Data processing method and device, electronic equipment and storage medium

Abstract

The invention relates to a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of computers. Based on the to-be-analyzed object indication information, obtaining to-be-analyzed object data corresponding to the to-be-analyzed object, associated object data of each associated object and inter-object associated data corresponding to each first target object pair; based on the first object collection times, the second object collection times and the inter-object association times, performing association analysis on each first target object pair to obtain object association index data corresponding to each first target object pair; and based on the object association index data corresponding to each first target object pair, performing object association analysis on the to-be-analyzed object to obtain an object association analysis result corresponding to the to-be-analyzed object. According to the embodiment of the invention, the non-linear relationship between the collection times and the association times can be comprehensively introduced to realize association analysis between the objects, and the object association analysis accuracy is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to a data processing method, apparatus, electronic device, and storage medium. Background Art

[0002] With the rapid development of technologies such as the Internet of Things, mobile Internet, big data, and artificial intelligence, real-time data processing and complex correlation analysis have become core requirements in fields such as financial risk control, intelligent manufacturing, online social networking, and health care. In traffic management and smart city construction, cameras and mobile phone collection devices deployed in key areas such as traffic checkpoints, railway stations, and school gates can collect multi-modal data such as mobile phone identifiers, face images, and license plates in real time, providing basic data support for correlation analysis between objects. Furthermore, by combining the results of correlation analysis between objects, dynamic monitoring and risk warning of objects can be achieved. Traditional correlation analysis algorithms are mostly based on co-occurrence times or simple similarity, and the accuracy of correlation analysis for the degree of association between objects is relatively low, thereby resulting in a relatively low accuracy of correlation analysis for the correlation relationship between objects. Summary of the Invention

[0003] In view of the above technical problems, the present disclosure provides a data processing method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of the embodiments of the present disclosure, a data processing method is provided. The method includes: Receiving an object correlation analysis instruction; the object correlation analysis instruction includes to-be-analyzed object indication information corresponding to a to-be-analyzed object; Based on the to-be-analyzed object indication information, obtaining to-be-analyzed object data corresponding to the to-be-analyzed object, association object data of each of a plurality of associated objects corresponding to the to-be-analyzed object, and object-to-object correlation data of each of a plurality of first target object pairs; the to-be-analyzed object data includes a first object collection count, the association object data includes a second object collection count, the object-to-object correlation data includes an object-to-object correlation count, and any one of the first target object pairs includes the to-be-analyzed object and any one of the plurality of associated objects; Performing correlation analysis on each first target object pair based on the first object collection count, the second object collection counts of the plurality of associated objects respectively corresponding thereto, and the object-to-object correlation counts of the plurality of first target object pairs respectively corresponding thereto, to obtain object correlation index data corresponding to each first target object pair; Performing object correlation analysis on the to-be-analyzed object based on the object correlation index data corresponding to each first target object pair, to obtain an object correlation analysis result corresponding to the to-be-analyzed object.

[0005] Optionally, the correlation analysis is performed on each first target object pair based on the collection times of the first object, the collection times of the second object corresponding to each of the multiple associated objects, and the object - to - object association times between each of the multiple first target object pairs, to obtain the object association index data corresponding to each first target object pair, including: Based on the object - to - object association times, perform object - to - object correlation probability analysis on each first target object pair to obtain the target association index data corresponding to each first target object pair; the target association index data is used to indicate the probability of correlation between the two objects in each first target object pair; Based on the collection times of the first object, the collection times of the second object, and the object - to - object association times, determine the correction coefficient corresponding to each first target object pair; the correction coefficient is used to enhance the difference between the object - to - object association times of different object pairs when the object - to - object association times are greater than the first preset association times; Based on the correction coefficient corresponding to each first target object pair, perform correction processing on the target association index data corresponding to each first target object pair to obtain the object association index data corresponding to each first target object pair.

[0006] Optionally, the determining the correction coefficient corresponding to each first target object pair based on the collection times of the first object, the collection times of the second object, and the object - to - object association times includes: Perform mean processing on the collection times of the first object and the collection times of the second object corresponding to the associated objects in each first target object pair to obtain the average collection times corresponding to each first target object pair; Based on the average collection times corresponding to each first target object pair and the object - to - object association times corresponding to each first target object pair, determine the correction coefficient corresponding to each first target object pair.

[0007] Optionally, the obtaining the data of the object to be analyzed, the data of the multiple associated objects corresponding to the object to be analyzed, and the object - to - object association data corresponding to each of the multiple first target object pairs based on the indication information of the object to be analyzed includes: Based on the indication information of the object to be analyzed, obtain the data of the object to be analyzed from the object data storage area; Based on the data of the object to be analyzed and the associated data storage area, determine the multiple associated objects corresponding to the object to be analyzed and the multiple first target object pairs, and obtain the object - to - object association data corresponding to each of the multiple first target object pairs; Obtain the data of the multiple associated objects corresponding to each of the multiple associated objects from the object data storage area.

[0008] Optionally, the data of the object to be analyzed includes first object identification information corresponding to the object to be analyzed; the associated data storage area stores preset associated data corresponding to any one of a plurality of preset object pairs, and the preset associated data corresponding to any one of the preset object pairs includes first relationship indication information, second relationship indication information, and the number of associations between objects corresponding to any one of the preset object pairs. Both the first relationship indication information and the second relationship indication information include the object identification information of two preset objects respectively. The object identification information of the first preset object in any one of the preset object pairs is located at the preset object query position in the first relationship indication information, and the object identification information of the second preset object in any one of the preset objects is located at the preset object query position in the second relationship indication information; Determining, based on the data of the object to be analyzed and the associated data storage area, a plurality of associated objects corresponding to the object to be analyzed and a plurality of first target object pairs, and obtaining the object - to - object association data of each of the plurality of first target object pairs, includes: Performing a matching process on the object identification information at the preset object query position in the two relationship indication information corresponding to each preset object pair and the first object identification information to obtain the plurality of first target object pairs and the object - to - object association data of each of the plurality of first target object pairs; Determining the plurality of associated objects based on the plurality of first target object pairs.

[0009] Optionally, the method further includes: When it is detected that there is a target object data pair in the plurality of currently to - be - detected object data, updating the associated data in the associated data storage area based on the target object data pair; the target object data pair is an object data pair in which the time interval between the object data collection times corresponding to any two of the plurality of currently to - be - detected object data is less than a first preset time interval.

