CN116451074B - Image generation method and device for target object, computer equipment and storage medium - Google Patents

Image generation method and device for target object, computer equipment and storage medium

Info

Publication number
CN116451074B
CN116451074B CN202310335774.9A CN202310335774A CN116451074B CN 116451074 B CN116451074 B CN 116451074B CN 202310335774 A CN202310335774 A CN 202310335774A CN 116451074 B CN116451074 B CN 116451074B
Authority
CN
China
Prior art keywords
data
feature
index data
target object
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310335774.9A
Other languages
Chinese (zh)
Other versions
CN116451074A (en
Inventor
颜丰
周隆慧
蔡长春
张冠榕
兰陈锦
谢锋
郑炀
陈庆武
林松平
张树东
邱旭凡
来泽齐
林红莲
王茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial Bank Co Ltd
CIB Fintech Services Shanghai Co Ltd
Original Assignee
Industrial Bank Co Ltd
CIB Fintech Services Shanghai Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industrial Bank Co Ltd, CIB Fintech Services Shanghai Co Ltd filed Critical Industrial Bank Co Ltd
Priority to CN202310335774.9A priority Critical patent/CN116451074B/en
Publication of CN116451074A publication Critical patent/CN116451074A/en
Application granted granted Critical
Publication of CN116451074B publication Critical patent/CN116451074B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/105—Human resources
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开涉及一种目标对象的画像生成方法、装置、计算机设备、存储介质。所述方法包括：获取至少一个目标对象的样本数据，确定所述样本数据中第一特征指标数据；至少利用所述第一特征指标数据进行聚类计算，确定聚类中心的中心特征值；计算所述中心特征值与预设的目标模型的模型特征值之间的偏差值，根据所述偏差值、所述第一特征指标数据和所述模型特征值，确定所述目标对象的标签数据，所述目标模型是根据目标位置的第三特征指标数据确定的，所述模型特征值是根据所述第三特征指标数据确定的；根据所述目标对象的标签数据生成所述目标对象的画像。采用本方法能够充分利用目标对象的各种数据，准确的生成画像。

This disclosure relates to a method, apparatus, computer device, and storage medium for generating a profile of a target object. The method includes: acquiring sample data of at least one target object; determining first feature index data in the sample data; performing clustering calculations using at least the first feature index data to determine the central feature values of the cluster centers; calculating the deviation between the central feature values and model feature values of a preset target model; determining label data of the target object based on the deviation value, the first feature index data, and the model feature values, wherein the target model is determined based on third feature index data of the target location, and the model feature values are determined based on the third feature index data; and generating a profile of the target object based on the label data. This method can fully utilize various data of the target object to accurately generate a profile.

