Method and apparatus for processing abnormal information, storage medium, and electronic device

Abstract

An embodiment of the present invention provides a method and apparatus for processing abnormal information, a storage medium, and an electronic device. The method includes: determining attribute information of a first object included in a target image; evaluating each piece of attribute information in the attribute information to obtain an attribute score; determining that the attribute information belongs to abnormal attribute information when an abnormal attribute score is detected; and performing clustering processing on the abnormal attribute information. Through the present invention, the problem of processing abnormal information in the related art can be solved, and the effect of accurately correcting abnormal data in the clustered and archived data can be achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing, and more specifically, to a method and device for processing abnormal information, a storage medium, and an electronic device. Background Art

[0002] Currently, the solutions for establishing personnel files only optimize the real-time personnel clustering and archiving of personnel or the file splitting of established files (i.e., the situation of multiple files for one person), but do not detect and process abnormal data in the personnel archived files; in the existing abnormal data point detection solutions, the focus is basically on the data itself, such as analyzing the spatial distribution law of data in terms of data (local) parameters, spatial dimensions, etc., so as to analyze abnormal data points, but the business logic of clustering and archiving is not combined, and the applicability is not high.

[0003] In view of the problems existing in the prior art, no effective solution has been proposed in the related art. Summary of the Invention

[0004] The embodiments of the present invention provide a method and device for processing abnormal information, a storage medium, and an electronic device, so as to at least solve the problem of abnormal information processing in the related art.

[0005] According to an embodiment of the present invention, a method for processing abnormal information is provided, including: determining the attribute information of a first object included in a target image; evaluating each piece of attribute information in the above-mentioned attribute information to obtain an attribute score; in the case where the above-mentioned attribute score is detected to be abnormal, determining that the above-mentioned attribute information belongs to abnormal attribute information; and clustering the above-mentioned abnormal attribute information.

[0006] According to another embodiment of the present invention, a device for processing abnormal information is provided, including: a first determination module, configured to determine the attribute information of a first object included in a target image; a first evaluation module, configured to evaluate each piece of attribute information in the above-mentioned attribute information to obtain an attribute score; a second determination module, configured to determine that the above-mentioned attribute information belongs to abnormal attribute information in the case where the above-mentioned attribute score is detected to be abnormal; and a first processing module, configured to cluster the above-mentioned abnormal attribute information.

[0007] In an exemplary embodiment, the above-mentioned first determination module includes one of the following: a first reading unit, configured to read the above-mentioned attribute information of the above-mentioned first object from a database; a first detection unit, configured to detect the above-mentioned attribute information of the above-mentioned first object from the above-mentioned target image.

[0008] In an exemplary embodiment, the first evaluation module includes: a first determination unit configured to determine the weight ratio of the attribute information among N pieces of attribute information, where the N pieces of attribute information include all attributes of the first object, and N is a natural number greater than or equal to 1; a first evaluation unit configured to evaluate the state of the first object corresponding to the attribute information to obtain a state score of the attribute information; a first calculation unit configured to determine an average score of the state scores; and a second calculation unit configured to calculate the attribute score based on the weight ratio, the state score, and the average score.

[0009] In an exemplary embodiment, the second calculation unit includes: where δ is used to represent the attribute score, and k i is used to represent the weight ratio, and w i is used to represent the state score, and is used to represent the average score.

[0010] In an exemplary embodiment, the second determination module includes: a first judgment unit configured to judge whether the attribute score is within a preset threshold range; and a second calculation unit configured to determine that the attribute information belongs to abnormal attribute information when the attribute score is not within the preset threshold range.

[0011] In an exemplary embodiment, the first processing module includes: a first classification unit configured to classify the attribute information of the first object into the first file cluster when the similarity between the abnormal attribute information and the attribute information of the second object in the first file cluster satisfies a second preset threshold range, and the attribute score corresponding to the abnormal attribute information satisfies the attribute score corresponding to the attribute information of the second object.

[0012] In an exemplary embodiment, the first processing module includes: a second classification unit configured to classify the K pieces of abnormal attribute information into a second file cluster when the aggregation of the obtained K pieces of abnormal attribute information satisfies a third preset threshold range, and the attribute difference scores of each piece of abnormal attribute information among the K pieces of abnormal attribute information satisfy a fourth preset threshold range, where the abnormal attribute information is included in the K pieces of abnormal attribute information.

