CN115878846A

CN115878846A - Cash sorting video clip acquisition method and device

Info

Publication number: CN115878846A
Application number: CN202211514991.6A
Authority: CN
Inventors: 高伟; 施好健; 宋宇诚; 杜媛媛
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-11-30
Filing date: 2022-11-30
Publication date: 2023-03-31

Abstract

The invention provides a cash liquidation video clip acquisition method and device, relates to the technical field of data acquisition, and can be used in the financial field or other technical fields. The method comprises the following steps: acquiring the reported amount and money box information; determining a reference weight interval of the money box loaded with cash according to the first preset corresponding relation, the reported amount and the cash; and determining a target retrieval data set for data query according to the comparison result of the money box weight and the money box reference weight interval, determining a corresponding video clip acquisition mode according to the identification result for identifying the money box serial number, and acquiring the cash sorting video clip corresponding to the money box in the target retrieval data set by using the video clip acquisition mode. The device performs the above method. The method and the device for acquiring the cash sorting video clip provided by the embodiment of the invention can improve the working efficiency of the cash sorting video clip in the cash box.

Description

Cash sorting video clip acquisition method and device

Technical Field

The invention relates to the technical field of data acquisition, in particular to a method and a device for acquiring cash clearing video clips.

Background

At present, before a commercial bank carries out cash sorting through a package, a worker in a region where cash sorting of a cash box is required to align one surface with a name of the cash box with a camera for recording, and records the cash sorting in the whole cash box packaging process to obtain a shot cash sorting video, so that when the sorting amount is different from the actually reported amount, the cash sorting video segment of a related cash box can be quickly searched, responsibility division of the worker is realized, but in actual operation, the worker possibly forgets to do the action of aligning one surface with the name of the cash box with the camera for recording on one hand, and on the other hand, even if the action is done, the problem that identification cannot be identified exists, and time and labor are wasted in subsequent searching of the cash sorting video segment corresponding to the cash box.

Disclosure of Invention

To solve the problems in the prior art, embodiments of the present invention provide a method and an apparatus for acquiring a cash liquidation video clip, which can at least partially solve the problems in the prior art.

On one hand, the invention provides a cash liquidity video clip acquisition method, which comprises the following steps:

acquiring the reported amount and money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type;

determining a reference weight interval of a money box for loading cash according to a first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount;

and determining a target retrieval data set for data query according to the comparison result of the money box weight and the money box reference weight interval, determining a corresponding video clip acquisition mode according to the identification result for identifying the money box serial number, and acquiring the cash sorting video clip corresponding to the money box in the target retrieval data set by using the video clip acquisition mode.

Wherein, the determining a target retrieval data set for data query according to the comparison result between the money box weight and the money box reference weight interval comprises:

if the weight of the money box is determined to be within the reference weight interval of the money box, determining that the target retrieval data set is a first retrieval data set with normal marked weight;

and if the weight of the money box is determined to be outside the reference weight interval of the money box, determining that the target retrieval data set is a second retrieval data set marked with abnormal weight.

Wherein, the determining the corresponding video clip acquisition mode according to the identification result of identifying the money box serial number comprises:

if the identification result is that the number of the money box serial numbers is equal to a preset numerical value and does not comprise letters, determining a video clip acquisition mode to be that the cash sorting video clips in the money box corresponding to the money box serial numbers are determined according to a second preset corresponding relation;

the second preset corresponding relationship comprises a corresponding relationship between a preset money box serial number and a preset cash sorting video clip identifier.

if the identification result is that the number of digits of the cash box serial number is not equal to a preset numerical value and/or includes letters, acquiring the region where the cash box is sorted according to the region name where the cash box is sorted, and acquiring a cash sorting video shot in the region where the cash box is sorted;

carrying out image recognition on the cash sorting video to obtain a frame image marked with the external surface information of the cash box;

and respectively carrying out similarity comparison on each frame of image and a money box image marked with the information of the external surface of the money box, and taking a target video clip corresponding to the target frame of image with the maximum similarity comparison result value as a cash sorting video clip in the money box.

