CN118299022A - Informationized management system and method for surgical equipment - Google Patents

Abstract

The invention relates to an informatization management system and method for surgical equipment, and relates to the technical field of informatization management. The method comprises the following steps: dividing the acquired historical use data based on the first time scale and the second time scale, and counting the use frequency to obtain a second scale use frequency time sequence input vector; then, extracting features by using a frequency time domain feature extractor based on a deep neural network, and processing by using a multi-scale feature fusion device to obtain multi-scale frequency time sequence associated features; and determining a usage frequency short-time predictor to obtain a predicted value based on the multi-scale usage frequency time sequence association characteristic, and determining whether to generate an early purchase prompt. Therefore, the prediction of the requirements of the surgical equipment and the optimization of resource planning can be realized, so that the purchase of the surgical equipment with higher requirements can be performed in advance, and the medical service quality can be improved.

Description

Surgical equipment information management system and method

Technical Field

The present invention relates to the technical field of information management, and in particular to an information management system and method for surgical equipment.

Background technique

Surgical equipment plays a vital role in the medical field. They are the tools used by doctors to perform surgical operations, which directly affect the progress and results of the operation. High-quality surgical equipment can not only improve the success rate and efficiency of the operation, but also reduce the risks and complications during the operation. With the continuous advancement of medical technology and the growth of medical needs, the types and scale of surgical equipment in hospitals are various. How to effectively manage and maintain these surgical equipment, so as to effectively carry out resource planning and procurement planning to meet the hospital's surgical needs, is one of the challenges faced by hospital managers.

Traditionally, hospitals usually manage surgical equipment based on experience, routine maintenance and regular procurement plans. This approach lacks detailed data analysis on the use of surgical equipment and cannot accurately understand the actual use of the equipment and demand changes. As a result, it is often difficult for hospitals to reasonably plan the resource allocation of surgical equipment and make corresponding purchases, resulting in waste of resources and inefficiency. At the same time, there will also be problems with procurement lags, which will affect the normal progress of the surgical process.

Therefore, an optimized information management solution for surgical equipment is desired.

Summary of the invention

This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

In a first aspect, the present invention provides a method for information management of surgical equipment, the method comprising:

Obtain historical usage data for specific surgical equipment;

Segmenting the historical usage data based on a first time scale and counting the usage frequency to obtain a first scale usage frequency time series input vector;

Segmenting the historical usage data based on a second time scale and counting the usage frequency to obtain a second-scale usage frequency time series input vector, wherein the first time scale is different from the second time scale;

Performing feature extraction on the first-scale usage frequency time series input vector and the second-scale usage frequency time series input vector respectively through a usage frequency time domain feature extractor based on a deep neural network to obtain a first-scale usage frequency time series associated feature vector and a second-scale usage frequency time series associated feature vector;

Using a multi-scale feature fuser to process the first-scale usage frequency temporal correlation feature vector and the second-scale usage frequency temporal correlation feature vector to obtain a multi-scale usage frequency temporal correlation feature;

Based on the multi-scale usage frequency time series correlation characteristics, determining a usage frequency short-term predictor to obtain a prediction value, and determining whether to generate an advance purchase reminder;

Wherein, the usage frequency time domain feature extractor based on deep neural network is a usage frequency time domain feature extractor based on one-dimensional convolution layer;

Among them, the first scale usage frequency time series input vector and the second scale usage frequency time series input vector are respectively subjected to feature extraction by a usage frequency time domain feature extractor based on a deep neural network to obtain a first scale usage frequency time series associated feature vector and a second scale usage frequency time series associated feature vector, including:

Each layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor performs convolution processing, mean pooling processing, and nonlinear activation processing on the input data in the forward pass of the layer, and the output of the last layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor is the first-scale frequency-of-use time-series associated feature vector and the second-scale frequency-of-use time-series associated feature vector, wherein the input of the first layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor is the first-scale frequency-of-use time-series input vector and the second-scale frequency-of-use time-series input vector.

Optionally, a multi-scale feature fusion device is used to process the first-scale usage frequency time series association feature vector and the second-scale usage frequency time series association feature vector to obtain a multi-scale usage frequency time series association feature, including: performing feature optimization on the first-scale usage frequency time series association feature vector and the second-scale usage frequency time series association feature vector to obtain an optimized first-scale usage frequency time series association feature vector and an optimized second-scale usage frequency time series association feature vector; using the multi-scale feature fusion device to process the optimized first-scale usage frequency time series association feature vector and the optimized second-scale usage frequency time series association feature vector to obtain a multi-scale usage frequency time series association feature vector as the multi-scale usage frequency time series association feature.

