Target object management method and system

Abstract

The invention provides a target object management method and system, and the method comprises the steps: obtaining target object information, and carrying out the data cleaning and screening of the target object information, so as to obtain key information; performing feature extraction on the key information to obtain target object category features; performing data prediction on the target object category features to obtain category information; the category information is evaluated and analyzed, an evaluation result is output, the supervision period of the target object information is calculated based on the evaluation result, and the target object is managed based on the supervision period. The corresponding supervision period can be determined according to the information of the target object, so that the supervision capability of the target object is improved; and meanwhile, the supervision efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of personnel management, and particularly relates to a method and system for managing target objects. Background Art

[0002] With the development of technology, there are more and more transportation methods, which are more efficient and convenient. It is easier for target objects to leave the set area than before. Coupled with the information asynchrony and non-sharing between different units, it has become more difficult to manage target objects in a timely manner. In the past, it was only possible to know which target objects lived in the jurisdiction and which target objects left the set area through on-site visits or inquiries, which had a large degree of uncertainty and was prone to the risks of unmanaged and missed management of target objects. At the same time, in the process of managing target objects, the supervision cycle of target objects can usually only be determined manually according to the experience of relevant personnel and existing evidence, which is inefficient and time-consuming. Summary of the Invention

[0003] To solve the above technical problems, the present invention provides a method and system for managing target objects to solve the technical problems in the prior art.

[0004] On the one hand, the present invention provides the following technical solution. A method for managing target objects includes:

[0005] Obtain target object information, perform data cleaning and screening on the target object information to obtain key information;

[0006] Extract features from the key information to obtain target object category features;

[0007] Perform data prediction on the target object category features to obtain category information;

[0008] Conduct evaluation and analysis on the category information and output an evaluation result. Calculate the supervision cycle of the target object information based on the evaluation result, and manage the target object based on the supervision cycle.

[0009] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention first obtains target object information, performs data cleaning and screening on the target object information to obtain key information; then extracts features from the key information to obtain target object category features; then performs data prediction on the target object category features to obtain category information; then conducts evaluation and analysis on the category information and outputs an evaluation result. Calculate the supervision cycle of the target object information based on the evaluation result, and manage the target object based on the supervision cycle. The present invention can determine the corresponding supervision cycle according to the information of the target object, thereby improving the supervision ability of the target object and also improving the supervision efficiency.

[0010] Preferably, the step of performing data cleaning and screening on the target object information to obtain key information includes:

[0011] Calculating the deviation value Z of the target object information:

[0012]

[0013] where x represents the x-th data in the target object information, and μ and σ represent the sample mean and sample standard deviation respectively;

[0014] Removing the data with deviation values greater than the preset deviation value from the target object information to obtain the removed information;

[0015] Calculating the first text ratio A in the removed information 1 :

[0016]

[0017] where D t represents the number of times the word t appears in the document D, and D a represents the total number of words of the word t;

[0018] Calculating the second text ratio A in the removed information 2 :

[0019]

[0020] where N t represents the number of samples containing the word t, and N a represents all the number of samples;

[0021] Based on the first text ratio A 1 and the second text ratio A 2 Calculating the text frequency B t :

[0022] B t = A 1 A 2 ;

[0023] Calculating the text frequency of each text word in each document of the target object information, arranging the text frequencies of each text word in a single document in descending order, and retaining the text words corresponding to the top several text frequencies in each document of the target object information to obtain key information.

[0024] Preferably, the step of performing feature extraction on the key information to obtain the target object category feature includes:

[0025] Use a dimensionality reduction algorithm to perform dimensionality reduction processing on the key information to obtain reduced-dimensional information;

[0026] Select K data from the reduced-dimensional information as the initial clustering centers, and calculate the clustering distances between each data in the reduced-dimensional information and the initial clustering centers;

[0027] And allocate the data in the reduced-dimensional information to the nearest initial clustering center according to the clustering distances to obtain initial clusters;

[0028] Based on the data in the initial clusters, update the initial clustering centers, and iteratively perform the data allocation and clustering center update processes until the clustering centers no longer change significantly, so as to output several clustering clusters;

[0029] Determine the target object category features based on several of the clustering clusters.