Wherein the money box information further comprises a passive tag number; correspondingly, the method for acquiring the cash liquidation video clip further comprises the following steps:

if the identification result is determined to be that the serial number of the money box is wrong and/or includes letters, acquiring a passive tag number set of the cash sorting area of the money box;

determining a cash liquidity video clip corresponding to the passive tag number according to a third preset corresponding relation; and the third preset corresponding relation comprises a corresponding relation between each preset passive tag number in the passive tag number set and a preset cash sorting video clip identifier.

Wherein, to the cash box serial number discerns, include:

extracting characters from the money box serial number by using a preset character recognition model to obtain a recognition result;

and the preset character recognition model is obtained by labeling and training a machine learning model based on the characteristics of the money box picture.

Before the step of obtaining the reported amount of money and the information of the money box, the method for obtaining the cash liquidity video clip further comprises the following steps:

and acquiring the clearing amount, and executing the steps of acquiring the reported amount and the money box information and the subsequent steps if the clearing amount is determined to be inconsistent with the reported amount.

In one aspect, the present invention provides a cash sorting video clip acquiring apparatus, including:

the first acquisition unit is used for acquiring the reported amount and the money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and a corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type;

the determining unit is used for determining a reference weight interval of the money box for loading cash according to a first preset corresponding relation, the reported amount of money and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount;

and the second acquisition unit is used for determining a target retrieval data set for data query according to the comparison result of the money box weight and the money box reference weight interval, determining a corresponding video clip acquisition mode according to the identification result for identifying the money box serial number, and acquiring the cash sorting video clip corresponding to the money box in the target retrieval data set by using the video clip acquisition mode.

In another aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus, wherein,

the processor and the memory are communicated with each other through the bus;

the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform a method comprising:

acquiring the reported amount and money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and a corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type;

determining a reference weight interval of the money box loaded with cash according to the first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount;

An embodiment of the present invention provides a non-transitory computer-readable storage medium, including:

the non-transitory computer readable storage medium stores computer instructions that cause the computer to perform a method comprising:

The method and the device for acquiring the cash sorting video clip, provided by the embodiment of the invention, are used for acquiring the reported amount and the money case information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type; determining a reference weight interval of the money box loaded with cash according to the first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount; according to the comparison result between the cash box weight and the cash box reference weight interval, a target retrieval data set for data query is determined, a corresponding video clip acquisition mode is determined according to the identification result for identifying the cash box serial number, and the cash sorting video clip corresponding to the cash box is acquired in the target retrieval data set by using the video clip acquisition mode, so that the working efficiency of the cash sorting video clip in the cash box can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:

fig. 1 is a block diagram of a cash liquidation assisting system.

FIG. 2 is a flow chart illustrating a method for using the cash credit assistance system.

Fig. 3 is a schematic flow chart of a cash liquidation video clip acquisition method according to an embodiment of the present invention.

Fig. 4 is a flowchart illustrating a cash liquidation video clip acquisition method according to another embodiment of the present invention.

Fig. 5 is a schematic structural diagram of a cash liquidation video clip acquiring apparatus according to an embodiment of the present invention.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.

Before the cash sorting video clip acquisition method of the embodiment of the invention is realized, a cash sorting auxiliary system composed of related equipment needs to be built, as shown in fig. 1, the cash sorting auxiliary system comprises an auxiliary device 11, a background system 20, an edge computing device 16, a sorting machine 17, a sorting camera 18 and a video memory 19;

wherein, auxiliary device 11 includes weight sensor 12, passive label recognizer 13, sign and shoots camera 14, speaker 15 and MCU 25, and auxiliary device 11 is put on sorter 17.

The weight sensor 12 may include a floor scale for taking the weight of the chest (loaded with cash) and sending the chest weight information to the edge computing device 16.

The passive tag reader 13 is used to identify the passive tag number of the chest (inside the chest) and transmit the passive tag number to the edge computing device 16.

The identification camera 14 is used to capture the zone name and the serial number of the money box where the cash of the money box marked on the outer surface of the money box is sorted, and to send picture information containing the zone name and the serial number of the money box to the edge computing device 16.

The speaker 15 is used for playing a prompt sound when the cash sorting of each cash box is completed.

The MCU 25 is the master control unit of the auxiliary device 11 for communicating with the edge computing apparatus 16.

The back office system 20 comprises a main control unit 21, a storage unit 22, a search unit 23 and an entry unit 24.

