Physical examination information pushing method and system

Abstract

The invention provides a physical examination information pushing method and system, and the method comprises the steps: determining a feedback difference degree when physical examination information in a physical examination record is fed back to different pushing nodes; the physical examination information is extracted from the physical examination record by the physical examination person according to the health prompt information and is fed back to the basic data flow of the physical examination person and the push data flow responded by the push node; based on the basic data flow and the feedback difference degree, consistency verification is carried out on the push data flow responded by the push nodes, and then the response deviation of each push node is obtained; performing node screening on the current physical examination information of the physical examinee to obtain a pushing pre-selection node; and determining the response confidence of each pre-selected pushing node based on all the response deviations, and pushing the current physical examination information of the physical examinee to the pre-selected pushing node of which the response confidence is higher than a preset threshold value. By adopting the scheme of the invention, the confidence response pushing of the physical examination information can be realized under the condition of multi-node coupling, so that the pushing credibility of the physical examination information is improved.

Description

Technical Field

[0001] The present application relates to the technical field of information push, and more specifically, to a method and system for pushing physical examination information. Background Art

[0002] Information push refers to the technology of recommending valuable information, services or products to users by analyzing user behavior, needs and preferences. The process of information push includes the collection, analysis and processing of user data, and can accurately deliver relevant information when users need it, thereby improving information utilization and user experience.

[0003] Physical examination information push is an important part of modern health management systems. The physical examination information push process is to push the physical examination information to relevant push nodes, and each department will make feedback on the same physical examination information. Physical examination information push is widely used in medical and health management. Since the traditional physical examination information push method relies on a single node or is based on limited conditions for push, the credibility of physical examination information feedback is low. The existing physical examination information push is prone to high resource occupancy and information deviation in the information system under the synchronous feedback of multiple push nodes, resulting in low push efficiency and reduced credibility of physical examination information. Therefore, how to realize the confidence response push of physical examination information under multi-node coupling, thereby improving the credibility of physical examination information push has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a physical examination information push method and system, which can realize the confidence response push of physical examination information in the case of multi-node coupling, thereby improving the credibility of the physical examination information push.

[0005] In a first aspect, the present application provides a method for pushing physical examination information, comprising the following steps: Obtain the physical examination records of the examinee within a specified time period, and determine the examinee's health reminder information through the preset disease knowledge graph; Determine the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, and extract the basic data flow of the physical examination information fed back to the examinee and the push data flow of each push node responding to the physical examination information from the physical examination record according to the health prompt information; Based on the basic data stream and the feedback difference, consistency check is performed on the push data stream responded by each push node to obtain the response deviation of each push node; Perform node screening on the examinee's current physical examination information to obtain all push pre-selected nodes; The response confidence of each push pre-selected node is determined based on all response deviations, and then the current physical examination information of the examinee is pushed to the push pre-selected node whose response confidence is higher than a preset threshold.

[0006] In some embodiments, determining the health reminder information of the examinee through the preset disease knowledge graph specifically includes: Preset disease knowledge graph based on medical literature; Determine physical examination related information for different diseases according to the disease knowledge graph; The physical examination record of the examinee is obtained, and then the health reminder information of the examinee is extracted from the physical examination record based on various physical examination related information.

[0007] In some embodiments, determining the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes specifically includes: Obtain feedback information from each push node, and then determine the difference in information feedback from each push node; Determining differential characteristics of the physical examination records within the specified time period; The feedback difference when the physical examination information in the physical examination record is fed back to different pushing nodes is determined by the difference feature and the information difference of each pushing node.

[0008] In some embodiments, the basic data stream of extracting the physical examination information from the physical examination record and feeding it back to the examinee according to the health reminder information and the push data stream of each push node responding to the physical examination information specifically include: Divide the physical examination record based on the health prompt information to obtain basic physical examination data and push data responded by each push node; Extracting the physical examination information in the physical examination record based on the basic data and feeding it back to the basic data stream of the examinee; The push data stream of each push node in response to the physical examination information is extracted through the push data of each push node.