[0030] Preferably, the step of determining the target object category features based on several of the clustering clusters includes:

[0031] Calculate the importance degree WCSS of each data in the clustering cluster:

[0032]

[0033] In the formula, x i 、y k respectively represent the i-th data in the k-th clustering cluster and the k-th clustering cluster;

[0034] Arrange each clustering cluster in descending order based on the importance degree WCSS to obtain the target object category features.

[0035] Preferably, the dimensionality reduction algorithm is specifically the PCA algorithm.

[0036] Preferably, the step of performing data prediction on the target object category features to obtain category information includes:

[0037] Obtain training data, input the training data into a preset prediction model for training, and input the target object category features into the trained preset prediction model for prediction to obtain category information.

[0038] Preferably, the step of evaluating and analyzing the category information and outputting an evaluation result, and calculating the supervision period of the target object information based on the evaluation result includes:

[0039] Determine each influencing factor in the category information, and construct a judgment matrix based on historical category data;

[0040] Perform hierarchical analysis on the judgment matrix to obtain a positive reciprocal matrix, and perform hierarchical single sorting and consistency test on the positive reciprocal matrix to obtain a sorting matrix;

[0041] Calculate the maximum eigenvalue and the corresponding eigenvector of the sorting matrix, arrange the eigenvector in descending order, and determine the influence weight of each influencing factor in turn according to the arranged eigenvector;

[0042] Calculate the comprehensive score S based on the influence weight and the category information m :

[0043] S m = SUM (n＝1toN) w n ×X mn ;

[0044] In the formula, N represents the number of influencing factors, w n represents the influence weight corresponding to the nth influencing factor, and X mn represents the data belonging to the nth influencing factor in the category information;

[0045] Determine the supervision period based on the comprehensive score.

[0046] In a second aspect, the present invention provides the following technical solution. A target object management system, the system includes:

[0047] A screening module, configured to obtain target object information, perform data cleaning and screening on the target object information to obtain key information;

[0048] An extraction module, configured to perform feature extraction on the key information to obtain target object category features;

[0049] A prediction module, configured to perform data prediction on the target object category features to obtain category information;

[0050] A management module, configured to perform evaluation analysis on the category information and output an evaluation result, calculate the supervision period of the target object information based on the evaluation result, and manage the target object based on the supervision period.

[0051] In a third aspect, the present invention provides the following technical solution. A computer includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the target object management method as described above is implemented.

[0052] In a fourth aspect, the present invention provides the following technical solution. A storage medium stores a computer program, and when the computer program is executed by a processor, the target object management method as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 It is a flowchart of the target object management method provided in the first embodiment of the present invention;

[0055] Figure 2 It is a structural block diagram of the target object management system provided in the second embodiment of the present invention;

[0056] Figure 3 It is a schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0057] The following will further illustrate the embodiments of the present invention with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] The following will describe in detail the embodiments of the present invention. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the embodiments of the present invention, and should not be construed as a limitation of the present invention.

[0059] In the description of the embodiments of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0060] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0061] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0062] The embodiment of the present invention mainly describes the supervision cycle of the target object in the online car-hailing scenario as an example. It should be understood that the methods involved in supervising personnel can all adopt the management method of this embodiment, and this embodiment does not limit this. At the same time, it should be understood that the data obtained in the embodiment of the present invention are all obtained, collected, stored, used, transmitted, provided and presented after the authorization of the corresponding user in accordance with the provisions of relevant laws and regulations, without infringing on the privacy of others and not violating public order and good morals, and the technical solutions presented in the embodiments of the present invention are in compliance with the provisions of relevant laws and regulations.

[0063] Embodiment 1

[0064] In the first embodiment of the present invention, Figure 1 As shown, a target object management method includes:

[0065] S1. Obtain target object information, and perform data cleaning and screening on the target object information to obtain key information;

[0066] Specifically, the target object information here can be obtained through internal sharing within relevant departments. By performing corresponding data cleaning and screening on the target object information, data that deviates from the normal range and unimportant data in the target object information can be identified.