[0010] Optionally, the plurality of currently to - be - detected object data are obtained in the following manner: Obtaining a plurality of currently collected object data; the plurality of currently collected object data are object data collected by a plurality of preset collection devices within the current time range; Determining, from the plurality of currently collected object data, a plurality of target collected object data corresponding to each preset collection device; the object feature information corresponding to the plurality of target collected object data is the same, and the maximum collection time interval corresponding to the plurality of target collected object data is less than a second preset time interval; Determine the first acquisition object data corresponding to each preset acquisition device and at least one second acquisition object data corresponding to each preset acquisition device, where the first acquisition object data is any one of the multiple target acquisition object data, and the at least one second acquisition object data is the target acquisition object data other than the first acquisition object data among the multiple target acquisition object data; Filter at least one second acquisition object data corresponding to each preset acquisition device from the multiple current acquisition object data to obtain the multiple current objects to be detected data.

[0011] Optionally, the method further includes: Filter the first target object pairs in the multiple first target object pairs whose corresponding object - to - object association times are less than the second preset association times to obtain multiple second target object pairs; The performing association analysis on each first target object pair based on the first object acquisition times, the second object acquisition times corresponding to the multiple associated objects respectively, and the object - to - object association times corresponding to the multiple first target object pairs respectively to obtain the object association index data corresponding to each first target object pair includes: Performing association analysis on each second target object pair based on the first object acquisition times, the second object acquisition times, and the object - to - object association times corresponding to the multiple second target object pairs respectively to obtain the object association index data corresponding to each second target object pair.

[0012] According to another aspect of the embodiments of the present disclosure, there is provided a data processing device, where the device includes: An instruction receiving module, configured to receive an object association analysis instruction; the object association analysis instruction includes the to - be - analyzed object indication information corresponding to the to - be - analyzed object; A first data acquisition module, configured to obtain the to - be - analyzed object data corresponding to the to - be - analyzed object, the association object data corresponding to the multiple associated objects corresponding to the to - be - analyzed object respectively, and the object - to - object association data corresponding to the multiple first target object pairs respectively based on the to - be - analyzed object indication information; the to - be - analyzed object data includes the first object acquisition times, the association object data includes the second object acquisition times, the object - to - object association data includes the object - to - object association times, and any one of the first target object pairs includes the to - be - analyzed object and any one of the multiple associated objects; A first association analysis module, configured to perform association analysis on each first target object pair based on the first object acquisition times, the second object acquisition times corresponding to the multiple associated objects respectively, and the object - to - object association times corresponding to the multiple first target object pairs respectively to obtain the object association index data corresponding to each first target object pair; A second correlation analysis module, configured to perform object correlation analysis on the object to be analyzed based on the object correlation index data corresponding to each first target object, so as to obtain an object correlation analysis result corresponding to the object to be analyzed.

[0013] According to another aspect of the embodiments of the present disclosure, there is provided an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the instructions to implement the above data processing method.

[0014] According to another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the above data processing method.

[0015] According to another aspect of the embodiments of the present disclosure, there is provided a computer program product containing instructions, when it runs on a computer, enabling the computer to execute the above data processing method.

[0016] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects: By receiving an object correlation analysis instruction, the object correlation analysis instruction includes object indication information corresponding to the object to be analyzed. Based on the object indication information corresponding to the object to be analyzed, object data corresponding to the object to be analyzed, association object data of each of the multiple associated objects corresponding to the object to be analyzed, and object - to - object association data of each of the multiple first target object pairs are obtained. The object data includes the first object collection times, the association object data includes the second object collection times, the object - to - object association data includes the object - to - object association times, and any one of the first target object pairs includes the object to be analyzed and any one of the multiple associated objects. When receiving the object correlation analysis instruction, relevant object data and object - to - object association data can be obtained for the object to be analyzed. Then, in combination with the first object collection times, the second object collection times corresponding to each of the multiple associated objects, and the object - to - object association times corresponding to each of the multiple first target object pairs, correlation analysis is performed on each first target object pair to obtain object correlation index data corresponding to each first target object pair. The non - linear relationship between the collection times and the association times can be comprehensively introduced to implement object - to - object correlation analysis, avoiding interference from high - frequency objects, thereby improving the accuracy of object - to - object correlation analysis. Then, in combination with the object correlation index data corresponding to each first target object pair, object correlation analysis is performed on the object to be analyzed to obtain an object correlation analysis result corresponding to the object to be analyzed, which can improve the accuracy of object correlation analysis.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0018] The accompanying drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with this disclosure, and are used together with the description to explain the principles of this disclosure, and do not constitute an improper limitation of this disclosure.

[0019] Figure 1 is a schematic diagram of an application system shown according to an exemplary embodiment; Figure 2 is a flowchart of a data processing method shown according to an exemplary embodiment; Figure 3 is a block diagram of a data processing device shown according to an exemplary embodiment; Figure 4 is a block diagram of an electronic device for performing object association analysis on an object to be analyzed shown according to an exemplary embodiment; Figure 5 is a block diagram of another electronic device for performing object association analysis on an object to be analyzed shown according to an exemplary embodiment. Detailed Embodiments

[0020] Various exemplary embodiments, features, and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0021] The special word "exemplary" here means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" here does not have to be construed as superior or better than other embodiments.

[0022] In addition, for a better description of the present application, numerous specific details are given in the following detailed embodiments. Those skilled in the art should understand that the present application can also be implemented without some specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art are not described in detail so as to highlight the gist of the present application.

[0023] Please refer to Figure 1 , Figure 1 is a schematic diagram of an application system shown according to an exemplary embodiment. The application system can be used for the data processing method of the present application. The application system can at least include a server 01 and a terminal 02.

[0024] In the embodiments of the present application, the server 01 can be used to perform object association analysis on the object to be analyzed. Specifically, the above-mentioned server 01 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0025] In the embodiments of the present application, the terminal 02 can be used to generate an object association analysis instruction. The above-mentioned terminal 02 can include entity devices of types such as smart phones, desktop computers, tablet computers, laptop computers, smart speakers, vehicle-mounted terminals, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices, or can also include software running on the entity devices, such as application programs, etc. In the embodiments of the present application, the operating system running on the above-mentioned terminal 02 can include but is not limited to Android system, GNU / Linux system, Windows system, etc.

[0026] In addition, it should be noted that Figure 1 The application environment shown is only one provided by the present disclosure. In actual applications, other application environments can also be included. For example, the process of performing object association analysis on the object to be analyzed can also be implemented on the terminal 02.

[0027] In the embodiments of this specification, the above-mentioned terminal 02 and server 01 can be directly or indirectly connected through wired or wireless communication methods, and the present application does not make any limitations in this regard.

[0028] It should be noted that this specification provides method operation steps such as in embodiments or flowcharts, but based on routine or non-creative labor, more or fewer operation steps can be included. The step sequence listed in the embodiments is only one way among the execution sequences of numerous steps and does not represent the only execution sequence.

[0029] Specifically, Figure 2 is a flowchart of a data processing method shown according to an exemplary embodiment. As Figure 2 shown, this data processing method can be used in electronic devices such as terminals or servers, and specifically can include the following steps: S201: Receive an object association analysis instruction.