[0013] According to another embodiment of the present invention, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0014] According to another embodiment of the present invention, there is also provided an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0015] Through the present invention, by evaluating the attribute information of the determined first object, an attribute score can be obtained, and it can be detected whether the attribute information is abnormal based on the attribute score. In the case where the attribute information is abnormal, clustering processing is performed on the abnormal attribute information, making the classification of the attribute information more accurate. Therefore, the problem of processing abnormal information in the related art can be solved, and the effect of accurately correcting abnormal data in the clustered and archived data can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a hardware structure block diagram of a mobile terminal for a method of processing abnormal information according to an embodiment of the present invention;

[0017] Figure 2 is a flowchart of a method of processing abnormal information according to an embodiment of the present invention;

[0018] Figure 3 is a structural diagram according to a specific embodiment of the present invention;

[0019] Figure 4 is a flowchart according to a specific embodiment of the present invention;

[0020] Figure 5 is a structural block diagram of a device for processing abnormal information according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings and in conjunction with the embodiments.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence.

[0023] The method embodiments provided in the embodiments of the present application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of a mobile terminal for a method of processing abnormal information according to an embodiment of the present invention. As Figure 1 shown, the mobile terminal may include one or more ( Figure 1Only one processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data are shown. Among them, the above mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 The structure shown is only schematic and does not limit the structure of the above mobile terminal. For example, the mobile terminal may further include more or fewer components than Figure 1 shown in, or have a different configuration from Figure 1 shown.

[0024] The memory 104 can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to the processing method of abnormal information in the embodiments of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely provided with respect to the processor 102, and these remote memories can be connected to the mobile terminal through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. Specific examples of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one instance, the transmission device 106 includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0026] In this embodiment, a method for processing abnormal information is provided. Figure 2 is a flowchart of the method for processing abnormal information according to the embodiments of the present invention. As Figure 2 shown, the process includes the following steps:

[0027] Step S202, determining the attribute information of the first object included in the target image;

[0028] Step S204, evaluating each piece of attribute information in the attribute information to obtain an attribute score;

[0029] Step S206, when the attribute score is detected as abnormal, determine that the attribute information belongs to abnormal attribute information;

[0030] Step S208, perform clustering processing on the abnormal attribute information.

[0031] Among them, the execution subject of the above steps can be a terminal or the like, but is not limited thereto.

[0032] This embodiment includes but is not limited to scenarios of performing abnormal detection on attribute information. For example, in a scenario of detecting the attribute information of a person in a personnel file. The attribute information includes but is not limited to characteristics such as a person's skin color, age, weight, etc.

[0033] Through the above steps, by evaluating the attribute information of the determined first object, an attribute score can be obtained, and it can be detected whether the attribute information is abnormal based on the attribute score. In the case where the attribute information is abnormal, clustering processing is performed on the abnormal attribute information. This makes the classification of the attribute information more accurate. Therefore, the problem of processing abnormal information in the related art can be solved, and the effect of accurately correcting abnormal data in the clustered archived data can be achieved.

[0034] In an exemplary embodiment, determining the attribute information of the first object included in the target image includes one of the following:

[0035] S1, read the attribute information of the first object from the database;

[0036] S2, detect the attribute information of the first object from the target image.

[0037] In this embodiment, the database also stores basic information such as the capture time and appearance location of the target image.

[0038] In this embodiment, attribute information such as the age, fatness score, charm value, and skin color degree of the first object can be detected from the target image.

[0039] In an exemplary embodiment, evaluating each attribute information in the attribute information to obtain an attribute score includes:

[0040] S1, determine the weight ratio of the attribute information among N attribute information, where the N attribute information includes all the attributes of the first object, and N is a natural number greater than or equal to 1;

[0041] S2, evaluate the state of the first object corresponding to the attribute information to obtain the state score of the attribute information;

[0042] S3, determine the average score of the state scores;

[0043] S4, calculate the attribute score based on the weight ratio, state score, and average score.

[0044] In this embodiment, for example, the first object appears 10 times in the personnel file. Among them, the fatness and thinness scores are always above 80 for 9 times, and the remaining one is below 60 and this time appears at the intermediate moment. Then this data point is probably abnormal attribute information.

