CN117633277A

CN117633277A - Asset verification method, asset verification device, computer readable medium and electronic device

Info

Publication number: CN117633277A
Application number: CN202211000688.4A
Authority: CN
Inventors: 江胜; 淦小健; 陈琴
Original assignee: Fengtu Technology Shenzhen Co Ltd
Current assignee: Fengtu Technology Shenzhen Co Ltd
Priority date: 2022-08-19
Filing date: 2022-08-19
Publication date: 2024-03-01

Abstract

Embodiments of the present application provide an asset verification method, apparatus, computer readable medium, and electronic device. The asset verification method, apparatus, computer readable medium and electronic device include: acquiring asset information to be queried; acquiring verification master data according to the asset coordinates to be queried, wherein the verification master data are master data in a preset range around the asset coordinates to be queried; judging whether the asset pictures to be queried have the same scene type assets or not; and if the asset pictures to be queried do not have the assets with the same scene type, performing fuzzy search in the verification master data according to the asset tags to be queried to obtain an asset verification result. Compared with the prior art, the picture acquired through the common mobile terminal can be identified through the manual or professional equipment disassembling mode, the crowdsourcing data with low cost can be adopted, the asset verification period is shortened, and the timeliness of asset verification is guaranteed.

Description

Asset verification method, asset verification device, computer readable medium and electronic device

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to an asset verification method, an asset verification device, a computer readable medium, and an electronic device.

Background

As economies develop, various material assets become enriched, and management and maintenance of material assets becomes a difficult problem. At present, a manual inspection and registration mode is still commonly adopted for the maintenance of material assets, or a mode of manually carrying out post-treatment after professional equipment acquisition is adopted, and the problems that the maintenance period is long, the update is not timely and a large amount of manpower is required to be consumed exist in any mode.

Disclosure of Invention

Embodiments of the present application provide an asset verification method, apparatus, computer readable medium, and electronic device, so as to improve timeliness of asset verification at least to some extent, and reduce cost of asset verification.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned in part by the practice of the application.

According to one aspect of embodiments of the present application, there is provided an asset verification method, the method comprising:

acquiring asset information to be queried, wherein the asset information to be queried comprises an asset picture to be queried containing an asset to be queried, asset coordinates corresponding to the asset to be queried and an asset label corresponding to the asset to be queried;

Acquiring verification master data according to the asset coordinates to be queried, wherein the verification master data are master data in a preset range around the asset coordinates to be queried;

judging whether the asset pictures to be queried have the same scene type assets or not;

and if the asset pictures to be queried do not have the same type of assets in the same scene, performing fuzzy search in the verification master data according to the asset tags to be queried to obtain an asset verification result, wherein the asset verification result comprises that the asset to be queried is an existing asset, a newly added asset or an asset to be checked.

In one embodiment of the present application, fuzzy search is performed in the verification master data to obtain a search result of whether verification asset information is searched;

if the search result is that a plurality of pieces of verification asset information are obtained, carrying out background feature matching on the asset information to be queried and the plurality of pieces of verification asset information to obtain an asset verification result;

if the search result is that the check asset information is obtained, judging that the asset to be queried is the existing asset;

and if the search result is that any verification asset information is not obtained, querying all the master asset pictures in the verification master data, and comparing the master asset pictures with the asset pictures to be queried to obtain an asset verification result.

In an embodiment of the present application, if the search result is that a plurality of pieces of verification asset information are obtained, performing background feature matching on the asset information to be queried and the plurality of pieces of verification asset information to obtain an asset verification result, which specifically includes:

if the similarity of the to-be-queried asset information and the check asset information is greater than a preset first similarity threshold value, judging that the to-be-queried asset is an existing asset;

and if the similarity of the asset information to be queried and the verification asset information is smaller than a preset first similarity threshold value, querying all the master asset pictures in the verification master data, and comparing with the asset pictures to be queried to obtain an asset verification result.

