WO2022022042A1 - 监控数据上报方法、装置、计算机设备及存储介质 - Google Patents

监控数据上报方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2022022042A1
WO2022022042A1 PCT/CN2021/096701 CN2021096701W WO2022022042A1 WO 2022022042 A1 WO2022022042 A1 WO 2022022042A1 CN 2021096701 W CN2021096701 W CN 2021096701W WO 2022022042 A1 WO2022022042 A1 WO 2022022042A1
Authority
WO
WIPO (PCT)
Prior art keywords
monitoring
feature information
preset
information
target
Prior art date
Application number
PCT/CN2021/096701
Other languages
English (en)
French (fr)
Inventor
蒋雪涵
孙行智
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2022022042A1 publication Critical patent/WO2022022042A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Definitions

  • the present application relates to the technical field of artificial intelligence, and in particular, to a monitoring data reporting method, device, computer equipment and storage medium.
  • medical behavior quality monitoring is one of the effective means to standardize medical behavior.
  • automated medical behavior quality monitoring has been widely used, such as disease data reporting systems, infectious disease direct reporting systems, etc.
  • the inventor realized that information monitoring by information monitoring departments often fails to achieve the preset goals. For example, for the disease reporting system of infectious diseases, medical institutions often report directly to the National Center for Disease Control and Prevention, and the country conducts unified outbreak monitoring. .
  • Embodiments of the present application provide a monitoring data reporting method, device, computer equipment, and storage medium, so as to solve the problem that the monitoring of information by an information monitoring department often fails to achieve a preset target.
  • a method for reporting monitoring data comprising:
  • the first monitoring feature information of the object to be monitored input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information corresponding to the first monitoring feature information from the preset data monitoring system. All monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • the target observation values If at least one of the target observation values is greater than or equal to a preset target estimated value corresponding to the target observation value, insert the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule middle;
  • the preset feature information is in the preset feature information.
  • the detection feature information of the warning state After determining that preset feature information exists in the first monitoring feature information by the retrieved spatiotemporal monitoring system, conduct investigation and detection on the to-be-monitored object to obtain an investigation and detection result; the preset feature information is in the preset feature information. the detection feature information of the warning state;
  • the investigation detection result is the first result
  • the first monitoring feature information is associated with the first result and reported to a preset recipient.
  • a monitoring data reporting device comprising:
  • the first monitoring feature information acquisition module is used to obtain the first monitoring feature information of the object to be monitored, input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information from the preset data monitoring system All monitoring groups corresponding to the first monitoring feature information; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • a target observation value acquisition module configured to acquire target observation values corresponding to each of the monitoring groups after performing spatiotemporal detection on each of the monitoring groups;
  • An information insertion module configured to insert the first monitoring feature information into the first monitoring feature information according to a preset feature insertion rule when at least one of the target observed values is greater than or equal to a preset target estimated value corresponding to the target observed value In the information list corresponding to the monitoring group;
  • a space-time monitoring system retrieval module configured to retrieve a space-time monitoring system corresponding to each monitoring feature in the first monitoring feature information inserted into the information list from a preset monitoring database
  • an investigation and detection module configured to conduct investigation and detection on the object to be monitored after determining that preset feature information exists in the first monitoring feature information through the retrieved spatiotemporal monitoring system, and obtain an investigation and detection result;
  • the preset The characteristic information is the characteristic information in a preset warning state;
  • a data reporting module configured to associate the first monitoring feature information with the first result and report it to a preset recipient when the investigation and detection result is the first result.
  • a computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer-readable instructions:
  • the first monitoring feature information of the object to be monitored input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information corresponding to the first monitoring feature information from the preset data monitoring system. All monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • the target observation values If at least one of the target observation values is greater than or equal to a preset target estimated value corresponding to the target observation value, insert the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule middle;
  • the preset feature information is in the preset feature information. the characteristic information of the warning state;
  • the investigation detection result is the first result
  • the first monitoring feature information is associated with the first result and reported to a preset recipient.
  • One or more readable storage media storing computer-readable instructions, wherein the computer-readable instructions, when executed by one or more processors, cause the one or more processors to perform the following steps:
  • the first monitoring feature information of the object to be monitored input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information corresponding to the first monitoring feature information from the preset data monitoring system. All monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • the target observation values If at least one of the target observation values is greater than or equal to a preset target estimated value corresponding to the target observation value, insert the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule middle;
  • the preset feature information is in the preset feature information. the characteristic information of the warning state;
  • the investigation detection result is the first result
  • the first monitoring feature information is associated with the first result and reported to the preset recipient.
  • the above monitoring data reporting method, device, computer equipment and storage medium obtain the target observation value through a method based on spatiotemporal detection, and determine whether the target observation value exceeds the historical contemporaneous level data, that is, compare the target observation value with the historical contemporaneous level data , from the time dimension and space dimension in the spatio-temporal detection, to determine whether the monitoring group has a phenomenon of spatial aggregation or a sudden increase in the time range, and then determine that the monitoring features in the current first monitoring feature information that exceed the historical level of the same period have abnormal conditions, Then, the object to be monitored is investigated and detected, so that after the detection is completed, the first monitoring feature information of the object to be monitored is associated with the investigation result and reported to the preset receiver, so that the receiver can quickly understand the scope of the local area and the preset If an abnormality occurs in a certain information data within a certain time, the abnormal situation can be controlled in advance. While avoiding the continuous occurrence of the abnormal situation, it is ensured that the response plan is introduced in advance, so that the information
  • FIG. 1 is a schematic diagram of an application environment of a monitoring data reporting method in an embodiment of the present application
  • FIG. 2 is a flowchart of a monitoring data reporting method in an embodiment of the present application
  • step S12 in the monitoring data reporting method in an embodiment of the present application
  • FIG. 4 is another flowchart of a monitoring data reporting method in an embodiment of the present application.
  • FIG. 5 is a schematic block diagram of an apparatus for reporting monitoring data in an embodiment of the present application.
  • FIG. 6 is a schematic block diagram of a target observation value acquisition module in a monitoring data reporting device in an embodiment of the present application
  • FIG. 7 is another principle block diagram of the monitoring data reporting device in an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a computer device in an embodiment of the present application.
  • the monitoring data reporting method provided by the embodiment of the present application can be applied in the application environment shown in FIG. 1 .
  • the monitoring data reporting method is applied in a data reporting system.
  • the data reporting system includes a client and a server as shown in FIG. 1 , and the client and the server communicate through the network to solve the monitoring of information by the information monitoring department. Often unable to achieve pre-set goals.
  • the client also known as the client, refers to the program corresponding to the server and providing local services for the client.
  • Clients can be installed on, but not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.
  • the server can be implemented as an independent server or a server cluster composed of multiple servers.
  • a method for reporting monitoring data is provided, and the method is applied to the server in FIG. 1 as an example for description, including the following steps:
  • S11 Acquire first monitoring feature information of the object to be monitored, input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information from the preset data monitoring system All corresponding monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group.
  • the objects to be monitored can be set as different objects according to application scenarios.
  • the first monitoring feature information may include, but is not limited to, basic information of the object to be monitored (such as gender, age, etc.), disease history, medication history, symptom complaints or inspection information, etc.;
  • the first monitoring feature information may be user information (such as ID, mobile phone number, etc.), download data, demand submission data, or purchase data, and the like.
  • the preset data monitoring system may be a CDSS system (Clinical Decision Support System, clinical decision support system), and the preset data monitoring system includes multiple groups of detection groups.
  • the monitoring group is a group corresponding to the first monitoring feature information, and one monitoring feature in the first monitoring feature information corresponds to one monitoring group.
  • one monitoring feature in the first monitoring feature information is a cold and a fever
  • the corresponding The monitoring group may be an influenza detection group; assuming that one monitoring feature in the first monitoring feature information is music, the corresponding monitoring group may be musicians or singers.
  • the spatiotemporal detection refers to the detection of the monitoring group based on time (eg, within a period of time) and space (eg, an area that is close to or associated with the object to be monitored).
  • the target observation value refers to a value that triggers a change in the monitoring group after spatiotemporal detection of the monitoring group (eg, a value that changes the characteristics of the monitoring group in time and/or space).
  • the target observation value of the influenza detection group or the target observation value of the musician detection group.
  • the estimated value of the preset target is determined according to the historical data value corresponding to the monitoring group.
  • the value of the historically changed value of the monitoring group can be used as the preset target. estimated value.
  • the preset feature insertion rule can be random insertion.
  • the information list refers to an information list composed of historical detection data, for example, the information list may be an information list containing known infectious diseases.
  • the preset target insertion rule inserts the first monitoring feature information into the information list corresponding to the monitoring group, that is, considering that although the sample detection group corresponds to the second monitoring feature information, for For a sudden abnormal data, it may be a new type of detection group, so the second monitoring feature information should be added to the known information list to verify the inserted information list.
  • S14 retrieve, from a preset monitoring database, a spatiotemporal monitoring system corresponding to each monitoring feature in the first monitoring feature information inserted into the information list.
  • the spatiotemporal monitoring system refers to a system that performs real-time monitoring of each monitoring feature. It is understandable that if the monitoring feature is an influenza feature, the corresponding spatiotemporal monitoring system will monitor the influenza population. During the period, the influenza population may increase, or it may be reduce.