Optionally, feature optimization is performed on the first-scale usage frequency time series association feature vector and the second-scale usage frequency time series association feature vector to obtain an optimized first-scale usage frequency time series association feature vector and an optimized second-scale usage frequency time series association feature vector, including: respectively calculating weight coefficients of the first-scale usage frequency time series association feature vector and the second-scale usage frequency time series association feature vector to obtain a first weight coefficient and a second weight coefficient; and weighted optimization is performed on the first-scale usage frequency time series association feature vector and the second-scale usage frequency time series association feature vector using the first weight coefficient and the second weight coefficient as weighting factors to obtain the optimized first-scale usage frequency time series association feature vector and the optimized second-scale usage frequency time series association feature vector.

Optionally, using the multi-scale feature fusion device to process the optimized first-scale usage frequency temporal association feature vector and the optimized second-scale usage frequency temporal association feature vector to obtain a multi-scale usage frequency temporal association feature vector as the multi-scale usage frequency temporal association feature, including: using the multi-scale feature fusion device to process the optimized first-scale usage frequency temporal association feature vector and the optimized second-scale usage frequency temporal association feature vector using the following multi-scale feature fusion formula to obtain the multi-scale usage frequency temporal association feature vector; wherein the multi-scale feature fusion formula is:

;

in, and are respectively the optimized first scale usage frequency temporal correlation feature vector and the optimized second scale usage frequency temporal correlation feature vector, is the multi-scale usage frequency temporal correlation feature vector, represents the concatenation of vectors, is the threshold value, , is the transformation matrix, is the bias vector, express Activation function.

Optionally, based on the multi-scale usage frequency temporal association characteristics, a usage frequency short-time predictor is determined to obtain a prediction value, and whether to generate an advance purchase prompt is determined, including: passing the multi-scale usage frequency temporal association feature vector through a decoder-based surgical equipment usage frequency short-time predictor to obtain a prediction value; based on a comparison between the prediction value and a predetermined threshold, determining whether to generate an advance purchase prompt.

In a second aspect, the present invention provides a surgical equipment information management system, the system comprising:

A historical usage data acquisition module, used to acquire historical usage data of a specific surgical device;

A first time scale data processing module, configured to segment the historical usage data based on a first time scale and count usage frequencies to obtain a first scale usage frequency time series input vector;

A second time scale data processing module, configured to segment the historical usage data based on a second time scale and count usage frequencies to obtain a second scale usage frequency time series input vector, wherein the first time scale is different from the second time scale;

A usage frequency time domain feature extraction module, used to extract features from the first scale usage frequency time series input vector and the second scale usage frequency time series input vector respectively through a usage frequency time domain feature extractor based on a deep neural network to obtain a first scale usage frequency time series associated feature vector and a second scale usage frequency time series associated feature vector;

A multi-scale feature fusion module, configured to use a multi-scale feature fuser to process the first-scale usage frequency temporal correlation feature vector and the second-scale usage frequency temporal correlation feature vector to obtain a multi-scale usage frequency temporal correlation feature;

An advance purchase reminder generating module, used to determine a usage frequency short-term predictor to obtain a prediction value based on the multi-scale usage frequency time series correlation characteristics, and determine whether to generate an advance purchase reminder;

Wherein, the usage frequency time domain feature extractor based on deep neural network is a usage frequency time domain feature extractor based on one-dimensional convolution layer;

Among them, the usage frequency time domain feature extraction module is used to: use each layer of the usage frequency time domain feature extractor based on the one-dimensional convolution layer to perform convolution processing, mean pooling processing and nonlinear activation processing on the input data in the forward transmission of the layer, and use the output of the last layer of the usage frequency time domain feature extractor based on the one-dimensional convolution layer as the first-scale usage frequency time series associated feature vector and the second-scale usage frequency time series associated feature vector, wherein the input of the first layer of the usage frequency time domain feature extractor based on the one-dimensional convolution layer is the first-scale usage frequency time series input vector and the second-scale usage frequency time series input vector.