In one embodiment of the present application, the querying all the master asset pictures in the verification master data and comparing with the asset pictures to be queried to obtain an asset verification result specifically includes:

if the verification master data contains master asset pictures with similarity to the asset pictures to be queried being greater than a second similarity threshold, judging the asset to be queried as an asset to be checked;

and if the verification master data does not have master asset pictures with the similarity to the asset pictures to be queried being greater than a second similarity threshold, judging that the asset to be queried is a newly added asset.

In one embodiment of the present application, after the determining whether the asset picture to be queried has the asset of the same scene type, the method further includes:

and if the asset pictures to be queried have the same scene type, querying all the master asset pictures in the verification master data, and comparing the master asset pictures with the asset pictures to be queried to obtain an asset verification result.

In an embodiment of the present application, if the asset pictures to be queried have the same scene type of assets, querying all the master asset pictures in the verification master data, and comparing the master asset pictures with the asset pictures to be queried to obtain an asset verification result, which specifically includes:

if the verification master data contains master asset pictures with similarity to the asset pictures to be queried being greater than a second similarity threshold, judging that the asset to be queried is an existing asset;

and if the verification master data does not have master asset pictures with the similarity to the asset pictures to be queried being greater than a second similarity threshold, judging the asset to be queried as a asset to be checked.

In one embodiment of the present application, before the obtaining the asset picture to be queried and the asset coordinates corresponding to the asset in the asset picture and the asset tag corresponding to the asset in the asset picture, the method further includes:

Acquiring a plurality of asset pictures to be queried;

performing data cleaning on a plurality of asset pictures to be queried to obtain preliminary processing pictures;

detecting the assets in the preliminary processing picture to obtain asset coordinates and asset tags;

and clustering the assets to be queried according to the asset coordinates and the asset labels to obtain the asset information to be queried.

In one embodiment of the present application, the performing data cleaning on the plurality of asset pictures to obtain a preliminary processing picture specifically includes:

identifying the assets to be queried in the asset picture to be queried to obtain an asset identification frame;

and filtering the asset identification frame smaller than the preset size to obtain a preliminary processing picture.

and filtering the asset identification frames which are positioned outside the preset identification range to obtain the preliminary processing picture.

Identifying the assets to be queried in the asset picture to be queried to obtain corresponding asset tags to be queried;

and if two or more identical asset tags exist in the asset picture, marking the identical asset tags to obtain a preliminary processing picture.

In one embodiment of the present application, the detecting the asset in the preliminary processing picture to obtain the asset coordinates and the corresponding tag specifically includes:

detecting the preliminary processing picture to obtain an asset identification frame, and obtaining asset coordinates according to the identification frame;

and classifying the assets in the identification frame based on the asset identification frame, and acquiring tag information corresponding to the assets.

According to an aspect of embodiments of the present application, there is provided an asset verification device, the asset verification device including:

the asset acquisition module is used for acquiring asset information to be queried, wherein the asset information to be queried comprises an asset picture to be queried containing an asset to be queried, asset coordinates to be queried corresponding to the asset to be queried and an asset label to be queried corresponding to the asset to be queried;

the master acquisition module is used for acquiring verification master data according to the asset coordinates to be queried, wherein the verification master data are master data in a preset range around the asset coordinates to be queried;

The picture judging module is used for judging whether the asset picture to be inquired has the same scene and the same type of asset;

and the fuzzy search module is used for carrying out fuzzy search in the verification master data according to the asset tag to be queried to obtain an asset verification result if the asset picture to be queried does not have the asset with the same scene type, wherein the asset verification result comprises that the asset to be queried is an existing asset, a newly added asset or an asset to be checked.

According to one aspect of the embodiments of the present application, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements an asset verification method as described in the above embodiments.

According to an aspect of an embodiment of the present application, there is provided an electronic device including: one or more processors; and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the asset verification method as described in the above embodiments.