  • the first monitoring feature information after inserting the first monitoring feature information into the information list corresponding to the monitoring group according to the preset feature insertion rule, retrieve and insert all the information in the information list from the preset monitoring database. Describe the spatiotemporal monitoring system corresponding to each monitoring feature in the first monitoring feature information, so as to determine whether there is feature information in the preset early warning state in the first monitoring feature information through each spatiotemporal monitoring system, that is, the feature information in the preset early warning state Information corresponding to the monitoring feature.
  • S15 After determining that preset feature information exists in the first monitoring feature information by the retrieved spatiotemporal monitoring system, conduct investigation and detection on the to-be-monitored object to obtain an investigation and detection result; the preset feature information is in The characteristic information of the pre-warning state is preset.
  • the survey test results refer to the results obtained after conducting an epidemiological survey or interview data survey on the subject to be monitored.
  • the preset early warning state may refer to a state corresponding to a monitoring feature in the first monitoring feature information during an outbreak or an epidemic, and the preset early warning state may also refer to a monitoring feature corresponding to a sudden increase in the number of visits in the first monitoring feature information. status.
  • the object to be monitored is investigated and detected to obtain an investigation and detection result.
  • a monitoring feature in the first monitoring feature information is an influenza feature
  • the spatiotemporal monitoring system corresponding to the influenza feature is retrieved to be an influenza monitoring system
  • the influenza monitoring system determines that the influenza symptoms are in an outbreak period (that is, influenza) in real-time monitoring.
  • the population gradually increases and the growth rate is very fast), that is, it is determined that there is preset feature information in the first monitoring feature information, and the subject to be monitored is tested for influenza symptoms, and an investigation and test result is obtained.
  • the first result refers to a result of determining that the monitoring feature in the first monitoring feature information that is the preset feature information is real.
  • the preset recipient may be a database storing various monitoring features, or may be a preset monitoring database in the above embodiment.
  • the object to be monitored is investigated and detected, and after the survey and detection results are obtained, if it is determined that the first monitoring feature information If the monitoring feature in the monitoring feature information that is the preset feature information is real, the first monitoring feature information is associated with the first result and reported to the preset recipient.
  • the first monitoring feature information is compared with the first. The result is associated and reported to the preset recipient.
  • the template can be filled in according to the information in the preset data monitoring system, the information to be uploaded is automatically extracted from the first monitoring feature information, and the required The uploaded information is automatically filled in the corresponding position in the information filling template, thereby reducing the tediousness of manual reporting and filling in the data manually.
  • a method based on spatiotemporal detection is used to determine whether there is a monitoring group that exceeds the historical level of the same period, so as to determine whether there is a spatial aggregation phenomenon or a sudden increase in the time range in the monitoring group through the time dimension and the space dimension, and then It is determined that the monitoring features in the current first monitoring feature information that exceed the historical level of the same period have abnormal conditions, and then the object to be monitored is investigated and detected, so that after the detection is completed, the first monitoring feature information of the object to be monitored is associated with the survey results.
  • a countermeasure is introduced to make the information monitoring of each object to be monitored reach the preset target.
  • the first monitoring feature information may be stored in the blockchain.
  • Blockchain is a storage structure of encrypted and chained transactions formed by blocks.
  • the header of each block can include not only the hash values of all transactions in the block, but also the hash values of all transactions in the previous block, so that the transactions in the block can be tamper-proof based on the hash value.
  • anti-counterfeiting the newly generated transaction is filled into the block and after the consensus of the nodes in the blockchain network, it will be appended to the end of the blockchain to form a chain growth.
  • step S12 that is, after acquiring at least one target observation value corresponding to each of the monitoring groups, the method further includes:
  • the target observation values are smaller than the preset target estimated value corresponding to the target observation value, obtain the regular recommendation information corresponding to the first monitoring feature information from the preset data monitoring system and push it to the object to be monitored.
  • the conventional recommendation information refers to the recommendation information conventionally given for the monitoring features in the first monitoring feature information in the historical data.
  • the first target observation value corresponding to the target observation value is obtained from the preset data monitoring system.
  • the regular recommendation information corresponding to the monitoring feature information is pushed to the object to be monitored.
  • one monitoring feature in the first monitoring feature information is cough, and the corresponding monitoring group is the respiratory tract group; after spatiotemporal detection of the respiratory tract group, the change value of the respiratory tract group during the spatiotemporal detection process (that is, the target observation value) are less than the preset target estimated value (that is, the historical contemporaneous level of the respiratory tract group), then the change of the respiratory tract group compared with the historical contemporaneous level is a normal phenomenon.
  • the corresponding routine recommendation information given to the respiratory group in the historical data is obtained, and the routine recommendation information is pushed to the object to be monitored.
  • the method for pushing the general recommendation information to the object to be monitored may be: sending the general recommendation information to a mobile terminal associated with the object to be monitored.
  • the method after inserting the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule, the method further includes:
  • the first monitoring feature information after inserting the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule, determine whether there is a preset in the first monitoring feature information through the retrieved spatiotemporal monitoring system feature information; after it is determined that the preset feature information does not exist in the first monitoring feature information, and none of the monitoring features representing the first monitoring feature information is in the preset warning state, the first monitoring feature is obtained from the preset data monitoring system and the first monitoring feature General recommendation information corresponding to the information, and push the general recommendation information to the object to be monitored.
  • step S12 that is, after performing spatiotemporal detection on each of the monitoring groups, acquiring at least one target observation value corresponding to each of the monitoring groups includes the following steps:
  • the detection time may be the time point when the first monitoring feature information is obtained, or the current month in which the first monitoring feature information is obtained, or the current season in which the first monitoring feature information is obtained.
  • the detection time is a specific time point at which the first monitoring feature information is obtained, so as to improve the accuracy of subsequent time detection for the monitoring group corresponding to the first monitoring feature information.
  • S122 Determine the time prediction observation value corresponding to the monitoring group according to the detection time and the preset seasonal prediction method.
  • the preset seasonal prediction method is the seasonal autoregressive integrated moving average method, which integrates autoregressive prediction (that is, using historical data corresponding to the monitoring group to predict the time observation value of the current monitoring group) and moving average Prediction (ie, predicting the temporal observations of the current monitoring population using the residuals of historical data corresponding to the monitoring population).
  • the time-predicted observations are obtained from time-based detection of the monitoring population.
  • a preset seasonal prediction method is determined according to the detection time, and a time prediction observation value corresponding to the monitoring group is determined.
  • a SARIMA model in R language which can be expressed as (e,d,q)(E,D,Q) m ; where (e,d,q) is the non-seasonal correlation part, and e is non-seasonal The order of the autoregression of the correlation part; d is the order of the difference of the non-seasonal correlation part; q is the order of the moving average of the non-seasonal part.
  • y t is the number of occurrences of the predicted time at time t (in this embodiment, it refers to predicting the time observation value of the current monitoring group by using the historical data corresponding to the monitoring group).
  • ⁇ t is the estimated residual error at time t (that is, the difference between the predicted data and the actual data for the monitoring population).
  • (1- ⁇ 1 B m - ⁇ - ⁇ PB mE ) is an E-order autoregressive function with a seasonal number of m;
  • D y t represents the d-order difference for the original y t Afterwards, the D-order difference is performed with the season number as m;
  • (1+ ⁇ 1 B+ ⁇ + ⁇ q B q )(1+ ⁇ 1 B m + ⁇ + ⁇ Q B mQ ) ⁇ t means considering the seasonal q-order residual and the Q-order residual prediction with the seasonal number m Time observations for the current monitoring population.
  • the parameter m represents the number of seasons, generally 4; d and D can be set according to user requirements, indicating the order of the difference; e, q, E and Q can be determined by AIC (Akaike's Information Criterion, Akaike Information Criterion); ⁇ 1 , ⁇ , ⁇ P , ⁇ 1 , ⁇ , ⁇ q , ⁇ 1 , ⁇ , ⁇ Q , etc. can be obtained by maximum likelihood estimation.
  • the above model building process can be directly implemented by packaged software packages in R language or Python language.
  • S123 Using the scanning statistics method, perform statistical verification on the monitoring group in a preset search window, and obtain a spatial prediction observation value corresponding to the monitoring group.
  • the scanning statistical method refers to a method of performing statistical verification on the number of changes in the monitored population within a certain space-time range.
  • the preset search window refers to the preset spatiotemporal detection range.
  • the preset search window can be the area corresponding to the monitoring group in the historical data.
  • the preset search window can be regarded as a cylinder, and its bottom surface is the space area, high is time, optionally, the preset search window can be a Kulldorff search window.
  • the spatial prediction observations refer to the spatial-based detection of the monitoring population.
  • the position of the detection area corresponding to the first monitoring feature information (such as the area position of the detection point where the object to be monitored is located) may be obtained, and according to the position of the detection area, a scanning statistical method is adopted.
  • Statistical verification is performed on the monitoring group within a preset search window (the location area set in the search window may be the same as or larger than the above-mentioned detection area) to obtain the spatial prediction observation value corresponding to the monitoring group.
  • LR Lowerihood ratio, likelihood ratio
  • the LR expression is as follows:
  • L 0 refers to the maximum likelihood value of the baseline incidence
  • L(z) refers to the observed incidence within the scan area z.
  • S124 Generate a target observation value according to the time prediction observation value and the space prediction observation value.
  • the time prediction observation value corresponding to the monitoring group is determined, and a scanning statistical method is used to perform statistics on the monitoring group within a preset search window.
  • the target observation value is generated according to the time prediction observation value and the space prediction observation value.
  • spatiotemporal detection is performed on the monitoring group to obtain target observation values.
  • time detection taking into account the seasonal cycle and trend, predicting the current time observation value based on the information of the same period in history can better avoid the phenomenon of sudden increase in data due to seasonality (such as the occurrence of influenza in winter). The phenomenon of increasing, or during the winter and summer vacations, the amount of access data will increase), thereby improving the accuracy of time-based detection; in terms of spatial detection, the likelihood ratio can be used to more sensitively determine whether the monitoring group has abnormally increased data. , and can realize the monitoring of rare events, in addition, different scanning granularity can be selected to improve the accuracy of spatial detection of monitoring groups.
  • step S11 the following steps are further included:
  • S21 Acquire second monitoring feature information of the object to be monitored and a preset standard vector set; the preset standard vector set includes at least one standard vector.
  • the second monitoring feature information is the feature information of the object to be monitored.