[0067] Wherein, the step S1 comprises:

[0068] S11, calculating the deviation value Z of the target object information:

[0069]

[0070] In the formula, x represents the xth data in the target object information, μ and σ represent the sample mean and sample standard deviation respectively.

[0071] S12, removing data whose deviation value is greater than a preset deviation value from the target object information to obtain removal information;

[0072] Specifically, the data is screened through the above process to identify and eliminate possible errors or abnormal records.

[0073] S13. Calculate the first text proportion A in the excluded information 1 :

[0074]

[0075] In the formula, D t represents the number of times the word t appears in the document D, and D a represents the total number of words of the word t;

[0076] Specifically, the first text proportion here can be used to reflect the importance of the keyword in the entire excluded information. For example, the text words related to violations and supervision account for a relatively large proportion in the entire excluded information.

[0077] S14. Calculate the second text proportion A in the excluded information 2 :

[0078]

[0079] In the formula, N t represents the number of samples containing the word t, and N a represents all the number of samples;

[0080] Specifically, the purpose of calculating the second text proportion is to reduce the importance of the words that may appear in almost all documents, such as common words like "is" and "of".

[0081] S15. Based on the first text proportion A 1 and the second text proportion A 2 calculate the text frequency B t :

[0082] B t = A 1 A 2 ;

[0083] S16. Calculate the text frequency of each text word in each document of the target object information, sort the text frequencies of each text word in a single document in descending order, and retain the text words corresponding to the first several text frequencies in each document of the target object information to obtain the key information;

[0084] Specifically, by sorting the text frequencies of each word in descending order and selecting the first several text words with larger text frequencies and the corresponding documents for retention, the key information can be obtained.

[0085] S2. Extract features from the key information to obtain the target object category features;

[0086] Among them, the step S2 includes:

[0087] S21. Use a dimensionality reduction algorithm to perform dimensionality reduction processing on the key information to obtain reduced-dimensional information;

[0088] Among them, the dimensionality reduction algorithm is specifically the PCA algorithm.

[0089] S22. Select K data from the reduced-dimensional information as the initial clustering centers, and calculate the clustering distances between each data in the reduced-dimensional information and the initial clustering centers.

[0090] S23. And allocate the data in the reduced-dimensional information to the nearest initial clustering center according to the clustering distances to obtain initial clusters.

[0091] S24. Update the initial clustering centers based on the data in the initial clusters, and iteratively perform the data allocation and clustering center update processes until the clustering centers no longer change significantly, so as to output several clustering clusters;

[0092] Specifically, the above steps are specifically the process of the K-means clustering algorithm, so it will not be elaborated in this application.

[0093] S25. Determine the target object category features based on several of the clustering clusters;

[0094] Among them, step S25 includes:

[0095] S251. Calculate the importance degree WCSS of each data in the clustering cluster:

[0096]

[0097] In the formula, x i , y k respectively represent the i-th data in the k-th clustering cluster and the k-th clustering cluster;

[0098] S252. Arrange each clustering cluster in descending order based on the importance degree WCSS to obtain the target object category features;

[0099] Specifically, by calculating the importance degree of the clustering clusters, it can be used to judge the importance degree of the data in each clustering cluster for the supervision of important personnel, and according to the target object category features, the specific management regulations and de-registration conditions of each category can be listed in detail to ensure that relevant personnel clearly understand what rules different types of target objects should follow and under what circumstances the supervision measures can be lifted.

[0100] S3. Perform data prediction on the target object category features to obtain category information;

[0101] Among them, step S3 is specifically:

[0102] Obtain training data, input the training data into a preset prediction model for training, and input the category features of the target object into the trained preset prediction model for prediction to obtain category information;

[0103] Among them, the preset prediction model is specifically a random forest model, which can be used to predict which information is more important for target objects of a specific category, so as to optimize the information collection strategy.

[0104] S4. Evaluate and analyze the category information and output an evaluation result, calculate the supervision period of the target object information based on the evaluation result, and manage the target object based on the supervision period;

[0105] Among them, the step S4 includes:

[0106] S41. Determine each influencing factor in the category information and construct a judgment matrix based on historical category data.