[0030] In a specific embodiment, the object association analysis instruction can be used to indicate to perform object association analysis on the object to be analyzed. The object association analysis instruction can include the object-to-be-analyzed indication information corresponding to the object to be analyzed. Among them, the object to be analyzed can refer to an object for which it is currently necessary to analyze the association with other associated objects. The object-to-be-analyzed indication information can be used to indicate the object to be analyzed. Specifically, the object to be analyzed can include a living being (such as a person), a mobile terminal, or a license plate, etc.; correspondingly, the object-to-be-analyzed indication information can include biometric image information, mobile user identification information, or license plate information, etc. The biometric image information can include face image data or face image feature information. The license plate information can include the license plate number. The mobile user identification information can be used to identify the user identity in the cellular network. The mobile user identification information can be stored in a SIM (Subscriber Identity Module) card. It can be understood that each SIM card corresponds to a unique mobile user identification information; in the case where any mobile terminal includes multiple SIM cards, any of the above mobile terminals can correspond to the mobile user identification information respectively corresponding to the above multiple SIM cards.

[0031] In a specific embodiment, the object analysis requester can perform an indication information input operation for the object to be analyzed on the target terminal, so that the target terminal obtains the object-to-be-analyzed indication information; correspondingly, based on the target terminal obtaining the object-to-be-analyzed indication information, the object analysis requester can perform an instruction generation operation on the target terminal, so that the target terminal generates an object association analysis instruction carrying the object-to-be-analyzed indication information. In this embodiment, taking the above data processing method applied to the target server as an example, the target terminal can send the above object association analysis instruction to the target server.

[0032] S203: Based on the object-to-be-analyzed indication information, obtain the object-to-be-analyzed data corresponding to the object to be analyzed, the association object data of each of the multiple associated objects corresponding to the object to be analyzed, and the object-to-object association data corresponding to each of the multiple first target object pairs.

[0033] In a specific embodiment, the data of the object to be analyzed can be used to characterize the features of the object to be analyzed. The data of the object to be analyzed can include the first object collection times. Further, the data of the object to be analyzed can also include the type indication information of the object type of the object to be analyzed or the object identification information of the object to be analyzed, etc. Among them, the first object collection times can refer to the object collection times of the object to be analyzed. The object collection times can refer to the cumulative times collected by the target system. The target system can include multiple groups of preset collection devices, and each group of preset collection devices can include preset collection devices corresponding to multiple different object types; it can be that a group of preset collection devices is set at each preset collection location among multiple preset collection locations. The object type can include biometric image type, mobile user identification type or license plate information type. The above object identification information can include biometric image information, mobile user identification information or license plate information, etc. Exemplarily, taking the object type of the object to be analyzed as the mobile user identification type as an example, the type indication information of the object to be analyzed can be "IMSI", the mobile user identification information of the object to be analyzed can be "46011XXXXXXX814", and the object identification information of the object to be analyzed can be "IMSI-46011XXXXXXX814". Further, assuming that object A has appeared 2 times at preset collection location 1, object A has appeared 3 times at preset collection location 2, and has not appeared at other preset collection locations, it can be determined that the object collection times corresponding to the above object A is 5.

[0034] In a specific embodiment, the associated object can refer to an object that has an association with the object to be analyzed. Specifically, the associated object can be an object that appears at the same location as the object to be analyzed within the first preset time interval. Exemplarily, object 1 can appear at location A at time T1, object 1 carries a mobile terminal 1 with mobile user identification information "XXX", object 2 can appear at location A at time T2, where location A can be a location where multiple different types of preset collection devices are set, and the face image 1 of object 1 and the face image 2 of object 2 can be collected, and the mobile user identification information "XXX" can be collected at time T3. The time interval between any two of T1, T2 and T3 is less than the above first preset time interval. Accordingly, it can be determined that there is an association between the face image 1 of the above object 1, the face image 2 of the above object 2 and the mobile user identification information "XXX"; assuming that the object to be analyzed is the face image 1 of object 1, it can be determined that the associated objects of the above object to be analyzed include the face image 2 of object 2 and the mobile user identification information "XXX". Specifically, the first preset time interval can be set according to actual application needs, and the present disclosure does not make a limitation.

[0035] In a specific embodiment, the associated object data of any associated object can be used to characterize the features of any of the above-mentioned associated objects. The associated object data of any associated object may include the second object collection times of any of the above-mentioned associated objects. The second object collection times may refer to the object collection times of any of the above-mentioned associated objects. The object collection times may refer to the cumulative times collected by the target system.

[0036] In a specific embodiment, the associated object data of any associated object may further include type indication information of the object type of any of the above-mentioned associated objects, object identification information of any of the above-mentioned associated objects, etc.

[0037] In a specific embodiment, any first target object pair may include an object to be analyzed and any one of a plurality of associated objects. Exemplarily, assuming that the plurality of associated objects are associated object A, associated object B, and associated object C, it can be determined that the plurality of first target object pairs can be [object to be analyzed, associated object A], [object to be analyzed, associated object B], and [object to be analyzed, associated object C].

[0038] In a specific embodiment, the inter-object association data corresponding to any first target object pair may include the inter-object association times of any first target object pair. Among them, the inter-object association times may refer to the cumulative times that the corresponding two objects are collected by the target acquisition device within the first preset time interval. Exemplarily, assuming that the number of times object A and object B appear at the preset acquisition position A within the first preset time interval is 3, and the number of times object A and object B appear at the preset acquisition position B within the first preset time interval is 5, and the above two objects A and B do not appear at other preset acquisition positions within the first preset time interval, it can be determined that the inter-object association times of the target object pair (including object A and object B) are 8.

[0039] In a specific embodiment, the above-mentioned obtaining the data of the object to be analyzed corresponding to the object to be analyzed, the associated object data of each of the multiple associated objects corresponding to the object to be analyzed, and the inter-object association data corresponding to each of the multiple first target object pairs based on the indication information of the object to be analyzed may include: Based on the indication information of the object to be analyzed, obtain the data of the object to be analyzed from the object data storage area; Based on the data of the object to be analyzed and the associated data storage area, determine the multiple associated objects and multiple first target object pairs corresponding to the object to be analyzed, and obtain the inter-object association data of each of the multiple first target object pairs; Obtain the associated object data of each of the multiple associated objects from the object data storage area.

[0040] In a specific embodiment, the object data storage area can be used to store the object data of multiple preset objects respectively. The object data of multiple preset objects can be stored in the object data storage area in the form of a table.

[0041] In a specific embodiment, the object data to be analyzed can include first object identification information; the first object identification information can refer to the object identification information of the object to be analyzed.

