CN113128305A - Portrait archive accumulation evaluation method and device, electronic equipment and storage medium - Google Patents
Portrait archive accumulation evaluation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113128305A CN113128305A CN201911426177.7A CN201911426177A CN113128305A CN 113128305 A CN113128305 A CN 113128305A CN 201911426177 A CN201911426177 A CN 201911426177A CN 113128305 A CN113128305 A CN 113128305A
- Authority
- CN
- China
- Prior art keywords
- gathering
- result
- effective
- document
- portrait
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 105
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000009825 accumulation Methods 0.000 title description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 98
- 238000004220 aggregation Methods 0.000 claims description 71
- 230000002776 aggregation Effects 0.000 claims description 71
- 238000000034 method Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 10
- 230000001815 facial effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 18
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 5
- 230000004931 aggregating effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a portrait archive gathering evaluation method, a portrait archive gathering evaluation device, electronic equipment and a storage medium, wherein the portrait archive gathering evaluation method comprises the following steps: acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model; calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result; detecting the gear-gathering result to obtain a valid gear-gathering result; and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result. According to the embodiment of the application, the measurement index of the portrait gathering effect is obtained according to the gathering result, and the portrait gathering effect of the clustering algorithm model can be effectively evaluated by using the measurement index.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a portrait archive gathering evaluation method and apparatus, an electronic device, and a storage medium.
Background
With the development of computer information technology and internet technology, big data not only has remarkable application achievements in the business field, but also has increased attention in the political field year by year. Typical examples are: in public security big data application, portrait application occupies a vital position, and the effect is more and more obvious, the application of the public security portrait emphasizes prevention and control striking, and is changed into prevention and treatment in recent years, an effective method for supporting the prevention and treatment is to perform gathering (filing) on all collected portraits, however, the quality of the gathering (filing) effect is lack of effective evaluation basis.
Disclosure of Invention
In view of the above problems, the present application provides a portrait archive filing evaluation method, device, electronic device, and storage medium, which can effectively evaluate the portrait filing effect of a clustering algorithm model.
A first aspect of an embodiment of the present application provides a portrait archive filing evaluation method, including:
acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model;
calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result;
detecting the gear-gathering result to obtain a valid gear-gathering result;
and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result.
With reference to the first aspect, in a possible implementation manner, the sample portrait data set is composed of sample archives of a first preset number of different sample objects, a sample archive of each sample object includes a second preset number of facial images of the sample object, and each facial image carries an identification tag;
the detecting the document-gathering result to obtain a valid document-gathering result includes:
traversing each face image in the gathering result to obtain the identification label of the first target face image in the gathering result; the first target face image is a face image in the sample face data set;
and acquiring the effective document gathering result according to the identification label of the first target face image.
With reference to the first aspect, in a possible implementation manner, the obtaining the valid document aggregation result according to the identification tag of the first target face image includes:
determining the number of second target face images in the gathering result according to the identification label of the first target face image; the second target face image is a face image belonging to the same sample object in the sample face data set; the first target face image comprises the second target face image;
and if the number of the second target face images is greater than or equal to a first threshold value and the total number of the face images in the document gathering result is greater than or equal to a second threshold value, determining the document gathering result as an effective document gathering result.
With reference to the first aspect, in one possible implementation manner, the obtaining a score of the valid document aggregation result includes:
if the second target face image belonging to one sample object only exists in the effective document gathering result, determining the effective document gathering result as an effective file of the sample object, and calculating by adopting a preset formula to obtain a score of the effective document gathering result;
the obtaining of the document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result comprises:
calculating to obtain the sum of the scores of all the effective document gathering results according to the scores of the effective document gathering results;
obtaining the effective gear-gathering rate of the target clustering algorithm model by using the sum of the scores of all the effective gear-gathering results;
and obtaining a gear-gathering evaluation result of the target clustering algorithm model according to the effective gear-gathering rate.
With reference to the first aspect, in a possible implementation manner, the obtaining a score of the effective archive result further includes:
if the number of the second target face images belonging to the n sample objects in the effective document gathering result is greater than or equal to a first threshold value, determining the effective document gathering result as an effective document of one sample object with the largest number of the second target face images in the n sample objects, and calculating the score of the effective document gathering result by adopting the preset formula.
A second aspect of the embodiments of the present application provides a portrait archive filing evaluation device, including:
the system comprises a request acquisition module, a data processing module and a data processing module, wherein the request acquisition module is used for acquiring an evaluation request of a portrait archive file sent by a user, and the evaluation request comprises identification information of a target clustering algorithm model;
the image clustering module is used for calling the target clustering algorithm model according to the identification information to perform clustering on the sample image data set and the interference image data set to obtain at least one clustering result;
the effective file acquisition module is used for detecting the file aggregation result to acquire an effective file aggregation result;
and the document gathering evaluation module is used for acquiring the score of the effective document gathering result and obtaining the document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result.
A third aspect of embodiments of the present application provides an electronic device, including: the system comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the portrait archive gathering evaluation method.
A fourth aspect of the present embodiment provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the method for evaluating a portrait archive collection.
