CN112231488A

CN112231488A - Data processing method, device, equipment and computer readable storage medium

Info

Publication number: CN112231488A
Application number: CN202011002971.1A
Authority: CN
Inventors: 肖艳清; 张钧波; 任朝淦; 陈国春; 郑宇�
Original assignee: Jingdong City Beijing Digital Technology Co Ltd
Current assignee: Jingdong City Beijing Digital Technology Co Ltd
Priority date: 2020-09-22
Filing date: 2020-09-22
Publication date: 2021-01-15

Abstract

The embodiment of the invention provides a data processing method, a device, equipment and a computer readable storage medium, the method constructs a space-time knowledge map according to static associated data and dynamic behavior data of a target population, the space-time knowledge map comprises contact associated information between any two persons in the target population and associated degree information of each person and a person to be attended, and by inquiring the space-time knowledge map, the method can quickly position an associated target with the specified person to be attended, wherein the associated degree of the associated target meets a first contact associated condition, thereby realizing the positioning of close associates with the specified person to be attended, improving the accuracy and efficiency of associated population analysis, pushing the information of the positioned close associates to enable the related persons to correspondingly process the close associates of the specified person to be attended in time, thereby being beneficial to ensuring public safety and social stability.

Description

Data processing method, device, equipment and computer readable storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for data processing.

Background

The related population analysis aims to extract closely related personnel and related modes from social mass data through modes of experience rules, statistical analysis, data mining and the like, analyze the distribution mode of the concerned personnel, calculate and search the population related to the concerned personnel and the like, and provide visual and effective analysis results for public safety precaution, epidemiological research, emergency response and the like.

The current associated population analysis methods mainly comprise: mining related personnel through the relativity relationship and the co-living relationship of the statistical personnel; and searching the related population of the concerned person through manual investigation.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: by counting the relative relationship between people and the static information of the same resident, the association generated by contact of people in various modes cannot be completely covered, and the associated people cannot be accurately positioned; the manual investigation mode is easy to omit and has low efficiency, so that close contacts of infected people or close relatives of suspects cannot be found in time, and public safety and social stability are influenced.

Disclosure of Invention

Embodiments of the present invention provide a data processing method, apparatus, device, and computer-readable storage medium, so as to solve the problem that the public safety and social stability are affected because the close contacts of infected people or the close contacts of suspects cannot be found in time due to the fact that the traditional analysis of associated people is easy to miss and has low efficiency.

In one aspect, an embodiment of the present invention provides a data processing method, including:

constructing a space-time knowledge graph according to static associated data and dynamic behavior data of a target crowd, wherein the space-time knowledge graph comprises contact associated information between any two persons in the target crowd and associated degree information of each person and a person to be concerned;

according to the spatio-temporal knowledge graph, inquiring an association target of which the association degree with the appointed concerned person meets a first contact association condition;

and pushing the information of the associated target.

In another aspect, an embodiment of the present invention provides a data processing apparatus, including:

the map building module is used for building a space-time knowledge map according to the static associated data and the dynamic behavior data of the target crowd, wherein the space-time knowledge map comprises contact associated information between any two persons in the target crowd and associated degree information of each person and a person to be concerned;

the correlation query module is used for querying a correlation target of which the correlation degree with the specified concerned person meets a first contact correlation condition according to the spatio-temporal knowledge map;

and the information pushing module is used for pushing the information of the associated target.

a processor, a memory, and a computer program stored on the memory and executable on the processor;

wherein the processor implements the data processing method when running the computer program.

In another aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the data processing method described above.

The data processing method, the device, the equipment and the computer readable storage medium provided by the embodiment of the invention construct the space-time knowledge map according to the static associated data and the dynamic behavior data of the target population, the space-time knowledge map comprises the contact associated information between any two persons in the target population, the contact associated information comprises the association of time dimension and space dimension, the space-time knowledge map also comprises the association degree information of each person and the person to be attended, the associated target with the association degree meeting the first contact associated condition with the appointed person to be attended can be quickly positioned by inquiring the space-time knowledge map, thereby realizing the positioning of the close associate with the appointed person to be attended, improving the accuracy and the efficiency of the analysis of the associated population, pushing the information of the positioned close associate to ensure that the related person can timely perform corresponding processing on the close associate with the appointed person to be attended, thereby being beneficial to ensuring public safety and social stability.

Drawings

Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention;

FIG. 2 is a flowchart of a data processing method according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a spatiotemporal knowledge map provided in this embodiment;

fig. 4 is a schematic structural diagram of a data processing apparatus according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a data processing apparatus according to a fourth embodiment of the present invention;

fig. 6 is a schematic structural diagram of a data processing device according to a fifth embodiment of the present invention.

With the above figures, certain embodiments of the invention have been illustrated and described in more detail below. The drawings and the description are not intended to limit the scope of the inventive concept in any way, but rather to illustrate it by those skilled in the art with reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

First, terms related to embodiments of the present invention are explained:

knowledge Graph (Knowledge Graph): and describing knowledge resources and carriers thereof by using a visualization technology, and mining, analyzing, constructing, drawing and displaying knowledge and mutual relations among the knowledge resources and the carriers.

PageRank: an evaluation method for borrowing the importance of an academic paper has the higher importance when the number of times of quotes is large.

Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the following examples, "plurality" means two or more unless specifically limited otherwise.

An application scenario of the embodiment of the present invention is as follows: the method is applied to the scene of epidemic disease prevention and control, and during the spreading of epidemic diseases, people closely related to known infected persons need to be found through analyzing related population of the infected persons, whether the closely related persons are infected or not is checked, and the infection source is timely found and cut off, so that epidemic disease prevention and control are realized. According to the embodiment, the space-time knowledge map comprising the association mode, the contact time, the contact place and the contact association information of the association mode between people and the association degree information of each person and the concerned person (known infected person) is established, the association target of the position and the appointed concerned person (appointed one or more known infected persons) meeting the first contact association condition can be quickly inquired, so that the quick positioning of the close contact person is realized, the contact association information of the close contact person and the appointed concerned person is pushed to the related person to inform isolation and investigation as soon as possible, the quick and accurate positioning of the close contact person can be realized, the investigation range is greatly reduced, omission is avoided, and the accuracy and the efficiency of the analysis of the associated people are improved.

Another application scenario of the embodiment of the present invention is as follows: the method is applied to public safety aspects, for example, relevant institutions need to perform relevant crowd analysis on suspects or fleets to search people closely related or contacted with the suspects or fleets, so that the relevant institutions can conveniently find places possibly hidden by the suspects or fleets, and effective relevant evidence of case situation analysis is collected. According to the embodiment, the space-time knowledge map comprising the association modes, the contact time, the contact places and the association mode contact association information between people and the association degree information of each person and the concerned person (known suspect or evasion) is established, the association target meeting the first contact association condition with the appointed concerned person (suspect or evasion) can be quickly inquired and positioned, so that the close-associated person and the close-associated person can be quickly positioned, the contact association information of the close-associated person and the appointed concerned person can be pushed to the relevant person for the relevant mechanism to refer to for investigation and information collection, the close-associated person and the close-associated person can be quickly and accurately positioned, the investigation range is greatly reduced, omission is avoided, and the accuracy and the efficiency of the analysis of the associated population are improved.