[0042] In a specific embodiment, matching processing can be performed on the object identification information in the object data of each preset object in the object data storage area and the object indication information to be analyzed; in the case where it is matched that the object identification information in the object data of any one of the preset objects matches the object indication information to be analyzed, the object data of any one of the preset objects can be used as the object data to be analyzed.

[0043] In a specific embodiment, the associated data storage area can be used to store the preset associated data corresponding to each preset object pair in multiple preset object pairs. Specifically, the associated data storage area stores the preset associated data corresponding to any one of the multiple preset object pairs, and the associated data storage area can store the preset associated data corresponding to each preset object pair in the form of a table.

[0044] In a specific embodiment, the preset associated data corresponding to any one of the preset object pairs can include first relationship indication information, second relationship indication information, and the number of object - to - object associations corresponding to any one of the preset object pairs. Among them, both the first relationship indication information and the second relationship indication information can include the object identification information of two preset objects respectively. The object identification information of the first preset object in any one of the preset object pairs can be located at the preset object query position in the first relationship indication information. The object identification information of the second preset object in any one of the preset objects can be located at the preset object query position in the second relationship indication information. The preset object query position can be the left - prefix position in the relationship indication information. Exemplarily, assuming that the preset object pair includes preset object A (i.e., the corresponding object identification information is "A") and preset object B (i.e., the corresponding object identification information is "B"), correspondingly, the first relationship indication information can be "AB", and the second relationship indication information can be "BA", where the preset object query position is the left - prefix position in the relationship indication information.

[0045] In a specific embodiment, determining multiple associated objects and multiple first target object pairs corresponding to the object to be analyzed based on the object data to be analyzed and the associated data storage area, and obtaining the object - to - object associated data of each of the multiple first target object pairs can include: Perform matching processing on the object identification information at the preset object query position and the first object identification information in the two relationship indication information corresponding to each preset object pair, to obtain multiple first target object pairs and the inter-object association data of each of the multiple first target object pairs; Based on the multiple first target object pairs, determine multiple associated objects.

[0046] In a specific embodiment, for each preset thread among the multiple preset threads, matching processing may be performed on the object identification information at the preset object query position and the first object identification information in the two relationship indication information corresponding to each preset object pair; in the case where it is matched that there is object identification information at the preset object query position in the two relationship indication information of any one of the preset object pairs, the above-mentioned any one of the preset object pairs may be used as the first target object pair, and the preset association data of the above-mentioned any one of the preset object pairs may be used as the inter-object association data of the above-mentioned first target object pair. Correspondingly, multiple first target object pairs and the inter-object association data of each of the multiple first target object pairs can be obtained.

[0047] In a specific embodiment, the objects other than the object to be analyzed in the above-mentioned first target object pairs may be used as the above-mentioned multiple associated objects.

[0048] In the above embodiment, by storing two association indication information in the association data storage area, and performing matching processing on the object identification information at the preset object query position and the first object identification information in the two relationship indication information corresponding to each preset object pair, multiple first target object pairs and the inter-object association data of each of the multiple first target object pairs are obtained, which can avoid global scanning and matching, improve the matching efficiency, and thus improve the object association analysis efficiency.

[0049] In a specific embodiment, in the object data storage area, the object data of each associated object may be searched. Correspondingly, the object data of the multiple associated objects found may be used as the respective associated object data of the above-mentioned multiple associated objects.

[0050] In the above embodiments, by storing object data and associated data in an object data storage area and an associated data storage area respectively, based on the object indication information to be analyzed, the object data to be analyzed is obtained from the object data storage area. Based on the object data to be analyzed and the associated data storage area, multiple associated objects and multiple first target object pairs corresponding to the object to be analyzed are determined, and the inter-object associated data of each of the multiple first target object pairs is obtained. The associated object data of each of the multiple associated objects is obtained from the object data storage area, which can balance write throughput and query efficiency, support efficient update of real-time collected data, improve the accuracy of inter-object association analysis by updating dynamic information in a timely manner, and further improve the efficiency and accuracy of object association analysis.

[0051] In a specific embodiment, when multiple current objects to be detected data are detected, the object data in the object data storage area can be updated based on each current object to be detected data. Specifically, when the object data of a preset object corresponding to any current object to be detected data is stored in the object data storage area, the object collection times in the above object data can be updated; when the object data of the preset object corresponding to any current object to be detected data is not stored in the object data storage area, the above current object to be detected data can be added, and the collection times in the object data are set to 1. Further, when the object data of a preset object corresponding to any current object to be detected data is stored in the object data storage area, by sending a collection times update instruction for the preset object corresponding to any current object to be detected data to the target server, when the target server receives the above collection times update instruction, for the object collection times in the object data of the preset object corresponding to any current object to be detected data, add 1 to the current object collection times. Or, when there are multiple preset object data corresponding to the current objects to be detected data that need to be updated, by sending a batch times update instruction for the preset objects corresponding to the multiple current objects to be detected data to the target server, when the target server receives the above batch times update instruction, add 1 to the current object collection times in the object data of the preset objects corresponding to the multiple current objects to be detected data.

[0052] In the above embodiments, by sending a collection times update instruction to the target server to perform an increment update of the object collection times, the number of data interactions can be reduced, the data update and maintenance efficiency can be improved, the dynamic real-time nature of the object data can be realized, and further, by improving the update timeliness of the object data, the accuracy of the object association analysis can be improved.

[0053] In a specific embodiment, the above method may further include: In the case that target object data pairs are present in multiple currently to-be-detected object data, update the associated data in the associated data storage area based on the target object data pairs.

[0054] In a specific embodiment, the target object data pairs can be object data pairs in which the time interval between the respective object data acquisition times of any two of the multiple currently to-be-detected object data is less than a first preset time interval. Herein, the first preset time interval can be set according to actual application requirements, and the present disclosure does not make any limitation. Exemplarily, the first preset time interval can be 5 min.

[0055] In a specific embodiment, a sliding window with a corresponding time length can be set based on the first preset time interval; correspondingly, multiple currently to-be-detected object data can be detected based on the sliding window; in the case that target object data pairs present in the multiple currently to-be-detected object data belong to the sliding window, update the associated data in the associated data storage area based on the target object data pairs.

[0056] In a specific embodiment, in the case that target object data pairs are present in the multiple currently to-be-detected object data, check whether there is associated data corresponding to the above target object data pairs in the associated data storage area. In the case that there is no corresponding associated data in the associated data storage area, generate the associated data corresponding to the above target object data pairs; in the case that there is corresponding associated data in the associated data storage area, increment by 1 the number of object-to-object associations in the associated data corresponding to the above target object data pairs.