The above scheme of the present application includes at least the following beneficial effects: acquiring identification information of a target clustering algorithm model to be called from an evaluation request by acquiring the evaluation request of the portrait archive archives sent by a user; calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait data set and the interference portrait data set to obtain at least one clustering result; detecting the gear-gathering result to obtain a valid gear-gathering result; and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result. After the disordered sample portrait dataset and the disturbed portrait dataset are subjected to document aggregation by adopting a target clustering algorithm, face images from the sample portrait dataset in a document aggregation result are detected to determine effective files from the document aggregation result, then the score of each effective file is calculated according to a preset rule, finally a measurement index of the document aggregation effect of the target clustering algorithm model is obtained according to the score of each effective file, and the document aggregation effect of the portrait can be effectively evaluated according to the measurement index.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of an application architecture provided by an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for evaluating a portrait file according to an embodiment of the present disclosure;
FIG. 3 is an exemplary diagram of a sample portrait dataset and an interference portrait dataset aggregation file according to an embodiment of the present application;
FIG. 4 is a flowchart illustrating another method for evaluating a portrait file according to an embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating a process for obtaining effective accumulation results according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of an apparatus for evaluating a document collection of a portrait file according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of another portrait file gathering evaluation device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of another portrait file gathering evaluation device according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "comprising" and "having," and any variations thereof, as appearing in the specification, claims and drawings of this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Furthermore, the terms "first," "second," and "third," etc. are used to distinguish between different objects and are not used to describe a particular order.
First, a network system architecture to which the solution of the embodiments of the present application may be applied will be described by way of example with reference to the accompanying drawings. Referring to fig. 1, fig. 1 is an application architecture diagram provided in an embodiment of the present application, and as shown in fig. 1, the application architecture diagram includes a user terminal, a database, an image capturing device, and a portrait gathering evaluation system, where the user terminal is mainly used for interacting with the portrait gathering evaluation system, for example: the user can input some operation instructions at the user terminal to send some request to the server of the portrait gathering evaluation system, and after the server performs corresponding processing to the request, the user terminal can receive the processing result returned by the server and display the processing result to the user at the display part, optionally, the operation instructions input by the user can be execution codes, voice instructions, touch instructions, key pressing instructions, and the like, and the user terminal includes but is not limited to a smart phone, a computer, a Personal Digital Assistant (PDA), and a wearable device. The database can be some open-source face databases at home and abroad, or can also be a local database, a cloud database and the like of a face document gathering evaluation system developer, and can provide face images for training and evaluating a clustering algorithm model for a user. The image acquisition device can provide a face image acquired in real time to a server of the portrait document gathering evaluation system under some conditions, a portrait dataset is formed after user labeling, and a user can divide the portrait dataset into a plurality of subsets according to actual needs, for example: a training set, a testing set, or a sample set, an interference set, etc., and in some cases, the image acquisition device may also store the acquired face image in the database for subsequent labeling or calling. The portrait gathering evaluation system is used for calling a clustering algorithm model to cluster a portrait data set after receiving a portrait archive gathering evaluation request sent by a user terminal, obtaining a series of indexes according to a clustering result to evaluate the clustering result, and finally returning the evaluation result to the user terminal, wherein at least one clustering algorithm model is pre-constructed in the portrait gathering evaluation system, the clustering algorithm models are respectively provided with unique identification information, and a user can call the corresponding clustering algorithm model according to the identification information.
Based on the application architecture shown in fig. 1, the method, the apparatus, the electronic device, and the storage medium for evaluating the portrait archive aggregate file provided in the embodiment of the present application are described in detail below with reference to other drawings.
Referring to fig. 2, fig. 2 is a flowchart illustrating a portrait file aggregation evaluation method according to an embodiment of the present disclosure, where the portrait file aggregation evaluation method can be executed by an electronic device, as shown in fig. 2, and includes steps S21-S24:
s21, obtaining an evaluation request of the portrait archive archives sent by the user, wherein the evaluation request comprises identification information of the target clustering algorithm model.
In this embodiment, the user may be an evaluator of the portrait archive filing, or may also be a developer of the portrait filing evaluation system, and so on. Specifically, a client of the portrait gathering evaluation system is installed on a user terminal, a client interface of the portrait gathering evaluation system can provide related controls, after a portrait data set to be gathered is prepared by a user, a corresponding clustering algorithm model can be selected in the portrait gathering evaluation system, and then a portrait archive gathering evaluation request is sent to a server of the portrait gathering evaluation system by triggering the related controls of the client interface of the portrait gathering evaluation system, wherein the evaluation request is used for requesting the server to execute a gathering operation on the portrait data set to be gathered. In addition, the target clustering algorithm model is a model which is selected by a user and needs to execute the clustering operation, the identification information is the identity of each clustering algorithm model, and the user can select the target clustering algorithm model through the identification information, so that the evaluation request carries the identification information of the target clustering algorithm model. It should be noted that, the embodiment of the present application is not limited to sending the evaluation request by triggering the relevant control, and the evaluation request may also be sent by inputting program code, for example.
And S22, calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait data set and the interference portrait data set to obtain at least one clustering result.
In this embodiment, the target clustering algorithm model may be a K-means clustering algorithm model, or may be a density-based clustering algorithm model, or may also be a maximum expected clustering algorithm model using a gaussian mixture model, and so on. In order to improve the anti-interference capability of the target clustering algorithm model, the scheme also adopts the face images which are not in the sample face data set to form an interference face data set.