Another application scenario of the embodiment of the present invention is as follows: in the aspect of emergency response, public health events, such as infectious germ leakage, can be found through the space-time knowledge map provided by the embodiment, and the action track of a person (a person to be concerned) with germs can be found, so that a polluted site can be quickly positioned.

At present, the associated population analysis method does not focus on dynamic contact association by mining static association relations such as relatives and friends through statistical learning, but in epidemiology, emergency response and other scenes, the dynamic contact association is a necessary analysis for mining propagation paths. Environmental changes and personnel flow can cause rapid evolution of the personnel association network. By counting the relative relationship between people and the static information of the same resident, the association generated by contact of people in various modes cannot be completely covered, and the associated people cannot be accurately positioned. The manual investigation mode is easy to omit and has low efficiency, so that close contacts of infected people or close relatives of suspects cannot be found in time, and public safety and social stability are influenced.

According to the data processing method provided by the embodiment of the invention, the spatio-temporal knowledge map comprising the association modes, the contact time, the contact places, the association mode contact association information and the association degree information of each person and the concerned person (known infected person) is established, the spatio-temporal knowledge map comprises the static association and dynamic contact association information between persons, the contact association information has spatio-temporal attributes and comprises the causal relationship on a time dimension, the contact time of the middle person in chain association can be judged, the positioning and searching of the associated person in chain multi-hop contact are carried out, and the accuracy and the efficiency of the analysis of the associated population are improved.

The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Example one

Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention. As shown in fig. 1, the method comprises the following specific steps:

step S101, constructing a space-time knowledge map according to the static associated data and the dynamic behavior data of the target crowd, wherein the space-time knowledge map comprises contact associated information between any two persons in the target crowd and associated degree information of each person and the concerned person.

In this embodiment, the target group may be determined by specifying a group of people, or may be formed by specifying a geographic range, and all people within the geographic range that generate the static association data and/or the dynamic behavior data. The target crowd is not a fixed crowd, can change along with the time, and can add or delete people contained in the target crowd according to the actual application scene. The target group includes which persons can be configured and adjusted according to the actual application scenario, and this embodiment is not specifically limited here.

The static association data may include any data capable of representing a static association relationship between persons, such as a relationship of relatives, a relationship of friends, a relationship of co-residents, and the like.

The dynamic behavior data may comprise data that enables contact between people to generate a contact relationship, for example, two people who are consuming, checking in or registering at the same location one after the other, or who enter or exit the same location within a short time, and the like, and both people may be in contact with each other and have a dynamic relationship.

The method comprises the steps of acquiring all static associated data and dynamic behavior data of a target crowd, and constructing a space-time knowledge map based on the static associated data and the dynamic behavior data, wherein the space-time knowledge map comprises contact associated information (including static association and dynamic association) between people and associated information of a time dimension and a space dimension.

Further, some persons needing important attention (such as known infectors, suspects or fleets, bacteria propagation sources, and the like) can be marked as the persons to be attended in the spatiotemporal knowledge graph, and the spatiotemporal knowledge graph can also comprise information of the association degree of each person and the persons to be attended, wherein the higher the association degree is, the closer the contact with the persons to be attended is, and the closer the association is.

And S102, inquiring an association target of which the association degree with the specified person to be concerned meets a first contact association condition according to the spatio-temporal knowledge map.

The first contact-related condition is used for limiting the condition of close association, and if the degree of association between a certain person and a specified person to be attended satisfies the first contact-related condition, the person is considered to be a close associate of the specified person to be attended.

Based on the constructed spatiotemporal knowledge graph, people closely related to the specified concerned people, namely related targets, can be quickly inquired.

And step S103, pushing information of the associated target.

After the associated target of the designated person of interest is determined, the information of the associated target can be pushed in a push mode, so that the related person can timely acquire the associated target of the designated person of interest.

For example, information of a person who is closely related to a suspect or an escaped person is pushed to a related institution, thereby facilitating the related institution to perform troubleshooting and collect information required for case situations.

For example, the information of the close contact person of the known infected person is pushed to epidemic prevention and control personnel, so that the prevention and control personnel can conveniently and timely check and isolate the close contact person, and effective prevention and control is realized.

Optionally, contact association information between the association target and the specified person of interest may also be pushed to provide information that can be referred to, so that relevant persons may conveniently perform troubleshooting according to the contact association information between the association target and the specified person of interest.

The embodiment of the invention constructs the space-time knowledge map according to the static associated data and the dynamic behavior data of the target crowd, the space-time knowledge map comprises the contact associated information between any two persons in the target crowd, the contact associated information comprises the association of time dimension and space dimension, the space-time knowledge map also comprises the association degree information of each person and the concerned person, and by inquiring the space-time knowledge map, it is possible to quickly locate an association target whose degree of association with the specified person of interest satisfies the first contact association condition, thereby realizing the positioning of close relatives of appointed concerned persons, improving the accuracy and efficiency of the analysis of the related population, pushing the information of the positioned close relatives, so that the related personnel can correspondingly process the close relatives to the appointed concerned personnel in time, thereby being beneficial to ensuring public safety and social stability.

Example two

Fig. 2 is a flowchart of a data processing method according to a second embodiment of the present invention. On the basis of the first embodiment, in this embodiment, the constructing a spatiotemporal knowledge graph according to the static associated data and the dynamic behavior data of the target population includes: according to the static associated data and the dynamic associated data, determining contact associated information between any two persons in the target group, wherein the contact associated information comprises: current person, associated person, association mode, contact time, and contact location; creating a corresponding entity point for each person in the target crowd, and initializing attributes of the entity points, wherein the attributes of the entity points comprise association degree information with the concerned person, and the association degree information comprises: attention state, correlation strength, correlation level and contact frequency; and creating an association edge which takes the entity point corresponding to the current person as a starting end point and takes the entity point corresponding to the associated person as a terminating end point according to each piece of contact association information, and taking the association mode, the contact time and the contact place in the contact association information as the attributes of the association edge.

Further, when the attention state of at least one entity point changes, the attention entity point of which the attention state is the attention state in the space-time knowledge map is determined; and updating the attribute of the entity point with the associated hop count smaller than the hop count threshold value between the entity point and the concerned entity point.

As shown in fig. 2, the method comprises the following specific steps:

step S201, obtaining static related data and dynamic behavior data of the target crowd.

In this embodiment, the static associated data at least includes the relationship data and the co-existence relationship data. The dynamic behavior data comprises stay mark data and/or access record data of all places in the region range corresponding to the target crowd.

Wherein each piece of stay mark data includes a mark person, a mark place, and a mark time. The stay mark data may be card punch, consumption or registration data, etc. for various locations. Such as consumption data of a mall, supermarket, railway station, subway station, etc., or registration data of a supermarket entrance, etc.

Each access record data comprises access personnel, access places, access time and egress time. The access record data may be access records in places such as venues and office areas.

