text information of the patient information field type, Indicates the total number of patients collected;

[0093] According to the patient historical information data volume of the guidance robot to be optimized, the patient information data volume at the future moment is predicted to obtain the patient information future data volume set;

[0094] In S11, the amount of patient information data at a future time is predicted based on the amount of patient historical information data of the guidance robot to be optimized, and obtaining a set of patient information future data includes the following steps:

[0095] S111, set the guidance robot to be optimized and multiple historical data collection time points to obtain a historical data collection time point set; collect data of the guidance robot to be optimized at each data collection time point according to the historical data collection time point set to obtain a patient information data set; obtain the data volume of the patient information data at each time point in the patient information data set to obtain a patient information historical data volume set , f i Indicates the first i The amount of historical data of patient information collected at each data collection time point, Indicates the total number of data collection time points in the historical data collection time point set;

[0096] S112, setting multiple future data prediction time points to obtain a future data prediction time point set; matching the future data prediction time point set, the historical data collection time point set, and the patient information historical data volume set Predict the amount of patient information data at future moments and obtain the future data volume set of patient information , Indicates the predicted i The amount of patient information at each future data prediction time point, represents the total number of future data prediction time points in the future data prediction time point set;

[0097] S112 cooperates with the future data prediction time point set, the historical data collection time point set and the patient information historical data volume set Predict the amount of patient information data at future moments and obtain the future data volume set of patient information The following steps are involved:

[0098] S1121, constructing an initial SVM prediction model, a third training data ratio and a test data ratio; and calculating the patient information historical data set according to the third training data ratio and the test data ratio. and divide the data according to the historical data collection time point set to obtain the patient information historical training data set, the historical data collection time point training set, the patient information historical test data set, the historical data collection time point test set, the patient information historical to-be-predicted data set, and the historical data collection time point to-be-predicted set;

[0099] S1122, setting a third training error threshold; inputting the patient information historical training data set and the historical data collection time point training set into the initial SVM prediction model for training; during the training process, when the training error is less than the third training error threshold, stopping the training to obtain a trained SVM prediction model; otherwise, continuing the training until the training error is less than the third training error threshold;

[0100] S1123, setting a third test accuracy threshold; inputting the patient information historical test data set and the historical data collection time point test set into the trained SVM prediction model for testing, and after the test is completed, obtaining the third test accuracy; when the third test accuracy is greater than or equal to the third test accuracy threshold, using the trained SVM prediction model as the final SVM prediction model; otherwise, returning to S422 to continue training the trained SVM prediction model until the third test accuracy is greater than or equal to the third test accuracy threshold;

[0101] S1124, input the patient information historical data volume set to be predicted and the historical data collection time point set to be predicted into the final SVM prediction model for prediction in conjunction with the future data prediction time point set to obtain the patient information future data volume set ;

[0102] S12: Perform denoising on each patient information data in the first patient information data matrix to obtain a processed patient information data matrix. ;as follows, ;

[0103] in, Indicates the collected i The patient'sj Speech information after denoising speech information of a patient information field type;

[0104] The pre-trained and tested Transformer model is used to process the processed patient information data matrix Perform speech-to-text conversion on each patient's spoken information to obtain the third patient information data matrix ;as follows, ;

[0105] in, Express Patient text information data obtained after text conversion;

[0106] S2. Use the second patient information data matrix and the third patient information data matrix to build the final BERT model; calculate the average growth rate and the increased duration of the patient information in the guidance robot to be optimized according to the future data set of the patient information, and obtain the first average growth rate data and the first duration data;

[0107] The S2 comprises the following steps:

[0108] S21, the second patient information data matrix And the third patient information data matrix Merging to obtain a merged patient information data matrix; annotating the sensitive information part of each patient information data in the merged patient information data matrix to obtain an annotated data matrix;

[0109] Calculate the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot according to the future data volume set of the patient information, and obtain the first average growth rate data and the first duration data;

[0110] In S21, the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot are calculated according to the future data volume set of the patient information, and the first average growth rate data and the first duration data are obtained, which include the following steps:

[0111] S211, the patient information future data set And patient information historical data set Merge to obtain a comprehensive data set of patient information , g i represents the first step after merging the future patient information data set and the historical patient information data set. i The amount of patient information data;