[0057] In a specific embodiment, an association count update instruction or a batch count update instruction for the number of object-to-object associations in the associated data can be sent to the target server, so that the target server increments the number of object-to-object associations corresponding to the target object data pairs in the associated data storage area. Specifically, for the specific increment process of the number of object-to-object associations, reference can be made to the above specific increment process of the object acquisition count, and the present disclosure will not elaborate further.

[0058] In a specific embodiment, the above multiple currently to-be-detected object data can be obtained in the following manner: Obtain multiple currently acquired object data; From the multiple currently acquired object data, determine multiple target acquired object data corresponding to each preset acquisition device; Determine the first acquired object data corresponding to each preset acquisition device and at least one second acquired object data corresponding to each preset acquisition device; Filter at least one second acquisition object data corresponding to each preset acquisition device among multiple current acquisition object data to obtain multiple current objects to be detected data.

[0059] In a specific embodiment, the multiple current acquisition object data may be object data acquired by each of multiple preset acquisition devices within a current time range. Among them, the duration corresponding to the current time range may be greater than the duration corresponding to a first preset time interval.

[0060] In a specific embodiment, a set of preset acquisition devices may be set at each preset acquisition position, and object data of different object types may be acquired by multiple preset acquisition devices of different object types in each set of preset acquisition devices.

[0061] In a specific embodiment, the object feature information corresponding to multiple target acquisition object data is the same, and the maximum acquisition time interval corresponding to the multiple target acquisition object data is less than a second preset time interval. Specifically, the second preset time interval may be less than or equal to the above-mentioned first preset time interval. The second preset time interval may be set according to actual application needs, and the present disclosure does not make a limitation. Exemplarily, the second preset time interval may be 1 min.

[0062] In a specific embodiment, the multiple target acquisition object data corresponding to any one preset acquisition device may refer to multiple current acquisition object data with the same object feature information acquired by any one of the above-mentioned preset acquisition devices.

[0063] In a specific embodiment, the first acquisition object data may be any one of the multiple target acquisition object data. At least one second acquisition object data may be the target acquisition object data other than the first acquisition object data among the multiple target acquisition object data.

[0064] In the above embodiment, by obtaining multiple current acquisition object data, determining multiple target acquisition object data corresponding to each preset acquisition device from the multiple current acquisition object data, determining the first acquisition object data corresponding to each preset acquisition device and at least one second acquisition object data corresponding to each preset acquisition device, and filtering at least one second acquisition object data corresponding to each preset acquisition device among the multiple current acquisition object data to obtain multiple current objects to be detected data, it is possible to achieve deduplication of the current acquisition object data acquired by each preset acquisition device, avoid inaccurate acquisition times or association times caused by the high-frequency acquisition device acquiring the same object multiple times due to different acquisition frequencies of different acquisition devices, thereby improving the accuracy of the data stored in the object data storage area and the associated data storage area, and further improving the accuracy of subsequent object association analysis.

[0065] S205: Based on the collection times of the first object, the collection times of the second object corresponding to each of the multiple associated objects, and the association times between objects corresponding to each of the multiple first target object pairs, perform association analysis on each first target object pair to obtain the object association index data corresponding to each first target object pair.

[0066] In a specific embodiment, the object association index data corresponding to any first target object pair can be used to characterize the degree of association between the two objects in any of the above first target object pairs.

[0067] In a specific embodiment, the above-mentioned performing association analysis on each first target object pair based on the collection times of the first object, the collection times of the second object corresponding to each of the multiple associated objects, and the association times between objects corresponding to each of the multiple first target object pairs to obtain the object association index data corresponding to each first target object pair may include: Based on the association times between objects, perform object correlation probability analysis on each first target object pair to obtain the target association index data corresponding to each first target object pair; Based on the collection times of the first object, the collection times of the second object, and the association times between objects, determine the correction coefficient corresponding to each first target object pair; Based on the correction coefficient corresponding to each first target object pair, perform correction processing on the target association index data corresponding to each first target object pair to obtain the object association index data corresponding to each first target object pair.

[0068] In a specific embodiment, the target association index data can be used to indicate the probability that there is a correlation between the two objects in each first target object pair.

[0069] In a specific embodiment, the target association index data corresponding to any of the above first target object pairs can be obtained through the following formula:

[0070] Where P is the target association index data corresponding to any first target object pair; cc is the association times between objects corresponding to any first target object pair.

[0071] It can be understood that by assuming that the prior correlation probability of any two objects meeting is P0 = 0.2 and the non - correlation probability is 1 - P0 = 0.8, correspondingly, the calculation formula for the above target association index data can be determined as: .

[0072] In a specific embodiment, the above correction coefficient can be used to enhance the difference between the association times between objects of different object pairs when the association times between objects are greater than the first preset association times.

[0073] In a specific embodiment, determining the correction coefficient corresponding to each first target object pair based on the collection times of the first object, the collection times of the second object, and the association times between objects may include: Performing an averaging process on the collection times of the first object and the collection times of the associated objects corresponding to each first target object pair to obtain the average collection times corresponding to each first target object pair; Based on the average collection times corresponding to each first target object pair and the association times between objects corresponding to each first target object pair, determining the correction coefficient corresponding to each first target object pair.

[0074] In a specific embodiment, the average collection times corresponding to any first target object pair can be used to characterize the average trend of the object collection times of the two objects in any first target object pair.

[0075] In a specific embodiment, the average collection times corresponding to each first target object pair can be obtained by performing a geometric averaging process on the collection times of the first object and the collection times of the associated objects corresponding to each first target object pair.

[0076] In a specific embodiment, the average collection times corresponding to each first target object pair can be obtained by performing an arithmetic averaging process on the collection times of the first object and the collection times of the associated objects corresponding to each first target object pair.

[0077] In a specific embodiment, the correction coefficient corresponding to any first target object pair can be obtained through the following formula:

[0078] Wherein, K is the correction coefficient corresponding to any first target object pair; cc is the association times between objects corresponding to any first target object pair; SC1 and SC2 are respectively the object collection times corresponding to the two objects in any first target object pair; α is a preset parameter. Exemplarily, α can be 0.2.

[0079] In a specific embodiment, the object association index data corresponding to any first target object pair can be obtained through the following formula:

[0080] Wherein, prob is the object association index data corresponding to any first target object pair; K is the correction coefficient corresponding to any first target object pair as described above; P is the target association index data corresponding to any first target object pair.

[0081] In the above embodiments, by combining the number of times of association between objects, the correlation probability analysis between objects is performed on each first target object pair, and the target association index data corresponding to each first target object pair is obtained, so as to realize the correlation probability prediction of each first target object pair. Then, by combining the number of times of collection of the first object, the number of times of collection of the second object, and the number of times of association between objects, the correction coefficient corresponding to each first target object pair is determined. Based on the correction coefficient corresponding to each first target object pair, the target association index data corresponding to each first target object pair is corrected to obtain the object association index data corresponding to each first target object pair, which can effectively suppress the excessive increase in the degree of association caused by a high number of collections, and suppress the divergence of the number of associations when it is relatively high. It can enhance the difference in the degree of association under a relatively high number of associations between objects through exponential smoothing, so that the object association index data is more in line with the real scenario and improves the accuracy of the object association index data.