By adopting the above technical solution, the acquired historical usage data is segmented based on the first time scale and the second time scale and the usage frequency is counted to obtain the second scale usage frequency time series input vector; then, the usage frequency time domain feature extractor based on the deep neural network is used to extract features, and the multi-scale feature fusion is used to process to obtain the multi-scale usage frequency time series correlation features; based on the multi-scale usage frequency time series correlation features, the usage frequency short-term predictor is determined to obtain the predicted value, and it is determined whether to generate an advance purchase prompt. In this way, the demand for surgical equipment can be predicted and resource planning can be optimized, so that surgical equipment with high demand can be purchased in advance, thereby improving the quality of medical services.

Other features and advantages of the present invention will be described in detail in the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

Fig. 1 is a flow chart showing a method for information management of surgical equipment according to an exemplary embodiment.

Fig. 2 is a block diagram of a surgical equipment information management system according to an exemplary embodiment.

Fig. 3 is a block diagram of an electronic device according to an exemplary embodiment.

Fig. 4 is an application scenario diagram of a surgical equipment information management method according to an exemplary embodiment.

Detailed ways

Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and/or in parallel. In addition, the method embodiments may include additional steps and/or omit the steps shown. The scope of the present invention is not limited in this respect.

The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

There are some problems with the traditional hospital surgical equipment management methods, which are mainly reflected in the following aspects:

1. Lack of detailed data analysis: Traditional management usually relies on experience and regular maintenance plans, rather than real-time data and detailed analysis. This approach may lead to an inaccurate understanding of equipment usage and an inability to respond to actual demand changes in a timely manner.

2. Improper resource allocation: Due to the lack of in-depth understanding of the usage patterns and needs of surgical equipment, hospitals may not be able to effectively plan the resource allocation of equipment, which may lead to overuse of some equipment and idleness of other equipment, resulting in waste of resources.

3. Delayed procurement plans: Traditional procurement plans may not be flexible enough and cannot be adjusted in time according to actual usage, resulting in delayed or excessive procurement of new equipment, affecting the smooth progress of the operation and the patient's treatment experience.

4. Inefficiency: Lack of information technology support for equipment management requires medical staff to spend more time and energy on equipment maintenance and scheduling, reducing work efficiency and medical service quality.

In order to solve these problems, modern hospitals have begun to adopt more scientific and refined equipment management methods. For example, by establishing full life cycle management of medical equipment, the equipment is tracked and managed throughout the process, from application for purchase, demonstration of purchase, installation and commissioning, operation and maintenance to elimination and scrapping. In addition, the use of information technology, such as medical equipment management software, can achieve refined management of equipment and improve management efficiency and effectiveness. Through these methods, hospitals can more accurately understand the actual use of equipment and changes in demand, rationally plan resource allocation, and make purchases in a timely manner, thereby improving the efficiency and quality of the surgical process.

In order to solve the above problems, the present invention provides a surgical equipment information management system and method, which divides the acquired historical usage data based on the first time scale and the second time scale and counts the usage frequency to obtain the second scale usage frequency time series input vector; then extracts features through a usage frequency time domain feature extractor based on a deep neural network, and uses a multi-scale feature fusion device to process to obtain multi-scale usage frequency time series correlation features; based on the multi-scale usage frequency time series correlation features, determines a usage frequency short-term predictor to obtain a predicted value, and determines whether to generate an advance purchase prompt. In this way, the demand for surgical equipment can be predicted and resource planning can be optimized, so that surgical equipment with high demand can be purchased in advance, thereby improving the quality of medical services.

The specific implementation modes of the present invention are described in detail below with reference to the accompanying drawings.

FIG. 1 is a flow chart of a surgical equipment information management method according to an exemplary embodiment. As shown in FIG. 1 , the method includes:

Step 101, obtaining historical usage data of a specific surgical device;

Step 102: segment the historical usage data based on a first time scale and count the usage frequency to obtain a first scale usage frequency time series input vector;

Step 103: segment the historical usage data based on a second time scale and count the usage frequency to obtain a second-scale usage frequency time series input vector, wherein the first time scale is different from the second time scale;

Step 104: extract features from the first-scale usage frequency time series input vector and the second-scale usage frequency time series input vector respectively by using a usage frequency time domain feature extractor based on a deep neural network to obtain a first-scale usage frequency time series associated feature vector and a second-scale usage frequency time series associated feature vector;

Step 105: Use a multi-scale feature fuser to process the first-scale usage frequency time series correlation feature vector and the second-scale usage frequency time series correlation feature vector to obtain a multi-scale usage frequency time series correlation feature;

Step 106: Based on the multi-scale usage frequency time series correlation characteristics, determine a usage frequency short-term predictor to obtain a prediction value, and determine whether to generate an advance purchase reminder.

