A wireless communication system for a digital ward

Abstract

The present invention relates to the technical field of communication processing, and particularly to a wireless communication system for a digital ward. The system includes: an acquisition module for acquiring network usage traffic, call times, and call moments; a traffic analysis module for determining a traffic demand index according to the change in network usage traffic; a call analysis module for obtaining a call prediction number according to the change in call times, determining a call frequency index according to the call time interval, and further determining a demand weight, and determining a call urgency index according to the call prediction number and the demand weight of the ward; a load distribution module for determining the degree of network demand allocated by the ward for the network in combination with the traffic demand index and the call urgency index, and performing network load distribution in combination with the network demand degrees of all wards. The present invention can combine the network demands within the ward itself, reasonably allocate different network loads, achieve dynamic load adjustment, and improve the stability effect of the wireless communication of the overall digital ward.

Description

Technical Field

[0001] The present invention relates to the technical field of communication processing, and particularly relates to a wireless communication system for a digital ward. Background Art

[0002] Hospitals are now gradually introducing intelligent technologies and management means to build digital wards, automatically collect and process clinical data, reduce the workload of medical staff, and at the same time provide a more convenient, safe and comfortable medical environment for patients. When using wireless communication technology to process clinical data in a digital ward, it is necessary to achieve network dynamic load balancing, which can dynamically adjust the load distribution of each network area according to the current network load situation of the digital ward, ensure that each network point in the ward can bear an appropriate load, and avoid a decline in network performance caused by overload of a certain access point.

[0003] In related technologies, the fixed network load is usually evenly distributed according to the number of hospital beds and the number of medical devices. However, due to the occupancy rate of patients in the ward and the change of the network requirements of the patients themselves, network overload may occur, which may lead to unreasonable overall load distribution and poor wireless communication stability. Therefore, dynamic load adjustment is urgently needed. Summary of the Invention

[0004] In order to solve the technical problems in related technologies that due to the occupancy rate of patients in the ward and the change of the network requirements of the patients themselves, network overload may occur, which may lead to unreasonable overall load distribution and poor wireless communication stability, the present invention provides a wireless communication system for a digital ward, and the specific technical solution adopted is as follows:

[0005] The present invention proposes a wireless communication system for a digital ward, and the system includes:

[0006] An acquisition module, configured to acquire the network usage traffic of each ward every day, the call times and call moments of the ward in each ward;

[0007] A traffic analysis module, configured to perform time series decomposition according to the numerical change of the network usage traffic of the same ward every day, determine a trend term and a seasonal term, and determine a traffic demand index of the ward according to the fitting slope of the trend term and the peak change of the seasonal term;

[0008] A call analysis module, which is used to predict the call times of the current day based on the change in call times on different days in the ward, so as to obtain the predicted call times; determine the call frequency index of the ward on the previous day according to the call time interval between two adjacent calls in the same ward on the previous day; classify the wards according to the call frequency index of all wards on the previous day to obtain mildly frequent wards and severely frequent wards; assign different demand weights to the mildly frequent wards and severely frequent wards respectively, where the demand weight of the mildly frequent ward is less than that of the severely frequent ward, and determine the call emergency index of each ward according to the predicted call times and the demand weights of the wards.

[0009] A load distribution module, which is used to combine the traffic demand index and the call emergency index to determine the degree of network demand of the ward for network allocation; perform network load distribution by combining the network demand degrees of all wards.

[0010] Further, the time series decomposition is performed according to the numerical change of the network usage traffic in each day in the same ward to determine the trend term and the seasonal term, including:

[0011] Taking time as the abscissa and the network usage traffic value as the ordinate to construct a two-dimensional coordinate system, determine the coordinate points of the network usage traffic for each day, and connect the coordinate points in time series to obtain a traffic curve;

[0012] Based on the STL time series decomposition algorithm, perform time series decomposition on the traffic curve to determine the trend term and the seasonal term of the traffic curve.