[0009] In some embodiments, the node screening of the current physical examination information of the examinee to obtain all the push pre-selected nodes specifically includes: Information to be pushed extracted from the physical examination information; Acquire the health reminder information of the examinee, compare the information to be pushed with the health reminder information, and obtain the difference information of the physical examination information; Get feedback information from each push node; All pre-selected nodes for pushing the physical examination information are determined according to all the feedback information and the difference information.

[0010] In some embodiments, determining the response confidence of each push pre-selected node based on all response deviations specifically includes: Determine the push priority of each push pre-selected node; The response confidence of each push pre-selected node is determined by all push priorities and the response deviation.

[0011] In some embodiments, the push node is a data node.

[0012] In a second aspect, the present application provides a physical examination information push system, including: The acquisition module is used to obtain the physical examination records of the examinee within a specified time period and determine the health reminder information of the examinee through a preset disease knowledge graph; A processing module, used to determine the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, and extract the basic data flow of the physical examination information fed back to the examinee and the push data flow of each push node responding to the physical examination information from the physical examination record according to the health prompt information; The processing module is further used to perform consistency check on the push data stream responded by each push node based on the basic data stream and the feedback difference, so as to obtain the response deviation of each push node; The processing module is also used to perform node screening on the current physical examination information of the examinee to obtain all the push pre-selected nodes; The execution module is used to determine the response confidence of each push pre-selected node based on all response deviations, and then push the current physical examination information of the examinee to the push pre-selected node whose response confidence is higher than a preset threshold.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned physical examination information push method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned physical examination information push method is implemented.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The present application provides a physical examination information push method and system. First, the physical examination records of the examinee within a specified time period are obtained, and the health prompt information of the examinee is determined through a preset disease knowledge graph; secondly, the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes is determined, and the basic data stream for feeding back the physical examination information to the examinee and the push data stream of each push node in response to the physical examination information are extracted from the physical examination record according to the health prompt information; then, based on the basic data stream and the feedback difference, the push data stream responded by each push node is respectively checked for consistency to obtain the response deviation of each push node; then, the current physical examination information of the examinee is node screened to obtain all push pre-selected nodes; finally, the response confidence of each push pre-selected node is determined based on all the response deviations, and the current physical examination information of the examinee is pushed to the push pre-selected node whose response confidence is higher than a preset threshold.

[0016] It can be seen that the present application determines the response confidence of each push pre-selected node through the response deviation, and then pushes the current physical examination information of the examinee to the push pre-selected node whose response confidence is higher than the preset threshold; first, the push pre-selected nodes of the physical examination information are preliminarily screened according to the information difference, and then the feedback levels of different push pre-selected nodes on the physical examination information are analyzed by calculating the response deviation, and the changing trend of the health status of the examinee is evaluated, and then the various push pre-selected nodes for pushing the physical examination records are optimized according to the feedback level obtained by the analysis, so as to ensure that the subsequent physical examination information is accurately and reasonably pushed to the push pre-selected nodes with small information deviation, which is conducive to improving the processing efficiency of the physical examination information; secondly, the push pre-selected nodes are screened and marked to determine the push pre-selected nodes. The push priority of the pre-selected nodes reduces the complexity of the push link, improves the efficiency of physical examination information processing, and can reduce the push error caused by information deviation, thereby improving the reliability of physical examination information push, and comprehensively determines the response confidence based on the completeness of the information received by the push node, the push priority and the response deviation; finally, the physical examination information is pushed to the push pre-selected nodes whose response confidence is higher than the preset threshold, and the physical examination information is pushed to the nodes with higher response confidence by giving priority to the response confidence, which can reduce the system resources for pushing the physical examination information and facilitate improving the credibility of the physical examination information push; in summary, the present application scheme can realize the confident response push of the physical examination information under the condition of multi-node coupling, thereby improving the credibility of the physical examination information push. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flow chart of a method for pushing physical examination information according to some embodiments of the present application; Figure 2 is a schematic diagram of a process for determining feedback difference according to some embodiments of the present application; Figure 3It is a schematic diagram of a process of determining and pushing a pre-selected node according to some embodiments of the present application; Figure 4 This is a schematic diagram of the structure of a physical examination information push system in some embodiments of the present application; Figure 5 It is a structural diagram of a computer device according to the method for pushing physical examination information applied in some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1 , which is an exemplary flow chart of a method for pushing physical examination information according to some embodiments of the present application. The method 100 for pushing physical examination information mainly includes the following steps: In step 101, the physical examination records of the examinee within a specified time period are obtained, and the health reminder information of the examinee is determined through a preset disease knowledge graph.