Illustratively, the total data of the target people group can be obtained through various channels, including static information of family conditions, addresses, native places, friend information and the like of various people, and related information of dynamic travel of various people. And the static associated data and the dynamic behavior data are extracted by cleaning and sorting the data of the total data.

Step S202, contact correlation information between any two persons in the target group is determined according to the static correlation data and the dynamic behavior data.

Wherein the contact associated information includes: current person, associated person, manner of association, time of contact, and location of contact.

After the static associated data and the dynamic associated data of the target crowd are obtained, further data processing is needed, and contact associated information between any two people is extracted.

And for the static associated data, performing data analysis according to the static associated data to generate static contact associated information between any two persons in the target group. The association mode of the static contact association information at least comprises a relationship of relatives and a relationship of living together.

In addition, the contact time and the contact location in the static contact related information may be determined according to a specific association relationship. For the relationship, a time period as a relative to each other may be set as the contact time, and the contact location may be a home address, or no setting may be made. For example from marriage to date, from birth to date, etc. For the relationship of the same residence, the time period of the same residence can be set as the contact time, and the contact place is the address of the same residence.

Optionally, persons with static association relations (including at least relatives or co-habitation relations) may be determined, and corresponding contact association information is generated for any two persons with static association relations.

For example, for two persons a and B having a relationship of being in the same residence, two pieces of contact related information may be generated. One piece of contact associated information comprises: the current person A is associated with the associated person B in the following way: parentage, contact time: stay period, contact location: the co-located address. Another piece of contact related information includes: the current person B is associated with the associated person A in the following way: parentage, contact time: stay period, contact location: the co-located address.

For the stay mark data in the dynamic behavior data, the stay mark data can be processed in the following way:

if any piece of data in the stay mark data is taken as first mark data, and second mark data which is the same as the mark position of the first mark data exists and the mark time of the second mark data is within a preset time interval after the mark time of the first mark data, generating a piece of contact related information; the contact related information comprises a current person, a contact position and a contact time, wherein the current person in the contact related information is a marker of first marker data, the related person is a marker of second marker data, the contact time comprises the marker time of the first marker data and the marker time of the second marker data, and the contact position is the marker position of the first marker data; and determining the association mode of the contact associated information according to the contact position.

When the stay mark data is processed, for any current person, assuming that the mark time of the current person is T, extracting the person entering the same mark place within the preset time interval T [ T, T + T ] as the associated person, and generating a piece of contact associated information for each associated person.

The preset time interval may be configured and adjusted according to an actual application scenario, and this embodiment is not specifically limited herein.

Illustratively, for the access record data in the dynamic behavior data, the following method can be used for processing:

respectively taking any piece of data in the access record data as first record data, and if second record data which is the same as the access point of the first record data exists and the intersection of the residence time of the access personnel of the first record data and the residence time of the access personnel of the second record data at the access point is not empty, generating a piece of contact associated information, wherein the current personnel in the contact associated information is the personnel who enter the access personnel of the first record data and the second record data first and the associated personnel are the personnel who enter the access personnel of the first record data and the second record data later, the contact time comprises the starting time and the ending time of the intersection of the residence time, and the contact point is the record point of the first record data; and determining the association mode of the contact associated information according to the contact position.

When the access record data is processed, for any person, extracting the time intersection of the residence time of the person and other persons in the same record place, and if the time intersection is not empty, generating corresponding contact associated information. The current person in the contact associated information is a person who enters the first recorded data and the second recorded data in the person who enters the second recorded data, and the associated person is a person who enters the second recorded data in the person who enters the second recorded data.

In this embodiment, when the corresponding contact related information is generated according to the dynamic behavior data, the association manner of the contact related information may be determined according to the contact location, and the corresponding association manner may be determined according to the size and type of the location corresponding to the contact location.

Alternatively, mapping information for setting the type and size of each place and the corresponding association manner may be preset. Based on the mapping information, the corresponding association method can be determined according to the size and type of the place corresponding to the contact location.

In addition, the association manner in this embodiment may include multiple manners, and may be specifically configured according to an actual application scenario, for example, the association manner may be divided and designed according to a contact manner, a location type and a size of a contact location, and the like, and this embodiment is not specifically limited herein.

For example, the association means may include: relatives, living relations, buses, airplanes, etc., gas stations, supermarkets, etc., buildings, such as office buildings, and railway stations.

Step S203, corresponding entity points are created for each person in the target crowd, and attributes of the entity points are initialized.

In this embodiment, a person is represented by an entity point in the spatiotemporal knowledge graph. The attribute of the entity point includes information of degree of association with the person concerned. The association degree information at least includes: attention state, association strength, association level, number of contacts.

The attention state is used for identifying whether the entity point corresponds to a person who is attended, and the attention state comprises an attended state and an unattended state. The person of interest may be a known infected person, or a wanted person, or a bacterial carrier, etc.

Alternatively, if the value of the attention state is "1", it indicates the attention state; if the value of the attention state is "0", it indicates an attention-free state.

In addition, the attribute of the entity point may further include identification information and other related information of a corresponding person, in other embodiments, the attribute of the entity point may further include other information, the association degree information may also include other information, and what information the attribute of the entity point and the association degree information specifically include may be configured and adjusted according to an actual application scenario, which is not specifically limited in this embodiment.

For example, when the attribute of the entity point is initialized, the attention state is initialized to the attention-free state, the value of the association strength is initialized to 0, the association level is initialized to none or empty, and the value of the number of contacts is initialized to 0.

And step S204, creating an association edge which takes the entity point corresponding to the current person as a starting end point and takes the entity point corresponding to the associated person as a terminating end point according to each piece of contact association information, and taking the association mode, the contact time and the contact place in the contact association information as the attributes of the association edge.

In this embodiment, the spatiotemporal knowledge graph may be constructed according to the time dimension information of the contact related information and the time sequence.

And establishing an association edge between the current person and the associated person according to each piece of contact association information, wherein the association edge takes the entity point corresponding to the current person as a starting end point and takes the entity point corresponding to the associated person as an ending end point. And simultaneously writing the association mode, the contact time and the contact position in the contact association information into the attribute of the association edge. Thus, the constructed space-time knowledge map records contact related information among various persons.

For example, fig. 3 is a schematic diagram of a spatiotemporal knowledge graph provided by this embodiment, and the constructed spatiotemporal knowledge graph may be as shown in fig. 3, where each circle represents a person, each arrow represents an associated edge and represents a contact, a start point of the arrow represents a start endpoint of the associated edge, and an end point of the arrow represents an end endpoint of the associated edge. Fig. 3 shows only a part of the entity points and the associated edges between the entity points, the attributes of the associated edges only show the association manner, the contact time and the contact location are not shown, and the attributes of the entity points are not shown.

In addition, the spatio-temporal knowledge graph may also display the attribute of the associated edge and the attribute of the entity point, which are not shown in fig. 3, or display the attribute of the associated edge and the attribute of the entity point, where the associated edge and the attribute of the entity point may be directly displayed at the corresponding position of the associated edge and the entity point, or displayed in a fixed area on the display interface, which is not specifically limited in this embodiment.