Description

Image generation method and device for target object, computer equipment and storage medium
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for generating an image of a target object.
Background
With the development of information technology, many enterprises store various information of staff, such as working experience, working performance, working post, salary standard, etc., into the business system of the enterprise. In the development of enterprises, the capability index of each employee has become extremely important, especially in the process of personnel management and personnel recruitment.
At present, a manner of quantifying capability indexes of each employee is usually a talent portrait manner to realize matching of employee posts or to manage each employee in a targeted manner.
However, most of the current talent representation modes are written according to some experiences of managers of human resource management departments and information of some staff obtained according to requirements of the staff, a certain subjective factor often exists, and the talent representation is obtained only according to the information of some staff obtained according to the requirements of the staff, various data of the staff are not fully utilized, and the formed talent representation is inaccurate.
Disclosure of Invention
In view of the above, it is necessary to provide an image generating method, an image generating device, a computer device, and a storage medium, which can accurately generate an image by using various data of an employee.
In a first aspect, the present disclosure provides a method for generating an image of a target object, the method including:
Acquiring sample data of at least one target object, and determining first characteristic index data in the sample data;
Performing clustering calculation by at least utilizing the first characteristic index data, and determining a central characteristic value of a clustering center;
Calculating a deviation value between the central characteristic value and a model characteristic value of a preset target model, and determining label data of the target object according to the deviation value, the first characteristic index data and the model characteristic value, wherein the target model is determined according to third characteristic index data of a target position, and the model characteristic value is determined according to the third characteristic index data;
And generating the portrait of the target object according to the label data of the target object.
In one embodiment, the determining the central feature value of the cluster center by performing cluster calculation at least using the first feature index data includes:
Performing clustering calculation on the first characteristic index data to obtain a characteristic value of a clustering center corresponding to the first characteristic index data;
and determining the central characteristic value of the clustering center according to the characteristic value of the clustering center corresponding to the first characteristic index data.
In one embodiment, the determining the central feature value of the cluster center by performing cluster calculation at least using the first feature index data includes:
Determining second characteristic index data in the first characteristic index data, and determining residual characteristic index data except the second characteristic index data in the first characteristic index data, wherein the number of the second characteristic index data is smaller than that of the first characteristic index data;
Performing cluster calculation on the second characteristic index data to determine an initial characteristic value of an initial cluster center;
And determining a central characteristic value of the clustering center according to the initial characteristic value and the residual characteristic index data.
In one embodiment, the determining the central feature value of the cluster center according to the initial feature value and the residual feature index data includes:
calculating the similarity between the initial characteristic value and the residual characteristic index data;
distributing the residual characteristic index data to the data corresponding to the initial cluster center to obtain a first cluster in response to the similarity being smaller than a preset similarity threshold;
Calculating a first characteristic value of a first cluster center of the first cluster, and determining the first characteristic value as a center characteristic value of the cluster center in response to the similarity between the first characteristic value and the residual characteristic index data being smaller than a preset similarity threshold;
and in response to the similarity between the first characteristic value and the residual characteristic index data being greater than or equal to a preset similarity threshold, the residual characteristic index data are distributed to the data corresponding to the initial clustering center again until the similarity between the first characteristic value and the residual characteristic index data is smaller than the preset similarity threshold.
In one embodiment, before calculating the deviation value between the central eigenvalue and the model eigenvalue of the preset target model, the method further comprises:
And normalizing the first characteristic index data and the model characteristic value through a logarithmic change method.
In one embodiment, the determining the tag data of the target object according to the deviation value, the first feature index data and the model feature value includes:
Calculating a second deviation value between the first characteristic index data and the central characteristic value in response to the deviation value being smaller than a preset deviation threshold value, and determining a data score of the first characteristic index data according to the second deviation value;
And determining the tag data of the target object according to the data score of the first characteristic index data.
In one embodiment, the method further comprises adjusting the target model and/or reacquiring the sample data in response to the deviation value being greater than or equal to a preset deviation threshold.
In one embodiment, before the generating the portrait of the target object according to the tag data of the target object, the method further includes:
determining a type score corresponding to the target type according to the target type corresponding to the tag data of the target object and the data score of the first characteristic index data;
Correspondingly, the generating the portrait of the target object according to the label data of the target object comprises the following steps:
And generating the portrait of the target object according to the label data of the target object and the type score corresponding to the target type.
In one embodiment, after the generating the portrait of the target object according to the tag data of the target object, the method further includes:
Responsive to a need to search for a representation of the target object, searching for a representation of the target object using a distributed search and analysis engine.
In a second aspect, the present disclosure further provides an image generating apparatus of a target object, the apparatus including:
The data acquisition module is used for acquiring sample data of at least one target object and determining first characteristic index data in the sample data;
The clustering calculation module is used for carrying out clustering calculation by at least utilizing the first characteristic index data and determining a central characteristic value of a clustering center;
The tag data determining module is used for calculating a deviation value between the central characteristic value and a model characteristic value of a preset target model, determining tag data of the target object according to the deviation value, the first characteristic index data and the model characteristic value, wherein the target model is determined according to third characteristic index data of a target position, and the model characteristic value is determined according to the third characteristic index data;
And the portrait generation module is used for generating a portrait of the target object according to the label data of the target object.
In a third aspect, the present disclosure also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of any of the method embodiments described above when the processor executes the computer program.
In a fourth aspect, the present disclosure also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of any of the method embodiments described above.
In a fifth aspect, the present disclosure also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of any of the method embodiments described above.
In the above embodiments, the first characteristic index data in the sample data is determined by obtaining the sample data of at least one target object, and the sample data typically includes various data of the target object, so that the first characteristic index data in multiple directions can be determined. And clustering calculation can be further carried out on the first characteristic index data in multiple directions, the central characteristic value of the clustering center is determined, and the most accurate or standard central characteristic value of each type can be determined. Calculating a deviation value between the central characteristic value and a model characteristic value of a preset target model, and determining label data of the target object according to the deviation value, the first characteristic index data and the model characteristic value. The tag data of the target object can be determined using a plurality of types of first characteristic index data. Since the tag data is obtained by using the various data and the deviation value of the target object, the tag data can accurately reflect various conditions of the target object. Further, it is possible to accurately generate an image of the target object based on the tag data of the target object.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the prior art, the drawings that are required in the detailed description or the prior art will be briefly described, it will be apparent that the drawings in the following description are some embodiments of the present disclosure, and other drawings may be obtained according to the drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic view of an application environment of a target object representation generation method in one embodiment;
FIG. 2 is a flow diagram of a method of generating an image of a target object in one embodiment;
FIG. 3 is a flow chart of step S204 in one embodiment;
FIG. 4 is a flow chart of step S204 in one embodiment;
FIG. 5 is a flow chart of step S406 in one embodiment;
FIG. 6 is a flow chart of step S206 in one embodiment;
FIG. 7 is a schematic diagram of an image of a target object in one embodiment;
FIG. 8 is a schematic block diagram of an image generating device of a target object in one embodiment;
FIG. 9 is a schematic diagram of the internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more apparent, the present disclosure will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims herein and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or device.
In this document, the term "and/or" is merely one association relationship describing the associated object, meaning that three relationships may exist. For example, A and/or B may mean that A alone, both A and B, and B alone are present. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
The embodiment of the disclosure provides a portrait generation method of a target object, which can be applied to an application environment as shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may obtain sample data of at least one target object in the server 104. The terminal 102 may determine first characteristic index data in the sample data. The terminal 102 performs cluster calculation by using at least the first feature index data, and determines a central feature value of the cluster center. The terminal 102 may calculate a deviation value between the central feature value and a model feature value of a preset target model, and determine tag data of the target object according to the deviation value and the first feature index data. The target model may be determined by the server 104 or the terminal 102 based on third characteristic index data of the target location. The model feature values are determined from the third feature index data. The terminal 102 may generate an representation of the target object based on the tag data of the target object. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, etc. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a method for generating an image of a target object is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