The main control unit 21 is responsible for processing binding of the video and each modal characteristic, obtaining binding relationships (i.e., a first preset corresponding relationship, a second preset corresponding relationship, and a third preset corresponding relationship), and overall scheduling and processing of search and display.

The storage unit 22 is used for storing the binding relationship, the picture information, the weight and other information.

The searching unit 23 is used for searching the video recording unit for the staff, and can search according to information such as weight, pictures, characters and the like.

And the recording unit 24 is used for recording the liquidation amount and the like into the system.

And the sorter 17 is used for sorting cash in the cash box.

And the sorting camera 18 is used for shooting the video of the whole cash sorting process.

And a video memory 19 for storing video data shot by the sorting camera 18.

As shown in fig. 2, the method for using the cash sorting aid system is described as follows:

step S101: the staff, the person who divides promptly begins to prepare to divide clearly, opens auxiliary device switch.

Step S102: and placing the money box to be cleared on the auxiliary device, pressing a trigger button, and acquiring a trigger timestamp by the MCU at the moment.

Step S103: the weighbridge, the passive tag recognizer and the identification shooting camera start to respectively acquire picture information of the weight, the passive tag number and the money box.

Step S104: the MCU judges whether the data such as the weight, the passive tag number and the picture data are acquired completely, and if the data are acquired completely, the MCU enters S105; otherwise, S103 is performed.

Step S105: after the auxiliary device acquires the weight, the passive tag number and the picture data, a finishing instruction is sent to the loudspeaker and played through the loudspeaker, so that workers can know the finishing instruction conveniently. Meanwhile, the MCU sends information such as weight, passive tag numbers, picture data and trigger time stamps to the edge computing equipment.

Step S106: after the edge computing device obtains the multi-mode data, the image information is processed firstly, and character extraction is carried out by utilizing a character recognition model. And then transmits information such as a time stamp, weight, passive tag number, picture data, etc. to the main control unit.

Step S107: after the main control unit obtains the multi-mode data sent by the edge computing device, the time stamp and the amount information when the input unit inputs the liquidation amount are received, the multi-mode data sent by the edge computing device and the data of the input unit are combined and bound, and then the data are stored in the storage unit, wherein the information such as weight, passive tag number, picture data and the like are used as video recording indexes of the liquidation operation of the money box. Wherein the start time and the end time are used to intercept the corresponding segment from the video memory.

Fig. 3 is a schematic flow chart of a method for acquiring a cash score video clip according to an embodiment of the present invention, and as shown in fig. 3, the method for acquiring a cash score video clip according to an embodiment of the present invention includes:

step S1: acquiring the reported amount and money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; wherein the cash in the cash box is the same currency value of the same currency type.

Step S2: determining a reference weight interval of a money box for loading cash according to a first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount.

And step S3: and determining a target retrieval data set for data query according to the comparison result of the cash box weight and the cash box reference weight interval, determining a corresponding video clip acquisition mode according to the identification result of identifying the cash box serial number, and acquiring cash sorting video clips corresponding to the cash box in the target retrieval data set by using the video clip acquisition mode.

In the step S1, the device acquires the reported amount of money and money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and a corresponding serial number of the money box; wherein the cash in the cash box is the same currency value of the same currency type. The apparatus may be a computer device that performs the method, and may include, for example, an edge computing device. It should be noted that the embodiments of the present invention relate to the acquisition and analysis of data being authorized by the user. The reported amount can be understood as the cash amount reported by the customer cash credit, and the cash is the same currency value of the same currency type, which is described as follows:

if the currency type is paper currency and the currency value is 1 yuan, then the cash in the cash box is 1 yuan paper currency; if the currency type is a banknote and the currency value is 100 dollars, then the cash in the cash box is 100 dollar banknotes; if the currency type is coin and the currency value is 1 dollar, then the cash in the cash box is 1 dollar coins.

The region name of the cash sorting place and the corresponding cash box serial number are marked on the outer surface of the cash box, so that the cash can be shot by the mark shooting camera.

Since there can be a plurality of cash sorting areas for respectively sorting cash, and each cash sorting area has a plurality of corresponding cash box serial numbers, it is necessary to uniquely determine a certain cash box in a certain cash sorting area according to the area name of the cash sorting area and the cash box serial number corresponding to the area name of the cash sorting area.