Optionally, when the spatiotemporal knowledge graph is displayed, statistical information in the spatiotemporal knowledge graph can be automatically counted and displayed, for example, the total number of people, the number of people concerned, the number of associated edges (i.e., the number of contacts) of various associated modes, and the like, so that the overall situation of data in the spatiotemporal knowledge graph can be intuitively understood.

And S205, acquiring newly added associated data of the target population, and updating the space-time knowledge map according to the newly added associated data.

The newly added associated data comprises static associated data and/or dynamic behavior data.

In the embodiment, the new data of the target population can be acquired in real time, and the new data is cleaned and sorted to generate corresponding new associated data; and then determining newly-added contact associated information according to the newly-added associated data, updating the space-time knowledge map according to the newly-added contact associated information, and updating the space-time knowledge map in real time so that the associated information between people contained in the space-time knowledge map is more comprehensive, and closely-associated people inquired based on the space-time knowledge map are not missed and are more accurate.

And if the data of the new personnel is added into the newly added associated data and the newly added contact associated information relates to the newly added personnel, creating entity points of the newly added personnel in the space-time knowledge graph, and creating corresponding associated edges in the space-time knowledge graph according to the newly added contact associated information.

And if the data of the new personnel is not added in the newly added associated data and only the contact associated information between the existing personnel is added, creating a corresponding associated edge in the space-time knowledge map according to the newly added contact associated information.

And step S206, when the attention state of at least one entity point changes, determining the attention entity point of which the attention state is the attention state in the space-time knowledge map.

The attention entity points refer to entity points of which the attention state is the attention state in the space-time knowledge graph.

In this embodiment, the attention state of the entity point in the spatio-temporal knowledge graph can be updated in real time according to the change information of the person to be attended. And when the attention state of the entity points in the space-time knowledge map is changed, updating the association degree information of the entity points in the state which is not concerned and the entity points in the state which is concerned after the change in the space-time knowledge map.

For example, when there is a newly added infected person, the attention state of the entity point corresponding to the newly added infected person in the spatio-temporal knowledge map may be set as the attention state.

Illustratively, change information of the person to be attended, which is input externally, can be imported, and automatically according to the change information of the person to be attended, the attention state of the entity points in the spatio-temporal knowledge map can be updated in real time, and when the attention state of the entity points changes, the attribute of the entity points with the smaller number of association hops between the entity points and the attention entity points in the spatio-temporal knowledge picture is triggered, so that the association degree information of the entity points and the attention entity points is updated.

Wherein the attended person change information may include person information changed from attended persons to unattended persons, and person information changed from unattended persons to attended persons; or the attendee change information may include information that changes the attended state of the specified entity point, and the like.

In the step, when the attention state of at least one entity point changes, all attention entity points in the space-time knowledge map are obtained according to the attention state of each entity point.

And step S207, updating the attribute of the entity point with the associated hop count smaller than the hop count threshold value between the entity point and the concerned entity point.

The number of associated hops between the first entity point and the second entity point refers to the number of associated edges included in the shortest path from the second entity point to the first entity point.

In this embodiment, an m-hop association point of an entity point refers to an entity point with m associated hops between the entity point and the entity point, where m is a positive integer.

Illustratively, a one-hop association point of one entity point refers to an entity point with an association hop count of 1, and a two-hop association point of one entity point refers to an entity point with an association hop count of 2.

The hop count threshold in this step may be configured and adjusted according to an actual application scenario, and this embodiment is not specifically limited here. For example, the hop count threshold may be 3, in which the attribute of the entity point having an associated hop count of 1 or 2 with the entity point of interest is updated.

After all the entity points of interest are determined according to the states of the people of interest, all the associated edges associated with the entity points of interest can be found.

In this embodiment, the association manner may be divided into a plurality of contact classifications according to the contact association information, and different contact classifications correspond to different association levels.

Illustratively, the association modes can be classified into the following three types of contacts according to the contact association information: the first type of contact is: long-time close contact, such as relatives and co-residents; the second type of contact is: short-time close contact or long-time long-distance contact, such as ticket picking and ticket checking contact, supermarket contact and the like; the third type of contact is: long-time remote contact, such as going to a park and the like;

the short-distance contact means that the contact is in a small closed space, namely, the contact place is a small closed space. The contact at a longer distance refers to the contact being in a large sealed space, namely the contact site is a large sealed space. Remote contact refers to the co-location within a large open space. Which places belong to small-sized closed space, which places belong to large-sized closed space, and which places belong to large-sized open space, can be configured and adjusted according to actual application scenes, and this embodiment is not specifically limited here. The specific time length ranges for the long time contact and the short time contact are not particularly limited.

In this embodiment, the contact classification to which each association method belongs may be configured in advance. According to each association mode, the corresponding contact classification can be determined, so that the corresponding association level can be determined.

For example, updating the attribute of the entity point of which the associated hop count with the entity point of interest is smaller than the hop count threshold includes updating the attribute of the one-hop associated point of the entity point of interest, which may specifically be implemented in the following manner:

determining a one-hop association point of the concerned entity point; and for each one-hop association point, updating the attribute of the one-hop association point according to the attribute of the association edge between the one-hop association point and each concerned entity point.

Illustratively, for each one-hop association point of the entity points of interest, the attribute of the one-hop association point is updated according to the attribute of the association edge between the one-hop association point and each entity point of interest, which may specifically be implemented as follows:

for each one-hop association point of the concerned entity points, determining a first association edge between the one-hop association point and each concerned entity point, wherein the first association edge takes any concerned entity point as an initial end point and takes the one-hop association point as an association edge of a termination end point; determining the association grade corresponding to the first association edge according to the association mode of the first association edge; determining the highest level in the association levels corresponding to the first association edges and the number of second association edges with the corresponding association levels being the highest levels; determining the correlation strength corresponding to each second correlation edge according to the attribute of the second correlation edge; and taking the highest level as the association level of the one-hop association point, taking the number of the first association edges corresponding to the highest level as the contact times of the one-hop association point, taking the maximum value of the association strengths corresponding to the second association edges as the association strength of the one-hop association point, and updating the attribute of the one-hop association point.

Each first association edge represents the association between one-hop association point and the attention entity point, and the association level corresponding to the association mode of the first association edge is the association level of the association between one-hop association point and the attention entity point. The highest level of the relevance levels corresponding to the first relevance edge is the highest level of all relevance levels of the one-hop relevance point and the entity point of interest. The number of the first associated edges corresponding to the highest level, that is, the cumulative number of associations having the highest level of association occurring between the one-hop association point and the entity point of interest.

In this embodiment, when calculating the association strength corresponding to the association edge, the association strength calculation manners corresponding to different association levels may be different according to the association levels corresponding to the association edges, and the association strength calculation manners corresponding to the association levels may be preset.

The association strength corresponding to the association edge between two entity points is also the association strength of the association corresponding to the association edge between two entity points. The association strength corresponding to the first association edge between a certain entity point and the attention entity point can embody the association of the attention entity point to the certain entity point in the contact corresponding to the first association edge.