S202, sample data of at least one target object are acquired, and first characteristic index data in the sample data are determined.
Wherein the target object may typically be an employee who needs to generate a representation. The representation may generally be a post representation in some embodiments of the present disclosure. In the process of screening talents by enterprises, establishing clear talent standards is an important link of talent planning, the clear talent standards are called post portraits in the enterprises, and the clear talent standards are accurate descriptions of staff which can generate high performance on key posts, and comprise dominant features (such as gender, age, knowledge, experience and tempering and the like) which can be directly observed and recessive features (such as characters, learning power, motivation and the like) which can not be directly observed. The sample data may generally be data including various information of the target object, such as a series of data of work performance, work years, wages, daily work hours, and the like. The first characteristic index data may be characteristic indexes in the sample data, such as behavior characteristic indexes, performance characteristic indexes, capability characteristic indexes, experience degrees and other characteristic indexes. For example, the sample data is a work performance, the first characteristic index data may be a performance index. According to the difference of the sample data, the first characteristic index data is different, in addition, the first characteristic index data can also comprise a plurality of different characteristic indexes, and the number and the type of the first characteristic indexes are not limited absolutely in some embodiments of the present disclosure.
Specifically, the terminal may determine the data source and the data interface according to different index extraction requirements, and obtain the sample data of the corresponding target object according to the data source and the data interface. And further determining first characteristic index data in the sample data.
In some exemplary embodiments, after the sample data is obtained, data cleaning may be further performed on the sample data, so as to determine first feature index data in the sample data after data cleaning, and remove the influence of invalid data.
S204, performing clustering calculation by at least utilizing the first characteristic index data, and determining a central characteristic value of a clustering center.
Wherein the cluster computation may generally be a way of cluster analysis. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster. The cluster center may be a center of a cluster obtained after performing a cluster calculation. The central feature value may generally reflect a feature trend of the target object. For example, the central feature value tends to be performance, or the central feature value tends to be personnel management, or the like.
Specifically, the clustering algorithm may be used to perform clustering calculation on the first feature index data, and then to the clustering center and the central feature value of the clustering center. The clustering algorithm may include K-MEANS, K-MEDOIDS, clara, and Clarans. The clustering algorithm used in clustering is not absolutely limited in some embodiments of the present disclosure. If the first feature index data is a plurality of different types, in a general case S206, calculating a deviation value between the central feature value and a model feature value of a preset target model, and determining tag data of the target object according to the deviation value, the first feature index data and the model feature value.
Wherein the target model is determined according to third characteristic index data of the target position, and the model characteristic value is determined according to the third characteristic index data. The target location may typically be a post that needs to be matched, such as a sales post, then its corresponding third characteristic index data may typically be performance data, responsible customer data, and so on. And each post to be matched has a corresponding target model. A plurality of model feature values may typically be included in the target model. And the model feature values may generally consist of one or more third feature index data. For example, a plurality of third feature index data combinations may result in a model feature value. A model feature value may also be obtained for a single third feature index data. The model characteristic value of the target model can be used for representing whether a certain target object can be qualified for the post, and ensuring that post personnel can successfully finish the characteristic value of the post work according to the post work requirement. For example, the post (target location) is a sales post, and its corresponding model feature index may be sales performance of 10w per month. Typically, this sales post is only adequate when a sales performance of 10w per month is reached. In addition, the model feature value type is usually required to be the same as the center feature value type, for example, the model feature value is a performance type, and the center feature value type is usually required to be a performance type.
In particular, a deviation value between the center feature value and each model feature value of the target model may be calculated. When the deviation value is relatively small, the tag data may be determined from the first characteristic index data and the model characteristic value. Each of the first characteristic index data typically corresponds to a different tag. When the deviation value between the first characteristic index data and the model characteristic value is small, the tag data of the target object can be determined according to the index corresponding to the first characteristic index data.
For example, each first characteristic index typically belongs to a large index type, e.g., the first characteristic index under a performance index may include performance data, customer data, etc. If the deviation value between the center feature value of the performance data and the model feature value is small, and the deviation value between the center feature value of the client data and another model feature value is small, it can be determined that the performance capability stands out as the tag data of the target object.
It will be appreciated that the manner in which the bias values are calculated is not an absolute limitation in some embodiments of the present disclosure, and may be, for example, calculated using the center feature value minus the model feature value, or may be calculated using some other manner, such as, for example, using the center feature value minus the average of the center feature values divided by the model feature value minus the average of the model feature values.
S208, generating an image of the target object according to the label data of the target object.
Specifically, the image of the target object may be generated using the tag data of the target object determined as described above.
In the image generation method of the target object, the first characteristic index data in the sample data is determined by acquiring the sample data of at least one target object, and the sample data generally includes various data of the target object, so that the first characteristic index data in multiple directions can be determined. And clustering calculation can be further carried out on the first characteristic index data in multiple directions, the central characteristic value of the clustering center is determined, and the most accurate or standard central characteristic value of each type can be determined. Calculating a deviation value between the central characteristic value and a model characteristic value of a preset target model, and determining label data of the target object according to the deviation value, the first characteristic index data and the model characteristic value. The tag data of the target object can be determined using a plurality of types of first characteristic index data. Since the tag data is obtained by using the various data and the deviation value of the target object, the tag data can accurately reflect various conditions of the target object. Further, it is possible to accurately generate an image of the target object based on the tag data of the target object.
In one embodiment, as shown in fig. 3, the performing cluster calculation by using at least the first feature index data, determining a central feature value of a cluster center includes:
s302, carrying out clustering calculation on the first characteristic index data to obtain a characteristic value of a clustering center corresponding to the first characteristic index data;
s304, determining the central characteristic value of the clustering center according to the characteristic value of the clustering center corresponding to the first characteristic index data.
Specifically, the first feature index data of each type may be subjected to clustering calculation, so as to obtain a feature value of a clustering center of the first feature index data of each type. And then determining the central characteristic value of the clustering center of each type according to the characteristic value of each type obtained through calculation.
In another case, as shown in fig. 4, the determining the central feature value of the cluster center by performing cluster calculation at least using the first feature index data includes:
S402, determining second characteristic index data in the first characteristic index data, and determining residual characteristic index data except the second characteristic index data in the first characteristic index data, wherein the number of the second characteristic index data is smaller than that of the first characteristic index data.
S404, performing cluster calculation on the second characteristic index data, and determining an initial characteristic value of an initial cluster center.
S406, determining a central characteristic value of the clustering center according to the initial characteristic value and the residual characteristic index data.
Specifically, a certain number of first characteristic index data may be selected from the first characteristic index data, and the certain number of first characteristic index data may be the second characteristic index data. In some embodiments of the present disclosure, the certain data is not limited, and the certain amount may be determined according to the amount of the first characteristic index data. And then determining the rest characteristic index data except the second characteristic index data in the first characteristic index data. And then carrying out clustering calculation on the second characteristic index data, and determining a central characteristic value of the initial clustering center obtained after the clustering calculation. And then, determining the central characteristic value of the clustering center according to the initial characteristic value and the residual characteristic index data obtained through calculation. For example, the feature value of the cluster center of the remaining feature index data may be calculated, and the center feature value of the cluster center may be determined from the relationship between the initial feature value and the feature value of the cluster center of the remaining feature index data. For example, if the difference between the initial feature value and the feature value of the cluster center of the remaining feature index data is greater than a preset difference threshold, it may be generally proven that the initial feature value and/or the remaining feature index data are unreasonable, and the second feature index data needs to be reselected, so as to recalculate the initial feature value and/or the remaining feature index data. If the difference is smaller than a preset difference threshold, the initial characteristic value and/or the characteristic value of the clustering center of the residual characteristic index data can be determined as a central characteristic value. The initial characteristic value may generally correspond to the type of the second characteristic index data, for example, the second characteristic index data is two types of data, and each type of second characteristic index data may generally obtain a corresponding initial characteristic value.