Among them, the usage frequency time domain feature extractor based on deep neural network is a usage frequency time domain feature extractor based on one-dimensional convolutional layer.

In response to the above-mentioned technical problems, the technical concept of the present application is to obtain historical usage data of specific surgical equipment and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time series analysis of the frequency of equipment usage in these historical usage data, so as to capture the characteristics of the usage, trends and demand changes of surgical equipment, thereby realizing the prediction of surgical equipment demand and optimizing resource planning, so as to purchase surgical equipment with higher demand in advance, thereby improving the quality of medical services.

Specifically, in the technical solution of the present application, first, the historical usage data of a specific surgical device is obtained. Next, considering that when actually analyzing the usage, trends, and demand changes of a specific surgical device, the most important data to pay attention to is the frequency of use of the device, and considering that these device usage frequency data have a dynamic change law of time series in the time dimension. Therefore, in order to be able to more comprehensively and fully capture the time series characteristics of the usage frequency data in the historical usage data of the equipment, in the technical solution of the present application, the historical usage data is segmented based on a first time scale and the usage frequency is counted to obtain a first-scale usage frequency time series input vector; and the historical usage data is segmented based on a second time scale and the usage frequency is counted to obtain a second-scale usage frequency time series input vector, wherein the first time scale is different from the second time scale. It should be understood that by segmenting and counting the historical usage data of specific surgical equipment at different time scales, a multi-dimensional time series analysis of the frequency of equipment use can be achieved. Different time scales reflect the different time series characteristics and changing laws of the frequency of equipment use. For example, short time scales are more likely to capture instantaneous changes in the frequency of equipment use, while long time scales can better reflect the long-term trend and cyclical laws of the frequency of surgical equipment use. Therefore, by comprehensively considering the historical frequency of surgical equipment use data at different time scales, we can have a more comprehensive understanding of the use of surgical equipment, thereby better describing the use patterns and laws of surgical equipment, so as to more accurately predict future use needs and formulate resource planning strategies.

Then, the first-scale usage frequency time series input vector and the second-scale usage frequency time series input vector are respectively subjected to feature mining in a usage frequency time domain feature extractor based on a one-dimensional convolution layer to respectively extract the time series dynamic features of the equipment usage frequency data at different time scales in the time dimension, thereby obtaining the first-scale usage frequency time series associated feature vector and the second-scale usage frequency time series associated feature vector. In other words, through the one-dimensional convolution operation, the key features and time series change laws in the equipment usage frequency time series data at different time scales can be identified and extracted, which helps to better understand the usage laws and patterns of surgical equipment.

In one embodiment of the present invention, each layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor performs convolution processing, mean pooling processing, and nonlinear activation processing on the input data in the forward transfer of the layer, and the output of the last layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor is the first-scale frequency-of-use time-series associated feature vector and the second-scale frequency-of-use time-series associated feature vector, wherein the input of the first layer of the one-dimensional convolutional layer-based frequency-of-use time-domain feature extractor is the first-scale frequency-of-use time-series input vector and the second-scale frequency-of-use time-series input vector.

Further, in one embodiment of the present invention, a multi-scale feature fusion device is used to process the first-scale frequency of use time series association feature vector and the second-scale frequency of use time series association feature vector to obtain a multi-scale frequency of use time series association feature, including: performing feature optimization on the first-scale frequency of use time series association feature vector and the second-scale frequency of use time series association feature vector to obtain an optimized first-scale frequency of use time series association feature vector and an optimized second-scale frequency of use time series association feature vector; using the multi-scale feature fusion device to process the optimized first-scale frequency of use time series association feature vector and the optimized second-scale frequency of use time series association feature vector to obtain a multi-scale frequency of use time series association feature vector as the multi-scale frequency of use time series association feature.