In the technical schemes provided by some embodiments of the present application, information of an asset to be queried is obtained first, then the approximate position of the asset to be queried is determined according to the coordinates of the asset to be queried, and then the master data in a predetermined range around the coordinates of the asset to be queried is obtained, namely, the master data is checked, then whether the same scene type asset exists in the picture of the asset to be queried is judged, if the same scene type asset does not exist, fuzzy search is performed according to the label of the asset to be queried, and the asset to be queried is further determined to be the existing asset, the newly added asset or the asset to be queried according to the result of the fuzzy search. Compared with the prior art, the picture acquired through the common mobile terminal can be identified through the manual or professional equipment disassembling mode, the crowdsourcing data with low cost can be adopted, the asset verification period is shortened, and the timeliness of asset verification is guaranteed.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application may be applied.

FIG. 2 schematically illustrates a flow chart of an asset verification method according to one embodiment of the present application.

FIG. 3 is a flow chart of yet another implementation of a method of asset verification according to the corresponding embodiment of FIG. 2.

Fig. 4 is a flowchart of one implementation of step S800 in the method of asset verification shown in accordance with the corresponding embodiment of fig. 2.

Fig. 5 is a flowchart of one implementation of step S820 in the method of asset verification shown in accordance with the corresponding embodiment of fig. 4.

Fig. 6 is a flowchart of one implementation of step S900 in the method of asset verification shown in accordance with the corresponding embodiment of fig. 2.

Fig. 7 schematically illustrates a block diagram of an asset verification device according to one embodiment of the present application.

Fig. 8 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

As shown in fig. 1, the system architecture may include a terminal device (such as one or more of the smartphone 101, tablet 102, and portable computer 103 shown in fig. 1, but of course, a desktop computer, etc.), a network 104, and a server 105. The network 104 is the medium used to provide communication links between the terminal devices and the server 105. The network 104 may include various connection types, such as wired communication links, wireless communication links, and the like.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.

A user may interact with the server 105 via the network 104 using a terminal device to receive or send messages or the like. The server 105 may be a server providing various services. For example, the user uploads the information of the asset to be queried to the server 105 by using the terminal device 103 (may also be the terminal device 101 or 102), and the server 105 may obtain verification master data according to the coordinates of the asset to be queried, where the verification master data is master data in a predetermined range around the coordinates of the asset to be queried; judging whether the asset pictures to be queried have the same scene type assets or not; and if the asset pictures to be queried do not have the same type of assets in the same scene, performing fuzzy search in the verification master data according to the asset tags to be queried to obtain an asset verification result, wherein the asset verification result comprises that the asset to be queried is an existing asset, a newly added asset or an asset to be checked.

It should be noted that the asset verification method provided in the embodiments of the present application is generally performed by the server 105, and accordingly, the asset verification device is generally disposed in the server 105. However, in other embodiments of the present application, the terminal device may also have similar functionality as the server, thereby performing the asset verification scheme provided by embodiments of the present application.

The implementation details of the technical solutions of the embodiments of the present application are described in detail below:

fig. 2 illustrates a flow chart of an asset verification method according to one embodiment of the present application, which may be performed by a server, which may be the server illustrated in fig. 1. Referring to fig. 2, the asset verification method may specifically include the steps of:

step S500, obtaining asset information to be queried, wherein the asset information to be queried comprises an asset picture to be queried containing an asset to be queried, asset coordinates to be queried corresponding to the asset to be queried and asset tags to be queried corresponding to the asset to be queried.

And step S600, obtaining verification master data according to the asset coordinates to be queried, wherein the verification master data are master data in a preset range around the asset coordinates to be queried.

And step S700, judging whether the asset picture to be queried has the same scene type asset.

Step S800, if there are no assets of the same scene type in the asset picture to be queried, performing fuzzy search in the verification master data according to the asset tag to be queried to obtain an asset verification result, where the asset verification result includes that the asset to be queried is an existing asset, a newly added asset or an asset to be verified.