In some exemplary embodiments, for example, the first feature index data is A, B, C and D, C and D may be selected as the second feature index data, the remaining feature index data may be a and B, and initial feature values of C and D may be calculated, respectively, to thereby determine a central feature value of the cluster center according to the initial feature values and the remaining feature index data.
In this embodiment, by determining the central feature value of the clustering center by using two different modes, different modes can be selected under different conditions, so that the calculation efficiency or the accuracy of the central feature value can be improved, and the label data obtained by subsequent calculation is more accurate.
In one embodiment, as shown in fig. 5, the determining the central feature value of the cluster center according to the initial feature value and the residual feature index data includes:
s502, calculating the similarity between the initial characteristic value and the residual characteristic index data;
s504, judging whether the similarity is smaller than a preset similarity threshold value.
S506, distributing the residual characteristic index data to the data corresponding to the initial clustering center to obtain a first cluster in response to the similarity being smaller than a preset similarity threshold;
S508, calculating a first characteristic value of a first cluster center of the first cluster, and determining the first characteristic value as a center characteristic value of the cluster center in response to the similarity between the first characteristic value and the residual characteristic index data being smaller than a preset similarity threshold;
S510, in response to the similarity between the first characteristic value and the residual characteristic index data being greater than or equal to a preset similarity threshold, the residual characteristic index data is distributed to the data corresponding to the initial clustering center again until the similarity between the first characteristic value and the residual characteristic index data is smaller than the preset similarity threshold.
The similarity may be calculated by euclidean distance, cosine similarity, pearson correlation coefficient, and the like.
Specifically, the similarity between the initial feature value and each of the remaining feature index data may be calculated. And then judging whether the calculated similarity is smaller than a preset similarity threshold value. The similarity threshold may be set by those skilled in the art according to the actual situation, and is not limited in this disclosure. When the calculated similarity is smaller than a preset similarity threshold, the initial characteristic value and the residual characteristic index data can be determined to be relatively related, so that the residual characteristic index data can be distributed to the second characteristic data calculated to obtain the initial characteristic value, and the first cluster is obtained after distribution. The first cluster center of the obtained first cluster can be calculated through a clustering algorithm, and a first characteristic value of the first cluster center. And calculating the similarity between the first characteristic value and the residual characteristic index again, and determining that the obtained first cluster after the residual characteristic index data are distributed is reasonable when the similarity is smaller than a preset similarity threshold value, wherein the first characteristic value of the first cluster center can be determined to be the central characteristic value of the cluster center. When the similarity between the first feature value and the residual feature index is greater than or equal to a preset similarity threshold, it can be determined that the obtained first cluster after the residual feature index data are distributed is unreasonable, and at the moment, the data deviation degree in the first cluster may be relatively large, so that the residual feature index data need to be redistributed, the first cluster is obtained again after distribution, the first feature value of the first cluster is recalculated until the similarity between the first feature value and the residual feature index data is smaller than the preset similarity threshold, and then the central feature value is obtained.
In some exemplary embodiments, for example, the initial feature value of the initial cluster center is S1, the remaining feature index data may be a and B, and the data corresponding to the initial cluster center (second feature index data) may be C and D. The similarity between S1 and a, and between S1 and B may be calculated, respectively, and if the similarity obtained respectively may be 5 and 6. When the similarity threshold is 7, the similarity between S1 and a is 5, the similarity between S1 and B is 6, and both are smaller than the similarity threshold, the remaining feature index data a and B may be assigned to the second feature index data, so as to obtain the first cluster. A, B, C and D may be included in the first cluster. Then at this point a first eigenvalue S2 of the first cluster center of the first cluster may be calculated. And respectively calculating the similarity between S2 and A, S and the similarity between B and S2, respectively, obtaining that the similarity can be 3 and 4 respectively and is smaller than a similarity threshold value, and determining the first characteristic value S2 as a central characteristic value of the clustering center.
If the initial feature values of the initial cluster center are S1 and S2, the second feature index data corresponding to the initial feature value S1 of the initial cluster center may be C, and the second feature index data corresponding to the initial feature value S2 of the initial cluster center may be D. The remaining characteristic index data may be a and B. The similarity between S1 and a, S1 and B, and the similarity between S2 and a, S2 and B can be calculated, respectively. If the similarity between S1 and A is 5, the similarity between S1 and B is 10. The similarity between S2 and a is 6, and the similarity between S2 and B is 6. In the case where the similarity threshold is 7, the remaining index data a may be assigned to C, and the remaining index data B may be assigned to D. A and C may be the first cluster, and B and D may also be the first cluster. Then, a first eigenvalue of a first cluster center of the first cluster of a and C may be calculated, and a similarity between the first eigenvalue and the remaining index data a and the remaining index data B may be calculated. When the similarity between the first feature value and the remaining index data a is 7, the remaining index data a needs to be reassigned, the remaining index data a may be assigned to D, A, B and D may be the first clusters, and then the first feature value of the cluster center of the first clusters of A, B and D is calculated. And further calculating the similarity between the first characteristic value and the residual index data A, and determining the first characteristic value as a central characteristic value of the clustering center when the similarity is 5.
In this embodiment, the remaining feature index data is assigned to the second feature index data by using the similarity, and the remaining feature index data can be reassigned under the condition that the similarity threshold is not satisfied, so that accurate clustering of various feature index data can be realized, and a central feature value of a clustering center can be accurately obtained.
In one embodiment, before calculating the deviation value between the central feature value and the model feature value of the preset target model, the method further includes:
And normalizing the first characteristic index data and the model characteristic value through a logarithmic change method.
The logarithmic transformation method may be a logarithmic transformation (log transformation), among others. Logarithmic transformation is a special way of transforming data that can transform a class of theoretically unresolved model problems into one that has been resolved. The reason for taking the logarithm of the data is based on the fact that the logarithm function is a monotonically increasing function within its defined domain. The relative relationship of the data is not changed after taking the logarithm. Their main effect is that it helps stabilize the variance, always keeping the distribution close to normal and making the data independent of the mean of the distribution.
Specifically, in order to eliminate the long tail effect that the first characteristic index data and the model characteristic value may be due to extreme, the first characteristic index data and the model characteristic value may be normalized using a logarithmic variation method
In the embodiment, the absolute value of the data can be reduced by using a logarithmic change method, so that the calculation is convenient. In addition, in some cases, the influence of the difference between the unused sections in the entire value domain of the data is different. In addition, after taking the logarithm, the property and the correlation of the data are not changed.
In one embodiment, as shown in fig. 6, the determining the tag data of the target object according to the deviation value, the first feature index data and the model feature value includes:
s602, judging whether the deviation value is larger than a preset deviation threshold value.
S604, in response to the deviation value being smaller than a preset deviation threshold, calculating a second deviation value between the first characteristic index data and the central characteristic value, and determining a data score of the first characteristic index data according to the second deviation value.
S606, determining the label data of the target object according to the data score of the first characteristic index data.
Specifically, a relationship between the deviation value and a preset deviation threshold value may be determined. When the deviation value is smaller than a preset deviation threshold value, it can be determined that the correlation between the first characteristic index data and the model characteristic value is strong. I.e. the first characteristic index data more closely corresponds to the target position. A second deviation value between the first characteristic index data and its corresponding central characteristic value may thus be calculated. A data score for the first characteristic index data is then determined based on the second bias value. For example, if the second deviation value is relatively high, the data score of the corresponding first characteristic index data is typically low. If the second deviation value is relatively low, the data score of the corresponding first characteristic index data is typically relatively high.
In addition, the tag data of the target object may be obtained by accumulating the data scores of all the first characteristic index data of each type. The tag data may be, for example, xxx capable, xxx empirical. For example, the first characteristic index data is a performance index and a client index, and the scores of the performance index and the client index are relatively high, namely 80 and 85, respectively, 165 points are accumulated, 165 points can be compared with a preset standard score threshold 120, and the score is larger than 120 points, so that the label data of a target object can be "the performance capability is excellent, and the client acceptance is high". It is to be understood that the foregoing is only illustrative.
And S608, adjusting the target model and/or reacquiring the sample data in response to the deviation value being greater than or equal to a preset deviation threshold.
Specifically, when the deviation value is equal to or greater than the deviation threshold value set in advance, it can be determined that the deviation value is large. There are two possibilities that the deviation is large, one is the problem of sampling sample data, i.e., the error in obtaining sample data of the target object, at which time the sample data can be re-obtained. Another possibility is that the model feature values of the target model have not met the current data requirements, and the appropriate model features are adjusted by the bias conditions. However, in general, the enterprise has a very clear model feature value of the target model of its own target location. Therefore, it is common to re-acquire the sample data.