Before the step of obtaining the reported amount and the money box information, the method for obtaining the cash sorting video clip further comprises the following steps:

and acquiring the clearing amount, and executing the steps of acquiring the reported amount and the money box information and the subsequent steps if the clearing amount is determined to be inconsistent with the reported amount. The counting amount refers to the actual cash amount counted by the bank, and it can be understood that if the counting amount is consistent with the reported amount, the subsequent steps of the method do not need to be executed.

And if the clearing amount is inconsistent with the reported amount, executing the steps of obtaining the reported amount and the money box information and the subsequent steps.

In the step S2, the apparatus determines a reference weight interval of the cash box for loading cash according to the first preset corresponding relationship, the reported amount of money and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount. The first preset correspondence is exemplified as follows:

if the number of the paper money is 1 yuan, the preset weight interval corresponding to the preset reported amount of 10 ten thousand yuan is 10 jin to 12 jin; if the paper money is 100 yuan, the preset weight interval corresponding to the preset reported amount of 10 ten thousand yuan is 7 jin to 9 jin; if the coin is 1 yuan, the preset weight interval corresponding to the preset reported amount of 10 ten thousand yuan is 700 jin to 800 jin.

If the reported amount is 5 ten thousand and the cash is 1 yuan of paper money, the reference weight interval of the cash box is determined to be 5 jin to 6 jin (the weight of the cash box is not considered at all).

In the step S3, the apparatus determines a target retrieval data set for performing data query according to a comparison result between the cash box weight and the cash box reference weight interval, determines a corresponding video clip acquisition mode according to an identification result for identifying the cash box serial number, and acquires the cash sorting video clip corresponding to the cash box in the target retrieval data set by using the video clip acquisition mode. The determining a target retrieval data set for data query according to the comparison result between the money box weight and the money box reference weight interval comprises the following steps:

if the weight of the money box is determined to be within the reference weight interval of the money box, determining that the target retrieval data set is a first retrieval data set with normal marked weight; the first search data set is a data set with normal weight.

And if the weight of the money box is determined to be outside the reference weight interval of the money box, determining that the target retrieval data set is a second retrieval data set marked with abnormal weight. The second retrieval data set is a data set with abnormal weight, the database is divided into a first retrieval data set and a second retrieval data set, and the first retrieval data set or the second retrieval data set can be used for subsequent data query (namely, the video clip acquisition mode is utilized and the cash sorting video clip corresponding to the money box is acquired in the target retrieval data set), so that the data volume needing to be traversed during data query is reduced, and the data query efficiency is improved.

The determining of the corresponding video clip acquisition mode according to the identification result of identifying the money box serial number comprises the following steps:

if the identification result is that the number of the money box serial numbers is equal to a preset numerical value and does not comprise letters, determining a video clip acquisition mode to be that the cash sorting video clips in the money box corresponding to the money box serial numbers are determined according to a second preset corresponding relation; the preset value can be set autonomously according to the actual situation, and can be selected as a 7-bit value, it should be noted that the correct money case serial number is a numeric character string consisting of 7 digits, such as 1020204, and if the money case label is worn and worn for a long time, data loss, such as remaining 6 bits, can be caused; or some portion of a certain numerical value is missing and is misidentified as a letter, such as the number "8", and is easily misidentified as the letter "o" if its upper or lower half is worn away.

Therefore, if the cash box serial number is a numeric character string consisting of 7 digits, the cash box serial number can be considered to be correct, and the cash sorting video clip in the cash box can be directly obtained by utilizing the second preset corresponding relation.

And the second preset corresponding relation comprises a corresponding relation between a preset money box serial number and a preset cash sorting video clip identifier. The second preset correspondence is exemplified as follows:

the preset money box serial number 1020204 corresponds to the preset cash sorting video clip identifier C1020204, that is, the C1020204 records the playing start time and the playing end time of the video clip, and it can be understood that the video content between the playing start time and the playing end time is a video image of the whole cash sorting process of shooting the money box serial number 1020204.