[0112] S212, according to the patient information comprehensive data set Calculate the average growth rate and increase duration of patient information in the guidance robot to be optimized to obtain the first average growth rate data And the first duration data The calculation formulas are as follows: ; ; In the formula, , They represent the first i and i -1 time point corresponding to the amount of patient information data; , They respectively represent the time points corresponding to the last and first patient information data in the patient information comprehensive data set;

[0113] S22, constructing an initial BERT model; using the combined patient information data matrix and the labeled data matrix to train and test the initial BERT model to obtain a final BERT model;

[0114] The S22 comprises the following steps:

[0115] S221, setting a first training data ratio; performing data partitioning on the combined patient information data matrix and the labeled data matrix according to the first training data ratio to obtain a combined patient information training data matrix, a labeled training data matrix, a combined patient information test data matrix, and a labeled test data matrix;

[0116] S222, setting a first training error threshold; inputting the combined patient information training data matrix and the labeled training data matrix into the initial BERT model for training; during the training process, when the training error is less than the first training error threshold, stopping the training to obtain a trained BERT model; otherwise, continuing the training until the training error is less than the first training error threshold;

[0117] S223, setting a first test accuracy threshold; inputting the combined patient information test data matrix and the labeled test data matrix into the trained BERT model for testing; after the test is completed, obtaining a first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy threshold, using the trained BERT model as the final BERT model; otherwise, returning to S222 to continue training the trained BERT model until the first test accuracy is greater than or equal to the first test accuracy threshold;

[0118] S3. Cooperate with the final BERT model to set the parameters for data transmission without interface, build the final total time consumption mapping model and adjust the parameters for data transmission without interface, and obtain the final set of transmitted data volume, the final set of threads for data transmission, and the final set of threads for sensitive data encryption;

[0119] The S3 comprises the following steps:

[0120] S31, according to the patient information data from the beginning to the end of the increase of the patient information data set a plurality of data volume statistical time periods to obtain a data volume statistical time period set , b i Indicates the setting i Data volume statistics time period, Indicates the total number of the set data volume statistics time period; In each data volume statistical time period, multiple time points of the same number are evenly set to obtain the data volume collection time point matrix ;as follows, ;in, Indicated in i The first set in the data volume statistics time period j The data collection time point, Indicates the total number of data collection time points set within each data statistics time period;

[0121] A matrix of time points is collected according to the data volume Calculate the duration of the increase in patient data volume to obtain a duration data set , Indicated in i The duration of the data volume statistics time period, ;

[0122] S32, collecting a time point matrix according to the data volume Collect data from the medical guidance robot or medical guidance system at each data collection time point to obtain a patient information data matrix; obtain the data volume of the patient information data at each time point in the patient information data matrix to obtain a patient information data volume matrix c ;as follows, ;

[0123] in, c ij Indicated in i The first set in the data volume statistics time period j The amount of patient information collected at each data collection time point;

[0124] According to the patient information data volume matrixc Calculate the average speed of data increase during each data volume statistical period to obtain the average data volume growth rate data set , Indicated in i The average growth rate of patient information data within the data volume statistical period; the calculation formula is as follows: ;

[0125] S33, setting the initial transmission data volume for each data transmission without an interface, and obtaining an initial transmission data volume set , the number of threads allocated to data transmission and sensitive data encryption, and the initial number of threads for data transmission are obtained respectively And the number of initial threads for sensitive data encryption , , , Respectively expressed in i The initial data volume transmitted, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption set for each data volume statistical time period;

[0126] According to the patient information data volume matrix c Set the total time consumption data threshold for patient information data transmission in each data volume statistical time period, and obtain the total time consumption threshold set , Indicates the setting i The total time consumption data threshold of patient information data transmission in the data volume statistical time period is used; in conjunction with the final BERT model, the patient information data in the patient information data matrix is ​​transmitted to the information system and the electronic medical record system according to the initial transmission data volume set, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption, and the total transmission time consumption is calculated to obtain the total transmission time consumption data set. , d i Indicates i The total time consumed in transmitting patient information data within the statistical time period;