[0020] In specific implementation, obtaining the physical examination records of the examinee within the specified time period can be achieved in the following manner, namely: obtaining the physical examination records of the examinee within the specified time period from a medical database, wherein the medical database can be a document-type database (for example: MongoDB), and the physical examination records include: basic physical examination indicators, surgical examination information, internal medicine examination information, feedback information of each push node and other additional physical examination information, wherein the push node is a data node.

[0021] It should be noted that, due to the different physical examination frequencies of the examinees, the physical examination records of the examinees within the specified time period are obtained in this application. The specified time period is the time period from the past three years to the current moment. The physical examination frequency includes: annual examination, semi-annual examination and quarterly examination. If the examinee undergoes a physical examination in the same hospital, the physical examination record of the examinee can be stored in the medical database of the hospital. Each department is allocated a data node of the medical database, and the data node of each department is used as a push node. In addition, the physical examination record also includes time information related to the physical examination record.

[0022] In some embodiments, determining the health reminder information of the examinee through a preset disease knowledge graph can be achieved by the following steps: Preset disease knowledge graph based on medical literature; Determine physical examination related information for different diseases according to the disease knowledge graph; The physical examination record of the examinee is obtained, and then the health reminder information of the examinee is extracted from the physical examination record based on various physical examination related information.

[0023] It should be noted that, in this embodiment, presetting the disease knowledge graph based on medical literature refers to analyzing the medical literature, clinical diagnosis experience and expert knowledge related to different diseases, and constructing a disease knowledge graph. As a preferred embodiment, the knowledge graph model in the prior art can be used to analyze medical literature, clinical diagnosis experience and expert knowledge. The use of the knowledge graph model can efficiently process large-scale knowledge graphs. In other embodiments, other existing models can also be used for analysis, which is not limited here.

[0024] In specific implementation, determining the physical examination-related information of different diseases according to the disease knowledge graph can be achieved in the following manner, namely: training the disease knowledge graph as the training text of the semantic analysis model, and then outputting the information related to various diseases in the disease knowledge graph through the trained semantic analysis model, and using the outputted various types of information as the physical examination-related information of different diseases, the physical examination-related information refers to an information set composed of data related to different diseases, for example: an information set composed of physical examination data such as "blood sugar", "blood pressure", "blood lipids", "urine sugar", and "body weight index" related to diabetes; in addition, obtaining the physical examination record of the examinee, and then extracting the health reminder information of the examinee from the physical examination record based on each physical examination-related information can be achieved in the following manner, namely: obtaining the physical examination record of the examinee, pre-training a semantic analysis model with the physical examination-related information as training data, extracting the data related to different diseases in the physical examination record through the pre-trained semantic analysis model, and using the set composed of the extracted data as the health reminder information related to the corresponding disease.

[0025] It should be noted that the health reminder information in this application refers to the illness reminder information of the person being examined. The health reminder information is a data set composed of physical examination push information related to different diseases. The health reminder information is a data set screened and reorganized from the physical examination records for diseases or departments. The health reminder information related to different diseases is targeted at each disease, and each health reminder information can be pushed to different push nodes to facilitate different departments to feedback and respond to the physical examination information.

[0026] In step 102, the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes is determined, and the basic data stream for feeding back the physical examination information to the examinee and the push data stream for each push node to respond to the physical examination information are extracted from the physical examination record based on the health prompt information.

[0027] In some embodiments, reference Figure 2As shown, this figure is a schematic diagram of a process for determining feedback difference shown in some embodiments of the present application. In this embodiment, the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes can be determined by the following steps: In step 1021, feedback information of each push node is obtained, and then the difference degree of information feedback of each push node is determined; In step 1022, determining the difference characteristics of the physical examination records within the specified time period; In step 1023, the feedback difference degree when the physical examination information in the physical examination record is fed back to different pushing nodes is determined through the difference feature and the information difference degree of each pushing node.

