Method for using a medical intelligent bed cabinet

Abstract

The present invention discloses a method for using a medical smart bed cabinet, comprising: obtaining relevant information data of people using the bed cabinet in a fixed area, and classifying and storing the relevant data in a database; collecting feature data required by a sorting and classification model, and sorting and classifying the feature data using the sorting and classification model; performing feature matching based on the sorted and classified data with the classified data stored in the database. If the matching degree is higher than a preset value, the match is successful, and accompanying personnel are assigned. When an emergency event occurs in the fixed area, a screening algorithm is used to quickly screen out vacant bed cabinets and corresponding accompanying personnel, thereby realizing the intelligent application of medical bed cabinets. The present invention combines smart bed cabinets with accompanying services to achieve the rational allocation and full utilization of hospital bed resources, improve the quality of accompanying services, and reduce patient expenses.

Description

Technical Field

[0001] The present invention relates to the technical field of use of intelligent bed cabinets, and in particular to a method for using a medical intelligent bed cabinet. Background Art

[0002] In recent years, with the gradual advancement of urbanization and the increasing density of populations, the resulting problems in the allocation of medical resources have become increasingly prominent, particularly in the management and allocation of hospital beds. The current approach to hospital bed allocation relies on dedicated bedside nurses who manually allocate beds based on real-time patient and bed information. This human-led approach to resource allocation is prone to problems such as irrational allocation, which can worsen doctor-patient relationships and trigger serious social incidents.

[0003] Therefore, how to achieve the rational allocation and full utilization of hospital bed resources is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the existing technology cannot achieve the reasonable allocation and full utilization of hospital bed resources.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: obtaining relevant information data of people using bed cabinets in a fixed area, and classifying and storing the relevant data in a database; collecting feature data required by the sorting and classification model, and using the sorting and classification model to sort and classify the feature data; performing feature matching based on the sorted and classified data and the classified data stored in the database. If the matching degree is higher than a preset value, the match is successful, and accompanying personnel are assigned.

[0008] As a preferred solution of the method for using the medical intelligent bed cabinet described in the present invention, the relevant information data of people using the bed cabinet in the fixed area includes the bed cabinet location IP, code, application time, amount, and end time.

[0009] As a preferred solution of the method for using the medical intelligent bed cabinet described in the present invention, the feature data includes accompanying personnel dimension features, user dimension features, cross features, and distance features.

[0010] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, it further includes:

[0011] Characteristics of accompanying staff: scope of care, gender, age, cost, discount, performance, rating, and click-through rate;

[0012] User dimension features: user level, user attributes, and user client type;

[0013] Cross-features: users’ clicks, favorites, and purchases of caregivers;

[0014] Distance features: the distance between the user's real-time geographic location, frequently visited geographic locations, workplace, residence, and POIs;

[0015] The features are presented in the form of scalar data.

[0016] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, wherein: the characteristic value is normalized, and the normalized conversion function includes:

[0017]

[0018] Among them, X max is the maximum value of the sample data, X min is the minimum value of the sample data;

[0019] The conversion function is used to convert the eigenvalue into a continuous value between 0 and 1.

[0020] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, wherein: establishing the sorting classification model includes:

[0021] Use weighted algorithm to build ranking classification model:

[0022]

[0023] Among them, w i represents the weight of each sample, R represents the random number between 0 and 1 generated when traversing each sample, S i Indicates the sampling fraction of each sample;

[0024] The output samples are classified and sorted according to their sampling scores, and the samples are sorted from high to low according to the sampling scores, and a data set is constructed.

[0025] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, wherein: data preprocessing is performed on the feature matching data set, and the preprocessing includes:

[0026] Clean up missing values, format content, logical errors, and non-required information;

[0027] Performing feature construction, data classification and data quantification on the data set;

[0028] Perform data statistics on the transformed data and merge the data into a unified data storage;

[0029] The clustering-based outlier detection strategy is used to detect and eliminate samples that may still be abnormal in the data samples.

[0030] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, wherein: the feature matching includes:

[0031] Use similarity calculation strategy to perform feature matching on the data:

[0032] In the relationship between event A and event B, k01 represents the number of times event A and event B co-occur, k02 represents the number of times event B occurs but event A does not occur, k11 represents the number of times event A occurs but event B does not occur, and k12 represents the number of times neither event A nor event B occurs. Then:

[0033] logLikelihoodRatio=2*(matrixEntropy-rowEntropy-columnEntropy)

[0034] Among them, rowEntropy=entropy(k11,k12)+entropy(k21,k22)columnEntropy=entropy(k11,k21)+entropy(k12,k22)matrixEntropy=entropy(k11,k12,k21,k22), entropy represents the Shannon entropy of a system composed of several elements.