  • the second monitoring feature information may include but not limited to basic information (such as gender, age), disease history, medication history , symptom complaint, inspection and inspection information, etc.; when the object to be monitored is a system visitor, the first monitoring feature information can be user information (such as ID, mobile phone number, etc.), download data, demand submission data, or purchase data, etc.
  • the preset standard vector set contains at least one standard vector, and the standard vector refers to a diagnostic standard generated based on historical data. By comparing the second monitoring feature information with each standard vector, the similarity of any object to be monitored can be determined. Whether the second monitoring feature information meets the standard associated with the standard vector (that is, whether the feature in the second monitoring feature information matches the feature in any standard vector).
  • S22 Obtain the target similarity between the second monitoring feature information and each standard vector, and when all target similarities are less than a preset similarity threshold, record the second monitoring feature information as the first monitoring feature information.
  • the second monitoring feature information after acquiring the second monitoring feature information of the object to be monitored and the preset standard vector set, performing feature identification on the second monitoring feature information to obtain the monitoring feature vector, and comparing the similarity between the monitoring feature vector and each standard vector , and obtain the target similarity between the second monitoring feature information and each standard vector, when all target similarities are less than the preset similarity threshold, it means that there is no standard vector matching the second monitoring feature information, then the first The second monitoring feature information is recorded as the first monitoring feature information.
  • step S22 that is, before acquiring the target similarity between the second monitoring feature information and each of the standard vectors, includes the following steps:
  • the feature identification refers to a processing method of extracting feature vectors in the second monitoring feature information through a convolutional neural network.
  • feature identification is performed on the second monitoring feature information.
  • the second monitoring feature information performs feature identification to obtain a monitoring feature vector corresponding to the second monitoring feature information.
  • the similarity between the monitoring feature vector and each of the standard vectors is compared to obtain the target similarity between the monitoring feature vector and each of the standard vectors.
  • the similarity comparison refers to the process of determining whether the features in the monitoring feature vector are similar to the features of each standard vector.
  • the target similarity refers to the similarity value between the monitoring feature vector and a standard vector.
  • the similarity between the monitoring feature vector and each standard vector is compared to obtain the monitoring feature vector and each standard vector.
  • the target similarity between the monitoring feature vector and any one of the standard vectors is determined as having an associated relationship with the standard vector when the target similarity between the monitoring feature vector and any one of the standard vectors is greater than the preset similarity threshold.
  • the method further includes:
  • any target similarity is greater than or equal to a preset similarity threshold, it means that the second monitoring feature information complies with one of the standard vectors corresponding to
  • the association rule is to associate the second monitoring feature information and the standard vector corresponding to the target similarity, and report the associated second monitoring feature information and the standard vector to the preset recipient.
  • the second monitoring feature information is a cold and a fever
  • there is an influenza standard vector in the standard vector and the feature information of the influenza standard vector is a cold and a fever. Therefore, the second monitoring feature information is compared with each standard vector.
  • the target similarity between the second monitoring feature information and the influenza standard vector is greater than the preset similarity threshold, which means that the second monitoring feature information conforms to the association rule corresponding to the influenza standard vector ( That is, it is determined that the object to be monitored corresponding to the second monitoring feature information is an influenza patient), then the second monitoring feature information is associated with the influenza standard vector, and is reported to the preset recipient at the same time, so that the second monitoring feature information can be further processed. check.
  • an apparatus for reporting monitoring data is provided, and the apparatus for reporting monitoring data is in one-to-one correspondence with the method for reporting monitoring data in the foregoing embodiment.
  • the monitoring data reporting device includes a first monitoring feature information acquisition module 11 , a target observation value acquisition module 12 , an information insertion module 13 , a spatiotemporal monitoring system retrieval module 14 , an investigation detection module 15 and a data reporting module 16 .
  • the detailed description of each functional module is as follows:
  • the first monitoring feature information acquisition module 11 is used to obtain the first monitoring feature information of the object to be monitored, and input the first monitoring feature information into a preset data monitoring system, from the preset data monitoring system. All monitoring groups corresponding to the first monitoring feature information are extracted; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group.
  • the target observation value obtaining module 12 is configured to obtain target observation values corresponding to each of the monitoring groups after performing spatiotemporal detection on each of the monitoring groups.
  • the information inserting module 13 is configured to insert the first monitoring feature information into the first monitoring feature information according to a preset feature insertion rule when at least one of the target observed values is greater than or equal to a preset target estimated value corresponding to the target observed value. in the information list corresponding to the monitoring groups described above.
  • the space-time monitoring system retrieval module 14 is configured to retrieve the space-time monitoring system corresponding to each monitoring feature in the first monitoring feature information inserted into the information list from a preset monitoring database.
  • the investigation and detection module 15 is configured to conduct investigation and detection on the to-be-monitored object after determining that preset characteristic information exists in the first monitoring characteristic information through the retrieved spatiotemporal monitoring system, and obtain an investigation and detection result;
  • the preset feature information is the detection feature information in a preset warning state;
  • the data reporting module 16 is configured to associate the first monitoring feature information with the first result and report it to a preset recipient when the investigation and detection result is the first result.
  • the monitoring data reporting device further includes:
  • a first recommendation module configured to obtain information related to the first monitoring feature from the preset data monitoring system when all the target observed values are less than the preset target estimated value corresponding to the target observed value The corresponding regular recommendation information is pushed to the object to be monitored.
  • the monitoring data reporting device further includes:
  • the second recommendation module is configured to obtain the first monitoring feature from the preset data monitoring system after determining that there is no preset feature information in the first monitoring feature information through the retrieved spatiotemporal monitoring system
  • the general recommendation information corresponding to the information is pushed to the object to be monitored.
  • the target observation value acquisition module 12 includes the following units:
  • a detection time acquisition unit 121 configured to acquire the detection time of the first monitoring feature information
  • a time prediction unit 122 configured to determine a time prediction observation value corresponding to the monitoring group according to the detection time and a preset seasonal prediction method
  • the spatial prediction unit 123 is configured to use a scanning statistical method to perform statistical verification on the monitoring group within a preset search window, and obtain a spatial prediction observation value corresponding to the monitoring group;
  • the target observation value generating unit 124 is configured to generate the target observation value according to the time prediction observation value and the space prediction observation value.
  • the monitoring data reporting device includes:
  • the data acquisition module 21 is configured to acquire the second monitoring feature information of the object to be monitored and a preset standard vector set; the preset standard vector set includes at least one standard vector.
  • the detection group extraction module 22 is used to obtain the target similarity between the second monitoring feature information and each standard vector, and when the target similarity is less than a preset similarity threshold, the second monitoring feature information Record as the first monitoring feature information.
  • the monitoring data reporting device further includes:
  • a feature identification module configured to perform feature identification on the second monitoring feature information to obtain a monitoring feature vector corresponding to the second monitoring feature information.
  • the similarity comparison module is configured to compare the similarity between the monitoring feature vector and each of the standard vectors, and obtain the target similarity between the monitoring feature vector and each of the standard vectors.
  • the monitoring data reporting device further includes:
  • a data reporting module is used to associate the second monitoring feature information and the standard vector corresponding to the target similarity when any of the target similarity is greater than or equal to a preset similarity threshold, and associate the associated The second monitoring feature information and the standard vector are reported to a preset recipient.
  • Each module in the above monitoring data reporting device may be implemented in whole or in part by software, hardware and combinations thereof.
  • the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 .
  • the computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a readable storage medium, an internal memory.
  • the readable storage medium stores an operating system, computer readable instructions and a database.
  • the internal memory provides an environment for the execution of the operating system and computer-readable instructions in the readable storage medium.
  • the database of the computer device is used to store the data used in the monitoring data reporting method in the above-mentioned embodiment, or store the data used in the monitoring data reporting method in the above-mentioned embodiment.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, the method for reporting monitoring data in the foregoing embodiment is implemented.
  • the readable storage medium provided by this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
  • a computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer-readable instructions:
  • the first monitoring feature information of the object to be monitored input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information corresponding to the first monitoring feature information from the preset data monitoring system. All monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • the target observation values If at least one of the target observation values is greater than or equal to a preset target estimated value corresponding to the target observation value, insert the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule middle;
  • the preset feature information is in the preset feature information. the characteristic information of the warning state;
  • the investigation detection result is the first result
  • the first monitoring feature information is associated with the first result and reported to a preset recipient.
  • One or more readable storage media storing computer-readable instructions, wherein the computer-readable instructions, when executed by one or more processors, cause the one or more processors to perform the following steps:
  • the first monitoring feature information of the object to be monitored input the first monitoring feature information into a preset data monitoring system, and extract the first monitoring feature information corresponding to the first monitoring feature information from the preset data monitoring system. All monitoring groups; the first monitoring feature information includes at least one monitoring feature, and one monitoring feature corresponds to one monitoring group;
  • the target observation values If at least one of the target observation values is greater than or equal to a preset target estimated value corresponding to the target observation value, insert the first monitoring feature information into the information list corresponding to the monitoring group according to a preset feature insertion rule middle;
  • the preset feature information is in the preset feature information. the characteristic information of the warning state;
  • the investigation detection result is the first result
  • the first monitoring feature information is associated with the first result and reported to a preset recipient.
  • Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Alarm Systems (AREA)