Optionally, the updating of the attribute of the entity point whose associated hop count with the entity point of interest is smaller than the hop count threshold value further includes updating the attribute of the two-hop association point of the entity point of interest, which may be specifically implemented by the following method:

and determining two-hop association points of the concerned entity points, and updating the attributes of the two-hop association points according to the attributes of the association edges between the two-hop association points and the concerned entity points, the attributes of the association edges between the concerned entity points and the attributes of the updated one-hop association points for each two-hop association point.

Specifically, for each two-hop association point of the concerned entity point, determining the two-hop association strength between the two-hop association point and the corresponding concerned entity point according to the attribute of the association edge between the two-hop association point and each one-hop association point, the attribute of the association edge between each one-hop association point and each concerned entity point, and the attribute of the updated one-hop association point; taking the maximum value of the two-hop association strength between the two-hop association point and the corresponding attention entity point as the association strength of the two-hop association point, and updating the association strength of the two-hop association point; updating the association level of the two-hop association point to be a designated association level; and updating the contact times of the two-hop associated points to the specified contact times.

Optionally, the association level of the two-hop association point is uniformly set to a specified association level, which may be the lowest association level or another lower association level, and is not specifically limited herein.

Optionally, the number of contacts of the two-hop association point is uniformly set to be a specified number of contacts, which may be 1 or another smaller number, and is not limited herein.

Further, determining the two-hop association strength between the two-hop association point and the corresponding attention entity point according to the attributes of the association edges between the two-hop association point and each one-hop association point, the attributes of the association edges between each one-hop association point and each attention entity point, and the attributes of the updated one-hop association point, including:

for each corresponding attention entity point, determining a third entity point, wherein the associated hop count of the third entity point and the corresponding attention entity point is 1, and the associated hop count of the second hop associated point and the third entity point is 1; for each third entity point, determining a third association edge between the second hop association point and the third entity point, wherein the third association edge takes the third entity point as a starting end point and takes the second hop association point as an association edge of a termination end point; determining the association grade corresponding to the third association side according to the association mode of the third association side; determining the correlation strength corresponding to the fourth correlation side according to the attribute of the fourth correlation side with the highest correlation grade in the third correlation sides; determining the second hop association strength corresponding to the third entity point according to the maximum value of the association strength corresponding to the fourth association edge and the updated association strength of the third entity point; and determining the maximum value of the two-hop association strength corresponding to each third entity point as the two-hop association strength between the two-hop association point and the corresponding association entity point.

Optionally, the two-hop association strength corresponding to the third entity point may be determined by multiplying the maximum value of the association strength corresponding to the fourth association edge by the updated association strength of the third entity point.

Optionally, the two-hop association strength corresponding to the third entity point may be determined by a weighted product of the maximum value of the association strength corresponding to the fourth association edge and the updated association strength of the third entity point. The weighted values of the two can be set according to the actual application scene.

Optionally, the updating of the attribute of the entity point whose associated hop count with the entity point of interest is smaller than the hop count threshold may also include updating the attribute of the three-hop association point of the entity point of interest, and a specific implementation manner may be obtained by extending an implementation manner of updating the attribute of the two-hop association point of the entity point of interest, which is not described herein again.

Further, determining the association strength corresponding to a certain association edge according to the attribute of the association edge may be implemented in the following manner:

and determining the corresponding association grade according to the association strength corresponding to the association edge, further determining a corresponding association strength calculation mode, and calculating according to the corresponding association strength calculation mode.

Exemplarily, several association manners are taken as examples in table 1, and the calculation manners of the association strengths corresponding to different association manners are exemplarily described, which are specifically shown in table 1 below:

TABLE 1

Wherein i represents an entity point of interest; j represents a one-hop association point of the entity point i of interest; k represents a two-hop association point of the concerned entity point i, and the two-hop association point k is associated with the concerned entity point i through a one-hop association point j; score_ijAn association strength, score, representing a first association edge between a one-hop association point j and an entity point of interest i_jkRepresents the strength of the association of a second association edge, score, between a two-hop association point k and a one-hop association point j_ijkAnd representing the strength of association between the two-hop association point k and the concerned entity point i through the one-hop association point j. a1, a2, a3, a4, a5 and a6 represent initial association strengths corresponding to preset association modes, the initial association strengths are highly correlated with the association levels of the association modes, the higher the association level is, the greater the initial association strength is, such as the association levels shown in table 1, a1, a2 and a3 are all larger than the maximum value of a4 and a5, and a4 and a5 are all larger than a6, a1, a2, a3, a4, a5 and a6 are all smaller than 1. b4, b5, b6 indicate that the correlation intensity decay/increase coefficients are all less than all the initial correlation intensities, and b4, b5, b6 are all less than 1. T is_ijRepresenting the time interval between the contact times of the persons corresponding to i and j, i.e. the consumption time interval of the persons corresponding to i and j. t is t_ijIndicating the length of time that i and j correspond to the intersection of the person and the time spent at the touch location. The 1h represents the duration of one hour, is a preset time interval, and can be set to other durations according to actual application scenarios. The 1day represents the time of day, and can be set to other time according to the actual application scene.

In this embodiment, when the attribute of the one-hop association point of the entity point of interest is updated, all edges associated with the entity point of interest may be derived, and the attribute of the one-hop association point is calculated according to the attribute of each edge and updated to the spatiotemporal knowledge map.

When the attributes of the two-hop association points of the concerned entity points are updated, all edges related to the one-hop association points of the concerned entity points and the attributes of the one-hop association points can be derived, the attributes of the two-hop association points are obtained through calculation according to the derived data, and the attributes are updated into the spatio-temporal knowledge map.

In this embodiment, after the spatio-temporal knowledge map is created, in steps S208 to S210, according to the spatio-temporal knowledge map, an association target satisfying the first contact association condition with the specified person of interest is queried, in this embodiment, a case of querying a first hop association target and a second hop association target with the specified person of interest is taken as an example for illustration, in other embodiments of this embodiment, only the first hop association target may be queried, or a case of querying a third hop association target or other association targets with more association hops between the specified person of interest and the specified person of interest may be queried, which is not specifically limited herein.

And step S208, determining a one-hop association point of the entity point corresponding to the appointed concerned person in the spatio-temporal knowledge map.

In this embodiment, when the association degree with the specified person of interest satisfies the association target of the first contact association condition, the query range may be limited to the one-hop association point of the specified person of interest, and the one-hop association point whose association degree with the specified person of interest satisfies the first contact association condition may be queried.

In this step, first, a one-hop association point of the entity point corresponding to the specified person of interest is determined, and then, a one-hop association point, in which the degree of association between the query and the specified person of interest satisfies the first contact association condition, is determined in the subsequent step S209.

In this embodiment, when querying the association target, a time range may be further specified, and the association target may be queried according to the contact association information and the entity point corresponding to the contact occurring within the specified time range.