[0107] S42. Conduct hierarchical analysis on the judgment matrix to obtain a positive reciprocal matrix, and conduct hierarchical single sorting and consistency test on the positive reciprocal matrix to obtain a sorting matrix.

[0108] S43. Calculate the maximum eigenvalue and the corresponding eigenvector of the sorting matrix, arrange the eigenvector in descending order, and sequentially determine the influence weight of each influencing factor according to the arranged eigenvector;

[0109] Specifically, the above steps are the specific steps of the analytic hierarchy process and will not be elaborated here.

[0110] S44. Calculate the comprehensive score S based on the influence weight and the category information m :

[0111] S m =SUM (n＝1toN) w n ×X mn ;

[0112] In the formula, N represents the number of influencing factors, w n represents the influence weight corresponding to the nth influencing factor, and X mn represents the data belonging to the nth influencing factor in the category information;

[0113] Specifically, the comprehensive score can be used to judge the comprehensive score obtained by superimposing each factor information in the information corresponding to each target object. This comprehensive score can be used to judge which supervision intensity the target object is suitable for and determine the corresponding supervision period.

[0114] S45. Determine the supervision period based on the comprehensive score;

[0115] Specifically, different supervision periods can be determined according to the range of the comprehensive score, and then the corresponding supervision period can be determined for each target object to implement the management process of the target object;

[0116] Meanwhile, after determining the important score, the disposal tasks are reasonably allocated according to the size of the important score and the personnel distribution of the relevant part. After receiving the task and disposing it on the platform, the disposal result is returned to the cloud, and the task can also be dispatched for the warning received by the platform.

[0117] For the target object management method provided in the first embodiment of the present invention, first, target object information is obtained, and the target object information is subjected to data cleaning and screening to obtain key information; then, feature extraction is performed on the key information to obtain target object category features; then, data prediction is performed on the target object category features to obtain category information; then, evaluation analysis is performed on the category information and an evaluation result is output. Based on the evaluation result, the supervision period of the target object information is calculated, and the target object is managed based on the supervision period. The present invention can determine the corresponding supervision period according to the information of the target object, thereby improving the supervision ability of the target object and also improving the supervision efficiency.

[0118] Embodiment Two

[0119] As Figure 2 shown, in the second embodiment of the present invention, a target object management system is provided. The system includes:

[0120] A screening module 1, configured to obtain target object information, and perform data cleaning and screening on the target object information to obtain key information;

[0121] An extraction module 2, configured to perform feature extraction on the key information to obtain target object category features;

[0122] A prediction module 3, configured to perform data prediction on the target object category features to obtain category information;

[0123] A management module 4, configured to perform evaluation analysis on the category information and output an evaluation result, calculate the supervision period of the target object information based on the evaluation result, and manage the target object based on the supervision period.

[0124] Among them, the screening module 1 includes:

[0125] A first calculation sub-module, configured to calculate the deviation value Z of the target object information:

[0126]

[0127] Wherein, x represents the x-th data in the target object information, and μ and σ respectively represent the sample mean and the sample standard deviation;

[0128] The elimination sub-module is used to eliminate the data with a deviation value greater than the preset deviation value from the target object information to obtain the elimination information;

[0129] The second calculation sub-module is used to calculate the first text proportion A in the elimination information 1 :

[0130]

[0131] Wherein, D t represents the number of times the word t appears in the document D, and D a represents the total number of words of the word t;

[0132] The third calculation sub-module is used to calculate the second text proportion A in the elimination information 2 :

[0133]

[0134] Wherein, N t represents the number of samples containing the word t, and N a represents all the number of samples;

[0135] The fourth calculation sub-module is used to calculate the text frequency B based on the first text proportion A 1 and the second text proportion A 2 : t :

[0136] B t = A 1 A 2 ;

[0137] The fifth calculation sub-module is used to calculate the text frequency of each text word in each document of the target object information, sort the text frequencies of each text word in a single document in descending order, and retain the text words corresponding to the first several text frequencies in each document of the target object information to obtain the key information.