Abstract

本申请涉及人工智能技术领域，应用于智慧医疗领域中，以便推动智慧城市的建设，揭露了一种监控数据上报方法、装置、计算机设备及存储介质。该方法通过在对与待监控对象对应的各监控群体进行时空检测之后，获取的至少一个目标观测值大于或等于与其对应的预设目标估计值时，将第一监控特征信息插入与监控群体对应的信息列表中；自预设的监测数据库中调取与插入后的信息列表中的各监控特征对应的时空监测系统；通过时空监测系统确定第一监控特征信息中存在预设特征信息，对待监控对象进行调查检测得到调查检测结果为第一结果时，将第一监控特征信息与第一结果关联并上报至预设接收方。本申请解决信息监控部门对于信息的监控无法达到预设目标的问题。

Description

监控数据上报方法、装置、计算机设备及存储介质
本申请要求于2020年7月28日提交中国专利局、申请号为202010738668.1，发明名称为“监控数据上报方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术领域，尤其涉及一种监控数据上报方法、装置、计算机设备及存储介质。
背景技术
随着科学技术的发展，对于信息监控的需求越来越高。比如，在医疗行业中，医疗行为质量监控是规范医疗行为的有效手段之一，目前，自动化进行医疗行为质量监控已被普遍使用，例如病情数据上报系统、传染病直报系统等。发明人意识到，信息监控部门对于信息的监控往往无法达到预设目标，比如，对于传染病的病情上报系统来说，常由医疗机构直接上报国家疾控中心，由国家进行统一的疫情爆发监测。但是这样的机制存在不足之处：首先，对于一些确诊周期长的疾病，在疾病确诊之前可能由于疾病的传染性导致出现了局部区域症状暴发，因此不利于在疾病暴发早期控制疾病的传播；其次，病情上报系统中存储的是已知的疾病数据，对于新的疾病无法快速确诊上报。
申请内容
本申请实施例提供一种监控数据上报方法、装置、计算机设备及存储介质，以解决信息监控部门对于信息的监控往往无法达到预设目标的问题。
一种监控数据上报方法，包括：
获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述检测特征信息；
在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
一种监控数据上报装置，包括：
第一监控特征信息获取模块，用于获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
目标观测值获取模块，用于在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
信息插入模块，用于在至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
时空监测系统调取模块，用于自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
调查检测模块，用于通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
数据上报模块，用于在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现如下步骤：
获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
一个或多个存储有计算机可读指令的可读存储介质，其中，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并 上报至预设接收方。
上述监控数据上报方法、装置、计算机设备及存储介质，通过基于时空检测的方法获取目标观测值，确定该目标观测值是否超过历史同期水平数据，也即通过目标观测值与历史同期水平数据进行比较，从时空检测中的时间维度以及空间维度，确定该监控群体是否存在空间聚集现象或者时间范围内的骤增，进而认定当前第一监控特征信息中超过历史同期水平的监控特征出现了异常状况，进而对该待监控对象进行调查检测，以在检测完毕之后，将待监控对象的第一监控特征信息与调查结果关联上报至预设接收方，进而使得接收方快速了解在局部区域范围和预设时间内，出现某一信息数据的异常，进而可以提前控制异常状况，在避免该异常状况持续发生的同时，确保提前推出应对方案，使得对各待监控对象的信息监控达到预设目标。
本申请的一个或多个实施例的细节在下面的附图和描述中提出，本申请的其他特征和优点将从说明书、附图以及权利要求变得明显。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一实施例中监控数据上报方法的一应用环境示意图；
图2是本申请一实施例中监控数据上报方法的一流程图；
图3是本申请一实施例中监控数据上报方法中步骤S12的一流程图；
图4是本申请一实施例中监控数据上报方法的另一流程图；
图5是本申请一实施例中监控数据上报装置的一原理框图；
图6是本申请一实施例中监控数据上报装置中目标观测值获取模块的一原理框图；
图7是本申请一实施例中监控数据上报装置的另一原理框图；
图8是本申请一实施例中计算机设备的一示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例提供的监控数据上报方法，该监控数据上报方法可应用如图1所示的应用环境中。具体地，该监控数据上报方法应用在数据上报系统中，该数据上报系统包括如图1所示的客户端和服务器，客户端与服务器通过网络进行通信，用于解决信息监控部门对于信息的监控往往无法达到预设目标的问题。其中，客户端又称为用户端，是指与服务器相对应,为客户提供本地服务的程序。客户端可安装在但不限于各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备上。服务器可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一实施例中，如图2所示，提供一种监控数据上报方法，以该方法应用在图1中的服务器为例进行说明，包括如下步骤：
S11：获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体。
其中，待监控对象可以根据应用场景设定为不同的对象。比如，在待监控对象为患者时，该第一监控特征信息可以包括但不限于待监控对象的基本信息(如性别、年龄等)、疾病史、用药史、症状主诉或者检验检查信息等；又比如，在待监控对象为系统访问者时，该第一监控特征信息可以为用户信息(如ID，手机号等)、下载数据、需求提交数据或者购买数据等。预设的数据监测系统可以为CDSS系统(Clinical Decision Support System，临床辅助决策系统)，该预设的数据监测系统中包含多组检测群体。监控群体为与第一监控特征信息对应的群体，第一监控特征信息中一个监控特征对应一个监控群体，示例性地，假若第一监控特征信息中的一个监控特征为感冒和发热，则对应的监控群体可以为流感检测群体；假设第一监控特征信息中的一个监控特征为音乐，则对应的监控群体可以为音乐人或者歌手。
S12：在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值。
其中，时空检测指的是对监控群体进行基于时间(如一段时间内)以及空间(如与待监控对象相近或者关联的区域)的检测。目标观测值指的是对监控群体进行时空检测后，该监控群体中触发变化的值(如监控群体在时间和/或空间上特征发生变化的值)。
具体地，在获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体之后，对各监控群体进行时间检测以及空间检测，以观测每一监控群体在预设时间以及预设空间内的变化值，也即与每一监控群体对应的目标观测值。示例性地，如上述实施例中提到的流感检测群体的目标观测值；或者音乐人检测群体的目标观测值。
S13：若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中。
其中，预设目标估计值是根据与监控群体对应的历史数据值来确定的，示例性地，在与上述时空检测对应的时间段以及空间内，监控群体历史发生变化的值可以作为预设目标估计值。预设的特征插入规则可以为随机插入。信息列表指的是由历史检测数据构成的信息列表，示例性地，该信息列表可以为包含已知传染病的信息列表。
具体地，具体地，在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值之后，对每一目标观测值与该目标观测值对应的预设目标估计值进行比较，若存在目标观测值大于或等于与其对应的预设目标观测值，则认为出现了与该目标观测值对应的监控群体的数据发生异常(如疾病暴发、导致系统崩溃的骤增访问量等)，则根据预设的特征插入规则，将第一监控特征信息插入与监控群体对应的信息列表中，也即考虑到虽然样本检测群体是与第二监控特征信息相对应的，但是对于一个突然发生异常的数据来说，可能为新的一类检测群体，故应该将第二监控特征信息加入已知的信息列表中，以对该插入后的信息列表进行校验。
S14：自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统。
其中，时空监测系统指的是对各监控特征进行实时监控的系统，可以理解地，如监控特征为流感特征时，对应的时空监测系统会对流感人群进行监测，期间流感人群可能增多，也可能减少。
具体地，在根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统，以通过各时空监测系统确定第一监控特征信息中是否存在处于预设预警状态的特征信息，也即处于预设预警状态的监控特征对应的信息。
S15：通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息。
其中，调查检测结果指的是对待监控对象进行如流行病学调查或者访问数据调查之后得到的结果。预设预警状态可以指的是第一监控特征信息中处于暴发或者疫情期间的监控特征对应的状态，预设预警状态还可以指的是第一监控特征信息中处于访问量骤增的监控特征对应的状态。
