Big data-based infectious disease transmission path generation and early warning method and device

Abstract

The embodiment of the invention discloses an infectious disease transmission path generation and early warning method and device based on big data. A specific embodiment of the method comprises the following steps: generating a diagnosed person set and a contact person set according to urban infectious disease data; determining an activity point sequence of each diagnosed person to obtain an activity point sequence set of the diagnosed persons; clustering the activity point sequence of each diagnosed person to obtain a high-risk region set; determining the urban personnel meeting a preset high-risk crowd condition as high-risk personnel, and obtaining a high-risk personnel set; determining an association node corresponding to each high-risk region to obtain a high-risk association node set; generating an infectious disease transmission map; and generating an infectious disease transmission path set according to the infectious disease transmission map, and generating an infectious disease transmission thermodynamic diagram according to the infectious disease transmission path set. According to the embodiment, the infectious disease transmission path can be tracked, and the infectious disease diffusion risk and the social prevention and control cost are reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and specifically to a method and device for generating and warning an infectious disease transmission path based on big data. Background Art

[0002] Tracking the transmission path of infectious diseases is a key link in infectious disease prevention and control. At present, the methods commonly used to generate the transmission path of infectious diseases are: manual collection and analysis method and infectious disease prediction system. Among them, the above-mentioned manual collection and analysis method relies on manual data collection, and then analyzes the collected data based on epidemiology to obtain the transmission path; the above-mentioned infectious disease prediction system performs path analysis through automated data processing.

[0003] However, when the above method is used to generate the transmission path of infectious diseases, the following technical problems often occur: First, existing technologies often ignore the important impact of human mobility on the spread of infectious diseases, and lack in-depth analysis of infectious disease transmission, making it difficult to accurately track the transmission routes of infectious diseases, thereby increasing the risk of infectious disease spread and social prevention and control costs; Second, the manual data collection and analysis method is limited by the timeliness of data collection, and it is difficult to issue early warning signals in a timely manner according to the development trend of infectious diseases, resulting in delayed prevention and control measures and failure to stop the spread of infectious diseases in a timely manner.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose methods and devices for generating infectious disease transmission paths based on big data to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for generating infectious disease transmission paths based on big data, the method comprising: generating a set of confirmed persons and a set of contact persons according to urban infectious disease data; determining the activity point sequence of each confirmed person in the confirmed person set to obtain a set of confirmed person activity point sequences; clustering the activity point sequences of each confirmed person in the confirmed person activity point sequence set to obtain a set of high-risk areas; according to the high-risk area set, determining urban personnel who meet preset high-risk population conditions as high-risk personnel to obtain a set of high-risk personnel; determining the associated nodes corresponding to each high-risk area in the high-risk area set to obtain a set of high-risk associated nodes; generating an infectious disease transmission map according to the confirmed person set, the confirmed person activity point sequence set, the high-risk area set, the high-risk person set and the high-risk associated node set; generating an infectious disease transmission path set according to the infectious disease transmission map, and generating an infectious disease transmission heat map according to the infectious disease transmission path set; superimposing the infectious disease transmission heat map on the corresponding city map to obtain an urban infectious disease transmission heat map, and displaying the urban infectious disease transmission heat map.

[0008] In a second aspect, some embodiments of the present disclosure provide a device for generating an infectious disease transmission path based on big data, the device comprising: a first generating unit, configured to generate a confirmed person set and a contact person group set based on urban infectious disease data; a first determining unit, configured to determine the activity point sequence of each confirmed person in the confirmed person set, and obtain a confirmed person activity point sequence set; a clustering unit, configured to cluster the activity point sequences of each confirmed person in the confirmed person activity point sequence set, and obtain a high-risk area set; a second determining unit, configured to determine urban personnel who meet preset high-risk population conditions as high-risk personnel based on the high-risk area set, and obtain a high-risk personnel set; a third determining unit, configured to determine the activity point sequence of each confirmed person in the confirmed person activity point sequence set, and obtain a high-risk area set; and a third determining unit, configured to determine the activity point sequence of each confirmed person in the confirmed person activity point sequence set, and obtain a high-risk area set. The first generating unit is configured to determine the associated nodes corresponding to each high-risk area in the high-risk area set to obtain a high-risk associated node set; the second generating unit is configured to generate an infectious disease transmission map according to the confirmed person set, the confirmed person activity point sequence set, the high-risk area set, the high-risk person set and the high-risk associated node set; the third generating unit is configured to generate an infectious disease transmission path set according to the infectious disease transmission map, and to generate an infectious disease transmission heat map according to the infectious disease transmission path set; the superposition and display unit is configured to superimpose the infectious disease transmission heat map on the corresponding city map to obtain a city infectious disease transmission heat map, and to display the city infectious disease transmission heat map.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the infectious disease transmission path generation method based on big data of some embodiments of the present disclosure, the risk of infectious disease spread and the social prevention and control cost can be reduced. Specifically, the reason for the increase in the risk of infectious disease spread and the social prevention and control cost is that the existing technology often ignores the important impact of personnel flow on the spread of infectious diseases, and lacks in-depth analysis of infectious disease transmission, making it difficult to accurately track the transmission path of infectious diseases. Based on this, the infectious disease transmission path generation method based on big data of some embodiments of the present disclosure, first, generates a set of confirmed personnel and a set of contact personnel according to urban infectious disease data. Through systematic data collection and structured storage of information on confirmed cases and contacts, the initial transmission source can be quickly locked and the risk of invisible transmission can be reduced. Secondly, the activity point sequence of each confirmed person in the above-mentioned confirmed person set is determined to obtain a set of confirmed person activity point sequences. Then, the activity point sequences of each confirmed person in the above-mentioned confirmed person activity point sequence set are clustered to obtain a set of high-risk areas. Thus, high-risk areas can be dynamically determined, the effectiveness of lockdown can be improved, and accurate infectious disease prevention and control can be achieved. Then, according to the above-mentioned high-risk area set, urban personnel who meet the preset high-risk population conditions are determined as high-risk personnel to obtain a set of high-risk personnel. Thus, the high-risk population can be accurately determined to implement timely observation measures, block the extension of the transmission chain, and avoid the social costs brought by full nucleic acid and comprehensive lockdown. Afterwards, the associated nodes corresponding to each high-risk area in the above-mentioned high-risk area concentration are determined to obtain a high-risk associated node set. Thus, the next transmission node of the infectious disease can be determined, so as to strengthen the prevention and control of the associated nodes in a targeted manner. Then, according to the above-mentioned confirmed personnel set, the above-mentioned confirmed personnel activity point sequence set, the above-mentioned high-risk area set, the above-mentioned high-risk personnel set and the above-mentioned high-risk associated node set, an infectious disease transmission map is generated. By storing the multidimensional relationship in the process of infectious disease transmission through the graph structure, the construction of the transmission network can be realized to assist in the decision-making of infectious disease prevention and control. Afterwards, according to the above-mentioned infectious disease transmission map, an infectious disease transmission path set is generated, and an infectious disease transmission heat map is generated according to the above-mentioned infectious disease transmission path set. Finally, the infectious disease transmission heat map is superimposed on the corresponding city map to obtain an urban infectious disease transmission heat map, and the urban infectious disease transmission heat map is displayed. By accurately generating the infectious disease transmission path and achieving transmission blocking with the smallest control unit, the utilization rate of prevention and control resources can be improved, while reducing the risk of infectious disease spread and social prevention and control costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flowchart of some embodiments of the method for generating infectious disease transmission paths based on big data according to the present disclosure; Figure 2 It is a schematic diagram of the structure of some embodiments of the infectious disease transmission path generation device based on big data according to the present disclosure; Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] With regard to the collection, storage, and use of user personal information (such as user portraits and historical user behaviors) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0020] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0021] Figure 1The process 100 of some embodiments of the infectious disease transmission path generation method based on big data according to the present disclosure is shown. The infectious disease transmission path generation method based on big data includes the following steps: Step 101, generating a set of confirmed persons and a set of contact persons based on the city infectious disease data.