As shown in fig. 3, the sample portrait dataset consists of H sample archives of H sample objects, one sample archive has S face images of one sample object, and it can be seen that the face images in the sample portrait dataset are S × H face images, and the S × H face images all have label information; the interference portrait dataset is provided with M face images, and the M face images are not from the H sample objects; after a sample portrait dataset and an interference portrait dataset are selected, face images in the two datasets are scrambled to obtain a merged portrait dataset. After receiving the evaluation request, the server firstly analyzes the evaluation request to obtain identification information of a target clustering algorithm model, determines the target clustering algorithm model according to the identification information, and inputs the combined portrait data set into the target clustering algorithm model to cluster to obtain n gathering results, wherein each gathering result is a portrait archive, n is a positive integer greater than or equal to 1, and the number of facial images in each gathering result is P1, P2 and P3 … Pn.
And S23, detecting the gathering result to obtain a valid gathering result.
In this embodiment of the application, after obtaining the binning result in step S23, the server detects each binning result to determine whether the detected portrait file is a valid binning result, i.e. a valid file, where the valid binning result is a binning result in which the number of facial images from the same sample file (the same sample object) is greater than or equal to a certain threshold and the total number of facial images is also greater than or equal to a certain threshold. For the sample portrait dataset and the interference portrait dataset shown in fig. 3, after the target clustering algorithm model is clustered, the number h of the generated effective clustering results is greater than or equal to 0 and less than or equal to S.
And S24, obtaining the score of the effective document gathering result, and obtaining a document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result.
In the embodiment of the application, after h effective document gathering results are determined, the score of each effective document gathering result is calculated firstly, and the adopted calculation rule is as follows: y ═ Si — Li, where i ═ 1, 2, …, h, Y denotes the score of the ith valid gather result, Si denotes the specific number of face images from the same sample archive (same sample object) in the ith valid gather result, the number of which is greater than or equal to a certain threshold, Li denotes the number of face images other than Si face images in the ith valid gather result, and the score of the found valid gather result whose Y value is less than 0 is taken as 0, then the sum of the scores of the h valid gather results is: (S1-L1) + (S2-L2) +. + - (Sh-Lh), the correct total score for all the gathers of the target clustering algorithm model for H sample archives in the sample portrait dataset is: and S, obtaining the effective grade-gathering rate of the target clustering algorithm model according to the sum of the scores of the H effective grade-gathering results and the total score of all grade-gathering correctness of the target clustering algorithm model: (S1-L1) + (S2-L2) +. + (Sh-Lh)/S × H. And then, comparing the effective gear-gathering rate with a preset effective gear-gathering rate, if the effective gear-gathering rate is greater than or equal to the preset effective gear-gathering rate, determining that the gear-gathering effect of the target clustering algorithm model is in accordance with the expectation, and if the effective gear-gathering rate is less than the effective gear-gathering rate, determining that the gear-gathering effect of the target clustering algorithm model is not in accordance with the expectation.
It should be noted that the preset effective accumulation rate may be multiple, and the accumulation evaluation result may be multiple, for example: if the effective gear-gathering rate is greater than or equal to a first preset effective gear-gathering rate, the gear-gathering effect of the target clustering algorithm model is considered to be better; the effective gear-gathering rate is smaller than or equal to a first preset effective gear-gathering rate and larger than or equal to a second preset effective gear-gathering rate, the gear-gathering effect of the target clustering algorithm model is considered to be basically qualified, the effective gear-gathering rate is smaller than or equal to the second preset effective gear-gathering rate, the gear-gathering effect of the target clustering algorithm model is considered to be poor, the preset effective gear-gathering rates are different due to different clustering algorithm models, and the preset effective gear-gathering rates of different portrait datasets using the same clustering algorithm model are also different.
The method comprises the steps that an evaluation request of the portrait archive archives sent by a user is obtained, and identification information of a target clustering algorithm model to be called is obtained from the evaluation request; calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait data set and the interference portrait data set to obtain at least one clustering result; detecting the gear-gathering result to obtain a valid gear-gathering result; and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result. After the disordered sample portrait dataset and the disturbed portrait dataset are subjected to document aggregation by adopting a target clustering algorithm, face images from the sample portrait dataset in a document aggregation result are detected to determine effective files from the document aggregation result, then the score of each effective file is calculated according to a preset rule, finally a measurement index (effective document aggregation rate) of the document aggregation effect of the target clustering algorithm model is obtained according to the score of each effective file, and the document aggregation effect can be effectively evaluated according to the measurement index.
Referring to fig. 4, fig. 4 is a flowchart illustrating another method for evaluating a portrait file according to an embodiment of the present application, as shown in fig. 4, including steps S41-S45:
s41, acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model;
s42, calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result; the sample portrait data set is composed of sample archives of a first preset number of different sample objects, the sample archives of each sample object comprise a second preset number of face images of the sample object, and each face image carries an identification label;
in this embodiment, the first preset number may be determined by the user according to an actual situation, for example: 500, the second preset number may also be determined by the user according to the actual situation, for example: the identification tag, i.e. the label information of the face image in each sample file, is used to determine whether the face image carrying the tag information in the aggregate file result is the face image in the same sample file, so the identification tag of each sample file in 500 sample files is different, for example: the identification tags of the face images in the sample file 1 are all 0, the identification tags of the face images in the sample file 2 are all 1, … …, the identification tags of the face images in the sample file 500 are all 499, and the like.