[0138] The extraction module 2 includes:

[0139] The dimensionality reduction sub-module is used to perform dimensionality reduction processing on the feature space of the key information by using a dimensionality reduction algorithm to obtain the dimensionality reduction information;

[0140] The first clustering sub-module is used to select K data in the dimensionality reduction information as the initial clustering centers and calculate the clustering distances between each data in the dimensionality reduction information and the initial clustering centers;

[0141] The second clustering sub-module is used to allocate the data in the dimensionality-reduced information to the nearest initial clustering center according to the clustering distance to obtain initial clusters;

[0142] The third clustering sub-module is used to update the initial clustering center based on the data in the initial clusters, and iteratively perform the processes of data allocation and clustering center update until the clustering center no longer changes significantly, so as to output several clustering clusters;

[0143] The feature sub-module is used to determine the target object category features based on several of the clustering clusters in the first clustering.

[0144] The feature sub-module includes:

[0145] A calculation unit for calculating the importance degree WCSS of each data in the clustering cluster:

[0146]

[0147] In the formula, x i , y k respectively represent the i-th data in the k-th clustering cluster and the k-th clustering cluster;

[0148] A sorting unit for sorting each clustering cluster in descending order based on the importance degree WCSS to obtain the target object category features.

[0149] The prediction module 3 is specifically used for:

[0150] Obtain training data, input the training data into a preset prediction model for training, and input the target object category features into the trained preset prediction model for prediction to obtain category information.

[0151] The management module 4 includes:

[0152] The first matrix sub-module is used to determine each influencing factor in the category information and construct a judgment matrix based on historical category data;

[0153] The second matrix sub-module is used to perform hierarchical analysis on the judgment matrix to obtain a positive reciprocal matrix and perform hierarchical single sorting and consistency test on the positive reciprocal matrix to obtain a sorting matrix;

[0154] The weight sub-module is used to calculate the maximum eigenvalue and the corresponding eigenvector of the sorting matrix, sort the eigenvector in descending order, and sequentially determine the influence weights of each influencing factor according to the sorted eigenvector;

[0155] The scoring sub-module is used to calculate the comprehensive score S m :

[0156] S m = SUM (n＝1toN) w n × X mn ;

[0157] In the formula, N represents the number of influencing factors, w n represents the influence weight corresponding to the nth influencing factor, and X mn represents the data belonging to the nth influencing factor in the category information;

[0158] A cycle sub-module, for a first matrix sub-module, for determining a supervision cycle based on the comprehensive score.

[0159] In some other embodiments of the present invention, the embodiments of the present invention provide the following technical solution. A computer includes a memory 102, a processor 101, and a computer program stored on the memory 102 and executable on the processor 101. When the processor 101 executes the computer program, the target object management method as described above is implemented.

[0160] Specifically, the above-mentioned processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits implementing the embodiments of the present invention.

[0161] Among them, the memory 102 may include a mass storage for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 102 may include removable or non-removable (or fixed) media. In a suitable case, the memory 102 may be internal or external to the data processing device. In a particular embodiment, the memory 102 is a non-volatile memory. In a particular embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. In a suitable case, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0162] The memory 102 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 101.

[0163] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned target object management method.

[0164] In some of these embodiments, the computer may further include a communication interface 103 and a bus 100. Among them, as Figure 3 shown, the processor 101, the memory 102, and the communication interface 103 are connected through the bus 100 and complete communication with each other.

[0165] The communication interface 103 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present invention. The communication interface 103 can also implement data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0166] Bus 100 includes hardware, software, or both, and couples components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, Local Bus. By way of example and not limitation, Bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. In suitable cases, Bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0167] The computer may execute the target object management method of the present invention based on obtaining a target object management system, thereby implementing target object management.

[0168] In still some other embodiments of the present invention, in combination with the above target object management method, embodiments of the present invention provide the following technical solution: a storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the above target object management method.