[0022] In some embodiments, the execution subject of the infectious disease transmission path generation method based on big data can generate a confirmed person set and a contact person set according to the city infectious disease data, wherein the above-mentioned city infectious disease data is data about confirmed cases in the city.

[0023] In some optional implementations of some embodiments, the execution subject generates a set of confirmed persons and a set of contact persons according to the city infectious disease data, which may include the following steps: The first step is to obtain urban infectious disease data. Among them, the above-mentioned urban infectious disease data includes social media case information, hospital case information, and community screening case information. In practice, first, social media case information can be obtained by crawling social media content. Secondly, hospital case information can be obtained through the hospital's Internet system. After that, community screening case information can be obtained through the screening information reported by the community. The above-mentioned social media case information, hospital case information, and community screening case information may include name, identity information, symptoms, body temperature, data acquisition time, data source and other information. The above-mentioned identity information may be a unique identification code corresponding to the case information. The above-mentioned data sources may include from social media, from hospitals, from the community, etc.

[0024] The second step is to perform data standardization on the social media case information, hospital case information, and community screening case information contained in the above-mentioned urban infectious disease data to obtain standard media case information, standard hospital case information, and standard community case information. In practice, first, the social media case information, hospital case information, and community screening case information can be cleaned separately through the preset data cleaning operation to obtain the cleaned social media case information, cleaned hospital case information, and cleaned community screening case information. Secondly, the elements in the cleaned social media case information, cleaned hospital case information, and cleaned community screening case information can be standardized to obtain standard media case information, standard hospital case information, and standard community case information. The above-mentioned standardization refers to the unification of the data format within the feature dimension. For example, the identity information is converted into the corresponding identity hash code; the time information such as the data acquisition time is unified into the UTC time format.

[0025] As an example, the above-mentioned preset data cleaning operation may include but is not limited to at least one of the following: missing value filling, outlier value modification, duplicate value deletion, etc.

[0026] The third step is to integrate the above-mentioned standard media case information, the above-mentioned standard hospital case information and the above-mentioned standard community case information to obtain valid case information, wherein the above-mentioned valid case information can be the union of all elements in the above-mentioned standard media case information, the above-mentioned standard hospital case information and the above-mentioned standard community case information.

[0027] The fourth step is to generate a set of confirmed persons based on the above valid case information. In practice, the identity hash code of each element in the above valid case information can be used to represent the confirmed persons to obtain the set of confirmed persons.

[0028] The fifth step is to determine the various contacts that each confirmed person in the above-mentioned confirmed person set has contacted to generate a contact person group and obtain a contact person group set. In practice, the contact person group corresponding to the confirmed person can be determined by the confirmed person reporting his or her contacts in the recent period of time. Among them, the recent period of time can be one week. Each confirmed person in the above-mentioned confirmed person set can correspond to multiple contacts, each contact person corresponds to a contact location, and the above-mentioned multiple contacts can be a contact person group. Each contact person group in the above-mentioned contact person group set can be composed of the identity hash codes of each contact person.

[0029] Optionally, the execution subject integrates the standard media case information, the standard hospital case information and the standard community case information to obtain valid case information, which may include the following steps: The first step is to perform field matching on the above-mentioned standard media case information, the above-mentioned standard hospital case information and the above-mentioned standard community case information to generate a similar case information group set and a unique case information set. In practice, first, the name, identity hash code, mobile phone number and other information of each element in the above-mentioned standard media case information, the above-mentioned standard hospital case information and the above-mentioned standard community case information can be used as the primary key information to obtain the primary key information set. Each primary key information in the above-mentioned primary key information set can be used to uniquely identify a case information. Secondly, each primary key information in the above-mentioned primary key information set can be field matched through a preset field matching algorithm to obtain a similar primary key information group set and a unique primary key information set. The similarity between each unique primary key information in the above-mentioned unique primary key information set and each other primary key information is close to 0. Afterwards, each case information corresponding to each similar primary key information group in the above-mentioned similar primary key information group set can be determined as a similar case information group to obtain a similar case information group set. At the same time, the case information corresponding to each unique primary key information in the above-mentioned unique primary key information set can be determined as a unique case information to obtain a unique case information set.

[0030] As an example, the field matching algorithm may include but is not limited to at least one of the following: Jaccard Similarity Coefficient, Hamming Distance, etc. The field matching algorithm may determine multiple primary key information in the primary key information set whose similarity is greater than a preset similarity threshold as a similar primary key information group. The similarity threshold is a numerical value, which may be 0.85, and is not specifically limited here.

[0031] The second step is to perform conflict merging on each similar case information group in the above similar case information group set to generate merged case information and obtain a merged case information set. In practice, for each similar case information group in the above similar case information group set, the similar case information in the above similar case information group whose corresponding data acquisition time is closest to the current one can be determined as the merged case information; or the similar case information in the above similar case information group corresponding to the hospital case information can be determined as the merged case information to obtain a merged case information set.

[0032] The third step is to determine the combined case information set and the unique case information set as valid case information. In practice, each combined case information in the combined case information set and each unique case information in the unique case information set can be jointly determined as valid case information.

[0033] Step 102, determining the activity point sequence of each confirmed person in the confirmed person set, and obtaining the confirmed person activity point sequence set.

[0034] In some embodiments, the above-mentioned execution entity can determine the activity point sequence of each confirmed person in the above-mentioned confirmed person set to obtain the confirmed person activity point sequence set.

[0035] In some optional implementations of some embodiments, the execution subject determines the activity point sequence of each confirmed person in the confirmed person set to obtain the confirmed person activity point sequence set, which may include the following steps: The first step is to determine the original trajectory point sequence of each confirmed person in the above-mentioned confirmed person set based on the base station positioning technology to obtain the original trajectory point sequence set. Among them, each original trajectory point sequence in the above-mentioned original trajectory point sequence set can characterize the movement trajectory of the corresponding confirmed person in the past period of time. The above-mentioned past period of time can be 7 days. In practice, for each confirmed person in the above-mentioned confirmed person set, the identity hash code or mobile phone number corresponding to the above-mentioned confirmed person can be determined first. After that, the base station connection record corresponding to the above-mentioned identity hash code or mobile phone number can be obtained. The above-mentioned base station connection record can be obtained from various operators. The above-mentioned base station connection record may contain the base station connection information of the above-mentioned confirmed person in the past period of time. The above-mentioned base station connection information may include a connection timestamp, a base station number, and a signal strength. Here, a connection timestamp may correspond to at least one base station number and signal strength. Then, for each base station number and signal strength of the same connection timestamp, the original trajectory point corresponding to the above-mentioned base station number and signal strength can be determined by multi-base station collaborative positioning technology. The above-mentioned original trajectory point may be a coordinate. Then, the determined original trajectory points can be arranged in chronological order to obtain an original trajectory point sequence. Finally, the obtained original trajectory point sequences are determined as an original trajectory point sequence set.

[0036] As an example, the above-mentioned multi-base station collaborative positioning technology may include but is not limited to at least one of the following: triangulation positioning method, fingerprint positioning method, etc.

[0037] In the second step, each original trajectory point sequence in the original trajectory point sequence set is subjected to trajectory interpolation optimization to generate a complementary trajectory point sequence, thereby obtaining a complementary trajectory point sequence set. In particular, each original trajectory point sequence in the original trajectory point sequence set is subjected to trajectory interpolation optimization to generate a complementary trajectory point sequence, thereby obtaining a complementary trajectory point sequence set, through a preset linear interpolation algorithm.