S43, traversing each face image in the gathering result to obtain the identification label of the first target face image in the gathering result; the first target face image is a face image in the sample face data set;
in the embodiment of the present application, for the at least one archive aggregation result, first, each face image in each archive aggregation result is traversed, whether the face image has an identification tag is determined, and the identification tag of the face image from the sample face data set is recorded.
And S44, acquiring the effective gathering result according to the identification label of the first target face image.
In a possible implementation manner, as shown in fig. 5, the obtaining the valid gathering result according to the identification tag of the first target face image includes:
s51, determining the number of second target face images in the gathering result according to the identification label of the first target face image; the second target face image is a face image belonging to the same sample object in the sample face data set; the first target face image comprises the second target face image;
and S52, if the number of the second target face images is greater than or equal to a first threshold value and the total number of the face images in the gathering result is greater than or equal to a second threshold value, determining the gathering result as a valid gathering result.
In the embodiment of the present application, after the identification tag of the first target face image is obtained, statistics is performed on the identification tag, for example: if 50 pieces of 1 in the aggregate file result 1 indicate that 50 face images from the sample file 2 exist in the aggregate file result 1; if there are 3 0 s in the aggregate result 1, it means that there are 3 face images from the sample archive 1 in the aggregate result 1. The first threshold may be preset, for example: half of the number of face images in the sample archive, i.e. 40, the second threshold may be determined by S x J, S representing the number of face images in the sample archive (e.g. 80), J may be customized according to practical situations, for example: 1. 2, 5, etc. It is understood that the number of face images from the sample file 2 in the aforementioned accumulation result 1 is already greater than the first threshold (e.g., 40), and if the total number of face images in the accumulation result 1 is greater than or equal to the second threshold (e.g., 80), the accumulation result 1 is determined as a valid accumulation result, i.e., the accumulation result 1 is a valid file, and accordingly, h valid accumulation results can be obtained.
In the embodiment, the number of the face images from the same sample file in the aggregate file result is determined by acquiring the identification tag in the aggregate file result, and whether the aggregate file result is an effective file is determined according to the number of the face images from the same sample file and the total number of the face images in the aggregate file result, so that the acquisition of subsequent measurement indexes is facilitated.
And S45, obtaining the score of the effective document gathering result, and obtaining a document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result.
The above steps have been described in relation to the embodiment shown in fig. 2, and can achieve the same or similar beneficial effects, and are not repeated here to avoid repetition.
In one possible embodiment, the obtaining the score of the valid document gathering result includes:
if the second target face image belonging to one sample object only exists in the effective document gathering result, determining the effective document gathering result as an effective file of the sample object, and calculating by adopting a preset formula to obtain a score of the effective document gathering result;
the obtaining of the document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result comprises:
calculating to obtain the sum of the scores of all the effective document gathering results according to the scores of the effective document gathering results;
obtaining the effective gear-gathering rate of the target clustering algorithm model by using the sum of the scores of all the effective gear-gathering results;
and obtaining a gear-gathering evaluation result of the target clustering algorithm model according to the effective gear-gathering rate.
In the specific embodiment of the application, when the number of second target face images of only one sample object in the effective document aggregation result is greater than or equal to the first threshold, the calculation rule described in the embodiment shown in fig. 2 is adopted to obtain a unique score of each effective document aggregation result, then the scores of each effective document aggregation result are summed to obtain a score sum of all effective document aggregation results, a ratio between the score sum of all effective document aggregation results and a total score of all document aggregation correctness of the target clustering algorithm model is used as an effective document aggregation rate of the target clustering algorithm model, and a document aggregation evaluation result of the target clustering algorithm model is obtained according to a comparison condition of the effective document aggregation rate and a preset effective document aggregation rate.
In a possible implementation manner, the obtaining the score of the effective gathering result further includes:
if the number of the second target face images belonging to the n sample objects in the effective document gathering result is greater than or equal to a first threshold value, determining the effective document gathering result as an effective document of one sample object with the largest number of the second target face images in the n sample objects, and calculating the score of the effective document gathering result by adopting the preset formula.
In the embodiment of the present application, when the number of the second target face images of n sample objects in the effective archive aggregating result is greater than or equal to the first threshold, the number of the second target face images of the n sample objects in the effective archive aggregating result is compared, the effective archive aggregating result is used as an effective archive of one sample object with the largest number of the second target face images in the n sample objects, and a unique score of the effective archive aggregating result is obtained according to the specific number of the second target face images of the sample objects by using the calculation rule described in the embodiment shown in fig. 2. For example: the number of the face images of the first group in the document gathering result is 55, the number of the face images of the second group in the document gathering result is 41, the number of the face images of the first group and the number of the face images of the second group are both larger than a first threshold, the number of the face images of the first group is the largest, the effective document gathering result can only be an effective file of the first group, the score of the effective document gathering result is calculated only for the first group, and at the moment, Si represents the number of the face images of the first group in the ith effective document gathering result, so that the situation that the same effective document gathering result is used as the effective files of a plurality of sample objects is.