[0028] In specific implementation, obtaining feedback information of each push node and then determining the information difference of each push node feedback can be achieved in the following manner, namely: first, the feedback information refers to the diagnosis and treatment recommendation information fed back by the doctor based on the physical examination data of the examinee, and the information fed back by each push node can be extracted by the keyword extraction function in the natural language processing technology, and the extracted information is used as the feedback information of each push node, wherein the keywords of the keyword extraction function can be set to: "diagnosis", "treatment recommendation", "recommendation" and other diagnostic instructions; then, using the unique hot encoding in the prior art to convert each feedback information into a vector, obtain different feedback information vectors, and use the mean vector of all feedback information vectors as the feedback mean vector, and then use the inverse of the cosine similarity between each feedback information vector and the feedback mean vector as the information difference of the push node corresponding to each feedback information, wherein when using the unique hot encoding to convert the feedback information into a vector, the direction of the vector can be random, and the information difference is an indicator to measure the degree of difference between the physical examination records when they are fed back at different push nodes.

[0029] In addition, determining the difference characteristics of the physical examination records within the specified time period can be achieved in the following manner, namely: performing autoregressive analysis on the physical examination records within the specified time period, and extracting the change differences of the same physical examination data during the autoregressive process, and then taking an array consisting of all the change differences as the difference characteristics of the physical examination records, wherein the difference characteristics represent the change differences of the same physical examination data in the physical examination records, and the same physical examination data refers to data of the same physical examination item, such as blood pressure, blood sugar, weight, height and data of other physical examination items.

[0030] In specific implementation, the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes is determined by the difference feature and the information difference of each push node, which can be achieved in the following manner, namely: the mean of all change differences in the difference feature is taken as the average change difference, and then the weighted sum of each information difference and the average time series difference is taken as the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, wherein the weight value when the information difference and the average time series difference are weighted summed can be determined in the following manner, namely: each information difference can be used as an independent variable in the process of autoregressive analysis of the physical examination record for comprehensive analysis, and the degree of influence of each information difference on the change difference in the process of the autoregressive analysis is obtained, and then the degree of influence of each information difference is taken as the weight value of the corresponding information difference, and the weight value of the average time series difference is 1-the weight value of the information difference.

[0031] It should be noted that the feedback difference in the present application is an indicator to measure the degree of difference when the physical examination information is fed back at different push nodes. The feedback difference is determined by comprehensively considering the difference characteristics and information difference, which is helpful to determine the push priority of each department in the feedback process. For example, the feedback difference can be used to identify which push nodes have the greatest impact on the feedback of the physical examination information, thereby providing resource allocation suggestions for the push of the physical examination information; in addition, when the physical examination information in the physical examination record is fed back to different push nodes, it is the process of pushing the physical examination information, that is, the medical system feeds back the physical examination information in the physical examination record to the push node, and the push node responds to the physical examination information and extracts the push data.

[0032] In some embodiments, the basic data stream of extracting the physical examination information from the physical examination record and feeding it back to the examinee according to the health reminder information and the push data stream of each push node responding to the physical examination information can be implemented by the following steps: Divide the physical examination record based on the health prompt information to obtain basic physical examination data and push data responded by each push node; Extracting the physical examination information in the physical examination record based on the basic data and feeding it back to the basic data stream of the examinee; The push data stream of each push node in response to the physical examination information is extracted through the push data of each push node.

[0033] It should be noted that the basic physical examination data in this application refers to information data related to the basic health status of the examinee, and the basic physical examination data includes physical examination indicators and routine examination data, wherein the physical examination indicators are prescribed health examination indicators, and the routine examination data refers to the height, weight, vision and other routine physical examination data obtained from the physical examination. In addition, the push data in this application refers to information data related to diseases or risk factors fed back by hospital departments, and the push data includes risk information of illness and related physical examination information, wherein the risk information refers to risk analysis information of the examinee's possible illness, and the related physical examination information refers to physical examination information related to the risk information.