Exemplarily, screening the associated edges in the time-space knowledge graph according to the specified time range, and determining a fifth associated edge with intersection between the contact time and the specified time range; and determining a starting end point in the fifth associated edge as a sixth associated edge of the entity point corresponding to the specified person to be noted, and determining a terminating end point of the sixth associated edge as a one-hop associated point.

And step S209, regarding the person corresponding to the one-hop association point meeting the first contact association condition as the one-hop association target of the designated concerned person.

The designated one-hop association target of the person concerned is a person corresponding to the one-hop association point of which the association degree of the designated person concerned satisfies the first contact association condition.

Optionally, sorting the one-hop association points according to the association level, the contact times and the association strength according to the attributes of the one-hop association points; and according to the sequencing result, the personnel corresponding to the first N-bit one-hop association point are used as the one-hop association target of the appointed concerned personnel, wherein N is a positive integer.

Specifically, the one-hop association points may be sorted according to the attribute of the one-hop association points from high to low in association level; for the one-hop association points with the same association level, sorting the association points according to the order of the contact times from more to less; and for the one-hop association points with the same association level and the same contact times, sorting the association points according to the sequence from high association strength to low association strength to obtain a sorting result.

N may be configured and adjusted according to an actual application scenario, and this embodiment is not specifically limited herein. For example, N may be 100.

Optionally, the sorting of the one-hop association points can also be realized by adopting a PageRank algorithm, and the more the contact times are, the higher the importance of the entity point is, and the higher the association strength is. According to the PageRank idea, the contact times are highlighted, and high-potential contacts are searched.

Optionally, the first contact association condition is that the association strength is greater than a preset threshold. The preset threshold may be configured and adjusted according to an actual application scenario, and this embodiment is not specifically limited herein.

Step S210, determining a two-hop association point of the appointed concerned person according to the one-hop association point; and taking the person corresponding to the second-hop association point meeting the second contact association condition as a second-hop association target of the appointed concerned person.

In this embodiment, after the first-hop association target is determined, the second-hop association points meeting the second contact association condition may be continuously searched in the second-hop association points of the specified attended person, and the second-hop association target of the specified attended person is determined.

The second contact association condition is similar to the first contact condition, where the setting of N and the preset threshold may be different from the first contact condition, and details are not repeated here.

Optionally, a specified three-hop associated target, four-hop associated target, and the like of the person to be attended may also be continuously queried, which is not specifically limited herein.

And step S211, pushing the information of the related targets.

The information of the associated target may include an attribute of an entity point corresponding to the associated target.

Optionally, the information of the associated target may further include contact associated information between the associated target and the specified person of interest, and by pushing the contact associated information between the associated target and the specified person of interest, more information that can be referred to is provided, so that the relevant person can conveniently perform troubleshooting according to the contact associated information between the associated target and the specified person of interest.

In the embodiment, the attribute information of the time dimension and the attribute information of the space dimension are stored in the time-space knowledge map for calculation through the time-space knowledge map technology, the causal relationship in the epidemic infection time dimension is fully considered, useless association is effectively screened, and the comprehensiveness and effectiveness of infection traceability and close-contact person risk calculation are ensured.

The embodiment provides a set of association level evaluation criteria and association strength calculation mode based on time constraint and space constraint, and can accurately calculate the association degree between the entity point and the entity point to be focused on.

According to the embodiment of the invention, the space-time knowledge map is constructed according to the static association data and the dynamic behavior data of the target population, the space-time knowledge map comprises the contact association information between any two persons in the target population, the contact association information comprises the association of the time dimension and the space dimension, the attribute information of the time dimension and the space dimension is stored in the map, the association strength is calculated, the causal relationship in the epidemic infection time dimension is fully considered, the useless association is effectively screened, the comprehensiveness and effectiveness of risk calculation of close contacts can be ensured by inquiring the space-time knowledge map, and the accuracy and the efficiency of the analysis of the associated population can be improved.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a data processing apparatus according to a third embodiment of the present invention. The data processing device provided by the embodiment of the invention can execute the processing flow provided by the method embodiment of the data processing. As shown in fig. 4, the data processing apparatus 30 includes: the system comprises a map building module 301, an association query module 302 and an information pushing module 303.

Specifically, the map building module 301 is configured to build a spatiotemporal knowledge map according to the static associated data and the dynamic behavior data of the target population, where the spatiotemporal knowledge map includes contact associated information between any two persons in the target population and associated degree information between each person and a person to be attended.

The association query module 302 is configured to query, according to the spatio-temporal knowledge graph, an association target whose association degree with the specified person of interest satisfies the first contact association condition.

The information pushing module 303 is configured to push information of the associated target.

The apparatus provided in the embodiment of the present invention may be specifically configured to execute the method embodiment provided in the first embodiment, and specific functions are not described herein again.

Example four

Fig. 5 is a schematic structural diagram of a data processing apparatus according to a fourth embodiment of the present invention. On the basis of the third embodiment, in this embodiment, the map building module is further configured to:

according to the static associated data and the dynamic associated data, determining contact associated information between any two persons in the target group, wherein the contact associated information comprises: current person, associated person, association mode, contact time, and contact location; creating a corresponding entity point for each person in the target crowd, and initializing attributes of the entity points, wherein the attributes of the entity points comprise association degree information with the concerned person, and the association degree information comprises: attention state, correlation strength, correlation level and contact frequency; and creating an association edge which takes the entity point corresponding to the current person as a starting end point and takes the entity point corresponding to the associated person as a terminating end point according to each piece of contact association information, and taking the association mode, the contact time and the contact place in the contact association information as the attributes of the association edge.

In an alternative embodiment, as shown in fig. 5, the data processing apparatus 30 further includes: a data processing module 304 for:

acquiring static associated data, wherein the static associated data at least comprises family relation data and living relation data; the method comprises the steps of obtaining dynamic behavior data, wherein the dynamic behavior data comprise stay mark data and/or access record data of all places in a region range corresponding to target people, each stay mark data comprises marked personnel, marked places and marked time, and each access record data comprises the marked personnel, the marked places, the marked times and the marked times.