Similarly, the preset money box serial number 1020205 corresponds to the preset cash liquidation video clip identifier C1020205.

if the identification result is that the number of digits of the cash box serial number is not equal to a preset numerical value and/or includes letters, acquiring the region where the cash box is sorted according to the region name where the cash box is sorted, and acquiring a cash sorting video shot in the region where the cash box is sorted; referring to the above description, if the serial number of the money box is not a numeric character string consisting of 7 digits, it indicates that the cash sorting video segment in the corresponding money box cannot be accurately acquired through the serial number of the money box. Because the cash sorting areas of the money boxes respectively shoot the corresponding cash sorting videos (which are composed of the cash sorting video segments in sequence), the cash sorting videos shot in the areas can be uniquely determined by the names of the areas where the money boxes are sorted.

Carrying out image recognition on the cash sorting video to obtain a frame image marked with the external surface information of the cash box; the cash sorting video can be subjected to image recognition by adopting the existing mature technology to obtain a frame image marked with the external surface information of the money box, wherein the external surface information of the money box comprises the area name of the cash sorting place of the money box and the corresponding serial number of the money box. Each frame of image respectively corresponds to the area name of the cash sorting place of one cash box and the corresponding serial number of the cash box.

And respectively comparing the similarity of each frame of image with the money box image marked with the external surface information of the money box, and taking the target video clip corresponding to the target frame of image with the maximum similarity comparison result value as the cash sorting video clip in the money box. The cash box image is an image of a cash box of which the cash sorting video clip is to be acquired. The maximum value of the similarity comparison result indicates that the image content of the frame image is more similar to that of the money box image.

If the frame image corresponding to the money box 1020204 is the target frame image, the target video clip is a video clip between the play start time and the play end time of the money box, and thus the cash liquidity video clip in the money box is obtained.

The cash box information further comprises a passive tag number; correspondingly, the cash liquidity video clip acquisition method further comprises the following steps:

if the identification result is determined to be that the serial number of the money box is wrong and/or includes letters, acquiring a passive tag number set of the cash sorting area of the money box; since each cash box cash sorting area can self-define the passive tag number, the passive tag number needs to correspond to each cash box cash sorting area number. For example, the set of passive tag numbers of the cash sorting area a of the cash box is 0001-0100, and the set of passive tag numbers of the cash sorting area B of the cash box is 0001-0095, wherein the passive tag numbers of 0001-0100 in a and 0001-0095 in B are not the same as the corresponding passive tag numbers of the cash box, and the following description will exemplify the set of passive tag numbers of a of 0001-0100.

Determining a cash sorting video clip corresponding to the passive tag number according to a third preset corresponding relation; the third preset corresponding relationship comprises a corresponding relationship between each preset passive tag number in the passive tag number set and a preset cash sorting video clip identifier. The third preset correspondence is exemplified as follows:

the preset passive tag number 0001 corresponds to the preset cash sorting video segment C0001, the preset passive tag number 0002 corresponds to the preset cash sorting video segment C0002, and so on. If the passive tag number is 0080, determining that the cash sorting video fragment corresponding to the passive tag number 0080 is C0080 according to the corresponding relation between each preset passive tag number in the passive tag number set 0001-0100 and the preset cash sorting video fragment identification.

Identifying the money box serial number, including:

extracting characters from the money box serial number by using a preset character recognition model to obtain a recognition result; the serial number of the money box may be input to the preset character recognition model, and an output result of the preset character recognition model may be used as a character extraction recognition result, for example, 1020204.

And the preset character recognition model is obtained by labeling and training a machine learning model based on the characteristics of the money box picture. The method for training the machine learning model by using the sample data can be selected as the conventional model training method, and the machine learning model can comprise a neural network, a random forest and the like without specific limitation.

As shown in fig. 4, the cash liquidation video clip acquiring method provided by the embodiment of the invention is briefly described as follows:

step S201: and when the liquidation amount is determined to be inconsistent with the reported amount, initiating a task of searching the video clip, and opening a search interface of the search unit.

Step S202: acquiring the reported amount and money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place and the corresponding serial number of the money box; wherein the cash in the cash box is of the same currency value of the same currency type.

Step S203: if the weight of the money box is within the reference weight interval of the money box, the weight of the money box is normal; and if the weight of the money box is outside the reference weight interval of the money box, the abnormal weight of the money box is indicated.

Step S204: and determining the target retrieval data set as a first retrieval data set with normal mark weight.

Step S205: and identifying the serial number of the money box.