[0034] In specific implementation, the physical examination records are divided based on the health prompt information to obtain basic physical examination data and push data responded by each push node, which can be achieved in the following manner, namely: the health prompt information is used as training data for a preset support vector machine model, so that the support vector machine model can identify routine examination data and risk information in the data, and the physical examination records are used as inputs of the support vector machine model, and then the basic physical examination data related to the routine examination data and the push data responded by each push node are extracted from the medical database through the support vector machine model, wherein the push data corresponding to different push nodes can use the risk information of the corresponding department to constrain the support vector machine model to distinguish the push data of different push nodes; as a preferred embodiment, the support vector machine model is selected to divide the physical examination records in order to improve the edge processing capability of the basic physical examination data and the push data, so as to better distinguish the basic physical examination data and the push data. In other embodiments, other existing models can also be used for division, which is not limited here.

[0035] In addition, the basic data stream for extracting the physical examination information in the physical examination record based on the basic data and feeding it back to the examinee can be implemented in the following manner, namely: using the Wireshark network analysis tool to capture the data stream of the basic physical examination data during the process of extracting the basic physical examination data from the medical database, and then using the extracted data stream as the basic data stream for feeding back the physical examination information in the physical examination record to the examinee. In other embodiments, other network analysis tools can also be used for capture, which is not limited here.

[0036] In specific implementation, the push data stream of each push node responding to the physical examination information can be extracted through the push data of each push node in the following manner, namely: using the Wireshark network analysis tool to capture the data stream of each push node responding to the physical examination information (that is, the data stream when each push node responds to the push data). In other embodiments, other network analysis tools can also be used for capture, which will not be repeated here.

[0037] It should be noted that, in the present application, the physical examination information in the physical examination record being fed back to the examinee and the push node responding to push data are two processes of pushing the physical examination information. The physical examination information in the physical examination record being fed back to the examinee means that the routine examination data in the physical examination information needs to be pushed to the examinee, and the push node responding to push data means the process in which the medical system feeds back the physical examination information and the push node responds to push data, which will not be repeated here.

[0038] In step 103, consistency check is performed on the push data stream responded by each push node based on the basic data stream and the feedback difference, so as to obtain the response deviation of each push node.

[0039] In some embodiments, based on the basic data stream and the feedback difference, the consistency check is performed on the push data stream responded by each push node, and the response deviation of each push node is obtained by the following steps: Determine the consistent information volume when each push node responds to push data through the basic data stream and the push data stream responded by each push node; Determine, by the basic data flow, a response threshold when all push nodes respond to push data; Based on the response threshold, the consistent information amount when each push node responds to the push data, and the feedback difference, information verification is performed on the push data stream responded by each push node to obtain the response deviation of each push node.

[0040] In addition, the consistent information amount when each push node responds to the push data is determined by the basic data stream and the push data stream responded by each push node, which can be achieved in the following manner, namely: for the process of each push node responding to the push data, the natural language model is used to extract the risk information in the push data at the push node, and the risk information and the same information in the basic physical examination data are used as consistent information, and then the repeated data stream in the basic data stream and the push data stream responded by the push node is used as the data stream of the consistent information, and then the information amount of the data stream of the consistent information is used as the consistent information amount when the push node responds to the push data, and then the consistent information amount when each push node responds to the push data is obtained, wherein the information amount of the data stream can be read by the Wireshark tool, and the consistent information amount refers to the repetition amount of the data stream between the basic data and the push data, and the consistent information amount can reflect the information coupling generated by the push node.

[0041] It should be noted that, in this embodiment, the response threshold refers to the reference standard for whether the physical examination record is pushed to the push node, and the value of the response threshold is 0-1; in specific implementation, the response threshold of all push nodes responding to push data determined by the basic data stream can be implemented in the following manner, namely: obtaining the response value of each push node, the response value refers to the amount of data when the push node responds to push data, which can be captured by the Wireshark network analysis tool, and the amount of information of the basic data stream is used as a constraint condition for the pre-trained machine learning algorithm, and then the basic data stream and all response values ​​are used as input data for the pre-trained machine learning algorithm, and the response threshold for pushing the physical examination record is output by the pre-trained machine learning algorithm; in addition, in this embodiment, the machine learning algorithm can be pre-trained by providing physical examination records of other examinees through the hospital physical examination center. As a preferred embodiment, the machine learning algorithm can adopt a decision tree algorithm, which is conducive to improving the credibility of the output response threshold. Other machine learning algorithms can also be used in other embodiments, which are not limited here.