[0082] In a specific embodiment, the above method may further include: Filter out the first target object pairs in the multiple first target object pairs whose corresponding number of times of association between objects is less than the second preset association number to obtain multiple second target object pairs; Correspondingly, the above-mentioned association analysis is performed on each first target object pair based on the number of times of collection of the first object, the number of times of collection of the second object corresponding to each of the multiple associated objects, and the number of times of association between objects corresponding to each of the multiple first target object pairs, to obtain the object association index data corresponding to each first target object pair, which may include: Based on the number of times of collection of the first object, the number of times of collection of the second object, and the number of times of association between objects corresponding to each of the multiple second target object pairs, perform association analysis on each second target object pair to obtain the object association index data corresponding to each second target object pair.

[0083] In a specific embodiment, the second preset association number can be set according to actual application needs, and the present disclosure does not make any limitation.

[0084] In a specific embodiment, it may be based on the number of times of collection of the first object, the number of times of collection of the second object, and the number of times of association between objects to perform association analysis on the filtered target object pairs to obtain the object association index data corresponding to each of the filtered target object pairs; correspondingly, based on the object association index data corresponding to each of the filtered target object pairs, perform object association analysis on the object to be analyzed to obtain the object association analysis result corresponding to the object to be analyzed.

[0085] In the above embodiment, when the number of times of association between the corresponding objects in any first target object pair is less than the second preset number of times of association, it can be determined that the degree of association between the two objects in any first target object pair is relatively low. In the subsequent object association analysis of the object to be analyzed, it is necessary to analyze the specific types of association relationships to which each object belongs. For the first target object pairs with a relatively low degree of association, they may not belong to any type of association relationship. By filtering the first target object pairs with a relatively low degree of association, the system operation amount can be reduced, and the overall object association analysis efficiency of the system can be improved.

[0086] In a specific embodiment, it can be through multiple preset threads, in combination with the first object collection times, the second object collection times respectively corresponding to multiple associated objects, and the object association times respectively corresponding to multiple first target object pairs, to perform association analysis on each first target object pair, and obtain the object association index data corresponding to each first target object pair, which can improve the association analysis efficiency of multiple first target object pairs.

[0087] In the above embodiment, by sinking the process of the association analysis of each first target object pair to the application layer, and the query layer is only responsible for data query, the computing burden on the database can be reduced, and the scalability and stability of the system can be improved.

[0088] S207: Based on the object association index data corresponding to each first target object pair, perform object association analysis on the object to be analyzed, and obtain the object association analysis result corresponding to the object to be analyzed.

[0089] In a specific embodiment, the object association analysis result corresponding to the object to be analyzed can be used to indicate the association relationship between the object to be analyzed and multiple associated objects. Specifically, the object association analysis result corresponding to the object to be analyzed can include the object identification information of the associated objects having an association relationship with the object to be analyzed, and the association relationship indication information of each first target object pair.

[0090] In a specific embodiment, the association relationship indication information of each first target object pair can be generated based on the object association indicator data corresponding to each first target object pair. Among them, the association relationship indication information of any first target object pair can be used to indicate the association relationship between two objects in any first target object pair. The association relationship indication information may include relationship type indication information corresponding to any preset association relationship type. Specifically, the preset association relationship type may include an accompanying relationship type, a same-device relationship type, or a belonging relationship type, etc. Among them, the accompanying relationship type can be used to indicate that the corresponding two objects are two people who may have a relationship (such as relatives, friends, or colleagues). The same-device relationship type can be used to indicate that the corresponding two objects are two SIM cards that may belong to the same mobile terminal. The belonging relationship type can be used to indicate that the corresponding two objects belong to the same person or that one of the objects (such as a license plate or a SIM card) belongs to another object (for example, it can be a person).

[0091] In a specific embodiment, multiple different object association indicator ranges can be preset; the object association indicator data corresponding to each first target object pair can be matched with each of the above-preset object association indicator ranges to obtain a range matching result; accordingly, the range matching result corresponding to any first target object pair and the object types of the two objects in any first target object pair can be combined to determine the target association relationship type corresponding to any first target object pair; accordingly, the object association analysis result corresponding to the object to be analyzed can be generated based on the association relationship indication information corresponding to the target association relationship type.

[0092] In a specific embodiment, the object association analysis result corresponding to the object to be analyzed may include association relationship indication information of multiple third target object pairs. The multiple third target object pairs may refer to a preset number of first target object pairs whose corresponding object association indicator data are arranged in descending order among multiple first target object pairs.

[0093] In the above embodiments, by receiving an object association analysis instruction, the object association analysis instruction includes the to-be-analyzed object indication information corresponding to the to-be-analyzed object. Based on the to-be-analyzed object indication information, the to-be-analyzed object data corresponding to the to-be-analyzed object, the association object data of each of the multiple association objects corresponding to the to-be-analyzed object, and the object-to-object association data of each of the multiple first target object pairs are obtained. The to-be-analyzed object data includes the first object collection times, the association object data includes the second object collection times, the object-to-object association data includes the object-to-object association times, and any one of the first target object pairs includes the to-be-analyzed object and any one of the multiple association objects. When receiving the object association analysis instruction, relevant object data and object-to-object association data can be obtained for the to-be-analyzed object. Then, by combining the first object collection times, the second object collection times corresponding to each of the multiple association objects, and the object-to-object association times corresponding to each of the multiple first target object pairs, association analysis is performed on each first target object pair to obtain the object association index data corresponding to each first target object pair. The non-linear relationship between the collection times and the association times can be comprehensively introduced to implement object-to-object association analysis, avoid interference from high-frequency objects, and improve the accuracy of object-to-object association analysis. Then, by combining the object association index data corresponding to each first target object pair, object association analysis is performed on the to-be-analyzed object to obtain the object association analysis result corresponding to the to-be-analyzed object, which can improve the accuracy of object association analysis.