In one possible embodiment, the method further comprises:
detecting the effective gear-gathering result to obtain an effective repeated gear-gathering result;
and obtaining the effective gear-gathering result repetition rate of the target clustering algorithm model according to the number of the effective repeated gear-gathering results.
In the embodiment of the present application, the effective repeated clustering result refers to a situation that the face image of the same sample object is clustered into different effective clustering results, for example: and the gear aggregation result 1 and the gear aggregation result 2 are effective gear aggregation results, the sample object is aggregated into the gear aggregation result 1 and the gear aggregation result 2, the gear aggregation result 1 and the gear aggregation result 2 are effective repeated gear aggregation results, the effective gear aggregation result repetition rate of the target clustering algorithm model is obtained by dividing the number of the effective repeated gear aggregation results by the number of all the effective gear aggregation results, and the lower the effective gear aggregation result repetition rate is, the better the effective gear aggregation result repetition rate is.
In one possible embodiment, the method further comprises:
detecting the gathering result to obtain an invalid gathering result;
and obtaining the invalid document gathering rate of the target clustering algorithm model according to the number of the invalid document gathering results.
In the embodiment of the present application, the invalid document aggregation result means that the face image of a certain sample document is allocated to a plurality of document aggregation results, and a document aggregation result in which the number of face images of the sample document is not greater than or equal to the first threshold is defined as an invalid document, the number of invalid document aggregation results is divided by the number of all document aggregation results to obtain an invalid document aggregation rate, and the invalid document aggregation rate is also used as one of the metrics for evaluating the document aggregation effect of the target clustering algorithm model.
In one possible embodiment, the method further comprises:
summing the number Li of the face images except the Si face images in the effective accumulation result to obtain the total wrong accumulation score of all the effective accumulation results: l1+ L2+. + Lh;
and calculating the error gear-gathering rate of the effective gear-gathering result by using the error gear-gathering total scores of all the effective gear-gathering results.
In the specific embodiment of the application, while the score of the effective gear-gathering result is calculated, the wrong gear-gathering score Li of the effective gear-gathering result is obtained, the wrong gear-gathering total score is obtained through Li of each effective gear-gathering result, and the wrong gear-gathering rate of the effective gear-gathering result is obtained by dividing the wrong gear-gathering total score by the total score S H of all the correct gear-gathering of the target clustering algorithm model.
It can be seen that, in the present application, multiple possible implementation manners are added on the basis of the embodiments shown in fig. 2 and fig. 4, the measure of the portrait archive accumulation effect includes an effective accumulation rate, an effective accumulation result repetition rate, an invalid accumulation rate, and an effective accumulation result error accumulation rate in addition to the effective accumulation rate, and the accumulation effect of the target clustering algorithm model is evaluated from multiple dimensions, so that the portrait archive accumulation evaluation method is more complete and effective.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a portrait file gathering evaluation device according to an embodiment of the present application, and as shown in fig. 6, the device includes:
the request acquisition module 61 is used for acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model;
the portrait clustering module 62 is configured to call the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result;
a valid file acquiring module 63, configured to detect the archive aggregation result to acquire a valid archive aggregation result;
and the document-gathering evaluation module 64 is configured to obtain a score of the effective document-gathering result, and obtain a document-gathering evaluation result of the target clustering algorithm model according to the score of the effective document-gathering result.
Optionally, the sample portrait data set is composed of sample archives of a first preset number of different sample objects, the sample archives of each sample object include a second preset number of face images of the sample object, and each face image carries an identification tag; the effective archive acquisition module 63 is specifically configured to, in detecting the archive aggregation result to acquire an effective archive aggregation result:
traversing each face image in the gathering result to obtain the identification label of the first target face image in the gathering result; the first target face image is a face image in the sample face data set;
and acquiring the effective document gathering result according to the identification label of the first target face image.
Optionally, the effective archive obtaining module 63, in terms of obtaining the effective archive aggregation result according to the identification tag of the first target face image, is specifically configured to:
determining the number of second target face images in the gathering result according to the identification label of the first target face image; the second target face image is a face image belonging to the same sample object in the sample face data set; the first target face image comprises the second target face image;
and if the number of the second target face images is greater than or equal to a first threshold value and the total number of the face images in the document gathering result is greater than or equal to a second threshold value, determining the document gathering result as an effective document gathering result.
Optionally, the document aggregation evaluation module 64 is specifically configured to, in terms of obtaining the score of the effective document aggregation result:
if the second target face image belonging to one sample object only exists in the effective document gathering result, determining the effective document gathering result as an effective file of the sample object, and calculating by adopting a preset formula to obtain a score of the effective document gathering result;
the document aggregation evaluation module 64 is specifically configured to, in terms of obtaining a document aggregation evaluation result of the target clustering algorithm model according to the score of the effective document aggregation result:
calculating to obtain the sum of the scores of all the effective document gathering results according to the scores of the effective document gathering results;
obtaining the effective gear-gathering rate of the target clustering algorithm model by using the sum of the scores of all the effective gear-gathering results;
and obtaining a gear-gathering evaluation result of the target clustering algorithm model according to the effective gear-gathering rate.