[0038] In practice, signal loss may occur during base station switching, resulting in missing trajectory points in the original trajectory point sequence. The above steps can complete the trajectory points of confirmed persons and improve the effectiveness of the trajectory point sequence.

[0039] The third step is to perform noise reduction processing on each of the complementary trajectory point sequences in the above complementary trajectory point sequence set to generate a trajectory point sequence and obtain a trajectory point sequence set. In particular, each of the complementary trajectory point sequences in the above complementary trajectory point sequence set can be subjected to noise reduction processing by a preset noise reduction algorithm to generate a trajectory point sequence and obtain a trajectory point sequence set.

[0040] As an example, the above-mentioned preset denoising algorithm may include but is not limited to at least one of the following: a wavelet denoising algorithm (Wavelet Denoising), a Kalman filter algorithm (Kalman Filter), etc.

[0041] The fourth step is to determine the confirmed person activity point sequence corresponding to each trajectory point sequence in the above-mentioned trajectory point sequence set, and obtain the confirmed person activity point sequence set. Among them, each confirmed person activity point sequence in the above-mentioned confirmed person activity point sequence set includes a stay point set and a transportation tool set. In practice, for each trajectory point sequence in the above-mentioned trajectory point sequence set, first, by means of a sliding window, it can be determined whether all trajectory points in each sliding window are within the preset position range, and the centroid of each trajectory point that meets the conditions is determined as a stay point to obtain a stay point set. Here, each trajectory point that does not meet the conditions can be determined as a journey point to obtain a journey point set. The above-mentioned sliding window can be a fixed time period, such as 30 minutes. The step size of the sliding window sliding can be a time period less than the above-mentioned fixed time period, such as 10 minutes. The above-mentioned preset position range can be a circular range with a radius of 500 meters, which is not specifically limited here. The coordinates of each stay point in the above-mentioned stay point set can be the coordinates of the centroid of each corresponding trajectory point. The various stay points in the above-mentioned stay point set can be arranged in chronological order. Next, each route point between any two adjacent stop points in the above-mentioned stop point set can be determined, and the transportation tools corresponding to the above-mentioned route points can be determined according to the preset moving speed and transportation tool type mapping table, thereby obtaining a transportation tool set. The above-mentioned moving speed and transportation tool type mapping table can be obtained through the urban public transportation system and travel software. Finally, the above-mentioned stop point set and each element in the above-mentioned transportation tool set can be sorted in chronological order to generate a sequence of confirmed person activity points, and obtain a confirmed person activity point sequence set.

[0042] Step 103, clustering each confirmed person activity point sequence in the confirmed person activity point sequence set to obtain a high-risk area set.

[0043] In some embodiments, the above-mentioned execution entity may cluster the activity point sequences of each confirmed person in the above-mentioned activity point sequence set of confirmed persons to obtain a set of high-risk areas.

[0044] In some optional implementations of some embodiments, the execution subject clusters each confirmed person activity point sequence in the confirmed person activity point sequence set to obtain a high-risk area set, which may include the following steps: The first step is to determine each stop point corresponding to the same time in each confirmed person's activity point sequence in the above confirmed person's activity point sequence set as a target time stop point, and obtain a target time stop point set to generate each target time stop point set. Among them, the above same time can be a time period, the above time period can be the same as the step size of the above sliding window, and the above time period can be 10 minutes or 30 minutes, which is not specifically limited here. For example, the stop point of each confirmed person between 2025-07-01T10:00:00Z and 2025-07-01T10:10:00Z can be determined as a target time stop point, and a target time stop point set is obtained. One time period corresponds to one target time stop point set.

[0045] In the second step, for each target time stop point set in each target time stop point set, the following steps are performed to generate a target time high-risk area set, thereby obtaining each target time high-risk area set: In the first sub-step, each target time stay point in the target time stay point set is clustered to obtain a cluster area set. Each cluster area in the cluster area set may contain multiple target time stay points. Here, the cluster area may be represented by the coordinates of the centroid between each target time stay point. In practice, each target time stay point in the target time stay point set may be clustered by a preset clustering algorithm to obtain a cluster area set.

[0046] As an example, the clustering algorithm may include but is not limited to at least one of the following: Ordering Points To Identify the Clustering Structure (OPTICS) algorithm, Hierarchical DBSCAN algorithm, etc.

[0047] In the second sub-step, the number of target time stay points contained in each cluster area in the above cluster area set is determined as the number of confirmed people in the area, and a set of confirmed people in the area is obtained.

[0048] In the third sub-step, according to the above contact person group set, the number of contacts corresponding to each cluster area in the above cluster area set is determined as the regional contact number, and the regional contact number set is obtained. In practice, the number of contacts corresponding to each cluster area can be determined according to each contact person and contact location corresponding to each contact person group in the above contact person group set, and the regional contact number set is obtained.

[0049] In the fourth sub-step, according to the set of confirmed cases in the above-mentioned area and the set of contacts in the above-mentioned area, each cluster area in the above-mentioned cluster area set that meets the preset high-risk conditions is determined as a high-risk area at the target time, and a set of high-risk areas at the target time is obtained. Among them, the above-mentioned high-risk condition may be that the density of confirmed and contacted persons in the cluster area exceeds the preset density value. The above-mentioned density value may be the ratio between the number of people and the area. For example, the above-mentioned high-risk condition may be that there are more than 18 confirmed persons and contacted persons within 1 square kilometer around.

[0050] The third step is to determine the above-mentioned high-risk area sets at each target time as high-risk area sets. Each high-risk area in the above-mentioned high-risk area set can be represented by the coordinates of its centroid, and each high-risk area corresponds to information such as coordinates, number of people gathered, and time window.

[0051] Step 104, based on the high-risk area set, urban residents who meet the preset high-risk population conditions are determined as high-risk persons to obtain a high-risk person set.

[0052] In some embodiments, the above-mentioned execution entity can determine the urban personnel who meet the preset high-risk population conditions as high-risk personnel based on the above-mentioned high-risk area set, and obtain a high-risk personnel set. Among them, the above-mentioned high-risk population condition can be that the trajectory point of the urban personnel is in the high-risk area and the duration meets the preset time period. The above-mentioned time period can be 30 minutes or 1 hour, which is not specifically limited here. In practice, first, the base stations corresponding to each high-risk area in the above-mentioned high-risk area set can be determined. Then, the urban personnel who have mobile communication connections with the above-mentioned base stations and whose connection duration meets the above-mentioned time end can be determined as high-risk personnel to obtain a high-risk personnel set.

[0053] Step 105, determining the associated node corresponding to each high-risk area in the high-risk area set, and obtaining a high-risk associated node set.

[0054] In some embodiments, the execution entity may determine the associated node corresponding to each high-risk region in the high-risk region set to obtain a high-risk associated node set.

[0055] In some optional implementations of some embodiments, the execution subject determines the associated node corresponding to each high-risk area in the high-risk area set to obtain the high-risk associated node set, which may include the following steps: The first step is to obtain the personnel trajectory point sequence corresponding to each city person and obtain a personnel trajectory point sequence set. Among them, each personnel trajectory point sequence in the above personnel trajectory point sequence set is a sequence composed of the movement coordinates of the person in the recent period of time. One personnel trajectory point sequence corresponds to one city person, and the above city person is a resident in the city. In practice, the trajectory point sequence of each city person can be obtained through the above base station positioning technology to obtain a personnel trajectory point sequence set. Here, a personnel trajectory point sequence can be uniquely identified by an identity hash code or a mobile phone number to avoid leakage of residents' identity privacy.