Step S206: if the identification result is that the number of digits of the money box serial number is equal to the preset numerical value and does not comprise letters, the money box serial number is normal; if the identification result is that the number of the money box serial number is not equal to the preset numerical value and/or includes letters, the money box serial number is abnormal.

Step S207: and determining the cash sorting video clip in the money box corresponding to the money box serial number according to the second preset corresponding relation.

Step S208: and determining the target retrieval data set as a second retrieval data set marked with weight abnormity.

Step S209: and acquiring the region of the cash sorting of the cash box according to the region name of the cash sorting of the cash box, and acquiring the cash sorting video shot in the region of the cash sorting of the cash box.

Step S210: and carrying out image recognition on the cash sorting video to obtain a frame image containing information marked with the external surface of the cash box.

Step S211: and respectively carrying out similarity comparison on each frame of image and a money box image marked with the information of the external surface of the money box, and taking a target video clip corresponding to the target frame of image with the maximum similarity comparison result value as a cash sorting video clip in the money box.

Step S212: and acquiring a passive tag number set of the cash sorting area of the cash box.

Step S213: and determining the cash sorting video clip corresponding to the passive tag number according to the third preset corresponding relation.

Step S214: a cash score video clip in the cash box is obtained.

The cash sorting video clip acquisition method provided by the embodiment of the invention comprehensively applies multi-mode technologies such as a weighbridge, a passive Internet of things label and machine vision, solves the problem of compliance of sorting personnel during sorting, can quickly search a corresponding video segment when an abnormality is found, and improves the working efficiency. The device is arranged on the sorting platform, the size of the device can be used for placing the money box, when the money box is placed for a certain time, the multi-mode characteristics such as the weight of the package to be sorted, the passive tag number and the character mark on the money box can be obtained, and the efficiency and the accuracy of video fragment retrieval are improved through the associated retrieval of the multi-mode characteristics.

The cash sorting video clip acquisition method provided by the embodiment of the invention acquires the reported amount and the money case information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type; determining a reference weight interval of the money box loaded with cash according to the first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount; according to the comparison result between the cash box weight and the cash box reference weight interval, a target retrieval data set for data query is determined, a corresponding video clip acquisition mode is determined according to the identification result for identifying the cash box serial number, and the cash sorting video clip corresponding to the cash box is acquired in the target retrieval data set by using the video clip acquisition mode, so that the working efficiency of the cash sorting video clip in the cash box can be improved.

Further, the determining a target retrieval data set for data query according to the comparison result between the money box weight and the money box reference weight interval includes:

if the weight of the money box is determined to be within the reference weight interval of the money box, determining that the target retrieval data set is a first retrieval data set with normal marked weight; reference is made to the above description and no further description is given.

And if the weight of the money box is determined to be outside the reference weight interval of the money box, determining that the target retrieval data set is a second retrieval data set marked with abnormal weight. Reference is made to the above description and no further description is given.

The cash liquidation video clip acquisition method provided by the embodiment of the invention can improve the data query efficiency.

Further, the determining a corresponding video clip acquisition mode according to the identification result of identifying the money box serial number includes:

if the identification result is that the number of the money box serial numbers is equal to a preset numerical value and does not comprise letters, determining a video clip acquisition mode to be that the cash sorting video clips in the money box corresponding to the money box serial numbers are determined according to a second preset corresponding relation; reference is made to the above description and no further description is given.

And the second preset corresponding relation comprises a corresponding relation between a preset money box serial number and a preset cash sorting video clip identifier. Reference is made to the above description and no further description is made.

The method for acquiring the cash sorting video clip provided by the embodiment of the invention can be used for more rapidly acquiring the cash sorting video clip in the cash box. Reference is made to the above description and no further description is made.

if the identification result is that the number of digits of the cash box serial number is not equal to a preset numerical value and/or includes letters, acquiring the region where the cash box is sorted according to the region name where the cash box is sorted, and acquiring a cash sorting video shot in the region where the cash box is sorted; reference is made to the above description and no further description is made.

Carrying out image recognition on the cash sorting video to obtain a frame image marked with the external surface information of the cash box; reference is made to the above description and no further description is given.