[0094] Figure 3 is a block diagram of a data processing device shown according to an exemplary embodiment. Specifically, as Figure 3 shown, the device may include: An instruction receiving module 310, which can be used to receive an object association analysis instruction; the object association analysis instruction includes the to-be-analyzed object indication information corresponding to the to-be-analyzed object; A first data acquisition module 320, which can be used to obtain the to-be-analyzed object data corresponding to the to-be-analyzed object, the association object data of each of the multiple association objects corresponding to the to-be-analyzed object, and the object-to-object association data of each of the multiple first target object pairs based on the to-be-analyzed object indication information; the to-be-analyzed object data includes the first object collection times, the association object data includes the second object collection times, the object-to-object association data includes the object-to-object association times, and any one of the first target object pairs includes the to-be-analyzed object and any one of the multiple association objects; A first association analysis module 330, which can be used to perform association analysis on each first target object pair based on the first object collection times, the second object collection times corresponding to each of the multiple association objects, and the object-to-object association times corresponding to each of the multiple first target object pairs to obtain the object association index data corresponding to each first target object pair; The second correlation analysis module 340 can be used to perform object correlation analysis on the object to be analyzed based on the object correlation index data corresponding to each first target object pair, and obtain the object correlation analysis result corresponding to the object to be analyzed.

[0095] In a specific embodiment, the above-mentioned first correlation analysis module 330 may include: The correlation probability analysis module can be used to perform object - to - object correlation probability analysis on each first target object pair based on the number of associations between objects, and obtain the target correlation index data corresponding to each first target object pair; the target correlation index data is used to indicate the probability of correlation between the two objects in each first target object pair; The correction coefficient determination module can be used to determine the correction coefficient corresponding to each first target object pair based on the first object collection times, the second object collection times, and the number of associations between objects; the correction coefficient is used to enhance the difference between the number of associations between different object pairs when the number of associations between objects is greater than the first preset number of associations; The correction processing module can be used to perform correction processing on the target correlation index data corresponding to each first target object pair based on the correction coefficient corresponding to each first target object pair, and obtain the object correlation index data corresponding to each first target object pair.

[0096] In a specific embodiment, the above - mentioned correction coefficient determination module may include: The mean processing module can be used to perform mean processing on the first object collection times and the second object collection times corresponding to the associated objects in each first target object pair, and obtain the average collection times corresponding to each first target object pair; The correction coefficient generation module can be used to determine the correction coefficient corresponding to each first target object pair based on the average collection times corresponding to each first target object pair and the number of associations between objects corresponding to each first target object pair.

[0097] In a specific embodiment, the above - mentioned first data acquisition module 320 may include: The second data acquisition module can be used to obtain the data of the object to be analyzed from the object data storage area based on the object - to - be - analyzed indication information; The third data acquisition module can be used to determine multiple associated objects and multiple first target object pairs corresponding to the object to be analyzed based on the data of the object to be analyzed and the associated data storage area, and obtain the object - to - object association data of each of the multiple first target object pairs; The fourth data acquisition module can be used to obtain the associated object data of each of the multiple associated objects from the object data storage area.

[0098] In a specific embodiment, the above-mentioned third data acquisition module may include: A matching processing module, which can be used to perform matching processing on the object identification information at the query position of the preset object and the first object identification information in the two relationship indication information corresponding to each preset object pair, so as to obtain a plurality of first target object pairs and the inter-object association data of each of the plurality of first target object pairs; An associated object determination module, which can be used to determine a plurality of associated objects based on the plurality of first target object pairs.

[0099] In a specific embodiment, the above-mentioned device may further include: A data update module, which can be used to update the association data in the association data storage area based on the target object data pair when it is detected that there is a target object data pair in the plurality of currently to-be-detected object data; the target object data pair is an object data pair in which the time interval between the respective object data acquisition times of any two of the plurality of currently to-be-detected object data is less than the first preset time interval.

[0100] In a specific embodiment, the above-mentioned device may further include: A fifth data acquisition module, which can be used to acquire a plurality of currently acquired object data; the plurality of currently acquired object data are object data respectively acquired by a plurality of preset acquisition devices within the current time range; A first data determination module, which can be used to determine, from the plurality of currently acquired object data, a plurality of target acquisition object data corresponding to each preset acquisition device; the object feature information corresponding to the plurality of target acquisition object data is the same, and the maximum acquisition time interval corresponding to the plurality of target acquisition object data is less than the second preset time interval; A second data determination module, which can be used to determine the first acquisition object data corresponding to each preset acquisition device and at least one second acquisition object data corresponding to each preset acquisition device, the first acquisition object data is any one of the plurality of target acquisition object data, and the at least one second acquisition object data is the target acquisition object data other than the first acquisition object data among the plurality of target acquisition object data; A data filtering module, which can be used to filter at least one second acquisition object data corresponding to each preset acquisition device in the plurality of currently acquired object data to obtain a plurality of currently to-be-detected object data.

[0101] In a specific embodiment, the above-mentioned device may further include: An object pair filtering module, which can be used to filter the first target object pairs in the plurality of first target object pairs in which the inter-object association times are less than the second preset association times to obtain a plurality of second target object pairs; Correspondingly, the above-mentioned first association analysis module 330 may include: The third correlation analysis module can be used to perform correlation analysis on each pair of second target objects based on the collection times of the first object, the collection times of the second object, and the inter-object correlation times corresponding to multiple second target objects, so as to obtain the object correlation index data corresponding to each pair of second target objects.

[0102] Regarding the device in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0103] Figure 4 is a block diagram of an electronic device for performing object correlation analysis on an object to be analyzed according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as Figure 4 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data processing method is implemented.

[0104] Figure 5 is a block diagram of another electronic device for performing object correlation analysis on an object to be analyzed according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as Figure 5 shown. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data processing method is implemented. The display screen of the electronic device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the electronic device, or an external keyboard, touchpad, or mouse, etc.

[0105] Those skilled in the art can understand, Figure 4 or Figure 5The structure shown is only a block diagram of some structures related to the present disclosure, and does not constitute a limitation on the electronic device to which the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have a different component arrangement.

[0106] In an exemplary embodiment, an electronic device is further provided, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the instructions to implement the data processing method as in the embodiments of the present disclosure.

[0107] In an exemplary embodiment, a computer-readable storage medium is further provided. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the data processing method in the embodiments of the present disclosure.

[0108] In an exemplary embodiment, a computer program product containing instructions is further provided. When it runs on a computer, the computer is enabled to execute the data processing method in the embodiments of the present disclosure.

[0109] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memories may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] Other embodiments of the present disclosure will be readily apparent to those skilled in the art in view of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered illustrative only, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0111] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A data processing method, characterized in that, The method includes: Receiving an object association analysis instruction; the object association analysis instruction includes the to-be-analyzed object indication information corresponding to the to-be-analyzed object; Based on the to-be-analyzed object indication information, obtaining the to-be-analyzed object data corresponding to the to-be-analyzed object, the association object data of each of the multiple association objects corresponding to the to-be-analyzed object, and the object-to-object association data corresponding to each of the multiple first target object pairs; the to-be-analyzed object data includes the first object collection times, the association object data includes the second object collection times, the object-to-object association data includes the object-to-object association times, and any first target object pair includes the to-be-analyzed object and any one of the multiple association objects; Based on the first object collection times, the second object collection times of each of the multiple association objects, and the object-to-object association times of each of the multiple first target object pairs, performing association analysis on each first target object pair to obtain the object association index data corresponding to each first target object pair; Based on the object association index data corresponding to each first target object pair, performing object association analysis on the to-be-analyzed object to obtain the object association analysis result corresponding to the to-be-analyzed object.