[0056] The second step is to generate a trajectory point item set based on the above-mentioned personnel trajectory point sequence set. The above-mentioned trajectory point item set includes a single-item trajectory point set and a double-item trajectory point set. The above-mentioned single-item trajectory point set is a set composed of each personnel trajectory point contained in the above-mentioned personnel trajectory point sequence set. Each double-item trajectory point in the above-mentioned double-item trajectory point set is an ordered pair composed of every two personnel trajectory points. For example, the above-mentioned single-item trajectory point set may include: "A Square", "B Shopping Mall", "C Subway Station" and other contents. The above-mentioned double-item trajectory point set may include: "A Square, C Subway Station", "C Subway Station, A Square", "D Street, E Store" and other contents.

[0057] The third step is to determine the number of occurrences of each single trajectory point in the single trajectory point set in the personnel trajectory point sequence set to obtain a single trajectory point frequency set. The number of occurrences of each single trajectory point in the single trajectory point frequency set may be the number of occurrences of the corresponding single trajectory point in each personnel trajectory point sequence in the personnel trajectory point sequence set.

[0058] In the fourth step, according to the preset single minimum support, the single trajectory point corresponding to each single trajectory point number that meets the minimum support condition in the above single trajectory point number set is determined as a candidate trajectory point to obtain a candidate trajectory point set. Among them, the above preset single minimum support can be a percentage or a decimal between 0 and 1. The above minimum support condition can be that the number of single trajectory points is greater than the product of the number of each personnel trajectory point sequence and the preset single minimum support. For example, the number of each personnel trajectory point sequence can be 10,000, the above preset single minimum support can be 0.5%, and the above minimum support condition can be that the number of single trajectory points is greater than 50. In practice, the single trajectory point corresponding to each single trajectory point number that does not meet the above minimum support condition in the above single trajectory point number set can also be determined as a non-candidate trajectory point to obtain a non-candidate trajectory point set.

[0059] In the fifth step, the two-item trajectory points in the two-item trajectory point set corresponding to each candidate trajectory point in the candidate trajectory point set are determined as candidate two-item trajectory points to obtain a candidate two-item trajectory point set. In practice, the two-item trajectory points in the trajectory point item set related to each non-candidate trajectory point in the non-candidate trajectory point set can also be deleted, and the undeleted two-item trajectory points can be determined as candidate two-item trajectory points to obtain a candidate two-item trajectory point set.

[0060] The sixth step is to determine the number of occurrences of each candidate double-item trajectory point in the candidate double-item trajectory point set in the personnel trajectory point sequence set to obtain a candidate double-item trajectory point frequency set. In practice, for each candidate double-item trajectory point in the candidate double-item trajectory point set, the number of times that the two personnel trajectory points included in the candidate double-item trajectory point simultaneously appear in each personnel trajectory point sequence in the personnel trajectory point sequence set can be determined as the candidate double-item trajectory point frequency to obtain a candidate double-item trajectory point frequency set.

[0061] The seventh step is to generate a double-item trajectory point confidence set based on the above-mentioned candidate double-item trajectory point frequency set. Among them, the confidence of each double-item trajectory point in the double-item trajectory point confidence set can be used to characterize the probability of the subsequent personnel trajectory point appearing when the current personnel trajectory point appears. In practice, for each candidate double-item trajectory point frequency in the above-mentioned candidate double-item trajectory point frequency set, the ratio between the above-mentioned candidate double-item trajectory point frequency and the corresponding single-item trajectory point frequency can be determined as the double-item trajectory point confidence, and the double-item trajectory point confidence set is obtained. Among them, one candidate double-item trajectory point frequency corresponds to one single-item trajectory point frequency, and the previous personnel trajectory point in the candidate double-item trajectory points corresponding to the candidate double-item trajectory point frequency is the same as the single-item trajectory point corresponding to the single-item trajectory point frequency.

[0062] In the eighth step, based on the Bayesian inference formula, the two-item minimum support and the two-item minimum confidence are generated. The two-item minimum support and the two-item minimum confidence can obey the Beta distribution. In practice, for each candidate two-item trajectory point number in the candidate two-item trajectory point number, a priori Beta distribution Beta (α, β) can be preset first. Secondly, the corresponding posterior distribution can be determined according to the candidate two-item trajectory point number. The posterior distribution can be Beta (α+k, β+nk), and the k can be used to characterize the candidate two-item trajectory point number. After that, the initial minimum support that meets the preset significance condition can be determined by the cumulative distribution function (CDF). The significance condition can be that the probability that the true support is greater than the initial minimum support satisfies the preset probability threshold. The true support can be the percentage between the candidate two-item trajectory point number and the number value of each personnel trajectory point sequence. The probability threshold can be 96%. Finally, the initial minimum support that meets the preset support condition among the determined initial minimum supports can be determined as the two-item minimum support. The above-mentioned preset support condition can be the initial minimum support with the smallest median value of the initial minimum support of the previous preset proportion number with the highest value. The above-mentioned preset proportion number can be the percentage number of the number of times of each candidate two-item trajectory point. The above-mentioned percentage can be 30%. By making a certain proportion of candidate two-item trajectory points meet the minimum support condition, the false positive rate can be reduced and the accuracy of generating associated nodes can be improved. Here, the two-item minimum confidence can be generated by the above-mentioned method of generating the two-item minimum support, which will not be repeated here.

[0063] As an example, for a candidate binary trajectory point number, first, a prior Beta distribution such as Beta (1, 1) can be preset. Secondly, when the quantity value of each of the above personnel trajectory point sequences is 10000 and the candidate binary trajectory point number is 100, the corresponding true support is 1%, and its posterior distribution can be Beta (101, 9901). After that, the initial minimum support that makes the probability that the above true support is greater than the initial minimum support greater than 96% can be determined through the cumulative distribution function. Finally, for each initial minimum support, the initial minimum support with the smallest value among the top 30% initial minimum support with higher values ​​can be determined as the binary minimum support.

[0064] In practice, the seventh step above adopts Bayesian inference to dynamically determine the two-item minimum support and the two-item minimum confidence based on real data, which can reduce the deviation caused by directly setting a fixed threshold, thereby improving the accuracy of the determined associated nodes.

[0065] In the eighth step, according to the above-mentioned minimum support for two items, the above-mentioned minimum confidence for two items, the number set of candidate two-item trajectory points, and the above-mentioned confidence set of two-item trajectory points, each candidate two-item trajectory point in the above-mentioned candidate two-item trajectory point set that meets the preset association condition is determined as an associated trajectory point group to obtain an associated trajectory point group set. In practice, for each candidate two-item trajectory point in the above-mentioned candidate two-item trajectory point set, if the percentage between the number of candidate two-item trajectory points corresponding to the above-mentioned candidate two-item trajectory point and the number value of each personnel trajectory point sequence is greater than the above-mentioned minimum support for two items, and the corresponding two-item trajectory point confidence is greater than the above-mentioned minimum confidence for two items, the above-mentioned candidate two-item trajectory point can be determined as an associated trajectory point group to obtain an associated trajectory point group set. Each associated trajectory point group in the above-mentioned associated trajectory point group set can be an ordered group consisting of two personnel trajectory points corresponding to the candidate two-item trajectory point. Each associated trajectory point in the above-mentioned associated trajectory point group can represent the potential association between two personnel trajectory points. For example, the associated trajectory point group "A Square, C Subway Station" can indicate that people who have been to A Square often also go to C Subway Station.