[0035] As a preferred solution of the method for using the medical intelligent bed cabinet of the present invention, the establishment of the screening algorithm includes:

[0036]

[0037] Among them, x1, x2, … x m represents the input variable, x i represents the i-th data, F represents the output variable, c i 、b i 、p i , x0 represents the model parameter, and i represents any one from 1 to m.

[0038] Beneficial effects of the present invention: The present invention combines the intelligent bed cabinet with the accompanying service, realizes the reasonable allocation and full utilization of hospital bed resources, improves the quality of accompanying service, and reduces patients' expenses. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0040] Figure 1 A schematic diagram of the basic flow of a method for using a medical intelligent bed cabinet provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0044] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0045] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0046] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0047] Example 1

[0048] Reference Figure 1 , as one embodiment of the present invention, provides a method for using a medical intelligent bed cabinet, comprising:

[0049] S1: Obtain relevant information data of people using bed cabinets in a fixed area, and classify and store the relevant data in a database;

[0050] It should be noted that the relevant information data of people using bed cabinets in a fixed area includes the bed cabinet location IP, code, application time, amount, and end time.

[0051] Among them, the scope of a fixed area is preset according to the demand and supply of different prefecture-level cities. The methods of obtaining the IP of the relevant location include but are not limited to Bluetooth, dynamic QR code, RFID electronic tags, and other data are directly generated by the electronic system.

[0052] Furthermore, the principle of classification storage is: within the same area, first sort by geographical location, then by application time, then by the difference between application time and end time, and finally by amount.

[0053] S2: Collect the feature data required by the sorting and classification model, and use the sorting and classification model to sort and classify the feature data;

[0054] It should be noted that the feature data includes the features of the accompanying personnel dimension, the features of the user dimension, the cross features, and the distance features.

[0055] Among them, the dimension characteristics of the accompanying staff include: scope of care, gender, age, cost, discount, performance, rating, and click rate;

[0056] User dimension features: user level, user attributes, and user client type;

[0057] Cross-features: users’ clicks, favorites, and purchases of caregivers;

[0058] Distance features: the distance between the user's real-time geographic location, frequently visited geographic locations, workplace, residence, and POIs;

[0059] Present features as scalar data.

[0060] The eigenvalues ​​are normalized, and the normalized conversion functions include:

[0061]

[0062] Among them, X max is the maximum value of the sample data, X min is the minimum value of the sample data;

[0063] The conversion function is used to convert the eigenvalues ​​into continuous values ​​between 0 and 1.

[0064] Furthermore, establishing a ranking classification model includes:

[0065] Use weighted algorithm to build ranking classification model:

[0066]

[0067] Among them, w i represents the weight of each sample, R represents the random number between 0 and 1 generated when traversing each sample, S i Indicates the sampling fraction of each sample;

[0068] Classify and sort according to the output sampling scores, sort from high to low according to the sampling scores, and build a data set.

[0069] Perform data preprocessing on the feature matching dataset, including:

[0070] Clean up missing values, format content, logical errors, and non-required information;

[0071] Perform feature construction, data classification and data quantification on the data set;

[0072] Perform data statistics on the transformed data and merge the data into a unified data storage;

[0073] The clustering-based outlier detection strategy is used to detect and eliminate samples that may still be abnormal in the data samples.

[0074] S3: Feature matching is performed based on the sorted and classified data and the classified data stored in the database. If the matching degree is higher than the preset value, the match is successful and the accompanying personnel are assigned;

[0075] It should be noted that feature matching includes:

[0076] Use similarity calculation strategy to perform feature matching on the data:

[0077] In the relationship between event A and event B, k01 represents the number of times event A and event B co-occur, k02 represents the number of times event B occurs but event A does not occur, k11 represents the number of times event A occurs but event B does not occur, and k12 represents the number of times neither event A nor event B occurs. Then:

[0078] logLikelihoodRatio=2*(matrixEntropy-rowEntropy-columnEntropy)

[0079] Among them, rowEntropy=entropy(k11,k12)+entropy(k21,k22)columnEntropy=entropy(k11,k21)+entropy(k12,k22)matrixEntropy=entropy(k11,k12,k21,k22), entropy represents the Shannon entropy of a system composed of several elements.

[0080] S4: When an emergency occurs in a fixed area, a screening algorithm is used to quickly screen out vacant bed cabinets and corresponding accompanying personnel, realizing the intelligent application of medical bed cabinets.

[0081] It should be noted that the establishment of the screening algorithm includes:

[0082]

[0083] Among them, x1, x2, … x m represents the input variable, x i represents the i-th data, F represents the output variable, c i 、b i 、p i , x0 represents the model parameter, and i represents any one from 1 to m.