[0013] Further, according to the fitting slope of the trend term and the peak change of the seasonal term, determine the traffic demand index of the ward, including:

[0014] Perform least squares fitting on the trend term, and take the slope obtained after fitting as the fitting slope;

[0015] Determine the peak data of the seasonal term, take the absolute value of the difference between two peak data that are closest in time series as the peak change index corresponding to the two peak data; calculate the mean of all peak data and the mean of all peak change indexes, and take the product of the two means as the peak influence coefficient;

[0016] Calculate the product of the peak influence coefficient and the fitting slope, and perform maximum-minimum normalization processing to obtain the traffic demand index.

[0017] Further, the prediction of the call times of the current day based on the change in call times on different days in the ward to obtain the predicted call times includes:

[0018] Perform fitting on the call times on different days based on the least squares method, and predict the call times of the current day according to the fitting result to obtain the predicted call times.

[0019] Further, determining the call frequency index of the ward on the previous day according to the call time interval between two adjacent call times in the same ward on the previous day includes:

[0020] Calculating the mean value of the call time intervals between all adjacent two call times in the same ward on the previous day to obtain the call interval mean value;

[0021] Taking the reciprocal of the call interval mean value as the call frequency index.

[0022] Further, classifying the wards according to the call frequency indexes of all wards on the previous day to obtain mildly frequent wards and severely frequent wards includes:

[0023] Clustering the call frequency indexes based on the k-means algorithm, setting the k value to 2, and obtaining two clustering clusters;

[0024] Calculating the mean value of all call frequency indexes in each clustering cluster. Among them, the beds corresponding to the clustering cluster with a larger mean value of the call frequency index are severely frequent wards, and the beds corresponding to the clustering cluster with a smaller mean value of the call frequency index are mildly frequent wards.

[0025] Further, assigning different demand weights to the mildly frequent wards and severely frequent wards respectively includes:

[0026] The demand weight of the mildly frequent ward is set to 0.5, and the demand weight of the severely frequent ward is set to 1.

[0027] Further, determining the call emergency index of each ward according to the call prediction times and the demand weight of the ward includes:

[0028] Calculating the product of the call prediction times and the demand weight of the ward, and performing maximum-minimum normalization processing to obtain the call emergency index.

[0029] Further, combining the traffic demand index and the call emergency index to determine the network demand degree of the ward for network allocation includes:

[0030] Calculating the product of the traffic demand index and the call emergency index to obtain the network demand degree.

[0031] Further, performing network load allocation by combining the network demand degrees of all wards includes:

[0032] Calculating the sum value of the network demand degrees of all wards as the total demand degree;

[0033] Taking the ratio of the network demand degree of any ward to the total demand degree as the load demand ratio;

[0034] Multiply the current allocable load by the load demand ratio of each ward to obtain the load to be allocated for each ward.

[0035] Perform load allocation according to the loads to be allocated for all wards.

[0036] The present invention has the following beneficial effects:

[0037] The present invention realizes network load allocation for wireless communication through two dimensions of network usage traffic and hospital bed call situations; by obtaining the daily network usage traffic of each ward and the call times and call moments in each ward, it provides a data basis for network load allocation analysis; then, perform time series decomposition on the numerical changes of the network usage traffic to determine the trend term and seasonal term, and determine the traffic demand index of the ward according to the fitting slope of the trend term and the peak change of the seasonal term. The traffic demand index accurately represents the traffic fluctuation and the demand degree of the traffic itself; afterwards, according to the distribution and numerical changes of the call times, perform prediction analysis and weight assignment to determine the call emergency index, and the call emergency situation represents the timeliness demand of the call; finally, combine the traffic demand index and the call emergency index to determine the network demand degree of the ward for network allocation; perform network load allocation by combining the network demand degrees of all wards. Thus, the present invention can achieve dynamic allocation of the network under the same total load, that is to say, reasonably allocate different network loads in combination with the network demands within the ward itself, so as to achieve dynamic load adjustment and improve the stability effect of wireless communication in the overall digital ward. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for description in the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 It is a structural diagram of a wireless communication system for a digital ward provided by an embodiment of the present invention. Detailed Embodiments

[0040] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, with reference to the accompanying drawings and preferred embodiments, a wireless communication system for a digital ward proposed according to the present invention, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0042] The following specifically describes the specific solution of a wireless communication system for a digital ward provided by the present invention with reference to the accompanying drawings.