[0045] In an exemplary embodiment, an attribute score is calculated based on the weight ratio, the status score, and the average score, and the following formula is used:

[0046] Among them, δ is used to represent the attribute score, k i is used to represent the weight ratio, w i is used to represent the status score, is used to represent the average score.

[0047] In an exemplary embodiment, when it is detected that the attribute score is abnormal, determining that the attribute information belongs to abnormal attribute information includes:

[0048] S1, judging whether the attribute score is within the range of the first preset threshold;

[0049] S2, when the attribute score is not within the range of the first preset threshold, determining that the attribute information belongs to abnormal attribute information.

[0050] In this embodiment, for example, judge whether the attribute difference score reaches the abnormal threshold (that is, not within the range of the first preset threshold).

[0051] In an exemplary embodiment, clustering processing is performed on the abnormal attribute information, including:

[0052] S1, when the similarity between the abnormal attribute information and the attribute information of the second object in the first file cluster meets the second preset threshold range, and the attribute score corresponding to the abnormal attribute information meets the attribute score corresponding to the attribute information of the second object, classify the attribute information of the first object into the first file cluster.

[0053] In this embodiment, for example, the abnormal attribute information is detected from the attribute information of the first object. The feature similarity with the first file cluster meets the requirements, and the attribute score within the first file cluster meets the attribute score corresponding to the attribute information of the second object in the first file cluster. Then the abnormal attribute information is classified into the first file cluster.

[0054] The present invention will be described below in conjunction with specific embodiments:

[0055] This embodiment is described by taking the file management of personnel as an example. For example, the detection of abnormal data points of attribute information such as skin color, age, and weight can reduce the occurrence of abnormal points in the personnel file and optimize the portrait information of the same person.

[0056] As Figure 3 shown, this embodiment mainly includes an archive acquisition module, an anomaly detection module, a secondary processing module, and a data archiving module. The functions and implementation processes of each module are as Figure 4 shown, and the steps are as follows:

[0057] (1) Archive acquisition module. The archive acquisition module mainly processes two types of information.

[0058] S401, acquire basic information: Query and acquire basic information such as archive pictures, capture times, and occurrence locations, which is mainly used for secondary clustering analysis.

[0059] S402, acquire archive attributes: If the archive storage data already exists, directly read it; if not, use the archive pictures for detection and acquisition to complete. Generally, the attributes include age, fatness and thinness scores, charm values, skin color degrees, etc.

[0060] (2) Anomaly detection module:

[0061] S403, receive the archive attributes (including the average archive attributes and the own attributes of each capture) in the archive acquisition module;

[0062] S404, calculate the attribute difference score δ, and determine whether the attribute difference score δ reaches the anomaly threshold. If all detections during traversal are normal, directly end this anomaly processing; otherwise, send it to the secondary processing module;

[0063] In this embodiment,

[0064] Explanation: A. δ represents the attribute difference score, and k i represents the weight ratio of attribute i. B. w i represents the status score of attribute i, represents the average score of attribute i in the archive.

[0065] Generally, the default attributes include but are not limited to scores such as age, fatness and thinness scores, charm values, skin color degrees, etc. The rest can be appropriately added or deleted according to the customer's business situation.

[0066] For example, for person A in the personnel archive, it appears 10 times in [t 0 , t 1 . Among them, the fatness and thinness scores are above 80 for 9 times, and the remaining one time is below 60 and this time appears at the middle moment. Then this data point is probably abnormal data.

[0067] (3) Secondary processing module;

[0068] S405, Periodically receive the detected abnormal data points, and perform clustering analysis on this batch of data and the previously established archives. Here, the clustering analysis includes, but is not limited to, partitioning clustering, hierarchical clustering, density clustering, etc.

[0069] S406, Process the abnormal data points according to the results of the clustering analysis:

[0070] S407 - S408, If a single data point a is detected from Archive B, but its similarity with the archive features of Archive A meets the requirements, and the abnormal score of the attribute difference within Archive A does not reach the threshold, then classify the abnormal data point into Archive A;

[0071] S409, If multiple abnormal data points have strong aggregation, and the abnormal score of the attribute difference of each point within the newly generated pre - archive does not reach the splitting threshold, then create a new archive.