[0169] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0170] More specific examples (non-exhaustive list) of the readable medium include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0171] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0172] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0173] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A target object management method, characterized in that: include: Acquire target object information, and perform data cleaning and screening on the target object information to obtain key information; Extracting features from the key information to obtain target object category features; Performing data prediction on the target object category features to obtain category information; The category information is evaluated and analyzed and an evaluation result is output; a supervision period of the target object information is calculated based on the evaluation result; and the target object is managed based on the supervision period.

2. The target object management method according to claim 1, characterized in that: The step of cleaning and screening the target object information to obtain key information includes: Calculate the deviation value Z of the target object information: In the formula, x represents the xth data in the target object information, μ and σ represent the sample mean and sample standard deviation respectively; Eliminate data with a deviation value greater than a preset deviation value from the target object information to obtain elimination information; Calculate the weight A1 of the first text in the rejection information: Where D t Indicates the number of times word t appears in document D, D a represents the total number of words in word t; Calculate the second text weight A2 in the rejection information: Where N t Represents the number of samples containing word t, N a Indicates the number of all samples; Calculate the text frequency B based on the first text weight A1 and the second text weight A2 t : B t =A1A2; The text frequency of each text word in each document in the target object information is calculated, and the text frequency of each text word in a single document is arranged in descending order, and the text words corresponding to the first several text frequencies in each document in the target object information are retained to obtain key information.

3. The target object management method according to claim 1, characterized in that: The step of extracting features from the key information to obtain target object category features includes: Using a dimensionality reduction algorithm to perform dimensionality reduction processing on the key information in feature space to obtain dimensionality reduction information; Select K data in the dimensionality reduction information as initial cluster centers, and calculate the cluster distance between each data in the dimensionality reduction information and the initial cluster center; And according to the clustering distance, the data in the dimension reduction information is assigned to the nearest initial clustering center to obtain an initial cluster; The initial cluster center is updated based on the data in the initial cluster, and the data distribution and cluster center update process are iterated until the cluster center no longer changes significantly, so as to output a plurality of clusters; A target object category feature is determined based on the plurality of clusters.

4. The target object management method according to claim 3, characterized in that: The step of determining the target object category features based on the plurality of clusters comprises: Calculate the importance WCSS of each data in the cluster: In the formula, x i ,y k Respectively represent the i-th data and the k-th cluster in the k-th cluster; Each cluster is arranged in descending order based on the importance WCSS to obtain the target object category feature.

5. The target object management method according to claim 3, characterized in that: The dimension reduction algorithm is specifically a PCA algorithm.

6. The target object management method according to claim 1, characterized in that: The step of performing data prediction on the target object category features to obtain category information comprises: The training data is obtained, the training data is input into a preset prediction model for training, and the target object category features are input into the trained preset prediction model for prediction to obtain category information.

7. The target object management method according to claim 1, characterized in that: The step of evaluating and analyzing the category information and outputting the evaluation result, and calculating the supervision period of the target object information based on the evaluation result comprises: Determine various influencing factors in the category information and construct a judgment matrix based on historical category data; Performing hierarchical analysis on the judgment matrix to obtain a positive reciprocal matrix, and performing hierarchical single sorting and consistency check on the positive reciprocal matrix to obtain a sorting matrix; Calculating the maximum eigenvalue and the corresponding eigenvector of the sorting matrix, arranging the eigenvectors in descending order, and determining the influence weight of each influencing factor in turn according to the arranged eigenvectors; Calculate the comprehensive score S based on the impact weight and the category information m : S m =SUM (n＝1toN) w n ×X mn ; In the formula, N represents the number of influencing factors, w n represents the influence weight corresponding to the nth influencing factor, X mn Indicates the data belonging to the nth influencing factor in the category information; A supervision period is determined based on the comprehensive score.

8. A target object management system, characterized in that: The system comprises: A screening module is used to obtain target object information, and perform data cleaning and screening on the target object information to obtain key information; An extraction module, used for extracting features from the key information to obtain target object category features; A prediction module, used to perform data prediction on the target object category features to obtain category information; The management module is used to evaluate and analyze the category information and output the evaluation result, calculate the supervision period of the target object information based on the evaluation result, and manage the target object based on the supervision period.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the target object management method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the target object management method according to any one of claims 1 to 7 is implemented.

Images