具体地，在自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统之后，通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述所述待监控对象进行调查检测，得到调查检测结果。示例性地，假设第一监控特征信息中的一个监控特征为流感特征，调取流感特征对应的时空监测系统为流感监测系统，该流感监测系统实时监测内确定流感症状处于暴发期(也即流感人群逐渐增多且增长速度很快)，也即确定第一监控特征信息中存在预设特征信息，对待监控对象进行流感病状检测，得到调查检测结果。
S16：在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
其中，第一结果指的是确定第一监控特征信息中为预设特征信息的监控特征为真实的结果。预设接收方可以为存储各类监控特征的数据库，也可以为上述实施例中的预设的监测数据库。
具体地，在通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果之后，若判定该第一监控特征信息中为预设特征信息的监控特征为真实的，则将第一监控特征信息与第一结果关联并上报至预设接收方。示例性地，假设对待监控对象进行流感病状检测之后，判定该待监控对象确实为流感病例，或者该待监控对象存在与流感病例相关联的新的病例，则将第一监控特征信息与第一结果关联上报至预设接收方。
进一步地，在获取到待监控对象的第一监控特征信息之后，可以根据预设的数据监测系统中的信息填写模板，自动从第一监控特征信息中抽取出需要上传的信息，并将该需要上传的信息自动填入信息填写模板中相对应的位置，从而减少人工上报手动填写数据的繁琐。
在本实施例中，通过基于时空检测的方法，确定是否存在超过历史同期水平的监控群体，以通过时间维度以及空间维度，确定该监控群体是否存在空间聚集现象或者时间范围内的骤增，进而认定当前第一监控特征信息中超过历史同期水平的监控特征出现了异常状况，进而对该待监控对象进行调查检测，以在检测完毕之后，将待监控对象的第一监控特征信息与调查结果关联上报至预设接收方，进而使得接收方快速了解在局部区域范围和预设时间内，出现某一信息数据的异常，进而可以提前控制异常状况，在避免该异常状况持续发生的同时，确保提前推出应对方案，使得对各待监控对象的信息监控达到预设目标。
在另一具体实施例中，为了保证上述实施例中的第一监控特征信息的私密以及安全性，可以将第一监控特征信息存储在区块链中。其中，区块链(Blockchain)，是由区块(Block)形成的加密的、链式的交易的存储结构。
例如，每个区块的头部既可以包括区块中所有交易的哈希值，同时也包含前一个区块中所有交易的哈希值，从而基于哈希值实现区块中交易的防篡改和防伪造；新产生的交易被填充到区块并经过区块链网络中节点的共识后，会被追加到区块链的尾部从而形成链式的增长。
在一实施例中，步骤S12之后，也即在获取与各所述监控群体对应的至少一个目标观测值之后，还包括
若所有所述目标观测值均小于与该目标观测值对应的所述预设目标估计值，则自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
其中，常规推荐信息指的是历史数据中，针对于第一监控特征信息中的监控特征常规给出的推荐信息。
具体地，在获取与各监控群体对应的至少一个目标观测值之后，若所有目标观测值均小于与该目标观测值对应的预设目标估计值，则从预设的数据监测系统获取与第一监控特征信息对应的常规推荐信息并推送至待监控对象。
示例性地，假设第一监控特征信息中一个监控特征为咳嗽，对应的监控群体为呼吸道群体；在对呼吸道群体进行时空检测之后，该呼吸道群体在时空检测过程中的变化值(也即目标观测值)均小于预设目标估计值(也即该呼吸道群体的历史同期水平)，则表征与历史同期水平比较该呼吸道群体的变化为正常现象，不需要启动防范预警，进而从预设的数据监测系统中，获取历史数据中对呼吸道群体给出的对应的常规推荐信息，并将常规推荐信息推送至待监控对象。其中，将常规推荐信息推送至待监控对象的方法可以为：将常规推荐信息发送至与待监控对象关联的移动终端中。
在一实施例中，在根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，还包括：
通过调取的所述时空监测系统确定所述第一监控特征信息中不存在预设特征信息之后，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
具体地，在根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，通过调取的时空监测系统确定第一监控特征信息中是否存在预设特征信息；在确定第一监控特征信息中不存在预设特征信息之后，表征第一监控特征信息的监控特征均没有处于预设预警状态，则从预设的数据监测系统获取与第一监控特征信息对应的常规推荐信息，并将该常规推荐信息推送至待监控对象。
在一实施例中，如图3所示，步骤S12中，也即在对各所述监控群体进行时空检测之后，获取与各所述监控群体对应的至少一个目标观测值，包括如下步骤：
S121：获取第一监控特征信息的检测时间。
其中，检测时间可以为获取到第一监控特征信息的时间点，或者获取到第一监控特征信息当前所处的月份，亦或者是获取到第一监控特征信息当前所处的季节等。优选地，该检测时间为获取第一监控特征信息的具体时间点，以提高后续对第一监控特征信息对应的监控群体进行时间检测的准确性。
S122：根据检测时间以及预设的季节性预测方法，确定与监控群体对应的时间预测观测值。
其中，预设的季节性预测方法为季节自回归整合移动平均值方法，该方法整合了自回归预测(也即利用与监控群体对应的历史数据预测当前监控群体的时间观测值)以及移动平均值预测(也即利用与监控群体对应的历史数据残差预测当前监控群体的时间观测值)。时间预测观测值为对监控群体进行基于时间检测得到的。
具体地，在获取第一监控特征信息的检测时间之后，根据检测时间确定预设的季节性预测方法，确定与监控群体对应的时间预测观测值。进一步地，在R语言中存在一个SARIMA模型可表示为(e,d,q)(E,D,Q) m；其中，(e,d,q)表示为非季节相关部分，e表示非季节相关部分的自回归的阶数；d表示非季节相关部分的差分的阶数；q表示非季部分移动平均的阶数。(E,D,Q) m表示为季节相关部分，m＝4(四个季节)；E表示季节相关部 分的自回归的阶数；D表示季节相关部分的差分的阶数；Q表示季节部分移动平均的阶数。该模型具体的表达式为：
Figure PCTCN2021096701-appb-000001
其中，y t为t时刻所预测时间的发生数(在本实施例中指的是利用与监控群体对应的历史数据预测当前监控群体的时间观测值)。ε t为t时刻估计的残差(也即对监控群体的预测数据与实际数据的差值)。B为一种操作符，可以返回上一步的值(如By t＝y t-1)。在该表达式中，
Figure PCTCN2021096701-appb-000002
为非季节相关部分的e阶自回归函数；
(1-ω 1B m-Λ-ωPB mE)为季节数为m的E阶自回归函数；(1-B) d(1-B m) Dy t表示对于原始的y t进行d阶差分后在以季节数为m进行D阶差分；
(1+θ 1B+Λ+θ qB q)(1+σ 1B m+Λ+σ QB mQ)ε t表示考虑季节性q阶残差和季节数为m的Q阶残差预测当前监控群体的时间观测值。参数m表示季节数，一般为4；d和D可以根据用户需求进行设定，表示差分的阶数；e、q、E以及Q可以通过AIC(Akaike’s Information Criterion，赤池信息准则)确定；
Figure PCTCN2021096701-appb-000003
ω 1，Λ，ω P，θ 1，Λ，θ q，σ 1，Λ，σ Q等可以通过最大似然估计得到。上述模型建立过程都可以通过R语言或者Python语言中封装好的软件包直接实现。
S123：采用扫描统计方法，在预设搜索窗内对监控群体进行统计校验，得到与监控群体对应的空间预测观测值。
其中，扫描统计方法指的是对一定时空范围内监控群体发生变化的数量进行统计校验的方法。预设搜索窗指的是预设的时空检测范围，该预设搜索窗可以为历史数据中与监控群体对应所处的区域范围，该预设搜索窗可以视为一个圆柱体，其底面为空间区域，高为时间，可选地，预设搜索窗可以采用如Kulldorff搜索窗。空间预测观测值指的是对监控群体进行基于空间检测得到的。
具体地，在对监控群体进行统计校验之前，可以获取第一监控特征信息对应的检测区域位置(如待监控对象所处检测点的区域位置)，根据该检测区域位置，通过采用扫描统计方法在预设搜索窗内(该搜索窗设置的位置区域可以与上述检测区域位置相同或者更大的范围)对监控群体进行统计校验，得到与监控群体对应的空间预测观测值。
进一步地，在任意一个预设搜索窗内，可以通过LR(Likelihood ratio，似然比)判断监控群体是否发生异常增高的数据，具体地，该LR表达式如下：
Figure PCTCN2021096701-appb-000004
其中，L 0指的是基线发生率的最大似然值；L(z)指的是扫描区域范围z之内观测的发生率。采用LR可以更加灵敏判断监控群体是否发生数据的异常增高，并能够实现对罕见事件的监测，此外还可以选择不同的扫描粒度，以提高对监控群体进行空间检测的准确率。
S124：根据时间预测观测值以及空间预测观测值，生成目标观测值。
具体地，在根据所述检测时间以及预设的季节性预测方法，确定与所述监控群体对应的时间预测观测值，以及采用扫描统计方法，在预设搜索窗内对所述监控群体进行统计校验，得到与所述监控群体对应的空间预测观测值之后，根据时间预测观测值以及空间预测观测值生成目标观测值。
在本实施例中，通过结合时间检测以及空间检测，对监控群体进行时空检测，以得到目标观测值。在时间检测方面，考虑到了季节性的周期和趋势，根据历史同期的信息预测当前的时间观测值，可以较好的规避了由于季节性带来的数据骤增的现象(如冬季流感人群会出现增多的现象，或者处于寒暑假假期，访问数据量会出现增多的现象)，进而提高基于时间检测的准确率；在空间检测方面，通过似然比可以更加灵敏判断监控群体是否发生数据的异常增高，并能够实现对罕见事件的监测，此外还可以选择不同的扫描粒度，以提高对监控群体进行空间检测的准确率。
在一实施例中，如图4所示，在步骤S11之前，还包括如下步骤：
S21：获取待监控对象的第二监控特征信息以及预设的标准向量集；所述预设的标准向量集包括至少一个标准向量。