In the present embodiment, when the deviation value is relatively small, it can be demonstrated that the correlation between the first characteristic index data and the model characteristic value is relatively strong. Therefore, the first characteristic index data can be determined to be used for determining the tag data, and the second deviation value between the first characteristic index data and the central characteristic value can be calculated to accurately determine the deviation between the first characteristic index data and the central characteristic value, so that the tag data of the target object can be accurately determined according to the second deviation value.
In one embodiment, before the generating the representation of the target object according to the tag data of the target object, the method further includes:
determining a type score corresponding to the target type according to the target type corresponding to the tag data of the target object and the data score of the first characteristic index data;
Correspondingly, the generating the portrait of the target object according to the label data of the target object comprises the following steps:
And generating the portrait of the target object according to the label data of the target object and the type score corresponding to the target type.
Among other things, the target type may generally be various different types of capabilities of the target object, such as various aspects of experience, contribution, innovation, expertise, and so forth.
Specifically, each tag data of the target object usually belongs to a target type (experience degree, professional force, innovation force and contribution degree), each tag data has a corresponding score, the type scores of the target types can be finally accumulated, or each tag data can be multiplied by a corresponding weight and added to obtain the type score of each target type.
As shown in FIG. 7, a representation of the target object may then be generated based on the tag data and the type score. In the process of generating the portrait of the target object, a scatter diagram component can be introduced, label data are stacked for visual presentation in a word cloud diagram mode, and the display effect is improved in a random font color mode. In addition, a multi-dimensional radar map may be generated for the type scores of the target types.
In this embodiment, the type score corresponding to the target column of the target object is determined by the tag data of the target object, so that the data of each aspect of the target object can be determined more accurately, and the generated image of the target object can reflect various index capabilities of the target object more accurately.
In one embodiment, after the generating the representation of the target object according to the tag data of the target object, the method further comprises:
Responsive to a need to search for a representation of the target object, searching for a representation of the target object using a distributed search and analysis engine.
Wherein the distributed search and analysis engine may typically be ES (Elasticsearch) smart search engine. The elastomer search is a Lucene-based search server that provides a distributed full text search capability.
Specifically, when there are many target objects and the sample data of the target objects are large, the tag data in the image of the target object is large. Tag data is continuously accumulated and accumulated, and a large number of search requirements for dynamic combination cannot be met only by means of a traditional relational database, so that an elastic search distributed search and analysis engine is introduced. When the portrait of a target object needs to be searched, all the tag data are set as indexes and can be searched, and then the database server is in butt joint with the RESTful web interface, so that the search requirements of user hundred percent user definition and high-speed stability can be met.
In the embodiment, the real-time search can be achieved by using the elastic search distributed search and analysis engine, and the portrait target of the corresponding target object can be obtained stably, reliably and quickly by using the tag data.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the disclosure also provides an image generating device of the target object for realizing the image generating method of the target object. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the image generating device for one or more target objects provided below may refer to the limitation of the image generating method for the target object hereinabove, and will not be repeated herein.
In one embodiment, as shown in FIG. 8, there is provided a representation generation apparatus 800 of a target object, comprising a data acquisition module 802, a cluster calculation module 804, a tag data determination module 806, and a representation generation module 808, wherein:
The data acquisition module 802 is configured to acquire sample data of at least one target object, and determine first feature index data in the sample data.
The cluster calculation module 804 is configured to perform cluster calculation by using at least the first feature index data, and determine a central feature value of a cluster center.
The tag data determining module 806 is configured to calculate a deviation value between the central feature value and a model feature value of a preset target model, determine tag data of the target object according to the deviation value, the first feature index data, and the model feature value, where the target model is determined according to third feature index data of a target position, and the model feature value is determined according to the third feature index data.
And a portrait generation module 808 for generating a portrait of the target object according to the tag data of the target object.
In one embodiment of the apparatus, the cluster calculation module 804 is further configured to perform cluster calculation on the first feature index data to obtain a feature value of a cluster center corresponding to the first feature index data, determine a center feature value of the cluster center according to the feature value of the cluster center corresponding to the first feature index data
In one embodiment of the apparatus, the cluster calculation module 804 includes:
The index data determining module is used for determining second characteristic index data in the first characteristic index data and determining residual characteristic index data except the second characteristic index data in the first characteristic index data, wherein the number of the second characteristic index data is smaller than that of the first characteristic index data.
And the cluster calculation sub-module is used for carrying out cluster calculation on the second characteristic index data and determining an initial characteristic value of an initial cluster center.
And the central characteristic value determining module is used for determining the central characteristic value of the clustering center according to the initial characteristic value and the residual characteristic index data.
In one embodiment of the apparatus, the central feature value determining module includes:
and the similarity calculation module is used for calculating the similarity between the initial characteristic value and the residual characteristic index data.
And the first clustering module is used for responding to the fact that the similarity is smaller than a preset similarity threshold value, distributing the residual characteristic index data to the data corresponding to the initial clustering center, and obtaining a first cluster.
The characteristic value determining module is used for calculating a first characteristic value of a first cluster center of the first cluster, and determining the first characteristic value as a center characteristic value of the cluster center in response to the fact that the similarity between the first characteristic value and the residual characteristic index data is smaller than a preset similarity threshold value.
And the secondary distribution module is used for responding to the fact that the similarity between the first characteristic value and the residual characteristic index data is larger than or equal to a preset similarity threshold value, and distributing the residual characteristic index data to the data corresponding to the initial clustering center again until the similarity between the first characteristic value and the residual characteristic index data is smaller than the preset similarity threshold value.
In one embodiment of the apparatus, the apparatus further comprises a normalization processing module for normalizing the first characteristic index data and the model characteristic values by a logarithmic change method.
In one embodiment of the apparatus, the tag data determining module 806 is further configured to calculate a second deviation value between the first characteristic index data and the central characteristic value in response to the deviation value being smaller than a preset deviation threshold, determine a data score of the first characteristic index data according to the second deviation value, and determine tag data of the target object according to the data score of the first characteristic index data.
In one embodiment of the apparatus, the apparatus further includes a type score determining module configured to determine a type score corresponding to the target type according to a target type corresponding to tag data of the target object and a data score of the first feature index data.
The portrait generation module 808 is further configured to generate a portrait of the target object according to tag data of the target object and a type score corresponding to the target type.
In one embodiment of the apparatus, the apparatus further comprises a search module for searching for the representation of the target object using a distributed search and analysis engine in response to a need to search for the representation of the target object.
The modules in the image generating device for the target object may be all or partially implemented by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 9. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer 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 computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method for generating an image of a target object. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the disclosed aspects and is not limiting of the computer device to which the disclosed aspects apply, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of any of the method embodiments described above when the computer program is executed.
In one embodiment, a computer readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements the steps of any of the method embodiments described above.
In an embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, implements the steps of any of the method embodiments described above.
It should be noted that, the sample data of the target object related to the disclosure are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided by the present disclosure may include at least one of non-volatile and volatile memory, among others. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the various embodiments provided by the present disclosure may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors involved in the embodiments provided by the present disclosure may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic, quantum computing-based data processing logic, etc., without limitation thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples have expressed only a few embodiments of the present disclosure, which are described in more detail and detail, but are not to be construed as limiting the scope of the present disclosure. It should be noted that variations and modifications can be made by those skilled in the art without departing from the spirit of the disclosure, which are within the scope of the disclosure. Accordingly, the scope of the present disclosure should be determined from the following claims.