[0043] Please refer to Figure 1 , which shows the structure diagram of a wireless communication system for a digital ward provided by an embodiment of the present invention. The system includes:

[0044] An acquisition module 101, configured to acquire the daily network usage traffic of each ward, the call times and call moments of each ward in the ward.

[0045] The scenario of the embodiment of the present invention is a ward communication scenario. It should be noted that the daily network usage traffic in each ward is the network traffic consumption situation of all personnel in each ward. Since the incidence of diseases is different in different periods, it will lead to relatively large differences in the number of patients and the use of medical resources in the ward, resulting in different network overheads in the wards of different departments and different regions in the hospital. The traffic data of the wards in each region can be obtained through the monitoring and analysis of network traffic, using tools such as Wireshark and NetFlow Analyzer.

[0046] At the same time, due to digital management, each bed in the ward is controlled by an intelligent call system. The bedside care system can be used to determine whether there are patients in each bed, and at the same time, it is matched with the ward bracelet call response system. The patient bedside transmitter is divided into two wireless buttons, one for nurses and one for nursing workers, to achieve point-to-point precise calls. The system will record the patients and call situations of the beds. The present invention mainly records the call times of all beds in a ward and the moment of each call. Among them, the moment of each call is used as the call moment.

[0047] A traffic analysis module 102, configured to perform time series decomposition according to the numerical change of the daily network usage traffic in the same ward, determine the trend term and the seasonal term, and determine the traffic demand index of the ward according to the fitting slope of the trend term and the peak change of the seasonal term.

[0048] Since the numerical fluctuations of network traffic usage are large and the overall fluctuation is sawtooth-shaped, feature decomposition is required to better analyze the characteristics of traffic fluctuations.

[0049] Furthermore, in some embodiments of the present invention, time series decomposition is performed based on the numerical changes in the network usage traffic in the same ward every day to determine trend items and seasonal items, including: constructing a two-dimensional coordinate system with time as the horizontal coordinate and the network usage traffic value as the vertical coordinate, determining the coordinate points of the network usage traffic for each day, and connecting the coordinate points in time series to obtain a traffic curve; performing time series decomposition on the traffic curve based on the STL time series decomposition algorithm to determine the trend item and seasonal item of the traffic curve.

[0050] In the embodiment of the present invention, the characteristic decomposition can be specifically an STL time series decomposition algorithm, which can decompose the flow curve into a trend term, a seasonal term and a residual term, wherein the trend term represents the overall numerical change trend, and the seasonal term represents the periodic change situation.

[0051] Therefore, in the embodiment of the present invention, the fitting slope of the trend term represents the overall trend characteristics, while the peak change of the season term represents the periodic peak impact characteristics. The flow demand of the ward can be analyzed by combining these two characteristics.

[0052] Furthermore, in some embodiments of the present invention, the flow demand index of the ward is determined based on the fitting slope of the trend item and the peak change of the seasonal item, including: performing least squares fitting on the trend item, and taking the slope obtained after fitting as the fitting slope; determining the peak data of the seasonal item, and taking the absolute value of the difference between the two peak data closest to each other in time series as the peak change index corresponding to the two peak data; calculating the mean of all peak data and the mean of all peak change indicators, and taking the product of the two means as the peak influence coefficient; calculating the product of the peak influence coefficient and the fitting slope, and normalizing the maximum and minimum values ​​to obtain the flow demand index.

[0053] Among them, the least squares method performs a straight line fit on the trend item to obtain a fitting straight line for the trend item, and the slope of the fitting straight line for the trend item is used as the fitting slope. The fitting slope represents the change in the overall flow demand. The larger the fitting slope value, the increased flow demand, and the smaller the fitting slope value, the decreased flow demand.

[0054] Among them, the seasonal term shows periodic fluctuations, that is, its fluctuations have peaks. The data value corresponding to the peak is used as the peak data. The absolute value of the difference between the two peak data that are closest in time series represents the change between two adjacent peak data in time series. The larger the value of the peak change index, the greater the flow fluctuation in the ward. Whether the flow usage suddenly increases or suddenly decreases, abnormal analysis is required. That is, the larger the value of the peak change index, the more abnormal the overall flow fluctuation is.