And respectively carrying out similarity comparison on each frame of image and a money box image marked with the information of the external surface of the money box, and taking a target video clip corresponding to the target frame of image with the maximum similarity comparison result value as a cash sorting video clip in the money box. Reference is made to the above description and no further description is given.

The method for acquiring the cash sorting video clip provided by the embodiment of the invention can further improve the working efficiency of the cash sorting video clip in the cash box under the condition that the serial number of the cash box cannot be used.

Further, the money box information also includes a passive tag number; correspondingly, the cash liquidity video clip acquisition method further comprises the following steps:

if the identification result is determined to be that the serial number of the money box is wrong and/or includes letters, acquiring a passive tag number set of the cash sorting area of the money box; reference is made to the above description and no further description is made.

Determining a cash sorting video clip corresponding to the passive tag number according to a third preset corresponding relation; and the third preset corresponding relation comprises a corresponding relation between each preset passive tag number in the passive tag number set and a preset cash sorting video clip identifier. Reference is made to the above description and no further description is made.

Further, identifying the serial number of the money box comprises:

extracting characters from the money box serial number by using a preset character recognition model to obtain a recognition result; reference is made to the above description and no further description is made.

And the preset character recognition model is obtained by labeling and training a machine learning model based on the characteristics of the money box picture. Reference is made to the above description and no further description is given.

The cash liquidation video clip acquisition method provided by the embodiment of the invention can improve the character recognition efficiency.

Further, before the step of acquiring the reported amount and the money box information, the method for acquiring the cash liquidation video clip further includes:

and acquiring the clearing amount, and if the clearing amount is determined to be inconsistent with the reported amount, executing the steps of acquiring the reported amount and the money box information and the subsequent steps. Reference is made to the above description and no further description is made.

According to the cash liquidation video clip acquisition method provided by the embodiment of the invention, the technical scheme does not need to be continuously executed under the condition that the liquidation amount is consistent with the reported amount, and further data processing resources are saved.

It should be noted that the method for acquiring the cash liquidity video segments provided by the embodiment of the present invention may be used in the financial field, and may also be used in any technical field other than the financial field.

Fig. 5 is a schematic structural diagram of a cash score video segment acquiring apparatus according to an embodiment of the present invention, and as shown in fig. 5, the cash score video segment acquiring apparatus according to the embodiment of the present invention includes a first acquiring unit 501, a determining unit 502, and a second acquiring unit 503, where:

the first obtaining unit 501 is configured to obtain the reported amount and the money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type; the determining unit 502 is configured to determine a reference weight interval of the money box for loading cash according to a first preset corresponding relationship, the reported amount of money, and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount; the second obtaining unit 503 is configured to determine a target retrieval dataset for performing data query according to a comparison result between the money box weight and the money box reference weight interval, determine a corresponding video clip obtaining manner according to an identification result for identifying the money box serial number, and obtain a cash sorting video clip corresponding to the money box in the target retrieval dataset by using the video clip obtaining manner.

Specifically, a first obtaining unit 501 in the device is configured to obtain the reported amount and the money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and a corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type; the determining unit 502 is configured to determine a reference weight interval of the money box loaded with cash according to the first preset corresponding relationship, the reported amount of money, and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount; the second obtaining unit 503 is configured to determine a target retrieval dataset for performing data query according to a comparison result between the money box weight and the money box reference weight interval, determine a corresponding video clip obtaining manner according to an identification result for identifying the money box serial number, and obtain a cash sorting video clip corresponding to the money box in the target retrieval dataset by using the video clip obtaining manner.

The cash sorting video clip acquisition device provided by the embodiment of the invention acquires the reported amount and the money case information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type; determining a reference weight interval of the money box loaded with cash according to the first preset corresponding relation, the reported amount and the cash; the first preset corresponding relation comprises a corresponding relation between a preset weight interval of a money box loaded with a preset cash type and a preset reported amount; according to the comparison result between the cash box weight and the cash box reference weight interval, a target retrieval data set for data query is determined, a corresponding video clip acquisition mode is determined according to the identification result for identifying the cash box serial number, and the cash sorting video clip corresponding to the cash box is acquired in the target retrieval data set by using the video clip acquisition mode, so that the working efficiency of the cash sorting video clip in the cash box can be improved.