In an alternative embodiment, the atlas-building module is further configured to:

and generating static contact associated information between any two persons in the target group according to the static associated data, wherein the association mode of the static contact associated information at least comprises a relationship of relativity and a relationship of living together.

respectively taking any piece of data in the stay mark data as first mark data, and if second mark data which is the same as the mark place of the first mark data exists and the mark time of the second mark data is within a preset time interval after the mark time of the first mark data, generating a piece of contact associated information; the contact related information comprises a current person, a contact position and a contact time, wherein the current person in the contact related information is a marker of first marker data, the related person is a marker of second marker data, the contact time comprises the marker time of the first marker data and the marker time of the second marker data, and the contact position is the marker position of the first marker data; and determining the association mode of the contact associated information according to the contact position.

when the attention state of at least one entity point changes, the attention entity point of which the attention state is the attention state in the space-time knowledge map is determined; and updating the attribute of the entity point of which the associated hop count between the entity point of interest and the entity point is less than the hop count threshold, wherein the associated hop count between the first entity point and the second entity point refers to the number of associated edges contained in the shortest path from the second entity point to the first entity point.

determining a one-hop association point of the concerned entity point, wherein the one-hop association point is an entity point with the concerned entity point and the association hop number of which is 1; and for each one-hop association point, updating the attribute of the one-hop association point according to the attribute of the association edge between the one-hop association point and each concerned entity point.

determining a two-hop association point of the concerned entity point, wherein the two-hop association point is an entity point with the concerned entity point and the association hop number of which is 2; and for each two-hop associated point, updating the attribute of the two-hop associated point according to the attribute of the associated edge between the two-hop associated point and each one-hop associated point, the attribute of the associated edge between each one-hop associated point and each concerned entity point and the attribute of the updated next-hop associated point.

for each one-hop association point, determining a first association edge between the one-hop association point and each concerned entity point, wherein the first association edge takes any concerned entity point as an initial end point and takes the one-hop association point as an association edge of a termination end point; determining the association grade corresponding to the first association edge according to the association mode of the first association edge; determining the highest level in the association levels corresponding to the first association edges and the number of second association edges with the corresponding association levels being the highest levels; and determining the association strength corresponding to each second association edge according to the attributes of the second association edges, taking the highest level as the association level of the association point of one hop, taking the number of the first association edges corresponding to the highest level as the contact times of the association point of one hop, taking the maximum value in the association strengths corresponding to each second association edge as the association strength of the association point of one hop, and updating the attribute of the association point of one hop.

for each two-hop association point, determining the two-hop association strength between the two-hop association point and the corresponding attention entity point according to the attribute of the association edge between the two-hop association point and each one-hop association point, the attribute of the association edge between each one-hop association point and each attention entity point and the attribute of the updated one-hop association point; taking the maximum value of the two-hop association strength between the two-hop association point and the corresponding attention entity point as the association strength of the two-hop association point, and updating the association strength of the two-hop association point; updating the association level of the two-hop association point to be a designated association level; and updating the contact times of the two-hop associated points to the specified contact times.

and updating the attention state of the entity points in the space-time knowledge map according to the change information of the person to be attended.

In an alternative embodiment, the data processing module 304 is further configured to: and acquiring newly added associated data of the target population, wherein the newly added associated data comprises static associated data and/or dynamic behavior data.

The map building module is further configured to: and updating the space-time knowledge map according to the newly added associated data.

In an optional implementation, the association query module is further configured to:

determining a one-hop association point of the entity point corresponding to the appointed concerned person in a spatio-temporal knowledge map, wherein the one-hop association point is the entity point with the association hop number of 1 between the entity point corresponding to the appointed concerned person and the entity point; and taking the person corresponding to the one-hop association point meeting the first contact association condition as a one-hop association target of the appointed concerned person.

screening the associated sides in the time-space knowledge graph according to the specified time range, and determining a fifth associated side with intersection between the contact time and the specified time range; and determining a starting end point in the fifth associated edge as a sixth associated edge of the entity point corresponding to the specified person to be noted, and determining a terminating end point of the sixth associated edge as a one-hop associated point.

sorting the one-hop association points according to the association grade, the contact times and the association strength according to the attributes of the one-hop association points; and according to the sequencing result, the personnel corresponding to the first N-bit one-hop association point are used as the one-hop association target of the appointed concerned personnel, wherein N is a positive integer.

In an alternative embodiment, the first contact correlation condition is that the correlation strength is greater than a preset threshold.

determining a two-hop association point of the appointed concerned person according to the one-hop association point; and taking the person corresponding to the second-hop association point meeting the second contact association condition as a second-hop association target of the appointed concerned person.

The apparatus provided in the embodiment of the present invention may be specifically configured to execute the method embodiment provided in the second embodiment, and specific functions are not described herein again.

EXAMPLE five

Fig. 6 is a schematic structural diagram of a data processing device according to a fifth embodiment of the present invention. As shown in fig. 6, the apparatus 100 includes: a processor 1001, a memory 1002, and computer programs stored on the memory 1002 and executable on the processor 1001.

When the processor 1001 runs the computer program, the method for processing data provided by any one of the above method embodiments is implemented.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the data processing method provided in any of the above method embodiments.

It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims

1. A method of data processing, comprising:

and pushing the information of the associated target.

2. The method of claim 1, wherein constructing a spatiotemporal knowledge graph from the static association data and the dynamic behavior data of the target population comprises:

according to the static associated data and the dynamic associated data, determining contact associated information between any two persons in the target group, wherein the contact associated information comprises: current person, associated person, association mode, contact time, and contact location;

creating a corresponding entity point for each person in the target crowd, and initializing attributes of the entity points, wherein the attributes of the entity points comprise association degree information of the person concerned, and the association degree information comprises: attention state, correlation strength, correlation level and contact frequency;

and creating an association edge which takes the entity point corresponding to the current person as a starting end point and the entity point corresponding to the associated person as a terminating end point according to each piece of contact association information, and taking the association mode, the contact time and the contact place in the contact association information as the attributes of the association edge.

3. The method according to claim 2, wherein before constructing the spatiotemporal knowledge graph according to the static association data and the dynamic behavior data of the target population, the method further comprises:

acquiring the static associated data, wherein the static associated data at least comprises relativity relationship data and living relationship data;

and acquiring the dynamic behavior data, wherein the dynamic behavior data comprises stay mark data and/or access record data of each place in a region range corresponding to the target population, each stay mark data comprises a mark person, a mark place and mark time, and each access record data comprises an access person, an access place, access time and egress time.

4. The method of claim 3, wherein determining contact correlation information between any two people in the target group of people based on the static correlation data and the dynamic correlation data comprises:

and generating static contact associated information between any two persons in the target group according to the static associated data, wherein the association mode of the static contact associated information at least comprises a relationship of relatives and a relationship of living together.

5. The method of claim 3, wherein generating the association record for each person in the target group based on the static association data and the dynamic association data comprises:

respectively taking any piece of data in the stay mark data as first mark data, and if second mark data which is the same as the mark position of the first mark data exists and the mark time of the second mark data is within a preset time interval after the mark time of the first mark data, generating a piece of contact related information; wherein the current person in the contact related information is a tagged person of the first tagged data, the associated person is a tagged person of the second tagged data, the contact time includes a tagging time of the first tagged data and a tagging time of the second tagged data, and the contact place is a tagging place of the first tagged data;

and determining the association mode of the contact association information according to the contact place.

6. The method of claim 3, wherein generating the association record for each person in the target group based on the static association data and the dynamic association data comprises:

respectively taking any piece of data in the access record data as first record data, and if second record data which is the same as the access point of the first record data exists and the intersection of the residence time of the access personnel of the first record data and the second record data at the access point is not empty, generating contact associated information, wherein the current personnel in the contact associated information is the personnel who enter the access personnel of the first record data and the second record data firstly, the associated personnel is the personnel who enter the access personnel of the first record data and the second record data later, the contact time comprises the starting time and the ending time of the intersection of the residence time, and the contact point is the record point of the first record data;

7. The method according to claim 2, wherein after the building the spatiotemporal knowledge graph according to the static association data and the dynamic behavior data of the target population, the method further comprises:

when the attention state of at least one entity point changes, the attention entity point of which the attention state is the attention state in the space-time knowledge map is determined;

and updating the attribute of the entity point of which the associated hop count between the entity point of interest and the entity point is less than a hop count threshold, wherein the associated hop count between the first entity point and the second entity point refers to the number of associated edges included in the shortest path from the second entity point to the first entity point.