[0055] Among them, the mean value of all peak data represents the flow size characteristic, and the mean value of all peak change indexes represents the abnormal characteristic of flow fluctuation. Thus, directly calculate the product value of the two mean values to obtain the peak influence coefficient. The larger the value of the peak influence coefficient, the larger the overall flow peak and the greater the change. Thus, the overall demand for flow is greater.

[0056] Furthermore, combined with the fact that the larger the fitting slope value, the greater the flow demand, and the smaller the fitting slope value, the lower the flow demand; the larger the value of the peak influence coefficient, the larger the overall flow peak and the greater the change. Thus, the overall demand for flow is greater. Directly calculate the product of the peak influence coefficient and the fitting slope, and perform maximum-minimum normalization processing to obtain the flow demand index.

[0057] Among them, the flow demand index represents the degree of demand determined according to the flow change. The larger the value of the flow demand index, the higher the flow load required to achieve overall communication stability in the corresponding ward.

[0058] The call analysis module 103 is used to predict the call times of the day according to the change of call times on different days in the ward, and obtain the call prediction times; determine the call frequency index of the ward on the previous day according to the call time interval between two adjacent call times in the previous day in the same ward; classify the wards according to the call frequency index of all wards on the previous day to obtain mildly frequent wards and severely frequent wards; assign different demand weights to the mildly frequent wards and severely frequent wards respectively. The demand weight of the mildly frequent ward is less than that of the severely frequent ward, and determine the call emergency index of each ward according to the call prediction times and the demand weights of the wards.

[0059] Among them, since the bed utilization rate in the ward is uncertain, the conditions of the patients on different beds are uncertain, and the frequency of care required by relevant nurses or nursing workers is uncertain, it is impossible to directly analyze the call situation by combining multiple data. In the embodiments of the present invention, the call times of multiple days before the current day can be analyzed to fit and predict the call times of the current day, which can be used as a data reference with extremely high credibility.

[0060] In the embodiments of the present invention, the call times of the current day can be directly predicted based on the change in the call times on different days in the ward. Further, in some embodiments of the present invention, the specific prediction method includes: fitting the call times on different days based on the least squares method, and predicting the call times of the current day according to the fitting result to obtain the predicted call times.

[0061] Among them, the least squares method can analyze the overall values to obtain more accurate and reliable predicted call times. This prediction method takes into account the change in the overall call times, making the predicted value more accurate and reliable.

[0062] After analyzing the call times, it is also necessary to predict the call frequency characteristics. It can be understood that since the ward usually has calls during the day, however, there are also call demands at night, but the number of times is relatively low. Therefore, the call frequency characteristics are directly analyzed through the time interval between two adjacent calls. That is, according to the call time interval between two adjacent call times of the same ward on the previous day, the call frequency index of the ward on the previous day is determined.

[0063] Further, in some embodiments of the present invention, the specific method for determining the call frequency index includes: calculating the mean value of the call time intervals between all adjacent two call times of the same ward on the previous day to obtain the call interval mean value; taking the reciprocal of the call interval mean value as the call frequency index.

[0064] Since the smaller the call interval mean value indicates the more frequent the overall calls, thus, in the embodiments of the present invention, the reciprocal of the call interval mean value is directly calculated as the call frequency index.

[0065] It can be understood that the larger the value of the call frequency index, the more frequent the calls, that is, the more the timeliness and reliability of communication are required. Therefore, the wards can be directly classified according to the call frequency index.

[0066] Further, in some embodiments of the present invention, classifying the wards according to the call frequency indexes of all wards on the previous day to obtain mildly frequent wards and severely frequent wards includes: clustering the call frequency indexes based on the k-means algorithm, setting the k value to 2 to obtain two clustering clusters; calculating the mean value of all call frequency indexes in each clustering cluster. Among them, the beds corresponding to the clustering cluster with a larger mean value of the call frequency index are severely frequent wards, and the beds corresponding to the clustering cluster with a smaller mean value of the call frequency index are mildly frequent wards.

[0067] Among them, clustering is implemented by the k-means algorithm, and the value of k is set to 2. Thus, all wards are directly divided into two categories based on the numerical size of the call frequency index. One category shows a larger numerical value, and the other category shows a smaller numerical value. In the embodiment of the present invention, the beds corresponding to the clustering cluster with a larger numerical value are severe frequent wards, and the beds corresponding to the clustering cluster with a smaller numerical value are mild frequent wards.