Further, the determining unit 502 is specifically configured to:

and if the weight of the money box is determined to be out of the reference weight interval of the money box, determining that the target retrieval data set is a second retrieval data set marked with abnormal weight.

The cash counting video clip acquisition device provided by the embodiment of the invention can improve the data query efficiency.

Further, the second obtaining unit 503 is specifically configured to:

and the second preset corresponding relation comprises a corresponding relation between a preset money box serial number and a preset cash sorting video clip identifier.

The cash sorting video clip acquisition device provided by the embodiment of the invention can more quickly acquire the cash sorting video clip in the cash box.

Further, the second obtaining unit 503 is specifically configured to:

The cash sorting video clip acquisition device provided by the embodiment of the invention can further improve the working efficiency of the cash sorting video clip in the cash box under the condition that the serial number of the cash box cannot be used.

Further, the money box information also comprises a passive tag number; correspondingly, the cash liquidation video clip acquisition device is also used for:

Further, the second obtaining unit 503 is specifically configured to:

The cash sorting video clip acquisition device provided by the embodiment of the invention can improve the character recognition efficiency.

Further, before the step of obtaining the reported amount of money and the money box information, the cash liquidity video clip obtaining device is further configured to:

The cash liquidation video clip acquisition device provided by the embodiment of the invention does not need to continuously execute the technical scheme under the condition that the liquidation amount is consistent with the reported amount, thereby saving data processing resources.

The embodiment of the apparatus for acquiring cash sorting video segments according to the embodiment of the present invention may be specifically configured to execute the processing flows of the above method embodiments, and the functions of the apparatus are not described herein again, and reference may be made to the detailed description of the above method embodiments.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device includes: a processor (processor) 601, a memory (memory) 602, and a bus 603;

the processor 601 and the memory 602 complete mutual communication through a bus 603;

the processor 601 is configured to call program instructions in the memory 602 to perform the methods provided by the above-mentioned method embodiments, for example, including:

The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising:

The present embodiment provides a computer-readable storage medium, which stores a computer program, where the computer program causes the computer to execute the method provided by the above method embodiments, for example, the method includes:

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and should not be used to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A cash liquidation video clip acquisition method is characterized by comprising the following steps:

2. The cash liquidation video clip acquisition method of claim 1, wherein the determining a target retrieval data set for data query according to the comparison result between the cash box weight and the cash box reference weight interval comprises:

3. The cash sorting video segment acquisition method according to claim 1, wherein the determining of the corresponding video segment acquisition mode according to the recognition result of the money box serial number includes:

if the identification result is that the number of the money box serial numbers is equal to a preset numerical value and does not comprise letters, determining that the video clip acquisition mode is to determine the cash sorting video clips in the money box corresponding to the money box serial numbers according to a second preset corresponding relation;

4. The method for acquiring cash sorting video segments according to claim 1, wherein the determining of the corresponding video segment acquisition mode according to the identification result of the serial number of the cash box comprises:

5. The cash sorting video segment acquisition method according to claim 4, wherein the cash box information further includes a passive tag number; correspondingly, the cash liquidity video clip acquisition method further comprises the following steps:

if the identification result is determined to be that the number of digits of the cash box serial number is wrong and/or letters are included, acquiring a passive tag number set of the cash sorting area of the cash box;

determining a cash sorting video clip corresponding to the passive tag number according to a third preset corresponding relation; and the third preset corresponding relation comprises a corresponding relation between each preset passive tag number in the passive tag number set and a preset cash sorting video clip identifier.

6. The method for acquiring cash sorting video segments according to any one of claims 1 to 5, wherein identifying the cash box serial number comprises:

7. The method for acquiring cash credit video clips according to any one of claims 1 to 5, wherein before the step of acquiring the reported amount of money and the cash box information, the method for acquiring cash credit video clips further comprises:

and acquiring the clearing amount, and if the clearing amount is determined to be inconsistent with the reported amount, executing the steps of acquiring the reported amount and the money box information and the subsequent steps.

8. A cash sorting video clip acquisition apparatus, comprising:

the first acquisition unit is used for acquiring the reported amount and the money box information; the money box information comprises the weight of the money box, the name of a region where the money box is marked on the outer surface of the money box and the cash sorting place, and the corresponding serial number of the money box; the cash in the cash box is the same currency value of the same currency type;

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.