Optionally, the document aggregation evaluation module 64 is further specifically configured to, in terms of obtaining the score of the effective document aggregation result:
if the number of the second target face images belonging to the n sample objects in the effective document gathering result is greater than or equal to a first threshold value, determining the effective document gathering result as an effective document of one sample object with the largest number of the second target face images in the n sample objects, and calculating the score of the effective document gathering result by adopting the preset formula.
Optionally, as shown in fig. 7, the portrait archive gathering evaluation device further includes:
an effective duplicate archive acquisition module 65, configured to detect the effective archive aggregation result to acquire an effective duplicate archive aggregation result;
and the repetition rate calculation module 66 is configured to obtain the effective gear-gathering result repetition rate of the target clustering algorithm model according to the number of the effective gear-gathering results.
Optionally, as shown in fig. 8, the portrait archive gathering evaluation device further includes:
an invalid archive acquisition module 67, configured to detect the archive aggregation result to acquire an invalid archive aggregation result;
and the invalid gear-gathering rate calculation module 68 is configured to obtain the invalid gear-gathering rate of the target clustering algorithm model according to the number of the invalid gear-gathering results.
According to an embodiment of the present application, the units in the portrait archive profile evaluation apparatus provided in the embodiment of the present application may be respectively or completely combined into one or several other units to form the portrait archive profile evaluation apparatus, or one or some of the units may be further split into multiple functionally smaller units to form the portrait archive profile evaluation apparatus, which may achieve the same operation without affecting the achievement of the technical effects of the embodiment of the present application. The units are divided based on logic functions, and in practical application, the functions of one unit can be realized by a plurality of units, or the functions of a plurality of units can be realized by one unit. In other embodiments of the present application, the portrait archive profile evaluation apparatus may also include other units, and in practical applications, these functions may also be implemented by the assistance of other units, and may be implemented by cooperation of a plurality of units.
According to another embodiment of the present application, the portrait archive gathering evaluation apparatus may be constructed by running a computer program (including program codes) capable of executing the steps involved in the corresponding method as shown in fig. 2 or fig. 4 on a general-purpose computing device such as a computer including a processing element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read-only storage medium (ROM), and a storage element, and the portrait archive gathering evaluation method of the embodiment of the present application may be implemented. The computer program may be recorded on a computer-readable recording medium, for example, and loaded and executed in the above-described computing apparatus via the computer-readable recording medium.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application, as shown in fig. 9, including: a memory 901 for storing a computer program; a processor 902, configured to invoke a computer program stored in the memory 901 to implement the steps in the embodiment of the portrait archive accumulation evaluation method; an input/output interface 903 for performing input/output, where the input/output interface 903 may be one or more; it will be appreciated that various portions of the electronic device are each coupled to bus 904.
The processor 902 is specifically configured to invoke a computer program to execute the following steps:
acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model;
calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result;
detecting the gear-gathering result to obtain a valid gear-gathering result;
and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result.
Optionally, the sample portrait data set is composed of sample archives of a first preset number of different sample objects, the sample archives of each sample object include a second preset number of face images of the sample object, and each face image carries an identification tag; processor 902 performs the detecting the polygraph result to obtain a valid polygraph result, including:
traversing each face image in the gathering result to obtain the identification label of the first target face image in the gathering result; the first target face image is a face image in the sample face data set;
and acquiring the effective document gathering result according to the identification label of the first target face image.
Optionally, the processor 902 executes the obtaining of the effective document gathering result according to the identification tag of the first target face image, including:
determining the number of second target face images in the gathering result according to the identification label of the first target face image; the second target face image is a face image belonging to the same sample object in the sample face data set; the first target face image comprises the second target face image;
and if the number of the second target face images is greater than or equal to a first threshold value and the total number of the face images in the document gathering result is greater than or equal to a second threshold value, determining the document gathering result as an effective document gathering result.
Optionally, the processor 902 executes the obtaining of the score of the effective document gathering result, including:
if the second target face image belonging to one sample object only exists in the effective document gathering result, determining the effective document gathering result as an effective file of the sample object, and calculating by adopting a preset formula to obtain a score of the effective document gathering result;
optionally, the processor 902 executes the score according to the effective document aggregation result to obtain a document aggregation evaluation result of the target clustering algorithm model, including:
calculating to obtain the sum of the scores of all the effective document gathering results according to the scores of the effective document gathering results;
obtaining the effective gear-gathering rate of the target clustering algorithm model by using the sum of the scores of all the effective gear-gathering results;
and obtaining a gear-gathering evaluation result of the target clustering algorithm model according to the effective gear-gathering rate.
Optionally, the processor 9012 executes the obtaining of the score of the effective document gathering result, further including:
if the number of the second target face images belonging to the n sample objects in the effective document gathering result is greater than or equal to a first threshold value, determining the effective document gathering result as an effective document of one sample object with the largest number of the second target face images in the n sample objects, and calculating the score of the effective document gathering result by adopting the preset formula.
Optionally, the processor 902 is further configured to: detecting the effective gear-gathering result to obtain an effective repeated gear-gathering result;
and obtaining the effective gear-gathering result repetition rate of the target clustering algorithm model according to the number of the effective repeated gear-gathering results.
Optionally, the processor 902 is further configured to: detecting the gathering result to obtain an invalid gathering result;
and obtaining the invalid document gathering rate of the target clustering algorithm model according to the number of the invalid document gathering results.