其中，第二监控特征信息为待监控对象的特征信息，比如，在待监控对象为患者时，该第二监控特征信息可以包括但不限于基本信息(如性别、年龄)、疾病史、用药史、症状主诉、检验检查信息等；在待监控对象为系统访问者时，该第一监控特征信息可以为用户信息(如ID，手机号等)、下载数据、需求提交数据或者购买数据等。预设的标准向量集中包含至少一个标准向量，该标准向量指的是基于历史数据生成的诊断标准，可以通过对第二监控特征信息与各标准向量进行相似度比较，从而确定任意待监控对象的第二监控特征信息中是否达到符合与标准向量关联的标准(也即第二监控特征信息中的特征是否与任意一个标准向量中的特征相匹配)。
S22：获取第二监控特征信息与各标准向量之间的目标相似度，在所有目标相似度均小于预设相似度阈值时，将第二监控特征信息记录为第一监控特征信息。
具体地，在获取待监控对象的第二监控特征信息以及预设的标准向量集之后，对第二监控特征信息进行特征识别得到监控特征向量后，将监控特征向量与各标准向量进行相似度比较，并获取第二监控特征信息与各标准向量之间的目标相似度，在所有目标相似度均小于预设相似度阈值时，表征不存在与第二监控特征信息匹配的标准向量，则将第二监控特征信息记录为第一监控特征信息。
在一实施例中，步骤S22中，也即获取所述第二监控特征信息与各所述标准向量之间的目标相似度之前，包括如下步骤：
对所述第二监控特征信息进行特征识别，得到与所述第二监控特征信息对应的监控特征向量。
其中，特征识别指的是通过卷积神经网络提取第二监控特征信息中的特征向量的处理方法。
具体地，在获取待监控对象的第二监控特征信息之后，对第二监控特征信息进行特征识别，进一步地，可以通过将第二监控特征信息输入至预设的卷积神经网络中，对第二监控特征信息进行特征识别，以得到与第二监控特征信息对应的监控特征向量。
对所述监控特征向量与每一所述标准向量进行相似度比较，得到所述监控特征向量与各所述标准向量之间的目标相似度。
其中，相似度比较指的是确定监控特征向量中的特征与每一标准向量的特征是否相似的过程。目标相似度指的是监控特征向量与个标准向量之间的相似度值。
具体地，在对第二监控特征信息进行特征识别，得到与第二监控特征信息对应的监控特征向量之后，将监控特征向量与每一标准向量进行相似度比较，得到监控特征向量与各标准向量之间的目标相似度，以在监控特征向量与任意一个标准向量之间的目标相似度大于预设相似度阈值时，将监控特征向量确定为与该标准向量具有关联关系。
在一实施例中，在获取所述第二监控特征信息与各所述标准向量之间的目标相似度之后，还包括：
在任一所述目标相似度值大于或等于预设相似阈值时，将所述第二监控特征信息以及与该目标相似度对应的所述标准向量关联，并将关联后的所述第二监控特征信息以及所述标准向量上报至预设接收方。
具体地，在获取第二监控特征信息与各标准向量之间的目标相似度之后，若任意一个目标相似度大于或等于预设相似度阈值，表征该第二监控特征信息符合其中一个标准向量对应的关联规则，则将第二监控特征信息以及该目标相似度对应的标准向量关联，并将关联后的第二监控特征信息以及标准向量上报至预设接收方。
示例性地，假设第二监控特征信息为感冒以及发热，而标准向量中存在流感标准向量，该流感标准向量的特征信息即为感冒以及发热，因此在对第二监控特征信息与各标准向量进行相似度比较的过程中，会出现第二监控特征信息与流感标准向量之间的目标相似度大于预设相似度阈值的情况，则表征第二监控特征信息符合于流感标准向量对应的关联规则(也即认定该第二监控特征信息对应的待监控对象为流感患者)，则将第二监控特征信息与流感标准向量关联，同时上报至预设接收方，以对第二监控特征信息进行进一步的校验。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在一实施例中，提供一种监控数据上报装置，该监控数据上报装置与上述实施例中监控数据上报方法一一对应。如图5所示，该监控数据上报装置包括第一监控特征信息获取模块11、目标观测值获取模块12、信息插入模块13、时空监测系统调取模块14、调查检测模块15和数据上报模块16。各功能模块详细说明如下：
第一监控特征信息获取模块11，用于获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体。
目标观测值获取模块12，用于在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值。
信息插入模块13，用于在至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值时，根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中。
时空监测系统调取模块14，用于自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统。
调查检测模块15，用于通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述检测特征信息；
数据上报模块16，用于在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
优选地，监控数据上报装置还包括：
第一推荐模块，用于在所有所述目标观测值均小于与该目标观测值对应的所述预设目 标估计值时，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
优选地，监控数据上报装置还包括：
第二推荐模块，用于通过调取的所述时空监测系统确定所述第一监控特征信息中不存在预设特征信息之后，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
优选地，如图6所示，目标观测值获取模块12包括如下单元：
检测时间获取单元121，用于获取所述第一监控特征信息的检测时间；
时间预测单元122，用于根据所述检测时间以及预设的季节性预测方法，确定与所述监控群体对应的时间预测观测值；
空间预测单元123，用于采用扫描统计方法，在预设搜索窗内对所述监控群体进行统计校验，得到与所述监控群体对应的空间预测观测值；
目标观测值生成单元124，用于根据所述时间预测观测值以及所述空间预测观测值，生成所述目标观测值。
优选地，该监控数据上报装置包括：
数据获取模块21，用于获取待监控对象的第二监控特征信息以及预设的标准向量集；所述预设的标准向量集包括至少一个标准向量。
检测群体提取模块22，用于获取所述第二监控特征信息与各所属标准向量之间的目标相似度，在所述目标相似度小于预设相似度阈值时，将所述第二监控特征信息记录为第一监控特征信息。
优选地，该监控数据上报装置还包括：
特征识别模块，用于对所述第二监控特征信息进行特征识别，得到与所述第二监控特征信息对应的监控特征向量。
相似度比较模块，用于对所述监控特征向量与每一所述标准向量进行相似度比较，得到所述监控特征向量与各所述标准向量之间的目标相似度。
优选地，监控数据上报装置还包括：
数据上报模块，用于在任一所述目标相似度大于或等于预设相似度阈值时，将所述第二监控特征信息以及与该目标相似度对应的所述标准向量关联，并将关联后的所述第二监控特征信息以及所述标准向量上报至预设接收方。
关于监控数据上报装置的具体限定可以参见上文中对于监控数据上报方法的限定，在此不再赘述。上述监控数据上报装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括可读存储介质、内存储器。该可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为可读存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储上述实施例中监控数据上报方法中所使用到的数据，或者，存储上述实施例中监控数据上报方法所使用到的数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现上述实施例中监控数据上报方法。本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。
一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上 运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现如下步骤：
获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
一个或多个存储有计算机可读指令的可读存储介质，其中，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质或者易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种监控数据上报方法，其中，包括：
    获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
    在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
    若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
    自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
    通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
    在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
  2. 如权利要求1所述的监控数据上报方法，其中，所述获取与各所述监控群体对应的至少一个目标观测值之后，还包括：
    若所有所述目标观测值均小于与该目标观测值对应的所述预设目标估计值，则自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  3. 如权利要求1所述的监控数据上报方法，其中，所述根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，还包括：
    通过调取的所述时空监测系统确定所述第一监控特征信息中不存在预设特征信息之后，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  4. 如权利要求1所述的监控数据上报方法，其中，所述在对各所述监控群体进行时空检测之后，获取与各所述监控群体对应的至少一个目标观测值，包括：