[0042] In specific implementation, based on the response threshold, the consistent information amount when each push node responds to the push data, and the feedback difference, the push data stream responded by each push node is verified, and the response deviation of each push node can be obtained in the following manner, namely: for the process of each push node responding to the push data, when the push node response value reaches the response threshold, the ratio of the feedback difference and the consistent information amount of the push node is used as the coupling weight, and then the difference between the information amount of the data stream when the push node responds to the push data and the weighted information amount of the push node (the weighted information amount = coupling weight * information amount) is used as the response deviation of the push node, thereby obtaining the response deviation of each push node.

[0043] It should be noted that the response deviation in the present application is an indicator to measure the degree of difference between information caused by information coupling when the physical examination records are pushed to each push node, that is: the larger the response deviation, the greater the degree of coupling when the physical examination records are pushed to each push node, and the more obvious the difference in information; the smaller the response deviation, the smaller the degree of coupling when the physical examination records are pushed to each push node, and the more obvious the difference in information. By calculating the response deviation, the process of pushing physical examination records can be optimized. In addition, in an embodiment of the present application, a consistency check is performed on the push data stream responded to by each push node, which is conducive to reducing information coupling.

[0044] In step 104, the physical examination information of the examinee is currently screened for nodes to obtain all the push pre-selected nodes.

[0045] It should be noted that the current physical examination information of the examinee in this application refers to the information of the examinee's most recent physical examination. In addition to the time difference, the physical examination information and the physical examination records in the aforementioned embodiments also include differences in specific numerical values ​​of the physical examination contents. Other information attributes are consistent with the physical examination records and will not be repeated here.

[0046] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the push pre-selected nodes shown in some embodiments of the present application. In this embodiment, the physical examination information of the physical examinee is screened for nodes, and all the push pre-selected nodes can be obtained by the following steps: In step 1041, the information to be pushed is extracted from the physical examination information; In step 1042, the health reminder information of the examinee is obtained, and the information to be pushed is compared with the health reminder information to obtain difference information of the physical examination information; In step 1043, feedback information of each push node is obtained; In step 1044, all pre-selected nodes for pushing the physical examination information are determined based on all feedback information and the difference information.

[0047] In specific implementation, the information to be pushed extracted from the physical examination information can be implemented in the following manner, namely: the support vector machine model trained in the aforementioned embodiment can be used to extract the risk information in the physical examination information, and the set of extracted risk information is used as the information to be pushed when the examinee is under physical examination; the health prompt information of the examinee is obtained, and the information to be pushed and the health prompt information are compared to obtain the difference information of the physical examination information, which can be implemented in the following manner, namely: a linear regression analysis model can be established based on the health prompt information, and then the difference information of the information to be pushed and the health prompt information is output through the model, wherein the difference information refers to the set of numerical differences between the information to be pushed and the health prompt information in the physical examination information, and the difference information reflects the degree of deviation between the current health status of the examinee and the expected health information, and analyzing the difference information is helpful to identify abnormal changes in the physical examination data of the examinee.

[0048] In addition, in the specific implementation, determining all the push pre-selected nodes of the physical examination information based on all the feedback information and the difference information can be achieved in the following manner, namely: using the unique hot encoding in the prior art to convert all the feedback information and the difference information into vectors respectively, to obtain the feedback information vector corresponding to each push node and the difference information vector of the difference information, and respectively taking the inverse of the Euclidean distance between the feedback information vector corresponding to each feedback information and the difference information vector as the information difference value of the corresponding feedback information, and then sorting all the information difference values ​​in order from large to small, selecting the top 80% of the information difference values, and taking the push nodes of the feedback information corresponding to the selected information difference values ​​as the push pre-selected nodes of the physical examination information, and then obtaining all the push pre-selected nodes of the physical examination information.