[0072] (4) Data archiving module:

[0073] S410, Match and archive the data processed by the secondary processing module; send the archiving result to the corresponding server and store it in the database.

[0074] S411, End.

[0075] In summary, in this embodiment, it is possible to detect abnormal data in a personnel archive according to multiple dimensions such as age, body fat score, charm value, skin color degree, etc. under the condition that a personnel archive has been established, appropriately split out mature and reasonable archives, and effectively optimize the archives of the same person.

[0076] Through the description of the above - mentioned implementation manners, those skilled in the art can clearly understand that the method according to the above - mentioned embodiments can be implemented by means of software plus a necessary general - purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0077] In this embodiment, an abnormal information processing device is also provided. This device is used to implement the above - mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation by hardware, or a combination of software and hardware is also possible and contemplated.

[0078] Figure 5It is a structural block diagram of a processing device for abnormal information according to an embodiment of the present invention. As Figure 5 shown, the device includes:

[0079] A first determination module 52, configured to determine the attribute information of a first object included in a target image;

[0080] A first evaluation module 54, configured to evaluate each piece of attribute information in the attribute information to obtain an attribute score;

[0081] A second determination module 56, configured to determine that the attribute information belongs to abnormal attribute information when it is detected that the attribute score is abnormal;

[0082] A first processing module 58, configured to perform clustering processing on the abnormal attribute information.

[0083] In an exemplary embodiment, the above-mentioned first determination module includes one of the following:

[0084] A first reading unit, configured to read the above-mentioned attribute information of the above-mentioned first object from a database;

[0085] A first detection unit, configured to detect the above-mentioned attribute information of the above-mentioned first object from the above-mentioned target image.

[0086] In an exemplary embodiment, the above-mentioned first evaluation module includes:

[0087] A first determination unit, configured to determine the weight ratio of the above-mentioned attribute information among N pieces of attribute information, where the above-mentioned N pieces of attribute information include all attributes of the above-mentioned first object, and N is a natural number greater than or equal to 1;

[0088] A first evaluation unit, configured to evaluate the state of the above-mentioned first object corresponding to the above-mentioned attribute information to obtain the state score of the above-mentioned attribute information;

[0089] A first calculation unit, configured to determine the average score of the state score;

[0090] A second calculation unit, configured to calculate the above-mentioned attribute score based on the above-mentioned weight ratio, the above-mentioned state score, and the above-mentioned average score.

[0091] In an exemplary embodiment, the above-mentioned second calculation unit adopts the following formula:

[0092] where, the above-mentioned δ is used to represent the above-mentioned attribute score, the above-mentioned k i is used to represent the above-mentioned weight ratio, the above-mentioned w i is used to represent the above-mentioned state score, and the above-mentioned is used to represent the above-mentioned average score.

[0093] In an exemplary embodiment, the above-mentioned second determination module includes:

[0094] A first judgment unit, configured to judge whether the above-mentioned attribute score is within a preset threshold range;

[0095] A second calculation unit, configured to determine that the above-mentioned attribute information belongs to abnormal attribute information in the case that the above-mentioned attribute score is not within the above-mentioned preset threshold range.

[0096] In an exemplary embodiment, the above-mentioned first processing module includes:

[0097] A first classification unit, configured to classify the attribute information of the above-mentioned first object into the above-mentioned first file cluster in the case that the similarity between the above-mentioned abnormal attribute information and the attribute information of the second object in the first file cluster meets a second preset threshold range, and the attribute score corresponding to the above-mentioned abnormal attribute information meets the attribute score corresponding to the attribute information of the above-mentioned second object.

[0098] In an exemplary embodiment, the above-mentioned first processing module includes:

[0099] A second classification unit, configured to classify the above-mentioned K abnormal attribute information into a second file cluster in the case that the aggregation among the obtained K abnormal attribute information meets a third preset threshold range, and the attribute difference score of each abnormal attribute information in the above-mentioned K abnormal attribute information meets a fourth preset threshold range, wherein the above-mentioned abnormal attribute information is included in the above-mentioned K abnormal attribute information.