Claims (12)

1.一种目标对象的画像生成方法，其特征在于，所述方法包括：1. A method for generating a portrait of a target object, characterized in that the method includes: 获取至少一个目标对象的样本数据，确定所述样本数据中第一特征指标数据；Obtain sample data of at least one target object, and determine the first feature index data in the sample data; 至少利用所述第一特征指标数据进行聚类计算，确定聚类中心的中心特征值；At least the first feature index data is used to perform clustering calculations to determine the central feature values of the cluster centers; 计算所述中心特征值与预设的目标模型的模型特征值之间的偏差值，根据所述偏差值、所述第一特征指标数据和所述模型特征值，确定所述目标对象的标签数据，所述目标模型是根据目标位置的第三特征指标数据确定的，所述模型特征值是根据所述第三特征指标数据确定的；Calculate the deviation between the central feature value and the model feature value of the preset target model. Based on the deviation value, the first feature index data, and the model feature value, determine the label data of the target object. The target model is determined based on the third feature index data of the target location, and the model feature value is determined based on the third feature index data. 根据所述目标对象的标签数据生成所述目标对象的画像；Generate a profile of the target object based on the target object's tag data; 其中，所述至少利用所述第一特征指标数据进行聚类计算，确定聚类中心的中心特征值，包括：Wherein, the step of performing clustering calculations using at least the first feature index data to determine the central feature values of the cluster centers includes: 在所述第一特征指标数据中确定第二特征指标数据，并确定所述第一特征指标数据中除第二特征指标数据外的剩余特征指标数据，其中，所述第二特征指标数据的数量小于第一特征指标数据的数量；Determine second feature index data from the first feature index data, and determine the remaining feature index data in the first feature index data excluding the second feature index data, wherein the number of second feature index data is less than the number of first feature index data. 对所述第二特征指标数据进行聚类计算，确定初始聚类中心的初始特征值；Clustering calculations are performed on the second feature index data to determine the initial feature values of the initial cluster centers; 根据所述初始特征值和所述剩余特征指标数据，确定聚类中心的中心特征值，包括：计算所述初始特征值和所述剩余特征指标数据之间的相似度；响应于所述相似度小于预设的相似度阈值，将所述剩余特征指标数据分配给所述初始聚类中心对应的数据，得到第一聚类；计算所述第一聚类的第一聚类中心的第一特征值，响应于所述第一特征值与所述剩余特征指标数据之间的相似度小于预设的相似度阈值，确定所述第一特征值为聚类中心的中心特征值；响应于所述第一特征值与所述剩余特征指标数据之间的相似度大于等于预设的相似度阈值，重新将所述剩余特征指标数据分配给所述初始聚类中心对应的数据，直至所述第一特征值与所述剩余特征指标数据之间的相似度小于预设的相似度阈值；Determining the center feature value of a cluster center based on the initial feature value and the remaining feature index data includes: calculating the similarity between the initial feature value and the remaining feature index data; in response to the similarity being less than a preset similarity threshold, assigning the remaining feature index data to the data corresponding to the initial cluster center to obtain a first cluster; calculating the first feature value of the first cluster center of the first cluster; in response to the similarity between the first feature value and the remaining feature index data being less than a preset similarity threshold, determining the first feature value as the center feature value of the cluster center; in response to the similarity between the first feature value and the remaining feature index data being greater than or equal to a preset similarity threshold, reassigning the remaining feature index data to the data corresponding to the initial cluster center until the similarity between the first feature value and the remaining feature index data is less than a preset similarity threshold; 所述根据所述偏差值、所述第一特征指标数据和所述模型特征值，确定所述目标对象的标签数据，包括：The step of determining the label data of the target object based on the deviation value, the first feature index data, and the model feature value includes: 响应于所述偏差值小于预先设置的偏差阈值，计算所述第一特征指标数据和所述中心特征值之间的第二偏差值，根据所述第二偏差值确定所述第一特征指标数据的数据分值；In response to the deviation value being less than a preset deviation threshold, a second deviation value is calculated between the first feature index data and the central feature value, and the data score of the first feature index data is determined based on the second deviation value. 根据所述第一特征指标数据的数据分值，确定所述目标对象的标签数据；The label data of the target object is determined based on the data score of the first feature index data; 所述根据所述目标对象的标签数据生成所述目标对象的画像之前，所述方法还包括：Before generating the profile of the target object based on the tag data of the target object, the method further includes: 根据所述目标对象的标签数据对应的目标类型和所述第一特征指标数据的数据分值，确定所述目标类型对应的类型分值；Based on the target type corresponding to the label data of the target object and the data score of the first feature index data, the type score corresponding to the target type is determined; 相应的，所述根据所述目标对象的标签数据生成所述目标对象的画像，包括：Accordingly, generating a profile of the target object based on the target object's tag data includes: 根据所述目标对象的标签数据和所述目标类型对应的类型分值，生成所述目标对象的画像。A profile of the target object is generated based on the tag data of the target object and the type score corresponding to the target type. 2.根据权利要求1所述的方法，其特征在于，所述至少利用所述第一特征指标数据进行聚类计算，确定聚类中心的中心特征值，包括：2. The method according to claim 1, wherein the step of performing clustering calculations using at least the first feature index data to determine the central feature values of the cluster centers includes: 对所述第一特征指标数据进行聚类计算，得到所述第一特征指标数据对应的聚类中心的特征值；Clustering calculations are performed on the first feature index data to obtain the feature values of the cluster centers corresponding to the first feature index data. 根据第一特征指标数据对应的聚类中心的特征值，确定聚类中心的中心特征值。Based on the feature values of the cluster centers corresponding to the first feature index data, the central feature values of the cluster centers are determined. 3.根据权利要求1所述的方法，其特征在于，所述计算所述中心特征值与预设的目标模型的模型特征值之间的偏差值之前，所述方法还包括：3. The method according to claim 1, characterized in that, before calculating the deviation between the central feature value and the model feature value of the preset target model, the method further includes: 通过对数变化法对所述第一特征指标数据和所述模型特征值进行正态化处理。The first feature index data and the model feature values are normalized using the logarithmic transformation method. 4.根据权利要求1所述的方法，其特征在于，所述方法还包括：响应于所述偏差值大于等于预先设置的偏差阈值，调整所述目标模型和/或重新获取所述样本数据。4. The method according to claim 1, wherein the method further comprises: adjusting the target model and/or reacquiring the sample data in response to the deviation value being greater than or equal to a preset deviation threshold. 5.根据权利要求1所述的方法，其特征在于，所述根据所述目标对象的标签数据生成所述目标对象的画像之后，所述方法还包括：5. The method according to claim 1, characterized in that, after generating the portrait of the target object based on the tag data of the target object, the method further includes: 响应于需要搜索所述目标对象的画像，利用分布式搜索与分析引擎搜索所述目标对象的画像。In response to the need to search for the profile of the target object, a distributed search and analysis engine is used to search for the profile of the target object. 6.