Among them, feature optimization is performed on the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector to obtain an optimized first-scale usage frequency temporal association feature vector and an optimized second-scale usage frequency temporal association feature vector, including: respectively calculating weighting coefficients of the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector to obtain a first weighting coefficient and a second weighting coefficient; and weighted optimization is performed on the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector using the first weighting coefficient and the second weighting coefficient as weighting factors to obtain the optimized first-scale usage frequency temporal association feature vector and the optimized second-scale usage frequency temporal association feature vector.

Furthermore, considering that the optimized first-scale usage frequency time series association feature vector and the optimized second-scale usage frequency time series association feature vector respectively contain the time series dynamic feature information of the time series data of the equipment usage frequency at different time scales, and the usage frequency time series features at different time scales are complementary. Therefore, in order to more accurately capture the usage frequency time series pattern and change trend of specific surgical equipment, in the technical solution of the present application, a multi-scale feature fusion device is further used to process the optimized first-scale usage frequency time series association feature vector and the optimized second-scale usage frequency time series association feature vector to obtain a multi-scale usage frequency time series association feature vector. By using a multi-scale feature fusion device, the equipment usage frequency time series feature information extracted at different time scales can be fused, thereby obtaining a more comprehensive and richer equipment usage frequency time series feature representation, covering the key time series information at different time scales. In this way, the complex usage patterns and laws of surgical equipment can be described more comprehensively, so that the model can better adapt to the changes and complex situations of the usage frequency of various equipment, so as to perform corresponding resource planning optimization.

Further, using the multi-scale feature fuser to process the optimized first-scale usage frequency time series association feature vector and the optimized second-scale usage frequency time series association feature vector to obtain a multi-scale usage frequency time series association feature vector as the multi-scale usage frequency time series association feature, including:

Using the multi-scale feature fuser to process the optimized first-scale usage frequency temporal association feature vector and the optimized second-scale usage frequency temporal association feature vector using the following multi-scale feature fusion formula to obtain the multi-scale usage frequency temporal association feature vector;

Among them, the multi-scale feature fusion formula is:

;

in, and are respectively the optimized first scale usage frequency temporal correlation feature vector and the optimized second scale usage frequency temporal correlation feature vector, is the multi-scale usage frequency temporal correlation feature vector, represents the concatenation of vectors, is the threshold value, , is the transformation matrix, is the bias vector, express Activation function.

In the technical solution described above, the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector respectively express the local temporal association characteristics of the historical usage data of a specific surgical device in local time domains of different scales divided by different scales in the global time domain. Thus, the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector have temporal association feature expression distinctiveness corresponding to different temporal association patterns in local time domains of different scales.

In this way, when the first-scale frequency-of-use temporal association feature vector and the second-scale frequency-of-use temporal association feature vector are processed using a multi-scale feature fuser to obtain the multi-scale frequency-of-use temporal association feature vector, and the multi-scale frequency-of-use temporal association feature vector is decoded through a decoder, it is expected that while maintaining the distinguishability of the temporal association feature expressions corresponding to different temporal association patterns of the first-scale frequency-of-use temporal association feature vector and the second-scale frequency-of-use temporal association feature vector, the probability mapping certainty of each to the decoding regression probability density domain of the decoder is improved to improve the accuracy of the decoding prediction value.

Based on this, the applicant of the present application respectively calculates the weighted coefficients of the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector, which are expressed as follows: the weighted coefficients of the first-scale usage frequency temporal association feature vector and the second-scale usage frequency temporal association feature vector are respectively calculated using the following optimization formula to obtain the first weighted coefficient and the second weighted coefficient; wherein the optimization formula is:

;

;

in, and They are the first scale usage frequency temporal correlation feature vectors and the second scale usage frequency temporal correlation feature vector The maximum eigenvalue of and is the first scale usage frequency temporal correlation feature vector and the second scale usage frequency temporal correlation feature vector First The characteristic values, is the length of the eigenvector, represents the logarithmic function with base 2, and is the weight hyperparameter, and are the first weighting coefficient and the second weighting coefficient respectively, It represents calculating the value of a natural exponential function with a numerical value as a power; using the first weighting coefficient and the second weighting coefficient as weighting factors, weighted optimization is performed on the first scale usage frequency time series association feature vector and the second scale usage frequency time series association feature vector to obtain the optimized first scale usage frequency time series association feature vector and the optimized second scale usage frequency time series association feature vector.