8. The method of claim 7, wherein updating the attributes of the entity points having associated hop counts smaller than a hop count threshold with the entity point of interest comprises:

determining a one-hop association point of the entity point concerned, wherein the one-hop association point refers to an entity point with the entity point concerned and the association hop number of which is 1;

and for each one-hop association point, updating the attribute of the one-hop association point according to the attribute of the association edge between the one-hop association point and each concerned entity point.

9. The method according to claim 8, wherein after updating the attribute of the one-hop association point according to the attribute of the first association edge between the one-hop association point and each entity point of interest, the method further comprises:

determining a two-hop association point of the entity point concerned, wherein the two-hop association point refers to an entity point with the entity point concerned and the association hop number of which is 2;

and for each two-hop associated point, updating the attribute of the two-hop associated point according to the attribute of the associated edge between the two-hop associated point and each one-hop associated point, the attribute of the associated edge between each one-hop associated point and each concerned entity point and the updated attribute of the one-hop associated point.

10. The method according to claim 9, wherein for each of the one-hop association points, updating the attribute of the one-hop association point according to the attribute of the association edge between the one-hop association point and each of the entity points of interest comprises:

for each one-hop association point, determining a first association edge between the one-hop association point and each concerned entity point, wherein the first association edge is an association edge which takes any concerned entity point as a starting endpoint and takes the one-hop association point as a terminating endpoint;

determining the association grade corresponding to the first association edge according to the association mode of the first association edge;

determining the highest level in the association levels corresponding to the first association edges and the number of second association edges of which the corresponding association levels are the highest levels;

determining the association strength corresponding to each second association edge according to the attribute of the second association edge, taking the highest level as the association level of the one-hop association point, taking the number of the first association edges corresponding to the highest level as the contact times of the one-hop association point, taking the maximum value in the association strengths corresponding to each second association edge as the association strength of the one-hop association point, and updating the attribute of the one-hop association point.

11. The method according to claim 10, wherein for each of the two-hop association points, updating the attribute of the two-hop association point according to the attribute of the association edge between the two-hop association point and each of the one-hop association points, the attribute of the association edge between each of the one-hop association points and each of the entity points of interest, and the updated attribute of the one-hop association point comprises:

for each two-hop association point, determining the two-hop association strength between the two-hop association point and the corresponding attention entity point according to the attribute of the association edge between the two-hop association point and each one-hop association point, the attribute of the association edge between each one-hop association point and each attention entity point and the updated attribute of the one-hop association point;

taking the maximum value of the two-hop association strength between the two-hop association point and the corresponding attention entity point as the association strength of the two-hop association point, and updating the association strength of the two-hop association point;

updating the association level of the two-hop association point to be a designated association level;

and updating the contact times of the two-hop association point to be the appointed contact times.

12. The method according to claim 11, wherein the determining the two-hop association strength between the two-hop association point and the corresponding entity point of interest according to the attribute of the association edge between the two-hop association point and each one-hop association point, the attribute of the association edge between each one-hop association point and each entity point of interest, and the updated attribute of the one-hop association point comprises:

for each corresponding attention entity point, determining a third entity point, wherein the associated hop count of the third entity point and the corresponding attention entity point is 1, and the associated hop count of the second hop associated point and the third entity point is 1;

for each third entity point, determining a third association edge between the second-hop association point and the third entity point, wherein the third association edge is an association edge which takes the third entity point as a starting endpoint and the second-hop association point as a terminating endpoint;

determining the association grade corresponding to the third association edge according to the association mode of the third association edge;

determining the correlation strength corresponding to a fourth correlation side with the highest correlation grade according to the attribute of the fourth correlation side corresponding to the third correlation side;

determining the second hop association strength corresponding to the third entity point according to the maximum value of the association strength corresponding to the fourth association edge and the updated association strength of the third entity point;

and determining the maximum value of the two-hop association strength corresponding to each third entity point as the two-hop association strength between the two-hop association point and the corresponding association entity point.

13. The method according to claim 7, wherein after the building the spatiotemporal knowledge graph according to the static association data and the dynamic behavior data of the target population, the method further comprises:

and updating the attention state of the entity points in the time-space knowledge graph according to the change information of the person to be attended.

14. The method according to any one of claims 2-13, wherein after constructing the spatiotemporal knowledge graph according to the static association data and the dynamic behavior data of the target population, the method further comprises:

acquiring newly added associated data of the target population, wherein the newly added associated data comprises static associated data and/or dynamic behavior data;

and updating the space-time knowledge map according to the newly added associated data.

15. The method according to claim 2, wherein the querying, according to the spatiotemporal knowledge graph, for an association objective whose association degree with a specified person of interest satisfies a first contact association condition comprises:

determining a one-hop association point of the entity point corresponding to the appointed concerned person in the spatio-temporal knowledge graph, wherein the one-hop association point is an entity point with the association hop number of 1 between the entity point corresponding to the appointed concerned person and the entity point;

and taking the person corresponding to the one-hop association point meeting the first contact association condition as a one-hop association target of the specified concerned person.

16. The method of claim 15, wherein determining the one-hop association point of the entity point corresponding to the designated person of interest in the spatio-temporal knowledge graph comprises:

screening the associated sides in the spatio-temporal knowledge graph according to the specified time range, and determining a fifth associated side with intersection of the contact time and the specified time range;

and determining a starting end point in the fifth associated edge as a sixth associated edge of the entity point corresponding to the specified concerned person, and determining a terminating end point of the sixth associated edge as the one-hop associated point.

17. The method according to claim 16, wherein the step of regarding the person corresponding to the one-hop association point satisfying the first contact association condition as the one-hop association target of the specified person of interest comprises:

sorting the one-hop association points according to the attributes of the one-hop association points and the association level, the contact times and the association strength;

and according to the sequencing result, the personnel corresponding to the first N-bit first-hop association points are used as the first-hop association targets of the appointed concerned personnel, wherein N is a positive integer.

18. The method of claim 16, wherein the first contact correlation condition is a correlation strength greater than a preset threshold.

19. The method according to any one of claims 15 to 18, wherein after the person corresponding to the one-hop association point satisfying the first contact association condition is taken as a one-hop association target of the specified person of interest, the method further comprises:

determining a two-hop association point of the appointed concerned person according to the one-hop association point;

and taking the person corresponding to the second-hop association point meeting the second contact association condition as a second-hop association target of the specified concerned person.

20. An apparatus for data processing, comprising:

21. An apparatus for data processing, comprising:

wherein the processor, when executing the computer program, implements the method of any of claims 1 to 19.

22. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 19.