[0049] It should be noted that the purpose of screening and pushing pre-selected nodes in the present application is to reduce the resource occupancy of the system during push, and to screen out push nodes with smaller differences so that the screened out push nodes no longer participate in the push of the current physical examination information of the examinee, thereby facilitating the optimization of the strategy for pushing physical examination information, saving the push consumption of physical examination information, and improving data processing efficiency. By determining the push pre-selected nodes, it is also helpful to reduce the push error caused by information deviation, thereby improving the reliability of pushing physical examination information.

[0050] In step 105, the response confidence of each push pre-selected node is determined based on all response deviations, and then the current physical examination information of the examinee is pushed to the push pre-selected node whose response confidence is higher than a preset threshold.

[0051] In some embodiments, determining the response confidence of each push pre-selected node based on all response deviations may be implemented by the following steps: Determine the push priority of each push pre-selected node; The response confidence of each push pre-selected node is determined by all push priorities and the response deviation.

[0052] It should be noted that the push priority is divided into three levels: high, medium and low. In specific implementation, the push priority of each push pre-selected node can be determined in the following manner, namely: all push pre-selected nodes can be sorted in descending order according to the information difference value in the aforementioned embodiment, and then all the sorted push nodes are evenly divided into three push priorities of "high", "medium" and "low", so as to obtain the push priority of each push node.

[0053] In specific implementation, determining the response confidence of each push pre-selected node through all push priorities and the response deviation can be implemented in the following manner, namely: a completeness scoring model can be established for each push node based on all push priorities, and the push tag information and the response deviation of each push node can be scored through the completeness scoring model, and then the completeness of each push node receiving the physical examination information can be calculated through the completeness scoring model. As a preferred embodiment, the scoring formula of the completeness scoring model can adopt the following formula, namely: completeness = push priority weight * (1-response deviation), wherein the push priority weight can be determined by the ratio between the push priorities of all push pre-selected nodes. It should be noted that the completeness of each push node receiving the physical examination information is negatively correlated with the response deviation, namely: the larger the response deviation, the smaller the completeness of the physical examination information, and the smaller the response deviation, the greater the completeness of the physical examination information. The completeness of each push node receiving the physical examination information can be used as an important basis for whether to push, that is: the completeness corresponding to the push pre-selected node can be used as the response confidence of the corresponding push pre-selected node.

[0054] In specific implementation, the current physical examination information of the examinee is pushed to a push pre-selected node whose response confidence is higher than a preset threshold, wherein it should be noted that the preset threshold can be set to the average value of all response confidences when the examinee's last physical examination information was pushed, and the initial value of the preset threshold can be set between 0.5-0.6; in addition, the response confidence is an indicator to measure the reliability of pushing the physical examination information, and the response confidence is determined based on the completeness of the physical examination information received by the push node, the priority in the push tag information, and the response deviation. Therefore, the response confidence can be used to indicate the reliability of the push node when processing the physical examination information, for example: the response confidence is helpful to select the push node that is most suitable for processing the examinee's physical examination information, and the response confidence can prioritize the physical examination information to be pushed to the push node with a higher response confidence, which can reduce the system resources for pushing the physical examination information, and thus help to improve the credibility of the physical examination information push.

[0055] On the other hand, in some embodiments, the present application provides a physical examination information push system, referring to Figure 4 , which is a schematic diagram of the structure of a physical examination information push system in some embodiments of the present application, the physical examination information push system 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows: Acquisition module 401, in this application, acquisition module 401 is mainly used to obtain the physical examination records of the examinee within a specified time period, and determine the health reminder information of the examinee through a preset disease knowledge graph; Processing module 402, in the present application, the processing module 402 is used to determine the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, and extract the basic data flow of the physical examination information fed back to the examinee and the push data flow of each push node responding to the physical examination information from the physical examination record according to the health prompt information; The processing module 402 in the present application is further used to perform consistency check on the push data stream responded by each push node based on the basic data stream and the feedback difference, and obtain the response deviation of each push node; In the present application, the processing module 402 is also used to perform node screening on the current physical examination information of the examinee to obtain all the push pre-selected nodes; Execution module 403, in the present application, the execution module 403 is mainly used to determine the response confidence of each push pre-selected node based on all response deviations, and then push the current physical examination information of the examinee to the push pre-selected node whose response confidence is higher than a preset threshold.