Specifically, the first scale is used to associate the frequency time series feature vectors and the second scale usage frequency temporal correlation feature vector The temporal correlation feature of represents the majority voting mechanism in the form of feature crowdsourcing to use the frequency temporal correlation feature vector at the first scale and the second scale usage frequency temporal correlation feature vector Relative to the distribution of the decoding regression probability space, the independent information expectation of each feature vector is maximized under the subordinate probability model. In this way, the coefficient and The frequency-time correlation feature vector is used for the first scale and the second scale usage frequency temporal correlation feature vector Weighting is performed to optimize the first scale usage frequency temporal correlation feature vector and the second scale usage frequency temporal correlation feature vector , we can use the frequency-series correlation feature vector based on the first scale and the second scale usage frequency temporal correlation feature vector The average information confidence of each eigenvalue is jointly estimated relative to the distribution of the decoding regression probability space to maintain the first scale using the frequency time series associated eigenvector and the second scale usage frequency temporal correlation feature vector The distinguishability of the feature distribution is improved while improving the certainty of its probability mapping to the decoding regression density domain, so as to improve the accuracy of the decoded prediction value obtained by the decoder of the multi-scale usage frequency time series correlation feature vector. In this way, the demand for surgical equipment can be predicted more accurately, so as to help hospitals make more reasonable resource planning and purchase surgical equipment with higher demand in advance.

Then, the multi-scale usage frequency time series associated feature vector is passed through a decoder-based surgical equipment usage frequency short-term predictor to obtain a predicted value. That is, the multi-scale time series fusion features of the historical usage frequency of a specific surgical device are used for decoding regression to perform a short-term prediction of the usage frequency based on the usage, trend, and demand changes of the surgical device. Furthermore, based on the comparison between the predicted value and a predetermined threshold, it is determined whether to generate an advance purchase prompt. In particular, in response to the predicted value being greater than the predetermined threshold, it is determined to generate an advance purchase prompt. In this way, the demand for surgical equipment can be predicted based on the usage, trend, and demand changes of surgical equipment, thereby helping hospitals to make more reasonable resource planning and improve the quality of medical services.

In one embodiment of the present invention, based on the multi-scale usage frequency temporal association characteristics, a usage frequency short-term predictor is determined to obtain a prediction value, and it is determined whether to generate an advance purchase prompt, including: passing the multi-scale usage frequency temporal association feature vector through a decoder-based surgical equipment usage frequency short-term predictor to obtain a prediction value; based on a comparison between the prediction value and a predetermined threshold, determining whether to generate an advance purchase prompt.

To summarize, the above solution is adopted to obtain the historical usage data of specific surgical equipment, and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time series analysis of the frequency of equipment usage in these historical usage data. In this way, the usage, trends and demand changes of surgical equipment can be captured, thereby realizing the prediction of surgical equipment demand and optimizing resource planning, so as to purchase surgical equipment with higher demand in advance, thereby improving the quality of medical services.

FIG2 is a block diagram of a surgical equipment information management system according to an exemplary embodiment. As shown in FIG2 , the system 200 includes:

A historical usage data acquisition module 201 is used to acquire historical usage data of a specific surgical device;

A first time scale data processing module 202, configured to segment the historical usage data based on a first time scale and count usage frequencies to obtain a first scale usage frequency time series input vector;

A second time scale data processing module 203, configured to segment the historical usage data based on a second time scale and count usage frequencies to obtain a second scale usage frequency time series input vector, wherein the first time scale is different from the second time scale;

A usage frequency time domain feature extraction module 204 is used to extract features from the first scale usage frequency time series input vector and the second scale usage frequency time series input vector respectively through a usage frequency time domain feature extractor based on a deep neural network to obtain a first scale usage frequency time series associated feature vector and a second scale usage frequency time series associated feature vector;

A multi-scale feature fusion module 205, configured to use a multi-scale feature fuser to process the first-scale usage frequency temporal correlation feature vector and the second-scale usage frequency temporal correlation feature vector to obtain a multi-scale usage frequency temporal correlation feature;

The advance purchase prompt generating module 206 is used to determine a usage frequency short-term predictor to obtain a prediction value based on the multi-scale usage frequency time series correlation characteristics, and determine whether to generate an advance purchase prompt.