一种目标对象的画像生成装置，其特征在于，所述装置包括：6. A portrait generation device for a target object, characterized in that the device comprises: 数据获取模块，用于获取至少一个目标对象的样本数据，确定所述样本数据中第一特征指标数据；The data acquisition module is used to acquire sample data of at least one target object and determine the first feature index data in the sample data; 聚类计算模块，用于至少利用所述第一特征指标数据进行聚类计算，确定聚类中心的中心特征值；The clustering calculation module is used to perform clustering calculations using at least the first feature index data to determine the central feature value of the cluster center; 标签数据确定模块，用于计算所述中心特征值与预设的目标模型的模型特征值之间的偏差值，根据所述偏差值、所述第一特征指标数据和所述模型特征值，确定所述目标对象的标签数据，所述目标模型是根据目标位置的第三特征指标数据确定的，所述模型特征值是根据所述第三特征指标数据确定的；The label data determination module is used to calculate the deviation value between the central feature value and the model feature value of the preset target model, and determine the label data of the target object based on the deviation value, the first feature index data and the model feature value. The target model is determined based on the third feature index data of the target location, and the model feature value is determined based on the third feature index data. 画像生成模块，用于根据所述目标对象的标签数据生成所述目标对象的画像；The profile generation module is used to generate a profile of the target object based on the tag data of the target object. 其中，所述聚类计算模块，包括：The clustering calculation module includes: 指标数据确定模块，用于在所述第一特征指标数据中确定第二特征指标数据，并确定所述第一特征指标数据中除第二特征指标数据外的剩余特征指标数据，其中，所述第二特征指标数据的数量小于第一特征指标数据的数量；The indicator data determination module is used to determine the second characteristic indicator data in the first characteristic indicator data, and to determine the remaining characteristic indicator data in the first characteristic indicator data excluding the second characteristic indicator data, wherein the number of the second characteristic indicator data is less than the number of the first characteristic indicator data. 聚类计算子模块，用于对所述第二特征指标数据进行聚类计算，确定初始聚类中心的初始特征值；The clustering calculation submodule is used to perform clustering calculations on the second feature index data to determine the initial feature values of the initial cluster centers. 中心特征值确定模块，用于根据所述初始特征值和所述剩余特征指标数据，确定聚类中心的中心特征值；The center feature value determination module is used to determine the center feature value of the cluster center based on the initial feature value and the remaining feature index data; 所述中心特征值确定模块，包括：The central feature value determination module includes: 相似度计算模块，用于计算所述初始特征值和所述剩余特征指标数据之间的相似度；The similarity calculation module is used to calculate the similarity between the initial feature value and the remaining feature index data; 第一聚类模块，用于响应于所述相似度小于预设的相似度阈值，将所述剩余特征指标数据分配给所述初始聚类中心对应的数据，得到第一聚类；The first clustering module is used to allocate the remaining feature index data to the data corresponding to the initial cluster center in response to the similarity being less than a preset similarity threshold, thereby obtaining the first cluster; 特征值确定模块，用于计算所述第一聚类的第一聚类中心的第一特征值，响应于所述第一特征值与所述剩余特征指标数据之间的相似度小于预设的相似度阈值，确定所述第一特征值为聚类中心的中心特征值；The feature value determination module is used to calculate the first feature value of the first cluster center of the first cluster, and in response to the fact that the similarity between the first feature value and the remaining feature index data is less than a preset similarity threshold, the first feature value is determined to be the center feature value of the cluster center. 二次分配模块，用于响应于所述第一特征值与所述剩余特征指标数据之间的相似度大于等于预设的相似度阈值，重新将所述剩余特征指标数据分配给所述初始聚类中心对应的数据，直至所述第一特征值与所述剩余特征指标数据之间的相似度小于预设的相似度阈值；The secondary allocation module is used to reassign the remaining feature index data to the data corresponding to the initial cluster center in response to the similarity between the first feature value and the remaining feature index data being greater than or equal to a preset similarity threshold, until the similarity between the first feature value and the remaining feature index data is less than the preset similarity threshold. 所述标签数据确定模块，还用于响应于所述偏差值小于预先设置的偏差阈值，计算所述第一特征指标数据和所述中心特征值之间的第二偏差值，根据所述第二偏差值确定所述第一特征指标数据的数据分值；根据所述第一特征指标数据的数据分值，确定所述目标对象的标签数据；The label data determination module is further configured to, in response to the deviation value being less than a preset deviation threshold, calculate a second deviation value between the first feature index data and the central feature value, determine the data score of the first feature index data based on the second deviation value, and determine the label data of the target object based on the data score of the first feature index data; 类型分值确定模块，用于根据所述目标对象的标签数据对应的目标类型和所述第一特征指标数据的数据分值，确定所述目标类型对应的类型分值；The type score determination module is used to determine the type score corresponding to the target type based on the target type corresponding to the tag data of the target object and the data score of the first feature index data; 相应的，所述画像生成模块，还用于根据所述目标对象的标签数据和所述目标类型对应的类型分值，生成所述目标对象的画像。Accordingly, the portrait generation module is also used to generate a portrait of the target object based on the tag data of the target object and the type score corresponding to the target type. 7.根据权利要求6所述的装置，其特征在于，所述聚类计算模块，还用于对所述第一特征指标数据进行聚类计算，得到所述第一特征指标数据对应的聚类中心的特征值；根据第一特征指标数据对应的聚类中心的特征值，确定聚类中心的中心特征值。7. The apparatus according to claim 6, wherein the clustering calculation module is further configured to perform clustering calculation on the first feature index data to obtain the feature values of the cluster centers corresponding to the first feature index data; and determine the center feature value of the cluster center based on the feature value of the cluster center corresponding to the first feature index data. 8.根据权利要求6所述的装置，其特征在于，所述装置还包括：8. The apparatus according to claim 6, wherein the apparatus further comprises: 正态化处理模块，用于通过对数变化法对所述第一特征指标数据和所述模型特征值进行正态化处理。The normalization module is used to perform normalization processing on the first feature index data and the model feature values using the logarithmic transformation method. 9.根据权利要求6所述的装置，其特征在于，所述装置还包括：9. The apparatus according to claim 6, characterized in that the apparatus further comprises: 搜索模块，用于响应于需要搜索所述目标对象的画像，利用分布式搜索与分析引擎搜索所述目标对象的画像。The search module is used to search for the profile of the target object using a distributed search and analysis engine in response to the need to search for the profile of the target object. 10.一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至5中任一项所述的方法的步骤。10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5. 11.一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至5中任一项所述的方法的步骤。11. A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5. 12.一种计算机程序产品，包括计算机程序，其特征在于，该计算机程序被处理器执行时实现权利要求1至5中任一项所述的方法的步骤。12. A computer program product comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 5.
CN202310335774.9A 2023-03-31 2023-03-31 Image generation method and device for target object, computer equipment and storage medium Active CN116451074B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310335774.9A CN116451074B (en) 2023-03-31 2023-03-31 Image generation method and device for target object, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310335774.9A CN116451074B (en) 2023-03-31 2023-03-31 Image generation method and device for target object, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116451074A CN116451074A (en) 2023-07-18
CN116451074B true CN116451074B (en) 2026-01-13