[0068] For the analysis of the specific numerical size performance within the clustering cluster, the mean value is directly calculated, that is, by calculating the mean value of all call frequency indexes in each clustering cluster, the clustering cluster with a larger mean value corresponds to the severe frequent ward, and the clustering cluster with a smaller mean value corresponds to the mild frequent ward.

[0069] It can be understood that the severe frequent wards have a greater demand for network timeliness and the calls are more urgent. In the embodiment of the present invention, different demand weights can be assigned to the severe frequent wards and the mild frequent wards respectively, and the demand weight of the severe wards is greater than that of the mild wards. Thus, in the embodiment of the present invention, the demand weight of the mild frequent ward is set to 0.5, and the demand weight of the severe frequent ward is set to 1.

[0070] Further, in some embodiments of the present invention, the call emergency index of each ward is determined according to the call prediction times and the demand weight of the ward, including: calculating the product of the call prediction times and the demand weight of the ward, and performing maximum-minimum normalization processing to obtain the call emergency index.

[0071] In the embodiment of the present invention, the call prediction times represent the prediction situation of the next day. By directly multiplying with the demand weight, the analysis of the call emergency characteristics can be obtained, that is, the larger the numerical value of the call emergency index, the more predicted call times and the more frequent the calls.

[0072] The load distribution module 104 is used to combine the traffic demand index and the call emergency index to determine the degree of network demand of the ward for network allocation; and perform network load distribution by combining the network demand degrees of all wards.

[0073] In the embodiment of the present invention, the communication network can be allocated for the ward by combining the traffic demand and the call demand. The traffic demand characterizes the overall communication volume demand, and the call demand represents the timeliness demand of the communication. Thus, in the embodiment of the present invention, the network is allocated to each ward by combining the traffic demand index and the call emergency index.

[0074] Further, in some embodiments of the present invention, combining the traffic demand index and the call emergency index to determine the degree of network demand of the ward for network allocation includes: calculating the product of the traffic demand index and the call emergency index to obtain the degree of network demand.

[0075] The larger the values of the traffic demand index and the call emergency index, the greater the demand for the network. Then, directly calculate the product of the traffic demand index and the call emergency index to obtain the network demand level.

[0076] Furthermore, in some embodiments of the present invention, network load allocation is performed in combination with the network demand levels of all wards, including: calculating the sum of the network demand levels of all wards as the total demand level; taking the ratio of the network demand level of any ward to the total demand level as the load demand ratio; taking the product of the currently allocable load and the load demand ratio of each ward as the load to be allocated for each ward; and realizing load allocation according to the loads to be allocated for all wards.

[0077] Normalization is performed through the load demand ratio to determine the load to be allocated for each ward, and load allocation for each ward is realized based on the load to be allocated, which is convenient for allocating more network loads to the wards with large and fluctuating network demands, and improving the stability of wireless communication in the overall digital ward.

[0078] The present invention realizes network load allocation for wireless communication through two dimensions of network usage traffic and hospital bed calls; by obtaining the network usage traffic of each ward every day and the call times and call moments in each ward, it provides a data basis for network load allocation analysis; then, time series decomposition is performed on the numerical changes of the network usage traffic to determine the trend term and the seasonal term, and according to the fitting slope of the trend term and the peak change of the seasonal term, the traffic demand index of the ward is determined, and the traffic demand index accurately represents the traffic fluctuation and the demand level of the traffic itself; after that, according to the distribution and numerical changes of the call times, predictive analysis and weight assignment are performed to determine the call emergency index, and the call emergency situation represents the timeliness demand of the call; finally, in combination with the traffic demand index and the call emergency index, the network demand level for network allocation of the ward is determined; network load allocation is performed in combination with the network demand levels of all wards. Thus, the present invention can achieve dynamic allocation of the network under the condition of the same total load amount, that is to say, reasonably allocate different network loads in combination with the network demand within the ward itself, so as to achieve dynamic load adjustment and improve the stability effect of wireless communication in the overall digital ward.

[0079] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. The key points of each embodiment are to illustrate the differences from other embodiments.