In one embodiment of the present invention, the usage frequency time domain feature extractor based on deep neural network is a usage frequency time domain feature extractor based on one-dimensional convolutional layer.

In one embodiment of the present invention, the frequency usage time domain feature extraction module 204 is used to: use each layer of the frequency usage time domain feature extractor based on the one-dimensional convolution layer to perform convolution processing, mean pooling processing and nonlinear activation processing on the input data in the forward transfer of the layer, and use the output of the last layer of the frequency usage time domain feature extractor based on the one-dimensional convolution layer as the first-scale frequency usage time series associated feature vector and the second-scale frequency usage time series associated feature vector, wherein the input of the first layer of the frequency usage time domain feature extractor based on the one-dimensional convolution layer is the first-scale frequency usage time series input vector and the second-scale frequency usage time series input vector.

Referring to FIG3 below, it shows a schematic diagram of the structure of an electronic device 600 suitable for implementing an embodiment of the present invention. The terminal device in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG3 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

As shown in FIG3 , the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Typically, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication device 609 may allow the electronic device 600 to communicate wirelessly or wired with other devices to exchange data. Although FIG. 3 shows an electronic device 600 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

It should be noted that the computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperTextTransferProtocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The modules involved in the embodiments of the present invention may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Fig. 4 is an application scenario diagram of a surgical equipment information management method according to an exemplary embodiment. As shown in Fig. 4, in this application scenario, first, the historical usage data of a specific surgical equipment is obtained (for example, C shown in Fig. 4); then, the obtained historical usage data is input into a server (for example, S shown in Fig. 4) that is deployed with a surgical equipment information management algorithm, wherein the server can process the historical usage data based on the surgical equipment information management algorithm to determine whether to generate an advance purchase reminder.

The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

Although the subject matter has been described in language specific to structural features and/or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims (6)

1. An informationized management method of surgical equipment, comprising:

Acquiring historical usage data for a particular surgical device;

Dividing the historical usage data based on a first time scale and counting the usage frequency to obtain a first scale usage frequency time sequence input vector;

dividing the historical usage data based on a second time scale and counting the usage frequency to obtain a second scale usage frequency time sequence input vector, wherein the first time scale is different from the second time scale;

the frequency time domain feature extractor based on the deep neural network is used for extracting features of the first scale frequency time sequence input vector and the second scale frequency time sequence input vector respectively so as to obtain a first scale frequency time sequence association feature vector and a second scale frequency time sequence association feature vector;

processing the first scale usage frequency time sequence correlation feature vector and the second scale usage frequency time sequence correlation feature vector by using a multi-scale feature fusion device to obtain a multi-scale usage frequency time sequence correlation feature;

Determining a usage frequency short-time predictor to obtain a predicted value based on the multi-scale usage frequency time sequence association characteristic, and determining whether to generate an early purchase prompt;

the depth neural network-based frequency-of-use time domain feature extractor is a one-dimensional convolution layer-based frequency-of-use time domain feature extractor;

the method for extracting the features of the first scale usage frequency time sequence input vector and the second scale usage frequency time sequence input vector by using the usage frequency time domain feature extractor based on the deep neural network to obtain the first scale usage frequency time sequence association feature vector and the second scale usage frequency time sequence association feature vector comprises the following steps:

And respectively carrying out convolution processing, average pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the one-dimensional convolution layer-based frequency time domain feature extractor, and using the output of the last layer of the one-dimensional convolution layer-based frequency time domain feature extractor as the first scale-use frequency time sequence correlation feature vector and the second scale-use frequency time sequence correlation feature vector, wherein the input of the first layer of the one-dimensional convolution layer-based frequency time domain feature extractor is the first scale-use frequency time sequence input vector and the second scale-use frequency time sequence input vector.

2. The method of claim 1, wherein processing the first scale usage frequency time series associated feature vector and the second scale usage frequency time series associated feature vector using a multi-scale feature fusion device to obtain a multi-scale usage frequency time series associated feature comprises:

Performing feature optimization on the first scale usage frequency time sequence association feature vector and the second scale usage frequency time sequence association feature vector to obtain an optimized first scale usage frequency time sequence association feature vector and an optimized second scale usage frequency time sequence association feature vector;

And processing the optimized first-scale use frequency time sequence correlation feature vector and the optimized second-scale use frequency time sequence correlation feature vector by using the multi-scale feature fusion device to obtain a multi-scale use frequency time sequence correlation feature vector serving as the multi-scale use frequency time sequence correlation feature.