Illustratively, the electronic device may be a super computer, a notebook computer, a tablet computer, a palm computer, a server, or the like. Electronic devices may include, but are not limited to, a processor 902, a memory 901, an input output interface 903, a bus 904. It will be appreciated by those skilled in the art that the schematic diagrams are merely examples of an electronic device and are not limiting of an electronic device and may include more or fewer components than those shown, or some components in combination, or different components.
It should be noted that, since the steps in the human image file archive filing evaluation method described above are implemented when the processor 902 of the electronic device executes the computer program, the embodiments of the human image archive filing evaluation method described above are all applicable to the electronic device, and all can achieve the same or similar beneficial effects.
The embodiment of the application also provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps in the portrait archive gathering evaluation method.
Illustratively, the computer program of the computer-readable storage medium comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
It should be noted that, since the computer program of the computer-readable storage medium is executed by the processor to implement the steps in the above-mentioned portrait archive accumulation assessment method, all the examples of the above-mentioned portrait archive accumulation assessment method are applicable to the computer-readable storage medium, and can achieve the same or similar beneficial effects.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A portrait archive filing evaluation method, comprising:
acquiring an evaluation request of the portrait archive archives sent by a user, wherein the evaluation request comprises identification information of a target clustering algorithm model;
calling the target clustering algorithm model according to the identification information to perform clustering on the sample portrait dataset and the interference portrait dataset to obtain at least one clustering result;
detecting the gear-gathering result to obtain a valid gear-gathering result;
and obtaining the score of the effective grade-gathering result, and obtaining the grade-gathering evaluation result of the target clustering algorithm model according to the score of the effective grade-gathering result.
2. The method according to claim 1, wherein the sample portrait data set is composed of sample archives of a first preset number of different sample objects, the sample archives of each sample object include a second preset number of facial images of the sample object, and each facial image carries an identification tag;
the detecting the document-gathering result to obtain a valid document-gathering result includes:
traversing each face image in the gathering result to obtain the identification label of the first target face image in the gathering result; the first target face image is a face image in the sample face data set;
and acquiring the effective document gathering result according to the identification label of the first target face image.
3. The method of claim 2, wherein the obtaining the valid gather result from the authentication tag of the first target face image comprises:
determining the number of second target face images in the gathering result according to the identification label of the first target face image; the second target face image is a face image belonging to the same sample object in the sample face data set; the first target face image comprises the second target face image;
and if the number of the second target face images is greater than or equal to a first threshold value and the total number of the face images in the document gathering result is greater than or equal to a second threshold value, determining the document gathering result as an effective document gathering result.
4. The method of claim 3, wherein obtaining the score of the valid archival result comprises:
if the second target face image belonging to one sample object only exists in the effective document gathering result, determining the effective document gathering result as an effective file of the sample object, and calculating by adopting a preset formula to obtain a score of the effective document gathering result;
the obtaining of the document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result comprises:
calculating to obtain the sum of the scores of all the effective document gathering results according to the scores of the effective document gathering results;
obtaining the effective gear-gathering rate of the target clustering algorithm model by using the sum of the scores of all the effective gear-gathering results;
and obtaining a gear-gathering evaluation result of the target clustering algorithm model according to the effective gear-gathering rate.
5. The method of claim 4, wherein obtaining the score of the valid archival result further comprises:
if the number of the second target face images belonging to the n sample objects in the effective document gathering result is greater than or equal to a first threshold value, determining the effective document gathering result as an effective document of one sample object with the largest number of the second target face images in the n sample objects, and calculating the score of the effective document gathering result by adopting the preset formula.
6. The method according to any one of claims 1 to 5, further comprising:
detecting the effective gear-gathering result to obtain an effective repeated gear-gathering result;
and obtaining the effective gear-gathering result repetition rate of the target clustering algorithm model according to the number of the effective repeated gear-gathering results.
7. The method according to any one of claims 1 to 5, further comprising:
detecting the gathering result to obtain an invalid gathering result;
and obtaining the invalid document gathering rate of the target clustering algorithm model according to the number of the invalid document gathering results.
8. A portrait archive filing evaluation apparatus, comprising:
the system comprises a request acquisition module, a data processing module and a data processing module, wherein the request acquisition module is used for acquiring an evaluation request of a portrait archive file sent by a user, and the evaluation request comprises identification information of a target clustering algorithm model;
the image clustering module is used for calling the target clustering algorithm model according to the identification information to perform clustering on the sample image data set and the interference image data set to obtain at least one clustering result;
the effective file acquisition module is used for detecting the file aggregation result to acquire an effective file aggregation result;
and the document gathering evaluation module is used for acquiring the score of the effective document gathering result and obtaining the document gathering evaluation result of the target clustering algorithm model according to the score of the effective document gathering result.