In this embodiment, the information of the asset to be queried is obtained first, then, according to the asset coordinates of the asset to be queried, the master data within a predetermined range around the asset is obtained in the master database, that is, the master data is checked, then, whether the asset with the same scene type exists in the picture of the asset to be queried is judged, if the asset with the same scene type does not exist, the fuzzy search is performed in the master data is checked according to the asset coordinates of the asset to be queried, and the asset verification result is determined according to the fuzzy search result, that is, whether the asset to be queried is the existing asset, the newly added asset or the asset to be checked is determined. Compared with the prior art, the picture acquired through the common mobile terminal can be identified through the manual or professional equipment disassembling mode, the crowdsourcing data with low cost can be adopted, the asset verification period is shortened, and the timeliness of asset verification is guaranteed.

The above-mentioned coordinates of the asset to be queried are the coordinates of the asset to be queried in the physical space, which can be embodied in a longitude and latitude manner.

Master data is data from a master database that is previously collected asset-related data for the corresponding locale. The master database is pre-established with data, such as asset coordinates, asset types, asset tags, etc., associated with the assets of the corresponding locale stored therein. The acquisition of the master data can be formed by clustering after being scanned in advance by professional acquisition equipment, and the master data can be updated according to the asset verification condition after each asset verification.

The master data within a predetermined range around the asset is master data within a predetermined range around the asset to be queried, for example, master data within 10m around the asset to be queried. The predetermined range is related to accuracy, which may be 10m, 20m, 50m, etc., and is not limited herein.

In this embodiment, step S600 and step S700 may be performed synchronously or asynchronously.

In step S500, the asset information to be queried includes an asset picture to be queried including the asset to be queried, the asset coordinates to be queried corresponding to the asset to be queried, and the asset tag to be queried corresponding to the asset to be queried.

The acquisition mode and channel of the asset information to be queried can be scanning shooting through acquisition equipment such as a mobile phone, a camera and the like, acquisition through crowdsourcing data, crawling through a network and the like.

In some embodiments of the present application, as shown in fig. 3, before step S500, the method further includes:

and step S100, acquiring a plurality of asset pictures to be queried.

And step S200, cleaning data of the asset pictures to be queried to obtain preliminary processing pictures.

And step S300, detecting the assets in the preliminary processing picture to obtain asset coordinates and asset tags.

And step S400, clustering the assets to be queried according to the asset coordinates and the asset tags to obtain the asset information to be queried.

In the present embodiment, steps S100 to S400 are preprocessing steps.

Generally, the asset pictures to be queried are obtained from the collected resource packages, and there are multiple asset pictures to be queried in one resource package, so in step S100, multiple asset pictures to be queried are obtained.

After the plurality of the asset pictures to be queried are acquired, in step S200, data cleaning is required, and attention is paid to filtering or distinguishing the unsatisfactory asset images in the asset pictures to be queried, such as undersize, incomplete and the same type.

Specifically, in some embodiments, the following embodiments may be referred to for a specific implementation of step S200. The present embodiment is a detailed description of step S200 in an asset verification method according to the corresponding embodiment of fig. 3, where step S200 may include the following steps:

and identifying the assets to be queried in the asset to be queried picture to obtain an asset identification frame.

The main principle of the filtering method is that asset identification is firstly performed on the asset picture to be queried to obtain a plurality of corresponding asset identification frames, and then undersize identification frames in the asset identification frames are filtered, so that the corresponding assets are not identified in the formal identification. The dimensional concept in this embodiment includes the area of the asset identification frame and the ratio of width to length, and when the width to length of one asset identification frame is too short or the area is too small, it may affect the identification, so they may be considered as undersized and filtered out without meeting the predetermined dimensional conditions.

In other embodiments, the filtering of the small-size asset may be solved by a small-size filtering model, that is, the asset picture to be queried is input into the small-size filtering model, and the filtered preliminary processing picture is output.

The main principle of the present embodiment is to perform asset identification on an asset picture to be queried to obtain a plurality of corresponding asset identification frames, and then filter out identification frames (for example, identification frames located at edges of the asset identification frames) outside a predetermined identification range, so that assets corresponding to the identification frames outside the predetermined identification range are not identified during formal identification. In this embodiment, the asset identification frame can be identified as a defective frame and filtered out as long as the coordinates of the asset identification frame are located at the edge of the picture, i.e., outside the predetermined identification range defined in this embodiment.

The predetermined recognition range may be a middle position between two side edges of the asset picture to be queried, a middle position surrounded by peripheral edges, and the like, which is not limited herein.

In other embodiments, the filtering of the incomplete asset may be also solved by an incomplete filtering model, that is, the asset picture to be queried is input into the incomplete filtering model, and the filtered preliminary processing picture is output.

and identifying the assets to be queried in the asset to be queried picture to obtain corresponding asset tags to be queried.

The main principle of the method is that asset identification is firstly carried out on the asset pictures to be queried to obtain a plurality of corresponding asset tags, then whether the same asset tags exist or not is searched in the asset tags, and if yes, the asset tags are marked so as to facilitate screening in the follow-up steps.

In other embodiments, the screening of the assets with the same scene type can be solved through the asset model with the same scene type, namely, the asset picture to be queried is input into the asset model with the same scene type, and the output is the marked preliminary processing picture.

In step S300, asset identification is performed on the primary processed picture that has been cleaned, and corresponding asset coordinates and asset tags are obtained, where the asset coordinates are coordinates of an asset identification frame.

Specifically, in some embodiments, the following embodiments may be referred to for a specific implementation of step S300. The present embodiment is a detailed description of step S300 in an asset verification method according to the corresponding embodiment of fig. 3, where step S300 may include the following steps:

and detecting the preliminary processing picture to obtain an asset identification frame, and obtaining asset coordinates according to the identification frame.

In this embodiment, the preliminary processing picture is detected first to obtain the asset identification frame, and the coordinates of the asset identification frame are used as the asset coordinates. And then, based on the asset identification frame, identifying and classifying the assets in the frame to obtain corresponding asset types, and further determining the tag information corresponding to the assets.

The asset type has different classification methods in different application fields, for example, in the traffic field, the classification can be classified according to warning marks, forbidden marks, indication marks, road indication marks, tourist area marks, road construction safety marks, indication lamps and the like. In municipal administration field, can classify according to street lamp, garbage bin, well lid etc..

In step S400, clustering the asset coordinates and the asset tags obtained in step S300 by using a DBSCAN algorithm, and clustering the same asset in different asset pictures to obtain final asset information to be queried.

Specifically, according to the asset coordinates and the asset tags, the assets with similar coordinates and the same asset tag type are clustered into one asset, so that the problem of repeated identification is avoided.

In step S600, according to the asset coordinates of the asset to be queried, the master data of the periphery of the asset, i.e. the verification master data, is obtained in the master database. The master database is pre-established with data relating to the assets of the corresponding locale stored therein. The acquisition of the master data can be formed by clustering after being scanned in advance by professional acquisition equipment, and the master data can be updated according to the asset verification condition after each asset verification.

The predetermined range may be a range within 50 meters, within 100 meters or within 150 meters around the coordinates of the asset to be queried, and may be flexibly adjusted according to the positioning accuracy of the acquisition device, which is not limited herein.

In step S700, determining whether the asset picture to be queried has the same scene type asset may be determined according to the tag marked in step S200, or may be determined by a specific step in step S200, which is not limited herein.

If it is determined that the asset picture to be queried does not have the asset of the same scene type, step S800 is performed. In step S800, fuzzy search is performed in the verification master data according to the asset tag to be queried, and master data matched with the asset tag to be queried is searched.

Specifically, in some embodiments, the specific implementation of step S800 may refer to fig. 4. Fig. 4 is a detailed description of step S800 in the asset verification method according to the corresponding embodiment of fig. 2, in which step S800 may include the steps of:

step 810, performing fuzzy search in the verification master data according to the asset tag to be queried to obtain a search result, wherein the search result comprises the number of the retrieved verification asset information.

And step S820, if the search result is that a plurality of pieces of verification asset information are obtained, carrying out background feature matching on the asset information to be queried and the plurality of pieces of verification asset information to obtain an asset verification result.

Step S830, if the search result is that the check asset information is obtained, determining that the asset to be queried is an existing asset.

Step S840, if the search result is that any verification asset information is not obtained, querying all the master asset pictures in the verification master data, and comparing with the asset pictures to be queried to obtain an asset verification result.

In this embodiment, fuzzy search is performed in the verification master data according to the to-be-queried asset tag, so as to obtain a search result, the search result includes the number of the retrieved verification asset information, if the search result is that a plurality of verification asset information are retrieved, background feature matching is performed with the verification asset information, an asset verification result is determined according to the background feature matching result, if the search result is that one verification asset information is retrieved, it is proved that the to-be-queried asset is the verification asset, the to-be-queried asset can be directly determined to be the existing asset, if the search result is that no verification asset information is retrieved, all master asset pictures in the verification master data are queried, comparison is performed with the to-be-queried asset pictures, and the asset verification result is determined according to the comparison result.

In step S810, the fuzzy search is performed by traversing, specifically, matching the asset tag to be queried with the check asset tag in the check master data one by one, and if the check asset tag can be matched with the asset tag to be queried, obtaining the check asset information corresponding to the check asset tag. If one check asset tag can be matched with the to-be-queried asset tag, the search result is that one check asset information is obtained, if a plurality of check asset tags can be matched with the to-be-queried asset tag, the search result is that a plurality of check asset information is obtained, and if no check asset tag can be matched with the to-be-queried asset tag, the search result is that no check asset information is obtained.

When the search result is that a plurality of pieces of verification asset information are obtained, the periphery of the asset to be queried is proved to have the asset with the same type as the asset to be queried, step S820 is executed, and background feature matching is carried out on the asset information to be queried and the verification asset information, so that an asset verification result is obtained.

Specifically, in some embodiments, the specific implementation of step S820 may refer to fig. 5. Fig. 5 is a detailed description of step S820 in the asset verification method according to the corresponding embodiment of fig. 4, in which step S820 may include the steps of:

step S821, if the similarity between the to-be-queried asset information and the check asset information is greater than a predetermined first similarity threshold, determining that the to-be-queried asset is an existing asset.

Step S822, if the similarity between the to-be-queried asset information and the verification asset information is smaller than a predetermined first similarity threshold, querying all the master asset pictures in the verification master data, and comparing with the to-be-queried asset pictures to obtain an asset verification result.

In this embodiment, the to-be-queried asset information and the check asset information are subjected to background feature matching, the similarity between the environmental features around the to-be-queried asset and the environmental features around the check asset is determined, if the similarity is greater than a predetermined first similarity threshold, the to-be-queried asset is proved to be the check asset which is the existing asset stored in the master database, if the similarity is less than the predetermined first similarity threshold, the to-be-queried asset is proved to be not the check asset which may be a new asset which is not entered in the master data, all master asset pictures in the check master data need to be queried, and comparison is performed with the to-be-queried asset pictures so as to further verify.

Specifically, in some embodiments, the following embodiments may be referred to for a specific implementation of step S822. The present embodiment is a detailed description of step S822 in an asset verification method according to the corresponding embodiment of fig. 5, where step S822 may include the following steps:

and if the verification master data contains master asset pictures with similarity to the asset pictures to be queried being greater than a second similarity threshold, judging the asset to be queried as an asset to be checked.

In this embodiment, whether the verification master data has a similar master picture is queried, where the similar master picture is a master asset picture whose similarity with the asset picture to be queried is greater than a second similarity threshold. If the similar master image exists in the verification master data, the asset corresponding to the suspected similar master image of the asset to be queried is proved to be possibly in error judgment, and further verification is needed manually, namely the asset to be checked is judged to be the asset to be checked. For the assets to be verified, in the embodiment of the application, the assets to be verified are sent to a manual end for further verification, and whether the assets are newly added assets or existing assets is judged manually. And if the verification master data does not have the similar master picture, proving that the asset to be queried is not recorded in the master data, wherein the asset to be queried is a new asset which is not recorded in the master data.

When the search result is that the check asset information is obtained, the asset to be queried is proved to be the check asset, and step S830 is executed to determine that the asset to be queried is an existing asset, and the information of the asset to be queried and the check asset are stored in the master data in association.

When the search result is that no verification asset information is obtained, it is proved that no asset with the same type as the asset to be queried is available around the asset to be queried, step S840 is executed, all the master asset pictures in the verification master data are queried, and comparison is performed with the asset pictures to be queried, so that an asset verification result is obtained.

Specifically, in some embodiments, the following embodiments may be referred to for a specific implementation of step S840. The present embodiment is a detailed description of step S840 in an asset verification method according to the corresponding embodiment of fig. 4, where step S840 may include the following steps:

In this embodiment, when the search result indicates that no check asset information is obtained, the check master data needs to be further queried, all master asset pictures in the check master data are compared with the asset picture to be queried, and whether similar master asset pictures exist in the check master data is determined, wherein the similar master asset pictures refer to master asset pictures with similarity to the asset picture to be queried being greater than a second similarity threshold. If the similar master image exists in the verification master data, the asset corresponding to the suspected similar master image of the asset to be queried is proved to be possibly in error judgment, and further verification is needed manually, namely the asset to be checked is judged to be the asset to be checked. For the assets to be verified, in the embodiment of the application, the assets to be verified are sent to a manual end for further verification, and whether the assets are newly added assets or existing assets is judged manually. And if the verification master data does not have the similar master picture, proving that the asset to be queried is not recorded in the master data, and the asset to be queried is really a new asset which is not recorded in the master data.

In some embodiments of the present application, after step S700, the method further comprises:

and step S900, if the asset pictures to be queried have the same scene type, querying all the master asset pictures in the verification master data, and comparing the master asset pictures with the asset pictures to be queried to obtain an asset verification result.

If it is determined that the asset picture to be queried has the same scene type asset, step S900 is performed. In step S900, all the master asset pictures in the verification master data are queried, and compared with the asset pictures to be queried, so as to obtain an asset verification result.

When it is determined that the same-scene type assets exist in the to-be-queried asset pictures, since the same-type assets exist in one picture, the common feature comparison and the similarity verification cannot be influenced by the same-type assets, so that the accuracy is reduced, the asset verification result cannot be well determined, in some embodiments, the to-be-queried asset can be directly calibrated to be the to-be-verified asset, and then sent to the manual end, and the asset verification is performed in a manual verification mode.

In some embodiments of the present application, asset verification may also be performed semi-manually.

Specifically, in some embodiments, the specific implementation of step S900 may refer to fig. 6. Fig. 6 is a detailed description of step S900 in the asset verification method according to the corresponding embodiment of fig. 2, where step S900 may include the steps of:

step S910, if the checked master data has a master asset picture whose similarity to the asset picture to be queried is greater than a second similarity threshold, determining that the asset to be queried is an existing asset.

Step S920, if the verification master data has no master asset picture with similarity to the asset picture to be queried greater than a second similarity threshold, determining that the asset to be queried is an asset to be checked.

In this embodiment, when it is determined that the asset picture to be queried has the same scene type asset, only check master data is needed to be queried directly, all master asset pictures in the check master data are compared with the asset picture to be queried, whether similar master pictures exist in the check master data is determined, and the similar master pictures refer to master asset pictures with similarity to the asset picture to be queried being greater than a second similarity threshold. And if the similar master image exists in the verification master data, proving that the asset to be queried is the asset corresponding to the similar master image, wherein the asset is the existing asset which is recorded in the master data. If the verification master data does not have the similar master pictures, the fact that the asset to be queried is possibly not recorded in the master data or is possibly influenced by the same scene type is proved, and at the moment, the asset to be queried is needed to be further verified manually, namely the asset to be checked is. For the assets to be verified, in the embodiment of the application, the assets to be verified are sent to a manual end for further verification, and whether the assets are newly added assets or existing assets is judged manually.

The following describes apparatus embodiments of the present application that may be used to perform the asset verification methods of the above-described embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the embodiments of the asset verification method described in the present application.

FIG. 7 illustrates a block diagram of an asset verification device according to one embodiment of the present application.

Referring to fig. 7, an asset verification apparatus 900 according to an embodiment of the present application includes:

the asset acquisition module 910 is configured to acquire asset information to be queried, where the asset information to be queried includes an asset picture to be queried including an asset to be queried, an asset coordinate to be queried corresponding to the asset to be queried, and an asset tag to be queried corresponding to the asset to be queried.

And the master acquisition module 920 is configured to acquire verification master data according to the asset coordinates to be queried, where the verification master data is master data in a predetermined range around the asset coordinates to be queried.

And the picture judging module 930 is configured to judge whether the asset picture to be queried has the asset with the same scene type.

And the fuzzy search module 940 is configured to perform fuzzy search in the verification master data according to the asset tag to be queried to obtain an asset verification result if the asset of the same scene type does not exist in the asset picture to be queried, where the asset verification result includes that the asset to be queried is an existing asset, a newly added asset or a asset to be verified.

It should be noted that, the computer system of the electronic device shown in fig. 8 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 8, the computer system includes a central processing unit (Central Processing Unit, CPU) 1801, which can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1802 or a program loaded from a storage section 1808 into a random access Memory (Random Access Memory, RAM) 1803. In the RAM 1803, various programs and data required for system operation are also stored. The CPU 1801, ROM 1802, and RAM 1803 are connected to each other via a bus 1804. An Input/Output (I/O) interface 1805 is also connected to the bus 1804.

The following components are connected to the I/O interface 1805: an input section 1806 including a keyboard, a mouse, and the like; an output portion 1807 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker, etc.; a storage section 1808 including a hard disk or the like; and a communication section 1809 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1809 performs communication processing via a network such as the internet. The drive 1810 is also connected to the I/O interface 1805 as needed. Removable media 1811, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memory, and the like, is installed as needed on drive 1810 so that a computer program read therefrom is installed as needed into storage portion 1808.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1809, and/or installed from the removable medium 1811. The computer programs, when executed by a Central Processing Unit (CPU) 1801, perform the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. An asset verification method, the method comprising:

2. The asset verification method as claimed in claim 1, wherein if the asset picture to be queried does not have the same scene type asset, performing fuzzy search in the verification master data according to the asset tag to be queried to obtain an asset verification result, comprising the following steps:

performing fuzzy search in the verification master data according to the asset tag to be queried to obtain a search result, wherein the search result comprises the number of the retrieved verification asset information;

3. The asset verification method as claimed in claim 2, wherein if the search result is that a plurality of the check asset information are obtained, performing background feature matching on the asset information to be queried and the plurality of check asset information to obtain an asset verification result, specifically comprising:

4. The asset verification method as claimed in claim 2 or 3, wherein said querying all the master asset pictures in the verification master data is compared with the asset pictures to be queried to obtain an asset verification result, and specifically comprises:

5. The asset verification method of claim 1, wherein after said determining whether the same scene type asset exists in the asset picture to be queried, the method further comprises:

6. The asset verification method of claim 1, wherein prior to the obtaining the asset picture to be queried and the asset coordinates corresponding to the asset in the asset picture and the asset tag corresponding to the asset in the asset picture, the method further comprises:

acquiring a plurality of asset pictures to be queried;

7. The asset verification method as claimed in claim 6, wherein said detecting the asset in the preliminary processing picture to obtain the asset coordinates and the corresponding tag, comprises:

8. An asset verification device, the asset verification device comprising:

9. A computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the asset verification method according to any one of claims 1 to 7.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs that when executed by the one or more processors cause the one or more processors to implement the asset verification method of any of claims 1 to 7.