    获取所述第一监控特征信息的检测时间；
    根据所述检测时间以及预设的季节性预测方法，确定与所述监控群体对应的时间预测观测值；
    采用扫描统计方法，在预设搜索窗内对所述监控群体进行统计校验，得到与所述监控群体对应的空间预测观测值；
    根据所述时间预测观测值以及所述空间预测观测值，生成所述目标观测值。
  5. 如权利要求1所述的监控数据上报方法，其中，所述获取待监控对象的第一监控特征信息之后，还包括：
    获取待监控对象的第二监控特征信息以及预设的标准向量集；所述预设的标准向量集包括至少一个标准向量；
    获取所述第二监控特征信息与各所述标准向量之间的目标相似度；
    在所有所述目标相似度均小于预设相似度阈值时，将所述第二监控特征信息记录为第一监控特征信息。
  6. 如权利要求5所述的监控数据上报方法，其中，在获取所述第二监控特征信息与各所述标准向量之间的目标相似度之后，还包括：
    在任一所述目标相似度值大于或等于预设相似阈值时，将所述第二监控特征信息以及与该目标相似度对应的所述标准向量关联，并将关联后的所述第二监控特征信息以及所述标准向量上报至预设接收方。
  7. 如权利要求5所述的监控数据上报方法，其中，所述获取所述第二监控特征信息与各所述标准向量之间的目标相似度之前，包括：
    对所述第二监控特征信息进行特征识别，得到与所述第二监控特征信息中的所有所述样本特征对应的监控特征向量；
    对所述监控特征向量与每一所述标准向量进行相似度比较，得到所述监控特征向量与各所述标准向量之间的目标相似度。
  8. 一种监控数据上报装置，其中，包括：
    第一监控特征信息获取模块，用于获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
    目标观测值获取模块，用于在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
    信息插入模块，用于在至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
    时空监测系统调取模块，用于自预设的监测数据库中调取与插入所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
    调查检测模块，用于通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
    数据上报模块，用于在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
  9. 一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，其中，所述处理器执行所述计算机可读指令时实现如下步骤：
    获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
    在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
    若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
    自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
    通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
    在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
  10. 如权利要求9所述的计算机设备，其中，所述获取与各所述监控群体对应的至少一个目标观测值之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    若所有所述目标观测值均小于与该目标观测值对应的所述预设目标估计值，则自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  11. 如权利要求9所述的计算机设备，其中，所述根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    通过调取的所述时空监测系统确定所述第一监控特征信息中不存在预设特征信息之后，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  12. 如权利要求9所述的计算机设备，其中，所述在对各所述监控群体进行时空检测之后，获取与各所述监控群体对应的至少一个目标观测值，包括：
    获取所述第一监控特征信息的检测时间；
    根据所述检测时间以及预设的季节性预测方法，确定与所述监控群体对应的时间预测观测值；
    采用扫描统计方法，在预设搜索窗内对所述监控群体进行统计校验，得到与所述监控群体对应的空间预测观测值；
    根据所述时间预测观测值以及所述空间预测观测值，生成所述目标观测值。
  13. 如权利要求9所述的计算机设备，其中，所述获取待监控对象的第一监控特征信息之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    获取待监控对象的第二监控特征信息以及预设的标准向量集；所述预设的标准向量集包括至少一个标准向量；
    获取所述第二监控特征信息与各所述标准向量之间的目标相似度；
    在所有所述目标相似度均小于预设相似度阈值时，将所述第二监控特征信息记录为第一监控特征信息。
  14. 如权利要求13所述的计算机设备，其中，在获取所述第二监控特征信息与各所述标准向量之间的目标相似度之后，所述处理器执行所述计算机可读指令时还实现如下步骤：
    在任一所述目标相似度值大于或等于预设相似阈值时，将所述第二监控特征信息以及与该目标相似度对应的所述标准向量关联，并将关联后的所述第二监控特征信息以及所述标准向量上报至预设接收方。
  15. 一个或多个存储有计算机可读指令的可读存储介质，其中，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
    获取待监控对象的第一监控特征信息，并将所述第一监控特征信息输入至预设的数据监测系统，从所述预设的数据监测系统中抽取与所述第一监控特征信息对应的所有监控群体；所述第一监控特征信息中包含至少一个监控特征，一个所述监控特征对应一个所述监控群体；
    在对各所述监控群体进行时空检测之后，获取与各所述监控群体分别对应的目标观测值；
    若至少一个所述目标观测值大于或等于与该目标观测值对应的预设目标估计值，则根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中；
    自预设的监测数据库中调取与插入后的所述信息列表中的所述第一监控特征信息中的各监控特征分别对应的时空监测系统；
    通过调取的所述时空监测系统确定所述第一监控特征信息中存在预设特征信息之后，对所述待监控对象进行调查检测，得到调查检测结果；所述预设特征信息为处于预设预警状态的所述特征信息；
    在所述调查检测结果为第一结果时，将所述第一监控特征信息与所述第一结果关联并上报至预设接收方。
  16. 如权利要求15所述的可读存储介质，其中，所述获取与各所述监控群体对应的至少一个目标观测值之后，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    若所有所述目标观测值均小于与该目标观测值对应的所述预设目标估计值，则自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  17. 如权利要求15所述的可读存储介质，其中，所述根据预设的特征插入规则将所述第一监控特征信息插入与所述监控群体对应的信息列表中之后，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    通过调取的所述时空监测系统确定所述第一监控特征信息中不存在预设特征信息之后，自所述预设的数据监测系统获取与所述第一监控特征信息对应的常规推荐信息并推送至所述待监控对象。
  18. 如权利要求15所述的可读存储介质，其中，所述在对各所述监控群体进行时空检测之后，获取与各所述监控群体对应的至少一个目标观测值，包括：
    获取所述第一监控特征信息的检测时间；
    根据所述检测时间以及预设的季节性预测方法，确定与所述监控群体对应的时间预测观测值；
    采用扫描统计方法，在预设搜索窗内对所述监控群体进行统计校验，得到与所述监控群体对应的空间预测观测值；
    根据所述时间预测观测值以及所述空间预测观测值，生成所述目标观测值。
  19. 如权利要求15所述的可读存储介质，其中，所述获取待监控对象的第一监控特征信息之后，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    获取待监控对象的第二监控特征信息以及预设的标准向量集；所述预设的标准向量集包括至少一个标准向量；
    获取所述第二监控特征信息与各所述标准向量之间的目标相似度；
    在所有所述目标相似度均小于预设相似度阈值时，将所述第二监控特征信息记录为第一监控特征信息。
  20. 如权利要求19所述的可读存储介质，其中，在获取所述第二监控特征信息与各所述标准向量之间的目标相似度之后，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    在任一所述目标相似度值大于或等于预设相似阈值时，将所述第二监控特征信息以及与该目标相似度对应的所述标准向量关联，并将关联后的所述第二监控特征信息以及所述标准向量上报至预设接收方。
PCT/CN2021/096701 2020-07-28 2021-05-28 监控数据上报方法、装置、计算机设备及存储介质 WO2022022042A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010738668.1A CN111885181B (zh) 2020-07-28 2020-07-28 监控数据上报方法、装置、计算机设备及存储介质
CN202010738668.1 2020-07-28