Family

ID=87133005

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310335774.9A Active CN116451074B (en) 2023-03-31 2023-03-31 Image generation method and device for target object, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116451074B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116680590B (en) * 2023-07-28 2023-10-20 中国人民解放军国防科技大学 Post portrait label extraction method and device based on work instruction analysis
CN120355043A (en) * 2025-06-24 2025-07-22 杭州聚玻科技有限公司 Product supply chain portrait generation and product resource optimization method, system and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023168966A (en) * 2022-05-16 2023-11-29 ブラザー工業株式会社 Computer program and inspection device
CN120263454A (en) * 2025-03-28 2025-07-04 兴容(上海)信息技术股份有限公司 Network security detection system and method based on machine learning

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113158922A (en) * 2021-04-26 2021-07-23 平安科技（深圳）有限公司 Traffic flow statistical method, device and equipment based on YOLO neural network
CN113112305A (en) * 2021-04-28 2021-07-13 腾讯科技（深圳）有限公司 Information delivery method, device and equipment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023168966A (en) * 2022-05-16 2023-11-29 ブラザー工業株式会社 Computer program and inspection device
CN120263454A (en) * 2025-03-28 2025-07-04 兴容(上海)信息技术股份有限公司 Network security detection system and method based on machine learning

Also Published As

Publication number Publication date
CN116451074A (en) 2023-07-18

Similar Documents

Publication Publication Date Title
CN111325353A (en) Contribution calculation method, device, equipment and storage medium of training data set
CN109558541B (en) Information processing method and device and computer storage medium
CN111340246A (en) Processing method and device for enterprise intelligent decision analysis and computer equipment
CN112528315B (en) Method and device for identifying sensitive data
CN116451074B (en) Image generation method and device for target object, computer equipment and storage medium
CN110175861A (en) Client management method, device, equipment and medium based on locating and monitoring
CN116467525A (en) Recommended methods, devices, equipment and storage media for business products
Liang et al. Cross-validation: An alternative bandwidth-selection method in kernel equating
CN114328600A (en) Method, device, equipment and storage medium for determining standard data element
CN117522519A (en) Product recommendation method, device, apparatus, storage medium and program product
Huang et al. An alternative test for zero modification in the INAR (1) model with Poisson innovations
CN114240670B (en) Service processing method, device, computer equipment and storage medium
CN119539419A (en) Personnel allocation method, device, computer equipment, storage medium and computer program product
JP2019160089A (en) Information processor, information processing method and program
CN119027078A (en) Power job matching method, device, computer equipment, readable storage medium and program product
US10853432B2 (en) Methods and systems for generating search results and recommendations based on multi-sourced two-way correspondence and relative entity prominence
CN114842939B (en) Physical examination recommendation information determining method, device, computer equipment and storage medium
US20150074118A1 (en) Systems, methods and computer-readable media for managing and incentivizing data entry
WO2019236338A1 (en) Computerized relevance scoring engine for identifying potential investors for a new business entity
CN114066618A (en) Object attribute information processing method, apparatus, computer equipment, storage medium
WO2022259512A1 (en) Business assistance device, business assistance method, and program
US10878048B2 (en) Methods and systems for generating search results and recommendations based on multi-sourced two-way correspondence and relative entity prominence
CN115587285B (en) Target object identification method, device, computer equipment and storage medium
JPWO2022259512A5 (en)
CN114693354B (en) Pricing method, device, computer equipment, storage medium and program product

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant