CN113923444A - Zoom lens quality evaluation method and device - Google Patents

Abstract

The invention provides a zoom lens quality evaluation method and a zoom lens quality evaluation device, wherein the method comprises the following steps: acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated; and performing quality evaluation on the zoom lens based on the data to be evaluated. The zoom lens quality evaluation method and the zoom lens quality evaluation device can be used for evaluating the quality of the zoom lens based on the data to be evaluated, can help workers to quickly evaluate the lens imaging quality in production, and can be used for carrying out optical adjustment on the zoom lens by utilizing the evaluation result, so that the imaging quality is improved, the reject ratio is reduced, and the enterprise cost is reduced.

Description

Zoom lens quality evaluation method and device

Technical Field

The invention relates to the technical field of lens evaluation, in particular to a zoom lens quality evaluation method and device.

Background

At present, with the development of the optical industry, higher requirements are placed on the definition, object image similarity and deformation degree of an image formed by an optical system, so that the development of a zoom lens is promoted, the requirements of zooming are met, the precision requirements of lenses and related lens frames need to be improved, but the precision improvement is not only limited by the existing processing technology, but also the production cost of enterprises is increased.

Therefore, a zoom lens quality evaluation method is needed to quickly evaluate the imaging quality of a lens during production, and perform optical adjustment on the zoom lens by using an evaluation result, so as to improve the imaging quality, reduce the reject ratio and reduce the enterprise cost.

Disclosure of Invention

One of the objectives of the present invention is to provide a zoom lens quality evaluation method and apparatus, which can perform quality evaluation on a zoom lens based on data to be evaluated, and can help workers to quickly evaluate the imaging quality of the lens during production, and perform optical adjustment on the zoom lens by using the evaluation result, thereby improving the imaging quality, reducing the reject ratio, and reducing the enterprise cost.

The zoom lens quality evaluation method provided by the embodiment of the invention comprises the following steps:

acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

and performing quality evaluation on the zoom lens based on the data to be evaluated.

Preferably, the acquiring of the imaging data of the zoom lens includes:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

Preferably, the quality evaluation of the zoom lens based on the data to be evaluated includes:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to a second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

Preferably, the screening of the second evaluation target to be evaluated from the first evaluation targets based on the attribute information includes:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting a second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises the following steps: a plurality of capture strategies;

determining at least one capture object corresponding to a capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in a capture object based on a capture strategy;

if the capture is successful, acquiring a capture process for capturing a first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

acquiring the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to acquire an association relationship between the second capture scene and the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the acquisition is successful, analyzing the association relationship to acquire a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of a sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting the first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the matched second feature as a third feature, and taking a corresponding first record item as a second record item;

based on a preset feature-supplement direction library, attempting to determine at least one supplement direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

when all third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether a second lens quality event and a fourth lens quality event contain negative events or not by the event determining model, and if so, outputting a first severity value corresponding to the contained negative events and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation targets corresponding to the first attribute items according to the size of the corresponding sorting values to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

Preferably, the zoom lens quality evaluation method further includes:

expanding a risk feature library;

wherein, expand the risk characteristic library, include:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of a first expansion node, wherein the guarantee information comprises: a second expansion node vouching the first expansion node and a first vouching value corresponding to the second expansion node;

determining a first expansion node in the second expansion nodes, taking the first expansion node as a third expansion node, and taking a first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion nodes except the third expansion node as fourth expansion nodes, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting a second guarantee value and a third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

acquiring at least one first risk characteristic through a fifth expansion node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to obtain at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is greater than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into a risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, the expansion is completed.

The zoom lens quality evaluation device provided by the embodiment of the invention comprises:

the acquisition module is used for acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

and the evaluation module is used for evaluating the quality of the zoom lens based on the data to be evaluated.

Preferably, the obtaining module performs the following operations:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

Preferably, the evaluation module performs the following operations:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to a second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

Preferably, the evaluation module performs the following operations:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting a second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises the following steps: a plurality of capture strategies;

determining at least one capture object corresponding to a capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in a capture object based on a capture strategy;

if the capture is successful, acquiring a capture process for capturing a first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

acquiring the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to acquire an association relationship between the second capture scene and the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the acquisition is successful, analyzing the association relationship to acquire a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of a sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting the first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the matched second feature as a third feature, and taking a corresponding first record item as a second record item;

based on a preset feature-supplement direction library, attempting to determine at least one supplement direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

when all third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether a second lens quality event and a fourth lens quality event contain negative events or not by the event determining model, and if so, outputting a first severity value corresponding to the contained negative events and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation targets corresponding to the first attribute items according to the size of the corresponding sorting values to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

Preferably, the zoom lens quality evaluation device further includes:

the expansion module is used for expanding the risk characteristic library;

the expansion module performs the following operations:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of a first expansion node, wherein the guarantee information comprises: a second expansion node vouching the first expansion node and a first vouching value corresponding to the second expansion node;

determining a first expansion node in the second expansion nodes, taking the first expansion node as a third expansion node, and taking a first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion nodes except the third expansion node as fourth expansion nodes, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting a second guarantee value and a third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

acquiring at least one first risk characteristic through a fifth expansion node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to obtain at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is greater than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into a risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, the expansion is completed.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

FIG. 1 is a flowchart illustrating a method for evaluating quality of a zoom lens according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating a zoom lens with quality evaluation applied in an embodiment of the present invention;

FIG. 3 is a schematic diagram of a zoom lens quality evaluation apparatus according to an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

An embodiment of the present invention provides a zoom lens quality evaluation method, as shown in fig. 1, including:

step S1: acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

step S2: and performing quality evaluation on the zoom lens based on the data to be evaluated.

The working principle and the beneficial effects of the technical scheme are as follows:

acquiring imaging data imaged by the zoom lens (a light source is used for emitting a light beam to pass through the lens to be imaged on an imaging device, the technology belongs to the prior art and is not described in detail), and because the imaging data belongs to optical information, photoelectric conversion is required to be carried out, and the optical information is converted into data to be evaluated, which belongs to electrical information; based on the data to be evaluated, carrying out quality evaluation on the zoom lens (for example, evaluating the image surface value, the contrast, the focal length, the depth of field, the field curvature and the like of an image);

the zoom lens quality evaluation method and device based on the data to be evaluated can help workers to quickly evaluate the lens imaging quality in production, and the evaluation result is used for carrying out optical adjustment on the zoom lens, so that the imaging quality is improved, the reject ratio is reduced, and the enterprise cost is reduced.

The embodiment of the invention provides a zoom lens quality evaluation method for acquiring imaging data of a zoom lens, which comprises the following steps:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

The working principle and the beneficial effects of the technical scheme are as follows:

as shown in FIG. 2, a monochromatic light source is provided (e.g., using a light source machine); a monochromatic light source is utilized to emit light beams which are sequentially transmitted through a differentiation plate (the function of the division plate is to superpose a cross wire or concentric ring pattern on an object to be imaged, the pattern can be used as a position reference and can be aligned to the object to be imaged, the cross differentiation plate or concentric ring differentiation plate can be used) and a zoom lens, imaging is carried out on a high-precision linear array CCD (Charge Coupled Device), and the acquisition of imaging data is completed.

The embodiment of the invention provides a zoom lens quality evaluation method, which is used for evaluating the quality of a zoom lens based on data to be evaluated and comprises the following steps:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to a second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

The working principle and the beneficial effects of the technical scheme are as follows:

the first evaluation target is specifically: for example, evaluating contrast, evaluating depth of field effects, etc.; the preset evaluation target-evaluation model library is specifically as follows: a database containing evaluation models corresponding to different evaluation targets, for example: the evaluation target is evaluation contrast, and the corresponding evaluation model is a model generated by learning a large number of records of manual evaluation contrast by using a machine learning algorithm and is used for evaluating the contrast; the attribute information of the zoom lens is specifically: for example, material provider data of the lens, production process of the lens, manufacturer, and the like;

after the second evaluation target is determined, target data (for example, contrast data) corresponding to the evaluation target in the data to be evaluated is determined, and evaluation is performed by using a corresponding evaluation model.

The embodiment of the invention provides a zoom lens quality evaluation method, which is used for screening out a second evaluation target needing to be evaluated from first evaluation targets on the basis of attribute information and comprises the following steps:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting a second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises the following steps: a plurality of capture strategies;

determining at least one capture object corresponding to a capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in a capture object based on a capture strategy;

if the capture is successful, acquiring a capture process for capturing a first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

acquiring the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to acquire an association relationship between the second capture scene and the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the acquisition is successful, analyzing the association relationship to acquire a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of a sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting the first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the matched second feature as a third feature, and taking a corresponding first record item as a second record item;

based on a preset feature-supplement direction library, attempting to determine at least one supplement direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

when all third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether a second lens quality event and a fourth lens quality event contain negative events or not by the event determining model, and if so, outputting a first severity value corresponding to the contained negative events and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation targets corresponding to the first attribute items according to the size of the corresponding sorting values to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

The working principle and the beneficial effects of the technical scheme are as follows:

the preset attribute type-important value library is specifically as follows: databases containing important values corresponding to different attribute types, such as: the attribute type is a lens material provider, the corresponding important value is 95, and the important value represents the influence degree of the attribute type on the lens quality; the preset importance value threshold specifically includes: for example, 75; the preset negative event generation model specifically comprises the following steps: a model generated after learning a record of a large number of artificially created negative events using a machine learning algorithm, the model may generate negative events based on attribute terms, such as: the attribute item is a certain lens material manufacturer, the negative event is the lens material produced by the manufacturer, the quality of the lens is unqualified, and the like, and a first severity value of the negative event is also output, wherein the greater the first severity value is, the more severe the corresponding negative event is; the capture strategy is specifically as follows: for example, web page crawling; the preset capture strategy-capture object library specifically comprises the following steps: data containing capture objects corresponding to different capture strategies, such as: step policy is web page crawling, and the capture objects are a plurality of shot forum websites; the preset confidence threshold specifically comprises: for example, 80; the preset relationship value threshold specifically comprises: for example, 90; the receiving node specifically comprises: a network node, the other side can send the data to the network node, namely finish the data reception; the preset inquiry mode specifically comprises the following steps: for example, whether there is newly received data, if so, please reply; the preset risk characteristic library specifically comprises the following steps: a database containing a plurality of risk features, a risk feature being a feature that may cause a malicious event, such as: the user wants to release false data and suddenly changes identity information (risk characteristics); the preset malicious feature library specifically comprises the following steps: the system comprises a plurality of malicious feature databases, wherein the malicious features are, for example: changing identity information, and checking the released data as false data; the preset range is specifically as follows: a range on the time axis corresponding to a certain length of time (e.g.: 2 days); the preset event determination model specifically includes: the model is generated after learning records for manually judging whether the events comprise certain events by utilizing a machine learning algorithm, and the model can determine whether the events comprise certain events;

when the second evaluation target to be evaluated is screened, it may be determined based on the attribute information of the zoom lens, for example: a manufacturer of production materials of the zoom lens needs to evaluate the contrast when a problem event that the contrast of lens imaging is poor due to material problems occurs; however, how to acquire problem events needs to be solved; extracting a first attribute item (such as a material provider) in attribute information, screening out a second attribute item which has an influence on a quality result based on an important value, generating a negative event corresponding to the second attribute item based on a negative event generation model, and determining whether the negative event occurs; trying to capture a shot quality event (for example, a quality evaluation article published by a certain user in a forum website), if the capture is successful, determining multiple processes in the capture process (for example, process 1, capturing a comment that the user does not "quality" in a manufacturer discussion area, process 2, capturing a homepage of the user and publishing a specific article), where a first capture scene corresponding to the processes is, for example: the process 1 corresponds to a web page of a manufacturer discussion area, and the process 2 corresponds to a web page of a user homepage; acquiring the credibility (webpage credibility) of the first capture scene, and if the credibility is smaller than a credibility threshold, taking the corresponding first capture scene as a second capture scene; trying to acquire an association relationship between a second capture scene and a capture object (for example, the second capture scene belongs to a webpage of the capture object, and the capture object guarantees the webpage to form a guarantee relationship), if the acquisition fails, it is indicated that the second capture scene is not credible (for example, from other forums), if the acquisition succeeds, the relationship (guarantee relationship) is analyzed to acquire a relationship value, and the greater the relationship value is, the greater the guarantee degree of the capture object guaranteeing the relationship is, and the higher the credibility is; some cooperative forums do not allow the party to capture in consideration of privacy security, receiving nodes can be set, and the other party can send the cooperative forums to the party; however, when a third shot quality event is received, the corresponding sender needs to be verified; acquiring a sending record (a record of historically sending data to a plurality of receiving nodes, and the like) of a sender, extracting a plurality of first record items, matching the first characteristics with the second characteristics, determining whether risk characteristics possibly causing malicious events occur, and if so, determining a supplement direction, for example: the third characteristic is that the user changes identity information suddenly, and false data can be uploaded later, and the supplement direction is later; if the supplement direction cannot be determined, the second record item is proved to have a malicious event, the first combination characteristic and the second combination characteristic are respectively combined based on the two conditions and are matched with the fourth characteristic, and whether the malicious event occurs or not is determined; after the lens quality events needing to be removed are removed, determining whether the remaining lens quality events contain corresponding negative events, wherein the larger the content is, the more the evaluation target corresponding to the first attribute item needs to be evaluated;

when the second evaluation target needing to be evaluated is screened from the first evaluation target, the second evaluation target can be determined based on the attribute information of the zoom lens, the setting is reasonable, the efficiency of quality evaluation on the zoom lens is improved, and unnecessary workload is reduced; meanwhile, when the lens quality event is acquired, the incredible lens quality event is eliminated, and the accuracy and the safety of acquisition are guaranteed.

The embodiment of the invention provides a zoom lens quality evaluation method, which further comprises the following steps:

expanding a risk feature library;

wherein, expand the risk characteristic library, include:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of a first expansion node, wherein the guarantee information comprises: a second expansion node vouching the first expansion node and a first vouching value corresponding to the second expansion node;

determining a first expansion node in the second expansion nodes, taking the first expansion node as a third expansion node, and taking a first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion nodes except the third expansion node as fourth expansion nodes, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting a second guarantee value and a third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

acquiring at least one first risk characteristic through a fifth expansion node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to obtain at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is greater than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into a risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, the expansion is completed.

The working principle and the beneficial effects of the technical scheme are as follows:

the first expansion node is specifically: the network node corresponds to a risk characteristic collector and can acquire the risk characteristics collected by the collector; the preset first scoring threshold specifically includes: for example, 85; the preset forward verification model specifically comprises the following steps: a model generated after a large number of records of manual forward verification (based on a large number of malicious event data, whether the risk characteristics can cause the occurrence of malicious events in the forward direction or not) are learned by using a machine learning algorithm, wherein the larger the forward verification value is, the larger the occurrence probability of the malicious events caused by the risk characteristics is; the preset reverse verification model specifically comprises the following steps: a model generated after learning is carried out on a large number of records of manual reverse verification (whether risk characteristics exist before a malicious event is verified reversely based on a large number of malicious event data) by utilizing a machine learning algorithm, wherein the larger the reverse verification value is, the larger the probability of the risk characteristics existing before the malicious event occurs is; the preset second scoring threshold specifically includes: for example, 90;

when the collector corresponds to the first expansion node, other second expansion nodes are needed to guarantee the first expansion node (guarantee is carried out, one side generates bad records, and the other side also generates influence, such as reduction of the guarantee value); calculating a first score based on the second insurance value and the third insurance value, wherein the larger the first score is, the higher the credibility of the corresponding first expansion node is; when the first risk characteristics are obtained, forward and backward verification is needed to determine whether the risk characteristics are real, and second risk characteristics meeting conditions are screened out to expand a risk characteristic library; the efficiency of the system for discovering the risk characteristics can be further improved;

the preset first calculation model specifically includes: the model of the built-in calculation formula comprises the following calculation formula:

wherein σ is the first score, A_iFor the ith said second wager value,/, is the total number of said second wager values, B_iIs the ith said third wager value, d is the total number of said third wager values, ε₁And ε₂Is a preset weight value, and is used as a weight value,

rho is an intermediate variable;

in the formula, the second insurance value and the third insurance value are positively correlated with the first score, and as the third expansion node approved by the third party corresponding to the second insurance value acquires the guarantee of the first expansion node, the guarantee approval degree is higher, so that l-d is also positively correlated with the first score;

the preset second calculation model specifically includes: the model of the built-in calculation formula comprises the following calculation formula:

wherein γ is the second score, e is a natural constant, α_tFor the tth said forward verification value, n₁Is the total number of the forward verification values, β_tFor the t-th said reverse verification value, n₂For the total number of reverse verification values, ε is the sum of a first number of the forward verification values that are less than or equal to a preset first threshold and a second number of the reverse verification values that are less than or equal to a preset second threshold;

in the formula, the forward verification value and the reverse verification value are positively correlated with the second score, the first number and the second number are negatively correlated with the second score, and the sum of the forward verification value and the reverse verification value is also negatively correlated with the second score.

Through the formula, the first score and the second score are calculated quickly, the expansion nodes and the risk characteristics are conveniently screened, and the working efficiency of the system is improved to a great extent.

An embodiment of the present invention provides a zoom lens quality evaluation device, as shown in fig. 3, including:

the acquisition module 1 is used for acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

and the evaluation module 2 is used for evaluating the quality of the zoom lens based on the data to be evaluated.

The working principle and the beneficial effects of the technical scheme are as follows:

acquiring imaging data imaged by the zoom lens (a light source is used for emitting a light beam to pass through the lens to be imaged on an imaging device, the technology belongs to the prior art and is not described in detail), and because the imaging data belongs to optical information, photoelectric conversion is required to be carried out, and the optical information is converted into data to be evaluated, which belongs to electrical information; based on the data to be evaluated, carrying out quality evaluation on the zoom lens (for example, evaluating the image surface value, the contrast, the focal length, the depth of field, the field curvature and the like of an image);

the zoom lens quality evaluation method and device based on the data to be evaluated can help workers to quickly evaluate the lens imaging quality in production, and the evaluation result is used for carrying out optical adjustment on the zoom lens, so that the imaging quality is improved, the reject ratio is reduced, and the enterprise cost is reduced.

The embodiment of the invention provides a zoom lens quality evaluation device, wherein an acquisition module 1 executes the following operations:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

The working principle and the beneficial effects of the technical scheme are as follows:

as shown in FIG. 2, a monochromatic light source is provided (e.g., using a light source machine); a monochromatic light source is utilized to emit light beams which are sequentially transmitted through a differentiation plate (the function of the division plate is to superpose a cross wire or concentric ring pattern on an object to be imaged, the pattern can be used as a position reference and can be aligned to the object to be imaged, the cross differentiation plate or concentric ring differentiation plate can be used) and a zoom lens, imaging is carried out on a high-precision linear array CCD (Charge Coupled Device), and the acquisition of imaging data is completed.

The embodiment of the invention provides a zoom lens quality evaluation device, wherein an evaluation module 2 executes the following operations:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to a second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

The working principle and the beneficial effects of the technical scheme are as follows:

the first evaluation target is specifically: for example, evaluating contrast, evaluating depth of field effects, etc.; the preset evaluation target-evaluation model library is specifically as follows: a database containing evaluation models corresponding to different evaluation targets, for example: the evaluation target is evaluation contrast, and the corresponding evaluation model is a model generated by learning a large number of records of manual evaluation contrast by using a machine learning algorithm and is used for evaluating the contrast; the attribute information of the zoom lens is specifically: for example, material provider data of the lens, production process of the lens, manufacturer, and the like;

after the second evaluation target is determined, target data (for example, contrast data) corresponding to the evaluation target in the data to be evaluated is determined, and evaluation is performed by using a corresponding evaluation model.

The embodiment of the invention provides a zoom lens quality evaluation device, and an evaluation module 2 executes the following operations:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting a second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises the following steps: a plurality of capture strategies;

determining at least one capture object corresponding to a capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in a capture object based on a capture strategy;

if the capture is successful, acquiring a capture process for capturing a first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

acquiring the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to acquire an association relationship between the second capture scene and the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the acquisition is successful, analyzing the association relationship to acquire a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of a sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting the first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the matched second feature as a third feature, and taking a corresponding first record item as a second record item;

based on a preset feature-supplement direction library, attempting to determine at least one supplement direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

when all third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether a second lens quality event and a fourth lens quality event contain negative events or not by the event determining model, and if so, outputting a first severity value corresponding to the contained negative events and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation targets corresponding to the first attribute items according to the size of the corresponding sorting values to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

The working principle and the beneficial effects of the technical scheme are as follows:

the preset attribute type-important value library is specifically as follows: databases containing important values corresponding to different attribute types, such as: the attribute type is a lens material provider, the corresponding important value is 95, and the important value represents the influence degree of the attribute type on the lens quality; the preset importance value threshold specifically includes: for example, 75; the preset negative event generation model specifically comprises the following steps: a model generated after learning a record of a large number of artificially created negative events using a machine learning algorithm, the model may generate negative events based on attribute terms, such as: the attribute item is a certain lens material manufacturer, the negative event is the lens material produced by the manufacturer, the quality of the lens is unqualified, and the like, and a first severity value of the negative event is also output, wherein the greater the first severity value is, the more severe the corresponding negative event is; the capture strategy is specifically as follows: for example, web page crawling; the preset capture strategy-capture object library specifically comprises the following steps: data containing capture objects corresponding to different capture strategies, such as: step policy is web page crawling, and the capture objects are a plurality of shot forum websites; the preset confidence threshold specifically comprises: for example, 80; the preset relationship value threshold specifically comprises: for example, 90; the receiving node specifically comprises: a network node, the other side can send the data to the network node, namely finish the data reception; the preset inquiry mode specifically comprises the following steps: for example, whether there is newly received data, if so, please reply; the preset risk characteristic library specifically comprises the following steps: a database containing a plurality of risk features, a risk feature being a feature that may cause a malicious event, such as: the user wants to release false data and suddenly changes identity information (risk characteristics); the preset malicious feature library specifically comprises the following steps: the system comprises a plurality of malicious feature databases, wherein the malicious features are, for example: changing identity information, and checking the released data as false data; the preset range is specifically as follows: a range on the time axis corresponding to a certain length of time (e.g.: 2 days); the preset event determination model specifically includes: the model is generated after learning records for manually judging whether the events comprise certain events by utilizing a machine learning algorithm, and the model can determine whether the events comprise certain events;

when the second evaluation target to be evaluated is screened, it may be determined based on the attribute information of the zoom lens, for example: a manufacturer of production materials of the zoom lens needs to evaluate the contrast when a problem event that the contrast of lens imaging is poor due to material problems occurs; however, how to acquire problem events needs to be solved; extracting a first attribute item (such as a material provider) in attribute information, screening out a second attribute item which has an influence on a quality result based on an important value, generating a negative event corresponding to the second attribute item based on a negative event generation model, and determining whether the negative event occurs; trying to capture a shot quality event (for example, a quality evaluation article published by a certain user in a forum website), if the capture is successful, determining multiple processes in the capture process (for example, process 1, capturing a comment that the user does not "quality" in a manufacturer discussion area, process 2, capturing a homepage of the user and publishing a specific article), where a first capture scene corresponding to the processes is, for example: the process 1 corresponds to a web page of a manufacturer discussion area, and the process 2 corresponds to a web page of a user homepage; acquiring the credibility (webpage credibility) of the first capture scene, and if the credibility is smaller than a credibility threshold, taking the corresponding first capture scene as a second capture scene; trying to acquire an association relationship between a second capture scene and a capture object (for example, the second capture scene belongs to a webpage of the capture object, and the capture object guarantees the webpage to form a guarantee relationship), if the acquisition fails, it is indicated that the second capture scene is not credible (for example, from other forums), if the acquisition succeeds, the relationship (guarantee relationship) is analyzed to acquire a relationship value, and the greater the relationship value is, the greater the guarantee degree of the capture object guaranteeing the relationship is, and the higher the credibility is; some cooperative forums do not allow the party to capture in consideration of privacy security, receiving nodes can be set, and the other party can send the cooperative forums to the party; however, when a third shot quality event is received, the corresponding sender needs to be verified; acquiring a sending record (a record of historically sending data to a plurality of receiving nodes, and the like) of a sender, extracting a plurality of first record items, matching the first characteristics with the second characteristics, determining whether risk characteristics possibly causing malicious events occur, and if so, determining a supplement direction, for example: the third characteristic is that the user changes identity information suddenly, and false data can be uploaded later, and the supplement direction is later; if the supplement direction cannot be determined, the second record item is proved to have a malicious event, the first combination characteristic and the second combination characteristic are respectively combined based on the two conditions and are matched with the fourth characteristic, and whether the malicious event occurs or not is determined; after the lens quality events needing to be removed are removed, determining whether the remaining lens quality events contain corresponding negative events, wherein the larger the content is, the more the evaluation target corresponding to the first attribute item needs to be evaluated;

when the second evaluation target needing to be evaluated is screened from the first evaluation target, the second evaluation target can be determined based on the attribute information of the zoom lens, the setting is reasonable, the efficiency of quality evaluation on the zoom lens is improved, and unnecessary workload is reduced; meanwhile, when the lens quality event is acquired, the incredible lens quality event is eliminated, and the accuracy and the safety of acquisition are guaranteed.

The embodiment of the invention provides a zoom lens quality evaluation device, which further comprises:

the expansion module is used for expanding the risk characteristic library;

the expansion module performs the following operations:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of a first expansion node, wherein the guarantee information comprises: a second expansion node vouching the first expansion node and a first vouching value corresponding to the second expansion node;

determining a first expansion node in the second expansion nodes, taking the first expansion node as a third expansion node, and taking a first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion nodes except the third expansion node as fourth expansion nodes, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting a second guarantee value and a third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

acquiring at least one first risk characteristic through a fifth expansion node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to obtain at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is greater than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into a risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, the expansion is completed.

The working principle and the beneficial effects of the technical scheme are as follows:

the first expansion node is specifically: the network node corresponds to a risk characteristic collector and can acquire the risk characteristics collected by the collector; the preset first scoring threshold specifically includes: for example, 85; the preset forward verification model specifically comprises the following steps: a model generated after a large number of records of manual forward verification (based on a large number of malicious event data, whether the risk characteristics can cause the occurrence of malicious events in the forward direction or not) are learned by using a machine learning algorithm, wherein the larger the forward verification value is, the larger the occurrence probability of the malicious events caused by the risk characteristics is; the preset reverse verification model specifically comprises the following steps: a model generated after learning is carried out on a large number of records of manual reverse verification (whether risk characteristics exist before a malicious event is verified reversely based on a large number of malicious event data) by utilizing a machine learning algorithm, wherein the larger the reverse verification value is, the larger the probability of the risk characteristics existing before the malicious event occurs is; the preset second scoring threshold specifically includes: for example, 90;

when the collector corresponds to the first expansion node, other second expansion nodes are needed to guarantee the first expansion node (guarantee is carried out, one side generates bad records, and the other side also generates influence, such as reduction of the guarantee value); calculating a first score based on the second insurance value and the third insurance value, wherein the larger the first score is, the higher the credibility of the corresponding first expansion node is; when the first risk characteristics are obtained, forward and backward verification is needed to determine whether the risk characteristics are real, and second risk characteristics meeting conditions are screened out to expand a risk characteristic library; the efficiency of the system for discovering the risk characteristics can be further improved;

the preset first calculation model specifically includes: the model of the built-in calculation formula comprises the following calculation formula:

wherein σ is the first score, A_iFor the ith said second wager value,/, is the total number of said second wager values, B_iIs the ith said third wager value, d is the total number of said third wager values, ε₁And ε₂Is a preset weight value, and is used as a weight value,

rho is an intermediate variable;

in the formula, the second insurance value and the third insurance value are positively correlated with the first score, and as the third expansion node approved by the third party corresponding to the second insurance value acquires the guarantee of the first expansion node, the guarantee approval degree is higher, so that l-d is also positively correlated with the first score;

the preset second calculation model specifically includes: the model of the built-in calculation formula comprises the following calculation formula:

wherein γ is the second score, e is a natural constant, α_tFor the tth said forward verification value, n₁Is the total number of the forward verification values, β_tFor the t-th said reverse verification value, n₂Is the total number of the reverse verification values, and epsilon is less than or equal to a preset value in the forward verification valuesA sum of a first number of the forward verification values of a first threshold and a second number of the reverse verification values that is less than or equal to a preset second threshold;

in the formula, the forward verification value and the reverse verification value are positively correlated with the second score, the first number and the second number are negatively correlated with the second score, and the sum of the forward verification value and the reverse verification value is also negatively correlated with the second score.

Through the formula, the first score and the second score are calculated quickly, the expansion nodes and the risk characteristics are conveniently screened, and the working efficiency of the system is improved to a great extent.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A zoom lens quality evaluation method is characterized by comprising the following steps:

acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

and performing quality evaluation on the zoom lens based on the data to be evaluated.

2. The zoom lens quality evaluation method according to claim 1, wherein acquiring imaging data of the zoom lens comprises:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

3. The zoom lens quality evaluation method according to claim 1, wherein performing quality evaluation on the zoom lens based on the data to be evaluated comprises:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to the second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

4. The zoom lens quality evaluation method according to claim 3, wherein the step of screening out a second evaluation target to be evaluated from the first evaluation targets based on the attribute information comprises:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting the second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises: a plurality of capture strategies;

determining at least one capture object corresponding to the capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in the capture object based on the capture strategy;

if the capture is successful, acquiring a capture process for capturing the first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

obtaining the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to obtain an association of the second capture scene with the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the association relationship is successfully obtained, analyzing the association relationship to obtain a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when the first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of the sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting a first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the second feature matched with the first feature as a third feature, and simultaneously taking the corresponding first record item as a second record item;

based on a preset feature-supplementary direction library, attempting to determine at least one supplementary direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing the corresponding third lens quality event;

when all the third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether the second lens quality event and the fourth lens quality event contain the negative event or not by the event determining model, if so, outputting the first severity value corresponding to the contained negative event, and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation target corresponding to the first attribute item according to the size of the sorting value to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

5. The zoom lens quality evaluation method according to claim 4, further comprising:

expanding the risk feature library;

wherein, expanding the risk feature library comprises:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of the first expansion node, wherein the guarantee information comprises: a second expansion node vouching for the first expansion node and a first vouching value corresponding to the second expansion node;

determining the first expansion node in the second expansion nodes to be used as a third expansion node, and simultaneously using the first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion node except the third expansion node as a fourth expansion node, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting the second guarantee value and the third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

obtaining at least one first risk characteristic by the fifth augmented node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to acquire at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is larger than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into the risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, completing the expansion.

6. A zoom lens quality evaluation device is characterized by comprising:

the acquisition module is used for acquiring imaging data of the zoom lens, and performing photoelectric conversion on the imaging data to obtain data to be evaluated;

and the evaluation module is used for evaluating the quality of the zoom lens based on the data to be evaluated.

7. The zoom lens quality evaluation device according to claim 6, wherein the obtaining module performs the following operations:

providing a monochromatic light source;

and the monochromatic light source is used for emitting light beams which are sequentially transmitted through the differentiation plate and the zoom lens to form images on the high-precision linear array CCD, and imaging data are obtained.

8. The zoom lens quality evaluation device according to claim 6, wherein the evaluation module performs the following operations:

acquiring a preset evaluation target set, wherein the evaluation target set comprises: a plurality of first evaluation targets;

acquiring attribute information of the zoom lens, and screening out a second evaluation target needing evaluation from the first evaluation target based on the attribute information;

extracting target data corresponding to the second evaluation target from the data to be evaluated;

determining an evaluation model corresponding to the second evaluation target based on a preset evaluation target-evaluation model library;

and inputting the target data into the corresponding evaluation model to obtain an evaluation result.

9. The zoom lens quality evaluation device according to claim 8, wherein the evaluation module performs the following operations:

extracting a plurality of first attribute items in the attribute information;

acquiring the attribute type of the first attribute item, and determining an important value corresponding to the attribute type based on a preset attribute type-important value library;

if the importance value is larger than or equal to a preset importance value threshold, taking the corresponding first attribute item as a second attribute item;

acquiring a preset negative event generation model, inputting the second attribute item into the negative event generation model, and acquiring at least one negative event and a first severity value corresponding to the negative event;

acquiring a preset capturing strategy set, wherein the capturing strategy set comprises: a plurality of capture strategies;

determining at least one capture object corresponding to the capture strategy based on a preset capture strategy-capture object library;

attempting to capture at least one first shot quality event in the capture object based on the capture strategy;

if the capture is successful, acquiring a capture process for capturing the first lens quality event;

carrying out flow splitting on the capturing flow to obtain a plurality of flows;

extracting at least one first captured scene in the flow;

obtaining the credibility of the first captured scene;

if the credibility is less than or equal to a preset credibility threshold value, taking the corresponding first capturing scene as a second capturing scene;

attempting to obtain an association of the second capture scene with the capture object;

if the acquisition fails, rejecting the corresponding first lens quality event;

if the association relationship is successfully obtained, analyzing the association relationship to obtain a relationship value;

if the relation value is smaller than or equal to a preset relation value threshold value, rejecting the corresponding first lens quality event;

when the first lens quality events needing to be removed in the first lens quality events are all removed, taking the remaining first lens quality events as second lens quality events;

acquiring a preset receiving node set, wherein the receiving node set comprises: a plurality of receiving nodes;

inquiring the receiving node at regular time based on a preset inquiring mode, and acquiring at least one third lens quality event replied by the inquired receiving node and at least one sender corresponding to the third lens quality event;

acquiring a sending record of the sender;

extracting a plurality of first record items in the sending record;

establishing a time axis, and setting a first record item on a corresponding time node on the time axis based on the generation time of the first record item;

performing feature extraction on the first record item to obtain a plurality of first features;

acquiring a preset risk feature library, matching the first feature with a second feature in the risk feature library, if the first feature is matched with the second feature in the risk feature library, taking the second feature matched with the first feature as a third feature, and simultaneously taking the corresponding first record item as a second record item;

based on a preset feature-supplementary direction library, attempting to determine at least one supplementary direction corresponding to the third feature;

if the determination fails, randomly combining the first features obtained by feature extraction on the second record item to obtain a plurality of first combined features;

acquiring a preset malicious feature library, matching the first combined feature with a fourth feature in the malicious feature library, and if the first combined feature is matched with the fourth feature in the malicious feature library, removing a corresponding third lens quality event;

if the determination is successful, selecting at least one first record item in a preset range in the supplement direction of the second record item on the time axis as a third record item;

performing feature extraction on the third record item to obtain a plurality of fifth features;

randomly combining the first feature and the fifth feature obtained by feature extraction on the second record item to obtain a plurality of second combined features;

matching the second combined feature with a fourth feature in the malicious feature library, and if the second combined feature is matched with the fourth feature in the malicious feature library, removing the corresponding third lens quality event;

when all the third lens quality events needing to be removed in the third lens quality events are removed, taking the remaining third lens quality events as fourth lens quality events;

acquiring a preset event determining model, determining whether the second lens quality event and the fourth lens quality event contain the negative event or not by the event determining model, if so, outputting the first severity value corresponding to the contained negative event, and taking the first severity value as a second severity value;

summarizing the second severity value to obtain a ranking value;

sorting the first evaluation target corresponding to the first attribute item according to the size of the sorting value to obtain an evaluation target sequence;

and selecting the first n first evaluation targets in the evaluation target sequence as second evaluation targets to complete screening.

10. The zoom lens quality evaluation device according to claim 9, further comprising:

the expansion module is used for expanding the risk characteristic library;

the expansion module performs the following operations:

acquiring a preset expansion node set, wherein the expansion node set comprises: a plurality of first expansion nodes;

obtaining guarantee information of the first expansion node, wherein the guarantee information comprises: a second expansion node vouching for the first expansion node and a first vouching value corresponding to the second expansion node;

determining the first expansion node in the second expansion nodes to be used as a third expansion node, and simultaneously using the first insurance value corresponding to the third expansion node as a second insurance value;

taking the second expansion node except the third expansion node as a fourth expansion node, and taking the first insurance value corresponding to the fourth expansion node as a third insurance value;

acquiring a preset first calculation model, inputting the second guarantee value and the third guarantee value into the first calculation model, and acquiring a first score;

if the first score is larger than or equal to a preset first score threshold value, taking the corresponding first expansion node as a fifth expansion node;

obtaining at least one first risk characteristic by the fifth augmented node;

acquiring a preset forward verification model, and inputting the first risk characteristics into the forward verification model to acquire at least one forward verification value;

acquiring a preset reverse verification model, and inputting the first risk characteristics into the reverse verification model to obtain at least one reverse verification value;

acquiring a preset second calculation model, and inputting the forward verification value and the reverse verification value into the second calculation model to obtain a second score;

if the second score is larger than or equal to a preset second score threshold value, taking the corresponding first risk feature as a second risk feature;

storing the second risk characteristics into the risk characteristic library;

and when the second risk characteristics which need to be stored in the risk characteristic library are stored, completing the expansion.

Images