[0084] Specifically, when an emergency event occurs in the area, vacant bed cabinets are screened out and the screened out bed cabinets are set to be in an available state. After the emergency event is over, the bed cabinets are set to be in an unavailable state.

[0085] When the bed cabinet is in an emergency available state, the accompanying personnel in the emergency vacant state are screened out, the screened accompanying personnel are notified to the designated area, and the accompanying personnel are located.

[0086] Example 2

[0087] This embodiment is another embodiment of the present invention. Unlike the first embodiment, this embodiment provides a verification test for the use of a medical intelligent bed cabinet. In order to verify and illustrate the technical effects adopted in this method, this embodiment adopts a traditional technical solution and the method of the present invention for comparative testing, and compares the test results by means of scientific demonstration to verify the real effect of this method.

[0088] Traditional technical solutions have a low level of intelligence and are therefore unable to quickly and accurately match each patient with a cost-effective accompanying caregiver. To verify that this method has higher matching speed and accuracy than traditional methods, this example uses both traditional caregiver selection methods and this method to conduct real-time comparisons of the caregiver matching accuracy of the simulated bed cabinet.

[0089] Test environment: The simulation platform simulated the demand for caregivers in different regions and the use of bedside cabinets. Traditional manual operation was used to test caregiver allocation and obtain test results. This method employed automated testing equipment and MATLAB software to implement simulation tests. The experimental results yielded simulation data, as shown in the table below.

[0090] Table 1: Comparison of experimental results.

[0091] Test samples Traditional methods Method of the present invention Matching speed ≥5 minutes 0.5s efficiency 60％ 99％ Accuracy 75％ 96％

[0092] It can be seen from the above table that the method of the present invention has higher matching accuracy than the traditional method, thereby reducing customer costs and improving customer satisfaction.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for using a medical intelligent bed cabinet, characterized in that: include: Obtain relevant information data of people using bed cabinets in a fixed area, and classify and store the relevant data in a database; Collecting feature data required by the sorting and classification model, and sorting and classifying the feature data using the sorting and classification model; Perform feature matching based on the sorted and classified data with the data stored in the database according to the classification. If the matching degree is higher than the preset value, the match is successful and the accompanying personnel are assigned; When an emergency occurs in the fixed area, a screening algorithm is used to quickly screen out vacant bed cabinets and corresponding accompanying personnel, thereby realizing the intelligent application of medical bed cabinets; The relevant information data of the person using the bed cabinet in the fixed area includes the bed cabinet location IP, code, application time, amount, and end time; The feature data includes features of the accompanying personnel dimension, features of the user dimension, cross features, and distance features; It also includes the following features: caregiver dimension: care scope, gender, age, cost, discount, performance, rating, click-through rate; user dimension: user level, user attributes, user client type; Cross-features: users’ clicks, favorites, and purchases of caregivers; Distance features: the distance between the user's real-time geographic location, frequently visited geographic locations, workplace, residence, and POIs; Presenting the features in the form of scalar data; The eigenvalues ​​are normalized, and the normalized conversion function includes: Among them, X max is the maximum value of the sample data, X min is the minimum value of the sample data; Converting the eigenvalue into a continuous value between 0 and 1 using the conversion function; Establishing the ranking classification model includes: Use weighted algorithm to build ranking classification model: Among them, w i represents the weight of each sample, R represents the random number between 0 and 1 generated when traversing each sample, S i Indicates the sampling fraction of each sample; Classify and sort according to the output sampling scores, sort from high to low according to the sampling scores, and construct a data set; Performing data preprocessing on the feature matching data set, the preprocessing includes: Clean up missing values, format content, logical errors, and non-required information; Performing feature construction, data classification and data quantification on the data set; Perform data statistics on the transformed data and merge the data into a unified data storage; Use clustering-based outlier detection strategies to detect and remove samples that may still be abnormal in the data samples; The feature matching includes performing feature matching on the user data using a similarity calculation strategy: In the relationship between event A and event B, k01 represents the number of times event A and event B co-occur, k02 represents the number of times event B occurs but event A does not occur, k11 represents the number of times event A occurs but event B does not occur, and k12 represents the number of times neither event A nor event B occurs. Then: logLikelihoodRatio=2*(matrixEntropy-rowEntropy-columnEntropy) Among them, rowEntropy=entropy(k11,k12)+entropy(k21,k22)columnEntropy=entropy(k11,k21)+entropy(k12,k22)matrixEntropy=entropy(k11,k12,k21,k22), entropy represents the Shannon entropy of a system composed of several elements; The establishment of the screening algorithm includes, Among them, x1, x2, … x m represents the input variable, x i represents the i-th data, F represents the output variable, c i 、b i 、p i , x0 represents the model parameter, and i represents any one from 1 to m.

Images