[0066] In the ninth step, based on the above-mentioned associated trajectory point group set, the associated nodes corresponding to each high-risk area in the above-mentioned high-risk area set are determined to obtain a high-risk associated node set. In practice, when a high-risk area in the above-mentioned high-risk area set exists in one or more associated trajectory point groups in the above-mentioned associated trajectory point group set, all personnel trajectory points in the above-mentioned one or more associated trajectory point groups except the above-mentioned high-risk area can be determined as associated nodes of the high-risk area, thereby obtaining a high-risk associated node set.

[0067] Optionally, the above execution entity may further perform the following steps: The first step is to determine the confidence between each high-risk area in the high-risk area set and the corresponding high-risk associated node in the high-risk associated node set according to the above two-item trajectory point confidence set and the above associated trajectory point group set, and obtain a confidence set. In practice, the confidence between each high-risk area in the high-risk area set and the corresponding high-risk associated node in the high-risk associated node set can be determined as the confidence according to the above two-item trajectory point confidence set, and a confidence set can be obtained.

[0068] The second step is to generate the influence matrix corresponding to the above-mentioned high-risk area set and the above-mentioned high-risk associated node set based on the above-mentioned confidence set. Among them, the above-mentioned influence matrix can be a square matrix. The number of rows and columns of the above-mentioned influence matrix can be equal to the sum of the number values ​​of each high-risk area and the number values ​​of each high-risk associated node. The element values ​​in the above-mentioned influence matrix are the confidences between the corresponding risk nodes. The above-mentioned risk nodes can be high-risk areas or high-risk associated nodes. The element values ​​of the mth row and nth column in the above-mentioned influence matrix can be used to characterize the degree of influence of the risk node corresponding to the mth row on the risk node corresponding to the nth column.

[0069] The third step is to determine the influence and impact degree of each high-risk region and each high-risk associated node in the above-mentioned high-risk region set and the above-mentioned high-risk associated node set according to the above-mentioned impact matrix, and obtain the risk node impact information set. In practice, the decision laboratory analysis method (DEMATEL) can be used to determine the influence and impact degree of each high-risk region and each high-risk associated node in the above-mentioned high-risk region set and the above-mentioned high-risk associated node set according to the above-mentioned impact matrix, and obtain the risk node impact information set. The above-mentioned influence degree can characterize the degree of influence of the risk node on other nodes. The above-mentioned impact degree can characterize the degree to which the risk node is affected by other nodes.

[0070] The fourth step is to determine the risk level information corresponding to each high-risk associated node in the above-mentioned high-risk associated node set according to the above-mentioned risk node impact information set, and obtain the risk level information set. In practice, the risk level information corresponding to each high-risk area in the above-mentioned high-risk area set can be third-level risk level information. For each high-risk area whose impact degree of high-risk area concentration is higher than the preset impact threshold, its corresponding high-risk associated node can be determined as second-level risk level information. For each high-risk area whose impact degree of high-risk area concentration is equal to or lower than the preset impact threshold, its corresponding high-risk associated node can be determined as first-level risk level information. Here, the high-risk associated nodes in the high-risk associated node set whose impact degree is higher than the preset impact threshold can also be determined as third-level risk level information. When a high-risk associated node corresponds to multiple risk level information, the highest risk level information can be determined as the risk level information of the high-risk associated node.

[0071] The above step 105 and its related contents, as an inventive point of an embodiment of the present disclosure, solve the above technical problem - "increased risk of infectious disease spread and social prevention and control costs". The factors that lead to the above technical problem are often as follows: the existing technology often ignores the important impact of personnel flow on the spread of infectious diseases, and lacks in-depth analysis of infectious disease spread, making it difficult to accurately track the spread of infectious diseases. If the above factors are solved, the ability to prevent the spread of infectious diseases can be improved. In order to achieve this effect, first, by analyzing the data related to personnel flow, the trajectory item set corresponding to the personnel trajectory point sequence set is determined. Then, by deleting infrequent single-item trajectory points, the number of double-item trajectory points to be processed can be reduced, the consumption of computing resources can be reduced, and the real-time performance of determining associated nodes can be increased. Afterwards, by comparing the number of occurrences and confidence of each double-item trajectory item with the preset minimum support and minimum confidence, the potential association between the two personnel trajectory points is determined, so that the potential transmission chain can be discovered. Among them, by dynamically adjusting the minimum support and minimum confidence through Bayesian inference, real-time analysis can be performed according to the changing infectious disease data, avoiding the deviation caused by the fixed threshold, so that nodes with strong association can be accurately identified. Then, the confidence obtained through the above steps generates an impact matrix, and combined with the decision laboratory analysis method, the impact relationship between each region can be clearly evaluated. In this way, the influence between high-risk areas and high-risk associated nodes can be evaluated, and the key role of each region in the infectious disease transmission chain can be determined, helping decision makers to make more accurate lockdown decisions and avoid unnecessary blockades or omissions. Finally, by determining the risk level information, resources can be allocated according to the risk level of different regions. High-risk areas can obtain priority testing, lockdown, disinfection and other measures, while low-risk areas can avoid unnecessary intervention. This differentiated management helps to improve resource utilization efficiency and reduce socioeconomic costs.

[0072] Optionally, the execution subject determines the associated node corresponding to each high-risk area in the high-risk area set to obtain the high-risk associated node set, and may further include the following steps: In the first step, an associated node detection is performed on each personnel trajectory point sequence in the above-mentioned personnel trajectory point sequence set to generate an associated node group, and an associated node group set is obtained. Each associated node group in the above-mentioned associated node group set is composed of at least two personnel trajectory points. In practice, an associated node detection can be performed on each personnel trajectory point sequence in the above-mentioned personnel trajectory point sequence set to generate an associated node group, and an associated node group set can be obtained through a preset association rule algorithm. The above-mentioned association rule algorithm can be an Apriori association rule algorithm.

[0073] In the second step, based on the above-mentioned associated node group set, the associated nodes corresponding to each high-risk area in the above-mentioned high-risk area set are determined to obtain a high-risk associated node set.

[0074] Step 106, generating an infectious disease transmission map based on the set of confirmed persons, the set of activity point sequences of confirmed persons, the set of high-risk areas, the set of high-risk persons, and the set of high-risk associated nodes.

[0075] In some embodiments, the execution subject may generate an infectious disease propagation graph based on the set of confirmed persons, the sequence set of activity points of confirmed persons, the set of high-risk areas, the set of high-risk persons, and the set of high-risk associated nodes. The infectious disease propagation graph may be a knowledge graph used to characterize infectious disease propagation data. The relationships in the infectious disease propagation graph may include: "contacted", "stayed", "status is", etc. As an example, the triples in the infectious disease propagation graph may be: "city person A, stayed in area B", "area B, status is, high-risk area", etc. In practice, an infectious disease propagation graph may be generated based on the set of confirmed persons, the sequence set of activity points of confirmed persons, the set of high-risk areas, the set of high-risk persons, and the set of high-risk associated nodes through a preset knowledge graph construction algorithm. The knowledge graph algorithm may be a schema-based knowledge graph construction algorithm or an automatic knowledge graph construction algorithm based on a graph neural network (GNN). The infectious disease propagation graph may be stored in a Neo4j graph database.

[0076] Step 107, generating an infectious disease transmission path set based on the infectious disease transmission map, and generating an infectious disease transmission heat map based on the infectious disease transmission path set.