2. The method according to claim 1, characterized in that, The performing association analysis on each first target object pair based on the first object collection times, the second object collection times of each of the multiple association objects, and the object-to-object association times of each of the multiple first target object pairs to obtain the object association index data corresponding to each first target object pair includes: Based on the object-to-object association times, performing object-to-object correlation probability analysis on each first target object pair to obtain the target association index data corresponding to each first target object pair; the target association index data is used to indicate the probability of correlation between the two objects in each first target object pair; Based on the first object collection times, the second object collection times, and the object-to-object association times, determining the correction coefficient corresponding to each first target object pair; the correction coefficient is used to enhance the difference between the object-to-object association times of different object pairs when the object-to-object association times are greater than the first preset association times; Based on the correction coefficient corresponding to each first target object pair, performing correction processing on the target association index data corresponding to each first target object pair to obtain the object association index data corresponding to each first target object pair.

3. The method according to claim 2, characterized in that The determining the correction coefficient corresponding to each first target object pair based on the first object collection times, the second object collection times, and the object-to-object association times includes: Performing mean processing on the first object collection times and the second object collection times of the association object in each first target object pair to obtain the average collection times corresponding to each first target object pair; Based on the average collection times corresponding to each first target object pair and the object-to-object association times corresponding to each first target object pair, determining the correction coefficient corresponding to each first target object pair.

4. The method according to claim 1, characterized in that, Based on the indication information of the object to be analyzed, obtaining the data of the object to be analyzed corresponding to the object to be analyzed, the associated object data of each of the multiple associated objects corresponding to the object to be analyzed, and the inter-object association data corresponding to each of the multiple first target object pairs, includes: Based on the indication information of the object to be analyzed, obtaining the data of the object to be analyzed from the object data storage area; Based on the data of the object to be analyzed and the associated data storage area, determining the multiple associated objects corresponding to the object to be analyzed and the multiple first target object pairs, and obtaining the inter-object association data corresponding to each of the multiple first target object pairs; Obtaining the associated object data of each of the multiple associated objects from the object data storage area.

5. The method according to claim 4, characterized in that The data of the object to be analyzed includes the first object identification information corresponding to the object to be analyzed; the associated data storage area stores the preset associated data corresponding to any one of the multiple preset object pairs, and the preset associated data corresponding to any one of the preset object pairs includes the first relationship indication information, the second relationship indication information, and the inter-object association times corresponding to any one of the preset object pairs. Both the first relationship indication information and the second relationship indication information include the object identification information of two preset objects respectively. The object identification information of the first preset object in any one of the preset object pairs is located at the preset object query position in the first relationship indication information, and the object identification information of the second preset object in any one of the preset objects is located at the preset object query position in the second relationship indication information; Based on the data of the object to be analyzed and the associated data storage area, determining the multiple associated objects corresponding to the object to be analyzed and the multiple first target object pairs, and obtaining the inter-object association data corresponding to each of the multiple first target object pairs, includes: Performing a matching process on the object identification information at the preset object query position in the two relationship indication information corresponding to each preset object pair and the first object identification information, to obtain the multiple first target object pairs and the inter-object association data corresponding to each of the multiple first target object pairs; Based on the multiple first target object pairs, determining the multiple associated objects.

6. The method according to claim 4, wherein The method further includes: When it is detected that there is a target object data pair among the multiple currently to-be-detected object data, updating the associated data in the associated data storage area based on the target object data pair; the target object data pair is an object data pair in which the time interval between the object data acquisition times corresponding to any two of the multiple currently to-be-detected object data is less than the first preset time interval.

7. The method according to claim 6, wherein The multiple currently to-be-detected object data are obtained in the following manner: Obtaining multiple currently collected object data; the multiple currently collected object data are object data collected by multiple preset collection devices within the current time range; Determining, from the multiple currently collected object data, the multiple target collection object data corresponding to each preset collection device; the object feature information corresponding to the multiple target collection object data is the same, and the maximum collection time interval corresponding to the multiple target collection object data is less than the second preset time interval; Determine the first acquisition object data corresponding to each preset acquisition device and at least one second acquisition object data corresponding to each preset acquisition device, where the first acquisition object data is any one of the multiple target acquisition object data, and the at least one second acquisition object data is the target acquisition object data other than the first acquisition object data among the multiple target acquisition object data; Filter at least one second acquisition object data corresponding to each preset acquisition device among the multiple current acquisition object data to obtain the multiple current objects to be detected data.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: Filter the first target object pairs in the multiple first target object pairs where the association times between the corresponding objects are less than the second preset association times to obtain multiple second target object pairs; Based on the first object acquisition times, the second object acquisition times corresponding to the multiple associated objects respectively, and the association times between the corresponding objects of the multiple first target object pairs respectively, perform association analysis on each first target object pair to obtain the object association index data corresponding to each first target object pair, including: Based on the first object acquisition times, the second object acquisition times, and the association times between the corresponding objects of the multiple second target object pairs respectively, perform association analysis on each second target object pair to obtain the object association index data corresponding to each second target object pair.

9. A data processing device, characterized in that, The device includes: An instruction receiving module, configured to receive an object association analysis instruction; the object association analysis instruction includes the to-be-analyzed object indication information corresponding to the to-be-analyzed object; A first data acquisition module, configured to obtain the to-be-analyzed object data corresponding to the to-be-analyzed object, the association object data corresponding to the multiple associated objects corresponding to the to-be-analyzed object respectively, and the object association data corresponding to the multiple first target object pairs respectively based on the to-be-analyzed object indication information; the to-be-analyzed object data includes the first object acquisition times, the association object data includes the second object acquisition times, the object association data includes the association times between the corresponding objects, and any one of the first target object pairs includes the to-be-analyzed object and any one of the multiple associated objects; A first association analysis module, configured to perform association analysis on each first target object pair based on the first object acquisition times, the second object acquisition times corresponding to the multiple associated objects respectively, and the association times between the corresponding objects of the multiple first target object pairs respectively to obtain the object association index data corresponding to each first target object pair; A second association analysis module, configured to perform object association analysis on the to-be-analyzed object based on the object association index data corresponding to each first target object pair to obtain the object association analysis result corresponding to the to-be-analyzed object.

10. An electronic device, characterized in that, Includes: A processor; A memory for storing a computer program; Wherein, the processor is configured to execute the computer program to implement the data processing method according to any one of claims 1 to 8.

Images