[0127] S34, constructing a final total time consumption mapping model according to the total transmission time consumption data set, the initial transmission data volume set, the data transmission initial thread number set, the sensitive data encryption initial thread number set, the duration data set, and the data volume average growth rate data set;

[0128] S35, when the total transmission time consumption data set There is a total transmission time data greater than or equal to the corresponding total time threshold set When the total time consumption threshold corresponding to the data volume statistics time period is reached, the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption are adjusted until the total transmission time consumption data set reaches There is no total transmission time data greater than or equal to the corresponding total time threshold set The corresponding total time threshold is reached, and the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption thread number set are obtained;

[0129] Otherwise, there is no need to adjust the initial transmission data volume, the initial number of data transmission threads, and the initial number of sensitive data encryption threads corresponding to the data volume statistical time period;

[0130] In S35, adjusting the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period includes the following steps:

[0131] S351. Build African vulture populations , Indicates the first i An African vulture, represents the size of the African vulture population; sets the maximum number of iterations of the African vulture population to e 1 , the current number of iterations is e 2 ; The search space dimension of the African vulture population is 3-dimensional;

[0132] S352: Set the lower and upper limits of the initial transmission data volume to be adjusted, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption, and obtain the value range of the initial transmission data volume to be adjusted. , The range of values ​​for the number of initial threads for data transmission to be adjusted And the range of the initial number of threads for sensitive data encryption to be adjusted ; , They represent the lower limit and upper limit of the initial transmission data volume to be adjusted, , They represent the lower limit and upper limit of the number of initial threads for data transmission to be adjusted. , They respectively represent the lower limit and upper limit of the number of initial threads for sensitive data encryption to be adjusted;

[0133] According to the value range of the initial transmission data amount to be adjusted , The range of values ​​for the number of initial threads for data transmission to be adjusted And the range of the initial number of threads for sensitive data encryption to be adjusted Set the initial position of each African vulture in the African vulture population to obtain the initial position matrix ;as follows, ;

[0134] in, , , Respectively represent the first i The components of the initial position of an African vulture in the dimensions of the amount of initial data transmission to be adjusted, the number of initial threads for data transmission to be adjusted, and the number of initial threads for sensitive data encryption to be adjusted; the calculation formulas are as follows: ; ; ; In the formula, rand i1 , rand i2 , rand i3 Respectively for , , Generate a random number between 0 and 1;

[0135] S354: According to the total transmission time consumption data set Constructing a fitness function for an African vulture population ;as follows, ;

[0136] S355, start iteration, before iteration, the current number of iterations is e 2 Set to 1; calculate the first hunger rate during the first round of iteration and determine whether the current iteration process is in the mining stage or the survey stage based on the first hunger rate; and in the first round of iteration, cooperate with the final total time mapping model and adopt the fitness function of the African vulture population Calculate the initial position matrix The fitness value of the initial position of each African vulture in the first fitness value set is obtained to obtain a first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position of the African vulture are respectively used as the first global optimal fitness and the first global optimal position; the initial position matrix is ​​adjusted according to the first global optimal fitness and the first global optimal position The initial position of each African vulture in is updated; after the update is completed, the current number of iterations is e 2 Add 1 and enter the next iteration;

[0137] In each other round of iteration, the second hunger rate is calculated and the current iteration process is determined to be in the mining stage or the survey stage according to the second hunger rate; and the fitness function of the African vulture population is adopted in conjunction with the final total time-consuming mapping model. Calculate the fitness value of the position of each African vulture updated in the previous round of iterations to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding initial position of the African vulture as the second global optimal fitness and the second global optimal position respectively; update the position of each African vulture according to the second global optimal fitness and the second global optimal position; after the update is completed, the current number of iterations is again e 2 Add 1 and enter the next iteration;

[0138] S356, when e 2 Greater than or equal to e 1 When , stop the iteration and get the final global optimal position; input the final global optimal position and the corresponding duration data and the average growth rate data of the data volume into the final total time consumption mapping model for mapping to get the adjusted total time consumption data; otherwise, continue to iterate until e 2 Greater than or equal to e 1 until the time;

[0139] S357. When the adjusted total time consumption data is less than the corresponding total time consumption threshold, the final global optimal position is used to replace the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set corresponding to the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set, to obtain the final transmission data volume set, the data transmission final thread number set, and the sensitive data encryption final thread number set;