[0077] In some embodiments, the above-mentioned execution entity may generate an infectious disease transmission path set according to the above-mentioned infectious disease transmission map, and generate an infectious disease transmission heat map according to the above-mentioned infectious disease transmission path set. Each infectious disease transmission path in the above-mentioned infectious disease transmission path set may be a sequence composed of each personnel trajectory point. For example, "<E store, D street, F park>". The above-mentioned infectious disease transmission heat map may be a picture representing the infectious disease areas in the city. Different risk-level infectious disease areas in the city may be reflected by images of different colors in the above-mentioned infectious disease transmission heat map. For example, the area corresponding to the third-level risk level information may be represented by a red image, the area corresponding to the second-level risk level information may be represented by an orange image, and the area corresponding to the first-level risk level information may be represented by a yellow image. In practice, a random walk algorithm (Random Walk) may be performed based on the infectious disease transmission map to generate an initial infectious disease transmission path set. Each initial infectious disease transmission path in the above-mentioned initial infectious disease transmission path set corresponds to a probability value. Then, each initial infectious disease transmission path in the above-mentioned initial infectious disease transmission path set that meets the preset path condition may be determined as an infectious disease transmission path to obtain an infectious disease transmission path set. The above-mentioned preset path condition may be the top k initial infectious disease transmission paths with the highest probability values, or the initial infectious disease transmission paths with probability values higher than a preset probability value. The above-mentioned k may be a positive integer, and the above-mentioned preset probability value may be a decimal greater than 0 and less than 1, which is not specifically limited herein. In addition, each confirmed personnel activity point sequence in the above-mentioned confirmed personnel activity point sequence set may be determined as an initial infectious disease transmission path to obtain an initial infectious disease transmission path set. Then, the initial infectious disease transmission paths in the above-mentioned initial infectious disease transmission path set corresponding to the high-risk areas or high-risk associated nodes in the high-risk area set and the high-risk associated node set are determined as infectious disease transmission paths to obtain an infectious disease transmission path set. Finally, for each infectious disease transmission path in the above-mentioned infectious disease transmission path set, the risk level information of the high-risk areas or high-risk associated nodes corresponding to each trajectory point in the above-mentioned infectious disease transmission path may be determined, and then different colors may be rendered for each of the above-mentioned trajectory points according to different risk level information to obtain an infectious disease transmission heat map.

[0078] Step 108, overlay the infectious disease transmission heat map on the corresponding city map to obtain a city infectious disease transmission heat map, and display the city infectious disease transmission heat map.

[0079] In some embodiments, the execution subject may superimpose the infectious disease propagation heat map onto the corresponding city map to obtain the urban infectious disease propagation heat map, and display the urban infectious disease propagation heat map. In practice, the infectious disease propagation heat map may be superimposed in equal proportion with the corresponding city map according to the coordinates of each trajectory point in the infectious disease propagation path to obtain the urban infectious disease propagation heat map. Finally, the urban infectious disease propagation heat map may be transmitted to a display terminal for display. The display terminal may be a display that is communicatively connected to the execution subject.

[0080] Optionally, the above execution entity may further perform the following steps: The first step is to determine the sequence of the number of new cases, the sequence of personnel flow values ​​and the sequence of positive detection rate contained in the above-mentioned urban infectious disease data as the first infectious disease data. Among them, the above-mentioned sequence of the number of new cases can represent the number of new cases per day in the past preset number of days. The above-mentioned preset number of days can be 7 days. The above-mentioned sequence of personnel flow values ​​can represent the personnel flow index of each day in the past preset number of days. The above-mentioned personnel flow index can be obtained through a preset personnel flow mapping table. The above-mentioned personnel flow mapping table can be a mapping table between the proportion of cross-regional mobile population and the personnel flow index. The above-mentioned proportion of cross-regional mobile population can be the ratio between the cross-regional mobile population and the urban population. The above-mentioned personnel flow index can be a natural number greater than 0 and less than 100. The above-mentioned detection positive rate sequence can represent the detection positive rate of each day in the past preset number of days. The above-mentioned detection positive rate can be the ratio between the number of positive people in the community screening and the number of all detected people.

[0081] The second step is to extract the time series features of the first infectious disease data to obtain the infectious disease time series features. The infectious disease time series features can be represented by a high-dimensional vector. In practice, the time series features of the first infectious disease data can be extracted by a pre-trained time series feature extraction network to obtain the infectious disease time series features. The pre-trained time series feature extraction network can be a pre-trained long short-term memory network (LSTM).

[0082] The third step is to determine the estimated incremental number of infected persons corresponding to the temporal characteristics of the infectious disease. The estimated incremental number of infected persons may be a positive integer, which is used to represent the number of newly infected persons. In practice, the estimated incremental number of infected persons corresponding to the temporal characteristics of the infectious disease may be determined by a pre-trained network for predicting the number of newly infected persons. The network for predicting the number of newly infected persons may consist of a fully connected layer and an activation function, and the output of the fully connected layer is the input of the activation function.

[0083] Specifically, the pre-trained long short-term memory network and the new infection number prediction network can be trained by pre-acquired sample data sets. The sample data sets may include a sample sequence of the number of new cases, a sample sequence of personnel flow values, and a sample sequence of the test positivity rate.

[0084] The fourth step is to generate the second infectious disease data based on the above-mentioned set of high-risk areas, the above-mentioned set of high-risk personnel and the social media sentiment index. Among them, the above-mentioned social media sentiment index can be a natural number between 0 and 100, which can be used to characterize the panic index of personnel. In practice, the sentiment analysis of the speech in social media can be performed through a preset sentiment analysis algorithm (Sentiment Analysis) to obtain the social media sentiment index. Among them, the case growth rate is positively correlated with the panic index of personnel. Afterwards, the above-mentioned set of high-risk areas, the above-mentioned set of high-risk personnel and the above-mentioned social media sentiment index can be combined into a high-dimensional vector, and the above-mentioned high-dimensional vector can be determined as the second infectious disease data.

[0085] The fifth step is to extract self-attention features from the second infectious disease data to obtain infectious disease self-attention features. The infectious disease self-attention features can be represented by high-dimensional vectors. In practice, the self-attention features of the second infectious disease data can be extracted through a pre-trained multi-head self-attention network to obtain infectious disease self-attention features.

[0086] The sixth step is to extract self-attention features from the infectious disease time series features to obtain infectious disease time series self-attention features. The infectious disease time series self-attention features can be represented by high-dimensional vectors. In practice, the pre-trained multi-head self-attention network can be used to extract self-attention features from the second infectious disease data to obtain infectious disease self-attention features.

[0087] In the seventh step, the infectious disease time series features are residually connected with the infectious disease time series self-attention features to obtain infectious disease residual connection features. The infectious disease residual connection features can be represented by a high-dimensional vector.

[0088] In the eighth step, the infectious disease self-attention feature and the infectious disease residual connection feature are feature-fused to obtain a fused infectious disease feature. The fused infectious disease feature can be represented by a high-dimensional vector. In practice, the infectious disease self-attention feature and the infectious disease residual connection feature can be feature-fused by a preset feature fusion algorithm to obtain a fused infectious disease feature.

[0089] As an example, the feature fusion algorithm may include but is not limited to at least one of the following: element-by-element addition, feature concatenation (Concat), etc.

[0090] The ninth step is to determine the warning information corresponding to the above-mentioned fused infectious disease features, and transmit the above-mentioned warning information to the target port. The above-mentioned warning information includes red warning, orange warning and yellow warning. The above-mentioned target port can be a mobile device terminal of an infectious disease worker. In practice, the warning information corresponding to the above-mentioned fused infectious disease features can be determined through a pre-trained output layer. The above-mentioned pre-trained output layer can include a fully connected layer and a softmax layer, and the output of the above-mentioned fully connected layer is the input of the above-mentioned softmax layer.