Claims

1. A wireless communication system for a digital ward, characterized in that: The system comprises: An acquisition module is used to obtain the network usage flow of each ward every day and the number of calls and call times in each ward; A traffic analysis module, used to perform time series decomposition according to the numerical changes of network usage traffic in the same ward every day, determine trend items and seasonal items, and determine the traffic demand index of the ward according to the fitting slope of the trend item and the peak change of the seasonal item. The traffic demand index is obtained by normalizing the maximum and minimum values ​​of the product of the peak influence coefficient and the fitting slope. The peak influence coefficient is the product of the mean of all peak data and the mean of all peak change indicators. The absolute value of the difference between the two peak data closest to each other in time series is the peak change index corresponding to the two peak data. The fitting slope is the slope obtained by fitting the trend item by the least square method. The fitting slope is used to represent the overall trend characteristics. The peak change is used to represent the periodic peak influence characteristics. The traffic demand index is used to represent the degree of demand determined according to the traffic change. The call analysis module is used to predict the number of calls on the day according to the change of the number of calls on different days in the ward, and obtain the predicted number of calls; determine the call frequency index of the ward on the previous day according to the call time interval between two adjacent call times of the same ward on the previous day; classify the wards according to the call frequency index of all wards on the previous day to obtain mild frequent wards and severe frequent wards; assign different demand weights to mild frequent wards and severe frequent wards respectively, the demand weight of the mild frequent ward is less than the demand weight of the severe frequent ward, and determine the call urgency index of each ward according to the predicted number of calls and the demand weight of the ward; The load distribution module is used to determine the network demand degree of the ward for network allocation in combination with the flow demand index and the call urgency index; and to distribute the network load in combination with the network demand degrees of all wards.

2. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: The time series decomposition is performed based on the numerical changes of the network usage flow in the same ward every day to determine the trend item and the seasonal item, including: A two-dimensional coordinate system is constructed with time as the horizontal axis and the network usage flow value as the vertical axis. The coordinate points of the network usage flow for each day are determined, and the flow curve is obtained by connecting the coordinate points in time sequence. The flow curve is decomposed into time series based on the STL time series decomposition algorithm to determine the trend item and the seasonal item of the flow curve.

3. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: The method predicts the number of calls on the day according to the change of the number of calls on different days in the ward to obtain the predicted number of calls, including: The number of calls on different days is fitted based on the least squares method, and the number of calls on the day is predicted according to the fitting results to obtain the predicted number of calls.

4. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: Determining the call frequency index of the ward on the previous day according to the call time interval between two adjacent call times of the same ward on the previous day includes: Calculate the average of the time intervals between all two adjacent call times in the same ward on the previous day to obtain the average call interval; The reciprocal of the calling interval mean is taken as the calling frequency index.

5. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: The wards are classified according to the call frequency index of all wards on the previous day to obtain mild frequent wards and severe frequent wards, including: The call frequency index is clustered based on the k-means algorithm, and the k value is set to 2, resulting in two clusters; The mean of all call frequency indicators in each cluster is calculated, wherein the beds corresponding to the clusters with larger mean values ​​of call frequency indicators are severe frequent wards, and the beds corresponding to the clusters with smaller mean values ​​of call frequency indicators are mild frequent wards.

6. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: Different demand weights are assigned to the mild frequent wards and the severe frequent wards, including: The demand weight of the mild frequent ward is set to 0.5, and the demand weight of the severe frequent ward is set to 1.

7. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: The call urgency index of each ward is determined according to the predicted number of calls and the demand weight of the ward, including: The product of the predicted number of calls and the demand weight of the ward is calculated, and the maximum and minimum values ​​are normalized to obtain a call urgency index.

8. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: Determining the degree of network demand of the ward for network allocation in combination with the flow demand index and the call urgency index includes: The product of the flow demand index and the call urgency index is calculated to obtain the network demand degree.

9. A wireless communication system for a digital ward as claimed in claim 1, characterized in that: The network load is distributed according to the network demand of all wards, including: Calculate the sum of the network demand levels of all wards as the total demand level; The ratio of the network demand level of any ward to the total demand level is taken as the load demand ratio; The product of the current allocable load and the load demand ratio of each ward is used as the load to be allocated for each ward; Load distribution is achieved based on the load to be distributed in all wards.

Images