[0140] Otherwise, return to S355 and continue to iterate until the adjusted total time consumption data is less than the corresponding total time consumption threshold;

[0141] S4, adjusting the transmission data volume, the number of data transmission threads, and the number of sensitive data encryption threads for each transmission of the optimized medical guidance robot when performing interface-free data transmission and sensitive data encryption in accordance with the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption thread number set, and according to the first average growth rate data and the first duration data;

[0142] The S4 comprises the following steps:

[0143] S41, merging the duration data set and the data volume average growth rate data set to obtain a first merged data set , h i1 , h i2 Respectively represent the average growth rate of the data volume in the data set i The average growth rate data of the data volume and the duration data set i duration data; then the first average speed data And the first duration data Combine to get the second merged data set ;

[0144] Calculate the second merged data set The Euclidean distance between each merged data in the first merged data set is calculated to obtain a Euclidean distance data set;

[0145] S42. In conjunction with the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption final thread number set, the final transmission data volume, the final data transmission thread number, and the final sensitive data encryption thread number corresponding to the minimum Euclidean distance in the Euclidean distance data set are used as the transmission data volume, the data transmission thread number, and the sensitive data encryption thread number for each transmission of the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption; the guidance robot to be optimized transmits patient information data to the information system and the electronic medical record system through interface-free data transmission.

[0146] Embodiment 2

[0147] This embodiment discloses an intelligent non-interface data interaction system for assisting medical consultation, which can implement the method of the above embodiment, including a patient data collection module, a preprocessing module, a sensitive information extraction information model construction module, a first patient information data volume feature calculation module, a non-interface transmission data setting collection module, a total time consumption mapping model construction module, a first non-interface transmission data adjustment module, a prediction module, a second patient information data volume feature calculation module and a second non-interface transmission data adjustment module;

[0148] The patient data collection module is used to collect spoken information and text information of multiple patients to obtain a first patient information data matrix and a second patient information data matrix;

[0149] The preprocessing module is used to perform denoising and text conversion on the first patient information data matrix to obtain a third patient information data matrix;

[0150] The sensitive information extraction information model construction module is used to construct a final BERT model using the second patient information data matrix and the third patient information data matrix;

[0151] The first patient information data volume feature calculation module is used to collect the duration of the increase in patient data volume and the average growth rate of the patient information data in multiple statistical time periods to obtain a duration data set and a data volume average growth rate data set;

[0152] The interface-free transmission data setting collection module is used to cooperate with the final BERT model to set the initial transmission data volume for data transmission without an interface, the number of threads allocated to data transmission and sensitive data encryption, and the total time consumed for collection, and obtain an initial transmission data volume set, a data transmission initial number of threads set, a sensitive data encryption initial number of threads set, and a total transmission time data set;

[0153] The total time consumption mapping model construction module is used to construct a final total time consumption mapping model using a total transmission time consumption data set, an initial transmission data volume set, an initial data transmission thread number set, an initial sensitive data encryption thread number set, a duration data set, and an average data volume growth rate data set;

[0154] The first interface-free transmission data adjustment module is used to adjust the initial transmission data volume set, the initial data transmission thread number set, and the sensitive data encryption initial thread number set according to the transmission total time consumption data set and in cooperation with the final total time consumption mapping model to obtain the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption final thread number set;

[0155] The prediction module is used to predict the amount of patient information data at a future time according to the amount of patient historical information data of the guidance robot to be optimized, and obtain a set of future patient information data;

[0156] The second patient information data volume feature calculation module is used to calculate the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot according to the future patient information data volume set, and obtain the first average growth rate data and the first duration data;

[0157] The second interfaceless transmission data adjustment module is used to adjust the amount of transmission data, the number of data transmission threads and the number of sensitive data encryption threads for each transmission of the optimized medical guidance robot when performing interfaceless data transmission and sensitive data encryption according to the first average growth rate data and the first duration data.