Publications (1)

Publication Number Publication Date
WO2022022042A1 true WO2022022042A1 (zh) 2022-02-03

Family

ID=73200893

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/096701 WO2022022042A1 (zh) 2020-07-28 2021-05-28 监控数据上报方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN111885181B (zh)
WO (1) WO2022022042A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111885181B (zh) * 2020-07-28 2023-02-28 平安科技（深圳）有限公司 监控数据上报方法、装置、计算机设备及存储介质
CN115515184B (zh) * 2022-11-04 2023-04-07 北京众森信和科技有限公司 一种业务数据的发送方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093106A (zh) * 2013-01-25 2013-05-08 上海市浦东新区疾病预防控制中心 大型活动中多源数据的传染病症状监测与预警方法
CN106326635A (zh) * 2016-08-08 2017-01-11 捷开通讯(深圳)有限公司 一种信息监测方法及系统
US20180173854A1 (en) * 2016-12-21 2018-06-21 Cerner Innovation, Inc. Monitoring predictive models
CN108565023A (zh) * 2018-03-16 2018-09-21 夏伟 一种儿童疾病防控监测方法、装置和系统
CN109935338A (zh) * 2019-03-07 2019-06-25 平安科技（深圳）有限公司 基于机器学习的数据预测处理方法、装置和计算机设备
CN111885181A (zh) * 2020-07-28 2020-11-03 平安科技（深圳）有限公司 监控数据上报方法、装置、计算机设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101515344A (zh) * 2009-04-03 2009-08-26 陈忠 动物疫病监测管理及预警工作站
CN109166630B (zh) * 2018-08-03 2021-11-23 杜占玮 一种传染病数据监控处理方法和系统
CN109767842B (zh) * 2018-12-13 2023-08-22 平安科技（深圳）有限公司 一种疾病预警方法、疾病预警装置及计算机可读存储介质
CN110929648B (zh) * 2019-11-22 2021-03-16 广东睿盟计算机科技有限公司 监控数据处理方法、装置、计算机设备以及存储介质
CN111081383A (zh) * 2020-01-20 2020-04-28 罗晖 一种基于云计算的流行病监控系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093106A (zh) * 2013-01-25 2013-05-08 上海市浦东新区疾病预防控制中心 大型活动中多源数据的传染病症状监测与预警方法
CN106326635A (zh) * 2016-08-08 2017-01-11 捷开通讯(深圳)有限公司 一种信息监测方法及系统
US20180173854A1 (en) * 2016-12-21 2018-06-21 Cerner Innovation, Inc. Monitoring predictive models
CN108565023A (zh) * 2018-03-16 2018-09-21 夏伟 一种儿童疾病防控监测方法、装置和系统
CN109935338A (zh) * 2019-03-07 2019-06-25 平安科技（深圳）有限公司 基于机器学习的数据预测处理方法、装置和计算机设备
CN111885181A (zh) * 2020-07-28 2020-11-03 平安科技（深圳）有限公司 监控数据上报方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN111885181A (zh) 2020-11-03
CN111885181B (zh) 2023-02-28

Similar Documents

Publication Publication Date Title
US11822975B2 (en) Systems and methods for synthetic data generation for time-series data using data segments
WO2021139235A1 (zh) 系统异常检测方法、装置、设备及存储介质
WO2021042843A1 (zh) 告警信息的决策方法、装置、计算机设备及存储介质
WO2021184554A1 (zh) 数据库异常监测方法、装置、计算机装置及存储介质
WO2019153581A1 (zh) 异常接口检测方法、装置、计算机设备和存储介质
CN111177714B (zh) 异常行为检测方法、装置、计算机设备和存储介质
WO2022022042A1 (zh) 监控数据上报方法、装置、计算机设备及存储介质
WO2020062702A1 (zh) 短信发送的方法、装置、计算机设备和存储介质
US20180082215A1 (en) Information processing apparatus and information processing method
WO2017076154A1 (zh) 网络事件预测以及建立网络事件预测模型的方法和装置
US11790369B2 (en) Systems and method for enhanced active machine learning through processing of partitioned uncertainty
WO2019200738A1 (zh) 数据特征提取的方法、装置、计算机设备和存储介质
WO2020034801A1 (zh) 医疗特征筛选方法、装置、计算机设备和存储介质
WO2023056723A1 (zh) 故障诊断的方法、装置、电子设备及存储介质
CN110912908B (zh) 网络协议异常检测方法、装置、计算机设备和存储介质
WO2022001125A1 (zh) 一种存储系统的存储故障预测方法、系统及装置
US20240054128A1 (en) Automatic database query load assessment and adaptive handling
WO2020056968A1 (zh) 数据降噪方法、装置、计算机设备和存储介质
WO2019148706A1 (zh) web入侵检测方法、装置、计算机设备和存储介质
CN115795928A (zh) 基于伽马过程的加速退化试验数据处理方法和装置
CN114785616A (zh) 数据风险检测方法、装置、计算机设备及存储介质
CN109493975B (zh) 基于xgboost模型的慢性病复发预测方法、装置和计算机设备
CN112732690B (zh) 一种用于慢病检测及风险评估的稳定系统及方法
CN112768090A (zh) 一种用于慢病检测及风险评估的过滤系统及方法
CN112133447A (zh) 胶体筛选模型的构建方法和胶体筛选方法

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 09/05/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21850582

Country of ref document: EP

Kind code of ref document: A1