9. An electronic device, wherein the node device comprises a processor, a memory and a computer program stored on the memory and operable on the processor, and the processor executes the computer program to implement the steps of the human figure archive gathering evaluation method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the portrait archive profile assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911426177.7A CN113128305B (en) | 2019-12-31 | 2019-12-31 | Portrait archive aggregation evaluation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911426177.7A CN113128305B (en) | 2019-12-31 | 2019-12-31 | Portrait archive aggregation evaluation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128305A true CN113128305A (en) | 2021-07-16 |
| CN113128305B CN113128305B (en) | 2024-06-11 |
Family
ID=76771555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911426177.7A Active CN113128305B (en) | 2019-12-31 | 2019-12-31 | Portrait archive aggregation evaluation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128305B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114286086A (en) * | 2021-12-29 | 2022-04-05 | 重庆紫光华山智安科技有限公司 | Camera detection method and related device |
| CN114329058A (en) * | 2021-12-29 | 2022-04-12 | 重庆紫光华山智安科技有限公司 | Image gathering method and device and electronic equipment |
| CN114359611A (en) * | 2022-03-18 | 2022-04-15 | 浙江大华技术股份有限公司 | Target file gathering method, computer equipment and storage device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109344271A (en) * | 2018-09-30 | 2019-02-15 | 南京物盟信息技术有限公司 | Video portrait records handling method and its system |
| WO2019051795A1 (en) * | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and device, terminal, server, and computer-readable storage medium |
| WO2019052316A1 (en) * | 2017-09-15 | 2019-03-21 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer-readable storage medium and mobile terminal |
| CN110211048A (en) * | 2019-05-28 | 2019-09-06 | 湖北华中电力科技开发有限责任公司 | A kind of complicated archival image Slant Rectify method based on convolutional neural networks |
| WO2019223313A1 (en) * | 2018-05-22 | 2019-11-28 | 深圳云天励飞技术有限公司 | Personnel file establishment method and apparatus |
-
2019
- 2019-12-31 CN CN201911426177.7A patent/CN113128305B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019051795A1 (en) * | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and device, terminal, server, and computer-readable storage medium |
| WO2019052316A1 (en) * | 2017-09-15 | 2019-03-21 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer-readable storage medium and mobile terminal |
| WO2019223313A1 (en) * | 2018-05-22 | 2019-11-28 | 深圳云天励飞技术有限公司 | Personnel file establishment method and apparatus |
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109344271A (en) * | 2018-09-30 | 2019-02-15 | 南京物盟信息技术有限公司 | Video portrait records handling method and its system |
| CN110211048A (en) * | 2019-05-28 | 2019-09-06 | 湖北华中电力科技开发有限责任公司 | A kind of complicated archival image Slant Rectify method based on convolutional neural networks |
Non-Patent Citations (3)
| Title |
|---|
| 田伟;韩海涛;陈静;: "构建档案用户数据分析引擎的研究", 档案与建设, no. 03 * |
| 章淑丛;房斌;: "基于改进K均值的脸形聚类算法", 世界科技研究与发展, no. 03, 15 June 2013 (2013-06-15) * |
| 肖轶涛;张义泰;: "基于人像识别技术在"一人一档"系统中的应用与探索", 数字技术与应用, no. 03, 25 March 2019 (2019-03-25) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114286086A (en) * | 2021-12-29 | 2022-04-05 | 重庆紫光华山智安科技有限公司 | Camera detection method and related device |
| CN114329058A (en) * | 2021-12-29 | 2022-04-12 | 重庆紫光华山智安科技有限公司 | Image gathering method and device and electronic equipment |
| CN114286086B (en) * | 2021-12-29 | 2023-08-01 | 重庆紫光华山智安科技有限公司 | Camera detection method and related device |
| CN114359611A (en) * | 2022-03-18 | 2022-04-15 | 浙江大华技术股份有限公司 | Target file gathering method, computer equipment and storage device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128305B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Cloud-enabled privacy-preserving collaborative learning for mobile sensing | |
| JP2018516421A (en) | Network access operation identification method, server, and storage medium | |
| CN113128305A (en) | Portrait archive accumulation evaluation method and device, electronic equipment and storage medium | |
| CN111371767B (en) | Malicious account identification method, malicious account identification device, medium and electronic device | |
| CN108763274B (en) | Access request identification method and device, electronic equipment and storage medium | |
| CN111612041A (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| CN107194430A (en) | A kind of screening sample method and device, electronic equipment | |
| CN111062808B (en) | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium | |
| CN112488863B (en) | Dangerous seed recommendation method and related equipment in user cold start scene | |
| CN112488716B (en) | Abnormal event detection system | |
| CN113344016A (en) | Deep migration learning method and device, electronic equipment and storage medium | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN108770002B (en) | Base station flow analysis method, device, equipment and storage medium | |
| CN110457387B (en) | Method and related device applied to user tag determination in network | |
| CN111538909A (en) | Information recommendation method and device | |
| CN114461906A (en) | Sequence recommendation method and device focusing on user core interests | |
| CN112559868B (en) | Information recall method and device, storage medium and electronic equipment | |
| CN113470799A (en) | Intelligent editor of hospital comprehensive quality supervision platform | |
| CN112269937A (en) | Method, system and device for calculating user similarity | |
| CN115049843A (en) | Confrontation sample generation method and device, electronic equipment and storage medium | |
| CN112131468A (en) | Data processing method and device in recommendation system | |
| CN114023397A (en) | Drug redirection model generation method and device, storage medium and computer equipment | |
| CN113065025A (en) | Video duplicate checking method, device, equipment and storage medium | |
| Abdelwahab et al. | Alleviating the sparsity problem of collaborative filtering using an efficient iterative clustered prediction technique | |
| CN109739839A (en) | Data processing empty value method, apparatus and terminal device |
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 |