[0158] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0159] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. An intelligent interface-free data interaction method for assisting medical consultation, characterized in that: The following steps are involved: S1. Collect and preprocess the spoken and written information of multiple patients to obtain a second patient information data matrix and a third patient information data matrix; predict the amount of patient information data at a future time based on the amount of historical patient information data of the guidance robot to be optimized to obtain a set of future patient information data; S2. Use the second patient information data matrix and the third patient information data matrix to build the final BERT model; calculate the average growth rate and the increased duration of the patient information in the guidance robot to be optimized according to the future data set of the patient information, and obtain the first average growth rate data and the first duration data; S3, cooperate with the final BERT model to set up the final total time-consuming mapping model by collecting patient information data and transmitting it to the information system and the electronic medical record system and counting the total transmission time, the initial transmission data volume for each data transmission without an interface, the number of threads allocated to data transmission and sensitive data encryption, the duration of the increase in patient data volume, and the average speed data of the data volume increase in each data volume statistical time period, and obtain the duration data set and the data volume average growth rate data set; then use the final total time-consuming mapping model and cooperate with the African vulture optimization algorithm to adjust the parameters of the data transmission without an interface to obtain the final global optimal position; the final global optimal position and the corresponding duration data and the average data volume growth rate data are input into the final total time-consuming mapping model for mapping to obtain the adjusted total time data; When the adjusted total time consumption data is less than the corresponding total time consumption threshold, the final global optimal position is used to replace the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set corresponding to the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set, to obtain the final transmission data volume set, the data transmission final thread number set, and the sensitive data encryption final thread number set; S4, merging the duration data set and the data volume average growth rate data set to obtain a first merged data set; Then combining the first average speed data and the first duration data to obtain a second combined data set; Calculating the Euclidean distance between each merged data in the second merged data set and the first merged data set to obtain a Euclidean distance data set; In conjunction with the final transmission data volume set, the final data transmission thread number set, and the sensitive data encryption final thread number set, the final transmission data volume, the final data transmission thread number, and the sensitive data encryption thread number corresponding to the minimum Euclidean distance in the Euclidean distance data set are used as the transmission data volume, the data transmission thread number, and the sensitive data encryption thread number for each transmission of the guidance robot to be optimized when performing interface-free data transmission and sensitive data encryption; the guidance robot to be optimized transmits patient information data to the information system and the electronic medical record system through interface-free data transmission.

2. The intelligent interface-free data interaction method for assisting medical consultation according to claim 1 is characterized in that: The S1 comprises the following steps: S11. Collect spoken and text information of multiple patients and perform denoising and speech-to-text operations to obtain a second patient information data matrix and a third patient information data matrix; and predict the amount of patient information data at a future time to obtain a future patient information data set.

3. The intelligent interface-free data interaction method for assisting medical consultation according to claim 2 is characterized by: The speech-to-text operation in S11 uses a pre-trained and tested Transformer model.

4. The intelligent interface-free data interaction method for assisting medical consultation according to claim 3 is characterized in that: In S11, the amount of patient information data at a future time is predicted to obtain a set of future patient information data, which includes the following steps: S111, setting a to-be-optimized medical guidance robot and obtaining the amount of patient information data at multiple historical time points in the to-be-optimized medical guidance robot to obtain a patient information historical data set; S112. Predict the data volume of the patient information at a future time in conjunction with the patient information historical data volume set to obtain a patient information future data volume set.

5. The intelligent interface-free data interaction method for assisting medical consultation according to claim 4 is characterized by: In the S112, the SVM prediction model is used to predict the data volume of the patient information at the future time.

6. The intelligent interface-free data interaction method for assisting medical consultation according to claim 5, characterized in that: The S2 comprises the following steps: S21, annotating the sensitive information part of each patient information data in the second patient information data matrix and the third patient information data matrix and constructing a final BERT model; S22. Calculate the average growth rate and the increase duration of the patient information in the to-be-optimized medical guidance robot according to the future data volume set of the patient information, and obtain first average growth rate data and first duration data.