[0100] It should be noted that the above-mentioned each module can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above-mentioned modules are all located in the same processor; or, the above-mentioned each module is separately located in different processors in any combination form.

[0101] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is set to execute the steps in any one of the above-mentioned method embodiments when running.

[0102] In this embodiment, the above-mentioned computer-readable storage medium can be set to store a computer program for executing the above-mentioned each step.

[0103] In an exemplary embodiment, the above-mentioned computer-readable storage medium may include but is not limited to: USB flash drive, read-only memory (abbreviation: ROM), random access memory (abbreviation: RAM), mobile hard disk, magnetic disk or optical disc and other various media that can store computer programs.

[0104] An embodiment of the present invention further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0105] In an exemplary embodiment, the above electronic device may further include a transmission device and an input / output device. The transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0106] In an exemplary embodiment, the above processor may be configured to execute the above steps through a computer program.

[0107] Specific examples in this embodiment may refer to the examples described in the above embodiments and exemplary embodiments, and will not be repeated here.

[0108] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. Thus, the present invention is not limited to any specific combination of hardware and software.

[0109] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing abnormal information, characterized in that, comprising: determining the attribute information of the first object included in the target image; evaluating each piece of attribute information in the attribute information to obtain an attribute score; when it is detected that the attribute score is abnormal, determining that the attribute information belongs to abnormal attribute information; performing clustering processing on the abnormal attribute information; wherein, performing clustering processing on the abnormal attribute information includes: when the similarity between the abnormal attribute information and the attribute information of the second object in the first file cluster satisfies a second preset threshold range, and the attribute score corresponding to the abnormal attribute information satisfies the attribute score corresponding to the attribute information of the second object, classifying the attribute information of the first object into the first file cluster; the first file cluster does not include the first object.

2. The method according to claim 1, characterized in that, determining the attribute information of the first object included in the target image includes one of the following: reading the attribute information of the first object from a database; detecting the attribute information of the first object from the target image.

3. The method according to claim 1, characterized in that, evaluating each piece of attribute information in the attribute information to obtain an attribute score includes: determining the weight ratio of the attribute information among N pieces of attribute information, where the N pieces of attribute information include all the attributes of the first object, and N is a natural number greater than or equal to 1; evaluating the state of the first object corresponding to the attribute information to obtain a state score of the attribute information; determining the average score of the state scores; calculating the attribute score based on the weight ratio, the state score, and the average score.

4. The method according to claim 3, characterized in that, calculating the attribute score based on the weight ratio, the state score, and the average score using the following formula: Among them, the δ is used to represent the attribute score, and the k i is used to represent the weight ratio, and the w i is used to represent the status score, and the is used to represent the average score.

5. The method according to claim 1, characterized in that, when it is detected that the attribute score is abnormal, determining that the attribute information belongs to abnormal attribute information includes: judging whether the attribute score is within a first preset threshold range; when the attribute score is not within the first preset threshold range, determining that the attribute information belongs to abnormal attribute information.

6. The method according to claim 1, characterized in that, performing clustering processing on the abnormal attribute information includes: when the aggregation among the obtained K pieces of abnormal attribute information satisfies a third preset threshold range, and the attribute scores of each piece of abnormal attribute information among the K pieces of abnormal attribute information satisfy a fourth preset threshold range, classifying the K pieces of abnormal attribute information into a second file cluster, where the abnormal attribute information is included in the K pieces of abnormal attribute information; the second file cluster includes the first object.

7. An apparatus for processing abnormal information, characterized in that, comprising: a first determination module for determining the attribute information of the first object included in the target image; a first evaluation module for evaluating each piece of attribute information in the attribute information to obtain an attribute score; A second determination module, configured to determine that the attribute information belongs to abnormal attribute information when it is detected that the attribute score is abnormal; A first processing module, configured to perform clustering processing on the abnormal attribute information; The first processing module is further configured to classify the attribute information of the first object into the first file cluster when the similarity between the abnormal attribute information and the attribute information of the second object in the first file cluster meets a second preset threshold range, and the attribute score corresponding to the abnormal attribute information meets the attribute score corresponding to the attribute information of the second object; Wherein, the first file cluster does not include the first object.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the method described in any one of claims 1 to 6.

9. An electronic device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to execute the method described in any one of claims 1 to 6.

Images