[0091] Specifically, the fourth to sixth steps can be implemented by a pre-trained infectious disease risk prediction model. The pre-trained infectious disease risk prediction model may include a pre-trained multi-head self-attention network, a pre-trained residual connection layer, a pre-trained feature fusion layer, and a pre-trained output layer. The pre-trained infectious disease risk prediction model can be trained by an infectious disease risk sample data set. Each infectious disease risk sample data in the infectious disease risk sample data set may include urban infectious disease data and corresponding warning signs. The urban infectious disease data may include infectious disease time series characteristics, a high-risk area set, a high-risk personnel set, and a social media sentiment index. The warning signs may include red warnings, orange warnings, and yellow warnings.

[0092] In practice, when the above-mentioned warning information is a yellow warning, the above-mentioned executive entity can send a nucleic acid test text message to each high-risk person in the above-mentioned high-risk personnel concentration to notify each high-risk person to undergo nucleic acid testing. When the above-mentioned warning information is an orange warning, the above-mentioned executive entity can send the corresponding information of each high-risk area in the above-mentioned high-risk area concentration to the mobile device terminal of the staff to notify the staff to complete the blockade of the high-risk area. When the above-mentioned warning information is a red warning, the above-mentioned executive entity can push the red warning information to the mobile device terminal of the above-mentioned staff to assist in the deployment of medical resources in surrounding cities.

[0093] The optional steps 1 to 9 and their related contents are an inventive point of the embodiment of the present disclosure, which solves the above technical problem "unable to prevent the spread of infectious diseases in time". The factors that cause the above technical problem are often as follows: the manual collection and analysis method is limited by the timeliness of data collection, and it is difficult to issue early warning signals in time according to the development trend of infectious diseases, resulting in delayed prevention and control measures. If the above factors are solved, the ability to prevent the spread of infectious diseases can be improved. In order to achieve this effect, first, the number of new cases in the future is predicted by the pre-trained network model and the first infectious disease data (the number of new cases, personnel flow value and test positive rate in the past period of time), which can dig out the potential laws and trends in the historical data and provide data support for prevention and control measures. Then, the second infectious disease data is constructed based on the high-risk area set, the high-risk personnel set and the social media sentiment index, capturing the comprehensive risk of infectious diseases from the two aspects of social psychology and epidemiology, and providing a more comprehensive perspective for decision-making. After that, the infectious disease time series features obtained for the first infectious disease data are input into the self-attention network, which combines the advantages of long short-term memory network and multi-head attention mechanism, and can improve the efficiency and accuracy of infectious disease data processing. Secondly, the features obtained from the second infectious disease data are fused with the features obtained from the first infectious disease data, which helps to extract more comprehensive information from multi-dimensional data and improve the prediction ability of the model. Finally, based on the fused features, early warning information is generated and transmitted to relevant staff through appropriate channels (such as mobile device terminals). In this way, different emergency measures can be taken according to the severity of the infectious disease to reduce the risk of the spread of the infectious disease.

[0094] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the infectious disease transmission path generation method based on big data of some embodiments of the present disclosure, the risk of infectious disease spread and the social prevention and control cost can be reduced. Specifically, the reason for the increase in the risk of infectious disease spread and the social prevention and control cost is that the existing technology often ignores the important impact of personnel flow on the spread of infectious diseases, and lacks in-depth analysis of infectious disease transmission, making it difficult to accurately track the transmission path of infectious diseases. Based on this, the infectious disease transmission path generation method based on big data of some embodiments of the present disclosure, first, generates a set of confirmed personnel and a set of contact personnel according to urban infectious disease data. Through systematic data collection and structured storage of information on confirmed cases and contacts, the initial transmission source can be quickly locked and the risk of invisible transmission can be reduced. Secondly, the activity point sequence of each confirmed person in the above-mentioned confirmed person set is determined to obtain a set of confirmed person activity point sequences. Then, the activity point sequences of each confirmed person in the above-mentioned confirmed person activity point sequence set are clustered to obtain a set of high-risk areas. Thus, high-risk areas can be dynamically determined, the effectiveness of lockdown can be improved, and accurate infectious disease prevention and control can be achieved. Then, according to the above-mentioned high-risk area set, urban personnel who meet the preset high-risk population conditions are determined as high-risk personnel to obtain a set of high-risk personnel. Thus, the high-risk population can be accurately determined to implement timely observation measures, block the extension of the transmission chain, and avoid the social costs brought by full nucleic acid and comprehensive lockdown. Afterwards, the associated nodes corresponding to each high-risk area in the above-mentioned high-risk area concentration are determined to obtain a high-risk associated node set. Thus, the next transmission node of the infectious disease can be determined, so as to strengthen the prevention and control of the associated nodes in a targeted manner. Then, according to the above-mentioned confirmed personnel set, the above-mentioned confirmed personnel activity point sequence set, the above-mentioned high-risk area set, the above-mentioned high-risk personnel set and the above-mentioned high-risk associated node set, an infectious disease transmission map is generated. By storing the multidimensional relationship in the process of infectious disease transmission through the graph structure, the construction of the transmission network can be realized to assist in the decision-making of infectious disease prevention and control. Afterwards, according to the above-mentioned infectious disease transmission map, an infectious disease transmission path set is generated, and an infectious disease transmission heat map is generated according to the above-mentioned infectious disease transmission path set. Finally, the infectious disease transmission heat map is superimposed on the corresponding city map to obtain an urban infectious disease transmission heat map, and the urban infectious disease transmission heat map is displayed. By accurately generating the infectious disease transmission path and achieving transmission blocking with the smallest control unit, the utilization rate of prevention and control resources can be improved, while reducing the risk of infectious disease spread and social prevention and control costs.

[0095] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an infectious disease transmission path generation device based on big data. These embodiments of infectious disease transmission path generation device based on big data are similar to Figure 1Corresponding to the method embodiments shown, the infectious disease transmission path generation device based on big data can be specifically applied to various electronic devices.

[0096] like Figure 2 As shown, some embodiments of the infectious disease transmission path generation device 200 based on big data include: a first generation unit 201, a first determination unit 202, a clustering unit 203, a second determination unit 204, a third determination unit 205, a second generation unit 206, a third generation unit 207, and a superposition and display unit 208. Among them, the first generation unit 201 is configured to generate a confirmed person set and a contact person group set according to the urban infectious disease data; the first determination unit 202 is configured to determine the activity point sequence of each confirmed person in the confirmed person set to obtain the confirmed person activity point sequence set; the clustering unit 203 is configured to cluster the activity point sequences of each confirmed person in the confirmed person activity point sequence set to obtain a high-risk area set; the second determination unit 204 is configured to determine the urban personnel who meet the preset high-risk population conditions as high-risk personnel according to the high-risk area set to obtain a high-risk personnel set; the third determination unit 205 is configured to determine each high-risk person in the high-risk area set. The associated nodes corresponding to the risk areas are used to obtain a high-risk associated node set; the second generating unit 206 is configured to generate an infectious disease transmission map according to the confirmed person set, the confirmed person activity point sequence set, the high-risk area set, the high-risk person set and the high-risk associated node set; the third generating unit 207 is configured to generate an infectious disease transmission path set according to the infectious disease transmission map, and to generate an infectious disease transmission heat map according to the infectious disease transmission path set; the superposition and display unit 208 is configured to superimpose the infectious disease transmission heat map on the corresponding city map to obtain a city infectious disease transmission heat map, and to display the city infectious disease transmission heat map.

[0097] It is understandable that the various units recorded in the big data-based infectious disease transmission path generation device 200 and the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the infectious disease transmission path generation device 200 based on big data and the units contained therein, and will not be repeated here.