7. The intelligent interface-free data interaction method for assisting medical consultation according to claim 6 is characterized in that: The S3 comprises the following steps: S31, setting multiple data volume statistical time periods from when the patient information data starts to increase to when the patient information data stops increasing, to obtain a data volume statistical time period set; evenly setting multiple time points of the same number in each data volume statistical time period in the data volume statistical time period set, to obtain a data volume collection time point matrix; Calculate the duration of the increase in patient data volume according to the data volume collection time point matrix to obtain a duration data set; S32, collecting data from the medical guidance robot or medical guidance system at each data collection time point according to the data volume collection time point matrix, to obtain a patient information data matrix; obtaining the data volume of the patient information data at each time point in the patient information data matrix, to obtain a patient information data volume matrix; calculating the average speed data of the data volume increase in each data volume statistical time period according to the patient information data volume matrix, to obtain a data volume average growth rate data set; S33, setting the initial transmission data volume for each data transmission without an interface, obtaining an initial transmission data volume set, the number of threads allocated to data transmission and sensitive data encryption, and obtaining a data transmission initial thread number set and a sensitive data encryption initial thread number set respectively; According to the patient information data volume matrix, a total time consumption data threshold for the transmission of patient information data in each data volume statistical time period is set to obtain a total time consumption threshold set; in conjunction with the final BERT model, the patient information data in the patient information data matrix is ​​transmitted to the information system and the electronic medical record system according to the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set, and the total transmission time consumption is calculated to obtain a total transmission time consumption data set; S34, constructing a final total time consumption mapping model according to the total transmission time consumption data set, the initial transmission data volume set, the data transmission initial thread number set, the sensitive data encryption initial thread number set, the duration data set, and the data volume average growth rate data set; S35. When there is a total transmission time consumption data in the total transmission time consumption data set that is greater than or equal to the total time consumption threshold corresponding to the corresponding total time consumption threshold set, the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period are adjusted until there is no total transmission time consumption data in the total transmission time consumption data set that is greater than or equal to the total time consumption threshold corresponding to the corresponding total time consumption threshold set, thereby obtaining a final transmission data volume set, a final number of threads for data transmission, and a final number of threads for sensitive data encryption; Otherwise, there is no need to adjust the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period.

8. The intelligent interface-free data interaction method for assisting medical consultation according to claim 7, characterized in that: In S35, adjusting the initial transmission data volume, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption corresponding to the data volume statistical time period includes the following steps: S351, constructing an African vulture population; setting the maximum number of iterations of the African vulture population to e 1 , the current number of iterations is e 2 ; S352, setting the lower limit and upper limit of the value corresponding to the initial transmission data volume to be adjusted, the initial number of threads for data transmission, and the initial number of threads for sensitive data encryption to be adjusted, and obtaining the value interval of the initial transmission data volume to be adjusted, the value interval of the initial number of threads for data transmission to be adjusted, and the value interval of the initial number of threads for sensitive data encryption to be adjusted; setting the initial position of each African vulture in the African vulture population according to the value interval of the initial transmission data volume to be adjusted, the value interval of the initial number of threads for data transmission to be adjusted, and the value interval of the initial number of threads for sensitive data encryption to be adjusted, and obtaining an initial position matrix; S354, constructing a fitness function of the African vulture population according to the total transmission time-consuming data set; S355, start iteration, calculate the second hunger rate in each round of iteration and determine whether the current iteration process is in the mining stage or the survey stage according to the second hunger rate; and cooperate with the final total time-consuming mapping model and use the fitness function of the African vulture population to calculate the fitness value of the position of each African vulture updated in the previous round of iteration and update the position of each African vulture; S356, when e 2 Greater than or equal to e 1 When , stop the iteration and get the final global optimal position; input the final global optimal position and the corresponding duration data and the average growth rate data of the data volume into the final total time consumption mapping model for mapping to get the adjusted total time consumption data; otherwise, continue to iterate until e 2 Greater than or equal to e 1 until the time; S357. When the adjusted total time consumption data is less than the corresponding total time consumption threshold, the final global optimal position is used to replace the initial transmission data volume set, the data transmission initial thread number set, and the sensitive data encryption initial thread number set corresponding to the initial transmission data volume, the data transmission initial thread number set, and the sensitive data encryption initial thread number set to obtain the final transmission data volume set, the data transmission final thread number set, and the sensitive data encryption final thread number set; otherwise, return to S355 to continue iterating until the adjusted total time consumption data is less than the corresponding total time consumption threshold.

9. A system for implementing the intelligent interface-free data interaction method for assisting medical consultation as described in any one of claims 1 to 8.

Images