3. The surgical device informatization management method according to claim 2, wherein performing feature optimization on the first scale usage frequency time-series associated feature vector and the second scale usage frequency time-series associated feature vector to obtain an optimized first scale usage frequency time-series associated feature vector and an optimized second scale usage frequency time-series associated feature vector, comprising:

respectively calculating the weighting coefficients of the first scale use frequency time sequence association characteristic vector and the second scale use frequency time sequence association characteristic vector to obtain a first weighting coefficient and a second weighting coefficient;

And taking the first weighting coefficient and the second weighting coefficient as weighting factors to carry out weighted optimization on the frequency time sequence association characteristic vector of the first scale and the frequency time sequence association characteristic vector of the second scale so as to obtain the optimized frequency time sequence association characteristic vector of the first scale and the optimized frequency time sequence association characteristic vector of the second scale.

4. The method according to claim 3, wherein processing the optimized first-scale usage frequency time-series associated feature vector and the optimized second-scale usage frequency time-series associated feature vector using the multi-scale feature fusion device to obtain a multi-scale usage frequency time-series associated feature vector as the multi-scale usage frequency time-series associated feature, comprises:

processing the optimized first scale usage frequency time sequence association feature vector and the optimized second scale usage frequency time sequence association feature vector by using the multi-scale feature fusion device according to the following multi-scale feature fusion formula to obtain the multi-scale usage frequency time sequence association feature vector;

wherein, the multiscale feature fusion formula is:

；

Wherein, AndThe optimized first scale usage frequency time sequence correlation feature vector and the optimized second scale usage frequency time sequence correlation feature vector,Is the multi-scale usage frequency timing-associated feature vector,A concatenation of vectors is represented and,Is a threshold value and,，Is a transformation matrix that is a function of the transformation matrix,Is the offset vector of the reference signal,Representation ofThe function is activated.

5. The method of informative management of surgical equipment according to claim 4, wherein determining a frequency of use short-term predictor to obtain a predicted value based on the multi-scale frequency of use timing correlation feature, and determining whether to generate an advance purchase prompt, comprises:

The multi-scale use frequency time sequence associated feature vector is used for obtaining a predicted value through a decoder-based operation equipment use frequency short-time predictor;

Based on a comparison between the predicted value and a predetermined threshold, it is determined whether to generate an advance purchase prompt.

6. An informationized surgical device management system, comprising:

The historical use data acquisition module is used for acquiring historical use data of the specific surgical equipment;

the first time scale data processing module is used for segmenting the historical use data based on a first time scale and counting the use frequency to obtain a first scale use frequency time sequence input vector;

the second time scale data processing module is used for segmenting the historical usage data based on a second time scale and counting the usage frequency to obtain a second scale usage frequency time sequence input vector, wherein the first time scale is different from the second time scale;

The frequency-use time domain feature extraction module is used for carrying out feature extraction on the first scale frequency-use time sequence input vector and the second scale frequency-use time sequence input vector through a frequency-use time domain feature extractor based on a deep neural network so as to obtain a first scale frequency-use time sequence associated feature vector and a second scale frequency-use time sequence associated feature vector;

The multi-scale feature fusion module is used for processing the first-scale use frequency time sequence association feature vector and the second-scale use frequency time sequence association feature vector by using a multi-scale feature fusion device so as to obtain multi-scale use frequency time sequence association features;

The early purchase prompt generation module is used for determining a use frequency short-time predictor to obtain a predicted value based on the multi-scale use frequency time sequence association characteristic and determining whether to generate an early purchase prompt;

the depth neural network-based frequency-of-use time domain feature extractor is a one-dimensional convolution layer-based frequency-of-use time domain feature extractor;

The frequency-of-use time domain feature extraction module is used for:

And respectively carrying out convolution processing, average pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the one-dimensional convolution layer-based frequency time domain feature extractor, and using the output of the last layer of the one-dimensional convolution layer-based frequency time domain feature extractor as the first scale-use frequency time sequence correlation feature vector and the second scale-use frequency time sequence correlation feature vector, wherein the input of the first layer of the one-dimensional convolution layer-based frequency time domain feature extractor is the first scale-use frequency time sequence input vector and the second scale-use frequency time sequence input vector.