[0056] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned physical examination information push method.

[0057] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device using a method for pushing physical examination information according to some embodiments of the present application. The method for pushing physical examination information in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0058] The processor 501 may be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0059] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0060] The memory 503 may be a read only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read only memory (EEPROM), a compact disc read only memory (CD ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0061] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The physical examination information push method in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0062] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0063] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0064] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0065] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned physical examination information push method is implemented.

[0066] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for pushing physical examination information, characterized in that: The steps include: Obtain the physical examination records of the examinee within a specified time period, and determine the examinee's health reminder information through the preset disease knowledge graph; Determine the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, and extract the basic data flow of the physical examination information fed back to the examinee and the push data flow of each push node responding to the physical examination information from the physical examination record according to the health prompt information; Based on the basic data stream and the feedback difference, consistency check is performed on the push data stream responded by each push node to obtain the response deviation of each push node; Perform node screening on the examinee's current physical examination information to obtain all push pre-selected nodes; The response confidence of each push pre-selected node is determined based on all response deviations, and then the current physical examination information of the examinee is pushed to the push pre-selected node whose response confidence is higher than a preset threshold.

2. The method according to claim 1, characterized in that The health tips for the examinee determined through the preset disease knowledge graph include: Preset disease knowledge graph based on medical literature; Determine physical examination related information for different diseases according to the disease knowledge graph; The physical examination record of the examinee is obtained, and then the health reminder information of the examinee is extracted from the physical examination record based on various physical examination related information.

3. The method according to claim 1, characterized in that Determining the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes specifically includes: Obtain feedback information from each push node, and then determine the difference in information feedback from each push node; Determining differential characteristics of the physical examination records within the specified time period; The feedback difference when the physical examination information in the physical examination record is fed back to different pushing nodes is determined by the difference feature and the information difference of each pushing node.

4. The method according to claim 1, characterized in that The basic data flow of extracting the physical examination information from the physical examination record according to the health reminder information and feeding it back to the examinee and the push data flow of each push node responding to the physical examination information specifically include: Divide the physical examination record based on the health prompt information to obtain basic physical examination data and push data responded by each push node; Extracting the physical examination information in the physical examination record based on the basic data and feeding it back to the basic data stream of the examinee; The push data stream of each push node in response to the physical examination information is extracted through the push data of each push node.

5. The method according to claim 1, characterized in that Filter the nodes of the examinee's current physical examination information to obtain all the push pre-selected nodes, including: Information to be pushed extracted from the physical examination information; Acquire the health reminder information of the examinee, compare the information to be pushed with the health reminder information, and obtain the difference information of the physical examination information; Get feedback information from each push node; All pre-selected nodes for pushing the physical examination information are determined according to all the feedback information and the difference information.

6. The method according to claim 1, characterized in that The response confidence of each push pre-selected node is determined based on all response deviations, including: Determine the push priority of each push pre-selected node; The response confidence of each push pre-selected node is determined by all push priorities and the response deviation.

7. The method according to claim 1, characterized in that The push node is a data node.

8. A physical examination information push system, characterized in that: include: The acquisition module is used to obtain the physical examination records of the examinee within a specified time period and determine the health reminder information of the examinee through a preset disease knowledge graph; A processing module, used to determine the feedback difference when the physical examination information in the physical examination record is fed back to different push nodes, and extract the basic data flow of the physical examination information fed back to the examinee and the push data flow of each push node responding to the physical examination information from the physical examination record according to the health prompt information; The processing module is further used to perform consistency check on the push data stream responded by each push node based on the basic data stream and the feedback difference, so as to obtain the response deviation of each push node; The processing module is also used to perform node screening on the current physical examination information of the examinee to obtain all the push pre-selected nodes; The execution module is used to determine the response confidence of each push pre-selected node based on all response deviations, and then push the current physical examination information of the examinee to the push pre-selected node whose response confidence is higher than a preset threshold.

9. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the physical examination information pushing method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the physical examination information pushing method according to any one of claims 1 to 7 is implemented.

Images