[0098] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0099] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0100] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0101] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0102] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0103] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0104] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: generates a set of confirmed persons and a set of contact persons according to urban infectious disease data; determines the activity point sequence of each confirmed person in the confirmed person set to obtain a set of confirmed person activity point sequences; clusters the activity point sequences of each confirmed person in the confirmed person activity point sequence set to obtain a set of high-risk areas; according to the high-risk area set, determines the urban personnel who meet the preset high-risk population conditions as high-risk personnel to obtain a set of high-risk personnel; determines the associated nodes corresponding to each high-risk area in the high-risk area set to obtain a set of high-risk associated nodes; generates an infectious disease transmission map according to the confirmed person set, the confirmed person activity point sequence set, the high-risk area set, the high-risk person set and the high-risk associated node set; generates an infectious disease transmission path set according to the infectious disease transmission map, and generates an infectious disease transmission heat map according to the infectious disease transmission path set; superimposes the infectious disease transmission heat map on the corresponding city map to obtain an urban infectious disease transmission heat map, and displays the urban infectious disease transmission heat map.

[0105] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including a first generating unit, a first determining unit, a clustering unit, a second determining unit, a third determining unit, a second generating unit, a third generating unit, an overlay and a display unit. Among them, the names of these units do not constitute a limitation on the unit itself in certain circumstances, for example, the first generating unit may also be described as "a unit for generating a set of confirmed persons and a set of contact persons according to urban infectious disease data".

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for generating and warning infectious disease transmission paths based on big data, comprising: Generate a set of confirmed persons and a set of contact persons based on the city's infectious disease data; Determine the activity point sequence of each confirmed person in the confirmed person set to obtain an activity point sequence set of the confirmed persons; Clustering each confirmed person activity point sequence in the confirmed person activity point sequence set to obtain a high-risk area set; According to the high-risk area set, urban residents who meet the preset high-risk population conditions are determined as high-risk individuals to obtain a high-risk individual set; Determine the associated node corresponding to each high-risk area in the high-risk area set to obtain a high-risk associated node set; Generate an infectious disease transmission map based on the set of confirmed persons, the set of activity point sequences of confirmed persons, the set of high-risk areas, the set of high-risk persons, and the set of high-risk associated nodes; Generate an infectious disease transmission path set according to the infectious disease transmission map, and generate an infectious disease transmission heat map according to the infectious disease transmission path set; The infectious disease transmission heat map is superimposed on the corresponding city map to obtain the urban infectious disease transmission heat map, and the urban infectious disease transmission heat map is displayed.

2. The method according to claim 1, wherein: The method of generating a confirmed person set and a contact person set based on the city infectious disease data includes: Acquire urban infectious disease data, wherein the urban infectious disease data includes social media case information, hospital case information, and community screening case information; Performing data standardization processing on social media case information, hospital case information, and community screening case information contained in the city's infectious disease data to obtain standard media case information, standard hospital case information, and standard community case information; Integrate the standard media case information, the standard hospital case information and the standard community case information to obtain valid case information; Generate a confirmed person set based on the valid case information; Determine each contact person that each confirmed person in the confirmed person set has contacted to generate a contact person group, and obtain a contact person group set.

3. The method according to claim 2, wherein: The data integration of the standard media case information, the standard hospital case information and the standard community case information to obtain valid case information includes: Performing field matching on the standard media case information, the standard hospital case information and the standard community case information to generate a similar case information group set and a unique case information set; Performing conflict merging on each similar case information group in the similar case information group set to generate merged case information, thereby obtaining a merged case information set; The combined case information set and the unique case information set are determined as valid case information.

4. The method according to claim 1, wherein: Determining the activity point sequence of each confirmed person in the confirmed person set to obtain the confirmed person activity point sequence set includes: Based on the base station positioning technology, determine the original trajectory point sequence of each confirmed person in the confirmed person set to obtain an original trajectory point sequence set; Performing trajectory interpolation optimization on each original trajectory point sequence in the original trajectory point sequence set to generate a completed trajectory point sequence, thereby obtaining a completed trajectory point sequence set; Performing noise reduction processing on each completed trajectory point sequence in the completed trajectory point sequence set to generate a trajectory point sequence, thereby obtaining a trajectory point sequence set; Determine the confirmed person activity point sequence corresponding to each trajectory point sequence in the trajectory point sequence set to obtain the confirmed person activity point sequence set, wherein each confirmed person activity point sequence in the confirmed person activity point sequence set includes a stay point set and a transportation tool set.

5. The method according to claim 1, wherein: The clustering of each confirmed person activity point sequence in the confirmed person activity point sequence set to obtain a high-risk area set includes: Determine each stay point corresponding to the same time in each confirmed person's activity point sequence in the confirmed person's activity point sequence set as a target time stay point, obtain a target time stay point set, and generate each target time stay point set; For each target time stop point set in each target time stop point set, perform the following steps to generate a target time high risk area set to obtain each target time high risk area set: Clustering each target time stay point in the target time stay point set to obtain a cluster region set, wherein each cluster region in the cluster region set contains a plurality of target time stay points; The number of target time stay points contained in each cluster area in the cluster area set is determined as the number of confirmed people in the area, to obtain a set of confirmed people in the area; According to the contact person group set, the number of contacts corresponding to each cluster area in the cluster area set is determined as the number of regional contacts, to obtain a set of the number of regional contacts; According to the set of confirmed cases in the region and the set of contacts in the region, each clustering region in the clustering region set that meets the preset high-risk condition is determined as a high-risk region at the target time, to obtain a set of high-risk regions at the target time; The high-risk area sets at each target time are determined as high-risk area sets.

6. The method according to claim 1, wherein: The urban infectious disease data includes a sequence of newly added cases, a sequence of personnel flow values, and a sequence of positive test rates; and the method further includes: Determine the newly added case number sequence, personnel flow value sequence and test positive rate sequence contained in the urban infectious disease data as the first infectious disease data; Extracting time series features from the first infectious disease data to obtain infectious disease time series features; Determine the estimated increase in infected persons corresponding to the temporal characteristics of the infectious disease; generating second infectious disease data according to the high-risk area set, the high-risk person set, and the social media sentiment index; Extracting self-attention features from the second infectious disease data to obtain infectious disease self-attention features; Extracting self-attention features from the infectious disease time series features to obtain infectious disease time series self-attention features; Performing a residual connection between the infectious disease time series feature and the infectious disease time series self-attention feature to obtain an infectious disease residual connection feature; Performing feature fusion on the infectious disease self-attention feature and the infectious disease residual connection feature to obtain a fused infectious disease feature; Determine the warning information corresponding to the fused infectious disease feature, and transmit the warning information to a target port, wherein the warning information includes a red warning, an orange warning, and a yellow warning.

7. A big data-based infectious disease transmission path generation and early warning device, comprising: The first generating unit is configured to generate a set of confirmed persons and a set of contact persons according to the city infectious disease data; A first determining unit is configured to determine an activity point sequence of each confirmed person in the confirmed person set to obtain an activity point sequence set of the confirmed persons; A clustering unit is configured to cluster each confirmed person activity point sequence in the confirmed person activity point sequence set to obtain a high-risk area set; The second determination unit is configured to determine, according to the high-risk area set, urban residents who meet the preset high-risk population conditions as high-risk individuals, and obtain a high-risk individual set; A third determining unit is configured to determine an associated node corresponding to each high-risk area in the high-risk area set to obtain a high-risk associated node set; A second generating unit is configured to generate an infectious disease propagation map according to the confirmed person set, the confirmed person activity point sequence set, the high-risk area set, the high-risk person set and the high-risk associated node set; A third generating unit is configured to generate an infectious disease transmission path set according to the infectious disease transmission map, and to generate an infectious disease transmission heat map according to the infectious disease transmission path set; The superimposition and display unit is configured to superimpose the infectious disease transmission heat map onto the corresponding city map to obtain the city infectious disease transmission heat map, and to display the city infectious disease transmission heat map.

8. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images